Commit ·
67d2d5e
0
Parent(s):
Duplicate from GODELEV/Rose-1.5-Mini
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +35 -0
- README.md +31 -0
- config.json +45 -0
- configuration_rose_x1_5.py +83 -0
- generation_config.json +4 -0
- logs/log_100000.jsonl +103 -0
- logs/log_101000.jsonl +154 -0
- logs/log_102000.jsonl +205 -0
- logs/log_103000.jsonl +256 -0
- logs/log_10400.jsonl +242 -0
- logs/log_104000.jsonl +52 -0
- logs/log_105000.jsonl +103 -0
- logs/log_106000.jsonl +154 -0
- logs/log_107000.jsonl +205 -0
- logs/log_108000.jsonl +256 -0
- logs/log_109000.jsonl +52 -0
- logs/log_11000.jsonl +32 -0
- logs/log_110000.jsonl +103 -0
- logs/log_111000.jsonl +154 -0
- logs/log_112000.jsonl +205 -0
- logs/log_113000.jsonl +256 -0
- logs/log_114000.jsonl +52 -0
- logs/log_115000.jsonl +103 -0
- logs/log_116000.jsonl +154 -0
- logs/log_117000.jsonl +205 -0
- logs/log_118000.jsonl +256 -0
- logs/log_119000.jsonl +52 -0
- logs/log_1200.jsonl +65 -0
- logs/log_12000.jsonl +83 -0
- logs/log_120000.jsonl +103 -0
- logs/log_121000.jsonl +154 -0
- logs/log_122000.jsonl +205 -0
- logs/log_123000.jsonl +256 -0
- logs/log_124000.jsonl +52 -0
- logs/log_125000.jsonl +103 -0
- logs/log_126000.jsonl +154 -0
- logs/log_127000.jsonl +205 -0
- logs/log_128000.jsonl +256 -0
- logs/log_129000.jsonl +307 -0
- logs/log_13000.jsonl +134 -0
- logs/log_130000.jsonl +52 -0
- logs/log_131000.jsonl +103 -0
- logs/log_132000.jsonl +154 -0
- logs/log_133000.jsonl +205 -0
- logs/log_134000.jsonl +256 -0
- logs/log_135000.jsonl +52 -0
- logs/log_136000.jsonl +103 -0
- logs/log_137000.jsonl +154 -0
- logs/log_138000.jsonl +205 -0
- logs/log_139000.jsonl +256 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
tags:
|
| 4 |
+
- causal-lm
|
| 5 |
+
- gqa
|
| 6 |
+
- qk-norm
|
| 7 |
+
- rope
|
| 8 |
+
- swiglu
|
| 9 |
+
- refresh-gate
|
| 10 |
+
- rose-x1
|
| 11 |
+
license: apache-2.0
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Rose-1.5-Mini
|
| 15 |
+
|
| 16 |
+
Rose X1.5 SLM (98.6M params).
|
| 17 |
+
|
| 18 |
+
## Architecture
|
| 19 |
+
| Property | Value |
|
| 20 |
+
|---|---|
|
| 21 |
+
| Layers | 22 |
|
| 22 |
+
| Hidden | 576 |
|
| 23 |
+
| Heads | 9 (kv=3) |
|
| 24 |
+
| QK Norm | True |
|
| 25 |
+
| Refresh Gate | [6, 13] |
|
| 26 |
+
| Params | 98.612M |
|
| 27 |
+
|
| 28 |
+
## Training
|
| 29 |
+
- Tokens: 160,392,960,000
|
| 30 |
+
- Val PPL: 5.29
|
| 31 |
+
- Optimizer: muon_adamw
|
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RoseX15ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"model_type": "rose_x1_5",
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "configuration_rose_x1_5.RoseX15Config",
|
| 8 |
+
"AutoModelForCausalLM": "modeling_rose_x1_5.RoseX15ForCausalLM"
|
| 9 |
+
},
|
| 10 |
+
"vocab_size": 32768,
|
| 11 |
+
"hidden_size": 576,
|
| 12 |
+
"intermediate_size": 1532,
|
| 13 |
+
"num_hidden_layers": 22,
|
| 14 |
+
"num_attention_heads": 9,
|
| 15 |
+
"num_key_value_heads": 3,
|
| 16 |
+
"head_dim": 64,
|
| 17 |
+
"max_position_embeddings": 4096,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"attention_bias": false,
|
| 21 |
+
"mlp_bias": false,
|
| 22 |
+
"attention_dropout": 0.0,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"rope_theta": 100000.0,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"use_qk_norm": true,
|
| 27 |
+
"use_xsa": true,
|
| 28 |
+
"refresh_gate_enabled": true,
|
| 29 |
+
"refresh_gate_inject_layers": [
|
| 30 |
+
6,
|
| 31 |
+
13
|
| 32 |
+
],
|
| 33 |
+
"refresh_gate_kernel_size": 9,
|
| 34 |
+
"mup_enabled": false,
|
| 35 |
+
"mup_base_hidden_size": null,
|
| 36 |
+
"mup_width_mult": null,
|
| 37 |
+
"bos_token_id": 2,
|
| 38 |
+
"eos_token_id": 3,
|
| 39 |
+
"pad_token_id": 0,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.40.0",
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"pretraining_tp": 1,
|
| 44 |
+
"initializer_range": 0.02
|
| 45 |
+
}
|
configuration_rose_x1_5.py
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Rose X1.5 model configuration."""
|
| 2 |
+
from transformers import PretrainedConfig
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
class RoseX15Config(PretrainedConfig):
|
| 6 |
+
"""Configuration for the Rose X1.5 architecture.
|
| 7 |
+
|
| 8 |
+
Rose X1.5 extends the T-X4 family with:
|
| 9 |
+
- Grouped-Query Attention (GQA) with per-head QK-Norm
|
| 10 |
+
- Half-split RoPE
|
| 11 |
+
- SwiGLU MLP
|
| 12 |
+
- RMSNorm
|
| 13 |
+
- Exclusive Self Attention (XSA)
|
| 14 |
+
- Refresh Gate (gated re-injection of original token embedding)
|
| 15 |
+
- Tied word embeddings
|
| 16 |
+
"""
|
| 17 |
+
|
| 18 |
+
model_type = "rose_x1_5"
|
| 19 |
+
|
| 20 |
+
def __init__(
|
| 21 |
+
self,
|
| 22 |
+
vocab_size=32768,
|
| 23 |
+
hidden_size=576,
|
| 24 |
+
num_hidden_layers=22,
|
| 25 |
+
num_attention_heads=9,
|
| 26 |
+
num_key_value_heads=3,
|
| 27 |
+
head_dim=64,
|
| 28 |
+
intermediate_size=1532,
|
| 29 |
+
max_position_embeddings=4096,
|
| 30 |
+
hidden_act="silu",
|
| 31 |
+
rms_norm_eps=1e-6,
|
| 32 |
+
attention_bias=False,
|
| 33 |
+
mlp_bias=False,
|
| 34 |
+
attention_dropout=0.0,
|
| 35 |
+
rope_theta=100000.0,
|
| 36 |
+
rope_scaling=None,
|
| 37 |
+
tie_word_embeddings=True,
|
| 38 |
+
# QK Norm
|
| 39 |
+
use_qk_norm=True,
|
| 40 |
+
# XSA (Exclusive Self Attention)
|
| 41 |
+
use_xsa=True,
|
| 42 |
+
# Refresh Gate
|
| 43 |
+
refresh_gate_enabled=True,
|
| 44 |
+
refresh_gate_inject_layers=None,
|
| 45 |
+
refresh_gate_kernel_size=9,
|
| 46 |
+
# muP (recorded for reproducibility; does not affect forward pass)
|
| 47 |
+
mup_enabled=False,
|
| 48 |
+
mup_base_hidden_size=None,
|
| 49 |
+
mup_width_mult=None,
|
| 50 |
+
**kwargs,
|
| 51 |
+
):
|
| 52 |
+
self.vocab_size = vocab_size
|
| 53 |
+
self.hidden_size = hidden_size
|
| 54 |
+
self.num_hidden_layers = num_hidden_layers
|
| 55 |
+
self.num_attention_heads = num_attention_heads
|
| 56 |
+
self.num_key_value_heads = num_key_value_heads
|
| 57 |
+
self.head_dim = head_dim
|
| 58 |
+
self.intermediate_size = intermediate_size
|
| 59 |
+
self.max_position_embeddings = max_position_embeddings
|
| 60 |
+
self.hidden_act = hidden_act
|
| 61 |
+
self.rms_norm_eps = rms_norm_eps
|
| 62 |
+
self.attention_bias = attention_bias
|
| 63 |
+
self.mlp_bias = mlp_bias
|
| 64 |
+
self.attention_dropout = attention_dropout
|
| 65 |
+
self.rope_theta = rope_theta
|
| 66 |
+
self.rope_scaling = rope_scaling
|
| 67 |
+
# QK Norm
|
| 68 |
+
self.use_qk_norm = use_qk_norm
|
| 69 |
+
# XSA
|
| 70 |
+
self.use_xsa = use_xsa
|
| 71 |
+
# Refresh Gate
|
| 72 |
+
self.refresh_gate_enabled = refresh_gate_enabled
|
| 73 |
+
self.refresh_gate_inject_layers = (
|
| 74 |
+
list(refresh_gate_inject_layers)
|
| 75 |
+
if refresh_gate_inject_layers is not None
|
| 76 |
+
else [4, 9]
|
| 77 |
+
)
|
| 78 |
+
self.refresh_gate_kernel_size = refresh_gate_kernel_size
|
| 79 |
+
# muP (metadata only)
|
| 80 |
+
self.mup_enabled = mup_enabled
|
| 81 |
+
self.mup_base_hidden_size = mup_base_hidden_size
|
| 82 |
+
self.mup_width_mult = mup_width_mult
|
| 83 |
+
super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)
|
generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"eos_token_id": 3
|
| 4 |
+
}
|
logs/log_100000.jsonl
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 98000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-03T10:06:49.525238"}
|
| 2 |
+
{"step": 98020, "epoch": 0.623, "loss": 1.74234, "ppl": 5.711, "lr": 0.003, "grad": 0.1615, "tokens": 102756326400, "tok_s": 158831.9}
|
| 3 |
+
{"step": 98040, "epoch": 0.623, "loss": 1.74419, "ppl": 5.721, "lr": 0.003, "grad": 0.1568, "tokens": 102777292800, "tok_s": 159307.9}
|
| 4 |
+
{"step": 98060, "epoch": 0.623, "loss": 1.71837, "ppl": 5.575, "lr": 0.003, "grad": 0.24, "tokens": 102798259200, "tok_s": 159258.6}
|
| 5 |
+
{"step": 98080, "epoch": 0.623, "loss": 1.61457, "ppl": 5.026, "lr": 0.003, "grad": 0.2472, "tokens": 102819225600, "tok_s": 159123.4}
|
| 6 |
+
{"step": 98100, "epoch": 0.623, "loss": 1.76972, "ppl": 5.869, "lr": 0.003, "grad": 0.2938, "tokens": 102840192000, "tok_s": 158311.3}
|
| 7 |
+
{"step": 98120, "epoch": 0.623, "loss": 1.7321, "ppl": 5.652, "lr": 0.003, "grad": 0.2529, "tokens": 102861158400, "tok_s": 158956.1}
|
| 8 |
+
{"step": 98140, "epoch": 0.624, "loss": 1.74611, "ppl": 5.732, "lr": 0.003, "grad": 0.168, "tokens": 102882124800, "tok_s": 158236.7}
|
| 9 |
+
{"step": 98160, "epoch": 0.624, "loss": 1.67902, "ppl": 5.36, "lr": 0.003, "grad": 0.2069, "tokens": 102903091200, "tok_s": 158659.4}
|
| 10 |
+
{"step": 98180, "epoch": 0.624, "loss": 1.63289, "ppl": 5.119, "lr": 0.003, "grad": 0.1619, "tokens": 102924057600, "tok_s": 158808.6}
|
| 11 |
+
{"step": 98200, "epoch": 0.624, "loss": 1.59509, "ppl": 4.929, "lr": 0.003, "grad": 0.109, "tokens": 102945024000, "tok_s": 158550.0}
|
| 12 |
+
{"step": 98220, "epoch": 0.624, "loss": 1.78202, "ppl": 5.942, "lr": 0.003, "grad": 0.1746, "tokens": 102965990400, "tok_s": 158582.9}
|
| 13 |
+
{"step": 98240, "epoch": 0.624, "loss": 1.70405, "ppl": 5.496, "lr": 0.003, "grad": 0.0643, "tokens": 102986956800, "tok_s": 158596.8}
|
| 14 |
+
{"step": 98260, "epoch": 0.624, "loss": 1.76348, "ppl": 5.833, "lr": 0.003, "grad": 0.0995, "tokens": 103007923200, "tok_s": 158424.4}
|
| 15 |
+
{"step": 98280, "epoch": 0.624, "loss": 1.71265, "ppl": 5.544, "lr": 0.003, "grad": 0.139, "tokens": 103028889600, "tok_s": 158760.6}
|
| 16 |
+
{"step": 98300, "epoch": 0.625, "loss": 1.75718, "ppl": 5.796, "lr": 0.003, "grad": 0.225, "tokens": 103049856000, "tok_s": 158437.8}
|
| 17 |
+
{"step": 98320, "epoch": 0.625, "loss": 1.76294, "ppl": 5.83, "lr": 0.003, "grad": 0.1228, "tokens": 103070822400, "tok_s": 158716.7}
|
| 18 |
+
{"step": 98340, "epoch": 0.625, "loss": 1.72793, "ppl": 5.629, "lr": 0.003, "grad": 0.2093, "tokens": 103091788800, "tok_s": 158619.1}
|
| 19 |
+
{"step": 98360, "epoch": 0.625, "loss": 1.77321, "ppl": 5.89, "lr": 0.003, "grad": 0.1054, "tokens": 103112755200, "tok_s": 158390.0}
|
| 20 |
+
{"step": 98380, "epoch": 0.625, "loss": 1.68316, "ppl": 5.383, "lr": 0.003, "grad": 0.1909, "tokens": 103133721600, "tok_s": 158677.2}
|
| 21 |
+
{"step": 98400, "epoch": 0.625, "loss": 1.78436, "ppl": 5.956, "lr": 0.003, "grad": 0.1462, "tokens": 103154688000, "tok_s": 158637.0}
|
| 22 |
+
{"step": 98420, "epoch": 0.625, "loss": 1.76305, "ppl": 5.83, "lr": 0.003, "grad": 0.3072, "tokens": 103175654400, "tok_s": 158327.8}
|
| 23 |
+
{"step": 98440, "epoch": 0.625, "loss": 1.67234, "ppl": 5.325, "lr": 0.003, "grad": 0.0597, "tokens": 103196620800, "tok_s": 158745.4}
|
| 24 |
+
{"step": 98460, "epoch": 0.626, "loss": 1.81416, "ppl": 6.136, "lr": 0.003, "grad": 0.2255, "tokens": 103217587200, "tok_s": 158439.9}
|
| 25 |
+
{"step": 98480, "epoch": 0.626, "loss": 1.80932, "ppl": 6.106, "lr": 0.003, "grad": 0.1879, "tokens": 103238553600, "tok_s": 158263.7}
|
| 26 |
+
{"step": 98500, "epoch": 0.626, "loss": 1.89911, "ppl": 6.68, "lr": 0.003, "grad": 0.1916, "tokens": 103259520000, "tok_s": 158892.9}
|
| 27 |
+
{"step": 98520, "epoch": 0.626, "loss": 1.76544, "ppl": 5.844, "lr": 0.003, "grad": 0.149, "tokens": 103280486400, "tok_s": 158358.7}
|
| 28 |
+
{"step": 98540, "epoch": 0.626, "loss": 1.66125, "ppl": 5.266, "lr": 0.003, "grad": 0.205, "tokens": 103301452800, "tok_s": 158075.1}
|
| 29 |
+
{"step": 98560, "epoch": 0.626, "loss": 1.68001, "ppl": 5.366, "lr": 0.003, "grad": 0.0882, "tokens": 103322419200, "tok_s": 158640.6}
|
| 30 |
+
{"step": 98580, "epoch": 0.626, "loss": 1.70608, "ppl": 5.507, "lr": 0.003, "grad": 0.1951, "tokens": 103343385600, "tok_s": 158672.7}
|
| 31 |
+
{"step": 98600, "epoch": 0.626, "loss": 1.64175, "ppl": 5.164, "lr": 0.003, "grad": 0.2165, "tokens": 103364352000, "tok_s": 158870.1}
|
| 32 |
+
{"step": 98620, "epoch": 0.627, "loss": 1.71613, "ppl": 5.563, "lr": 0.003, "grad": 0.2244, "tokens": 103385318400, "tok_s": 158282.1}
|
| 33 |
+
{"step": 98640, "epoch": 0.627, "loss": 1.6649, "ppl": 5.285, "lr": 0.003, "grad": 0.182, "tokens": 103406284800, "tok_s": 158912.1}
|
| 34 |
+
{"step": 98660, "epoch": 0.627, "loss": 1.84504, "ppl": 6.328, "lr": 0.003, "grad": 0.0664, "tokens": 103427251200, "tok_s": 158841.8}
|
| 35 |
+
{"step": 98680, "epoch": 0.627, "loss": 1.77318, "ppl": 5.89, "lr": 0.003, "grad": 0.2696, "tokens": 103448217600, "tok_s": 158928.0}
|
| 36 |
+
{"step": 98700, "epoch": 0.627, "loss": 1.74386, "ppl": 5.719, "lr": 0.003, "grad": 0.1621, "tokens": 103469184000, "tok_s": 158718.0}
|
| 37 |
+
{"step": 98720, "epoch": 0.627, "loss": 1.66862, "ppl": 5.305, "lr": 0.003, "grad": 0.1715, "tokens": 103490150400, "tok_s": 158637.2}
|
| 38 |
+
{"step": 98740, "epoch": 0.627, "loss": 1.70017, "ppl": 5.475, "lr": 0.003, "grad": 0.0869, "tokens": 103511116800, "tok_s": 158363.5}
|
| 39 |
+
{"step": 98760, "epoch": 0.627, "loss": 1.76833, "ppl": 5.861, "lr": 0.003, "grad": 0.1433, "tokens": 103532083200, "tok_s": 158108.0}
|
| 40 |
+
{"step": 98780, "epoch": 0.628, "loss": 1.67864, "ppl": 5.358, "lr": 0.003, "grad": 0.1898, "tokens": 103553049600, "tok_s": 158064.4}
|
| 41 |
+
{"step": 98800, "epoch": 0.628, "loss": 1.69462, "ppl": 5.445, "lr": 0.003, "grad": 0.1092, "tokens": 103574016000, "tok_s": 158171.6}
|
| 42 |
+
{"step": 98820, "epoch": 0.628, "loss": 1.7443, "ppl": 5.722, "lr": 0.003, "grad": 0.2392, "tokens": 103594982400, "tok_s": 158398.4}
|
| 43 |
+
{"step": 98840, "epoch": 0.628, "loss": 1.67709, "ppl": 5.35, "lr": 0.003, "grad": 0.124, "tokens": 103615948800, "tok_s": 158617.8}
|
| 44 |
+
{"step": 98860, "epoch": 0.628, "loss": 1.75499, "ppl": 5.783, "lr": 0.003, "grad": 0.176, "tokens": 103636915200, "tok_s": 158667.3}
|
| 45 |
+
{"step": 98880, "epoch": 0.628, "loss": 1.7819, "ppl": 5.941, "lr": 0.003, "grad": 0.1736, "tokens": 103657881600, "tok_s": 158679.1}
|
| 46 |
+
{"step": 98900, "epoch": 0.628, "loss": 1.45226, "ppl": 4.273, "lr": 0.003, "grad": 0.1131, "tokens": 103678848000, "tok_s": 159066.4}
|
| 47 |
+
{"step": 98920, "epoch": 0.629, "loss": 1.67966, "ppl": 5.364, "lr": 0.003, "grad": 0.2455, "tokens": 103699814400, "tok_s": 158681.4}
|
| 48 |
+
{"step": 98940, "epoch": 0.629, "loss": 1.69065, "ppl": 5.423, "lr": 0.003, "grad": 0.0637, "tokens": 103720780800, "tok_s": 158740.0}
|
| 49 |
+
{"step": 98960, "epoch": 0.629, "loss": 1.78638, "ppl": 5.968, "lr": 0.003, "grad": 0.1644, "tokens": 103741747200, "tok_s": 158716.4}
|
| 50 |
+
{"step": 98980, "epoch": 0.629, "loss": 1.73764, "ppl": 5.684, "lr": 0.003, "grad": 0.1215, "tokens": 103762713600, "tok_s": 158906.6}
|
| 51 |
+
{"step": 99000, "epoch": 0.629, "loss": 1.89288, "ppl": 6.638, "lr": 0.003, "grad": 0.1775, "tokens": 103783680000, "tok_s": 158012.5}
|
| 52 |
+
{"step": 99000, "val_loss": 1.73407, "val_ppl": 5.664, "is_best": true}
|
| 53 |
+
{"step": 99020, "epoch": 0.629, "loss": 1.73741, "ppl": 5.683, "lr": 0.003, "grad": 0.1851, "tokens": 103804646400, "tok_s": 158546.5}
|
| 54 |
+
{"step": 99040, "epoch": 0.629, "loss": 1.67998, "ppl": 5.365, "lr": 0.003, "grad": 0.1925, "tokens": 103825612800, "tok_s": 158399.1}
|
| 55 |
+
{"step": 99060, "epoch": 0.629, "loss": 1.77716, "ppl": 5.913, "lr": 0.003, "grad": 0.2115, "tokens": 103846579200, "tok_s": 158850.5}
|
| 56 |
+
{"step": 99080, "epoch": 0.63, "loss": 1.72841, "ppl": 5.632, "lr": 0.003, "grad": 0.1886, "tokens": 103867545600, "tok_s": 159120.1}
|
| 57 |
+
{"step": 99100, "epoch": 0.63, "loss": 1.59968, "ppl": 4.951, "lr": 0.003, "grad": 0.1398, "tokens": 103888512000, "tok_s": 158873.1}
|
| 58 |
+
{"step": 99120, "epoch": 0.63, "loss": 1.87214, "ppl": 6.502, "lr": 0.003, "grad": 0.2815, "tokens": 103909478400, "tok_s": 158451.1}
|
| 59 |
+
{"step": 99140, "epoch": 0.63, "loss": 1.76729, "ppl": 5.855, "lr": 0.003, "grad": 0.0983, "tokens": 103930444800, "tok_s": 158927.9}
|
| 60 |
+
{"step": 99160, "epoch": 0.63, "loss": 1.75331, "ppl": 5.774, "lr": 0.003, "grad": 0.1859, "tokens": 103951411200, "tok_s": 158931.3}
|
| 61 |
+
{"step": 99180, "epoch": 0.63, "loss": 1.79687, "ppl": 6.031, "lr": 0.003, "grad": 0.2698, "tokens": 103972377600, "tok_s": 159022.7}
|
| 62 |
+
{"step": 99200, "epoch": 0.63, "loss": 1.7116, "ppl": 5.538, "lr": 0.003, "grad": 0.2608, "tokens": 103993344000, "tok_s": 158720.5}
|
| 63 |
+
{"step": 99220, "epoch": 0.63, "loss": 1.78302, "ppl": 5.948, "lr": 0.003, "grad": 0.157, "tokens": 104014310400, "tok_s": 158913.5}
|
| 64 |
+
{"step": 99240, "epoch": 0.631, "loss": 1.69405, "ppl": 5.441, "lr": 0.003, "grad": 0.1307, "tokens": 104035276800, "tok_s": 158606.4}
|
| 65 |
+
{"step": 99260, "epoch": 0.631, "loss": 1.72396, "ppl": 5.607, "lr": 0.003, "grad": 0.2175, "tokens": 104056243200, "tok_s": 158370.1}
|
| 66 |
+
{"step": 99280, "epoch": 0.631, "loss": 1.60761, "ppl": 4.991, "lr": 0.003, "grad": 0.2016, "tokens": 104077209600, "tok_s": 159143.8}
|
| 67 |
+
{"step": 99300, "epoch": 0.631, "loss": 1.80625, "ppl": 6.088, "lr": 0.003, "grad": 0.1761, "tokens": 104098176000, "tok_s": 158750.2}
|
| 68 |
+
{"step": 99320, "epoch": 0.631, "loss": 1.74722, "ppl": 5.739, "lr": 0.003, "grad": 0.1159, "tokens": 104119142400, "tok_s": 159043.8}
|
| 69 |
+
{"step": 99340, "epoch": 0.631, "loss": 1.79794, "ppl": 6.037, "lr": 0.003, "grad": 0.2484, "tokens": 104140108800, "tok_s": 157502.7}
|
| 70 |
+
{"step": 99360, "epoch": 0.631, "loss": 1.73634, "ppl": 5.677, "lr": 0.003, "grad": 0.2103, "tokens": 104161075200, "tok_s": 158964.5}
|
| 71 |
+
{"step": 99380, "epoch": 0.631, "loss": 1.84738, "ppl": 6.343, "lr": 0.003, "grad": 0.1322, "tokens": 104182041600, "tok_s": 158505.8}
|
| 72 |
+
{"step": 99400, "epoch": 0.632, "loss": 1.81449, "ppl": 6.138, "lr": 0.003, "grad": 0.0855, "tokens": 104203008000, "tok_s": 158424.9}
|
| 73 |
+
{"step": 99420, "epoch": 0.632, "loss": 1.79644, "ppl": 6.028, "lr": 0.003, "grad": 0.2372, "tokens": 104223974400, "tok_s": 158182.5}
|
| 74 |
+
{"step": 99440, "epoch": 0.632, "loss": 1.73503, "ppl": 5.669, "lr": 0.003, "grad": 0.0897, "tokens": 104244940800, "tok_s": 158762.1}
|
| 75 |
+
{"step": 99460, "epoch": 0.632, "loss": 1.77811, "ppl": 5.919, "lr": 0.003, "grad": 0.2212, "tokens": 104265907200, "tok_s": 158674.5}
|
| 76 |
+
{"step": 99480, "epoch": 0.632, "loss": 1.82359, "ppl": 6.194, "lr": 0.003, "grad": 0.1493, "tokens": 104286873600, "tok_s": 157828.0}
|
| 77 |
+
{"step": 99500, "epoch": 0.632, "loss": 1.78333, "ppl": 5.95, "lr": 0.003, "grad": 0.2179, "tokens": 104307840000, "tok_s": 158687.2}
|
| 78 |
+
{"step": 99520, "epoch": 0.632, "loss": 1.7877, "ppl": 5.976, "lr": 0.003, "grad": 0.2217, "tokens": 104328806400, "tok_s": 158939.4}
|
| 79 |
+
{"step": 99540, "epoch": 0.632, "loss": 1.71253, "ppl": 5.543, "lr": 0.003, "grad": 0.1373, "tokens": 104349772800, "tok_s": 158815.1}
|
| 80 |
+
{"step": 99560, "epoch": 0.633, "loss": 1.79391, "ppl": 6.013, "lr": 0.003, "grad": 0.1657, "tokens": 104370739200, "tok_s": 158911.9}
|
| 81 |
+
{"step": 99580, "epoch": 0.633, "loss": 1.5946, "ppl": 4.926, "lr": 0.003, "grad": 0.0812, "tokens": 104391705600, "tok_s": 159125.2}
|
| 82 |
+
{"step": 99600, "epoch": 0.633, "loss": 1.76997, "ppl": 5.871, "lr": 0.003, "grad": 0.2467, "tokens": 104412672000, "tok_s": 158407.3}
|
| 83 |
+
{"step": 99620, "epoch": 0.633, "loss": 1.77052, "ppl": 5.874, "lr": 0.003, "grad": 0.1559, "tokens": 104433638400, "tok_s": 158644.4}
|
| 84 |
+
{"step": 99640, "epoch": 0.633, "loss": 1.73424, "ppl": 5.665, "lr": 0.003, "grad": 0.1818, "tokens": 104454604800, "tok_s": 158669.7}
|
| 85 |
+
{"step": 99660, "epoch": 0.633, "loss": 1.78674, "ppl": 5.97, "lr": 0.003, "grad": 0.1056, "tokens": 104475571200, "tok_s": 158107.0}
|
| 86 |
+
{"step": 99680, "epoch": 0.633, "loss": 1.76014, "ppl": 5.813, "lr": 0.003, "grad": 0.1567, "tokens": 104496537600, "tok_s": 158854.4}
|
| 87 |
+
{"step": 99700, "epoch": 0.633, "loss": 1.73144, "ppl": 5.649, "lr": 0.003, "grad": 0.1001, "tokens": 104517504000, "tok_s": 159199.8}
|
| 88 |
+
{"step": 99720, "epoch": 0.634, "loss": 1.70994, "ppl": 5.529, "lr": 0.003, "grad": 0.1988, "tokens": 104538470400, "tok_s": 159124.6}
|
| 89 |
+
{"step": 99740, "epoch": 0.634, "loss": 1.74776, "ppl": 5.742, "lr": 0.003, "grad": 0.1705, "tokens": 104559436800, "tok_s": 158403.4}
|
| 90 |
+
{"step": 99760, "epoch": 0.634, "loss": 1.64034, "ppl": 5.157, "lr": 0.003, "grad": 0.0577, "tokens": 104580403200, "tok_s": 158729.6}
|
| 91 |
+
{"step": 99780, "epoch": 0.634, "loss": 1.71929, "ppl": 5.581, "lr": 0.003, "grad": 0.2309, "tokens": 104601369600, "tok_s": 159146.4}
|
| 92 |
+
{"step": 99800, "epoch": 0.634, "loss": 1.74177, "ppl": 5.707, "lr": 0.003, "grad": 0.1331, "tokens": 104622336000, "tok_s": 159165.7}
|
| 93 |
+
{"step": 99820, "epoch": 0.634, "loss": 1.76581, "ppl": 5.846, "lr": 0.003, "grad": 0.2304, "tokens": 104643302400, "tok_s": 158440.8}
|
| 94 |
+
{"step": 99840, "epoch": 0.634, "loss": 1.78162, "ppl": 5.939, "lr": 0.003, "grad": 0.1354, "tokens": 104664268800, "tok_s": 158901.3}
|
| 95 |
+
{"step": 99860, "epoch": 0.634, "loss": 1.79237, "ppl": 6.004, "lr": 0.003, "grad": 0.1002, "tokens": 104685235200, "tok_s": 159220.2}
|
| 96 |
+
{"step": 99880, "epoch": 0.635, "loss": 1.77332, "ppl": 5.89, "lr": 0.003, "grad": 0.2522, "tokens": 104706201600, "tok_s": 158770.4}
|
| 97 |
+
{"step": 99900, "epoch": 0.635, "loss": 1.75601, "ppl": 5.789, "lr": 0.003, "grad": 0.2031, "tokens": 104727168000, "tok_s": 159025.1}
|
| 98 |
+
{"step": 99920, "epoch": 0.635, "loss": 1.78005, "ppl": 5.93, "lr": 0.003, "grad": 0.1312, "tokens": 104748134400, "tok_s": 158650.2}
|
| 99 |
+
{"step": 99940, "epoch": 0.635, "loss": 1.72988, "ppl": 5.64, "lr": 0.003, "grad": 0.1439, "tokens": 104769100800, "tok_s": 158564.4}
|
| 100 |
+
{"step": 99960, "epoch": 0.635, "loss": 1.7527, "ppl": 5.77, "lr": 0.003, "grad": 0.1267, "tokens": 104790067200, "tok_s": 158936.1}
|
| 101 |
+
{"step": 99980, "epoch": 0.635, "loss": 1.80049, "ppl": 6.053, "lr": 0.003, "grad": 0.1848, "tokens": 104811033600, "tok_s": 158680.4}
|
| 102 |
+
{"step": 100000, "epoch": 0.635, "loss": 1.72863, "ppl": 5.633, "lr": 0.003, "grad": 0.1562, "tokens": 104832000000, "tok_s": 159182.3}
|
| 103 |
+
{"step": 100000, "val_loss": 1.74523, "val_ppl": 5.727, "is_best": false}
|
logs/log_101000.jsonl
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 98000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-03T10:06:49.525238"}
|
| 2 |
+
{"step": 98020, "epoch": 0.623, "loss": 1.74234, "ppl": 5.711, "lr": 0.003, "grad": 0.1615, "tokens": 102756326400, "tok_s": 158831.9}
|
| 3 |
+
{"step": 98040, "epoch": 0.623, "loss": 1.74419, "ppl": 5.721, "lr": 0.003, "grad": 0.1568, "tokens": 102777292800, "tok_s": 159307.9}
|
| 4 |
+
{"step": 98060, "epoch": 0.623, "loss": 1.71837, "ppl": 5.575, "lr": 0.003, "grad": 0.24, "tokens": 102798259200, "tok_s": 159258.6}
|
| 5 |
+
{"step": 98080, "epoch": 0.623, "loss": 1.61457, "ppl": 5.026, "lr": 0.003, "grad": 0.2472, "tokens": 102819225600, "tok_s": 159123.4}
|
| 6 |
+
{"step": 98100, "epoch": 0.623, "loss": 1.76972, "ppl": 5.869, "lr": 0.003, "grad": 0.2938, "tokens": 102840192000, "tok_s": 158311.3}
|
| 7 |
+
{"step": 98120, "epoch": 0.623, "loss": 1.7321, "ppl": 5.652, "lr": 0.003, "grad": 0.2529, "tokens": 102861158400, "tok_s": 158956.1}
|
| 8 |
+
{"step": 98140, "epoch": 0.624, "loss": 1.74611, "ppl": 5.732, "lr": 0.003, "grad": 0.168, "tokens": 102882124800, "tok_s": 158236.7}
|
| 9 |
+
{"step": 98160, "epoch": 0.624, "loss": 1.67902, "ppl": 5.36, "lr": 0.003, "grad": 0.2069, "tokens": 102903091200, "tok_s": 158659.4}
|
| 10 |
+
{"step": 98180, "epoch": 0.624, "loss": 1.63289, "ppl": 5.119, "lr": 0.003, "grad": 0.1619, "tokens": 102924057600, "tok_s": 158808.6}
|
| 11 |
+
{"step": 98200, "epoch": 0.624, "loss": 1.59509, "ppl": 4.929, "lr": 0.003, "grad": 0.109, "tokens": 102945024000, "tok_s": 158550.0}
|
| 12 |
+
{"step": 98220, "epoch": 0.624, "loss": 1.78202, "ppl": 5.942, "lr": 0.003, "grad": 0.1746, "tokens": 102965990400, "tok_s": 158582.9}
|
| 13 |
+
{"step": 98240, "epoch": 0.624, "loss": 1.70405, "ppl": 5.496, "lr": 0.003, "grad": 0.0643, "tokens": 102986956800, "tok_s": 158596.8}
|
| 14 |
+
{"step": 98260, "epoch": 0.624, "loss": 1.76348, "ppl": 5.833, "lr": 0.003, "grad": 0.0995, "tokens": 103007923200, "tok_s": 158424.4}
|
| 15 |
+
{"step": 98280, "epoch": 0.624, "loss": 1.71265, "ppl": 5.544, "lr": 0.003, "grad": 0.139, "tokens": 103028889600, "tok_s": 158760.6}
|
| 16 |
+
{"step": 98300, "epoch": 0.625, "loss": 1.75718, "ppl": 5.796, "lr": 0.003, "grad": 0.225, "tokens": 103049856000, "tok_s": 158437.8}
|
| 17 |
+
{"step": 98320, "epoch": 0.625, "loss": 1.76294, "ppl": 5.83, "lr": 0.003, "grad": 0.1228, "tokens": 103070822400, "tok_s": 158716.7}
|
| 18 |
+
{"step": 98340, "epoch": 0.625, "loss": 1.72793, "ppl": 5.629, "lr": 0.003, "grad": 0.2093, "tokens": 103091788800, "tok_s": 158619.1}
|
| 19 |
+
{"step": 98360, "epoch": 0.625, "loss": 1.77321, "ppl": 5.89, "lr": 0.003, "grad": 0.1054, "tokens": 103112755200, "tok_s": 158390.0}
|
| 20 |
+
{"step": 98380, "epoch": 0.625, "loss": 1.68316, "ppl": 5.383, "lr": 0.003, "grad": 0.1909, "tokens": 103133721600, "tok_s": 158677.2}
|
| 21 |
+
{"step": 98400, "epoch": 0.625, "loss": 1.78436, "ppl": 5.956, "lr": 0.003, "grad": 0.1462, "tokens": 103154688000, "tok_s": 158637.0}
|
| 22 |
+
{"step": 98420, "epoch": 0.625, "loss": 1.76305, "ppl": 5.83, "lr": 0.003, "grad": 0.3072, "tokens": 103175654400, "tok_s": 158327.8}
|
| 23 |
+
{"step": 98440, "epoch": 0.625, "loss": 1.67234, "ppl": 5.325, "lr": 0.003, "grad": 0.0597, "tokens": 103196620800, "tok_s": 158745.4}
|
| 24 |
+
{"step": 98460, "epoch": 0.626, "loss": 1.81416, "ppl": 6.136, "lr": 0.003, "grad": 0.2255, "tokens": 103217587200, "tok_s": 158439.9}
|
| 25 |
+
{"step": 98480, "epoch": 0.626, "loss": 1.80932, "ppl": 6.106, "lr": 0.003, "grad": 0.1879, "tokens": 103238553600, "tok_s": 158263.7}
|
| 26 |
+
{"step": 98500, "epoch": 0.626, "loss": 1.89911, "ppl": 6.68, "lr": 0.003, "grad": 0.1916, "tokens": 103259520000, "tok_s": 158892.9}
|
| 27 |
+
{"step": 98520, "epoch": 0.626, "loss": 1.76544, "ppl": 5.844, "lr": 0.003, "grad": 0.149, "tokens": 103280486400, "tok_s": 158358.7}
|
| 28 |
+
{"step": 98540, "epoch": 0.626, "loss": 1.66125, "ppl": 5.266, "lr": 0.003, "grad": 0.205, "tokens": 103301452800, "tok_s": 158075.1}
|
| 29 |
+
{"step": 98560, "epoch": 0.626, "loss": 1.68001, "ppl": 5.366, "lr": 0.003, "grad": 0.0882, "tokens": 103322419200, "tok_s": 158640.6}
|
| 30 |
+
{"step": 98580, "epoch": 0.626, "loss": 1.70608, "ppl": 5.507, "lr": 0.003, "grad": 0.1951, "tokens": 103343385600, "tok_s": 158672.7}
|
| 31 |
+
{"step": 98600, "epoch": 0.626, "loss": 1.64175, "ppl": 5.164, "lr": 0.003, "grad": 0.2165, "tokens": 103364352000, "tok_s": 158870.1}
|
| 32 |
+
{"step": 98620, "epoch": 0.627, "loss": 1.71613, "ppl": 5.563, "lr": 0.003, "grad": 0.2244, "tokens": 103385318400, "tok_s": 158282.1}
|
| 33 |
+
{"step": 98640, "epoch": 0.627, "loss": 1.6649, "ppl": 5.285, "lr": 0.003, "grad": 0.182, "tokens": 103406284800, "tok_s": 158912.1}
|
| 34 |
+
{"step": 98660, "epoch": 0.627, "loss": 1.84504, "ppl": 6.328, "lr": 0.003, "grad": 0.0664, "tokens": 103427251200, "tok_s": 158841.8}
|
| 35 |
+
{"step": 98680, "epoch": 0.627, "loss": 1.77318, "ppl": 5.89, "lr": 0.003, "grad": 0.2696, "tokens": 103448217600, "tok_s": 158928.0}
|
| 36 |
+
{"step": 98700, "epoch": 0.627, "loss": 1.74386, "ppl": 5.719, "lr": 0.003, "grad": 0.1621, "tokens": 103469184000, "tok_s": 158718.0}
|
| 37 |
+
{"step": 98720, "epoch": 0.627, "loss": 1.66862, "ppl": 5.305, "lr": 0.003, "grad": 0.1715, "tokens": 103490150400, "tok_s": 158637.2}
|
| 38 |
+
{"step": 98740, "epoch": 0.627, "loss": 1.70017, "ppl": 5.475, "lr": 0.003, "grad": 0.0869, "tokens": 103511116800, "tok_s": 158363.5}
|
| 39 |
+
{"step": 98760, "epoch": 0.627, "loss": 1.76833, "ppl": 5.861, "lr": 0.003, "grad": 0.1433, "tokens": 103532083200, "tok_s": 158108.0}
|
| 40 |
+
{"step": 98780, "epoch": 0.628, "loss": 1.67864, "ppl": 5.358, "lr": 0.003, "grad": 0.1898, "tokens": 103553049600, "tok_s": 158064.4}
|
| 41 |
+
{"step": 98800, "epoch": 0.628, "loss": 1.69462, "ppl": 5.445, "lr": 0.003, "grad": 0.1092, "tokens": 103574016000, "tok_s": 158171.6}
|
| 42 |
+
{"step": 98820, "epoch": 0.628, "loss": 1.7443, "ppl": 5.722, "lr": 0.003, "grad": 0.2392, "tokens": 103594982400, "tok_s": 158398.4}
|
| 43 |
+
{"step": 98840, "epoch": 0.628, "loss": 1.67709, "ppl": 5.35, "lr": 0.003, "grad": 0.124, "tokens": 103615948800, "tok_s": 158617.8}
|
| 44 |
+
{"step": 98860, "epoch": 0.628, "loss": 1.75499, "ppl": 5.783, "lr": 0.003, "grad": 0.176, "tokens": 103636915200, "tok_s": 158667.3}
|
| 45 |
+
{"step": 98880, "epoch": 0.628, "loss": 1.7819, "ppl": 5.941, "lr": 0.003, "grad": 0.1736, "tokens": 103657881600, "tok_s": 158679.1}
|
| 46 |
+
{"step": 98900, "epoch": 0.628, "loss": 1.45226, "ppl": 4.273, "lr": 0.003, "grad": 0.1131, "tokens": 103678848000, "tok_s": 159066.4}
|
| 47 |
+
{"step": 98920, "epoch": 0.629, "loss": 1.67966, "ppl": 5.364, "lr": 0.003, "grad": 0.2455, "tokens": 103699814400, "tok_s": 158681.4}
|
| 48 |
+
{"step": 98940, "epoch": 0.629, "loss": 1.69065, "ppl": 5.423, "lr": 0.003, "grad": 0.0637, "tokens": 103720780800, "tok_s": 158740.0}
|
| 49 |
+
{"step": 98960, "epoch": 0.629, "loss": 1.78638, "ppl": 5.968, "lr": 0.003, "grad": 0.1644, "tokens": 103741747200, "tok_s": 158716.4}
|
| 50 |
+
{"step": 98980, "epoch": 0.629, "loss": 1.73764, "ppl": 5.684, "lr": 0.003, "grad": 0.1215, "tokens": 103762713600, "tok_s": 158906.6}
|
| 51 |
+
{"step": 99000, "epoch": 0.629, "loss": 1.89288, "ppl": 6.638, "lr": 0.003, "grad": 0.1775, "tokens": 103783680000, "tok_s": 158012.5}
|
| 52 |
+
{"step": 99000, "val_loss": 1.73407, "val_ppl": 5.664, "is_best": true}
|
| 53 |
+
{"step": 99020, "epoch": 0.629, "loss": 1.73741, "ppl": 5.683, "lr": 0.003, "grad": 0.1851, "tokens": 103804646400, "tok_s": 158546.5}
|
| 54 |
+
{"step": 99040, "epoch": 0.629, "loss": 1.67998, "ppl": 5.365, "lr": 0.003, "grad": 0.1925, "tokens": 103825612800, "tok_s": 158399.1}
|
| 55 |
+
{"step": 99060, "epoch": 0.629, "loss": 1.77716, "ppl": 5.913, "lr": 0.003, "grad": 0.2115, "tokens": 103846579200, "tok_s": 158850.5}
|
| 56 |
+
{"step": 99080, "epoch": 0.63, "loss": 1.72841, "ppl": 5.632, "lr": 0.003, "grad": 0.1886, "tokens": 103867545600, "tok_s": 159120.1}
|
| 57 |
+
{"step": 99100, "epoch": 0.63, "loss": 1.59968, "ppl": 4.951, "lr": 0.003, "grad": 0.1398, "tokens": 103888512000, "tok_s": 158873.1}
|
| 58 |
+
{"step": 99120, "epoch": 0.63, "loss": 1.87214, "ppl": 6.502, "lr": 0.003, "grad": 0.2815, "tokens": 103909478400, "tok_s": 158451.1}
|
| 59 |
+
{"step": 99140, "epoch": 0.63, "loss": 1.76729, "ppl": 5.855, "lr": 0.003, "grad": 0.0983, "tokens": 103930444800, "tok_s": 158927.9}
|
| 60 |
+
{"step": 99160, "epoch": 0.63, "loss": 1.75331, "ppl": 5.774, "lr": 0.003, "grad": 0.1859, "tokens": 103951411200, "tok_s": 158931.3}
|
| 61 |
+
{"step": 99180, "epoch": 0.63, "loss": 1.79687, "ppl": 6.031, "lr": 0.003, "grad": 0.2698, "tokens": 103972377600, "tok_s": 159022.7}
|
| 62 |
+
{"step": 99200, "epoch": 0.63, "loss": 1.7116, "ppl": 5.538, "lr": 0.003, "grad": 0.2608, "tokens": 103993344000, "tok_s": 158720.5}
|
| 63 |
+
{"step": 99220, "epoch": 0.63, "loss": 1.78302, "ppl": 5.948, "lr": 0.003, "grad": 0.157, "tokens": 104014310400, "tok_s": 158913.5}
|
| 64 |
+
{"step": 99240, "epoch": 0.631, "loss": 1.69405, "ppl": 5.441, "lr": 0.003, "grad": 0.1307, "tokens": 104035276800, "tok_s": 158606.4}
|
| 65 |
+
{"step": 99260, "epoch": 0.631, "loss": 1.72396, "ppl": 5.607, "lr": 0.003, "grad": 0.2175, "tokens": 104056243200, "tok_s": 158370.1}
|
| 66 |
+
{"step": 99280, "epoch": 0.631, "loss": 1.60761, "ppl": 4.991, "lr": 0.003, "grad": 0.2016, "tokens": 104077209600, "tok_s": 159143.8}
|
| 67 |
+
{"step": 99300, "epoch": 0.631, "loss": 1.80625, "ppl": 6.088, "lr": 0.003, "grad": 0.1761, "tokens": 104098176000, "tok_s": 158750.2}
|
| 68 |
+
{"step": 99320, "epoch": 0.631, "loss": 1.74722, "ppl": 5.739, "lr": 0.003, "grad": 0.1159, "tokens": 104119142400, "tok_s": 159043.8}
|
| 69 |
+
{"step": 99340, "epoch": 0.631, "loss": 1.79794, "ppl": 6.037, "lr": 0.003, "grad": 0.2484, "tokens": 104140108800, "tok_s": 157502.7}
|
| 70 |
+
{"step": 99360, "epoch": 0.631, "loss": 1.73634, "ppl": 5.677, "lr": 0.003, "grad": 0.2103, "tokens": 104161075200, "tok_s": 158964.5}
|
| 71 |
+
{"step": 99380, "epoch": 0.631, "loss": 1.84738, "ppl": 6.343, "lr": 0.003, "grad": 0.1322, "tokens": 104182041600, "tok_s": 158505.8}
|
| 72 |
+
{"step": 99400, "epoch": 0.632, "loss": 1.81449, "ppl": 6.138, "lr": 0.003, "grad": 0.0855, "tokens": 104203008000, "tok_s": 158424.9}
|
| 73 |
+
{"step": 99420, "epoch": 0.632, "loss": 1.79644, "ppl": 6.028, "lr": 0.003, "grad": 0.2372, "tokens": 104223974400, "tok_s": 158182.5}
|
| 74 |
+
{"step": 99440, "epoch": 0.632, "loss": 1.73503, "ppl": 5.669, "lr": 0.003, "grad": 0.0897, "tokens": 104244940800, "tok_s": 158762.1}
|
| 75 |
+
{"step": 99460, "epoch": 0.632, "loss": 1.77811, "ppl": 5.919, "lr": 0.003, "grad": 0.2212, "tokens": 104265907200, "tok_s": 158674.5}
|
| 76 |
+
{"step": 99480, "epoch": 0.632, "loss": 1.82359, "ppl": 6.194, "lr": 0.003, "grad": 0.1493, "tokens": 104286873600, "tok_s": 157828.0}
|
| 77 |
+
{"step": 99500, "epoch": 0.632, "loss": 1.78333, "ppl": 5.95, "lr": 0.003, "grad": 0.2179, "tokens": 104307840000, "tok_s": 158687.2}
|
| 78 |
+
{"step": 99520, "epoch": 0.632, "loss": 1.7877, "ppl": 5.976, "lr": 0.003, "grad": 0.2217, "tokens": 104328806400, "tok_s": 158939.4}
|
| 79 |
+
{"step": 99540, "epoch": 0.632, "loss": 1.71253, "ppl": 5.543, "lr": 0.003, "grad": 0.1373, "tokens": 104349772800, "tok_s": 158815.1}
|
| 80 |
+
{"step": 99560, "epoch": 0.633, "loss": 1.79391, "ppl": 6.013, "lr": 0.003, "grad": 0.1657, "tokens": 104370739200, "tok_s": 158911.9}
|
| 81 |
+
{"step": 99580, "epoch": 0.633, "loss": 1.5946, "ppl": 4.926, "lr": 0.003, "grad": 0.0812, "tokens": 104391705600, "tok_s": 159125.2}
|
| 82 |
+
{"step": 99600, "epoch": 0.633, "loss": 1.76997, "ppl": 5.871, "lr": 0.003, "grad": 0.2467, "tokens": 104412672000, "tok_s": 158407.3}
|
| 83 |
+
{"step": 99620, "epoch": 0.633, "loss": 1.77052, "ppl": 5.874, "lr": 0.003, "grad": 0.1559, "tokens": 104433638400, "tok_s": 158644.4}
|
| 84 |
+
{"step": 99640, "epoch": 0.633, "loss": 1.73424, "ppl": 5.665, "lr": 0.003, "grad": 0.1818, "tokens": 104454604800, "tok_s": 158669.7}
|
| 85 |
+
{"step": 99660, "epoch": 0.633, "loss": 1.78674, "ppl": 5.97, "lr": 0.003, "grad": 0.1056, "tokens": 104475571200, "tok_s": 158107.0}
|
| 86 |
+
{"step": 99680, "epoch": 0.633, "loss": 1.76014, "ppl": 5.813, "lr": 0.003, "grad": 0.1567, "tokens": 104496537600, "tok_s": 158854.4}
|
| 87 |
+
{"step": 99700, "epoch": 0.633, "loss": 1.73144, "ppl": 5.649, "lr": 0.003, "grad": 0.1001, "tokens": 104517504000, "tok_s": 159199.8}
|
| 88 |
+
{"step": 99720, "epoch": 0.634, "loss": 1.70994, "ppl": 5.529, "lr": 0.003, "grad": 0.1988, "tokens": 104538470400, "tok_s": 159124.6}
|
| 89 |
+
{"step": 99740, "epoch": 0.634, "loss": 1.74776, "ppl": 5.742, "lr": 0.003, "grad": 0.1705, "tokens": 104559436800, "tok_s": 158403.4}
|
| 90 |
+
{"step": 99760, "epoch": 0.634, "loss": 1.64034, "ppl": 5.157, "lr": 0.003, "grad": 0.0577, "tokens": 104580403200, "tok_s": 158729.6}
|
| 91 |
+
{"step": 99780, "epoch": 0.634, "loss": 1.71929, "ppl": 5.581, "lr": 0.003, "grad": 0.2309, "tokens": 104601369600, "tok_s": 159146.4}
|
| 92 |
+
{"step": 99800, "epoch": 0.634, "loss": 1.74177, "ppl": 5.707, "lr": 0.003, "grad": 0.1331, "tokens": 104622336000, "tok_s": 159165.7}
|
| 93 |
+
{"step": 99820, "epoch": 0.634, "loss": 1.76581, "ppl": 5.846, "lr": 0.003, "grad": 0.2304, "tokens": 104643302400, "tok_s": 158440.8}
|
| 94 |
+
{"step": 99840, "epoch": 0.634, "loss": 1.78162, "ppl": 5.939, "lr": 0.003, "grad": 0.1354, "tokens": 104664268800, "tok_s": 158901.3}
|
| 95 |
+
{"step": 99860, "epoch": 0.634, "loss": 1.79237, "ppl": 6.004, "lr": 0.003, "grad": 0.1002, "tokens": 104685235200, "tok_s": 159220.2}
|
| 96 |
+
{"step": 99880, "epoch": 0.635, "loss": 1.77332, "ppl": 5.89, "lr": 0.003, "grad": 0.2522, "tokens": 104706201600, "tok_s": 158770.4}
|
| 97 |
+
{"step": 99900, "epoch": 0.635, "loss": 1.75601, "ppl": 5.789, "lr": 0.003, "grad": 0.2031, "tokens": 104727168000, "tok_s": 159025.1}
|
| 98 |
+
{"step": 99920, "epoch": 0.635, "loss": 1.78005, "ppl": 5.93, "lr": 0.003, "grad": 0.1312, "tokens": 104748134400, "tok_s": 158650.2}
|
| 99 |
+
{"step": 99940, "epoch": 0.635, "loss": 1.72988, "ppl": 5.64, "lr": 0.003, "grad": 0.1439, "tokens": 104769100800, "tok_s": 158564.4}
|
| 100 |
+
{"step": 99960, "epoch": 0.635, "loss": 1.7527, "ppl": 5.77, "lr": 0.003, "grad": 0.1267, "tokens": 104790067200, "tok_s": 158936.1}
|
| 101 |
+
{"step": 99980, "epoch": 0.635, "loss": 1.80049, "ppl": 6.053, "lr": 0.003, "grad": 0.1848, "tokens": 104811033600, "tok_s": 158680.4}
|
| 102 |
+
{"step": 100000, "epoch": 0.635, "loss": 1.72863, "ppl": 5.633, "lr": 0.003, "grad": 0.1562, "tokens": 104832000000, "tok_s": 159182.3}
|
| 103 |
+
{"step": 100000, "val_loss": 1.74523, "val_ppl": 5.727, "is_best": false}
|
| 104 |
+
{"step": 100020, "epoch": 0.635, "loss": 1.76133, "ppl": 5.82, "lr": 0.003, "grad": 0.1194, "tokens": 104852966400, "tok_s": 159239.4}
|
| 105 |
+
{"step": 100040, "epoch": 0.636, "loss": 1.75271, "ppl": 5.77, "lr": 0.003, "grad": 0.198, "tokens": 104873932800, "tok_s": 159230.0}
|
| 106 |
+
{"step": 100060, "epoch": 0.636, "loss": 1.69763, "ppl": 5.461, "lr": 0.003, "grad": 0.1639, "tokens": 104894899200, "tok_s": 159023.7}
|
| 107 |
+
{"step": 100080, "epoch": 0.636, "loss": 1.76829, "ppl": 5.861, "lr": 0.003, "grad": 0.1201, "tokens": 104915865600, "tok_s": 158687.6}
|
| 108 |
+
{"step": 100100, "epoch": 0.636, "loss": 1.75829, "ppl": 5.803, "lr": 0.003, "grad": 0.2354, "tokens": 104936832000, "tok_s": 158462.5}
|
| 109 |
+
{"step": 100120, "epoch": 0.636, "loss": 1.83092, "ppl": 6.24, "lr": 0.003, "grad": 0.1264, "tokens": 104957798400, "tok_s": 158276.7}
|
| 110 |
+
{"step": 100140, "epoch": 0.636, "loss": 1.77311, "ppl": 5.889, "lr": 0.003, "grad": 0.0773, "tokens": 104978764800, "tok_s": 158954.1}
|
| 111 |
+
{"step": 100160, "epoch": 0.636, "loss": 1.72604, "ppl": 5.618, "lr": 0.003, "grad": 0.2332, "tokens": 104999731200, "tok_s": 158877.6}
|
| 112 |
+
{"step": 100180, "epoch": 0.637, "loss": 1.75094, "ppl": 5.76, "lr": 0.003, "grad": 0.1893, "tokens": 105020697600, "tok_s": 158932.9}
|
| 113 |
+
{"step": 100200, "epoch": 0.637, "loss": 1.80651, "ppl": 6.089, "lr": 0.003, "grad": 0.1768, "tokens": 105041664000, "tok_s": 159161.3}
|
| 114 |
+
{"step": 100220, "epoch": 0.637, "loss": 1.70541, "ppl": 5.504, "lr": 0.003, "grad": 0.1091, "tokens": 105062630400, "tok_s": 158848.9}
|
| 115 |
+
{"step": 100240, "epoch": 0.637, "loss": 1.75121, "ppl": 5.762, "lr": 0.003, "grad": 0.2336, "tokens": 105083596800, "tok_s": 158300.4}
|
| 116 |
+
{"step": 100260, "epoch": 0.637, "loss": 1.66422, "ppl": 5.282, "lr": 0.003, "grad": 0.0934, "tokens": 105104563200, "tok_s": 158953.8}
|
| 117 |
+
{"step": 100280, "epoch": 0.637, "loss": 1.76342, "ppl": 5.832, "lr": 0.003, "grad": 0.2033, "tokens": 105125529600, "tok_s": 158844.1}
|
| 118 |
+
{"step": 100300, "epoch": 0.637, "loss": 1.78765, "ppl": 5.975, "lr": 0.003, "grad": 0.2248, "tokens": 105146496000, "tok_s": 158717.8}
|
| 119 |
+
{"step": 100320, "epoch": 0.637, "loss": 1.67113, "ppl": 5.318, "lr": 0.003, "grad": 0.1879, "tokens": 105167462400, "tok_s": 159040.6}
|
| 120 |
+
{"step": 100340, "epoch": 0.638, "loss": 1.63346, "ppl": 5.122, "lr": 0.003, "grad": 0.2012, "tokens": 105188428800, "tok_s": 158322.3}
|
| 121 |
+
{"step": 100360, "epoch": 0.638, "loss": 1.76098, "ppl": 5.818, "lr": 0.003, "grad": 0.1868, "tokens": 105209395200, "tok_s": 159372.9}
|
| 122 |
+
{"step": 100380, "epoch": 0.638, "loss": 1.73441, "ppl": 5.666, "lr": 0.003, "grad": 0.1119, "tokens": 105230361600, "tok_s": 158834.7}
|
| 123 |
+
{"step": 100400, "epoch": 0.638, "loss": 1.65126, "ppl": 5.214, "lr": 0.003, "grad": 0.0998, "tokens": 105251328000, "tok_s": 159126.9}
|
| 124 |
+
{"step": 100420, "epoch": 0.638, "loss": 1.66853, "ppl": 5.304, "lr": 0.003, "grad": 0.1093, "tokens": 105272294400, "tok_s": 159037.5}
|
| 125 |
+
{"step": 100440, "epoch": 0.638, "loss": 1.85578, "ppl": 6.397, "lr": 0.003, "grad": 0.2527, "tokens": 105293260800, "tok_s": 159096.2}
|
| 126 |
+
{"step": 100460, "epoch": 0.638, "loss": 1.64939, "ppl": 5.204, "lr": 0.003, "grad": 0.1813, "tokens": 105314227200, "tok_s": 159202.3}
|
| 127 |
+
{"step": 100480, "epoch": 0.638, "loss": 1.72721, "ppl": 5.625, "lr": 0.003, "grad": 0.1119, "tokens": 105335193600, "tok_s": 158458.4}
|
| 128 |
+
{"step": 100500, "epoch": 0.639, "loss": 1.70222, "ppl": 5.486, "lr": 0.003, "grad": 0.2038, "tokens": 105356160000, "tok_s": 158937.2}
|
| 129 |
+
{"step": 100520, "epoch": 0.639, "loss": 1.71569, "ppl": 5.56, "lr": 0.003, "grad": 0.1298, "tokens": 105377126400, "tok_s": 158760.1}
|
| 130 |
+
{"step": 100540, "epoch": 0.639, "loss": 1.71714, "ppl": 5.569, "lr": 0.003, "grad": 0.1024, "tokens": 105398092800, "tok_s": 159124.7}
|
| 131 |
+
{"step": 100560, "epoch": 0.639, "loss": 1.81384, "ppl": 6.134, "lr": 0.003, "grad": 0.1022, "tokens": 105419059200, "tok_s": 158941.9}
|
| 132 |
+
{"step": 100580, "epoch": 0.639, "loss": 1.74652, "ppl": 5.735, "lr": 0.003, "grad": 0.2359, "tokens": 105440025600, "tok_s": 159294.8}
|
| 133 |
+
{"step": 100600, "epoch": 0.639, "loss": 1.77641, "ppl": 5.909, "lr": 0.003, "grad": 0.0924, "tokens": 105460992000, "tok_s": 159040.8}
|
| 134 |
+
{"step": 100620, "epoch": 0.639, "loss": 1.7402, "ppl": 5.698, "lr": 0.003, "grad": 0.0868, "tokens": 105481958400, "tok_s": 159254.1}
|
| 135 |
+
{"step": 100640, "epoch": 0.639, "loss": 1.77878, "ppl": 5.923, "lr": 0.003, "grad": 0.1206, "tokens": 105502924800, "tok_s": 159213.1}
|
| 136 |
+
{"step": 100660, "epoch": 0.64, "loss": 1.64735, "ppl": 5.193, "lr": 0.003, "grad": 0.1146, "tokens": 105523891200, "tok_s": 158402.8}
|
| 137 |
+
{"step": 100680, "epoch": 0.64, "loss": 1.74138, "ppl": 5.705, "lr": 0.003, "grad": 0.2744, "tokens": 105544857600, "tok_s": 158572.3}
|
| 138 |
+
{"step": 100700, "epoch": 0.64, "loss": 1.70216, "ppl": 5.486, "lr": 0.003, "grad": 0.1618, "tokens": 105565824000, "tok_s": 158916.0}
|
| 139 |
+
{"step": 100720, "epoch": 0.64, "loss": 1.78789, "ppl": 5.977, "lr": 0.003, "grad": 0.2276, "tokens": 105586790400, "tok_s": 159022.1}
|
| 140 |
+
{"step": 100740, "epoch": 0.64, "loss": 1.60956, "ppl": 5.001, "lr": 0.003, "grad": 0.0722, "tokens": 105607756800, "tok_s": 159006.6}
|
| 141 |
+
{"step": 100760, "epoch": 0.64, "loss": 1.77971, "ppl": 5.928, "lr": 0.003, "grad": 0.1114, "tokens": 105628723200, "tok_s": 159067.0}
|
| 142 |
+
{"step": 100780, "epoch": 0.64, "loss": 1.78492, "ppl": 5.959, "lr": 0.003, "grad": 0.1217, "tokens": 105649689600, "tok_s": 159249.0}
|
| 143 |
+
{"step": 100800, "epoch": 0.64, "loss": 1.75956, "ppl": 5.81, "lr": 0.003, "grad": 0.1516, "tokens": 105670656000, "tok_s": 159276.5}
|
| 144 |
+
{"step": 100820, "epoch": 0.641, "loss": 1.77946, "ppl": 5.927, "lr": 0.003, "grad": 0.1612, "tokens": 105691622400, "tok_s": 158893.4}
|
| 145 |
+
{"step": 100840, "epoch": 0.641, "loss": 1.77931, "ppl": 5.926, "lr": 0.003, "grad": 0.1753, "tokens": 105712588800, "tok_s": 158875.4}
|
| 146 |
+
{"step": 100860, "epoch": 0.641, "loss": 1.80462, "ppl": 6.078, "lr": 0.003, "grad": 0.1857, "tokens": 105733555200, "tok_s": 158509.7}
|
| 147 |
+
{"step": 100880, "epoch": 0.641, "loss": 1.71768, "ppl": 5.572, "lr": 0.003, "grad": 0.0872, "tokens": 105754521600, "tok_s": 158856.5}
|
| 148 |
+
{"step": 100900, "epoch": 0.641, "loss": 1.77097, "ppl": 5.877, "lr": 0.003, "grad": 0.0717, "tokens": 105775488000, "tok_s": 159306.4}
|
| 149 |
+
{"step": 100920, "epoch": 0.641, "loss": 1.76658, "ppl": 5.851, "lr": 0.003, "grad": 0.1288, "tokens": 105796454400, "tok_s": 158962.2}
|
| 150 |
+
{"step": 100940, "epoch": 0.641, "loss": 1.73555, "ppl": 5.672, "lr": 0.003, "grad": 0.1269, "tokens": 105817420800, "tok_s": 158964.5}
|
| 151 |
+
{"step": 100960, "epoch": 0.641, "loss": 1.79175, "ppl": 6.0, "lr": 0.003, "grad": 0.1948, "tokens": 105838387200, "tok_s": 159334.7}
|
| 152 |
+
{"step": 100980, "epoch": 0.642, "loss": 1.76393, "ppl": 5.835, "lr": 0.003, "grad": 0.1839, "tokens": 105859353600, "tok_s": 159411.2}
|
| 153 |
+
{"step": 101000, "epoch": 0.642, "loss": 1.76894, "ppl": 5.865, "lr": 0.003, "grad": 0.2442, "tokens": 105880320000, "tok_s": 159080.9}
|
| 154 |
+
{"step": 101000, "val_loss": 1.75203, "val_ppl": 5.766, "is_best": false}
|
logs/log_102000.jsonl
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 98000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-03T10:06:49.525238"}
|
| 2 |
+
{"step": 98020, "epoch": 0.623, "loss": 1.74234, "ppl": 5.711, "lr": 0.003, "grad": 0.1615, "tokens": 102756326400, "tok_s": 158831.9}
|
| 3 |
+
{"step": 98040, "epoch": 0.623, "loss": 1.74419, "ppl": 5.721, "lr": 0.003, "grad": 0.1568, "tokens": 102777292800, "tok_s": 159307.9}
|
| 4 |
+
{"step": 98060, "epoch": 0.623, "loss": 1.71837, "ppl": 5.575, "lr": 0.003, "grad": 0.24, "tokens": 102798259200, "tok_s": 159258.6}
|
| 5 |
+
{"step": 98080, "epoch": 0.623, "loss": 1.61457, "ppl": 5.026, "lr": 0.003, "grad": 0.2472, "tokens": 102819225600, "tok_s": 159123.4}
|
| 6 |
+
{"step": 98100, "epoch": 0.623, "loss": 1.76972, "ppl": 5.869, "lr": 0.003, "grad": 0.2938, "tokens": 102840192000, "tok_s": 158311.3}
|
| 7 |
+
{"step": 98120, "epoch": 0.623, "loss": 1.7321, "ppl": 5.652, "lr": 0.003, "grad": 0.2529, "tokens": 102861158400, "tok_s": 158956.1}
|
| 8 |
+
{"step": 98140, "epoch": 0.624, "loss": 1.74611, "ppl": 5.732, "lr": 0.003, "grad": 0.168, "tokens": 102882124800, "tok_s": 158236.7}
|
| 9 |
+
{"step": 98160, "epoch": 0.624, "loss": 1.67902, "ppl": 5.36, "lr": 0.003, "grad": 0.2069, "tokens": 102903091200, "tok_s": 158659.4}
|
| 10 |
+
{"step": 98180, "epoch": 0.624, "loss": 1.63289, "ppl": 5.119, "lr": 0.003, "grad": 0.1619, "tokens": 102924057600, "tok_s": 158808.6}
|
| 11 |
+
{"step": 98200, "epoch": 0.624, "loss": 1.59509, "ppl": 4.929, "lr": 0.003, "grad": 0.109, "tokens": 102945024000, "tok_s": 158550.0}
|
| 12 |
+
{"step": 98220, "epoch": 0.624, "loss": 1.78202, "ppl": 5.942, "lr": 0.003, "grad": 0.1746, "tokens": 102965990400, "tok_s": 158582.9}
|
| 13 |
+
{"step": 98240, "epoch": 0.624, "loss": 1.70405, "ppl": 5.496, "lr": 0.003, "grad": 0.0643, "tokens": 102986956800, "tok_s": 158596.8}
|
| 14 |
+
{"step": 98260, "epoch": 0.624, "loss": 1.76348, "ppl": 5.833, "lr": 0.003, "grad": 0.0995, "tokens": 103007923200, "tok_s": 158424.4}
|
| 15 |
+
{"step": 98280, "epoch": 0.624, "loss": 1.71265, "ppl": 5.544, "lr": 0.003, "grad": 0.139, "tokens": 103028889600, "tok_s": 158760.6}
|
| 16 |
+
{"step": 98300, "epoch": 0.625, "loss": 1.75718, "ppl": 5.796, "lr": 0.003, "grad": 0.225, "tokens": 103049856000, "tok_s": 158437.8}
|
| 17 |
+
{"step": 98320, "epoch": 0.625, "loss": 1.76294, "ppl": 5.83, "lr": 0.003, "grad": 0.1228, "tokens": 103070822400, "tok_s": 158716.7}
|
| 18 |
+
{"step": 98340, "epoch": 0.625, "loss": 1.72793, "ppl": 5.629, "lr": 0.003, "grad": 0.2093, "tokens": 103091788800, "tok_s": 158619.1}
|
| 19 |
+
{"step": 98360, "epoch": 0.625, "loss": 1.77321, "ppl": 5.89, "lr": 0.003, "grad": 0.1054, "tokens": 103112755200, "tok_s": 158390.0}
|
| 20 |
+
{"step": 98380, "epoch": 0.625, "loss": 1.68316, "ppl": 5.383, "lr": 0.003, "grad": 0.1909, "tokens": 103133721600, "tok_s": 158677.2}
|
| 21 |
+
{"step": 98400, "epoch": 0.625, "loss": 1.78436, "ppl": 5.956, "lr": 0.003, "grad": 0.1462, "tokens": 103154688000, "tok_s": 158637.0}
|
| 22 |
+
{"step": 98420, "epoch": 0.625, "loss": 1.76305, "ppl": 5.83, "lr": 0.003, "grad": 0.3072, "tokens": 103175654400, "tok_s": 158327.8}
|
| 23 |
+
{"step": 98440, "epoch": 0.625, "loss": 1.67234, "ppl": 5.325, "lr": 0.003, "grad": 0.0597, "tokens": 103196620800, "tok_s": 158745.4}
|
| 24 |
+
{"step": 98460, "epoch": 0.626, "loss": 1.81416, "ppl": 6.136, "lr": 0.003, "grad": 0.2255, "tokens": 103217587200, "tok_s": 158439.9}
|
| 25 |
+
{"step": 98480, "epoch": 0.626, "loss": 1.80932, "ppl": 6.106, "lr": 0.003, "grad": 0.1879, "tokens": 103238553600, "tok_s": 158263.7}
|
| 26 |
+
{"step": 98500, "epoch": 0.626, "loss": 1.89911, "ppl": 6.68, "lr": 0.003, "grad": 0.1916, "tokens": 103259520000, "tok_s": 158892.9}
|
| 27 |
+
{"step": 98520, "epoch": 0.626, "loss": 1.76544, "ppl": 5.844, "lr": 0.003, "grad": 0.149, "tokens": 103280486400, "tok_s": 158358.7}
|
| 28 |
+
{"step": 98540, "epoch": 0.626, "loss": 1.66125, "ppl": 5.266, "lr": 0.003, "grad": 0.205, "tokens": 103301452800, "tok_s": 158075.1}
|
| 29 |
+
{"step": 98560, "epoch": 0.626, "loss": 1.68001, "ppl": 5.366, "lr": 0.003, "grad": 0.0882, "tokens": 103322419200, "tok_s": 158640.6}
|
| 30 |
+
{"step": 98580, "epoch": 0.626, "loss": 1.70608, "ppl": 5.507, "lr": 0.003, "grad": 0.1951, "tokens": 103343385600, "tok_s": 158672.7}
|
| 31 |
+
{"step": 98600, "epoch": 0.626, "loss": 1.64175, "ppl": 5.164, "lr": 0.003, "grad": 0.2165, "tokens": 103364352000, "tok_s": 158870.1}
|
| 32 |
+
{"step": 98620, "epoch": 0.627, "loss": 1.71613, "ppl": 5.563, "lr": 0.003, "grad": 0.2244, "tokens": 103385318400, "tok_s": 158282.1}
|
| 33 |
+
{"step": 98640, "epoch": 0.627, "loss": 1.6649, "ppl": 5.285, "lr": 0.003, "grad": 0.182, "tokens": 103406284800, "tok_s": 158912.1}
|
| 34 |
+
{"step": 98660, "epoch": 0.627, "loss": 1.84504, "ppl": 6.328, "lr": 0.003, "grad": 0.0664, "tokens": 103427251200, "tok_s": 158841.8}
|
| 35 |
+
{"step": 98680, "epoch": 0.627, "loss": 1.77318, "ppl": 5.89, "lr": 0.003, "grad": 0.2696, "tokens": 103448217600, "tok_s": 158928.0}
|
| 36 |
+
{"step": 98700, "epoch": 0.627, "loss": 1.74386, "ppl": 5.719, "lr": 0.003, "grad": 0.1621, "tokens": 103469184000, "tok_s": 158718.0}
|
| 37 |
+
{"step": 98720, "epoch": 0.627, "loss": 1.66862, "ppl": 5.305, "lr": 0.003, "grad": 0.1715, "tokens": 103490150400, "tok_s": 158637.2}
|
| 38 |
+
{"step": 98740, "epoch": 0.627, "loss": 1.70017, "ppl": 5.475, "lr": 0.003, "grad": 0.0869, "tokens": 103511116800, "tok_s": 158363.5}
|
| 39 |
+
{"step": 98760, "epoch": 0.627, "loss": 1.76833, "ppl": 5.861, "lr": 0.003, "grad": 0.1433, "tokens": 103532083200, "tok_s": 158108.0}
|
| 40 |
+
{"step": 98780, "epoch": 0.628, "loss": 1.67864, "ppl": 5.358, "lr": 0.003, "grad": 0.1898, "tokens": 103553049600, "tok_s": 158064.4}
|
| 41 |
+
{"step": 98800, "epoch": 0.628, "loss": 1.69462, "ppl": 5.445, "lr": 0.003, "grad": 0.1092, "tokens": 103574016000, "tok_s": 158171.6}
|
| 42 |
+
{"step": 98820, "epoch": 0.628, "loss": 1.7443, "ppl": 5.722, "lr": 0.003, "grad": 0.2392, "tokens": 103594982400, "tok_s": 158398.4}
|
| 43 |
+
{"step": 98840, "epoch": 0.628, "loss": 1.67709, "ppl": 5.35, "lr": 0.003, "grad": 0.124, "tokens": 103615948800, "tok_s": 158617.8}
|
| 44 |
+
{"step": 98860, "epoch": 0.628, "loss": 1.75499, "ppl": 5.783, "lr": 0.003, "grad": 0.176, "tokens": 103636915200, "tok_s": 158667.3}
|
| 45 |
+
{"step": 98880, "epoch": 0.628, "loss": 1.7819, "ppl": 5.941, "lr": 0.003, "grad": 0.1736, "tokens": 103657881600, "tok_s": 158679.1}
|
| 46 |
+
{"step": 98900, "epoch": 0.628, "loss": 1.45226, "ppl": 4.273, "lr": 0.003, "grad": 0.1131, "tokens": 103678848000, "tok_s": 159066.4}
|
| 47 |
+
{"step": 98920, "epoch": 0.629, "loss": 1.67966, "ppl": 5.364, "lr": 0.003, "grad": 0.2455, "tokens": 103699814400, "tok_s": 158681.4}
|
| 48 |
+
{"step": 98940, "epoch": 0.629, "loss": 1.69065, "ppl": 5.423, "lr": 0.003, "grad": 0.0637, "tokens": 103720780800, "tok_s": 158740.0}
|
| 49 |
+
{"step": 98960, "epoch": 0.629, "loss": 1.78638, "ppl": 5.968, "lr": 0.003, "grad": 0.1644, "tokens": 103741747200, "tok_s": 158716.4}
|
| 50 |
+
{"step": 98980, "epoch": 0.629, "loss": 1.73764, "ppl": 5.684, "lr": 0.003, "grad": 0.1215, "tokens": 103762713600, "tok_s": 158906.6}
|
| 51 |
+
{"step": 99000, "epoch": 0.629, "loss": 1.89288, "ppl": 6.638, "lr": 0.003, "grad": 0.1775, "tokens": 103783680000, "tok_s": 158012.5}
|
| 52 |
+
{"step": 99000, "val_loss": 1.73407, "val_ppl": 5.664, "is_best": true}
|
| 53 |
+
{"step": 99020, "epoch": 0.629, "loss": 1.73741, "ppl": 5.683, "lr": 0.003, "grad": 0.1851, "tokens": 103804646400, "tok_s": 158546.5}
|
| 54 |
+
{"step": 99040, "epoch": 0.629, "loss": 1.67998, "ppl": 5.365, "lr": 0.003, "grad": 0.1925, "tokens": 103825612800, "tok_s": 158399.1}
|
| 55 |
+
{"step": 99060, "epoch": 0.629, "loss": 1.77716, "ppl": 5.913, "lr": 0.003, "grad": 0.2115, "tokens": 103846579200, "tok_s": 158850.5}
|
| 56 |
+
{"step": 99080, "epoch": 0.63, "loss": 1.72841, "ppl": 5.632, "lr": 0.003, "grad": 0.1886, "tokens": 103867545600, "tok_s": 159120.1}
|
| 57 |
+
{"step": 99100, "epoch": 0.63, "loss": 1.59968, "ppl": 4.951, "lr": 0.003, "grad": 0.1398, "tokens": 103888512000, "tok_s": 158873.1}
|
| 58 |
+
{"step": 99120, "epoch": 0.63, "loss": 1.87214, "ppl": 6.502, "lr": 0.003, "grad": 0.2815, "tokens": 103909478400, "tok_s": 158451.1}
|
| 59 |
+
{"step": 99140, "epoch": 0.63, "loss": 1.76729, "ppl": 5.855, "lr": 0.003, "grad": 0.0983, "tokens": 103930444800, "tok_s": 158927.9}
|
| 60 |
+
{"step": 99160, "epoch": 0.63, "loss": 1.75331, "ppl": 5.774, "lr": 0.003, "grad": 0.1859, "tokens": 103951411200, "tok_s": 158931.3}
|
| 61 |
+
{"step": 99180, "epoch": 0.63, "loss": 1.79687, "ppl": 6.031, "lr": 0.003, "grad": 0.2698, "tokens": 103972377600, "tok_s": 159022.7}
|
| 62 |
+
{"step": 99200, "epoch": 0.63, "loss": 1.7116, "ppl": 5.538, "lr": 0.003, "grad": 0.2608, "tokens": 103993344000, "tok_s": 158720.5}
|
| 63 |
+
{"step": 99220, "epoch": 0.63, "loss": 1.78302, "ppl": 5.948, "lr": 0.003, "grad": 0.157, "tokens": 104014310400, "tok_s": 158913.5}
|
| 64 |
+
{"step": 99240, "epoch": 0.631, "loss": 1.69405, "ppl": 5.441, "lr": 0.003, "grad": 0.1307, "tokens": 104035276800, "tok_s": 158606.4}
|
| 65 |
+
{"step": 99260, "epoch": 0.631, "loss": 1.72396, "ppl": 5.607, "lr": 0.003, "grad": 0.2175, "tokens": 104056243200, "tok_s": 158370.1}
|
| 66 |
+
{"step": 99280, "epoch": 0.631, "loss": 1.60761, "ppl": 4.991, "lr": 0.003, "grad": 0.2016, "tokens": 104077209600, "tok_s": 159143.8}
|
| 67 |
+
{"step": 99300, "epoch": 0.631, "loss": 1.80625, "ppl": 6.088, "lr": 0.003, "grad": 0.1761, "tokens": 104098176000, "tok_s": 158750.2}
|
| 68 |
+
{"step": 99320, "epoch": 0.631, "loss": 1.74722, "ppl": 5.739, "lr": 0.003, "grad": 0.1159, "tokens": 104119142400, "tok_s": 159043.8}
|
| 69 |
+
{"step": 99340, "epoch": 0.631, "loss": 1.79794, "ppl": 6.037, "lr": 0.003, "grad": 0.2484, "tokens": 104140108800, "tok_s": 157502.7}
|
| 70 |
+
{"step": 99360, "epoch": 0.631, "loss": 1.73634, "ppl": 5.677, "lr": 0.003, "grad": 0.2103, "tokens": 104161075200, "tok_s": 158964.5}
|
| 71 |
+
{"step": 99380, "epoch": 0.631, "loss": 1.84738, "ppl": 6.343, "lr": 0.003, "grad": 0.1322, "tokens": 104182041600, "tok_s": 158505.8}
|
| 72 |
+
{"step": 99400, "epoch": 0.632, "loss": 1.81449, "ppl": 6.138, "lr": 0.003, "grad": 0.0855, "tokens": 104203008000, "tok_s": 158424.9}
|
| 73 |
+
{"step": 99420, "epoch": 0.632, "loss": 1.79644, "ppl": 6.028, "lr": 0.003, "grad": 0.2372, "tokens": 104223974400, "tok_s": 158182.5}
|
| 74 |
+
{"step": 99440, "epoch": 0.632, "loss": 1.73503, "ppl": 5.669, "lr": 0.003, "grad": 0.0897, "tokens": 104244940800, "tok_s": 158762.1}
|
| 75 |
+
{"step": 99460, "epoch": 0.632, "loss": 1.77811, "ppl": 5.919, "lr": 0.003, "grad": 0.2212, "tokens": 104265907200, "tok_s": 158674.5}
|
| 76 |
+
{"step": 99480, "epoch": 0.632, "loss": 1.82359, "ppl": 6.194, "lr": 0.003, "grad": 0.1493, "tokens": 104286873600, "tok_s": 157828.0}
|
| 77 |
+
{"step": 99500, "epoch": 0.632, "loss": 1.78333, "ppl": 5.95, "lr": 0.003, "grad": 0.2179, "tokens": 104307840000, "tok_s": 158687.2}
|
| 78 |
+
{"step": 99520, "epoch": 0.632, "loss": 1.7877, "ppl": 5.976, "lr": 0.003, "grad": 0.2217, "tokens": 104328806400, "tok_s": 158939.4}
|
| 79 |
+
{"step": 99540, "epoch": 0.632, "loss": 1.71253, "ppl": 5.543, "lr": 0.003, "grad": 0.1373, "tokens": 104349772800, "tok_s": 158815.1}
|
| 80 |
+
{"step": 99560, "epoch": 0.633, "loss": 1.79391, "ppl": 6.013, "lr": 0.003, "grad": 0.1657, "tokens": 104370739200, "tok_s": 158911.9}
|
| 81 |
+
{"step": 99580, "epoch": 0.633, "loss": 1.5946, "ppl": 4.926, "lr": 0.003, "grad": 0.0812, "tokens": 104391705600, "tok_s": 159125.2}
|
| 82 |
+
{"step": 99600, "epoch": 0.633, "loss": 1.76997, "ppl": 5.871, "lr": 0.003, "grad": 0.2467, "tokens": 104412672000, "tok_s": 158407.3}
|
| 83 |
+
{"step": 99620, "epoch": 0.633, "loss": 1.77052, "ppl": 5.874, "lr": 0.003, "grad": 0.1559, "tokens": 104433638400, "tok_s": 158644.4}
|
| 84 |
+
{"step": 99640, "epoch": 0.633, "loss": 1.73424, "ppl": 5.665, "lr": 0.003, "grad": 0.1818, "tokens": 104454604800, "tok_s": 158669.7}
|
| 85 |
+
{"step": 99660, "epoch": 0.633, "loss": 1.78674, "ppl": 5.97, "lr": 0.003, "grad": 0.1056, "tokens": 104475571200, "tok_s": 158107.0}
|
| 86 |
+
{"step": 99680, "epoch": 0.633, "loss": 1.76014, "ppl": 5.813, "lr": 0.003, "grad": 0.1567, "tokens": 104496537600, "tok_s": 158854.4}
|
| 87 |
+
{"step": 99700, "epoch": 0.633, "loss": 1.73144, "ppl": 5.649, "lr": 0.003, "grad": 0.1001, "tokens": 104517504000, "tok_s": 159199.8}
|
| 88 |
+
{"step": 99720, "epoch": 0.634, "loss": 1.70994, "ppl": 5.529, "lr": 0.003, "grad": 0.1988, "tokens": 104538470400, "tok_s": 159124.6}
|
| 89 |
+
{"step": 99740, "epoch": 0.634, "loss": 1.74776, "ppl": 5.742, "lr": 0.003, "grad": 0.1705, "tokens": 104559436800, "tok_s": 158403.4}
|
| 90 |
+
{"step": 99760, "epoch": 0.634, "loss": 1.64034, "ppl": 5.157, "lr": 0.003, "grad": 0.0577, "tokens": 104580403200, "tok_s": 158729.6}
|
| 91 |
+
{"step": 99780, "epoch": 0.634, "loss": 1.71929, "ppl": 5.581, "lr": 0.003, "grad": 0.2309, "tokens": 104601369600, "tok_s": 159146.4}
|
| 92 |
+
{"step": 99800, "epoch": 0.634, "loss": 1.74177, "ppl": 5.707, "lr": 0.003, "grad": 0.1331, "tokens": 104622336000, "tok_s": 159165.7}
|
| 93 |
+
{"step": 99820, "epoch": 0.634, "loss": 1.76581, "ppl": 5.846, "lr": 0.003, "grad": 0.2304, "tokens": 104643302400, "tok_s": 158440.8}
|
| 94 |
+
{"step": 99840, "epoch": 0.634, "loss": 1.78162, "ppl": 5.939, "lr": 0.003, "grad": 0.1354, "tokens": 104664268800, "tok_s": 158901.3}
|
| 95 |
+
{"step": 99860, "epoch": 0.634, "loss": 1.79237, "ppl": 6.004, "lr": 0.003, "grad": 0.1002, "tokens": 104685235200, "tok_s": 159220.2}
|
| 96 |
+
{"step": 99880, "epoch": 0.635, "loss": 1.77332, "ppl": 5.89, "lr": 0.003, "grad": 0.2522, "tokens": 104706201600, "tok_s": 158770.4}
|
| 97 |
+
{"step": 99900, "epoch": 0.635, "loss": 1.75601, "ppl": 5.789, "lr": 0.003, "grad": 0.2031, "tokens": 104727168000, "tok_s": 159025.1}
|
| 98 |
+
{"step": 99920, "epoch": 0.635, "loss": 1.78005, "ppl": 5.93, "lr": 0.003, "grad": 0.1312, "tokens": 104748134400, "tok_s": 158650.2}
|
| 99 |
+
{"step": 99940, "epoch": 0.635, "loss": 1.72988, "ppl": 5.64, "lr": 0.003, "grad": 0.1439, "tokens": 104769100800, "tok_s": 158564.4}
|
| 100 |
+
{"step": 99960, "epoch": 0.635, "loss": 1.7527, "ppl": 5.77, "lr": 0.003, "grad": 0.1267, "tokens": 104790067200, "tok_s": 158936.1}
|
| 101 |
+
{"step": 99980, "epoch": 0.635, "loss": 1.80049, "ppl": 6.053, "lr": 0.003, "grad": 0.1848, "tokens": 104811033600, "tok_s": 158680.4}
|
| 102 |
+
{"step": 100000, "epoch": 0.635, "loss": 1.72863, "ppl": 5.633, "lr": 0.003, "grad": 0.1562, "tokens": 104832000000, "tok_s": 159182.3}
|
| 103 |
+
{"step": 100000, "val_loss": 1.74523, "val_ppl": 5.727, "is_best": false}
|
| 104 |
+
{"step": 100020, "epoch": 0.635, "loss": 1.76133, "ppl": 5.82, "lr": 0.003, "grad": 0.1194, "tokens": 104852966400, "tok_s": 159239.4}
|
| 105 |
+
{"step": 100040, "epoch": 0.636, "loss": 1.75271, "ppl": 5.77, "lr": 0.003, "grad": 0.198, "tokens": 104873932800, "tok_s": 159230.0}
|
| 106 |
+
{"step": 100060, "epoch": 0.636, "loss": 1.69763, "ppl": 5.461, "lr": 0.003, "grad": 0.1639, "tokens": 104894899200, "tok_s": 159023.7}
|
| 107 |
+
{"step": 100080, "epoch": 0.636, "loss": 1.76829, "ppl": 5.861, "lr": 0.003, "grad": 0.1201, "tokens": 104915865600, "tok_s": 158687.6}
|
| 108 |
+
{"step": 100100, "epoch": 0.636, "loss": 1.75829, "ppl": 5.803, "lr": 0.003, "grad": 0.2354, "tokens": 104936832000, "tok_s": 158462.5}
|
| 109 |
+
{"step": 100120, "epoch": 0.636, "loss": 1.83092, "ppl": 6.24, "lr": 0.003, "grad": 0.1264, "tokens": 104957798400, "tok_s": 158276.7}
|
| 110 |
+
{"step": 100140, "epoch": 0.636, "loss": 1.77311, "ppl": 5.889, "lr": 0.003, "grad": 0.0773, "tokens": 104978764800, "tok_s": 158954.1}
|
| 111 |
+
{"step": 100160, "epoch": 0.636, "loss": 1.72604, "ppl": 5.618, "lr": 0.003, "grad": 0.2332, "tokens": 104999731200, "tok_s": 158877.6}
|
| 112 |
+
{"step": 100180, "epoch": 0.637, "loss": 1.75094, "ppl": 5.76, "lr": 0.003, "grad": 0.1893, "tokens": 105020697600, "tok_s": 158932.9}
|
| 113 |
+
{"step": 100200, "epoch": 0.637, "loss": 1.80651, "ppl": 6.089, "lr": 0.003, "grad": 0.1768, "tokens": 105041664000, "tok_s": 159161.3}
|
| 114 |
+
{"step": 100220, "epoch": 0.637, "loss": 1.70541, "ppl": 5.504, "lr": 0.003, "grad": 0.1091, "tokens": 105062630400, "tok_s": 158848.9}
|
| 115 |
+
{"step": 100240, "epoch": 0.637, "loss": 1.75121, "ppl": 5.762, "lr": 0.003, "grad": 0.2336, "tokens": 105083596800, "tok_s": 158300.4}
|
| 116 |
+
{"step": 100260, "epoch": 0.637, "loss": 1.66422, "ppl": 5.282, "lr": 0.003, "grad": 0.0934, "tokens": 105104563200, "tok_s": 158953.8}
|
| 117 |
+
{"step": 100280, "epoch": 0.637, "loss": 1.76342, "ppl": 5.832, "lr": 0.003, "grad": 0.2033, "tokens": 105125529600, "tok_s": 158844.1}
|
| 118 |
+
{"step": 100300, "epoch": 0.637, "loss": 1.78765, "ppl": 5.975, "lr": 0.003, "grad": 0.2248, "tokens": 105146496000, "tok_s": 158717.8}
|
| 119 |
+
{"step": 100320, "epoch": 0.637, "loss": 1.67113, "ppl": 5.318, "lr": 0.003, "grad": 0.1879, "tokens": 105167462400, "tok_s": 159040.6}
|
| 120 |
+
{"step": 100340, "epoch": 0.638, "loss": 1.63346, "ppl": 5.122, "lr": 0.003, "grad": 0.2012, "tokens": 105188428800, "tok_s": 158322.3}
|
| 121 |
+
{"step": 100360, "epoch": 0.638, "loss": 1.76098, "ppl": 5.818, "lr": 0.003, "grad": 0.1868, "tokens": 105209395200, "tok_s": 159372.9}
|
| 122 |
+
{"step": 100380, "epoch": 0.638, "loss": 1.73441, "ppl": 5.666, "lr": 0.003, "grad": 0.1119, "tokens": 105230361600, "tok_s": 158834.7}
|
| 123 |
+
{"step": 100400, "epoch": 0.638, "loss": 1.65126, "ppl": 5.214, "lr": 0.003, "grad": 0.0998, "tokens": 105251328000, "tok_s": 159126.9}
|
| 124 |
+
{"step": 100420, "epoch": 0.638, "loss": 1.66853, "ppl": 5.304, "lr": 0.003, "grad": 0.1093, "tokens": 105272294400, "tok_s": 159037.5}
|
| 125 |
+
{"step": 100440, "epoch": 0.638, "loss": 1.85578, "ppl": 6.397, "lr": 0.003, "grad": 0.2527, "tokens": 105293260800, "tok_s": 159096.2}
|
| 126 |
+
{"step": 100460, "epoch": 0.638, "loss": 1.64939, "ppl": 5.204, "lr": 0.003, "grad": 0.1813, "tokens": 105314227200, "tok_s": 159202.3}
|
| 127 |
+
{"step": 100480, "epoch": 0.638, "loss": 1.72721, "ppl": 5.625, "lr": 0.003, "grad": 0.1119, "tokens": 105335193600, "tok_s": 158458.4}
|
| 128 |
+
{"step": 100500, "epoch": 0.639, "loss": 1.70222, "ppl": 5.486, "lr": 0.003, "grad": 0.2038, "tokens": 105356160000, "tok_s": 158937.2}
|
| 129 |
+
{"step": 100520, "epoch": 0.639, "loss": 1.71569, "ppl": 5.56, "lr": 0.003, "grad": 0.1298, "tokens": 105377126400, "tok_s": 158760.1}
|
| 130 |
+
{"step": 100540, "epoch": 0.639, "loss": 1.71714, "ppl": 5.569, "lr": 0.003, "grad": 0.1024, "tokens": 105398092800, "tok_s": 159124.7}
|
| 131 |
+
{"step": 100560, "epoch": 0.639, "loss": 1.81384, "ppl": 6.134, "lr": 0.003, "grad": 0.1022, "tokens": 105419059200, "tok_s": 158941.9}
|
| 132 |
+
{"step": 100580, "epoch": 0.639, "loss": 1.74652, "ppl": 5.735, "lr": 0.003, "grad": 0.2359, "tokens": 105440025600, "tok_s": 159294.8}
|
| 133 |
+
{"step": 100600, "epoch": 0.639, "loss": 1.77641, "ppl": 5.909, "lr": 0.003, "grad": 0.0924, "tokens": 105460992000, "tok_s": 159040.8}
|
| 134 |
+
{"step": 100620, "epoch": 0.639, "loss": 1.7402, "ppl": 5.698, "lr": 0.003, "grad": 0.0868, "tokens": 105481958400, "tok_s": 159254.1}
|
| 135 |
+
{"step": 100640, "epoch": 0.639, "loss": 1.77878, "ppl": 5.923, "lr": 0.003, "grad": 0.1206, "tokens": 105502924800, "tok_s": 159213.1}
|
| 136 |
+
{"step": 100660, "epoch": 0.64, "loss": 1.64735, "ppl": 5.193, "lr": 0.003, "grad": 0.1146, "tokens": 105523891200, "tok_s": 158402.8}
|
| 137 |
+
{"step": 100680, "epoch": 0.64, "loss": 1.74138, "ppl": 5.705, "lr": 0.003, "grad": 0.2744, "tokens": 105544857600, "tok_s": 158572.3}
|
| 138 |
+
{"step": 100700, "epoch": 0.64, "loss": 1.70216, "ppl": 5.486, "lr": 0.003, "grad": 0.1618, "tokens": 105565824000, "tok_s": 158916.0}
|
| 139 |
+
{"step": 100720, "epoch": 0.64, "loss": 1.78789, "ppl": 5.977, "lr": 0.003, "grad": 0.2276, "tokens": 105586790400, "tok_s": 159022.1}
|
| 140 |
+
{"step": 100740, "epoch": 0.64, "loss": 1.60956, "ppl": 5.001, "lr": 0.003, "grad": 0.0722, "tokens": 105607756800, "tok_s": 159006.6}
|
| 141 |
+
{"step": 100760, "epoch": 0.64, "loss": 1.77971, "ppl": 5.928, "lr": 0.003, "grad": 0.1114, "tokens": 105628723200, "tok_s": 159067.0}
|
| 142 |
+
{"step": 100780, "epoch": 0.64, "loss": 1.78492, "ppl": 5.959, "lr": 0.003, "grad": 0.1217, "tokens": 105649689600, "tok_s": 159249.0}
|
| 143 |
+
{"step": 100800, "epoch": 0.64, "loss": 1.75956, "ppl": 5.81, "lr": 0.003, "grad": 0.1516, "tokens": 105670656000, "tok_s": 159276.5}
|
| 144 |
+
{"step": 100820, "epoch": 0.641, "loss": 1.77946, "ppl": 5.927, "lr": 0.003, "grad": 0.1612, "tokens": 105691622400, "tok_s": 158893.4}
|
| 145 |
+
{"step": 100840, "epoch": 0.641, "loss": 1.77931, "ppl": 5.926, "lr": 0.003, "grad": 0.1753, "tokens": 105712588800, "tok_s": 158875.4}
|
| 146 |
+
{"step": 100860, "epoch": 0.641, "loss": 1.80462, "ppl": 6.078, "lr": 0.003, "grad": 0.1857, "tokens": 105733555200, "tok_s": 158509.7}
|
| 147 |
+
{"step": 100880, "epoch": 0.641, "loss": 1.71768, "ppl": 5.572, "lr": 0.003, "grad": 0.0872, "tokens": 105754521600, "tok_s": 158856.5}
|
| 148 |
+
{"step": 100900, "epoch": 0.641, "loss": 1.77097, "ppl": 5.877, "lr": 0.003, "grad": 0.0717, "tokens": 105775488000, "tok_s": 159306.4}
|
| 149 |
+
{"step": 100920, "epoch": 0.641, "loss": 1.76658, "ppl": 5.851, "lr": 0.003, "grad": 0.1288, "tokens": 105796454400, "tok_s": 158962.2}
|
| 150 |
+
{"step": 100940, "epoch": 0.641, "loss": 1.73555, "ppl": 5.672, "lr": 0.003, "grad": 0.1269, "tokens": 105817420800, "tok_s": 158964.5}
|
| 151 |
+
{"step": 100960, "epoch": 0.641, "loss": 1.79175, "ppl": 6.0, "lr": 0.003, "grad": 0.1948, "tokens": 105838387200, "tok_s": 159334.7}
|
| 152 |
+
{"step": 100980, "epoch": 0.642, "loss": 1.76393, "ppl": 5.835, "lr": 0.003, "grad": 0.1839, "tokens": 105859353600, "tok_s": 159411.2}
|
| 153 |
+
{"step": 101000, "epoch": 0.642, "loss": 1.76894, "ppl": 5.865, "lr": 0.003, "grad": 0.2442, "tokens": 105880320000, "tok_s": 159080.9}
|
| 154 |
+
{"step": 101000, "val_loss": 1.75203, "val_ppl": 5.766, "is_best": false}
|
| 155 |
+
{"step": 101020, "epoch": 0.642, "loss": 1.69902, "ppl": 5.469, "lr": 0.003, "grad": 0.1677, "tokens": 105901286400, "tok_s": 158890.3}
|
| 156 |
+
{"step": 101040, "epoch": 0.642, "loss": 1.75659, "ppl": 5.793, "lr": 0.003, "grad": 0.1696, "tokens": 105922252800, "tok_s": 158949.1}
|
| 157 |
+
{"step": 101060, "epoch": 0.642, "loss": 1.73938, "ppl": 5.694, "lr": 0.003, "grad": 0.1758, "tokens": 105943219200, "tok_s": 159333.2}
|
| 158 |
+
{"step": 101080, "epoch": 0.642, "loss": 1.78052, "ppl": 5.933, "lr": 0.003, "grad": 0.2245, "tokens": 105964185600, "tok_s": 159289.0}
|
| 159 |
+
{"step": 101100, "epoch": 0.642, "loss": 1.77636, "ppl": 5.908, "lr": 0.003, "grad": 0.1133, "tokens": 105985152000, "tok_s": 159195.0}
|
| 160 |
+
{"step": 101120, "epoch": 0.642, "loss": 1.74436, "ppl": 5.722, "lr": 0.003, "grad": 0.2201, "tokens": 106006118400, "tok_s": 159049.5}
|
| 161 |
+
{"step": 101140, "epoch": 0.643, "loss": 1.72839, "ppl": 5.632, "lr": 0.003, "grad": 0.1824, "tokens": 106027084800, "tok_s": 159205.3}
|
| 162 |
+
{"step": 101160, "epoch": 0.643, "loss": 1.73873, "ppl": 5.69, "lr": 0.003, "grad": 0.1227, "tokens": 106048051200, "tok_s": 159438.2}
|
| 163 |
+
{"step": 101180, "epoch": 0.643, "loss": 1.68381, "ppl": 5.386, "lr": 0.003, "grad": 0.1494, "tokens": 106069017600, "tok_s": 159089.2}
|
| 164 |
+
{"step": 101200, "epoch": 0.643, "loss": 1.74575, "ppl": 5.73, "lr": 0.003, "grad": 0.1308, "tokens": 106089984000, "tok_s": 159278.5}
|
| 165 |
+
{"step": 101220, "epoch": 0.643, "loss": 1.73196, "ppl": 5.652, "lr": 0.003, "grad": 0.1239, "tokens": 106110950400, "tok_s": 158915.9}
|
| 166 |
+
{"step": 101240, "epoch": 0.643, "loss": 1.73589, "ppl": 5.674, "lr": 0.003, "grad": 0.1975, "tokens": 106131916800, "tok_s": 158681.8}
|
| 167 |
+
{"step": 101260, "epoch": 0.643, "loss": 1.74935, "ppl": 5.751, "lr": 0.003, "grad": 0.0941, "tokens": 106152883200, "tok_s": 158808.8}
|
| 168 |
+
{"step": 101280, "epoch": 0.643, "loss": 1.77235, "ppl": 5.885, "lr": 0.003, "grad": 0.1716, "tokens": 106173849600, "tok_s": 159071.8}
|
| 169 |
+
{"step": 101300, "epoch": 0.644, "loss": 1.82546, "ppl": 6.206, "lr": 0.003, "grad": 0.0788, "tokens": 106194816000, "tok_s": 158688.6}
|
| 170 |
+
{"step": 101320, "epoch": 0.644, "loss": 1.72601, "ppl": 5.618, "lr": 0.003, "grad": 0.1309, "tokens": 106215782400, "tok_s": 159107.3}
|
| 171 |
+
{"step": 101340, "epoch": 0.644, "loss": 1.75493, "ppl": 5.783, "lr": 0.003, "grad": 0.1279, "tokens": 106236748800, "tok_s": 158848.6}
|
| 172 |
+
{"step": 101360, "epoch": 0.644, "loss": 1.74348, "ppl": 5.717, "lr": 0.003, "grad": 0.214, "tokens": 106257715200, "tok_s": 159038.4}
|
| 173 |
+
{"step": 101380, "epoch": 0.644, "loss": 1.69554, "ppl": 5.45, "lr": 0.003, "grad": 0.1319, "tokens": 106278681600, "tok_s": 159144.6}
|
| 174 |
+
{"step": 101400, "epoch": 0.644, "loss": 1.71532, "ppl": 5.558, "lr": 0.003, "grad": 0.1737, "tokens": 106299648000, "tok_s": 159372.0}
|
| 175 |
+
{"step": 101420, "epoch": 0.644, "loss": 1.7421, "ppl": 5.709, "lr": 0.003, "grad": 0.1713, "tokens": 106320614400, "tok_s": 159283.1}
|
| 176 |
+
{"step": 101440, "epoch": 0.645, "loss": 1.73007, "ppl": 5.641, "lr": 0.003, "grad": 0.1542, "tokens": 106341580800, "tok_s": 159391.7}
|
| 177 |
+
{"step": 101460, "epoch": 0.645, "loss": 1.74194, "ppl": 5.708, "lr": 0.003, "grad": 0.0687, "tokens": 106362547200, "tok_s": 158961.1}
|
| 178 |
+
{"step": 101480, "epoch": 0.645, "loss": 1.65542, "ppl": 5.235, "lr": 0.003, "grad": 0.122, "tokens": 106383513600, "tok_s": 159161.1}
|
| 179 |
+
{"step": 101500, "epoch": 0.645, "loss": 1.86622, "ppl": 6.464, "lr": 0.003, "grad": 0.2153, "tokens": 106404480000, "tok_s": 159222.0}
|
| 180 |
+
{"step": 101520, "epoch": 0.645, "loss": 1.79329, "ppl": 6.009, "lr": 0.003, "grad": 0.1094, "tokens": 106425446400, "tok_s": 159134.2}
|
| 181 |
+
{"step": 101540, "epoch": 0.645, "loss": 1.69867, "ppl": 5.467, "lr": 0.003, "grad": 0.0603, "tokens": 106446412800, "tok_s": 158824.8}
|
| 182 |
+
{"step": 101560, "epoch": 0.645, "loss": 1.85273, "ppl": 6.377, "lr": 0.003, "grad": 0.2808, "tokens": 106467379200, "tok_s": 158153.3}
|
| 183 |
+
{"step": 101580, "epoch": 0.645, "loss": 1.73513, "ppl": 5.67, "lr": 0.003, "grad": 0.0673, "tokens": 106488345600, "tok_s": 158464.1}
|
| 184 |
+
{"step": 101600, "epoch": 0.646, "loss": 1.82406, "ppl": 6.197, "lr": 0.003, "grad": 0.1838, "tokens": 106509312000, "tok_s": 158936.4}
|
| 185 |
+
{"step": 101620, "epoch": 0.646, "loss": 1.74053, "ppl": 5.7, "lr": 0.003, "grad": 0.1894, "tokens": 106530278400, "tok_s": 158590.6}
|
| 186 |
+
{"step": 101640, "epoch": 0.646, "loss": 1.7564, "ppl": 5.792, "lr": 0.003, "grad": 0.1321, "tokens": 106551244800, "tok_s": 158597.9}
|
| 187 |
+
{"step": 101660, "epoch": 0.646, "loss": 1.63894, "ppl": 5.15, "lr": 0.003, "grad": 0.1901, "tokens": 106572211200, "tok_s": 158515.0}
|
| 188 |
+
{"step": 101680, "epoch": 0.646, "loss": 1.46939, "ppl": 4.347, "lr": 0.003, "grad": 0.1417, "tokens": 106593177600, "tok_s": 158621.3}
|
| 189 |
+
{"step": 101700, "epoch": 0.646, "loss": 1.80227, "ppl": 6.063, "lr": 0.003, "grad": 0.1476, "tokens": 106614144000, "tok_s": 158864.0}
|
| 190 |
+
{"step": 101720, "epoch": 0.646, "loss": 1.70335, "ppl": 5.492, "lr": 0.003, "grad": 0.1755, "tokens": 106635110400, "tok_s": 158887.6}
|
| 191 |
+
{"step": 101740, "epoch": 0.646, "loss": 1.71813, "ppl": 5.574, "lr": 0.003, "grad": 0.1338, "tokens": 106656076800, "tok_s": 158149.7}
|
| 192 |
+
{"step": 101760, "epoch": 0.647, "loss": 1.74782, "ppl": 5.742, "lr": 0.003, "grad": 0.0897, "tokens": 106677043200, "tok_s": 158231.4}
|
| 193 |
+
{"step": 101780, "epoch": 0.647, "loss": 1.71042, "ppl": 5.531, "lr": 0.003, "grad": 0.1879, "tokens": 106698009600, "tok_s": 158417.2}
|
| 194 |
+
{"step": 101800, "epoch": 0.647, "loss": 1.76983, "ppl": 5.87, "lr": 0.003, "grad": 0.2051, "tokens": 106718976000, "tok_s": 158644.8}
|
| 195 |
+
{"step": 101820, "epoch": 0.647, "loss": 1.75357, "ppl": 5.775, "lr": 0.003, "grad": 0.1548, "tokens": 106739942400, "tok_s": 158490.2}
|
| 196 |
+
{"step": 101840, "epoch": 0.647, "loss": 1.7686, "ppl": 5.863, "lr": 0.003, "grad": 0.2222, "tokens": 106760908800, "tok_s": 158008.1}
|
| 197 |
+
{"step": 101860, "epoch": 0.647, "loss": 1.7426, "ppl": 5.712, "lr": 0.003, "grad": 0.1588, "tokens": 106781875200, "tok_s": 158613.5}
|
| 198 |
+
{"step": 101880, "epoch": 0.647, "loss": 1.74632, "ppl": 5.733, "lr": 0.003, "grad": 0.1726, "tokens": 106802841600, "tok_s": 158743.3}
|
| 199 |
+
{"step": 101900, "epoch": 0.647, "loss": 1.73346, "ppl": 5.66, "lr": 0.003, "grad": 0.1723, "tokens": 106823808000, "tok_s": 158765.4}
|
| 200 |
+
{"step": 101920, "epoch": 0.648, "loss": 1.7343, "ppl": 5.665, "lr": 0.003, "grad": 0.2052, "tokens": 106844774400, "tok_s": 157833.7}
|
| 201 |
+
{"step": 101940, "epoch": 0.648, "loss": 1.74141, "ppl": 5.705, "lr": 0.003, "grad": 0.1354, "tokens": 106865740800, "tok_s": 158489.0}
|
| 202 |
+
{"step": 101960, "epoch": 0.648, "loss": 1.77316, "ppl": 5.889, "lr": 0.003, "grad": 0.11, "tokens": 106886707200, "tok_s": 157945.1}
|
| 203 |
+
{"step": 101980, "epoch": 0.648, "loss": 1.73974, "ppl": 5.696, "lr": 0.003, "grad": 0.158, "tokens": 106907673600, "tok_s": 158334.6}
|
| 204 |
+
{"step": 102000, "epoch": 0.648, "loss": 1.77002, "ppl": 5.871, "lr": 0.003, "grad": 0.1912, "tokens": 106928640000, "tok_s": 158656.6}
|
| 205 |
+
{"step": 102000, "val_loss": 1.75325, "val_ppl": 5.773, "is_best": false}
|
logs/log_103000.jsonl
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 98000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-03T10:06:49.525238"}
|
| 2 |
+
{"step": 98020, "epoch": 0.623, "loss": 1.74234, "ppl": 5.711, "lr": 0.003, "grad": 0.1615, "tokens": 102756326400, "tok_s": 158831.9}
|
| 3 |
+
{"step": 98040, "epoch": 0.623, "loss": 1.74419, "ppl": 5.721, "lr": 0.003, "grad": 0.1568, "tokens": 102777292800, "tok_s": 159307.9}
|
| 4 |
+
{"step": 98060, "epoch": 0.623, "loss": 1.71837, "ppl": 5.575, "lr": 0.003, "grad": 0.24, "tokens": 102798259200, "tok_s": 159258.6}
|
| 5 |
+
{"step": 98080, "epoch": 0.623, "loss": 1.61457, "ppl": 5.026, "lr": 0.003, "grad": 0.2472, "tokens": 102819225600, "tok_s": 159123.4}
|
| 6 |
+
{"step": 98100, "epoch": 0.623, "loss": 1.76972, "ppl": 5.869, "lr": 0.003, "grad": 0.2938, "tokens": 102840192000, "tok_s": 158311.3}
|
| 7 |
+
{"step": 98120, "epoch": 0.623, "loss": 1.7321, "ppl": 5.652, "lr": 0.003, "grad": 0.2529, "tokens": 102861158400, "tok_s": 158956.1}
|
| 8 |
+
{"step": 98140, "epoch": 0.624, "loss": 1.74611, "ppl": 5.732, "lr": 0.003, "grad": 0.168, "tokens": 102882124800, "tok_s": 158236.7}
|
| 9 |
+
{"step": 98160, "epoch": 0.624, "loss": 1.67902, "ppl": 5.36, "lr": 0.003, "grad": 0.2069, "tokens": 102903091200, "tok_s": 158659.4}
|
| 10 |
+
{"step": 98180, "epoch": 0.624, "loss": 1.63289, "ppl": 5.119, "lr": 0.003, "grad": 0.1619, "tokens": 102924057600, "tok_s": 158808.6}
|
| 11 |
+
{"step": 98200, "epoch": 0.624, "loss": 1.59509, "ppl": 4.929, "lr": 0.003, "grad": 0.109, "tokens": 102945024000, "tok_s": 158550.0}
|
| 12 |
+
{"step": 98220, "epoch": 0.624, "loss": 1.78202, "ppl": 5.942, "lr": 0.003, "grad": 0.1746, "tokens": 102965990400, "tok_s": 158582.9}
|
| 13 |
+
{"step": 98240, "epoch": 0.624, "loss": 1.70405, "ppl": 5.496, "lr": 0.003, "grad": 0.0643, "tokens": 102986956800, "tok_s": 158596.8}
|
| 14 |
+
{"step": 98260, "epoch": 0.624, "loss": 1.76348, "ppl": 5.833, "lr": 0.003, "grad": 0.0995, "tokens": 103007923200, "tok_s": 158424.4}
|
| 15 |
+
{"step": 98280, "epoch": 0.624, "loss": 1.71265, "ppl": 5.544, "lr": 0.003, "grad": 0.139, "tokens": 103028889600, "tok_s": 158760.6}
|
| 16 |
+
{"step": 98300, "epoch": 0.625, "loss": 1.75718, "ppl": 5.796, "lr": 0.003, "grad": 0.225, "tokens": 103049856000, "tok_s": 158437.8}
|
| 17 |
+
{"step": 98320, "epoch": 0.625, "loss": 1.76294, "ppl": 5.83, "lr": 0.003, "grad": 0.1228, "tokens": 103070822400, "tok_s": 158716.7}
|
| 18 |
+
{"step": 98340, "epoch": 0.625, "loss": 1.72793, "ppl": 5.629, "lr": 0.003, "grad": 0.2093, "tokens": 103091788800, "tok_s": 158619.1}
|
| 19 |
+
{"step": 98360, "epoch": 0.625, "loss": 1.77321, "ppl": 5.89, "lr": 0.003, "grad": 0.1054, "tokens": 103112755200, "tok_s": 158390.0}
|
| 20 |
+
{"step": 98380, "epoch": 0.625, "loss": 1.68316, "ppl": 5.383, "lr": 0.003, "grad": 0.1909, "tokens": 103133721600, "tok_s": 158677.2}
|
| 21 |
+
{"step": 98400, "epoch": 0.625, "loss": 1.78436, "ppl": 5.956, "lr": 0.003, "grad": 0.1462, "tokens": 103154688000, "tok_s": 158637.0}
|
| 22 |
+
{"step": 98420, "epoch": 0.625, "loss": 1.76305, "ppl": 5.83, "lr": 0.003, "grad": 0.3072, "tokens": 103175654400, "tok_s": 158327.8}
|
| 23 |
+
{"step": 98440, "epoch": 0.625, "loss": 1.67234, "ppl": 5.325, "lr": 0.003, "grad": 0.0597, "tokens": 103196620800, "tok_s": 158745.4}
|
| 24 |
+
{"step": 98460, "epoch": 0.626, "loss": 1.81416, "ppl": 6.136, "lr": 0.003, "grad": 0.2255, "tokens": 103217587200, "tok_s": 158439.9}
|
| 25 |
+
{"step": 98480, "epoch": 0.626, "loss": 1.80932, "ppl": 6.106, "lr": 0.003, "grad": 0.1879, "tokens": 103238553600, "tok_s": 158263.7}
|
| 26 |
+
{"step": 98500, "epoch": 0.626, "loss": 1.89911, "ppl": 6.68, "lr": 0.003, "grad": 0.1916, "tokens": 103259520000, "tok_s": 158892.9}
|
| 27 |
+
{"step": 98520, "epoch": 0.626, "loss": 1.76544, "ppl": 5.844, "lr": 0.003, "grad": 0.149, "tokens": 103280486400, "tok_s": 158358.7}
|
| 28 |
+
{"step": 98540, "epoch": 0.626, "loss": 1.66125, "ppl": 5.266, "lr": 0.003, "grad": 0.205, "tokens": 103301452800, "tok_s": 158075.1}
|
| 29 |
+
{"step": 98560, "epoch": 0.626, "loss": 1.68001, "ppl": 5.366, "lr": 0.003, "grad": 0.0882, "tokens": 103322419200, "tok_s": 158640.6}
|
| 30 |
+
{"step": 98580, "epoch": 0.626, "loss": 1.70608, "ppl": 5.507, "lr": 0.003, "grad": 0.1951, "tokens": 103343385600, "tok_s": 158672.7}
|
| 31 |
+
{"step": 98600, "epoch": 0.626, "loss": 1.64175, "ppl": 5.164, "lr": 0.003, "grad": 0.2165, "tokens": 103364352000, "tok_s": 158870.1}
|
| 32 |
+
{"step": 98620, "epoch": 0.627, "loss": 1.71613, "ppl": 5.563, "lr": 0.003, "grad": 0.2244, "tokens": 103385318400, "tok_s": 158282.1}
|
| 33 |
+
{"step": 98640, "epoch": 0.627, "loss": 1.6649, "ppl": 5.285, "lr": 0.003, "grad": 0.182, "tokens": 103406284800, "tok_s": 158912.1}
|
| 34 |
+
{"step": 98660, "epoch": 0.627, "loss": 1.84504, "ppl": 6.328, "lr": 0.003, "grad": 0.0664, "tokens": 103427251200, "tok_s": 158841.8}
|
| 35 |
+
{"step": 98680, "epoch": 0.627, "loss": 1.77318, "ppl": 5.89, "lr": 0.003, "grad": 0.2696, "tokens": 103448217600, "tok_s": 158928.0}
|
| 36 |
+
{"step": 98700, "epoch": 0.627, "loss": 1.74386, "ppl": 5.719, "lr": 0.003, "grad": 0.1621, "tokens": 103469184000, "tok_s": 158718.0}
|
| 37 |
+
{"step": 98720, "epoch": 0.627, "loss": 1.66862, "ppl": 5.305, "lr": 0.003, "grad": 0.1715, "tokens": 103490150400, "tok_s": 158637.2}
|
| 38 |
+
{"step": 98740, "epoch": 0.627, "loss": 1.70017, "ppl": 5.475, "lr": 0.003, "grad": 0.0869, "tokens": 103511116800, "tok_s": 158363.5}
|
| 39 |
+
{"step": 98760, "epoch": 0.627, "loss": 1.76833, "ppl": 5.861, "lr": 0.003, "grad": 0.1433, "tokens": 103532083200, "tok_s": 158108.0}
|
| 40 |
+
{"step": 98780, "epoch": 0.628, "loss": 1.67864, "ppl": 5.358, "lr": 0.003, "grad": 0.1898, "tokens": 103553049600, "tok_s": 158064.4}
|
| 41 |
+
{"step": 98800, "epoch": 0.628, "loss": 1.69462, "ppl": 5.445, "lr": 0.003, "grad": 0.1092, "tokens": 103574016000, "tok_s": 158171.6}
|
| 42 |
+
{"step": 98820, "epoch": 0.628, "loss": 1.7443, "ppl": 5.722, "lr": 0.003, "grad": 0.2392, "tokens": 103594982400, "tok_s": 158398.4}
|
| 43 |
+
{"step": 98840, "epoch": 0.628, "loss": 1.67709, "ppl": 5.35, "lr": 0.003, "grad": 0.124, "tokens": 103615948800, "tok_s": 158617.8}
|
| 44 |
+
{"step": 98860, "epoch": 0.628, "loss": 1.75499, "ppl": 5.783, "lr": 0.003, "grad": 0.176, "tokens": 103636915200, "tok_s": 158667.3}
|
| 45 |
+
{"step": 98880, "epoch": 0.628, "loss": 1.7819, "ppl": 5.941, "lr": 0.003, "grad": 0.1736, "tokens": 103657881600, "tok_s": 158679.1}
|
| 46 |
+
{"step": 98900, "epoch": 0.628, "loss": 1.45226, "ppl": 4.273, "lr": 0.003, "grad": 0.1131, "tokens": 103678848000, "tok_s": 159066.4}
|
| 47 |
+
{"step": 98920, "epoch": 0.629, "loss": 1.67966, "ppl": 5.364, "lr": 0.003, "grad": 0.2455, "tokens": 103699814400, "tok_s": 158681.4}
|
| 48 |
+
{"step": 98940, "epoch": 0.629, "loss": 1.69065, "ppl": 5.423, "lr": 0.003, "grad": 0.0637, "tokens": 103720780800, "tok_s": 158740.0}
|
| 49 |
+
{"step": 98960, "epoch": 0.629, "loss": 1.78638, "ppl": 5.968, "lr": 0.003, "grad": 0.1644, "tokens": 103741747200, "tok_s": 158716.4}
|
| 50 |
+
{"step": 98980, "epoch": 0.629, "loss": 1.73764, "ppl": 5.684, "lr": 0.003, "grad": 0.1215, "tokens": 103762713600, "tok_s": 158906.6}
|
| 51 |
+
{"step": 99000, "epoch": 0.629, "loss": 1.89288, "ppl": 6.638, "lr": 0.003, "grad": 0.1775, "tokens": 103783680000, "tok_s": 158012.5}
|
| 52 |
+
{"step": 99000, "val_loss": 1.73407, "val_ppl": 5.664, "is_best": true}
|
| 53 |
+
{"step": 99020, "epoch": 0.629, "loss": 1.73741, "ppl": 5.683, "lr": 0.003, "grad": 0.1851, "tokens": 103804646400, "tok_s": 158546.5}
|
| 54 |
+
{"step": 99040, "epoch": 0.629, "loss": 1.67998, "ppl": 5.365, "lr": 0.003, "grad": 0.1925, "tokens": 103825612800, "tok_s": 158399.1}
|
| 55 |
+
{"step": 99060, "epoch": 0.629, "loss": 1.77716, "ppl": 5.913, "lr": 0.003, "grad": 0.2115, "tokens": 103846579200, "tok_s": 158850.5}
|
| 56 |
+
{"step": 99080, "epoch": 0.63, "loss": 1.72841, "ppl": 5.632, "lr": 0.003, "grad": 0.1886, "tokens": 103867545600, "tok_s": 159120.1}
|
| 57 |
+
{"step": 99100, "epoch": 0.63, "loss": 1.59968, "ppl": 4.951, "lr": 0.003, "grad": 0.1398, "tokens": 103888512000, "tok_s": 158873.1}
|
| 58 |
+
{"step": 99120, "epoch": 0.63, "loss": 1.87214, "ppl": 6.502, "lr": 0.003, "grad": 0.2815, "tokens": 103909478400, "tok_s": 158451.1}
|
| 59 |
+
{"step": 99140, "epoch": 0.63, "loss": 1.76729, "ppl": 5.855, "lr": 0.003, "grad": 0.0983, "tokens": 103930444800, "tok_s": 158927.9}
|
| 60 |
+
{"step": 99160, "epoch": 0.63, "loss": 1.75331, "ppl": 5.774, "lr": 0.003, "grad": 0.1859, "tokens": 103951411200, "tok_s": 158931.3}
|
| 61 |
+
{"step": 99180, "epoch": 0.63, "loss": 1.79687, "ppl": 6.031, "lr": 0.003, "grad": 0.2698, "tokens": 103972377600, "tok_s": 159022.7}
|
| 62 |
+
{"step": 99200, "epoch": 0.63, "loss": 1.7116, "ppl": 5.538, "lr": 0.003, "grad": 0.2608, "tokens": 103993344000, "tok_s": 158720.5}
|
| 63 |
+
{"step": 99220, "epoch": 0.63, "loss": 1.78302, "ppl": 5.948, "lr": 0.003, "grad": 0.157, "tokens": 104014310400, "tok_s": 158913.5}
|
| 64 |
+
{"step": 99240, "epoch": 0.631, "loss": 1.69405, "ppl": 5.441, "lr": 0.003, "grad": 0.1307, "tokens": 104035276800, "tok_s": 158606.4}
|
| 65 |
+
{"step": 99260, "epoch": 0.631, "loss": 1.72396, "ppl": 5.607, "lr": 0.003, "grad": 0.2175, "tokens": 104056243200, "tok_s": 158370.1}
|
| 66 |
+
{"step": 99280, "epoch": 0.631, "loss": 1.60761, "ppl": 4.991, "lr": 0.003, "grad": 0.2016, "tokens": 104077209600, "tok_s": 159143.8}
|
| 67 |
+
{"step": 99300, "epoch": 0.631, "loss": 1.80625, "ppl": 6.088, "lr": 0.003, "grad": 0.1761, "tokens": 104098176000, "tok_s": 158750.2}
|
| 68 |
+
{"step": 99320, "epoch": 0.631, "loss": 1.74722, "ppl": 5.739, "lr": 0.003, "grad": 0.1159, "tokens": 104119142400, "tok_s": 159043.8}
|
| 69 |
+
{"step": 99340, "epoch": 0.631, "loss": 1.79794, "ppl": 6.037, "lr": 0.003, "grad": 0.2484, "tokens": 104140108800, "tok_s": 157502.7}
|
| 70 |
+
{"step": 99360, "epoch": 0.631, "loss": 1.73634, "ppl": 5.677, "lr": 0.003, "grad": 0.2103, "tokens": 104161075200, "tok_s": 158964.5}
|
| 71 |
+
{"step": 99380, "epoch": 0.631, "loss": 1.84738, "ppl": 6.343, "lr": 0.003, "grad": 0.1322, "tokens": 104182041600, "tok_s": 158505.8}
|
| 72 |
+
{"step": 99400, "epoch": 0.632, "loss": 1.81449, "ppl": 6.138, "lr": 0.003, "grad": 0.0855, "tokens": 104203008000, "tok_s": 158424.9}
|
| 73 |
+
{"step": 99420, "epoch": 0.632, "loss": 1.79644, "ppl": 6.028, "lr": 0.003, "grad": 0.2372, "tokens": 104223974400, "tok_s": 158182.5}
|
| 74 |
+
{"step": 99440, "epoch": 0.632, "loss": 1.73503, "ppl": 5.669, "lr": 0.003, "grad": 0.0897, "tokens": 104244940800, "tok_s": 158762.1}
|
| 75 |
+
{"step": 99460, "epoch": 0.632, "loss": 1.77811, "ppl": 5.919, "lr": 0.003, "grad": 0.2212, "tokens": 104265907200, "tok_s": 158674.5}
|
| 76 |
+
{"step": 99480, "epoch": 0.632, "loss": 1.82359, "ppl": 6.194, "lr": 0.003, "grad": 0.1493, "tokens": 104286873600, "tok_s": 157828.0}
|
| 77 |
+
{"step": 99500, "epoch": 0.632, "loss": 1.78333, "ppl": 5.95, "lr": 0.003, "grad": 0.2179, "tokens": 104307840000, "tok_s": 158687.2}
|
| 78 |
+
{"step": 99520, "epoch": 0.632, "loss": 1.7877, "ppl": 5.976, "lr": 0.003, "grad": 0.2217, "tokens": 104328806400, "tok_s": 158939.4}
|
| 79 |
+
{"step": 99540, "epoch": 0.632, "loss": 1.71253, "ppl": 5.543, "lr": 0.003, "grad": 0.1373, "tokens": 104349772800, "tok_s": 158815.1}
|
| 80 |
+
{"step": 99560, "epoch": 0.633, "loss": 1.79391, "ppl": 6.013, "lr": 0.003, "grad": 0.1657, "tokens": 104370739200, "tok_s": 158911.9}
|
| 81 |
+
{"step": 99580, "epoch": 0.633, "loss": 1.5946, "ppl": 4.926, "lr": 0.003, "grad": 0.0812, "tokens": 104391705600, "tok_s": 159125.2}
|
| 82 |
+
{"step": 99600, "epoch": 0.633, "loss": 1.76997, "ppl": 5.871, "lr": 0.003, "grad": 0.2467, "tokens": 104412672000, "tok_s": 158407.3}
|
| 83 |
+
{"step": 99620, "epoch": 0.633, "loss": 1.77052, "ppl": 5.874, "lr": 0.003, "grad": 0.1559, "tokens": 104433638400, "tok_s": 158644.4}
|
| 84 |
+
{"step": 99640, "epoch": 0.633, "loss": 1.73424, "ppl": 5.665, "lr": 0.003, "grad": 0.1818, "tokens": 104454604800, "tok_s": 158669.7}
|
| 85 |
+
{"step": 99660, "epoch": 0.633, "loss": 1.78674, "ppl": 5.97, "lr": 0.003, "grad": 0.1056, "tokens": 104475571200, "tok_s": 158107.0}
|
| 86 |
+
{"step": 99680, "epoch": 0.633, "loss": 1.76014, "ppl": 5.813, "lr": 0.003, "grad": 0.1567, "tokens": 104496537600, "tok_s": 158854.4}
|
| 87 |
+
{"step": 99700, "epoch": 0.633, "loss": 1.73144, "ppl": 5.649, "lr": 0.003, "grad": 0.1001, "tokens": 104517504000, "tok_s": 159199.8}
|
| 88 |
+
{"step": 99720, "epoch": 0.634, "loss": 1.70994, "ppl": 5.529, "lr": 0.003, "grad": 0.1988, "tokens": 104538470400, "tok_s": 159124.6}
|
| 89 |
+
{"step": 99740, "epoch": 0.634, "loss": 1.74776, "ppl": 5.742, "lr": 0.003, "grad": 0.1705, "tokens": 104559436800, "tok_s": 158403.4}
|
| 90 |
+
{"step": 99760, "epoch": 0.634, "loss": 1.64034, "ppl": 5.157, "lr": 0.003, "grad": 0.0577, "tokens": 104580403200, "tok_s": 158729.6}
|
| 91 |
+
{"step": 99780, "epoch": 0.634, "loss": 1.71929, "ppl": 5.581, "lr": 0.003, "grad": 0.2309, "tokens": 104601369600, "tok_s": 159146.4}
|
| 92 |
+
{"step": 99800, "epoch": 0.634, "loss": 1.74177, "ppl": 5.707, "lr": 0.003, "grad": 0.1331, "tokens": 104622336000, "tok_s": 159165.7}
|
| 93 |
+
{"step": 99820, "epoch": 0.634, "loss": 1.76581, "ppl": 5.846, "lr": 0.003, "grad": 0.2304, "tokens": 104643302400, "tok_s": 158440.8}
|
| 94 |
+
{"step": 99840, "epoch": 0.634, "loss": 1.78162, "ppl": 5.939, "lr": 0.003, "grad": 0.1354, "tokens": 104664268800, "tok_s": 158901.3}
|
| 95 |
+
{"step": 99860, "epoch": 0.634, "loss": 1.79237, "ppl": 6.004, "lr": 0.003, "grad": 0.1002, "tokens": 104685235200, "tok_s": 159220.2}
|
| 96 |
+
{"step": 99880, "epoch": 0.635, "loss": 1.77332, "ppl": 5.89, "lr": 0.003, "grad": 0.2522, "tokens": 104706201600, "tok_s": 158770.4}
|
| 97 |
+
{"step": 99900, "epoch": 0.635, "loss": 1.75601, "ppl": 5.789, "lr": 0.003, "grad": 0.2031, "tokens": 104727168000, "tok_s": 159025.1}
|
| 98 |
+
{"step": 99920, "epoch": 0.635, "loss": 1.78005, "ppl": 5.93, "lr": 0.003, "grad": 0.1312, "tokens": 104748134400, "tok_s": 158650.2}
|
| 99 |
+
{"step": 99940, "epoch": 0.635, "loss": 1.72988, "ppl": 5.64, "lr": 0.003, "grad": 0.1439, "tokens": 104769100800, "tok_s": 158564.4}
|
| 100 |
+
{"step": 99960, "epoch": 0.635, "loss": 1.7527, "ppl": 5.77, "lr": 0.003, "grad": 0.1267, "tokens": 104790067200, "tok_s": 158936.1}
|
| 101 |
+
{"step": 99980, "epoch": 0.635, "loss": 1.80049, "ppl": 6.053, "lr": 0.003, "grad": 0.1848, "tokens": 104811033600, "tok_s": 158680.4}
|
| 102 |
+
{"step": 100000, "epoch": 0.635, "loss": 1.72863, "ppl": 5.633, "lr": 0.003, "grad": 0.1562, "tokens": 104832000000, "tok_s": 159182.3}
|
| 103 |
+
{"step": 100000, "val_loss": 1.74523, "val_ppl": 5.727, "is_best": false}
|
| 104 |
+
{"step": 100020, "epoch": 0.635, "loss": 1.76133, "ppl": 5.82, "lr": 0.003, "grad": 0.1194, "tokens": 104852966400, "tok_s": 159239.4}
|
| 105 |
+
{"step": 100040, "epoch": 0.636, "loss": 1.75271, "ppl": 5.77, "lr": 0.003, "grad": 0.198, "tokens": 104873932800, "tok_s": 159230.0}
|
| 106 |
+
{"step": 100060, "epoch": 0.636, "loss": 1.69763, "ppl": 5.461, "lr": 0.003, "grad": 0.1639, "tokens": 104894899200, "tok_s": 159023.7}
|
| 107 |
+
{"step": 100080, "epoch": 0.636, "loss": 1.76829, "ppl": 5.861, "lr": 0.003, "grad": 0.1201, "tokens": 104915865600, "tok_s": 158687.6}
|
| 108 |
+
{"step": 100100, "epoch": 0.636, "loss": 1.75829, "ppl": 5.803, "lr": 0.003, "grad": 0.2354, "tokens": 104936832000, "tok_s": 158462.5}
|
| 109 |
+
{"step": 100120, "epoch": 0.636, "loss": 1.83092, "ppl": 6.24, "lr": 0.003, "grad": 0.1264, "tokens": 104957798400, "tok_s": 158276.7}
|
| 110 |
+
{"step": 100140, "epoch": 0.636, "loss": 1.77311, "ppl": 5.889, "lr": 0.003, "grad": 0.0773, "tokens": 104978764800, "tok_s": 158954.1}
|
| 111 |
+
{"step": 100160, "epoch": 0.636, "loss": 1.72604, "ppl": 5.618, "lr": 0.003, "grad": 0.2332, "tokens": 104999731200, "tok_s": 158877.6}
|
| 112 |
+
{"step": 100180, "epoch": 0.637, "loss": 1.75094, "ppl": 5.76, "lr": 0.003, "grad": 0.1893, "tokens": 105020697600, "tok_s": 158932.9}
|
| 113 |
+
{"step": 100200, "epoch": 0.637, "loss": 1.80651, "ppl": 6.089, "lr": 0.003, "grad": 0.1768, "tokens": 105041664000, "tok_s": 159161.3}
|
| 114 |
+
{"step": 100220, "epoch": 0.637, "loss": 1.70541, "ppl": 5.504, "lr": 0.003, "grad": 0.1091, "tokens": 105062630400, "tok_s": 158848.9}
|
| 115 |
+
{"step": 100240, "epoch": 0.637, "loss": 1.75121, "ppl": 5.762, "lr": 0.003, "grad": 0.2336, "tokens": 105083596800, "tok_s": 158300.4}
|
| 116 |
+
{"step": 100260, "epoch": 0.637, "loss": 1.66422, "ppl": 5.282, "lr": 0.003, "grad": 0.0934, "tokens": 105104563200, "tok_s": 158953.8}
|
| 117 |
+
{"step": 100280, "epoch": 0.637, "loss": 1.76342, "ppl": 5.832, "lr": 0.003, "grad": 0.2033, "tokens": 105125529600, "tok_s": 158844.1}
|
| 118 |
+
{"step": 100300, "epoch": 0.637, "loss": 1.78765, "ppl": 5.975, "lr": 0.003, "grad": 0.2248, "tokens": 105146496000, "tok_s": 158717.8}
|
| 119 |
+
{"step": 100320, "epoch": 0.637, "loss": 1.67113, "ppl": 5.318, "lr": 0.003, "grad": 0.1879, "tokens": 105167462400, "tok_s": 159040.6}
|
| 120 |
+
{"step": 100340, "epoch": 0.638, "loss": 1.63346, "ppl": 5.122, "lr": 0.003, "grad": 0.2012, "tokens": 105188428800, "tok_s": 158322.3}
|
| 121 |
+
{"step": 100360, "epoch": 0.638, "loss": 1.76098, "ppl": 5.818, "lr": 0.003, "grad": 0.1868, "tokens": 105209395200, "tok_s": 159372.9}
|
| 122 |
+
{"step": 100380, "epoch": 0.638, "loss": 1.73441, "ppl": 5.666, "lr": 0.003, "grad": 0.1119, "tokens": 105230361600, "tok_s": 158834.7}
|
| 123 |
+
{"step": 100400, "epoch": 0.638, "loss": 1.65126, "ppl": 5.214, "lr": 0.003, "grad": 0.0998, "tokens": 105251328000, "tok_s": 159126.9}
|
| 124 |
+
{"step": 100420, "epoch": 0.638, "loss": 1.66853, "ppl": 5.304, "lr": 0.003, "grad": 0.1093, "tokens": 105272294400, "tok_s": 159037.5}
|
| 125 |
+
{"step": 100440, "epoch": 0.638, "loss": 1.85578, "ppl": 6.397, "lr": 0.003, "grad": 0.2527, "tokens": 105293260800, "tok_s": 159096.2}
|
| 126 |
+
{"step": 100460, "epoch": 0.638, "loss": 1.64939, "ppl": 5.204, "lr": 0.003, "grad": 0.1813, "tokens": 105314227200, "tok_s": 159202.3}
|
| 127 |
+
{"step": 100480, "epoch": 0.638, "loss": 1.72721, "ppl": 5.625, "lr": 0.003, "grad": 0.1119, "tokens": 105335193600, "tok_s": 158458.4}
|
| 128 |
+
{"step": 100500, "epoch": 0.639, "loss": 1.70222, "ppl": 5.486, "lr": 0.003, "grad": 0.2038, "tokens": 105356160000, "tok_s": 158937.2}
|
| 129 |
+
{"step": 100520, "epoch": 0.639, "loss": 1.71569, "ppl": 5.56, "lr": 0.003, "grad": 0.1298, "tokens": 105377126400, "tok_s": 158760.1}
|
| 130 |
+
{"step": 100540, "epoch": 0.639, "loss": 1.71714, "ppl": 5.569, "lr": 0.003, "grad": 0.1024, "tokens": 105398092800, "tok_s": 159124.7}
|
| 131 |
+
{"step": 100560, "epoch": 0.639, "loss": 1.81384, "ppl": 6.134, "lr": 0.003, "grad": 0.1022, "tokens": 105419059200, "tok_s": 158941.9}
|
| 132 |
+
{"step": 100580, "epoch": 0.639, "loss": 1.74652, "ppl": 5.735, "lr": 0.003, "grad": 0.2359, "tokens": 105440025600, "tok_s": 159294.8}
|
| 133 |
+
{"step": 100600, "epoch": 0.639, "loss": 1.77641, "ppl": 5.909, "lr": 0.003, "grad": 0.0924, "tokens": 105460992000, "tok_s": 159040.8}
|
| 134 |
+
{"step": 100620, "epoch": 0.639, "loss": 1.7402, "ppl": 5.698, "lr": 0.003, "grad": 0.0868, "tokens": 105481958400, "tok_s": 159254.1}
|
| 135 |
+
{"step": 100640, "epoch": 0.639, "loss": 1.77878, "ppl": 5.923, "lr": 0.003, "grad": 0.1206, "tokens": 105502924800, "tok_s": 159213.1}
|
| 136 |
+
{"step": 100660, "epoch": 0.64, "loss": 1.64735, "ppl": 5.193, "lr": 0.003, "grad": 0.1146, "tokens": 105523891200, "tok_s": 158402.8}
|
| 137 |
+
{"step": 100680, "epoch": 0.64, "loss": 1.74138, "ppl": 5.705, "lr": 0.003, "grad": 0.2744, "tokens": 105544857600, "tok_s": 158572.3}
|
| 138 |
+
{"step": 100700, "epoch": 0.64, "loss": 1.70216, "ppl": 5.486, "lr": 0.003, "grad": 0.1618, "tokens": 105565824000, "tok_s": 158916.0}
|
| 139 |
+
{"step": 100720, "epoch": 0.64, "loss": 1.78789, "ppl": 5.977, "lr": 0.003, "grad": 0.2276, "tokens": 105586790400, "tok_s": 159022.1}
|
| 140 |
+
{"step": 100740, "epoch": 0.64, "loss": 1.60956, "ppl": 5.001, "lr": 0.003, "grad": 0.0722, "tokens": 105607756800, "tok_s": 159006.6}
|
| 141 |
+
{"step": 100760, "epoch": 0.64, "loss": 1.77971, "ppl": 5.928, "lr": 0.003, "grad": 0.1114, "tokens": 105628723200, "tok_s": 159067.0}
|
| 142 |
+
{"step": 100780, "epoch": 0.64, "loss": 1.78492, "ppl": 5.959, "lr": 0.003, "grad": 0.1217, "tokens": 105649689600, "tok_s": 159249.0}
|
| 143 |
+
{"step": 100800, "epoch": 0.64, "loss": 1.75956, "ppl": 5.81, "lr": 0.003, "grad": 0.1516, "tokens": 105670656000, "tok_s": 159276.5}
|
| 144 |
+
{"step": 100820, "epoch": 0.641, "loss": 1.77946, "ppl": 5.927, "lr": 0.003, "grad": 0.1612, "tokens": 105691622400, "tok_s": 158893.4}
|
| 145 |
+
{"step": 100840, "epoch": 0.641, "loss": 1.77931, "ppl": 5.926, "lr": 0.003, "grad": 0.1753, "tokens": 105712588800, "tok_s": 158875.4}
|
| 146 |
+
{"step": 100860, "epoch": 0.641, "loss": 1.80462, "ppl": 6.078, "lr": 0.003, "grad": 0.1857, "tokens": 105733555200, "tok_s": 158509.7}
|
| 147 |
+
{"step": 100880, "epoch": 0.641, "loss": 1.71768, "ppl": 5.572, "lr": 0.003, "grad": 0.0872, "tokens": 105754521600, "tok_s": 158856.5}
|
| 148 |
+
{"step": 100900, "epoch": 0.641, "loss": 1.77097, "ppl": 5.877, "lr": 0.003, "grad": 0.0717, "tokens": 105775488000, "tok_s": 159306.4}
|
| 149 |
+
{"step": 100920, "epoch": 0.641, "loss": 1.76658, "ppl": 5.851, "lr": 0.003, "grad": 0.1288, "tokens": 105796454400, "tok_s": 158962.2}
|
| 150 |
+
{"step": 100940, "epoch": 0.641, "loss": 1.73555, "ppl": 5.672, "lr": 0.003, "grad": 0.1269, "tokens": 105817420800, "tok_s": 158964.5}
|
| 151 |
+
{"step": 100960, "epoch": 0.641, "loss": 1.79175, "ppl": 6.0, "lr": 0.003, "grad": 0.1948, "tokens": 105838387200, "tok_s": 159334.7}
|
| 152 |
+
{"step": 100980, "epoch": 0.642, "loss": 1.76393, "ppl": 5.835, "lr": 0.003, "grad": 0.1839, "tokens": 105859353600, "tok_s": 159411.2}
|
| 153 |
+
{"step": 101000, "epoch": 0.642, "loss": 1.76894, "ppl": 5.865, "lr": 0.003, "grad": 0.2442, "tokens": 105880320000, "tok_s": 159080.9}
|
| 154 |
+
{"step": 101000, "val_loss": 1.75203, "val_ppl": 5.766, "is_best": false}
|
| 155 |
+
{"step": 101020, "epoch": 0.642, "loss": 1.69902, "ppl": 5.469, "lr": 0.003, "grad": 0.1677, "tokens": 105901286400, "tok_s": 158890.3}
|
| 156 |
+
{"step": 101040, "epoch": 0.642, "loss": 1.75659, "ppl": 5.793, "lr": 0.003, "grad": 0.1696, "tokens": 105922252800, "tok_s": 158949.1}
|
| 157 |
+
{"step": 101060, "epoch": 0.642, "loss": 1.73938, "ppl": 5.694, "lr": 0.003, "grad": 0.1758, "tokens": 105943219200, "tok_s": 159333.2}
|
| 158 |
+
{"step": 101080, "epoch": 0.642, "loss": 1.78052, "ppl": 5.933, "lr": 0.003, "grad": 0.2245, "tokens": 105964185600, "tok_s": 159289.0}
|
| 159 |
+
{"step": 101100, "epoch": 0.642, "loss": 1.77636, "ppl": 5.908, "lr": 0.003, "grad": 0.1133, "tokens": 105985152000, "tok_s": 159195.0}
|
| 160 |
+
{"step": 101120, "epoch": 0.642, "loss": 1.74436, "ppl": 5.722, "lr": 0.003, "grad": 0.2201, "tokens": 106006118400, "tok_s": 159049.5}
|
| 161 |
+
{"step": 101140, "epoch": 0.643, "loss": 1.72839, "ppl": 5.632, "lr": 0.003, "grad": 0.1824, "tokens": 106027084800, "tok_s": 159205.3}
|
| 162 |
+
{"step": 101160, "epoch": 0.643, "loss": 1.73873, "ppl": 5.69, "lr": 0.003, "grad": 0.1227, "tokens": 106048051200, "tok_s": 159438.2}
|
| 163 |
+
{"step": 101180, "epoch": 0.643, "loss": 1.68381, "ppl": 5.386, "lr": 0.003, "grad": 0.1494, "tokens": 106069017600, "tok_s": 159089.2}
|
| 164 |
+
{"step": 101200, "epoch": 0.643, "loss": 1.74575, "ppl": 5.73, "lr": 0.003, "grad": 0.1308, "tokens": 106089984000, "tok_s": 159278.5}
|
| 165 |
+
{"step": 101220, "epoch": 0.643, "loss": 1.73196, "ppl": 5.652, "lr": 0.003, "grad": 0.1239, "tokens": 106110950400, "tok_s": 158915.9}
|
| 166 |
+
{"step": 101240, "epoch": 0.643, "loss": 1.73589, "ppl": 5.674, "lr": 0.003, "grad": 0.1975, "tokens": 106131916800, "tok_s": 158681.8}
|
| 167 |
+
{"step": 101260, "epoch": 0.643, "loss": 1.74935, "ppl": 5.751, "lr": 0.003, "grad": 0.0941, "tokens": 106152883200, "tok_s": 158808.8}
|
| 168 |
+
{"step": 101280, "epoch": 0.643, "loss": 1.77235, "ppl": 5.885, "lr": 0.003, "grad": 0.1716, "tokens": 106173849600, "tok_s": 159071.8}
|
| 169 |
+
{"step": 101300, "epoch": 0.644, "loss": 1.82546, "ppl": 6.206, "lr": 0.003, "grad": 0.0788, "tokens": 106194816000, "tok_s": 158688.6}
|
| 170 |
+
{"step": 101320, "epoch": 0.644, "loss": 1.72601, "ppl": 5.618, "lr": 0.003, "grad": 0.1309, "tokens": 106215782400, "tok_s": 159107.3}
|
| 171 |
+
{"step": 101340, "epoch": 0.644, "loss": 1.75493, "ppl": 5.783, "lr": 0.003, "grad": 0.1279, "tokens": 106236748800, "tok_s": 158848.6}
|
| 172 |
+
{"step": 101360, "epoch": 0.644, "loss": 1.74348, "ppl": 5.717, "lr": 0.003, "grad": 0.214, "tokens": 106257715200, "tok_s": 159038.4}
|
| 173 |
+
{"step": 101380, "epoch": 0.644, "loss": 1.69554, "ppl": 5.45, "lr": 0.003, "grad": 0.1319, "tokens": 106278681600, "tok_s": 159144.6}
|
| 174 |
+
{"step": 101400, "epoch": 0.644, "loss": 1.71532, "ppl": 5.558, "lr": 0.003, "grad": 0.1737, "tokens": 106299648000, "tok_s": 159372.0}
|
| 175 |
+
{"step": 101420, "epoch": 0.644, "loss": 1.7421, "ppl": 5.709, "lr": 0.003, "grad": 0.1713, "tokens": 106320614400, "tok_s": 159283.1}
|
| 176 |
+
{"step": 101440, "epoch": 0.645, "loss": 1.73007, "ppl": 5.641, "lr": 0.003, "grad": 0.1542, "tokens": 106341580800, "tok_s": 159391.7}
|
| 177 |
+
{"step": 101460, "epoch": 0.645, "loss": 1.74194, "ppl": 5.708, "lr": 0.003, "grad": 0.0687, "tokens": 106362547200, "tok_s": 158961.1}
|
| 178 |
+
{"step": 101480, "epoch": 0.645, "loss": 1.65542, "ppl": 5.235, "lr": 0.003, "grad": 0.122, "tokens": 106383513600, "tok_s": 159161.1}
|
| 179 |
+
{"step": 101500, "epoch": 0.645, "loss": 1.86622, "ppl": 6.464, "lr": 0.003, "grad": 0.2153, "tokens": 106404480000, "tok_s": 159222.0}
|
| 180 |
+
{"step": 101520, "epoch": 0.645, "loss": 1.79329, "ppl": 6.009, "lr": 0.003, "grad": 0.1094, "tokens": 106425446400, "tok_s": 159134.2}
|
| 181 |
+
{"step": 101540, "epoch": 0.645, "loss": 1.69867, "ppl": 5.467, "lr": 0.003, "grad": 0.0603, "tokens": 106446412800, "tok_s": 158824.8}
|
| 182 |
+
{"step": 101560, "epoch": 0.645, "loss": 1.85273, "ppl": 6.377, "lr": 0.003, "grad": 0.2808, "tokens": 106467379200, "tok_s": 158153.3}
|
| 183 |
+
{"step": 101580, "epoch": 0.645, "loss": 1.73513, "ppl": 5.67, "lr": 0.003, "grad": 0.0673, "tokens": 106488345600, "tok_s": 158464.1}
|
| 184 |
+
{"step": 101600, "epoch": 0.646, "loss": 1.82406, "ppl": 6.197, "lr": 0.003, "grad": 0.1838, "tokens": 106509312000, "tok_s": 158936.4}
|
| 185 |
+
{"step": 101620, "epoch": 0.646, "loss": 1.74053, "ppl": 5.7, "lr": 0.003, "grad": 0.1894, "tokens": 106530278400, "tok_s": 158590.6}
|
| 186 |
+
{"step": 101640, "epoch": 0.646, "loss": 1.7564, "ppl": 5.792, "lr": 0.003, "grad": 0.1321, "tokens": 106551244800, "tok_s": 158597.9}
|
| 187 |
+
{"step": 101660, "epoch": 0.646, "loss": 1.63894, "ppl": 5.15, "lr": 0.003, "grad": 0.1901, "tokens": 106572211200, "tok_s": 158515.0}
|
| 188 |
+
{"step": 101680, "epoch": 0.646, "loss": 1.46939, "ppl": 4.347, "lr": 0.003, "grad": 0.1417, "tokens": 106593177600, "tok_s": 158621.3}
|
| 189 |
+
{"step": 101700, "epoch": 0.646, "loss": 1.80227, "ppl": 6.063, "lr": 0.003, "grad": 0.1476, "tokens": 106614144000, "tok_s": 158864.0}
|
| 190 |
+
{"step": 101720, "epoch": 0.646, "loss": 1.70335, "ppl": 5.492, "lr": 0.003, "grad": 0.1755, "tokens": 106635110400, "tok_s": 158887.6}
|
| 191 |
+
{"step": 101740, "epoch": 0.646, "loss": 1.71813, "ppl": 5.574, "lr": 0.003, "grad": 0.1338, "tokens": 106656076800, "tok_s": 158149.7}
|
| 192 |
+
{"step": 101760, "epoch": 0.647, "loss": 1.74782, "ppl": 5.742, "lr": 0.003, "grad": 0.0897, "tokens": 106677043200, "tok_s": 158231.4}
|
| 193 |
+
{"step": 101780, "epoch": 0.647, "loss": 1.71042, "ppl": 5.531, "lr": 0.003, "grad": 0.1879, "tokens": 106698009600, "tok_s": 158417.2}
|
| 194 |
+
{"step": 101800, "epoch": 0.647, "loss": 1.76983, "ppl": 5.87, "lr": 0.003, "grad": 0.2051, "tokens": 106718976000, "tok_s": 158644.8}
|
| 195 |
+
{"step": 101820, "epoch": 0.647, "loss": 1.75357, "ppl": 5.775, "lr": 0.003, "grad": 0.1548, "tokens": 106739942400, "tok_s": 158490.2}
|
| 196 |
+
{"step": 101840, "epoch": 0.647, "loss": 1.7686, "ppl": 5.863, "lr": 0.003, "grad": 0.2222, "tokens": 106760908800, "tok_s": 158008.1}
|
| 197 |
+
{"step": 101860, "epoch": 0.647, "loss": 1.7426, "ppl": 5.712, "lr": 0.003, "grad": 0.1588, "tokens": 106781875200, "tok_s": 158613.5}
|
| 198 |
+
{"step": 101880, "epoch": 0.647, "loss": 1.74632, "ppl": 5.733, "lr": 0.003, "grad": 0.1726, "tokens": 106802841600, "tok_s": 158743.3}
|
| 199 |
+
{"step": 101900, "epoch": 0.647, "loss": 1.73346, "ppl": 5.66, "lr": 0.003, "grad": 0.1723, "tokens": 106823808000, "tok_s": 158765.4}
|
| 200 |
+
{"step": 101920, "epoch": 0.648, "loss": 1.7343, "ppl": 5.665, "lr": 0.003, "grad": 0.2052, "tokens": 106844774400, "tok_s": 157833.7}
|
| 201 |
+
{"step": 101940, "epoch": 0.648, "loss": 1.74141, "ppl": 5.705, "lr": 0.003, "grad": 0.1354, "tokens": 106865740800, "tok_s": 158489.0}
|
| 202 |
+
{"step": 101960, "epoch": 0.648, "loss": 1.77316, "ppl": 5.889, "lr": 0.003, "grad": 0.11, "tokens": 106886707200, "tok_s": 157945.1}
|
| 203 |
+
{"step": 101980, "epoch": 0.648, "loss": 1.73974, "ppl": 5.696, "lr": 0.003, "grad": 0.158, "tokens": 106907673600, "tok_s": 158334.6}
|
| 204 |
+
{"step": 102000, "epoch": 0.648, "loss": 1.77002, "ppl": 5.871, "lr": 0.003, "grad": 0.1912, "tokens": 106928640000, "tok_s": 158656.6}
|
| 205 |
+
{"step": 102000, "val_loss": 1.75325, "val_ppl": 5.773, "is_best": false}
|
| 206 |
+
{"step": 102020, "epoch": 0.648, "loss": 1.71894, "ppl": 5.579, "lr": 0.003, "grad": 0.1834, "tokens": 106949606400, "tok_s": 158791.0}
|
| 207 |
+
{"step": 102040, "epoch": 0.648, "loss": 1.77267, "ppl": 5.887, "lr": 0.003, "grad": 0.1795, "tokens": 106970572800, "tok_s": 158619.6}
|
| 208 |
+
{"step": 102060, "epoch": 0.648, "loss": 1.72006, "ppl": 5.585, "lr": 0.003, "grad": 0.14, "tokens": 106991539200, "tok_s": 158508.9}
|
| 209 |
+
{"step": 102080, "epoch": 0.649, "loss": 1.78415, "ppl": 5.955, "lr": 0.003, "grad": 0.1601, "tokens": 107012505600, "tok_s": 158386.6}
|
| 210 |
+
{"step": 102100, "epoch": 0.649, "loss": 1.75915, "ppl": 5.808, "lr": 0.003, "grad": 0.1723, "tokens": 107033472000, "tok_s": 157556.9}
|
| 211 |
+
{"step": 102120, "epoch": 0.649, "loss": 1.77999, "ppl": 5.93, "lr": 0.003, "grad": 0.138, "tokens": 107054438400, "tok_s": 157591.9}
|
| 212 |
+
{"step": 102140, "epoch": 0.649, "loss": 1.7184, "ppl": 5.576, "lr": 0.003, "grad": 0.0908, "tokens": 107075404800, "tok_s": 158365.4}
|
| 213 |
+
{"step": 102160, "epoch": 0.649, "loss": 1.759, "ppl": 5.807, "lr": 0.003, "grad": 0.0955, "tokens": 107096371200, "tok_s": 158793.6}
|
| 214 |
+
{"step": 102180, "epoch": 0.649, "loss": 1.77124, "ppl": 5.878, "lr": 0.003, "grad": 0.0991, "tokens": 107117337600, "tok_s": 158015.3}
|
| 215 |
+
{"step": 102200, "epoch": 0.649, "loss": 1.80034, "ppl": 6.052, "lr": 0.003, "grad": 0.1386, "tokens": 107138304000, "tok_s": 158826.2}
|
| 216 |
+
{"step": 102220, "epoch": 0.649, "loss": 1.79533, "ppl": 6.021, "lr": 0.003, "grad": 0.273, "tokens": 107159270400, "tok_s": 158111.9}
|
| 217 |
+
{"step": 102240, "epoch": 0.65, "loss": 1.76523, "ppl": 5.843, "lr": 0.003, "grad": 0.0554, "tokens": 107180236800, "tok_s": 158698.3}
|
| 218 |
+
{"step": 102260, "epoch": 0.65, "loss": 1.72243, "ppl": 5.598, "lr": 0.003, "grad": 0.1209, "tokens": 107201203200, "tok_s": 158698.6}
|
| 219 |
+
{"step": 102280, "epoch": 0.65, "loss": 1.80623, "ppl": 6.087, "lr": 0.003, "grad": 0.1822, "tokens": 107222169600, "tok_s": 158791.9}
|
| 220 |
+
{"step": 102300, "epoch": 0.65, "loss": 1.77391, "ppl": 5.894, "lr": 0.003, "grad": 0.1096, "tokens": 107243136000, "tok_s": 158256.7}
|
| 221 |
+
{"step": 102320, "epoch": 0.65, "loss": 1.72145, "ppl": 5.593, "lr": 0.003, "grad": 0.1507, "tokens": 107264102400, "tok_s": 157693.4}
|
| 222 |
+
{"step": 102340, "epoch": 0.65, "loss": 1.78053, "ppl": 5.933, "lr": 0.003, "grad": 0.1716, "tokens": 107285068800, "tok_s": 157849.9}
|
| 223 |
+
{"step": 102360, "epoch": 0.65, "loss": 1.71884, "ppl": 5.578, "lr": 0.003, "grad": 0.1518, "tokens": 107306035200, "tok_s": 158199.0}
|
| 224 |
+
{"step": 102380, "epoch": 0.65, "loss": 1.76705, "ppl": 5.854, "lr": 0.003, "grad": 0.1294, "tokens": 107327001600, "tok_s": 158465.1}
|
| 225 |
+
{"step": 102400, "epoch": 0.651, "loss": 1.65154, "ppl": 5.215, "lr": 0.003, "grad": 0.1528, "tokens": 107347968000, "tok_s": 158959.5}
|
| 226 |
+
{"step": 102420, "epoch": 0.651, "loss": 1.76125, "ppl": 5.82, "lr": 0.003, "grad": 0.1314, "tokens": 107368934400, "tok_s": 158877.1}
|
| 227 |
+
{"step": 102440, "epoch": 0.651, "loss": 1.75673, "ppl": 5.793, "lr": 0.003, "grad": 0.2034, "tokens": 107389900800, "tok_s": 158699.9}
|
| 228 |
+
{"step": 102460, "epoch": 0.651, "loss": 1.76831, "ppl": 5.861, "lr": 0.003, "grad": 0.1653, "tokens": 107410867200, "tok_s": 158890.5}
|
| 229 |
+
{"step": 102480, "epoch": 0.651, "loss": 1.91902, "ppl": 6.814, "lr": 0.003, "grad": 0.1752, "tokens": 107431833600, "tok_s": 158630.5}
|
| 230 |
+
{"step": 102500, "epoch": 0.651, "loss": 1.79742, "ppl": 6.034, "lr": 0.003, "grad": 0.149, "tokens": 107452800000, "tok_s": 157624.6}
|
| 231 |
+
{"step": 102520, "epoch": 0.651, "loss": 1.74787, "ppl": 5.742, "lr": 0.003, "grad": 0.1017, "tokens": 107473766400, "tok_s": 158498.1}
|
| 232 |
+
{"step": 102540, "epoch": 0.652, "loss": 1.74066, "ppl": 5.701, "lr": 0.003, "grad": 0.0646, "tokens": 107494732800, "tok_s": 159033.0}
|
| 233 |
+
{"step": 102560, "epoch": 0.652, "loss": 1.81274, "ppl": 6.127, "lr": 0.003, "grad": 0.2914, "tokens": 107515699200, "tok_s": 158719.7}
|
| 234 |
+
{"step": 102580, "epoch": 0.652, "loss": 1.72332, "ppl": 5.603, "lr": 0.003, "grad": 0.1318, "tokens": 107536665600, "tok_s": 158711.5}
|
| 235 |
+
{"step": 102600, "epoch": 0.652, "loss": 1.75613, "ppl": 5.79, "lr": 0.003, "grad": 0.125, "tokens": 107557632000, "tok_s": 158117.9}
|
| 236 |
+
{"step": 102620, "epoch": 0.652, "loss": 1.77182, "ppl": 5.882, "lr": 0.003, "grad": 0.1534, "tokens": 107578598400, "tok_s": 158880.0}
|
| 237 |
+
{"step": 102640, "epoch": 0.652, "loss": 1.74327, "ppl": 5.716, "lr": 0.003, "grad": 0.0898, "tokens": 107599564800, "tok_s": 158639.2}
|
| 238 |
+
{"step": 102660, "epoch": 0.652, "loss": 1.71676, "ppl": 5.566, "lr": 0.003, "grad": 0.2239, "tokens": 107620531200, "tok_s": 158809.2}
|
| 239 |
+
{"step": 102680, "epoch": 0.652, "loss": 1.80052, "ppl": 6.053, "lr": 0.003, "grad": 0.1332, "tokens": 107641497600, "tok_s": 158832.3}
|
| 240 |
+
{"step": 102700, "epoch": 0.653, "loss": 1.71271, "ppl": 5.544, "lr": 0.003, "grad": 0.1882, "tokens": 107662464000, "tok_s": 158057.7}
|
| 241 |
+
{"step": 102720, "epoch": 0.653, "loss": 1.74288, "ppl": 5.714, "lr": 0.003, "grad": 0.1468, "tokens": 107683430400, "tok_s": 158695.9}
|
| 242 |
+
{"step": 102740, "epoch": 0.653, "loss": 1.76872, "ppl": 5.863, "lr": 0.003, "grad": 0.1758, "tokens": 107704396800, "tok_s": 158615.9}
|
| 243 |
+
{"step": 102760, "epoch": 0.653, "loss": 1.78283, "ppl": 5.947, "lr": 0.003, "grad": 0.1881, "tokens": 107725363200, "tok_s": 158270.4}
|
| 244 |
+
{"step": 102780, "epoch": 0.653, "loss": 1.73678, "ppl": 5.679, "lr": 0.003, "grad": 0.111, "tokens": 107746329600, "tok_s": 158580.3}
|
| 245 |
+
{"step": 102800, "epoch": 0.653, "loss": 1.77276, "ppl": 5.887, "lr": 0.003, "grad": 0.1156, "tokens": 107767296000, "tok_s": 157961.8}
|
| 246 |
+
{"step": 102820, "epoch": 0.653, "loss": 1.70861, "ppl": 5.521, "lr": 0.003, "grad": 0.1297, "tokens": 107788262400, "tok_s": 158809.5}
|
| 247 |
+
{"step": 102840, "epoch": 0.653, "loss": 1.75137, "ppl": 5.763, "lr": 0.003, "grad": 0.1032, "tokens": 107809228800, "tok_s": 158486.8}
|
| 248 |
+
{"step": 102860, "epoch": 0.654, "loss": 1.75927, "ppl": 5.808, "lr": 0.003, "grad": 0.1587, "tokens": 107830195200, "tok_s": 157893.8}
|
| 249 |
+
{"step": 102880, "epoch": 0.654, "loss": 1.66914, "ppl": 5.308, "lr": 0.003, "grad": 0.091, "tokens": 107851161600, "tok_s": 158847.2}
|
| 250 |
+
{"step": 102900, "epoch": 0.654, "loss": 1.75564, "ppl": 5.787, "lr": 0.003, "grad": 0.1678, "tokens": 107872128000, "tok_s": 158807.0}
|
| 251 |
+
{"step": 102920, "epoch": 0.654, "loss": 1.73966, "ppl": 5.695, "lr": 0.003, "grad": 0.1044, "tokens": 107893094400, "tok_s": 158762.7}
|
| 252 |
+
{"step": 102940, "epoch": 0.654, "loss": 1.72931, "ppl": 5.637, "lr": 0.003, "grad": 0.063, "tokens": 107914060800, "tok_s": 158773.1}
|
| 253 |
+
{"step": 102960, "epoch": 0.654, "loss": 1.70128, "ppl": 5.481, "lr": 0.003, "grad": 0.1274, "tokens": 107935027200, "tok_s": 158226.2}
|
| 254 |
+
{"step": 102980, "epoch": 0.654, "loss": 1.76752, "ppl": 5.856, "lr": 0.003, "grad": 0.1776, "tokens": 107955993600, "tok_s": 158645.0}
|
| 255 |
+
{"step": 103000, "epoch": 0.654, "loss": 1.78405, "ppl": 5.954, "lr": 0.003, "grad": 0.1763, "tokens": 107976960000, "tok_s": 158828.5}
|
| 256 |
+
{"step": 103000, "val_loss": 1.75443, "val_ppl": 5.78, "is_best": false}
|
logs/log_10400.jsonl
ADDED
|
@@ -0,0 +1,242 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 5600, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-08-24T20:26:47.358751"}
|
| 2 |
+
{"step": 5620, "epoch": 0.036, "loss": 1.89401, "ppl": 6.646, "lr": 0.003, "grad": 0.1475, "tokens": 5891558400, "tok_s": 172423.6}
|
| 3 |
+
{"step": 5640, "epoch": 0.036, "loss": 1.88982, "ppl": 6.618, "lr": 0.003, "grad": 0.1533, "tokens": 5912524800, "tok_s": 172391.2}
|
| 4 |
+
{"step": 5660, "epoch": 0.036, "loss": 1.86492, "ppl": 6.455, "lr": 0.003, "grad": 0.1109, "tokens": 5933491200, "tok_s": 172665.6}
|
| 5 |
+
{"step": 5680, "epoch": 0.036, "loss": 1.73942, "ppl": 5.694, "lr": 0.003, "grad": 0.1289, "tokens": 5954457600, "tok_s": 172312.1}
|
| 6 |
+
{"step": 5700, "epoch": 0.036, "loss": 1.90868, "ppl": 6.744, "lr": 0.003, "grad": 0.1413, "tokens": 5975424000, "tok_s": 171982.1}
|
| 7 |
+
{"step": 5720, "epoch": 0.036, "loss": 1.87684, "ppl": 6.533, "lr": 0.003, "grad": 0.1519, "tokens": 5996390400, "tok_s": 172224.6}
|
| 8 |
+
{"step": 5740, "epoch": 0.036, "loss": 1.88138, "ppl": 6.563, "lr": 0.003, "grad": 0.1208, "tokens": 6017356800, "tok_s": 172321.5}
|
| 9 |
+
{"step": 5760, "epoch": 0.037, "loss": 1.81272, "ppl": 6.127, "lr": 0.003, "grad": 0.135, "tokens": 6038323200, "tok_s": 171811.9}
|
| 10 |
+
{"step": 5780, "epoch": 0.037, "loss": 1.75523, "ppl": 5.785, "lr": 0.003, "grad": 0.141, "tokens": 6059289600, "tok_s": 172055.3}
|
| 11 |
+
{"step": 5800, "epoch": 0.037, "loss": 1.71455, "ppl": 5.554, "lr": 0.003, "grad": 0.1607, "tokens": 6080256000, "tok_s": 172358.4}
|
| 12 |
+
{"step": 5820, "epoch": 0.037, "loss": 1.92186, "ppl": 6.834, "lr": 0.003, "grad": 0.1442, "tokens": 6101222400, "tok_s": 172159.0}
|
| 13 |
+
{"step": 5840, "epoch": 0.037, "loss": 1.8498, "ppl": 6.359, "lr": 0.003, "grad": 0.1886, "tokens": 6122188800, "tok_s": 172499.7}
|
| 14 |
+
{"step": 5860, "epoch": 0.037, "loss": 1.8955, "ppl": 6.656, "lr": 0.003, "grad": 0.1725, "tokens": 6143155200, "tok_s": 172113.6}
|
| 15 |
+
{"step": 5880, "epoch": 0.037, "loss": 1.84048, "ppl": 6.3, "lr": 0.003, "grad": 0.1772, "tokens": 6164121600, "tok_s": 172116.7}
|
| 16 |
+
{"step": 5900, "epoch": 0.037, "loss": 1.89385, "ppl": 6.645, "lr": 0.003, "grad": 0.1908, "tokens": 6185088000, "tok_s": 172244.4}
|
| 17 |
+
{"step": 5920, "epoch": 0.038, "loss": 1.89896, "ppl": 6.679, "lr": 0.003, "grad": 0.1301, "tokens": 6206054400, "tok_s": 172297.3}
|
| 18 |
+
{"step": 5940, "epoch": 0.038, "loss": 1.86038, "ppl": 6.426, "lr": 0.003, "grad": 0.1851, "tokens": 6227020800, "tok_s": 172016.7}
|
| 19 |
+
{"step": 5960, "epoch": 0.038, "loss": 1.9033, "ppl": 6.708, "lr": 0.003, "grad": 0.1762, "tokens": 6247987200, "tok_s": 172125.7}
|
| 20 |
+
{"step": 5980, "epoch": 0.038, "loss": 1.8139, "ppl": 6.134, "lr": 0.003, "grad": 0.1718, "tokens": 6268953600, "tok_s": 171603.0}
|
| 21 |
+
{"step": 6000, "epoch": 0.038, "loss": 1.91966, "ppl": 6.819, "lr": 0.003, "grad": 0.2536, "tokens": 6289920000, "tok_s": 172569.3}
|
| 22 |
+
{"step": 6020, "epoch": 0.038, "loss": 1.89866, "ppl": 6.677, "lr": 0.003, "grad": 0.3241, "tokens": 6310886400, "tok_s": 172434.1}
|
| 23 |
+
{"step": 6040, "epoch": 0.038, "loss": 1.79733, "ppl": 6.034, "lr": 0.003, "grad": 0.3024, "tokens": 6331852800, "tok_s": 171797.7}
|
| 24 |
+
{"step": 6060, "epoch": 0.039, "loss": 1.94974, "ppl": 7.027, "lr": 0.003, "grad": 0.2176, "tokens": 6352819200, "tok_s": 172216.3}
|
| 25 |
+
{"step": 6080, "epoch": 0.039, "loss": 1.94145, "ppl": 6.969, "lr": 0.003, "grad": 0.2037, "tokens": 6373785600, "tok_s": 171761.6}
|
| 26 |
+
{"step": 6100, "epoch": 0.039, "loss": 2.05014, "ppl": 7.769, "lr": 0.003, "grad": 0.1884, "tokens": 6394752000, "tok_s": 171998.0}
|
| 27 |
+
{"step": 6120, "epoch": 0.039, "loss": 1.90102, "ppl": 6.693, "lr": 0.003, "grad": 0.2242, "tokens": 6415718400, "tok_s": 172128.2}
|
| 28 |
+
{"step": 6140, "epoch": 0.039, "loss": 1.78074, "ppl": 5.934, "lr": 0.003, "grad": 0.1605, "tokens": 6436684800, "tok_s": 172528.7}
|
| 29 |
+
{"step": 6160, "epoch": 0.039, "loss": 1.7984, "ppl": 6.04, "lr": 0.003, "grad": 0.1653, "tokens": 6457651200, "tok_s": 172345.3}
|
| 30 |
+
{"step": 6180, "epoch": 0.039, "loss": 1.83176, "ppl": 6.245, "lr": 0.003, "grad": 0.2649, "tokens": 6478617600, "tok_s": 172420.5}
|
| 31 |
+
{"step": 6200, "epoch": 0.039, "loss": 1.76457, "ppl": 5.839, "lr": 0.003, "grad": 0.1559, "tokens": 6499584000, "tok_s": 172080.5}
|
| 32 |
+
{"step": 6220, "epoch": 0.04, "loss": 1.84543, "ppl": 6.331, "lr": 0.003, "grad": 0.1601, "tokens": 6520550400, "tok_s": 172091.9}
|
| 33 |
+
{"step": 6240, "epoch": 0.04, "loss": 1.77896, "ppl": 5.924, "lr": 0.003, "grad": 0.1525, "tokens": 6541516800, "tok_s": 172220.8}
|
| 34 |
+
{"step": 6260, "epoch": 0.04, "loss": 1.9737, "ppl": 7.197, "lr": 0.003, "grad": 0.1522, "tokens": 6562483200, "tok_s": 172602.4}
|
| 35 |
+
{"step": 6280, "epoch": 0.04, "loss": 1.89591, "ppl": 6.659, "lr": 0.003, "grad": 0.175, "tokens": 6583449600, "tok_s": 171377.9}
|
| 36 |
+
{"step": 6300, "epoch": 0.04, "loss": 1.87053, "ppl": 6.492, "lr": 0.003, "grad": 0.168, "tokens": 6604416000, "tok_s": 172152.1}
|
| 37 |
+
{"step": 6320, "epoch": 0.04, "loss": 1.78815, "ppl": 5.978, "lr": 0.003, "grad": 0.1309, "tokens": 6625382400, "tok_s": 171855.1}
|
| 38 |
+
{"step": 6340, "epoch": 0.04, "loss": 1.82298, "ppl": 6.19, "lr": 0.003, "grad": 0.1382, "tokens": 6646348800, "tok_s": 172473.8}
|
| 39 |
+
{"step": 6360, "epoch": 0.04, "loss": 1.88883, "ppl": 6.612, "lr": 0.003, "grad": 0.1231, "tokens": 6667315200, "tok_s": 172367.4}
|
| 40 |
+
{"step": 6380, "epoch": 0.041, "loss": 1.79528, "ppl": 6.021, "lr": 0.003, "grad": 0.1204, "tokens": 6688281600, "tok_s": 172306.1}
|
| 41 |
+
{"step": 6400, "epoch": 0.041, "loss": 1.82022, "ppl": 6.173, "lr": 0.003, "grad": 0.1648, "tokens": 6709248000, "tok_s": 172418.4}
|
| 42 |
+
{"step": 6420, "epoch": 0.041, "loss": 1.86541, "ppl": 6.459, "lr": 0.003, "grad": 0.1445, "tokens": 6730214400, "tok_s": 172150.4}
|
| 43 |
+
{"step": 6440, "epoch": 0.041, "loss": 1.80127, "ppl": 6.057, "lr": 0.003, "grad": 0.1259, "tokens": 6751180800, "tok_s": 172063.4}
|
| 44 |
+
{"step": 6460, "epoch": 0.041, "loss": 1.87662, "ppl": 6.531, "lr": 0.003, "grad": 0.1333, "tokens": 6772147200, "tok_s": 172301.8}
|
| 45 |
+
{"step": 6480, "epoch": 0.041, "loss": 1.90716, "ppl": 6.734, "lr": 0.003, "grad": 0.1422, "tokens": 6793113600, "tok_s": 172108.8}
|
| 46 |
+
{"step": 6500, "epoch": 0.041, "loss": 1.55547, "ppl": 4.737, "lr": 0.003, "grad": 0.1131, "tokens": 6814080000, "tok_s": 172578.1}
|
| 47 |
+
{"step": 6520, "epoch": 0.041, "loss": 1.79381, "ppl": 6.012, "lr": 0.003, "grad": 0.131, "tokens": 6835046400, "tok_s": 172340.6}
|
| 48 |
+
{"step": 6540, "epoch": 0.042, "loss": 1.80078, "ppl": 6.054, "lr": 0.003, "grad": 0.1297, "tokens": 6856012800, "tok_s": 171621.8}
|
| 49 |
+
{"step": 6560, "epoch": 0.042, "loss": 1.89989, "ppl": 6.685, "lr": 0.003, "grad": 0.1153, "tokens": 6876979200, "tok_s": 172432.4}
|
| 50 |
+
{"step": 6580, "epoch": 0.042, "loss": 1.85268, "ppl": 6.377, "lr": 0.003, "grad": 0.1224, "tokens": 6897945600, "tok_s": 171961.7}
|
| 51 |
+
{"step": 6600, "epoch": 0.042, "loss": 2.00347, "ppl": 7.415, "lr": 0.003, "grad": 0.122, "tokens": 6918912000, "tok_s": 172470.6}
|
| 52 |
+
{"step": 6620, "epoch": 0.042, "loss": 1.84997, "ppl": 6.36, "lr": 0.003, "grad": 0.1132, "tokens": 6939878400, "tok_s": 172209.5}
|
| 53 |
+
{"step": 6640, "epoch": 0.042, "loss": 1.79555, "ppl": 6.023, "lr": 0.003, "grad": 0.1196, "tokens": 6960844800, "tok_s": 172386.6}
|
| 54 |
+
{"step": 6660, "epoch": 0.042, "loss": 1.88839, "ppl": 6.609, "lr": 0.003, "grad": 0.1119, "tokens": 6981811200, "tok_s": 172063.2}
|
| 55 |
+
{"step": 6680, "epoch": 0.042, "loss": 1.84115, "ppl": 6.304, "lr": 0.003, "grad": 0.115, "tokens": 7002777600, "tok_s": 172038.5}
|
| 56 |
+
{"step": 6700, "epoch": 0.043, "loss": 1.71087, "ppl": 5.534, "lr": 0.003, "grad": 0.1343, "tokens": 7023744000, "tok_s": 171878.0}
|
| 57 |
+
{"step": 6720, "epoch": 0.043, "loss": 1.98436, "ppl": 7.274, "lr": 0.003, "grad": 0.1648, "tokens": 7044710400, "tok_s": 171733.2}
|
| 58 |
+
{"step": 6740, "epoch": 0.043, "loss": 1.87767, "ppl": 6.538, "lr": 0.003, "grad": 0.1566, "tokens": 7065676800, "tok_s": 172161.7}
|
| 59 |
+
{"step": 6760, "epoch": 0.043, "loss": 1.8671, "ppl": 6.47, "lr": 0.003, "grad": 0.1213, "tokens": 7086643200, "tok_s": 172346.6}
|
| 60 |
+
{"step": 6780, "epoch": 0.043, "loss": 1.91033, "ppl": 6.755, "lr": 0.003, "grad": 0.103, "tokens": 7107609600, "tok_s": 171957.6}
|
| 61 |
+
{"step": 6800, "epoch": 0.043, "loss": 1.82497, "ppl": 6.203, "lr": 0.003, "grad": 0.1276, "tokens": 7128576000, "tok_s": 172410.9}
|
| 62 |
+
{"step": 6820, "epoch": 0.043, "loss": 1.89312, "ppl": 6.64, "lr": 0.003, "grad": 0.1141, "tokens": 7149542400, "tok_s": 171624.2}
|
| 63 |
+
{"step": 6840, "epoch": 0.043, "loss": 1.80573, "ppl": 6.084, "lr": 0.003, "grad": 0.1139, "tokens": 7170508800, "tok_s": 172004.7}
|
| 64 |
+
{"step": 6860, "epoch": 0.044, "loss": 1.83316, "ppl": 6.254, "lr": 0.003, "grad": 0.1196, "tokens": 7191475200, "tok_s": 172341.5}
|
| 65 |
+
{"step": 6880, "epoch": 0.044, "loss": 1.70114, "ppl": 5.48, "lr": 0.003, "grad": 0.1061, "tokens": 7212441600, "tok_s": 171644.3}
|
| 66 |
+
{"step": 6900, "epoch": 0.044, "loss": 1.91587, "ppl": 6.793, "lr": 0.003, "grad": 0.1391, "tokens": 7233408000, "tok_s": 172190.1}
|
| 67 |
+
{"step": 6920, "epoch": 0.044, "loss": 1.85771, "ppl": 6.409, "lr": 0.003, "grad": 0.1351, "tokens": 7254374400, "tok_s": 171879.8}
|
| 68 |
+
{"step": 6940, "epoch": 0.044, "loss": 1.90463, "ppl": 6.717, "lr": 0.003, "grad": 0.1333, "tokens": 7275340800, "tok_s": 171572.4}
|
| 69 |
+
{"step": 6960, "epoch": 0.044, "loss": 1.84908, "ppl": 6.354, "lr": 0.003, "grad": 0.1277, "tokens": 7296307200, "tok_s": 170683.1}
|
| 70 |
+
{"step": 6980, "epoch": 0.044, "loss": 1.95314, "ppl": 7.051, "lr": 0.003, "grad": 0.1248, "tokens": 7317273600, "tok_s": 172336.6}
|
| 71 |
+
{"step": 7000, "epoch": 0.044, "loss": 1.92508, "ppl": 6.856, "lr": 0.003, "grad": 0.1009, "tokens": 7338240000, "tok_s": 172253.4}
|
| 72 |
+
{"step": 7020, "epoch": 0.045, "loss": 1.90638, "ppl": 6.729, "lr": 0.003, "grad": 0.2081, "tokens": 7359206400, "tok_s": 172580.8}
|
| 73 |
+
{"step": 7040, "epoch": 0.045, "loss": 1.84036, "ppl": 6.299, "lr": 0.003, "grad": 0.179, "tokens": 7380172800, "tok_s": 172326.9}
|
| 74 |
+
{"step": 7060, "epoch": 0.045, "loss": 1.88125, "ppl": 6.562, "lr": 0.003, "grad": 0.1712, "tokens": 7401139200, "tok_s": 171434.4}
|
| 75 |
+
{"step": 7080, "epoch": 0.045, "loss": 1.93449, "ppl": 6.92, "lr": 0.003, "grad": 0.1701, "tokens": 7422105600, "tok_s": 172148.4}
|
| 76 |
+
{"step": 7100, "epoch": 0.045, "loss": 1.88842, "ppl": 6.609, "lr": 0.003, "grad": 0.1622, "tokens": 7443072000, "tok_s": 171728.8}
|
| 77 |
+
{"step": 7120, "epoch": 0.045, "loss": 1.89506, "ppl": 6.653, "lr": 0.003, "grad": 0.1442, "tokens": 7464038400, "tok_s": 171709.4}
|
| 78 |
+
{"step": 7140, "epoch": 0.045, "loss": 1.81442, "ppl": 6.138, "lr": 0.003, "grad": 0.1012, "tokens": 7485004800, "tok_s": 172000.4}
|
| 79 |
+
{"step": 7160, "epoch": 0.045, "loss": 1.89673, "ppl": 6.664, "lr": 0.003, "grad": 0.1156, "tokens": 7505971200, "tok_s": 172271.1}
|
| 80 |
+
{"step": 7180, "epoch": 0.046, "loss": 1.68992, "ppl": 5.419, "lr": 0.003, "grad": 0.0992, "tokens": 7526937600, "tok_s": 171761.1}
|
| 81 |
+
{"step": 7200, "epoch": 0.046, "loss": 1.87061, "ppl": 6.492, "lr": 0.003, "grad": 0.1219, "tokens": 7547904000, "tok_s": 171115.0}
|
| 82 |
+
{"step": 7220, "epoch": 0.046, "loss": 1.87561, "ppl": 6.525, "lr": 0.003, "grad": 0.1354, "tokens": 7568870400, "tok_s": 171789.1}
|
| 83 |
+
{"step": 7240, "epoch": 0.046, "loss": 1.83861, "ppl": 6.288, "lr": 0.003, "grad": 0.1465, "tokens": 7589836800, "tok_s": 172358.8}
|
| 84 |
+
{"step": 7260, "epoch": 0.046, "loss": 1.89295, "ppl": 6.639, "lr": 0.003, "grad": 0.1205, "tokens": 7610803200, "tok_s": 172023.4}
|
| 85 |
+
{"step": 7280, "epoch": 0.046, "loss": 1.86113, "ppl": 6.431, "lr": 0.003, "grad": 0.142, "tokens": 7631769600, "tok_s": 172462.7}
|
| 86 |
+
{"step": 7300, "epoch": 0.046, "loss": 1.83469, "ppl": 6.263, "lr": 0.003, "grad": 0.1425, "tokens": 7652736000, "tok_s": 172271.1}
|
| 87 |
+
{"step": 7320, "epoch": 0.047, "loss": 1.80886, "ppl": 6.104, "lr": 0.003, "grad": 0.1249, "tokens": 7673702400, "tok_s": 171820.2}
|
| 88 |
+
{"step": 7340, "epoch": 0.047, "loss": 1.85399, "ppl": 6.385, "lr": 0.003, "grad": 0.1253, "tokens": 7694668800, "tok_s": 172312.4}
|
| 89 |
+
{"step": 7360, "epoch": 0.047, "loss": 1.73878, "ppl": 5.69, "lr": 0.003, "grad": 0.1094, "tokens": 7715635200, "tok_s": 171586.6}
|
| 90 |
+
{"step": 7380, "epoch": 0.047, "loss": 1.82556, "ppl": 6.206, "lr": 0.003, "grad": 0.1662, "tokens": 7736601600, "tok_s": 172114.7}
|
| 91 |
+
{"step": 7400, "epoch": 0.047, "loss": 1.83839, "ppl": 6.286, "lr": 0.003, "grad": 0.1087, "tokens": 7757568000, "tok_s": 172361.2}
|
| 92 |
+
{"step": 7420, "epoch": 0.047, "loss": 1.86267, "ppl": 6.441, "lr": 0.003, "grad": 0.1071, "tokens": 7778534400, "tok_s": 172436.3}
|
| 93 |
+
{"step": 7440, "epoch": 0.047, "loss": 1.88314, "ppl": 6.574, "lr": 0.003, "grad": 0.1298, "tokens": 7799500800, "tok_s": 171688.0}
|
| 94 |
+
{"step": 7460, "epoch": 0.047, "loss": 1.89334, "ppl": 6.641, "lr": 0.003, "grad": 0.0951, "tokens": 7820467200, "tok_s": 172167.4}
|
| 95 |
+
{"step": 7480, "epoch": 0.048, "loss": 1.87341, "ppl": 6.51, "lr": 0.003, "grad": 0.1033, "tokens": 7841433600, "tok_s": 172553.6}
|
| 96 |
+
{"step": 7500, "epoch": 0.048, "loss": 1.85843, "ppl": 6.414, "lr": 0.003, "grad": 0.109, "tokens": 7862400000, "tok_s": 171157.7}
|
| 97 |
+
{"step": 7520, "epoch": 0.048, "loss": 1.88284, "ppl": 6.572, "lr": 0.003, "grad": 0.1398, "tokens": 7883366400, "tok_s": 172375.0}
|
| 98 |
+
{"step": 7540, "epoch": 0.048, "loss": 1.83192, "ppl": 6.246, "lr": 0.003, "grad": 0.1106, "tokens": 7904332800, "tok_s": 171879.8}
|
| 99 |
+
{"step": 7560, "epoch": 0.048, "loss": 1.85224, "ppl": 6.374, "lr": 0.003, "grad": 0.0898, "tokens": 7925299200, "tok_s": 172265.6}
|
| 100 |
+
{"step": 7580, "epoch": 0.048, "loss": 1.89837, "ppl": 6.675, "lr": 0.003, "grad": 0.1092, "tokens": 7946265600, "tok_s": 172496.0}
|
| 101 |
+
{"step": 7600, "epoch": 0.048, "loss": 1.82826, "ppl": 6.223, "lr": 0.003, "grad": 0.1111, "tokens": 7967232000, "tok_s": 172317.9}
|
| 102 |
+
{"step": 7620, "epoch": 0.048, "loss": 1.86228, "ppl": 6.438, "lr": 0.003, "grad": 0.1209, "tokens": 7988198400, "tok_s": 172124.9}
|
| 103 |
+
{"step": 7640, "epoch": 0.049, "loss": 1.84979, "ppl": 6.358, "lr": 0.003, "grad": 0.1101, "tokens": 8009164800, "tok_s": 172126.9}
|
| 104 |
+
{"step": 7660, "epoch": 0.049, "loss": 1.78897, "ppl": 5.983, "lr": 0.003, "grad": 0.1003, "tokens": 8030131200, "tok_s": 172490.0}
|
| 105 |
+
{"step": 7680, "epoch": 0.049, "loss": 1.86442, "ppl": 6.452, "lr": 0.003, "grad": 0.1259, "tokens": 8051097600, "tok_s": 172338.3}
|
| 106 |
+
{"step": 7700, "epoch": 0.049, "loss": 1.85516, "ppl": 6.393, "lr": 0.003, "grad": 0.1012, "tokens": 8072064000, "tok_s": 172427.1}
|
| 107 |
+
{"step": 7720, "epoch": 0.049, "loss": 1.92247, "ppl": 6.838, "lr": 0.003, "grad": 0.1195, "tokens": 8093030400, "tok_s": 171843.2}
|
| 108 |
+
{"step": 7740, "epoch": 0.049, "loss": 1.87022, "ppl": 6.49, "lr": 0.003, "grad": 0.1021, "tokens": 8113996800, "tok_s": 172345.0}
|
| 109 |
+
{"step": 7760, "epoch": 0.049, "loss": 1.82067, "ppl": 6.176, "lr": 0.003, "grad": 0.1124, "tokens": 8134963200, "tok_s": 171672.3}
|
| 110 |
+
{"step": 7780, "epoch": 0.049, "loss": 1.84692, "ppl": 6.34, "lr": 0.003, "grad": 0.0817, "tokens": 8155929600, "tok_s": 172506.2}
|
| 111 |
+
{"step": 7800, "epoch": 0.05, "loss": 1.90304, "ppl": 6.706, "lr": 0.003, "grad": 0.1273, "tokens": 8176896000, "tok_s": 172124.8}
|
| 112 |
+
{"step": 7820, "epoch": 0.05, "loss": 1.80188, "ppl": 6.061, "lr": 0.003, "grad": 0.0954, "tokens": 8197862400, "tok_s": 171856.6}
|
| 113 |
+
{"step": 7840, "epoch": 0.05, "loss": 1.84283, "ppl": 6.314, "lr": 0.003, "grad": 0.1032, "tokens": 8218828800, "tok_s": 172226.0}
|
| 114 |
+
{"step": 7860, "epoch": 0.05, "loss": 1.75843, "ppl": 5.803, "lr": 0.003, "grad": 0.1042, "tokens": 8239795200, "tok_s": 172036.5}
|
| 115 |
+
{"step": 7880, "epoch": 0.05, "loss": 1.85723, "ppl": 6.406, "lr": 0.003, "grad": 0.1031, "tokens": 8260761600, "tok_s": 171984.9}
|
| 116 |
+
{"step": 7900, "epoch": 0.05, "loss": 1.88135, "ppl": 6.562, "lr": 0.003, "grad": 0.1251, "tokens": 8281728000, "tok_s": 172555.1}
|
| 117 |
+
{"step": 7920, "epoch": 0.05, "loss": 1.763, "ppl": 5.83, "lr": 0.003, "grad": 0.1093, "tokens": 8302694400, "tok_s": 172457.0}
|
| 118 |
+
{"step": 7940, "epoch": 0.05, "loss": 1.72324, "ppl": 5.603, "lr": 0.003, "grad": 0.0986, "tokens": 8323660800, "tok_s": 172549.3}
|
| 119 |
+
{"step": 7960, "epoch": 0.051, "loss": 1.85482, "ppl": 6.391, "lr": 0.003, "grad": 0.106, "tokens": 8344627200, "tok_s": 171934.5}
|
| 120 |
+
{"step": 7980, "epoch": 0.051, "loss": 1.82962, "ppl": 6.231, "lr": 0.003, "grad": 0.1232, "tokens": 8365593600, "tok_s": 172051.2}
|
| 121 |
+
{"step": 8000, "epoch": 0.051, "loss": 1.74266, "ppl": 5.713, "lr": 0.003, "grad": 0.0821, "tokens": 8386560000, "tok_s": 172163.1}
|
| 122 |
+
{"step": 8020, "epoch": 0.051, "loss": 1.75257, "ppl": 5.769, "lr": 0.003, "grad": 0.0941, "tokens": 8407526400, "tok_s": 172073.7}
|
| 123 |
+
{"step": 8040, "epoch": 0.051, "loss": 1.9464, "ppl": 7.003, "lr": 0.003, "grad": 0.0928, "tokens": 8428492800, "tok_s": 172031.2}
|
| 124 |
+
{"step": 8060, "epoch": 0.051, "loss": 1.74081, "ppl": 5.702, "lr": 0.003, "grad": 0.0995, "tokens": 8449459200, "tok_s": 171927.7}
|
| 125 |
+
{"step": 8080, "epoch": 0.051, "loss": 1.8125, "ppl": 6.126, "lr": 0.003, "grad": 0.0872, "tokens": 8470425600, "tok_s": 172138.1}
|
| 126 |
+
{"step": 8100, "epoch": 0.051, "loss": 1.78829, "ppl": 5.979, "lr": 0.003, "grad": 0.085, "tokens": 8491392000, "tok_s": 172310.2}
|
| 127 |
+
{"step": 8120, "epoch": 0.052, "loss": 1.80545, "ppl": 6.083, "lr": 0.003, "grad": 0.0778, "tokens": 8512358400, "tok_s": 172157.1}
|
| 128 |
+
{"step": 8140, "epoch": 0.052, "loss": 1.80498, "ppl": 6.08, "lr": 0.003, "grad": 0.0848, "tokens": 8533324800, "tok_s": 172272.6}
|
| 129 |
+
{"step": 8160, "epoch": 0.052, "loss": 1.90402, "ppl": 6.713, "lr": 0.003, "grad": 0.0912, "tokens": 8554291200, "tok_s": 171813.9}
|
| 130 |
+
{"step": 8180, "epoch": 0.052, "loss": 1.84347, "ppl": 6.318, "lr": 0.003, "grad": 0.1, "tokens": 8575257600, "tok_s": 172349.8}
|
| 131 |
+
{"step": 8200, "epoch": 0.052, "loss": 1.86355, "ppl": 6.447, "lr": 0.003, "grad": 0.0852, "tokens": 8596224000, "tok_s": 172611.2}
|
| 132 |
+
{"step": 8220, "epoch": 0.052, "loss": 1.82987, "ppl": 6.233, "lr": 0.003, "grad": 0.1063, "tokens": 8617190400, "tok_s": 172491.7}
|
| 133 |
+
{"step": 8240, "epoch": 0.052, "loss": 1.86451, "ppl": 6.453, "lr": 0.003, "grad": 0.0696, "tokens": 8638156800, "tok_s": 172551.1}
|
| 134 |
+
{"step": 8260, "epoch": 0.052, "loss": 1.73045, "ppl": 5.643, "lr": 0.003, "grad": 0.0924, "tokens": 8659123200, "tok_s": 171358.2}
|
| 135 |
+
{"step": 8280, "epoch": 0.053, "loss": 1.8337, "ppl": 6.257, "lr": 0.003, "grad": 0.1329, "tokens": 8680089600, "tok_s": 171700.2}
|
| 136 |
+
{"step": 8300, "epoch": 0.053, "loss": 1.78923, "ppl": 5.985, "lr": 0.003, "grad": 0.1016, "tokens": 8701056000, "tok_s": 172452.4}
|
| 137 |
+
{"step": 8320, "epoch": 0.053, "loss": 1.87597, "ppl": 6.527, "lr": 0.003, "grad": 0.0835, "tokens": 8722022400, "tok_s": 172471.2}
|
| 138 |
+
{"step": 8340, "epoch": 0.053, "loss": 1.69222, "ppl": 5.432, "lr": 0.003, "grad": 0.0908, "tokens": 8742988800, "tok_s": 171806.9}
|
| 139 |
+
{"step": 8360, "epoch": 0.053, "loss": 1.86699, "ppl": 6.469, "lr": 0.003, "grad": 0.1162, "tokens": 8763955200, "tok_s": 172203.9}
|
| 140 |
+
{"step": 8380, "epoch": 0.053, "loss": 1.87179, "ppl": 6.5, "lr": 0.003, "grad": 0.1034, "tokens": 8784921600, "tok_s": 172500.0}
|
| 141 |
+
{"step": 8400, "epoch": 0.053, "loss": 1.84444, "ppl": 6.325, "lr": 0.003, "grad": 0.1051, "tokens": 8805888000, "tok_s": 172418.1}
|
| 142 |
+
{"step": 8420, "epoch": 0.053, "loss": 1.86837, "ppl": 6.478, "lr": 0.003, "grad": 0.0965, "tokens": 8826854400, "tok_s": 172611.0}
|
| 143 |
+
{"step": 8440, "epoch": 0.054, "loss": 1.87294, "ppl": 6.507, "lr": 0.003, "grad": 0.1586, "tokens": 8847820800, "tok_s": 172284.7}
|
| 144 |
+
{"step": 8460, "epoch": 0.054, "loss": 1.89496, "ppl": 6.652, "lr": 0.003, "grad": 0.1718, "tokens": 8868787200, "tok_s": 171902.6}
|
| 145 |
+
{"step": 8480, "epoch": 0.054, "loss": 1.79839, "ppl": 6.04, "lr": 0.003, "grad": 0.1389, "tokens": 8889753600, "tok_s": 171725.7}
|
| 146 |
+
{"step": 8500, "epoch": 0.054, "loss": 1.85882, "ppl": 6.416, "lr": 0.003, "grad": 0.1386, "tokens": 8910720000, "tok_s": 172244.5}
|
| 147 |
+
{"step": 8520, "epoch": 0.054, "loss": 1.85505, "ppl": 6.392, "lr": 0.003, "grad": 0.1646, "tokens": 8931686400, "tok_s": 172313.9}
|
| 148 |
+
{"step": 8540, "epoch": 0.054, "loss": 1.82156, "ppl": 6.182, "lr": 0.003, "grad": 0.1333, "tokens": 8952652800, "tok_s": 172722.1}
|
| 149 |
+
{"step": 8560, "epoch": 0.054, "loss": 1.8767, "ppl": 6.532, "lr": 0.003, "grad": 0.1457, "tokens": 8973619200, "tok_s": 172229.8}
|
| 150 |
+
{"step": 8580, "epoch": 0.055, "loss": 1.8513, "ppl": 6.368, "lr": 0.003, "grad": 0.1414, "tokens": 8994585600, "tok_s": 171866.3}
|
| 151 |
+
{"step": 8600, "epoch": 0.055, "loss": 1.85381, "ppl": 6.384, "lr": 0.003, "grad": 0.1125, "tokens": 9015552000, "tok_s": 171827.6}
|
| 152 |
+
{"step": 8620, "epoch": 0.055, "loss": 1.785, "ppl": 5.96, "lr": 0.003, "grad": 0.0976, "tokens": 9036518400, "tok_s": 171860.5}
|
| 153 |
+
{"step": 8640, "epoch": 0.055, "loss": 1.84067, "ppl": 6.301, "lr": 0.003, "grad": 0.1201, "tokens": 9057484800, "tok_s": 172509.3}
|
| 154 |
+
{"step": 8660, "epoch": 0.055, "loss": 1.82752, "ppl": 6.218, "lr": 0.003, "grad": 0.1317, "tokens": 9078451200, "tok_s": 172536.9}
|
| 155 |
+
{"step": 8680, "epoch": 0.055, "loss": 1.86607, "ppl": 6.463, "lr": 0.003, "grad": 0.1269, "tokens": 9099417600, "tok_s": 172482.3}
|
| 156 |
+
{"step": 8700, "epoch": 0.055, "loss": 1.86252, "ppl": 6.44, "lr": 0.003, "grad": 0.093, "tokens": 9120384000, "tok_s": 171939.4}
|
| 157 |
+
{"step": 8720, "epoch": 0.055, "loss": 1.82722, "ppl": 6.217, "lr": 0.003, "grad": 0.1216, "tokens": 9141350400, "tok_s": 171792.0}
|
| 158 |
+
{"step": 8740, "epoch": 0.056, "loss": 1.80937, "ppl": 6.107, "lr": 0.003, "grad": 0.0922, "tokens": 9162316800, "tok_s": 171785.4}
|
| 159 |
+
{"step": 8760, "epoch": 0.056, "loss": 1.82316, "ppl": 6.191, "lr": 0.003, "grad": 0.0844, "tokens": 9183283200, "tok_s": 172360.4}
|
| 160 |
+
{"step": 8780, "epoch": 0.056, "loss": 1.76226, "ppl": 5.826, "lr": 0.003, "grad": 0.0728, "tokens": 9204249600, "tok_s": 171908.5}
|
| 161 |
+
{"step": 8800, "epoch": 0.056, "loss": 1.83141, "ppl": 6.243, "lr": 0.003, "grad": 0.1175, "tokens": 9225216000, "tok_s": 172636.3}
|
| 162 |
+
{"step": 8820, "epoch": 0.056, "loss": 1.81396, "ppl": 6.135, "lr": 0.003, "grad": 0.0975, "tokens": 9246182400, "tok_s": 171878.4}
|
| 163 |
+
{"step": 8840, "epoch": 0.056, "loss": 1.816, "ppl": 6.147, "lr": 0.003, "grad": 0.1176, "tokens": 9267148800, "tok_s": 172231.6}
|
| 164 |
+
{"step": 8860, "epoch": 0.056, "loss": 1.83258, "ppl": 6.25, "lr": 0.003, "grad": 0.1121, "tokens": 9288115200, "tok_s": 171571.6}
|
| 165 |
+
{"step": 8880, "epoch": 0.056, "loss": 1.85585, "ppl": 6.397, "lr": 0.003, "grad": 0.075, "tokens": 9309081600, "tok_s": 171564.4}
|
| 166 |
+
{"step": 8900, "epoch": 0.057, "loss": 1.90797, "ppl": 6.739, "lr": 0.003, "grad": 0.0969, "tokens": 9330048000, "tok_s": 172228.0}
|
| 167 |
+
{"step": 8920, "epoch": 0.057, "loss": 1.80743, "ppl": 6.095, "lr": 0.003, "grad": 0.0883, "tokens": 9351014400, "tok_s": 172046.4}
|
| 168 |
+
{"step": 8940, "epoch": 0.057, "loss": 1.83212, "ppl": 6.247, "lr": 0.003, "grad": 0.0862, "tokens": 9371980800, "tok_s": 172277.2}
|
| 169 |
+
{"step": 8960, "epoch": 0.057, "loss": 1.82561, "ppl": 6.207, "lr": 0.003, "grad": 0.1031, "tokens": 9392947200, "tok_s": 172462.1}
|
| 170 |
+
{"step": 8980, "epoch": 0.057, "loss": 1.77462, "ppl": 5.898, "lr": 0.003, "grad": 0.1079, "tokens": 9413913600, "tok_s": 172237.7}
|
| 171 |
+
{"step": 9000, "epoch": 0.057, "loss": 1.79914, "ppl": 6.044, "lr": 0.003, "grad": 0.1313, "tokens": 9434880000, "tok_s": 171620.8}
|
| 172 |
+
{"step": 9020, "epoch": 0.057, "loss": 1.82248, "ppl": 6.187, "lr": 0.003, "grad": 0.1004, "tokens": 9455846400, "tok_s": 172120.9}
|
| 173 |
+
{"step": 9040, "epoch": 0.057, "loss": 1.81134, "ppl": 6.119, "lr": 0.003, "grad": 0.0991, "tokens": 9476812800, "tok_s": 171701.3}
|
| 174 |
+
{"step": 9060, "epoch": 0.058, "loss": 1.82493, "ppl": 6.202, "lr": 0.003, "grad": 0.0959, "tokens": 9497779200, "tok_s": 170829.9}
|
| 175 |
+
{"step": 9080, "epoch": 0.058, "loss": 1.73451, "ppl": 5.666, "lr": 0.003, "grad": 0.1279, "tokens": 9518745600, "tok_s": 170958.1}
|
| 176 |
+
{"step": 9100, "epoch": 0.058, "loss": 1.95408, "ppl": 7.057, "lr": 0.003, "grad": 0.1247, "tokens": 9539712000, "tok_s": 171356.2}
|
| 177 |
+
{"step": 9120, "epoch": 0.058, "loss": 1.87205, "ppl": 6.502, "lr": 0.003, "grad": 0.1248, "tokens": 9560678400, "tok_s": 170834.9}
|
| 178 |
+
{"step": 9140, "epoch": 0.058, "loss": 1.7774, "ppl": 5.914, "lr": 0.003, "grad": 0.073, "tokens": 9581644800, "tok_s": 171393.9}
|
| 179 |
+
{"step": 9160, "epoch": 0.058, "loss": 1.94593, "ppl": 7.0, "lr": 0.003, "grad": 0.1124, "tokens": 9602611200, "tok_s": 171717.3}
|
| 180 |
+
{"step": 9180, "epoch": 0.058, "loss": 1.82195, "ppl": 6.184, "lr": 0.003, "grad": 0.1105, "tokens": 9623577600, "tok_s": 171358.1}
|
| 181 |
+
{"step": 9200, "epoch": 0.058, "loss": 1.90735, "ppl": 6.735, "lr": 0.003, "grad": 0.1057, "tokens": 9644544000, "tok_s": 171188.8}
|
| 182 |
+
{"step": 9220, "epoch": 0.059, "loss": 1.82142, "ppl": 6.181, "lr": 0.003, "grad": 0.0862, "tokens": 9665510400, "tok_s": 172099.0}
|
| 183 |
+
{"step": 9240, "epoch": 0.059, "loss": 1.83647, "ppl": 6.274, "lr": 0.003, "grad": 0.126, "tokens": 9686476800, "tok_s": 170214.3}
|
| 184 |
+
{"step": 9260, "epoch": 0.059, "loss": 1.71346, "ppl": 5.548, "lr": 0.003, "grad": 0.0838, "tokens": 9707443200, "tok_s": 171078.0}
|
| 185 |
+
{"step": 9280, "epoch": 0.059, "loss": 1.53666, "ppl": 4.649, "lr": 0.003, "grad": 0.0907, "tokens": 9728409600, "tok_s": 170537.0}
|
| 186 |
+
{"step": 9300, "epoch": 0.059, "loss": 1.88308, "ppl": 6.574, "lr": 0.003, "grad": 0.1251, "tokens": 9749376000, "tok_s": 170940.8}
|
| 187 |
+
{"step": 9320, "epoch": 0.059, "loss": 1.78609, "ppl": 5.966, "lr": 0.003, "grad": 0.0798, "tokens": 9770342400, "tok_s": 171622.9}
|
| 188 |
+
{"step": 9340, "epoch": 0.059, "loss": 1.79752, "ppl": 6.035, "lr": 0.003, "grad": 0.1185, "tokens": 9791308800, "tok_s": 171543.1}
|
| 189 |
+
{"step": 9360, "epoch": 0.059, "loss": 1.82848, "ppl": 6.224, "lr": 0.003, "grad": 0.094, "tokens": 9812275200, "tok_s": 171906.4}
|
| 190 |
+
{"step": 9380, "epoch": 0.06, "loss": 1.78883, "ppl": 5.982, "lr": 0.003, "grad": 0.1194, "tokens": 9833241600, "tok_s": 170672.4}
|
| 191 |
+
{"step": 9400, "epoch": 0.06, "loss": 1.84689, "ppl": 6.34, "lr": 0.003, "grad": 0.0881, "tokens": 9854208000, "tok_s": 170899.4}
|
| 192 |
+
{"step": 9420, "epoch": 0.06, "loss": 1.83359, "ppl": 6.256, "lr": 0.003, "grad": 0.1055, "tokens": 9875174400, "tok_s": 171838.4}
|
| 193 |
+
{"step": 9440, "epoch": 0.06, "loss": 1.84964, "ppl": 6.358, "lr": 0.003, "grad": 0.0935, "tokens": 9896140800, "tok_s": 169959.4}
|
| 194 |
+
{"step": 9460, "epoch": 0.06, "loss": 1.82368, "ppl": 6.195, "lr": 0.003, "grad": 0.0892, "tokens": 9917107200, "tok_s": 171936.5}
|
| 195 |
+
{"step": 9480, "epoch": 0.06, "loss": 1.82694, "ppl": 6.215, "lr": 0.003, "grad": 0.0874, "tokens": 9938073600, "tok_s": 171924.7}
|
| 196 |
+
{"step": 9500, "epoch": 0.06, "loss": 1.81411, "ppl": 6.136, "lr": 0.003, "grad": 0.0695, "tokens": 9959040000, "tok_s": 171378.2}
|
| 197 |
+
{"step": 9520, "epoch": 0.06, "loss": 1.81382, "ppl": 6.134, "lr": 0.003, "grad": 0.1105, "tokens": 9980006400, "tok_s": 170597.2}
|
| 198 |
+
{"step": 9540, "epoch": 0.061, "loss": 1.82108, "ppl": 6.179, "lr": 0.003, "grad": 0.1012, "tokens": 10000972800, "tok_s": 171612.4}
|
| 199 |
+
{"step": 9560, "epoch": 0.061, "loss": 1.85135, "ppl": 6.368, "lr": 0.003, "grad": 0.0934, "tokens": 10021939200, "tok_s": 171309.8}
|
| 200 |
+
{"step": 9580, "epoch": 0.061, "loss": 1.82062, "ppl": 6.176, "lr": 0.003, "grad": 0.0872, "tokens": 10042905600, "tok_s": 171074.0}
|
| 201 |
+
{"step": 9600, "epoch": 0.061, "loss": 1.84671, "ppl": 6.339, "lr": 0.003, "grad": 0.1095, "tokens": 10063872000, "tok_s": 171578.6}
|
| 202 |
+
{"step": 9620, "epoch": 0.061, "loss": 1.79717, "ppl": 6.033, "lr": 0.003, "grad": 0.109, "tokens": 10084838400, "tok_s": 171401.5}
|
| 203 |
+
{"step": 9640, "epoch": 0.061, "loss": 1.85177, "ppl": 6.371, "lr": 0.003, "grad": 0.0763, "tokens": 10105804800, "tok_s": 170936.9}
|
| 204 |
+
{"step": 9660, "epoch": 0.061, "loss": 1.79851, "ppl": 6.041, "lr": 0.003, "grad": 0.0963, "tokens": 10126771200, "tok_s": 170599.7}
|
| 205 |
+
{"step": 9680, "epoch": 0.062, "loss": 1.86152, "ppl": 6.434, "lr": 0.003, "grad": 0.0833, "tokens": 10147737600, "tok_s": 171423.3}
|
| 206 |
+
{"step": 9700, "epoch": 0.062, "loss": 1.83529, "ppl": 6.267, "lr": 0.003, "grad": 0.097, "tokens": 10168704000, "tok_s": 171871.8}
|
| 207 |
+
{"step": 9720, "epoch": 0.062, "loss": 1.86135, "ppl": 6.432, "lr": 0.003, "grad": 0.1075, "tokens": 10189670400, "tok_s": 172170.4}
|
| 208 |
+
{"step": 9740, "epoch": 0.062, "loss": 1.7917, "ppl": 6.0, "lr": 0.003, "grad": 0.0795, "tokens": 10210636800, "tok_s": 170776.4}
|
| 209 |
+
{"step": 9760, "epoch": 0.062, "loss": 1.8366, "ppl": 6.275, "lr": 0.003, "grad": 0.0632, "tokens": 10231603200, "tok_s": 171913.6}
|
| 210 |
+
{"step": 9780, "epoch": 0.062, "loss": 1.84815, "ppl": 6.348, "lr": 0.003, "grad": 0.1021, "tokens": 10252569600, "tok_s": 171900.1}
|
| 211 |
+
{"step": 9800, "epoch": 0.062, "loss": 1.87961, "ppl": 6.551, "lr": 0.003, "grad": 0.0899, "tokens": 10273536000, "tok_s": 171114.3}
|
| 212 |
+
{"step": 9820, "epoch": 0.062, "loss": 1.87279, "ppl": 6.506, "lr": 0.003, "grad": 0.1131, "tokens": 10294502400, "tok_s": 170682.3}
|
| 213 |
+
{"step": 9840, "epoch": 0.063, "loss": 1.84351, "ppl": 6.319, "lr": 0.003, "grad": 0.067, "tokens": 10315468800, "tok_s": 171131.2}
|
| 214 |
+
{"step": 9860, "epoch": 0.063, "loss": 1.79461, "ppl": 6.017, "lr": 0.003, "grad": 0.1296, "tokens": 10336435200, "tok_s": 171855.0}
|
| 215 |
+
{"step": 9880, "epoch": 0.063, "loss": 1.88072, "ppl": 6.558, "lr": 0.003, "grad": 0.0863, "tokens": 10357401600, "tok_s": 172377.7}
|
| 216 |
+
{"step": 9900, "epoch": 0.063, "loss": 1.84683, "ppl": 6.34, "lr": 0.003, "grad": 0.0831, "tokens": 10378368000, "tok_s": 171386.3}
|
| 217 |
+
{"step": 9920, "epoch": 0.063, "loss": 1.79613, "ppl": 6.026, "lr": 0.003, "grad": 0.068, "tokens": 10399334400, "tok_s": 171319.0}
|
| 218 |
+
{"step": 9940, "epoch": 0.063, "loss": 1.85264, "ppl": 6.377, "lr": 0.003, "grad": 0.0865, "tokens": 10420300800, "tok_s": 171354.1}
|
| 219 |
+
{"step": 9960, "epoch": 0.063, "loss": 1.79011, "ppl": 5.99, "lr": 0.003, "grad": 0.1058, "tokens": 10441267200, "tok_s": 170759.2}
|
| 220 |
+
{"step": 9980, "epoch": 0.063, "loss": 1.84251, "ppl": 6.312, "lr": 0.003, "grad": 0.0633, "tokens": 10462233600, "tok_s": 171322.2}
|
| 221 |
+
{"step": 10000, "epoch": 0.064, "loss": 1.72274, "ppl": 5.6, "lr": 0.003, "grad": 0.0767, "tokens": 10483200000, "tok_s": 170980.2}
|
| 222 |
+
{"step": 10020, "epoch": 0.064, "loss": 1.83397, "ppl": 6.259, "lr": 0.003, "grad": 0.1057, "tokens": 10504166400, "tok_s": 171467.4}
|
| 223 |
+
{"step": 10040, "epoch": 0.064, "loss": 1.8293, "ppl": 6.23, "lr": 0.003, "grad": 0.1032, "tokens": 10525132800, "tok_s": 170979.9}
|
| 224 |
+
{"step": 10060, "epoch": 0.064, "loss": 1.84083, "ppl": 6.302, "lr": 0.003, "grad": 0.0734, "tokens": 10546099200, "tok_s": 171756.1}
|
| 225 |
+
{"step": 10080, "epoch": 0.064, "loss": 1.99646, "ppl": 7.363, "lr": 0.003, "grad": 0.0964, "tokens": 10567065600, "tok_s": 171208.8}
|
| 226 |
+
{"step": 10100, "epoch": 0.064, "loss": 1.87124, "ppl": 6.496, "lr": 0.003, "grad": 0.0894, "tokens": 10588032000, "tok_s": 171178.1}
|
| 227 |
+
{"step": 10120, "epoch": 0.064, "loss": 1.81989, "ppl": 6.171, "lr": 0.003, "grad": 0.0819, "tokens": 10608998400, "tok_s": 172188.6}
|
| 228 |
+
{"step": 10140, "epoch": 0.064, "loss": 1.81398, "ppl": 6.135, "lr": 0.003, "grad": 0.0946, "tokens": 10629964800, "tok_s": 171994.1}
|
| 229 |
+
{"step": 10160, "epoch": 0.065, "loss": 1.8898, "ppl": 6.618, "lr": 0.003, "grad": 0.0832, "tokens": 10650931200, "tok_s": 171382.3}
|
| 230 |
+
{"step": 10180, "epoch": 0.065, "loss": 1.80106, "ppl": 6.056, "lr": 0.003, "grad": 0.113, "tokens": 10671897600, "tok_s": 172109.2}
|
| 231 |
+
{"step": 10200, "epoch": 0.065, "loss": 1.83142, "ppl": 6.243, "lr": 0.003, "grad": 0.0787, "tokens": 10692864000, "tok_s": 172304.2}
|
| 232 |
+
{"step": 10220, "epoch": 0.065, "loss": 1.84482, "ppl": 6.327, "lr": 0.003, "grad": 0.126, "tokens": 10713830400, "tok_s": 171497.9}
|
| 233 |
+
{"step": 10240, "epoch": 0.065, "loss": 1.82408, "ppl": 6.197, "lr": 0.003, "grad": 0.0996, "tokens": 10734796800, "tok_s": 171827.3}
|
| 234 |
+
{"step": 10260, "epoch": 0.065, "loss": 1.79253, "ppl": 6.005, "lr": 0.003, "grad": 0.0972, "tokens": 10755763200, "tok_s": 172021.3}
|
| 235 |
+
{"step": 10280, "epoch": 0.065, "loss": 1.87121, "ppl": 6.496, "lr": 0.003, "grad": 0.116, "tokens": 10776729600, "tok_s": 171627.6}
|
| 236 |
+
{"step": 10300, "epoch": 0.065, "loss": 1.7832, "ppl": 5.949, "lr": 0.003, "grad": 0.0855, "tokens": 10797696000, "tok_s": 172401.3}
|
| 237 |
+
{"step": 10320, "epoch": 0.066, "loss": 1.81833, "ppl": 6.162, "lr": 0.003, "grad": 0.0977, "tokens": 10818662400, "tok_s": 172514.4}
|
| 238 |
+
{"step": 10340, "epoch": 0.066, "loss": 1.84087, "ppl": 6.302, "lr": 0.003, "grad": 0.1328, "tokens": 10839628800, "tok_s": 172219.9}
|
| 239 |
+
{"step": 10360, "epoch": 0.066, "loss": 1.85191, "ppl": 6.372, "lr": 0.003, "grad": 0.0879, "tokens": 10860595200, "tok_s": 172614.6}
|
| 240 |
+
{"step": 10380, "epoch": 0.066, "loss": 1.80973, "ppl": 6.109, "lr": 0.003, "grad": 0.078, "tokens": 10881561600, "tok_s": 171340.8}
|
| 241 |
+
{"step": 10400, "epoch": 0.066, "loss": 1.84255, "ppl": 6.313, "lr": 0.003, "grad": 0.0796, "tokens": 10902528000, "tok_s": 172214.5}
|
| 242 |
+
{"step": 10400, "val_loss": 1.82846, "val_ppl": 6.224, "is_best": true}
|
logs/log_104000.jsonl
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 103000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-04T05:34:52.650367"}
|
| 2 |
+
{"step": 103020, "epoch": 0.655, "loss": 1.74124, "ppl": 5.704, "lr": 0.003, "grad": 0.1737, "tokens": 107997926400, "tok_s": 157750.1}
|
| 3 |
+
{"step": 103040, "epoch": 0.655, "loss": 1.74289, "ppl": 5.714, "lr": 0.003, "grad": 0.1636, "tokens": 108018892800, "tok_s": 158638.8}
|
| 4 |
+
{"step": 103060, "epoch": 0.655, "loss": 1.71677, "ppl": 5.566, "lr": 0.003, "grad": 0.072, "tokens": 108039859200, "tok_s": 159090.9}
|
| 5 |
+
{"step": 103080, "epoch": 0.655, "loss": 1.61426, "ppl": 5.024, "lr": 0.003, "grad": 0.0842, "tokens": 108060825600, "tok_s": 159069.0}
|
| 6 |
+
{"step": 103100, "epoch": 0.655, "loss": 1.76967, "ppl": 5.869, "lr": 0.003, "grad": 0.1676, "tokens": 108081792000, "tok_s": 159265.0}
|
| 7 |
+
{"step": 103120, "epoch": 0.655, "loss": 1.73171, "ppl": 5.65, "lr": 0.003, "grad": 0.1788, "tokens": 108102758400, "tok_s": 159215.7}
|
| 8 |
+
{"step": 103140, "epoch": 0.655, "loss": 1.7461, "ppl": 5.732, "lr": 0.003, "grad": 0.1556, "tokens": 108123724800, "tok_s": 159252.4}
|
| 9 |
+
{"step": 103160, "epoch": 0.655, "loss": 1.67759, "ppl": 5.353, "lr": 0.003, "grad": 0.1307, "tokens": 108144691200, "tok_s": 159388.2}
|
| 10 |
+
{"step": 103180, "epoch": 0.656, "loss": 1.63079, "ppl": 5.108, "lr": 0.003, "grad": 0.0818, "tokens": 108165657600, "tok_s": 158915.5}
|
| 11 |
+
{"step": 103200, "epoch": 0.656, "loss": 1.59425, "ppl": 4.925, "lr": 0.003, "grad": 0.1396, "tokens": 108186624000, "tok_s": 159220.4}
|
| 12 |
+
{"step": 103220, "epoch": 0.656, "loss": 1.78181, "ppl": 5.941, "lr": 0.003, "grad": 0.1365, "tokens": 108207590400, "tok_s": 158956.6}
|
| 13 |
+
{"step": 103240, "epoch": 0.656, "loss": 1.70449, "ppl": 5.499, "lr": 0.003, "grad": 0.1402, "tokens": 108228556800, "tok_s": 159099.3}
|
| 14 |
+
{"step": 103260, "epoch": 0.656, "loss": 1.76033, "ppl": 5.814, "lr": 0.003, "grad": 0.1569, "tokens": 108249523200, "tok_s": 159076.4}
|
| 15 |
+
{"step": 103280, "epoch": 0.656, "loss": 1.71133, "ppl": 5.536, "lr": 0.003, "grad": 0.1348, "tokens": 108270489600, "tok_s": 159322.3}
|
| 16 |
+
{"step": 103300, "epoch": 0.656, "loss": 1.75602, "ppl": 5.789, "lr": 0.003, "grad": 0.133, "tokens": 108291456000, "tok_s": 159092.8}
|
| 17 |
+
{"step": 103320, "epoch": 0.656, "loss": 1.76105, "ppl": 5.819, "lr": 0.003, "grad": 0.0797, "tokens": 108312422400, "tok_s": 158991.1}
|
| 18 |
+
{"step": 103340, "epoch": 0.657, "loss": 1.72515, "ppl": 5.613, "lr": 0.003, "grad": 0.1414, "tokens": 108333388800, "tok_s": 158883.4}
|
| 19 |
+
{"step": 103360, "epoch": 0.657, "loss": 1.77313, "ppl": 5.889, "lr": 0.003, "grad": 0.141, "tokens": 108354355200, "tok_s": 159152.5}
|
| 20 |
+
{"step": 103380, "epoch": 0.657, "loss": 1.68315, "ppl": 5.382, "lr": 0.003, "grad": 0.1103, "tokens": 108375321600, "tok_s": 158884.2}
|
| 21 |
+
{"step": 103400, "epoch": 0.657, "loss": 1.78506, "ppl": 5.96, "lr": 0.003, "grad": 0.1633, "tokens": 108396288000, "tok_s": 159328.9}
|
| 22 |
+
{"step": 103420, "epoch": 0.657, "loss": 1.76313, "ppl": 5.831, "lr": 0.003, "grad": 0.1131, "tokens": 108417254400, "tok_s": 159196.1}
|
| 23 |
+
{"step": 103440, "epoch": 0.657, "loss": 1.67384, "ppl": 5.333, "lr": 0.003, "grad": 0.1986, "tokens": 108438220800, "tok_s": 159181.8}
|
| 24 |
+
{"step": 103460, "epoch": 0.657, "loss": 1.8131, "ppl": 6.129, "lr": 0.003, "grad": 0.0915, "tokens": 108459187200, "tok_s": 158871.5}
|
| 25 |
+
{"step": 103480, "epoch": 0.657, "loss": 1.80905, "ppl": 6.105, "lr": 0.003, "grad": 0.1683, "tokens": 108480153600, "tok_s": 159278.2}
|
| 26 |
+
{"step": 103500, "epoch": 0.658, "loss": 1.90143, "ppl": 6.695, "lr": 0.003, "grad": 0.1496, "tokens": 108501120000, "tok_s": 158915.3}
|
| 27 |
+
{"step": 103520, "epoch": 0.658, "loss": 1.76599, "ppl": 5.847, "lr": 0.003, "grad": 0.1804, "tokens": 108522086400, "tok_s": 158787.2}
|
| 28 |
+
{"step": 103540, "epoch": 0.658, "loss": 1.66056, "ppl": 5.262, "lr": 0.003, "grad": 0.1552, "tokens": 108543052800, "tok_s": 158658.2}
|
| 29 |
+
{"step": 103560, "epoch": 0.658, "loss": 1.68044, "ppl": 5.368, "lr": 0.003, "grad": 0.0855, "tokens": 108564019200, "tok_s": 159166.5}
|
| 30 |
+
{"step": 103580, "epoch": 0.658, "loss": 1.70551, "ppl": 5.504, "lr": 0.003, "grad": 0.1333, "tokens": 108584985600, "tok_s": 158797.9}
|
| 31 |
+
{"step": 103600, "epoch": 0.658, "loss": 1.64139, "ppl": 5.162, "lr": 0.003, "grad": 0.092, "tokens": 108605952000, "tok_s": 159140.5}
|
| 32 |
+
{"step": 103620, "epoch": 0.658, "loss": 1.71522, "ppl": 5.558, "lr": 0.003, "grad": 0.1698, "tokens": 108626918400, "tok_s": 159154.2}
|
| 33 |
+
{"step": 103640, "epoch": 0.658, "loss": 1.66387, "ppl": 5.28, "lr": 0.003, "grad": 0.1658, "tokens": 108647884800, "tok_s": 159108.1}
|
| 34 |
+
{"step": 103660, "epoch": 0.659, "loss": 1.84406, "ppl": 6.322, "lr": 0.003, "grad": 0.0839, "tokens": 108668851200, "tok_s": 159059.2}
|
| 35 |
+
{"step": 103680, "epoch": 0.659, "loss": 1.77286, "ppl": 5.888, "lr": 0.003, "grad": 0.1964, "tokens": 108689817600, "tok_s": 159131.7}
|
| 36 |
+
{"step": 103700, "epoch": 0.659, "loss": 1.74173, "ppl": 5.707, "lr": 0.003, "grad": 0.1256, "tokens": 108710784000, "tok_s": 158927.0}
|
| 37 |
+
{"step": 103720, "epoch": 0.659, "loss": 1.6683, "ppl": 5.303, "lr": 0.003, "grad": 0.1101, "tokens": 108731750400, "tok_s": 159215.4}
|
| 38 |
+
{"step": 103740, "epoch": 0.659, "loss": 1.70027, "ppl": 5.475, "lr": 0.003, "grad": 0.2066, "tokens": 108752716800, "tok_s": 159167.5}
|
| 39 |
+
{"step": 103760, "epoch": 0.659, "loss": 1.76893, "ppl": 5.865, "lr": 0.003, "grad": 0.2198, "tokens": 108773683200, "tok_s": 159097.2}
|
| 40 |
+
{"step": 103780, "epoch": 0.659, "loss": 1.67872, "ppl": 5.359, "lr": 0.003, "grad": 0.1615, "tokens": 108794649600, "tok_s": 159025.0}
|
| 41 |
+
{"step": 103800, "epoch": 0.66, "loss": 1.69452, "ppl": 5.444, "lr": 0.003, "grad": 0.1566, "tokens": 108815616000, "tok_s": 159177.5}
|
| 42 |
+
{"step": 103820, "epoch": 0.66, "loss": 1.74359, "ppl": 5.718, "lr": 0.003, "grad": 0.0974, "tokens": 108836582400, "tok_s": 159199.5}
|
| 43 |
+
{"step": 103840, "epoch": 0.66, "loss": 1.67706, "ppl": 5.35, "lr": 0.003, "grad": 0.104, "tokens": 108857548800, "tok_s": 159248.0}
|
| 44 |
+
{"step": 103860, "epoch": 0.66, "loss": 1.75409, "ppl": 5.778, "lr": 0.003, "grad": 0.1085, "tokens": 108878515200, "tok_s": 159090.0}
|
| 45 |
+
{"step": 103880, "epoch": 0.66, "loss": 1.78152, "ppl": 5.939, "lr": 0.003, "grad": 0.1585, "tokens": 108899481600, "tok_s": 159101.0}
|
| 46 |
+
{"step": 103900, "epoch": 0.66, "loss": 1.45016, "ppl": 4.264, "lr": 0.003, "grad": 0.1273, "tokens": 108920448000, "tok_s": 158927.5}
|
| 47 |
+
{"step": 103920, "epoch": 0.66, "loss": 1.68008, "ppl": 5.366, "lr": 0.003, "grad": 0.1713, "tokens": 108941414400, "tok_s": 159220.5}
|
| 48 |
+
{"step": 103940, "epoch": 0.66, "loss": 1.69084, "ppl": 5.424, "lr": 0.003, "grad": 0.0837, "tokens": 108962380800, "tok_s": 159170.3}
|
| 49 |
+
{"step": 103960, "epoch": 0.661, "loss": 1.78521, "ppl": 5.961, "lr": 0.003, "grad": 0.1482, "tokens": 108983347200, "tok_s": 159091.8}
|
| 50 |
+
{"step": 103980, "epoch": 0.661, "loss": 1.73619, "ppl": 5.676, "lr": 0.003, "grad": 0.1255, "tokens": 109004313600, "tok_s": 159215.5}
|
| 51 |
+
{"step": 104000, "epoch": 0.661, "loss": 1.89156, "ppl": 6.63, "lr": 0.003, "grad": 0.1592, "tokens": 109025280000, "tok_s": 158827.5}
|
| 52 |
+
{"step": 104000, "val_loss": 1.73307, "val_ppl": 5.658, "is_best": true}
|
logs/log_105000.jsonl
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 103000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-04T05:34:52.650367"}
|
| 2 |
+
{"step": 103020, "epoch": 0.655, "loss": 1.74124, "ppl": 5.704, "lr": 0.003, "grad": 0.1737, "tokens": 107997926400, "tok_s": 157750.1}
|
| 3 |
+
{"step": 103040, "epoch": 0.655, "loss": 1.74289, "ppl": 5.714, "lr": 0.003, "grad": 0.1636, "tokens": 108018892800, "tok_s": 158638.8}
|
| 4 |
+
{"step": 103060, "epoch": 0.655, "loss": 1.71677, "ppl": 5.566, "lr": 0.003, "grad": 0.072, "tokens": 108039859200, "tok_s": 159090.9}
|
| 5 |
+
{"step": 103080, "epoch": 0.655, "loss": 1.61426, "ppl": 5.024, "lr": 0.003, "grad": 0.0842, "tokens": 108060825600, "tok_s": 159069.0}
|
| 6 |
+
{"step": 103100, "epoch": 0.655, "loss": 1.76967, "ppl": 5.869, "lr": 0.003, "grad": 0.1676, "tokens": 108081792000, "tok_s": 159265.0}
|
| 7 |
+
{"step": 103120, "epoch": 0.655, "loss": 1.73171, "ppl": 5.65, "lr": 0.003, "grad": 0.1788, "tokens": 108102758400, "tok_s": 159215.7}
|
| 8 |
+
{"step": 103140, "epoch": 0.655, "loss": 1.7461, "ppl": 5.732, "lr": 0.003, "grad": 0.1556, "tokens": 108123724800, "tok_s": 159252.4}
|
| 9 |
+
{"step": 103160, "epoch": 0.655, "loss": 1.67759, "ppl": 5.353, "lr": 0.003, "grad": 0.1307, "tokens": 108144691200, "tok_s": 159388.2}
|
| 10 |
+
{"step": 103180, "epoch": 0.656, "loss": 1.63079, "ppl": 5.108, "lr": 0.003, "grad": 0.0818, "tokens": 108165657600, "tok_s": 158915.5}
|
| 11 |
+
{"step": 103200, "epoch": 0.656, "loss": 1.59425, "ppl": 4.925, "lr": 0.003, "grad": 0.1396, "tokens": 108186624000, "tok_s": 159220.4}
|
| 12 |
+
{"step": 103220, "epoch": 0.656, "loss": 1.78181, "ppl": 5.941, "lr": 0.003, "grad": 0.1365, "tokens": 108207590400, "tok_s": 158956.6}
|
| 13 |
+
{"step": 103240, "epoch": 0.656, "loss": 1.70449, "ppl": 5.499, "lr": 0.003, "grad": 0.1402, "tokens": 108228556800, "tok_s": 159099.3}
|
| 14 |
+
{"step": 103260, "epoch": 0.656, "loss": 1.76033, "ppl": 5.814, "lr": 0.003, "grad": 0.1569, "tokens": 108249523200, "tok_s": 159076.4}
|
| 15 |
+
{"step": 103280, "epoch": 0.656, "loss": 1.71133, "ppl": 5.536, "lr": 0.003, "grad": 0.1348, "tokens": 108270489600, "tok_s": 159322.3}
|
| 16 |
+
{"step": 103300, "epoch": 0.656, "loss": 1.75602, "ppl": 5.789, "lr": 0.003, "grad": 0.133, "tokens": 108291456000, "tok_s": 159092.8}
|
| 17 |
+
{"step": 103320, "epoch": 0.656, "loss": 1.76105, "ppl": 5.819, "lr": 0.003, "grad": 0.0797, "tokens": 108312422400, "tok_s": 158991.1}
|
| 18 |
+
{"step": 103340, "epoch": 0.657, "loss": 1.72515, "ppl": 5.613, "lr": 0.003, "grad": 0.1414, "tokens": 108333388800, "tok_s": 158883.4}
|
| 19 |
+
{"step": 103360, "epoch": 0.657, "loss": 1.77313, "ppl": 5.889, "lr": 0.003, "grad": 0.141, "tokens": 108354355200, "tok_s": 159152.5}
|
| 20 |
+
{"step": 103380, "epoch": 0.657, "loss": 1.68315, "ppl": 5.382, "lr": 0.003, "grad": 0.1103, "tokens": 108375321600, "tok_s": 158884.2}
|
| 21 |
+
{"step": 103400, "epoch": 0.657, "loss": 1.78506, "ppl": 5.96, "lr": 0.003, "grad": 0.1633, "tokens": 108396288000, "tok_s": 159328.9}
|
| 22 |
+
{"step": 103420, "epoch": 0.657, "loss": 1.76313, "ppl": 5.831, "lr": 0.003, "grad": 0.1131, "tokens": 108417254400, "tok_s": 159196.1}
|
| 23 |
+
{"step": 103440, "epoch": 0.657, "loss": 1.67384, "ppl": 5.333, "lr": 0.003, "grad": 0.1986, "tokens": 108438220800, "tok_s": 159181.8}
|
| 24 |
+
{"step": 103460, "epoch": 0.657, "loss": 1.8131, "ppl": 6.129, "lr": 0.003, "grad": 0.0915, "tokens": 108459187200, "tok_s": 158871.5}
|
| 25 |
+
{"step": 103480, "epoch": 0.657, "loss": 1.80905, "ppl": 6.105, "lr": 0.003, "grad": 0.1683, "tokens": 108480153600, "tok_s": 159278.2}
|
| 26 |
+
{"step": 103500, "epoch": 0.658, "loss": 1.90143, "ppl": 6.695, "lr": 0.003, "grad": 0.1496, "tokens": 108501120000, "tok_s": 158915.3}
|
| 27 |
+
{"step": 103520, "epoch": 0.658, "loss": 1.76599, "ppl": 5.847, "lr": 0.003, "grad": 0.1804, "tokens": 108522086400, "tok_s": 158787.2}
|
| 28 |
+
{"step": 103540, "epoch": 0.658, "loss": 1.66056, "ppl": 5.262, "lr": 0.003, "grad": 0.1552, "tokens": 108543052800, "tok_s": 158658.2}
|
| 29 |
+
{"step": 103560, "epoch": 0.658, "loss": 1.68044, "ppl": 5.368, "lr": 0.003, "grad": 0.0855, "tokens": 108564019200, "tok_s": 159166.5}
|
| 30 |
+
{"step": 103580, "epoch": 0.658, "loss": 1.70551, "ppl": 5.504, "lr": 0.003, "grad": 0.1333, "tokens": 108584985600, "tok_s": 158797.9}
|
| 31 |
+
{"step": 103600, "epoch": 0.658, "loss": 1.64139, "ppl": 5.162, "lr": 0.003, "grad": 0.092, "tokens": 108605952000, "tok_s": 159140.5}
|
| 32 |
+
{"step": 103620, "epoch": 0.658, "loss": 1.71522, "ppl": 5.558, "lr": 0.003, "grad": 0.1698, "tokens": 108626918400, "tok_s": 159154.2}
|
| 33 |
+
{"step": 103640, "epoch": 0.658, "loss": 1.66387, "ppl": 5.28, "lr": 0.003, "grad": 0.1658, "tokens": 108647884800, "tok_s": 159108.1}
|
| 34 |
+
{"step": 103660, "epoch": 0.659, "loss": 1.84406, "ppl": 6.322, "lr": 0.003, "grad": 0.0839, "tokens": 108668851200, "tok_s": 159059.2}
|
| 35 |
+
{"step": 103680, "epoch": 0.659, "loss": 1.77286, "ppl": 5.888, "lr": 0.003, "grad": 0.1964, "tokens": 108689817600, "tok_s": 159131.7}
|
| 36 |
+
{"step": 103700, "epoch": 0.659, "loss": 1.74173, "ppl": 5.707, "lr": 0.003, "grad": 0.1256, "tokens": 108710784000, "tok_s": 158927.0}
|
| 37 |
+
{"step": 103720, "epoch": 0.659, "loss": 1.6683, "ppl": 5.303, "lr": 0.003, "grad": 0.1101, "tokens": 108731750400, "tok_s": 159215.4}
|
| 38 |
+
{"step": 103740, "epoch": 0.659, "loss": 1.70027, "ppl": 5.475, "lr": 0.003, "grad": 0.2066, "tokens": 108752716800, "tok_s": 159167.5}
|
| 39 |
+
{"step": 103760, "epoch": 0.659, "loss": 1.76893, "ppl": 5.865, "lr": 0.003, "grad": 0.2198, "tokens": 108773683200, "tok_s": 159097.2}
|
| 40 |
+
{"step": 103780, "epoch": 0.659, "loss": 1.67872, "ppl": 5.359, "lr": 0.003, "grad": 0.1615, "tokens": 108794649600, "tok_s": 159025.0}
|
| 41 |
+
{"step": 103800, "epoch": 0.66, "loss": 1.69452, "ppl": 5.444, "lr": 0.003, "grad": 0.1566, "tokens": 108815616000, "tok_s": 159177.5}
|
| 42 |
+
{"step": 103820, "epoch": 0.66, "loss": 1.74359, "ppl": 5.718, "lr": 0.003, "grad": 0.0974, "tokens": 108836582400, "tok_s": 159199.5}
|
| 43 |
+
{"step": 103840, "epoch": 0.66, "loss": 1.67706, "ppl": 5.35, "lr": 0.003, "grad": 0.104, "tokens": 108857548800, "tok_s": 159248.0}
|
| 44 |
+
{"step": 103860, "epoch": 0.66, "loss": 1.75409, "ppl": 5.778, "lr": 0.003, "grad": 0.1085, "tokens": 108878515200, "tok_s": 159090.0}
|
| 45 |
+
{"step": 103880, "epoch": 0.66, "loss": 1.78152, "ppl": 5.939, "lr": 0.003, "grad": 0.1585, "tokens": 108899481600, "tok_s": 159101.0}
|
| 46 |
+
{"step": 103900, "epoch": 0.66, "loss": 1.45016, "ppl": 4.264, "lr": 0.003, "grad": 0.1273, "tokens": 108920448000, "tok_s": 158927.5}
|
| 47 |
+
{"step": 103920, "epoch": 0.66, "loss": 1.68008, "ppl": 5.366, "lr": 0.003, "grad": 0.1713, "tokens": 108941414400, "tok_s": 159220.5}
|
| 48 |
+
{"step": 103940, "epoch": 0.66, "loss": 1.69084, "ppl": 5.424, "lr": 0.003, "grad": 0.0837, "tokens": 108962380800, "tok_s": 159170.3}
|
| 49 |
+
{"step": 103960, "epoch": 0.661, "loss": 1.78521, "ppl": 5.961, "lr": 0.003, "grad": 0.1482, "tokens": 108983347200, "tok_s": 159091.8}
|
| 50 |
+
{"step": 103980, "epoch": 0.661, "loss": 1.73619, "ppl": 5.676, "lr": 0.003, "grad": 0.1255, "tokens": 109004313600, "tok_s": 159215.5}
|
| 51 |
+
{"step": 104000, "epoch": 0.661, "loss": 1.89156, "ppl": 6.63, "lr": 0.003, "grad": 0.1592, "tokens": 109025280000, "tok_s": 158827.5}
|
| 52 |
+
{"step": 104000, "val_loss": 1.73307, "val_ppl": 5.658, "is_best": true}
|
| 53 |
+
{"step": 104020, "epoch": 0.661, "loss": 1.73662, "ppl": 5.678, "lr": 0.003, "grad": 0.1665, "tokens": 109046246400, "tok_s": 158997.7}
|
| 54 |
+
{"step": 104040, "epoch": 0.661, "loss": 1.6789, "ppl": 5.36, "lr": 0.003, "grad": 0.1479, "tokens": 109067212800, "tok_s": 159135.6}
|
| 55 |
+
{"step": 104060, "epoch": 0.661, "loss": 1.77655, "ppl": 5.909, "lr": 0.003, "grad": 0.0996, "tokens": 109088179200, "tok_s": 158830.7}
|
| 56 |
+
{"step": 104080, "epoch": 0.661, "loss": 1.72722, "ppl": 5.625, "lr": 0.003, "grad": 0.106, "tokens": 109109145600, "tok_s": 158995.1}
|
| 57 |
+
{"step": 104100, "epoch": 0.661, "loss": 1.59814, "ppl": 4.944, "lr": 0.003, "grad": 0.0722, "tokens": 109130112000, "tok_s": 158956.0}
|
| 58 |
+
{"step": 104120, "epoch": 0.662, "loss": 1.87211, "ppl": 6.502, "lr": 0.003, "grad": 0.1723, "tokens": 109151078400, "tok_s": 159004.9}
|
| 59 |
+
{"step": 104140, "epoch": 0.662, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.1128, "tokens": 109172044800, "tok_s": 158715.8}
|
| 60 |
+
{"step": 104160, "epoch": 0.662, "loss": 1.75281, "ppl": 5.771, "lr": 0.003, "grad": 0.1824, "tokens": 109193011200, "tok_s": 158738.1}
|
| 61 |
+
{"step": 104180, "epoch": 0.662, "loss": 1.79538, "ppl": 6.022, "lr": 0.003, "grad": 0.2017, "tokens": 109213977600, "tok_s": 158633.8}
|
| 62 |
+
{"step": 104200, "epoch": 0.662, "loss": 1.70962, "ppl": 5.527, "lr": 0.003, "grad": 0.1821, "tokens": 109234944000, "tok_s": 158863.6}
|
| 63 |
+
{"step": 104220, "epoch": 0.662, "loss": 1.78149, "ppl": 5.939, "lr": 0.003, "grad": 0.1032, "tokens": 109255910400, "tok_s": 159130.0}
|
| 64 |
+
{"step": 104240, "epoch": 0.662, "loss": 1.69264, "ppl": 5.434, "lr": 0.003, "grad": 0.0855, "tokens": 109276876800, "tok_s": 158660.9}
|
| 65 |
+
{"step": 104260, "epoch": 0.662, "loss": 1.72285, "ppl": 5.6, "lr": 0.003, "grad": 0.1449, "tokens": 109297843200, "tok_s": 158872.8}
|
| 66 |
+
{"step": 104280, "epoch": 0.663, "loss": 1.60635, "ppl": 4.985, "lr": 0.003, "grad": 0.1624, "tokens": 109318809600, "tok_s": 158882.7}
|
| 67 |
+
{"step": 104300, "epoch": 0.663, "loss": 1.80534, "ppl": 6.082, "lr": 0.003, "grad": 0.1375, "tokens": 109339776000, "tok_s": 158833.1}
|
| 68 |
+
{"step": 104320, "epoch": 0.663, "loss": 1.74444, "ppl": 5.723, "lr": 0.003, "grad": 0.1149, "tokens": 109360742400, "tok_s": 158947.3}
|
| 69 |
+
{"step": 104340, "epoch": 0.663, "loss": 1.79691, "ppl": 6.031, "lr": 0.003, "grad": 0.2072, "tokens": 109381708800, "tok_s": 158998.7}
|
| 70 |
+
{"step": 104360, "epoch": 0.663, "loss": 1.73588, "ppl": 5.674, "lr": 0.003, "grad": 0.1396, "tokens": 109402675200, "tok_s": 158683.7}
|
| 71 |
+
{"step": 104380, "epoch": 0.663, "loss": 1.8465, "ppl": 6.338, "lr": 0.003, "grad": 0.1107, "tokens": 109423641600, "tok_s": 158875.4}
|
| 72 |
+
{"step": 104400, "epoch": 0.663, "loss": 1.81251, "ppl": 6.126, "lr": 0.003, "grad": 0.0807, "tokens": 109444608000, "tok_s": 158669.8}
|
| 73 |
+
{"step": 104420, "epoch": 0.663, "loss": 1.7951, "ppl": 6.02, "lr": 0.003, "grad": 0.1246, "tokens": 109465574400, "tok_s": 158742.5}
|
| 74 |
+
{"step": 104440, "epoch": 0.664, "loss": 1.73516, "ppl": 5.67, "lr": 0.003, "grad": 0.0797, "tokens": 109486540800, "tok_s": 158811.7}
|
| 75 |
+
{"step": 104460, "epoch": 0.664, "loss": 1.77739, "ppl": 5.914, "lr": 0.003, "grad": 0.2092, "tokens": 109507507200, "tok_s": 159175.4}
|
| 76 |
+
{"step": 104480, "epoch": 0.664, "loss": 1.82117, "ppl": 6.179, "lr": 0.003, "grad": 0.1147, "tokens": 109528473600, "tok_s": 158902.0}
|
| 77 |
+
{"step": 104500, "epoch": 0.664, "loss": 1.78193, "ppl": 5.941, "lr": 0.003, "grad": 0.0972, "tokens": 109549440000, "tok_s": 158571.8}
|
| 78 |
+
{"step": 104520, "epoch": 0.664, "loss": 1.78727, "ppl": 5.973, "lr": 0.003, "grad": 0.1308, "tokens": 109570406400, "tok_s": 159003.7}
|
| 79 |
+
{"step": 104540, "epoch": 0.664, "loss": 1.71035, "ppl": 5.531, "lr": 0.003, "grad": 0.0935, "tokens": 109591372800, "tok_s": 158566.8}
|
| 80 |
+
{"step": 104560, "epoch": 0.664, "loss": 1.79273, "ppl": 6.006, "lr": 0.003, "grad": 0.1619, "tokens": 109612339200, "tok_s": 159022.1}
|
| 81 |
+
{"step": 104580, "epoch": 0.664, "loss": 1.59285, "ppl": 4.918, "lr": 0.003, "grad": 0.0923, "tokens": 109633305600, "tok_s": 158996.6}
|
| 82 |
+
{"step": 104600, "epoch": 0.665, "loss": 1.76848, "ppl": 5.862, "lr": 0.003, "grad": 0.0946, "tokens": 109654272000, "tok_s": 159063.0}
|
| 83 |
+
{"step": 104620, "epoch": 0.665, "loss": 1.76793, "ppl": 5.859, "lr": 0.003, "grad": 0.0949, "tokens": 109675238400, "tok_s": 158677.9}
|
| 84 |
+
{"step": 104640, "epoch": 0.665, "loss": 1.73267, "ppl": 5.656, "lr": 0.003, "grad": 0.1246, "tokens": 109696204800, "tok_s": 159086.8}
|
| 85 |
+
{"step": 104660, "epoch": 0.665, "loss": 1.78542, "ppl": 5.962, "lr": 0.003, "grad": 0.08, "tokens": 109717171200, "tok_s": 159076.5}
|
| 86 |
+
{"step": 104680, "epoch": 0.665, "loss": 1.75886, "ppl": 5.806, "lr": 0.003, "grad": 0.125, "tokens": 109738137600, "tok_s": 159037.3}
|
| 87 |
+
{"step": 104700, "epoch": 0.665, "loss": 1.73196, "ppl": 5.652, "lr": 0.003, "grad": 0.1015, "tokens": 109759104000, "tok_s": 158854.1}
|
| 88 |
+
{"step": 104720, "epoch": 0.665, "loss": 1.7098, "ppl": 5.528, "lr": 0.003, "grad": 0.1101, "tokens": 109780070400, "tok_s": 159124.5}
|
| 89 |
+
{"step": 104740, "epoch": 0.665, "loss": 1.74681, "ppl": 5.736, "lr": 0.003, "grad": 0.1051, "tokens": 109801036800, "tok_s": 159026.5}
|
| 90 |
+
{"step": 104760, "epoch": 0.666, "loss": 1.63925, "ppl": 5.151, "lr": 0.003, "grad": 0.0543, "tokens": 109822003200, "tok_s": 158990.3}
|
| 91 |
+
{"step": 104780, "epoch": 0.666, "loss": 1.71809, "ppl": 5.574, "lr": 0.003, "grad": 0.1393, "tokens": 109842969600, "tok_s": 159137.8}
|
| 92 |
+
{"step": 104800, "epoch": 0.666, "loss": 1.74093, "ppl": 5.703, "lr": 0.003, "grad": 0.1612, "tokens": 109863936000, "tok_s": 158846.4}
|
| 93 |
+
{"step": 104820, "epoch": 0.666, "loss": 1.76485, "ppl": 5.841, "lr": 0.003, "grad": 0.1143, "tokens": 109884902400, "tok_s": 158972.5}
|
| 94 |
+
{"step": 104840, "epoch": 0.666, "loss": 1.78046, "ppl": 5.933, "lr": 0.003, "grad": 0.085, "tokens": 109905868800, "tok_s": 158689.6}
|
| 95 |
+
{"step": 104860, "epoch": 0.666, "loss": 1.79138, "ppl": 5.998, "lr": 0.003, "grad": 0.0665, "tokens": 109926835200, "tok_s": 158956.5}
|
| 96 |
+
{"step": 104880, "epoch": 0.666, "loss": 1.77218, "ppl": 5.884, "lr": 0.003, "grad": 0.1442, "tokens": 109947801600, "tok_s": 159018.8}
|
| 97 |
+
{"step": 104900, "epoch": 0.666, "loss": 1.75558, "ppl": 5.787, "lr": 0.003, "grad": 0.1406, "tokens": 109968768000, "tok_s": 158995.5}
|
| 98 |
+
{"step": 104920, "epoch": 0.667, "loss": 1.78012, "ppl": 5.931, "lr": 0.003, "grad": 0.1164, "tokens": 109989734400, "tok_s": 158956.1}
|
| 99 |
+
{"step": 104940, "epoch": 0.667, "loss": 1.7293, "ppl": 5.637, "lr": 0.003, "grad": 0.0836, "tokens": 110010700800, "tok_s": 158958.7}
|
| 100 |
+
{"step": 104960, "epoch": 0.667, "loss": 1.75256, "ppl": 5.769, "lr": 0.003, "grad": 0.145, "tokens": 110031667200, "tok_s": 158967.2}
|
| 101 |
+
{"step": 104980, "epoch": 0.667, "loss": 1.79842, "ppl": 6.04, "lr": 0.003, "grad": 0.141, "tokens": 110052633600, "tok_s": 159126.4}
|
| 102 |
+
{"step": 105000, "epoch": 0.667, "loss": 1.72704, "ppl": 5.624, "lr": 0.003, "grad": 0.1398, "tokens": 110073600000, "tok_s": 158991.1}
|
| 103 |
+
{"step": 105000, "val_loss": 1.74304, "val_ppl": 5.715, "is_best": false}
|
logs/log_106000.jsonl
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 103000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-04T05:34:52.650367"}
|
| 2 |
+
{"step": 103020, "epoch": 0.655, "loss": 1.74124, "ppl": 5.704, "lr": 0.003, "grad": 0.1737, "tokens": 107997926400, "tok_s": 157750.1}
|
| 3 |
+
{"step": 103040, "epoch": 0.655, "loss": 1.74289, "ppl": 5.714, "lr": 0.003, "grad": 0.1636, "tokens": 108018892800, "tok_s": 158638.8}
|
| 4 |
+
{"step": 103060, "epoch": 0.655, "loss": 1.71677, "ppl": 5.566, "lr": 0.003, "grad": 0.072, "tokens": 108039859200, "tok_s": 159090.9}
|
| 5 |
+
{"step": 103080, "epoch": 0.655, "loss": 1.61426, "ppl": 5.024, "lr": 0.003, "grad": 0.0842, "tokens": 108060825600, "tok_s": 159069.0}
|
| 6 |
+
{"step": 103100, "epoch": 0.655, "loss": 1.76967, "ppl": 5.869, "lr": 0.003, "grad": 0.1676, "tokens": 108081792000, "tok_s": 159265.0}
|
| 7 |
+
{"step": 103120, "epoch": 0.655, "loss": 1.73171, "ppl": 5.65, "lr": 0.003, "grad": 0.1788, "tokens": 108102758400, "tok_s": 159215.7}
|
| 8 |
+
{"step": 103140, "epoch": 0.655, "loss": 1.7461, "ppl": 5.732, "lr": 0.003, "grad": 0.1556, "tokens": 108123724800, "tok_s": 159252.4}
|
| 9 |
+
{"step": 103160, "epoch": 0.655, "loss": 1.67759, "ppl": 5.353, "lr": 0.003, "grad": 0.1307, "tokens": 108144691200, "tok_s": 159388.2}
|
| 10 |
+
{"step": 103180, "epoch": 0.656, "loss": 1.63079, "ppl": 5.108, "lr": 0.003, "grad": 0.0818, "tokens": 108165657600, "tok_s": 158915.5}
|
| 11 |
+
{"step": 103200, "epoch": 0.656, "loss": 1.59425, "ppl": 4.925, "lr": 0.003, "grad": 0.1396, "tokens": 108186624000, "tok_s": 159220.4}
|
| 12 |
+
{"step": 103220, "epoch": 0.656, "loss": 1.78181, "ppl": 5.941, "lr": 0.003, "grad": 0.1365, "tokens": 108207590400, "tok_s": 158956.6}
|
| 13 |
+
{"step": 103240, "epoch": 0.656, "loss": 1.70449, "ppl": 5.499, "lr": 0.003, "grad": 0.1402, "tokens": 108228556800, "tok_s": 159099.3}
|
| 14 |
+
{"step": 103260, "epoch": 0.656, "loss": 1.76033, "ppl": 5.814, "lr": 0.003, "grad": 0.1569, "tokens": 108249523200, "tok_s": 159076.4}
|
| 15 |
+
{"step": 103280, "epoch": 0.656, "loss": 1.71133, "ppl": 5.536, "lr": 0.003, "grad": 0.1348, "tokens": 108270489600, "tok_s": 159322.3}
|
| 16 |
+
{"step": 103300, "epoch": 0.656, "loss": 1.75602, "ppl": 5.789, "lr": 0.003, "grad": 0.133, "tokens": 108291456000, "tok_s": 159092.8}
|
| 17 |
+
{"step": 103320, "epoch": 0.656, "loss": 1.76105, "ppl": 5.819, "lr": 0.003, "grad": 0.0797, "tokens": 108312422400, "tok_s": 158991.1}
|
| 18 |
+
{"step": 103340, "epoch": 0.657, "loss": 1.72515, "ppl": 5.613, "lr": 0.003, "grad": 0.1414, "tokens": 108333388800, "tok_s": 158883.4}
|
| 19 |
+
{"step": 103360, "epoch": 0.657, "loss": 1.77313, "ppl": 5.889, "lr": 0.003, "grad": 0.141, "tokens": 108354355200, "tok_s": 159152.5}
|
| 20 |
+
{"step": 103380, "epoch": 0.657, "loss": 1.68315, "ppl": 5.382, "lr": 0.003, "grad": 0.1103, "tokens": 108375321600, "tok_s": 158884.2}
|
| 21 |
+
{"step": 103400, "epoch": 0.657, "loss": 1.78506, "ppl": 5.96, "lr": 0.003, "grad": 0.1633, "tokens": 108396288000, "tok_s": 159328.9}
|
| 22 |
+
{"step": 103420, "epoch": 0.657, "loss": 1.76313, "ppl": 5.831, "lr": 0.003, "grad": 0.1131, "tokens": 108417254400, "tok_s": 159196.1}
|
| 23 |
+
{"step": 103440, "epoch": 0.657, "loss": 1.67384, "ppl": 5.333, "lr": 0.003, "grad": 0.1986, "tokens": 108438220800, "tok_s": 159181.8}
|
| 24 |
+
{"step": 103460, "epoch": 0.657, "loss": 1.8131, "ppl": 6.129, "lr": 0.003, "grad": 0.0915, "tokens": 108459187200, "tok_s": 158871.5}
|
| 25 |
+
{"step": 103480, "epoch": 0.657, "loss": 1.80905, "ppl": 6.105, "lr": 0.003, "grad": 0.1683, "tokens": 108480153600, "tok_s": 159278.2}
|
| 26 |
+
{"step": 103500, "epoch": 0.658, "loss": 1.90143, "ppl": 6.695, "lr": 0.003, "grad": 0.1496, "tokens": 108501120000, "tok_s": 158915.3}
|
| 27 |
+
{"step": 103520, "epoch": 0.658, "loss": 1.76599, "ppl": 5.847, "lr": 0.003, "grad": 0.1804, "tokens": 108522086400, "tok_s": 158787.2}
|
| 28 |
+
{"step": 103540, "epoch": 0.658, "loss": 1.66056, "ppl": 5.262, "lr": 0.003, "grad": 0.1552, "tokens": 108543052800, "tok_s": 158658.2}
|
| 29 |
+
{"step": 103560, "epoch": 0.658, "loss": 1.68044, "ppl": 5.368, "lr": 0.003, "grad": 0.0855, "tokens": 108564019200, "tok_s": 159166.5}
|
| 30 |
+
{"step": 103580, "epoch": 0.658, "loss": 1.70551, "ppl": 5.504, "lr": 0.003, "grad": 0.1333, "tokens": 108584985600, "tok_s": 158797.9}
|
| 31 |
+
{"step": 103600, "epoch": 0.658, "loss": 1.64139, "ppl": 5.162, "lr": 0.003, "grad": 0.092, "tokens": 108605952000, "tok_s": 159140.5}
|
| 32 |
+
{"step": 103620, "epoch": 0.658, "loss": 1.71522, "ppl": 5.558, "lr": 0.003, "grad": 0.1698, "tokens": 108626918400, "tok_s": 159154.2}
|
| 33 |
+
{"step": 103640, "epoch": 0.658, "loss": 1.66387, "ppl": 5.28, "lr": 0.003, "grad": 0.1658, "tokens": 108647884800, "tok_s": 159108.1}
|
| 34 |
+
{"step": 103660, "epoch": 0.659, "loss": 1.84406, "ppl": 6.322, "lr": 0.003, "grad": 0.0839, "tokens": 108668851200, "tok_s": 159059.2}
|
| 35 |
+
{"step": 103680, "epoch": 0.659, "loss": 1.77286, "ppl": 5.888, "lr": 0.003, "grad": 0.1964, "tokens": 108689817600, "tok_s": 159131.7}
|
| 36 |
+
{"step": 103700, "epoch": 0.659, "loss": 1.74173, "ppl": 5.707, "lr": 0.003, "grad": 0.1256, "tokens": 108710784000, "tok_s": 158927.0}
|
| 37 |
+
{"step": 103720, "epoch": 0.659, "loss": 1.6683, "ppl": 5.303, "lr": 0.003, "grad": 0.1101, "tokens": 108731750400, "tok_s": 159215.4}
|
| 38 |
+
{"step": 103740, "epoch": 0.659, "loss": 1.70027, "ppl": 5.475, "lr": 0.003, "grad": 0.2066, "tokens": 108752716800, "tok_s": 159167.5}
|
| 39 |
+
{"step": 103760, "epoch": 0.659, "loss": 1.76893, "ppl": 5.865, "lr": 0.003, "grad": 0.2198, "tokens": 108773683200, "tok_s": 159097.2}
|
| 40 |
+
{"step": 103780, "epoch": 0.659, "loss": 1.67872, "ppl": 5.359, "lr": 0.003, "grad": 0.1615, "tokens": 108794649600, "tok_s": 159025.0}
|
| 41 |
+
{"step": 103800, "epoch": 0.66, "loss": 1.69452, "ppl": 5.444, "lr": 0.003, "grad": 0.1566, "tokens": 108815616000, "tok_s": 159177.5}
|
| 42 |
+
{"step": 103820, "epoch": 0.66, "loss": 1.74359, "ppl": 5.718, "lr": 0.003, "grad": 0.0974, "tokens": 108836582400, "tok_s": 159199.5}
|
| 43 |
+
{"step": 103840, "epoch": 0.66, "loss": 1.67706, "ppl": 5.35, "lr": 0.003, "grad": 0.104, "tokens": 108857548800, "tok_s": 159248.0}
|
| 44 |
+
{"step": 103860, "epoch": 0.66, "loss": 1.75409, "ppl": 5.778, "lr": 0.003, "grad": 0.1085, "tokens": 108878515200, "tok_s": 159090.0}
|
| 45 |
+
{"step": 103880, "epoch": 0.66, "loss": 1.78152, "ppl": 5.939, "lr": 0.003, "grad": 0.1585, "tokens": 108899481600, "tok_s": 159101.0}
|
| 46 |
+
{"step": 103900, "epoch": 0.66, "loss": 1.45016, "ppl": 4.264, "lr": 0.003, "grad": 0.1273, "tokens": 108920448000, "tok_s": 158927.5}
|
| 47 |
+
{"step": 103920, "epoch": 0.66, "loss": 1.68008, "ppl": 5.366, "lr": 0.003, "grad": 0.1713, "tokens": 108941414400, "tok_s": 159220.5}
|
| 48 |
+
{"step": 103940, "epoch": 0.66, "loss": 1.69084, "ppl": 5.424, "lr": 0.003, "grad": 0.0837, "tokens": 108962380800, "tok_s": 159170.3}
|
| 49 |
+
{"step": 103960, "epoch": 0.661, "loss": 1.78521, "ppl": 5.961, "lr": 0.003, "grad": 0.1482, "tokens": 108983347200, "tok_s": 159091.8}
|
| 50 |
+
{"step": 103980, "epoch": 0.661, "loss": 1.73619, "ppl": 5.676, "lr": 0.003, "grad": 0.1255, "tokens": 109004313600, "tok_s": 159215.5}
|
| 51 |
+
{"step": 104000, "epoch": 0.661, "loss": 1.89156, "ppl": 6.63, "lr": 0.003, "grad": 0.1592, "tokens": 109025280000, "tok_s": 158827.5}
|
| 52 |
+
{"step": 104000, "val_loss": 1.73307, "val_ppl": 5.658, "is_best": true}
|
| 53 |
+
{"step": 104020, "epoch": 0.661, "loss": 1.73662, "ppl": 5.678, "lr": 0.003, "grad": 0.1665, "tokens": 109046246400, "tok_s": 158997.7}
|
| 54 |
+
{"step": 104040, "epoch": 0.661, "loss": 1.6789, "ppl": 5.36, "lr": 0.003, "grad": 0.1479, "tokens": 109067212800, "tok_s": 159135.6}
|
| 55 |
+
{"step": 104060, "epoch": 0.661, "loss": 1.77655, "ppl": 5.909, "lr": 0.003, "grad": 0.0996, "tokens": 109088179200, "tok_s": 158830.7}
|
| 56 |
+
{"step": 104080, "epoch": 0.661, "loss": 1.72722, "ppl": 5.625, "lr": 0.003, "grad": 0.106, "tokens": 109109145600, "tok_s": 158995.1}
|
| 57 |
+
{"step": 104100, "epoch": 0.661, "loss": 1.59814, "ppl": 4.944, "lr": 0.003, "grad": 0.0722, "tokens": 109130112000, "tok_s": 158956.0}
|
| 58 |
+
{"step": 104120, "epoch": 0.662, "loss": 1.87211, "ppl": 6.502, "lr": 0.003, "grad": 0.1723, "tokens": 109151078400, "tok_s": 159004.9}
|
| 59 |
+
{"step": 104140, "epoch": 0.662, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.1128, "tokens": 109172044800, "tok_s": 158715.8}
|
| 60 |
+
{"step": 104160, "epoch": 0.662, "loss": 1.75281, "ppl": 5.771, "lr": 0.003, "grad": 0.1824, "tokens": 109193011200, "tok_s": 158738.1}
|
| 61 |
+
{"step": 104180, "epoch": 0.662, "loss": 1.79538, "ppl": 6.022, "lr": 0.003, "grad": 0.2017, "tokens": 109213977600, "tok_s": 158633.8}
|
| 62 |
+
{"step": 104200, "epoch": 0.662, "loss": 1.70962, "ppl": 5.527, "lr": 0.003, "grad": 0.1821, "tokens": 109234944000, "tok_s": 158863.6}
|
| 63 |
+
{"step": 104220, "epoch": 0.662, "loss": 1.78149, "ppl": 5.939, "lr": 0.003, "grad": 0.1032, "tokens": 109255910400, "tok_s": 159130.0}
|
| 64 |
+
{"step": 104240, "epoch": 0.662, "loss": 1.69264, "ppl": 5.434, "lr": 0.003, "grad": 0.0855, "tokens": 109276876800, "tok_s": 158660.9}
|
| 65 |
+
{"step": 104260, "epoch": 0.662, "loss": 1.72285, "ppl": 5.6, "lr": 0.003, "grad": 0.1449, "tokens": 109297843200, "tok_s": 158872.8}
|
| 66 |
+
{"step": 104280, "epoch": 0.663, "loss": 1.60635, "ppl": 4.985, "lr": 0.003, "grad": 0.1624, "tokens": 109318809600, "tok_s": 158882.7}
|
| 67 |
+
{"step": 104300, "epoch": 0.663, "loss": 1.80534, "ppl": 6.082, "lr": 0.003, "grad": 0.1375, "tokens": 109339776000, "tok_s": 158833.1}
|
| 68 |
+
{"step": 104320, "epoch": 0.663, "loss": 1.74444, "ppl": 5.723, "lr": 0.003, "grad": 0.1149, "tokens": 109360742400, "tok_s": 158947.3}
|
| 69 |
+
{"step": 104340, "epoch": 0.663, "loss": 1.79691, "ppl": 6.031, "lr": 0.003, "grad": 0.2072, "tokens": 109381708800, "tok_s": 158998.7}
|
| 70 |
+
{"step": 104360, "epoch": 0.663, "loss": 1.73588, "ppl": 5.674, "lr": 0.003, "grad": 0.1396, "tokens": 109402675200, "tok_s": 158683.7}
|
| 71 |
+
{"step": 104380, "epoch": 0.663, "loss": 1.8465, "ppl": 6.338, "lr": 0.003, "grad": 0.1107, "tokens": 109423641600, "tok_s": 158875.4}
|
| 72 |
+
{"step": 104400, "epoch": 0.663, "loss": 1.81251, "ppl": 6.126, "lr": 0.003, "grad": 0.0807, "tokens": 109444608000, "tok_s": 158669.8}
|
| 73 |
+
{"step": 104420, "epoch": 0.663, "loss": 1.7951, "ppl": 6.02, "lr": 0.003, "grad": 0.1246, "tokens": 109465574400, "tok_s": 158742.5}
|
| 74 |
+
{"step": 104440, "epoch": 0.664, "loss": 1.73516, "ppl": 5.67, "lr": 0.003, "grad": 0.0797, "tokens": 109486540800, "tok_s": 158811.7}
|
| 75 |
+
{"step": 104460, "epoch": 0.664, "loss": 1.77739, "ppl": 5.914, "lr": 0.003, "grad": 0.2092, "tokens": 109507507200, "tok_s": 159175.4}
|
| 76 |
+
{"step": 104480, "epoch": 0.664, "loss": 1.82117, "ppl": 6.179, "lr": 0.003, "grad": 0.1147, "tokens": 109528473600, "tok_s": 158902.0}
|
| 77 |
+
{"step": 104500, "epoch": 0.664, "loss": 1.78193, "ppl": 5.941, "lr": 0.003, "grad": 0.0972, "tokens": 109549440000, "tok_s": 158571.8}
|
| 78 |
+
{"step": 104520, "epoch": 0.664, "loss": 1.78727, "ppl": 5.973, "lr": 0.003, "grad": 0.1308, "tokens": 109570406400, "tok_s": 159003.7}
|
| 79 |
+
{"step": 104540, "epoch": 0.664, "loss": 1.71035, "ppl": 5.531, "lr": 0.003, "grad": 0.0935, "tokens": 109591372800, "tok_s": 158566.8}
|
| 80 |
+
{"step": 104560, "epoch": 0.664, "loss": 1.79273, "ppl": 6.006, "lr": 0.003, "grad": 0.1619, "tokens": 109612339200, "tok_s": 159022.1}
|
| 81 |
+
{"step": 104580, "epoch": 0.664, "loss": 1.59285, "ppl": 4.918, "lr": 0.003, "grad": 0.0923, "tokens": 109633305600, "tok_s": 158996.6}
|
| 82 |
+
{"step": 104600, "epoch": 0.665, "loss": 1.76848, "ppl": 5.862, "lr": 0.003, "grad": 0.0946, "tokens": 109654272000, "tok_s": 159063.0}
|
| 83 |
+
{"step": 104620, "epoch": 0.665, "loss": 1.76793, "ppl": 5.859, "lr": 0.003, "grad": 0.0949, "tokens": 109675238400, "tok_s": 158677.9}
|
| 84 |
+
{"step": 104640, "epoch": 0.665, "loss": 1.73267, "ppl": 5.656, "lr": 0.003, "grad": 0.1246, "tokens": 109696204800, "tok_s": 159086.8}
|
| 85 |
+
{"step": 104660, "epoch": 0.665, "loss": 1.78542, "ppl": 5.962, "lr": 0.003, "grad": 0.08, "tokens": 109717171200, "tok_s": 159076.5}
|
| 86 |
+
{"step": 104680, "epoch": 0.665, "loss": 1.75886, "ppl": 5.806, "lr": 0.003, "grad": 0.125, "tokens": 109738137600, "tok_s": 159037.3}
|
| 87 |
+
{"step": 104700, "epoch": 0.665, "loss": 1.73196, "ppl": 5.652, "lr": 0.003, "grad": 0.1015, "tokens": 109759104000, "tok_s": 158854.1}
|
| 88 |
+
{"step": 104720, "epoch": 0.665, "loss": 1.7098, "ppl": 5.528, "lr": 0.003, "grad": 0.1101, "tokens": 109780070400, "tok_s": 159124.5}
|
| 89 |
+
{"step": 104740, "epoch": 0.665, "loss": 1.74681, "ppl": 5.736, "lr": 0.003, "grad": 0.1051, "tokens": 109801036800, "tok_s": 159026.5}
|
| 90 |
+
{"step": 104760, "epoch": 0.666, "loss": 1.63925, "ppl": 5.151, "lr": 0.003, "grad": 0.0543, "tokens": 109822003200, "tok_s": 158990.3}
|
| 91 |
+
{"step": 104780, "epoch": 0.666, "loss": 1.71809, "ppl": 5.574, "lr": 0.003, "grad": 0.1393, "tokens": 109842969600, "tok_s": 159137.8}
|
| 92 |
+
{"step": 104800, "epoch": 0.666, "loss": 1.74093, "ppl": 5.703, "lr": 0.003, "grad": 0.1612, "tokens": 109863936000, "tok_s": 158846.4}
|
| 93 |
+
{"step": 104820, "epoch": 0.666, "loss": 1.76485, "ppl": 5.841, "lr": 0.003, "grad": 0.1143, "tokens": 109884902400, "tok_s": 158972.5}
|
| 94 |
+
{"step": 104840, "epoch": 0.666, "loss": 1.78046, "ppl": 5.933, "lr": 0.003, "grad": 0.085, "tokens": 109905868800, "tok_s": 158689.6}
|
| 95 |
+
{"step": 104860, "epoch": 0.666, "loss": 1.79138, "ppl": 5.998, "lr": 0.003, "grad": 0.0665, "tokens": 109926835200, "tok_s": 158956.5}
|
| 96 |
+
{"step": 104880, "epoch": 0.666, "loss": 1.77218, "ppl": 5.884, "lr": 0.003, "grad": 0.1442, "tokens": 109947801600, "tok_s": 159018.8}
|
| 97 |
+
{"step": 104900, "epoch": 0.666, "loss": 1.75558, "ppl": 5.787, "lr": 0.003, "grad": 0.1406, "tokens": 109968768000, "tok_s": 158995.5}
|
| 98 |
+
{"step": 104920, "epoch": 0.667, "loss": 1.78012, "ppl": 5.931, "lr": 0.003, "grad": 0.1164, "tokens": 109989734400, "tok_s": 158956.1}
|
| 99 |
+
{"step": 104940, "epoch": 0.667, "loss": 1.7293, "ppl": 5.637, "lr": 0.003, "grad": 0.0836, "tokens": 110010700800, "tok_s": 158958.7}
|
| 100 |
+
{"step": 104960, "epoch": 0.667, "loss": 1.75256, "ppl": 5.769, "lr": 0.003, "grad": 0.145, "tokens": 110031667200, "tok_s": 158967.2}
|
| 101 |
+
{"step": 104980, "epoch": 0.667, "loss": 1.79842, "ppl": 6.04, "lr": 0.003, "grad": 0.141, "tokens": 110052633600, "tok_s": 159126.4}
|
| 102 |
+
{"step": 105000, "epoch": 0.667, "loss": 1.72704, "ppl": 5.624, "lr": 0.003, "grad": 0.1398, "tokens": 110073600000, "tok_s": 158991.1}
|
| 103 |
+
{"step": 105000, "val_loss": 1.74304, "val_ppl": 5.715, "is_best": false}
|
| 104 |
+
{"step": 105020, "epoch": 0.667, "loss": 1.76215, "ppl": 5.825, "lr": 0.003, "grad": 0.1806, "tokens": 110094566400, "tok_s": 158671.8}
|
| 105 |
+
{"step": 105040, "epoch": 0.667, "loss": 1.75137, "ppl": 5.763, "lr": 0.003, "grad": 0.0962, "tokens": 110115532800, "tok_s": 158974.6}
|
| 106 |
+
{"step": 105060, "epoch": 0.668, "loss": 1.69628, "ppl": 5.454, "lr": 0.003, "grad": 0.0863, "tokens": 110136499200, "tok_s": 158912.0}
|
| 107 |
+
{"step": 105080, "epoch": 0.668, "loss": 1.76755, "ppl": 5.856, "lr": 0.003, "grad": 0.1386, "tokens": 110157465600, "tok_s": 158756.9}
|
| 108 |
+
{"step": 105100, "epoch": 0.668, "loss": 1.75679, "ppl": 5.794, "lr": 0.003, "grad": 0.1659, "tokens": 110178432000, "tok_s": 158854.3}
|
| 109 |
+
{"step": 105120, "epoch": 0.668, "loss": 1.83078, "ppl": 6.239, "lr": 0.003, "grad": 0.0992, "tokens": 110199398400, "tok_s": 158941.0}
|
| 110 |
+
{"step": 105140, "epoch": 0.668, "loss": 1.772, "ppl": 5.883, "lr": 0.003, "grad": 0.096, "tokens": 110220364800, "tok_s": 159249.8}
|
| 111 |
+
{"step": 105160, "epoch": 0.668, "loss": 1.72506, "ppl": 5.613, "lr": 0.003, "grad": 0.1498, "tokens": 110241331200, "tok_s": 158660.2}
|
| 112 |
+
{"step": 105180, "epoch": 0.668, "loss": 1.7513, "ppl": 5.762, "lr": 0.003, "grad": 0.1525, "tokens": 110262297600, "tok_s": 158921.5}
|
| 113 |
+
{"step": 105200, "epoch": 0.668, "loss": 1.80524, "ppl": 6.081, "lr": 0.003, "grad": 0.1137, "tokens": 110283264000, "tok_s": 158794.3}
|
| 114 |
+
{"step": 105220, "epoch": 0.669, "loss": 1.7043, "ppl": 5.498, "lr": 0.003, "grad": 0.0862, "tokens": 110304230400, "tok_s": 159014.6}
|
| 115 |
+
{"step": 105240, "epoch": 0.669, "loss": 1.75034, "ppl": 5.757, "lr": 0.003, "grad": 0.1358, "tokens": 110325196800, "tok_s": 158690.7}
|
| 116 |
+
{"step": 105260, "epoch": 0.669, "loss": 1.66413, "ppl": 5.281, "lr": 0.003, "grad": 0.0687, "tokens": 110346163200, "tok_s": 158623.5}
|
| 117 |
+
{"step": 105280, "epoch": 0.669, "loss": 1.76264, "ppl": 5.828, "lr": 0.003, "grad": 0.1444, "tokens": 110367129600, "tok_s": 158682.2}
|
| 118 |
+
{"step": 105300, "epoch": 0.669, "loss": 1.78643, "ppl": 5.968, "lr": 0.003, "grad": 0.1082, "tokens": 110388096000, "tok_s": 158903.4}
|
| 119 |
+
{"step": 105320, "epoch": 0.669, "loss": 1.66896, "ppl": 5.307, "lr": 0.003, "grad": 0.0696, "tokens": 110409062400, "tok_s": 159098.4}
|
| 120 |
+
{"step": 105340, "epoch": 0.669, "loss": 1.63363, "ppl": 5.122, "lr": 0.003, "grad": 0.1139, "tokens": 110430028800, "tok_s": 158622.7}
|
| 121 |
+
{"step": 105360, "epoch": 0.669, "loss": 1.76022, "ppl": 5.814, "lr": 0.003, "grad": 0.1553, "tokens": 110450995200, "tok_s": 158832.6}
|
| 122 |
+
{"step": 105380, "epoch": 0.67, "loss": 1.73319, "ppl": 5.659, "lr": 0.003, "grad": 0.1156, "tokens": 110471961600, "tok_s": 158747.8}
|
| 123 |
+
{"step": 105400, "epoch": 0.67, "loss": 1.64827, "ppl": 5.198, "lr": 0.003, "grad": 0.0792, "tokens": 110492928000, "tok_s": 159063.9}
|
| 124 |
+
{"step": 105420, "epoch": 0.67, "loss": 1.66882, "ppl": 5.306, "lr": 0.003, "grad": 0.0799, "tokens": 110513894400, "tok_s": 158993.6}
|
| 125 |
+
{"step": 105440, "epoch": 0.67, "loss": 1.85582, "ppl": 6.397, "lr": 0.003, "grad": 0.1864, "tokens": 110534860800, "tok_s": 159145.8}
|
| 126 |
+
{"step": 105460, "epoch": 0.67, "loss": 1.64841, "ppl": 5.199, "lr": 0.003, "grad": 0.1361, "tokens": 110555827200, "tok_s": 158950.5}
|
| 127 |
+
{"step": 105480, "epoch": 0.67, "loss": 1.72625, "ppl": 5.62, "lr": 0.003, "grad": 0.107, "tokens": 110576793600, "tok_s": 159055.6}
|
| 128 |
+
{"step": 105500, "epoch": 0.67, "loss": 1.70148, "ppl": 5.482, "lr": 0.003, "grad": 0.0887, "tokens": 110597760000, "tok_s": 158735.0}
|
| 129 |
+
{"step": 105520, "epoch": 0.67, "loss": 1.71477, "ppl": 5.555, "lr": 0.003, "grad": 0.0792, "tokens": 110618726400, "tok_s": 158689.6}
|
| 130 |
+
{"step": 105540, "epoch": 0.671, "loss": 1.71728, "ppl": 5.569, "lr": 0.003, "grad": 0.123, "tokens": 110639692800, "tok_s": 158888.5}
|
| 131 |
+
{"step": 105560, "epoch": 0.671, "loss": 1.81532, "ppl": 6.143, "lr": 0.003, "grad": 0.1478, "tokens": 110660659200, "tok_s": 158992.0}
|
| 132 |
+
{"step": 105580, "epoch": 0.671, "loss": 1.74605, "ppl": 5.732, "lr": 0.003, "grad": 0.1198, "tokens": 110681625600, "tok_s": 158645.1}
|
| 133 |
+
{"step": 105600, "epoch": 0.671, "loss": 1.77535, "ppl": 5.902, "lr": 0.003, "grad": 0.0567, "tokens": 110702592000, "tok_s": 158893.2}
|
| 134 |
+
{"step": 105620, "epoch": 0.671, "loss": 1.73959, "ppl": 5.695, "lr": 0.003, "grad": 0.1804, "tokens": 110723558400, "tok_s": 158901.6}
|
| 135 |
+
{"step": 105640, "epoch": 0.671, "loss": 1.77731, "ppl": 5.914, "lr": 0.003, "grad": 0.0678, "tokens": 110744524800, "tok_s": 158973.1}
|
| 136 |
+
{"step": 105660, "epoch": 0.671, "loss": 1.64497, "ppl": 5.181, "lr": 0.003, "grad": 0.0925, "tokens": 110765491200, "tok_s": 158751.5}
|
| 137 |
+
{"step": 105680, "epoch": 0.671, "loss": 1.74163, "ppl": 5.707, "lr": 0.003, "grad": 0.1118, "tokens": 110786457600, "tok_s": 159074.0}
|
| 138 |
+
{"step": 105700, "epoch": 0.672, "loss": 1.70014, "ppl": 5.475, "lr": 0.003, "grad": 0.163, "tokens": 110807424000, "tok_s": 159020.5}
|
| 139 |
+
{"step": 105720, "epoch": 0.672, "loss": 1.7869, "ppl": 5.971, "lr": 0.003, "grad": 0.1481, "tokens": 110828390400, "tok_s": 159177.7}
|
| 140 |
+
{"step": 105740, "epoch": 0.672, "loss": 1.61031, "ppl": 5.004, "lr": 0.003, "grad": 0.0901, "tokens": 110849356800, "tok_s": 158749.6}
|
| 141 |
+
{"step": 105760, "epoch": 0.672, "loss": 1.7785, "ppl": 5.921, "lr": 0.003, "grad": 0.1427, "tokens": 110870323200, "tok_s": 159106.9}
|
| 142 |
+
{"step": 105780, "epoch": 0.672, "loss": 1.78613, "ppl": 5.966, "lr": 0.003, "grad": 0.0907, "tokens": 110891289600, "tok_s": 158747.7}
|
| 143 |
+
{"step": 105800, "epoch": 0.672, "loss": 1.75972, "ppl": 5.811, "lr": 0.003, "grad": 0.0823, "tokens": 110912256000, "tok_s": 159199.7}
|
| 144 |
+
{"step": 105820, "epoch": 0.672, "loss": 1.77934, "ppl": 5.926, "lr": 0.003, "grad": 0.1421, "tokens": 110933222400, "tok_s": 159174.4}
|
| 145 |
+
{"step": 105840, "epoch": 0.672, "loss": 1.78072, "ppl": 5.934, "lr": 0.003, "grad": 0.1411, "tokens": 110954188800, "tok_s": 159082.7}
|
| 146 |
+
{"step": 105860, "epoch": 0.673, "loss": 1.80478, "ppl": 6.079, "lr": 0.003, "grad": 0.1266, "tokens": 110975155200, "tok_s": 159265.3}
|
| 147 |
+
{"step": 105880, "epoch": 0.673, "loss": 1.71682, "ppl": 5.567, "lr": 0.003, "grad": 0.0713, "tokens": 110996121600, "tok_s": 158888.2}
|
| 148 |
+
{"step": 105900, "epoch": 0.673, "loss": 1.77119, "ppl": 5.878, "lr": 0.003, "grad": 0.1137, "tokens": 111017088000, "tok_s": 158721.0}
|
| 149 |
+
{"step": 105920, "epoch": 0.673, "loss": 1.76743, "ppl": 5.856, "lr": 0.003, "grad": 0.0879, "tokens": 111038054400, "tok_s": 159106.7}
|
| 150 |
+
{"step": 105940, "epoch": 0.673, "loss": 1.73487, "ppl": 5.668, "lr": 0.003, "grad": 0.1173, "tokens": 111059020800, "tok_s": 158721.2}
|
| 151 |
+
{"step": 105960, "epoch": 0.673, "loss": 1.79097, "ppl": 5.995, "lr": 0.003, "grad": 0.1112, "tokens": 111079987200, "tok_s": 159015.9}
|
| 152 |
+
{"step": 105980, "epoch": 0.673, "loss": 1.76332, "ppl": 5.832, "lr": 0.003, "grad": 0.1556, "tokens": 111100953600, "tok_s": 158890.5}
|
| 153 |
+
{"step": 106000, "epoch": 0.673, "loss": 1.76822, "ppl": 5.86, "lr": 0.003, "grad": 0.1682, "tokens": 111121920000, "tok_s": 159095.2}
|
| 154 |
+
{"step": 106000, "val_loss": 1.75145, "val_ppl": 5.763, "is_best": false}
|
logs/log_107000.jsonl
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 103000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-04T05:34:52.650367"}
|
| 2 |
+
{"step": 103020, "epoch": 0.655, "loss": 1.74124, "ppl": 5.704, "lr": 0.003, "grad": 0.1737, "tokens": 107997926400, "tok_s": 157750.1}
|
| 3 |
+
{"step": 103040, "epoch": 0.655, "loss": 1.74289, "ppl": 5.714, "lr": 0.003, "grad": 0.1636, "tokens": 108018892800, "tok_s": 158638.8}
|
| 4 |
+
{"step": 103060, "epoch": 0.655, "loss": 1.71677, "ppl": 5.566, "lr": 0.003, "grad": 0.072, "tokens": 108039859200, "tok_s": 159090.9}
|
| 5 |
+
{"step": 103080, "epoch": 0.655, "loss": 1.61426, "ppl": 5.024, "lr": 0.003, "grad": 0.0842, "tokens": 108060825600, "tok_s": 159069.0}
|
| 6 |
+
{"step": 103100, "epoch": 0.655, "loss": 1.76967, "ppl": 5.869, "lr": 0.003, "grad": 0.1676, "tokens": 108081792000, "tok_s": 159265.0}
|
| 7 |
+
{"step": 103120, "epoch": 0.655, "loss": 1.73171, "ppl": 5.65, "lr": 0.003, "grad": 0.1788, "tokens": 108102758400, "tok_s": 159215.7}
|
| 8 |
+
{"step": 103140, "epoch": 0.655, "loss": 1.7461, "ppl": 5.732, "lr": 0.003, "grad": 0.1556, "tokens": 108123724800, "tok_s": 159252.4}
|
| 9 |
+
{"step": 103160, "epoch": 0.655, "loss": 1.67759, "ppl": 5.353, "lr": 0.003, "grad": 0.1307, "tokens": 108144691200, "tok_s": 159388.2}
|
| 10 |
+
{"step": 103180, "epoch": 0.656, "loss": 1.63079, "ppl": 5.108, "lr": 0.003, "grad": 0.0818, "tokens": 108165657600, "tok_s": 158915.5}
|
| 11 |
+
{"step": 103200, "epoch": 0.656, "loss": 1.59425, "ppl": 4.925, "lr": 0.003, "grad": 0.1396, "tokens": 108186624000, "tok_s": 159220.4}
|
| 12 |
+
{"step": 103220, "epoch": 0.656, "loss": 1.78181, "ppl": 5.941, "lr": 0.003, "grad": 0.1365, "tokens": 108207590400, "tok_s": 158956.6}
|
| 13 |
+
{"step": 103240, "epoch": 0.656, "loss": 1.70449, "ppl": 5.499, "lr": 0.003, "grad": 0.1402, "tokens": 108228556800, "tok_s": 159099.3}
|
| 14 |
+
{"step": 103260, "epoch": 0.656, "loss": 1.76033, "ppl": 5.814, "lr": 0.003, "grad": 0.1569, "tokens": 108249523200, "tok_s": 159076.4}
|
| 15 |
+
{"step": 103280, "epoch": 0.656, "loss": 1.71133, "ppl": 5.536, "lr": 0.003, "grad": 0.1348, "tokens": 108270489600, "tok_s": 159322.3}
|
| 16 |
+
{"step": 103300, "epoch": 0.656, "loss": 1.75602, "ppl": 5.789, "lr": 0.003, "grad": 0.133, "tokens": 108291456000, "tok_s": 159092.8}
|
| 17 |
+
{"step": 103320, "epoch": 0.656, "loss": 1.76105, "ppl": 5.819, "lr": 0.003, "grad": 0.0797, "tokens": 108312422400, "tok_s": 158991.1}
|
| 18 |
+
{"step": 103340, "epoch": 0.657, "loss": 1.72515, "ppl": 5.613, "lr": 0.003, "grad": 0.1414, "tokens": 108333388800, "tok_s": 158883.4}
|
| 19 |
+
{"step": 103360, "epoch": 0.657, "loss": 1.77313, "ppl": 5.889, "lr": 0.003, "grad": 0.141, "tokens": 108354355200, "tok_s": 159152.5}
|
| 20 |
+
{"step": 103380, "epoch": 0.657, "loss": 1.68315, "ppl": 5.382, "lr": 0.003, "grad": 0.1103, "tokens": 108375321600, "tok_s": 158884.2}
|
| 21 |
+
{"step": 103400, "epoch": 0.657, "loss": 1.78506, "ppl": 5.96, "lr": 0.003, "grad": 0.1633, "tokens": 108396288000, "tok_s": 159328.9}
|
| 22 |
+
{"step": 103420, "epoch": 0.657, "loss": 1.76313, "ppl": 5.831, "lr": 0.003, "grad": 0.1131, "tokens": 108417254400, "tok_s": 159196.1}
|
| 23 |
+
{"step": 103440, "epoch": 0.657, "loss": 1.67384, "ppl": 5.333, "lr": 0.003, "grad": 0.1986, "tokens": 108438220800, "tok_s": 159181.8}
|
| 24 |
+
{"step": 103460, "epoch": 0.657, "loss": 1.8131, "ppl": 6.129, "lr": 0.003, "grad": 0.0915, "tokens": 108459187200, "tok_s": 158871.5}
|
| 25 |
+
{"step": 103480, "epoch": 0.657, "loss": 1.80905, "ppl": 6.105, "lr": 0.003, "grad": 0.1683, "tokens": 108480153600, "tok_s": 159278.2}
|
| 26 |
+
{"step": 103500, "epoch": 0.658, "loss": 1.90143, "ppl": 6.695, "lr": 0.003, "grad": 0.1496, "tokens": 108501120000, "tok_s": 158915.3}
|
| 27 |
+
{"step": 103520, "epoch": 0.658, "loss": 1.76599, "ppl": 5.847, "lr": 0.003, "grad": 0.1804, "tokens": 108522086400, "tok_s": 158787.2}
|
| 28 |
+
{"step": 103540, "epoch": 0.658, "loss": 1.66056, "ppl": 5.262, "lr": 0.003, "grad": 0.1552, "tokens": 108543052800, "tok_s": 158658.2}
|
| 29 |
+
{"step": 103560, "epoch": 0.658, "loss": 1.68044, "ppl": 5.368, "lr": 0.003, "grad": 0.0855, "tokens": 108564019200, "tok_s": 159166.5}
|
| 30 |
+
{"step": 103580, "epoch": 0.658, "loss": 1.70551, "ppl": 5.504, "lr": 0.003, "grad": 0.1333, "tokens": 108584985600, "tok_s": 158797.9}
|
| 31 |
+
{"step": 103600, "epoch": 0.658, "loss": 1.64139, "ppl": 5.162, "lr": 0.003, "grad": 0.092, "tokens": 108605952000, "tok_s": 159140.5}
|
| 32 |
+
{"step": 103620, "epoch": 0.658, "loss": 1.71522, "ppl": 5.558, "lr": 0.003, "grad": 0.1698, "tokens": 108626918400, "tok_s": 159154.2}
|
| 33 |
+
{"step": 103640, "epoch": 0.658, "loss": 1.66387, "ppl": 5.28, "lr": 0.003, "grad": 0.1658, "tokens": 108647884800, "tok_s": 159108.1}
|
| 34 |
+
{"step": 103660, "epoch": 0.659, "loss": 1.84406, "ppl": 6.322, "lr": 0.003, "grad": 0.0839, "tokens": 108668851200, "tok_s": 159059.2}
|
| 35 |
+
{"step": 103680, "epoch": 0.659, "loss": 1.77286, "ppl": 5.888, "lr": 0.003, "grad": 0.1964, "tokens": 108689817600, "tok_s": 159131.7}
|
| 36 |
+
{"step": 103700, "epoch": 0.659, "loss": 1.74173, "ppl": 5.707, "lr": 0.003, "grad": 0.1256, "tokens": 108710784000, "tok_s": 158927.0}
|
| 37 |
+
{"step": 103720, "epoch": 0.659, "loss": 1.6683, "ppl": 5.303, "lr": 0.003, "grad": 0.1101, "tokens": 108731750400, "tok_s": 159215.4}
|
| 38 |
+
{"step": 103740, "epoch": 0.659, "loss": 1.70027, "ppl": 5.475, "lr": 0.003, "grad": 0.2066, "tokens": 108752716800, "tok_s": 159167.5}
|
| 39 |
+
{"step": 103760, "epoch": 0.659, "loss": 1.76893, "ppl": 5.865, "lr": 0.003, "grad": 0.2198, "tokens": 108773683200, "tok_s": 159097.2}
|
| 40 |
+
{"step": 103780, "epoch": 0.659, "loss": 1.67872, "ppl": 5.359, "lr": 0.003, "grad": 0.1615, "tokens": 108794649600, "tok_s": 159025.0}
|
| 41 |
+
{"step": 103800, "epoch": 0.66, "loss": 1.69452, "ppl": 5.444, "lr": 0.003, "grad": 0.1566, "tokens": 108815616000, "tok_s": 159177.5}
|
| 42 |
+
{"step": 103820, "epoch": 0.66, "loss": 1.74359, "ppl": 5.718, "lr": 0.003, "grad": 0.0974, "tokens": 108836582400, "tok_s": 159199.5}
|
| 43 |
+
{"step": 103840, "epoch": 0.66, "loss": 1.67706, "ppl": 5.35, "lr": 0.003, "grad": 0.104, "tokens": 108857548800, "tok_s": 159248.0}
|
| 44 |
+
{"step": 103860, "epoch": 0.66, "loss": 1.75409, "ppl": 5.778, "lr": 0.003, "grad": 0.1085, "tokens": 108878515200, "tok_s": 159090.0}
|
| 45 |
+
{"step": 103880, "epoch": 0.66, "loss": 1.78152, "ppl": 5.939, "lr": 0.003, "grad": 0.1585, "tokens": 108899481600, "tok_s": 159101.0}
|
| 46 |
+
{"step": 103900, "epoch": 0.66, "loss": 1.45016, "ppl": 4.264, "lr": 0.003, "grad": 0.1273, "tokens": 108920448000, "tok_s": 158927.5}
|
| 47 |
+
{"step": 103920, "epoch": 0.66, "loss": 1.68008, "ppl": 5.366, "lr": 0.003, "grad": 0.1713, "tokens": 108941414400, "tok_s": 159220.5}
|
| 48 |
+
{"step": 103940, "epoch": 0.66, "loss": 1.69084, "ppl": 5.424, "lr": 0.003, "grad": 0.0837, "tokens": 108962380800, "tok_s": 159170.3}
|
| 49 |
+
{"step": 103960, "epoch": 0.661, "loss": 1.78521, "ppl": 5.961, "lr": 0.003, "grad": 0.1482, "tokens": 108983347200, "tok_s": 159091.8}
|
| 50 |
+
{"step": 103980, "epoch": 0.661, "loss": 1.73619, "ppl": 5.676, "lr": 0.003, "grad": 0.1255, "tokens": 109004313600, "tok_s": 159215.5}
|
| 51 |
+
{"step": 104000, "epoch": 0.661, "loss": 1.89156, "ppl": 6.63, "lr": 0.003, "grad": 0.1592, "tokens": 109025280000, "tok_s": 158827.5}
|
| 52 |
+
{"step": 104000, "val_loss": 1.73307, "val_ppl": 5.658, "is_best": true}
|
| 53 |
+
{"step": 104020, "epoch": 0.661, "loss": 1.73662, "ppl": 5.678, "lr": 0.003, "grad": 0.1665, "tokens": 109046246400, "tok_s": 158997.7}
|
| 54 |
+
{"step": 104040, "epoch": 0.661, "loss": 1.6789, "ppl": 5.36, "lr": 0.003, "grad": 0.1479, "tokens": 109067212800, "tok_s": 159135.6}
|
| 55 |
+
{"step": 104060, "epoch": 0.661, "loss": 1.77655, "ppl": 5.909, "lr": 0.003, "grad": 0.0996, "tokens": 109088179200, "tok_s": 158830.7}
|
| 56 |
+
{"step": 104080, "epoch": 0.661, "loss": 1.72722, "ppl": 5.625, "lr": 0.003, "grad": 0.106, "tokens": 109109145600, "tok_s": 158995.1}
|
| 57 |
+
{"step": 104100, "epoch": 0.661, "loss": 1.59814, "ppl": 4.944, "lr": 0.003, "grad": 0.0722, "tokens": 109130112000, "tok_s": 158956.0}
|
| 58 |
+
{"step": 104120, "epoch": 0.662, "loss": 1.87211, "ppl": 6.502, "lr": 0.003, "grad": 0.1723, "tokens": 109151078400, "tok_s": 159004.9}
|
| 59 |
+
{"step": 104140, "epoch": 0.662, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.1128, "tokens": 109172044800, "tok_s": 158715.8}
|
| 60 |
+
{"step": 104160, "epoch": 0.662, "loss": 1.75281, "ppl": 5.771, "lr": 0.003, "grad": 0.1824, "tokens": 109193011200, "tok_s": 158738.1}
|
| 61 |
+
{"step": 104180, "epoch": 0.662, "loss": 1.79538, "ppl": 6.022, "lr": 0.003, "grad": 0.2017, "tokens": 109213977600, "tok_s": 158633.8}
|
| 62 |
+
{"step": 104200, "epoch": 0.662, "loss": 1.70962, "ppl": 5.527, "lr": 0.003, "grad": 0.1821, "tokens": 109234944000, "tok_s": 158863.6}
|
| 63 |
+
{"step": 104220, "epoch": 0.662, "loss": 1.78149, "ppl": 5.939, "lr": 0.003, "grad": 0.1032, "tokens": 109255910400, "tok_s": 159130.0}
|
| 64 |
+
{"step": 104240, "epoch": 0.662, "loss": 1.69264, "ppl": 5.434, "lr": 0.003, "grad": 0.0855, "tokens": 109276876800, "tok_s": 158660.9}
|
| 65 |
+
{"step": 104260, "epoch": 0.662, "loss": 1.72285, "ppl": 5.6, "lr": 0.003, "grad": 0.1449, "tokens": 109297843200, "tok_s": 158872.8}
|
| 66 |
+
{"step": 104280, "epoch": 0.663, "loss": 1.60635, "ppl": 4.985, "lr": 0.003, "grad": 0.1624, "tokens": 109318809600, "tok_s": 158882.7}
|
| 67 |
+
{"step": 104300, "epoch": 0.663, "loss": 1.80534, "ppl": 6.082, "lr": 0.003, "grad": 0.1375, "tokens": 109339776000, "tok_s": 158833.1}
|
| 68 |
+
{"step": 104320, "epoch": 0.663, "loss": 1.74444, "ppl": 5.723, "lr": 0.003, "grad": 0.1149, "tokens": 109360742400, "tok_s": 158947.3}
|
| 69 |
+
{"step": 104340, "epoch": 0.663, "loss": 1.79691, "ppl": 6.031, "lr": 0.003, "grad": 0.2072, "tokens": 109381708800, "tok_s": 158998.7}
|
| 70 |
+
{"step": 104360, "epoch": 0.663, "loss": 1.73588, "ppl": 5.674, "lr": 0.003, "grad": 0.1396, "tokens": 109402675200, "tok_s": 158683.7}
|
| 71 |
+
{"step": 104380, "epoch": 0.663, "loss": 1.8465, "ppl": 6.338, "lr": 0.003, "grad": 0.1107, "tokens": 109423641600, "tok_s": 158875.4}
|
| 72 |
+
{"step": 104400, "epoch": 0.663, "loss": 1.81251, "ppl": 6.126, "lr": 0.003, "grad": 0.0807, "tokens": 109444608000, "tok_s": 158669.8}
|
| 73 |
+
{"step": 104420, "epoch": 0.663, "loss": 1.7951, "ppl": 6.02, "lr": 0.003, "grad": 0.1246, "tokens": 109465574400, "tok_s": 158742.5}
|
| 74 |
+
{"step": 104440, "epoch": 0.664, "loss": 1.73516, "ppl": 5.67, "lr": 0.003, "grad": 0.0797, "tokens": 109486540800, "tok_s": 158811.7}
|
| 75 |
+
{"step": 104460, "epoch": 0.664, "loss": 1.77739, "ppl": 5.914, "lr": 0.003, "grad": 0.2092, "tokens": 109507507200, "tok_s": 159175.4}
|
| 76 |
+
{"step": 104480, "epoch": 0.664, "loss": 1.82117, "ppl": 6.179, "lr": 0.003, "grad": 0.1147, "tokens": 109528473600, "tok_s": 158902.0}
|
| 77 |
+
{"step": 104500, "epoch": 0.664, "loss": 1.78193, "ppl": 5.941, "lr": 0.003, "grad": 0.0972, "tokens": 109549440000, "tok_s": 158571.8}
|
| 78 |
+
{"step": 104520, "epoch": 0.664, "loss": 1.78727, "ppl": 5.973, "lr": 0.003, "grad": 0.1308, "tokens": 109570406400, "tok_s": 159003.7}
|
| 79 |
+
{"step": 104540, "epoch": 0.664, "loss": 1.71035, "ppl": 5.531, "lr": 0.003, "grad": 0.0935, "tokens": 109591372800, "tok_s": 158566.8}
|
| 80 |
+
{"step": 104560, "epoch": 0.664, "loss": 1.79273, "ppl": 6.006, "lr": 0.003, "grad": 0.1619, "tokens": 109612339200, "tok_s": 159022.1}
|
| 81 |
+
{"step": 104580, "epoch": 0.664, "loss": 1.59285, "ppl": 4.918, "lr": 0.003, "grad": 0.0923, "tokens": 109633305600, "tok_s": 158996.6}
|
| 82 |
+
{"step": 104600, "epoch": 0.665, "loss": 1.76848, "ppl": 5.862, "lr": 0.003, "grad": 0.0946, "tokens": 109654272000, "tok_s": 159063.0}
|
| 83 |
+
{"step": 104620, "epoch": 0.665, "loss": 1.76793, "ppl": 5.859, "lr": 0.003, "grad": 0.0949, "tokens": 109675238400, "tok_s": 158677.9}
|
| 84 |
+
{"step": 104640, "epoch": 0.665, "loss": 1.73267, "ppl": 5.656, "lr": 0.003, "grad": 0.1246, "tokens": 109696204800, "tok_s": 159086.8}
|
| 85 |
+
{"step": 104660, "epoch": 0.665, "loss": 1.78542, "ppl": 5.962, "lr": 0.003, "grad": 0.08, "tokens": 109717171200, "tok_s": 159076.5}
|
| 86 |
+
{"step": 104680, "epoch": 0.665, "loss": 1.75886, "ppl": 5.806, "lr": 0.003, "grad": 0.125, "tokens": 109738137600, "tok_s": 159037.3}
|
| 87 |
+
{"step": 104700, "epoch": 0.665, "loss": 1.73196, "ppl": 5.652, "lr": 0.003, "grad": 0.1015, "tokens": 109759104000, "tok_s": 158854.1}
|
| 88 |
+
{"step": 104720, "epoch": 0.665, "loss": 1.7098, "ppl": 5.528, "lr": 0.003, "grad": 0.1101, "tokens": 109780070400, "tok_s": 159124.5}
|
| 89 |
+
{"step": 104740, "epoch": 0.665, "loss": 1.74681, "ppl": 5.736, "lr": 0.003, "grad": 0.1051, "tokens": 109801036800, "tok_s": 159026.5}
|
| 90 |
+
{"step": 104760, "epoch": 0.666, "loss": 1.63925, "ppl": 5.151, "lr": 0.003, "grad": 0.0543, "tokens": 109822003200, "tok_s": 158990.3}
|
| 91 |
+
{"step": 104780, "epoch": 0.666, "loss": 1.71809, "ppl": 5.574, "lr": 0.003, "grad": 0.1393, "tokens": 109842969600, "tok_s": 159137.8}
|
| 92 |
+
{"step": 104800, "epoch": 0.666, "loss": 1.74093, "ppl": 5.703, "lr": 0.003, "grad": 0.1612, "tokens": 109863936000, "tok_s": 158846.4}
|
| 93 |
+
{"step": 104820, "epoch": 0.666, "loss": 1.76485, "ppl": 5.841, "lr": 0.003, "grad": 0.1143, "tokens": 109884902400, "tok_s": 158972.5}
|
| 94 |
+
{"step": 104840, "epoch": 0.666, "loss": 1.78046, "ppl": 5.933, "lr": 0.003, "grad": 0.085, "tokens": 109905868800, "tok_s": 158689.6}
|
| 95 |
+
{"step": 104860, "epoch": 0.666, "loss": 1.79138, "ppl": 5.998, "lr": 0.003, "grad": 0.0665, "tokens": 109926835200, "tok_s": 158956.5}
|
| 96 |
+
{"step": 104880, "epoch": 0.666, "loss": 1.77218, "ppl": 5.884, "lr": 0.003, "grad": 0.1442, "tokens": 109947801600, "tok_s": 159018.8}
|
| 97 |
+
{"step": 104900, "epoch": 0.666, "loss": 1.75558, "ppl": 5.787, "lr": 0.003, "grad": 0.1406, "tokens": 109968768000, "tok_s": 158995.5}
|
| 98 |
+
{"step": 104920, "epoch": 0.667, "loss": 1.78012, "ppl": 5.931, "lr": 0.003, "grad": 0.1164, "tokens": 109989734400, "tok_s": 158956.1}
|
| 99 |
+
{"step": 104940, "epoch": 0.667, "loss": 1.7293, "ppl": 5.637, "lr": 0.003, "grad": 0.0836, "tokens": 110010700800, "tok_s": 158958.7}
|
| 100 |
+
{"step": 104960, "epoch": 0.667, "loss": 1.75256, "ppl": 5.769, "lr": 0.003, "grad": 0.145, "tokens": 110031667200, "tok_s": 158967.2}
|
| 101 |
+
{"step": 104980, "epoch": 0.667, "loss": 1.79842, "ppl": 6.04, "lr": 0.003, "grad": 0.141, "tokens": 110052633600, "tok_s": 159126.4}
|
| 102 |
+
{"step": 105000, "epoch": 0.667, "loss": 1.72704, "ppl": 5.624, "lr": 0.003, "grad": 0.1398, "tokens": 110073600000, "tok_s": 158991.1}
|
| 103 |
+
{"step": 105000, "val_loss": 1.74304, "val_ppl": 5.715, "is_best": false}
|
| 104 |
+
{"step": 105020, "epoch": 0.667, "loss": 1.76215, "ppl": 5.825, "lr": 0.003, "grad": 0.1806, "tokens": 110094566400, "tok_s": 158671.8}
|
| 105 |
+
{"step": 105040, "epoch": 0.667, "loss": 1.75137, "ppl": 5.763, "lr": 0.003, "grad": 0.0962, "tokens": 110115532800, "tok_s": 158974.6}
|
| 106 |
+
{"step": 105060, "epoch": 0.668, "loss": 1.69628, "ppl": 5.454, "lr": 0.003, "grad": 0.0863, "tokens": 110136499200, "tok_s": 158912.0}
|
| 107 |
+
{"step": 105080, "epoch": 0.668, "loss": 1.76755, "ppl": 5.856, "lr": 0.003, "grad": 0.1386, "tokens": 110157465600, "tok_s": 158756.9}
|
| 108 |
+
{"step": 105100, "epoch": 0.668, "loss": 1.75679, "ppl": 5.794, "lr": 0.003, "grad": 0.1659, "tokens": 110178432000, "tok_s": 158854.3}
|
| 109 |
+
{"step": 105120, "epoch": 0.668, "loss": 1.83078, "ppl": 6.239, "lr": 0.003, "grad": 0.0992, "tokens": 110199398400, "tok_s": 158941.0}
|
| 110 |
+
{"step": 105140, "epoch": 0.668, "loss": 1.772, "ppl": 5.883, "lr": 0.003, "grad": 0.096, "tokens": 110220364800, "tok_s": 159249.8}
|
| 111 |
+
{"step": 105160, "epoch": 0.668, "loss": 1.72506, "ppl": 5.613, "lr": 0.003, "grad": 0.1498, "tokens": 110241331200, "tok_s": 158660.2}
|
| 112 |
+
{"step": 105180, "epoch": 0.668, "loss": 1.7513, "ppl": 5.762, "lr": 0.003, "grad": 0.1525, "tokens": 110262297600, "tok_s": 158921.5}
|
| 113 |
+
{"step": 105200, "epoch": 0.668, "loss": 1.80524, "ppl": 6.081, "lr": 0.003, "grad": 0.1137, "tokens": 110283264000, "tok_s": 158794.3}
|
| 114 |
+
{"step": 105220, "epoch": 0.669, "loss": 1.7043, "ppl": 5.498, "lr": 0.003, "grad": 0.0862, "tokens": 110304230400, "tok_s": 159014.6}
|
| 115 |
+
{"step": 105240, "epoch": 0.669, "loss": 1.75034, "ppl": 5.757, "lr": 0.003, "grad": 0.1358, "tokens": 110325196800, "tok_s": 158690.7}
|
| 116 |
+
{"step": 105260, "epoch": 0.669, "loss": 1.66413, "ppl": 5.281, "lr": 0.003, "grad": 0.0687, "tokens": 110346163200, "tok_s": 158623.5}
|
| 117 |
+
{"step": 105280, "epoch": 0.669, "loss": 1.76264, "ppl": 5.828, "lr": 0.003, "grad": 0.1444, "tokens": 110367129600, "tok_s": 158682.2}
|
| 118 |
+
{"step": 105300, "epoch": 0.669, "loss": 1.78643, "ppl": 5.968, "lr": 0.003, "grad": 0.1082, "tokens": 110388096000, "tok_s": 158903.4}
|
| 119 |
+
{"step": 105320, "epoch": 0.669, "loss": 1.66896, "ppl": 5.307, "lr": 0.003, "grad": 0.0696, "tokens": 110409062400, "tok_s": 159098.4}
|
| 120 |
+
{"step": 105340, "epoch": 0.669, "loss": 1.63363, "ppl": 5.122, "lr": 0.003, "grad": 0.1139, "tokens": 110430028800, "tok_s": 158622.7}
|
| 121 |
+
{"step": 105360, "epoch": 0.669, "loss": 1.76022, "ppl": 5.814, "lr": 0.003, "grad": 0.1553, "tokens": 110450995200, "tok_s": 158832.6}
|
| 122 |
+
{"step": 105380, "epoch": 0.67, "loss": 1.73319, "ppl": 5.659, "lr": 0.003, "grad": 0.1156, "tokens": 110471961600, "tok_s": 158747.8}
|
| 123 |
+
{"step": 105400, "epoch": 0.67, "loss": 1.64827, "ppl": 5.198, "lr": 0.003, "grad": 0.0792, "tokens": 110492928000, "tok_s": 159063.9}
|
| 124 |
+
{"step": 105420, "epoch": 0.67, "loss": 1.66882, "ppl": 5.306, "lr": 0.003, "grad": 0.0799, "tokens": 110513894400, "tok_s": 158993.6}
|
| 125 |
+
{"step": 105440, "epoch": 0.67, "loss": 1.85582, "ppl": 6.397, "lr": 0.003, "grad": 0.1864, "tokens": 110534860800, "tok_s": 159145.8}
|
| 126 |
+
{"step": 105460, "epoch": 0.67, "loss": 1.64841, "ppl": 5.199, "lr": 0.003, "grad": 0.1361, "tokens": 110555827200, "tok_s": 158950.5}
|
| 127 |
+
{"step": 105480, "epoch": 0.67, "loss": 1.72625, "ppl": 5.62, "lr": 0.003, "grad": 0.107, "tokens": 110576793600, "tok_s": 159055.6}
|
| 128 |
+
{"step": 105500, "epoch": 0.67, "loss": 1.70148, "ppl": 5.482, "lr": 0.003, "grad": 0.0887, "tokens": 110597760000, "tok_s": 158735.0}
|
| 129 |
+
{"step": 105520, "epoch": 0.67, "loss": 1.71477, "ppl": 5.555, "lr": 0.003, "grad": 0.0792, "tokens": 110618726400, "tok_s": 158689.6}
|
| 130 |
+
{"step": 105540, "epoch": 0.671, "loss": 1.71728, "ppl": 5.569, "lr": 0.003, "grad": 0.123, "tokens": 110639692800, "tok_s": 158888.5}
|
| 131 |
+
{"step": 105560, "epoch": 0.671, "loss": 1.81532, "ppl": 6.143, "lr": 0.003, "grad": 0.1478, "tokens": 110660659200, "tok_s": 158992.0}
|
| 132 |
+
{"step": 105580, "epoch": 0.671, "loss": 1.74605, "ppl": 5.732, "lr": 0.003, "grad": 0.1198, "tokens": 110681625600, "tok_s": 158645.1}
|
| 133 |
+
{"step": 105600, "epoch": 0.671, "loss": 1.77535, "ppl": 5.902, "lr": 0.003, "grad": 0.0567, "tokens": 110702592000, "tok_s": 158893.2}
|
| 134 |
+
{"step": 105620, "epoch": 0.671, "loss": 1.73959, "ppl": 5.695, "lr": 0.003, "grad": 0.1804, "tokens": 110723558400, "tok_s": 158901.6}
|
| 135 |
+
{"step": 105640, "epoch": 0.671, "loss": 1.77731, "ppl": 5.914, "lr": 0.003, "grad": 0.0678, "tokens": 110744524800, "tok_s": 158973.1}
|
| 136 |
+
{"step": 105660, "epoch": 0.671, "loss": 1.64497, "ppl": 5.181, "lr": 0.003, "grad": 0.0925, "tokens": 110765491200, "tok_s": 158751.5}
|
| 137 |
+
{"step": 105680, "epoch": 0.671, "loss": 1.74163, "ppl": 5.707, "lr": 0.003, "grad": 0.1118, "tokens": 110786457600, "tok_s": 159074.0}
|
| 138 |
+
{"step": 105700, "epoch": 0.672, "loss": 1.70014, "ppl": 5.475, "lr": 0.003, "grad": 0.163, "tokens": 110807424000, "tok_s": 159020.5}
|
| 139 |
+
{"step": 105720, "epoch": 0.672, "loss": 1.7869, "ppl": 5.971, "lr": 0.003, "grad": 0.1481, "tokens": 110828390400, "tok_s": 159177.7}
|
| 140 |
+
{"step": 105740, "epoch": 0.672, "loss": 1.61031, "ppl": 5.004, "lr": 0.003, "grad": 0.0901, "tokens": 110849356800, "tok_s": 158749.6}
|
| 141 |
+
{"step": 105760, "epoch": 0.672, "loss": 1.7785, "ppl": 5.921, "lr": 0.003, "grad": 0.1427, "tokens": 110870323200, "tok_s": 159106.9}
|
| 142 |
+
{"step": 105780, "epoch": 0.672, "loss": 1.78613, "ppl": 5.966, "lr": 0.003, "grad": 0.0907, "tokens": 110891289600, "tok_s": 158747.7}
|
| 143 |
+
{"step": 105800, "epoch": 0.672, "loss": 1.75972, "ppl": 5.811, "lr": 0.003, "grad": 0.0823, "tokens": 110912256000, "tok_s": 159199.7}
|
| 144 |
+
{"step": 105820, "epoch": 0.672, "loss": 1.77934, "ppl": 5.926, "lr": 0.003, "grad": 0.1421, "tokens": 110933222400, "tok_s": 159174.4}
|
| 145 |
+
{"step": 105840, "epoch": 0.672, "loss": 1.78072, "ppl": 5.934, "lr": 0.003, "grad": 0.1411, "tokens": 110954188800, "tok_s": 159082.7}
|
| 146 |
+
{"step": 105860, "epoch": 0.673, "loss": 1.80478, "ppl": 6.079, "lr": 0.003, "grad": 0.1266, "tokens": 110975155200, "tok_s": 159265.3}
|
| 147 |
+
{"step": 105880, "epoch": 0.673, "loss": 1.71682, "ppl": 5.567, "lr": 0.003, "grad": 0.0713, "tokens": 110996121600, "tok_s": 158888.2}
|
| 148 |
+
{"step": 105900, "epoch": 0.673, "loss": 1.77119, "ppl": 5.878, "lr": 0.003, "grad": 0.1137, "tokens": 111017088000, "tok_s": 158721.0}
|
| 149 |
+
{"step": 105920, "epoch": 0.673, "loss": 1.76743, "ppl": 5.856, "lr": 0.003, "grad": 0.0879, "tokens": 111038054400, "tok_s": 159106.7}
|
| 150 |
+
{"step": 105940, "epoch": 0.673, "loss": 1.73487, "ppl": 5.668, "lr": 0.003, "grad": 0.1173, "tokens": 111059020800, "tok_s": 158721.2}
|
| 151 |
+
{"step": 105960, "epoch": 0.673, "loss": 1.79097, "ppl": 5.995, "lr": 0.003, "grad": 0.1112, "tokens": 111079987200, "tok_s": 159015.9}
|
| 152 |
+
{"step": 105980, "epoch": 0.673, "loss": 1.76332, "ppl": 5.832, "lr": 0.003, "grad": 0.1556, "tokens": 111100953600, "tok_s": 158890.5}
|
| 153 |
+
{"step": 106000, "epoch": 0.673, "loss": 1.76822, "ppl": 5.86, "lr": 0.003, "grad": 0.1682, "tokens": 111121920000, "tok_s": 159095.2}
|
| 154 |
+
{"step": 106000, "val_loss": 1.75145, "val_ppl": 5.763, "is_best": false}
|
| 155 |
+
{"step": 106020, "epoch": 0.674, "loss": 1.69846, "ppl": 5.465, "lr": 0.003, "grad": 0.1133, "tokens": 111142886400, "tok_s": 158627.0}
|
| 156 |
+
{"step": 106040, "epoch": 0.674, "loss": 1.75588, "ppl": 5.789, "lr": 0.003, "grad": 0.1398, "tokens": 111163852800, "tok_s": 158986.6}
|
| 157 |
+
{"step": 106060, "epoch": 0.674, "loss": 1.73895, "ppl": 5.691, "lr": 0.003, "grad": 0.1201, "tokens": 111184819200, "tok_s": 159077.8}
|
| 158 |
+
{"step": 106080, "epoch": 0.674, "loss": 1.77928, "ppl": 5.926, "lr": 0.003, "grad": 0.1641, "tokens": 111205785600, "tok_s": 158731.6}
|
| 159 |
+
{"step": 106100, "epoch": 0.674, "loss": 1.77578, "ppl": 5.905, "lr": 0.003, "grad": 0.0847, "tokens": 111226752000, "tok_s": 158920.3}
|
| 160 |
+
{"step": 106120, "epoch": 0.674, "loss": 1.74289, "ppl": 5.714, "lr": 0.003, "grad": 0.1248, "tokens": 111247718400, "tok_s": 159159.5}
|
| 161 |
+
{"step": 106140, "epoch": 0.674, "loss": 1.72757, "ppl": 5.627, "lr": 0.003, "grad": 0.1132, "tokens": 111268684800, "tok_s": 158656.1}
|
| 162 |
+
{"step": 106160, "epoch": 0.675, "loss": 1.73902, "ppl": 5.692, "lr": 0.003, "grad": 0.1502, "tokens": 111289651200, "tok_s": 158645.5}
|
| 163 |
+
{"step": 106180, "epoch": 0.675, "loss": 1.68355, "ppl": 5.385, "lr": 0.003, "grad": 0.093, "tokens": 111310617600, "tok_s": 158128.2}
|
| 164 |
+
{"step": 106200, "epoch": 0.675, "loss": 1.74524, "ppl": 5.727, "lr": 0.003, "grad": 0.0942, "tokens": 111331584000, "tok_s": 158672.0}
|
| 165 |
+
{"step": 106220, "epoch": 0.675, "loss": 1.73209, "ppl": 5.652, "lr": 0.003, "grad": 0.0934, "tokens": 111352550400, "tok_s": 158635.5}
|
| 166 |
+
{"step": 106240, "epoch": 0.675, "loss": 1.7352, "ppl": 5.67, "lr": 0.003, "grad": 0.1363, "tokens": 111373516800, "tok_s": 159019.7}
|
| 167 |
+
{"step": 106260, "epoch": 0.675, "loss": 1.74852, "ppl": 5.746, "lr": 0.003, "grad": 0.1467, "tokens": 111394483200, "tok_s": 158402.8}
|
| 168 |
+
{"step": 106280, "epoch": 0.675, "loss": 1.771, "ppl": 5.877, "lr": 0.003, "grad": 0.0893, "tokens": 111415449600, "tok_s": 158670.0}
|
| 169 |
+
{"step": 106300, "epoch": 0.675, "loss": 1.82433, "ppl": 6.199, "lr": 0.003, "grad": 0.0874, "tokens": 111436416000, "tok_s": 158221.7}
|
| 170 |
+
{"step": 106320, "epoch": 0.676, "loss": 1.72527, "ppl": 5.614, "lr": 0.003, "grad": 0.0792, "tokens": 111457382400, "tok_s": 158663.7}
|
| 171 |
+
{"step": 106340, "epoch": 0.676, "loss": 1.75491, "ppl": 5.783, "lr": 0.003, "grad": 0.1451, "tokens": 111478348800, "tok_s": 158730.6}
|
| 172 |
+
{"step": 106360, "epoch": 0.676, "loss": 1.74147, "ppl": 5.706, "lr": 0.003, "grad": 0.0831, "tokens": 111499315200, "tok_s": 158842.0}
|
| 173 |
+
{"step": 106380, "epoch": 0.676, "loss": 1.6952, "ppl": 5.448, "lr": 0.003, "grad": 0.1765, "tokens": 111520281600, "tok_s": 158518.0}
|
| 174 |
+
{"step": 106400, "epoch": 0.676, "loss": 1.71558, "ppl": 5.56, "lr": 0.003, "grad": 0.0933, "tokens": 111541248000, "tok_s": 159022.1}
|
| 175 |
+
{"step": 106420, "epoch": 0.676, "loss": 1.74255, "ppl": 5.712, "lr": 0.003, "grad": 0.1161, "tokens": 111562214400, "tok_s": 158900.8}
|
| 176 |
+
{"step": 106440, "epoch": 0.676, "loss": 1.72939, "ppl": 5.637, "lr": 0.003, "grad": 0.0949, "tokens": 111583180800, "tok_s": 158143.8}
|
| 177 |
+
{"step": 106460, "epoch": 0.676, "loss": 1.74077, "ppl": 5.702, "lr": 0.003, "grad": 0.056, "tokens": 111604147200, "tok_s": 158801.8}
|
| 178 |
+
{"step": 106480, "epoch": 0.677, "loss": 1.65382, "ppl": 5.227, "lr": 0.003, "grad": 0.1495, "tokens": 111625113600, "tok_s": 158843.9}
|
| 179 |
+
{"step": 106500, "epoch": 0.677, "loss": 1.86545, "ppl": 6.459, "lr": 0.003, "grad": 0.1017, "tokens": 111646080000, "tok_s": 158862.1}
|
| 180 |
+
{"step": 106520, "epoch": 0.677, "loss": 1.79127, "ppl": 5.997, "lr": 0.003, "grad": 0.0986, "tokens": 111667046400, "tok_s": 158428.3}
|
| 181 |
+
{"step": 106540, "epoch": 0.677, "loss": 1.69771, "ppl": 5.461, "lr": 0.003, "grad": 0.0667, "tokens": 111688012800, "tok_s": 159026.3}
|
| 182 |
+
{"step": 106560, "epoch": 0.677, "loss": 1.85277, "ppl": 6.377, "lr": 0.003, "grad": 0.1884, "tokens": 111708979200, "tok_s": 158904.1}
|
| 183 |
+
{"step": 106580, "epoch": 0.677, "loss": 1.73439, "ppl": 5.665, "lr": 0.003, "grad": 0.0549, "tokens": 111729945600, "tok_s": 159133.6}
|
| 184 |
+
{"step": 106600, "epoch": 0.677, "loss": 1.82285, "ppl": 6.189, "lr": 0.003, "grad": 0.1159, "tokens": 111750912000, "tok_s": 158845.7}
|
| 185 |
+
{"step": 106620, "epoch": 0.677, "loss": 1.73941, "ppl": 5.694, "lr": 0.003, "grad": 0.1109, "tokens": 111771878400, "tok_s": 159003.1}
|
| 186 |
+
{"step": 106640, "epoch": 0.678, "loss": 1.75547, "ppl": 5.786, "lr": 0.003, "grad": 0.0886, "tokens": 111792844800, "tok_s": 158787.6}
|
| 187 |
+
{"step": 106660, "epoch": 0.678, "loss": 1.6383, "ppl": 5.146, "lr": 0.003, "grad": 0.1472, "tokens": 111813811200, "tok_s": 159093.1}
|
| 188 |
+
{"step": 106680, "epoch": 0.678, "loss": 1.46855, "ppl": 4.343, "lr": 0.003, "grad": 0.0733, "tokens": 111834777600, "tok_s": 158856.7}
|
| 189 |
+
{"step": 106700, "epoch": 0.678, "loss": 1.80103, "ppl": 6.056, "lr": 0.003, "grad": 0.1077, "tokens": 111855744000, "tok_s": 159000.6}
|
| 190 |
+
{"step": 106720, "epoch": 0.678, "loss": 1.70293, "ppl": 5.49, "lr": 0.003, "grad": 0.1523, "tokens": 111876710400, "tok_s": 159060.9}
|
| 191 |
+
{"step": 106740, "epoch": 0.678, "loss": 1.71797, "ppl": 5.573, "lr": 0.003, "grad": 0.0874, "tokens": 111897676800, "tok_s": 159170.3}
|
| 192 |
+
{"step": 106760, "epoch": 0.678, "loss": 1.74612, "ppl": 5.732, "lr": 0.003, "grad": 0.1351, "tokens": 111918643200, "tok_s": 158878.2}
|
| 193 |
+
{"step": 106780, "epoch": 0.678, "loss": 1.70947, "ppl": 5.526, "lr": 0.003, "grad": 0.1471, "tokens": 111939609600, "tok_s": 159044.1}
|
| 194 |
+
{"step": 106800, "epoch": 0.679, "loss": 1.76839, "ppl": 5.861, "lr": 0.003, "grad": 0.1151, "tokens": 111960576000, "tok_s": 159015.0}
|
| 195 |
+
{"step": 106820, "epoch": 0.679, "loss": 1.75148, "ppl": 5.763, "lr": 0.003, "grad": 0.101, "tokens": 111981542400, "tok_s": 159038.3}
|
| 196 |
+
{"step": 106840, "epoch": 0.679, "loss": 1.76693, "ppl": 5.853, "lr": 0.003, "grad": 0.0988, "tokens": 112002508800, "tok_s": 158604.0}
|
| 197 |
+
{"step": 106860, "epoch": 0.679, "loss": 1.74152, "ppl": 5.706, "lr": 0.003, "grad": 0.1404, "tokens": 112023475200, "tok_s": 158987.0}
|
| 198 |
+
{"step": 106880, "epoch": 0.679, "loss": 1.7451, "ppl": 5.726, "lr": 0.003, "grad": 0.0941, "tokens": 112044441600, "tok_s": 158901.4}
|
| 199 |
+
{"step": 106900, "epoch": 0.679, "loss": 1.73282, "ppl": 5.657, "lr": 0.003, "grad": 0.1308, "tokens": 112065408000, "tok_s": 158731.6}
|
| 200 |
+
{"step": 106920, "epoch": 0.679, "loss": 1.73412, "ppl": 5.664, "lr": 0.003, "grad": 0.1138, "tokens": 112086374400, "tok_s": 158895.0}
|
| 201 |
+
{"step": 106940, "epoch": 0.679, "loss": 1.74119, "ppl": 5.704, "lr": 0.003, "grad": 0.1453, "tokens": 112107340800, "tok_s": 159026.8}
|
| 202 |
+
{"step": 106960, "epoch": 0.68, "loss": 1.77176, "ppl": 5.881, "lr": 0.003, "grad": 0.1112, "tokens": 112128307200, "tok_s": 159001.9}
|
| 203 |
+
{"step": 106980, "epoch": 0.68, "loss": 1.73934, "ppl": 5.694, "lr": 0.003, "grad": 0.143, "tokens": 112149273600, "tok_s": 159014.6}
|
| 204 |
+
{"step": 107000, "epoch": 0.68, "loss": 1.76938, "ppl": 5.867, "lr": 0.003, "grad": 0.1606, "tokens": 112170240000, "tok_s": 159003.9}
|
| 205 |
+
{"step": 107000, "val_loss": 1.75256, "val_ppl": 5.769, "is_best": false}
|
logs/log_108000.jsonl
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 103000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-04T05:34:52.650367"}
|
| 2 |
+
{"step": 103020, "epoch": 0.655, "loss": 1.74124, "ppl": 5.704, "lr": 0.003, "grad": 0.1737, "tokens": 107997926400, "tok_s": 157750.1}
|
| 3 |
+
{"step": 103040, "epoch": 0.655, "loss": 1.74289, "ppl": 5.714, "lr": 0.003, "grad": 0.1636, "tokens": 108018892800, "tok_s": 158638.8}
|
| 4 |
+
{"step": 103060, "epoch": 0.655, "loss": 1.71677, "ppl": 5.566, "lr": 0.003, "grad": 0.072, "tokens": 108039859200, "tok_s": 159090.9}
|
| 5 |
+
{"step": 103080, "epoch": 0.655, "loss": 1.61426, "ppl": 5.024, "lr": 0.003, "grad": 0.0842, "tokens": 108060825600, "tok_s": 159069.0}
|
| 6 |
+
{"step": 103100, "epoch": 0.655, "loss": 1.76967, "ppl": 5.869, "lr": 0.003, "grad": 0.1676, "tokens": 108081792000, "tok_s": 159265.0}
|
| 7 |
+
{"step": 103120, "epoch": 0.655, "loss": 1.73171, "ppl": 5.65, "lr": 0.003, "grad": 0.1788, "tokens": 108102758400, "tok_s": 159215.7}
|
| 8 |
+
{"step": 103140, "epoch": 0.655, "loss": 1.7461, "ppl": 5.732, "lr": 0.003, "grad": 0.1556, "tokens": 108123724800, "tok_s": 159252.4}
|
| 9 |
+
{"step": 103160, "epoch": 0.655, "loss": 1.67759, "ppl": 5.353, "lr": 0.003, "grad": 0.1307, "tokens": 108144691200, "tok_s": 159388.2}
|
| 10 |
+
{"step": 103180, "epoch": 0.656, "loss": 1.63079, "ppl": 5.108, "lr": 0.003, "grad": 0.0818, "tokens": 108165657600, "tok_s": 158915.5}
|
| 11 |
+
{"step": 103200, "epoch": 0.656, "loss": 1.59425, "ppl": 4.925, "lr": 0.003, "grad": 0.1396, "tokens": 108186624000, "tok_s": 159220.4}
|
| 12 |
+
{"step": 103220, "epoch": 0.656, "loss": 1.78181, "ppl": 5.941, "lr": 0.003, "grad": 0.1365, "tokens": 108207590400, "tok_s": 158956.6}
|
| 13 |
+
{"step": 103240, "epoch": 0.656, "loss": 1.70449, "ppl": 5.499, "lr": 0.003, "grad": 0.1402, "tokens": 108228556800, "tok_s": 159099.3}
|
| 14 |
+
{"step": 103260, "epoch": 0.656, "loss": 1.76033, "ppl": 5.814, "lr": 0.003, "grad": 0.1569, "tokens": 108249523200, "tok_s": 159076.4}
|
| 15 |
+
{"step": 103280, "epoch": 0.656, "loss": 1.71133, "ppl": 5.536, "lr": 0.003, "grad": 0.1348, "tokens": 108270489600, "tok_s": 159322.3}
|
| 16 |
+
{"step": 103300, "epoch": 0.656, "loss": 1.75602, "ppl": 5.789, "lr": 0.003, "grad": 0.133, "tokens": 108291456000, "tok_s": 159092.8}
|
| 17 |
+
{"step": 103320, "epoch": 0.656, "loss": 1.76105, "ppl": 5.819, "lr": 0.003, "grad": 0.0797, "tokens": 108312422400, "tok_s": 158991.1}
|
| 18 |
+
{"step": 103340, "epoch": 0.657, "loss": 1.72515, "ppl": 5.613, "lr": 0.003, "grad": 0.1414, "tokens": 108333388800, "tok_s": 158883.4}
|
| 19 |
+
{"step": 103360, "epoch": 0.657, "loss": 1.77313, "ppl": 5.889, "lr": 0.003, "grad": 0.141, "tokens": 108354355200, "tok_s": 159152.5}
|
| 20 |
+
{"step": 103380, "epoch": 0.657, "loss": 1.68315, "ppl": 5.382, "lr": 0.003, "grad": 0.1103, "tokens": 108375321600, "tok_s": 158884.2}
|
| 21 |
+
{"step": 103400, "epoch": 0.657, "loss": 1.78506, "ppl": 5.96, "lr": 0.003, "grad": 0.1633, "tokens": 108396288000, "tok_s": 159328.9}
|
| 22 |
+
{"step": 103420, "epoch": 0.657, "loss": 1.76313, "ppl": 5.831, "lr": 0.003, "grad": 0.1131, "tokens": 108417254400, "tok_s": 159196.1}
|
| 23 |
+
{"step": 103440, "epoch": 0.657, "loss": 1.67384, "ppl": 5.333, "lr": 0.003, "grad": 0.1986, "tokens": 108438220800, "tok_s": 159181.8}
|
| 24 |
+
{"step": 103460, "epoch": 0.657, "loss": 1.8131, "ppl": 6.129, "lr": 0.003, "grad": 0.0915, "tokens": 108459187200, "tok_s": 158871.5}
|
| 25 |
+
{"step": 103480, "epoch": 0.657, "loss": 1.80905, "ppl": 6.105, "lr": 0.003, "grad": 0.1683, "tokens": 108480153600, "tok_s": 159278.2}
|
| 26 |
+
{"step": 103500, "epoch": 0.658, "loss": 1.90143, "ppl": 6.695, "lr": 0.003, "grad": 0.1496, "tokens": 108501120000, "tok_s": 158915.3}
|
| 27 |
+
{"step": 103520, "epoch": 0.658, "loss": 1.76599, "ppl": 5.847, "lr": 0.003, "grad": 0.1804, "tokens": 108522086400, "tok_s": 158787.2}
|
| 28 |
+
{"step": 103540, "epoch": 0.658, "loss": 1.66056, "ppl": 5.262, "lr": 0.003, "grad": 0.1552, "tokens": 108543052800, "tok_s": 158658.2}
|
| 29 |
+
{"step": 103560, "epoch": 0.658, "loss": 1.68044, "ppl": 5.368, "lr": 0.003, "grad": 0.0855, "tokens": 108564019200, "tok_s": 159166.5}
|
| 30 |
+
{"step": 103580, "epoch": 0.658, "loss": 1.70551, "ppl": 5.504, "lr": 0.003, "grad": 0.1333, "tokens": 108584985600, "tok_s": 158797.9}
|
| 31 |
+
{"step": 103600, "epoch": 0.658, "loss": 1.64139, "ppl": 5.162, "lr": 0.003, "grad": 0.092, "tokens": 108605952000, "tok_s": 159140.5}
|
| 32 |
+
{"step": 103620, "epoch": 0.658, "loss": 1.71522, "ppl": 5.558, "lr": 0.003, "grad": 0.1698, "tokens": 108626918400, "tok_s": 159154.2}
|
| 33 |
+
{"step": 103640, "epoch": 0.658, "loss": 1.66387, "ppl": 5.28, "lr": 0.003, "grad": 0.1658, "tokens": 108647884800, "tok_s": 159108.1}
|
| 34 |
+
{"step": 103660, "epoch": 0.659, "loss": 1.84406, "ppl": 6.322, "lr": 0.003, "grad": 0.0839, "tokens": 108668851200, "tok_s": 159059.2}
|
| 35 |
+
{"step": 103680, "epoch": 0.659, "loss": 1.77286, "ppl": 5.888, "lr": 0.003, "grad": 0.1964, "tokens": 108689817600, "tok_s": 159131.7}
|
| 36 |
+
{"step": 103700, "epoch": 0.659, "loss": 1.74173, "ppl": 5.707, "lr": 0.003, "grad": 0.1256, "tokens": 108710784000, "tok_s": 158927.0}
|
| 37 |
+
{"step": 103720, "epoch": 0.659, "loss": 1.6683, "ppl": 5.303, "lr": 0.003, "grad": 0.1101, "tokens": 108731750400, "tok_s": 159215.4}
|
| 38 |
+
{"step": 103740, "epoch": 0.659, "loss": 1.70027, "ppl": 5.475, "lr": 0.003, "grad": 0.2066, "tokens": 108752716800, "tok_s": 159167.5}
|
| 39 |
+
{"step": 103760, "epoch": 0.659, "loss": 1.76893, "ppl": 5.865, "lr": 0.003, "grad": 0.2198, "tokens": 108773683200, "tok_s": 159097.2}
|
| 40 |
+
{"step": 103780, "epoch": 0.659, "loss": 1.67872, "ppl": 5.359, "lr": 0.003, "grad": 0.1615, "tokens": 108794649600, "tok_s": 159025.0}
|
| 41 |
+
{"step": 103800, "epoch": 0.66, "loss": 1.69452, "ppl": 5.444, "lr": 0.003, "grad": 0.1566, "tokens": 108815616000, "tok_s": 159177.5}
|
| 42 |
+
{"step": 103820, "epoch": 0.66, "loss": 1.74359, "ppl": 5.718, "lr": 0.003, "grad": 0.0974, "tokens": 108836582400, "tok_s": 159199.5}
|
| 43 |
+
{"step": 103840, "epoch": 0.66, "loss": 1.67706, "ppl": 5.35, "lr": 0.003, "grad": 0.104, "tokens": 108857548800, "tok_s": 159248.0}
|
| 44 |
+
{"step": 103860, "epoch": 0.66, "loss": 1.75409, "ppl": 5.778, "lr": 0.003, "grad": 0.1085, "tokens": 108878515200, "tok_s": 159090.0}
|
| 45 |
+
{"step": 103880, "epoch": 0.66, "loss": 1.78152, "ppl": 5.939, "lr": 0.003, "grad": 0.1585, "tokens": 108899481600, "tok_s": 159101.0}
|
| 46 |
+
{"step": 103900, "epoch": 0.66, "loss": 1.45016, "ppl": 4.264, "lr": 0.003, "grad": 0.1273, "tokens": 108920448000, "tok_s": 158927.5}
|
| 47 |
+
{"step": 103920, "epoch": 0.66, "loss": 1.68008, "ppl": 5.366, "lr": 0.003, "grad": 0.1713, "tokens": 108941414400, "tok_s": 159220.5}
|
| 48 |
+
{"step": 103940, "epoch": 0.66, "loss": 1.69084, "ppl": 5.424, "lr": 0.003, "grad": 0.0837, "tokens": 108962380800, "tok_s": 159170.3}
|
| 49 |
+
{"step": 103960, "epoch": 0.661, "loss": 1.78521, "ppl": 5.961, "lr": 0.003, "grad": 0.1482, "tokens": 108983347200, "tok_s": 159091.8}
|
| 50 |
+
{"step": 103980, "epoch": 0.661, "loss": 1.73619, "ppl": 5.676, "lr": 0.003, "grad": 0.1255, "tokens": 109004313600, "tok_s": 159215.5}
|
| 51 |
+
{"step": 104000, "epoch": 0.661, "loss": 1.89156, "ppl": 6.63, "lr": 0.003, "grad": 0.1592, "tokens": 109025280000, "tok_s": 158827.5}
|
| 52 |
+
{"step": 104000, "val_loss": 1.73307, "val_ppl": 5.658, "is_best": true}
|
| 53 |
+
{"step": 104020, "epoch": 0.661, "loss": 1.73662, "ppl": 5.678, "lr": 0.003, "grad": 0.1665, "tokens": 109046246400, "tok_s": 158997.7}
|
| 54 |
+
{"step": 104040, "epoch": 0.661, "loss": 1.6789, "ppl": 5.36, "lr": 0.003, "grad": 0.1479, "tokens": 109067212800, "tok_s": 159135.6}
|
| 55 |
+
{"step": 104060, "epoch": 0.661, "loss": 1.77655, "ppl": 5.909, "lr": 0.003, "grad": 0.0996, "tokens": 109088179200, "tok_s": 158830.7}
|
| 56 |
+
{"step": 104080, "epoch": 0.661, "loss": 1.72722, "ppl": 5.625, "lr": 0.003, "grad": 0.106, "tokens": 109109145600, "tok_s": 158995.1}
|
| 57 |
+
{"step": 104100, "epoch": 0.661, "loss": 1.59814, "ppl": 4.944, "lr": 0.003, "grad": 0.0722, "tokens": 109130112000, "tok_s": 158956.0}
|
| 58 |
+
{"step": 104120, "epoch": 0.662, "loss": 1.87211, "ppl": 6.502, "lr": 0.003, "grad": 0.1723, "tokens": 109151078400, "tok_s": 159004.9}
|
| 59 |
+
{"step": 104140, "epoch": 0.662, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.1128, "tokens": 109172044800, "tok_s": 158715.8}
|
| 60 |
+
{"step": 104160, "epoch": 0.662, "loss": 1.75281, "ppl": 5.771, "lr": 0.003, "grad": 0.1824, "tokens": 109193011200, "tok_s": 158738.1}
|
| 61 |
+
{"step": 104180, "epoch": 0.662, "loss": 1.79538, "ppl": 6.022, "lr": 0.003, "grad": 0.2017, "tokens": 109213977600, "tok_s": 158633.8}
|
| 62 |
+
{"step": 104200, "epoch": 0.662, "loss": 1.70962, "ppl": 5.527, "lr": 0.003, "grad": 0.1821, "tokens": 109234944000, "tok_s": 158863.6}
|
| 63 |
+
{"step": 104220, "epoch": 0.662, "loss": 1.78149, "ppl": 5.939, "lr": 0.003, "grad": 0.1032, "tokens": 109255910400, "tok_s": 159130.0}
|
| 64 |
+
{"step": 104240, "epoch": 0.662, "loss": 1.69264, "ppl": 5.434, "lr": 0.003, "grad": 0.0855, "tokens": 109276876800, "tok_s": 158660.9}
|
| 65 |
+
{"step": 104260, "epoch": 0.662, "loss": 1.72285, "ppl": 5.6, "lr": 0.003, "grad": 0.1449, "tokens": 109297843200, "tok_s": 158872.8}
|
| 66 |
+
{"step": 104280, "epoch": 0.663, "loss": 1.60635, "ppl": 4.985, "lr": 0.003, "grad": 0.1624, "tokens": 109318809600, "tok_s": 158882.7}
|
| 67 |
+
{"step": 104300, "epoch": 0.663, "loss": 1.80534, "ppl": 6.082, "lr": 0.003, "grad": 0.1375, "tokens": 109339776000, "tok_s": 158833.1}
|
| 68 |
+
{"step": 104320, "epoch": 0.663, "loss": 1.74444, "ppl": 5.723, "lr": 0.003, "grad": 0.1149, "tokens": 109360742400, "tok_s": 158947.3}
|
| 69 |
+
{"step": 104340, "epoch": 0.663, "loss": 1.79691, "ppl": 6.031, "lr": 0.003, "grad": 0.2072, "tokens": 109381708800, "tok_s": 158998.7}
|
| 70 |
+
{"step": 104360, "epoch": 0.663, "loss": 1.73588, "ppl": 5.674, "lr": 0.003, "grad": 0.1396, "tokens": 109402675200, "tok_s": 158683.7}
|
| 71 |
+
{"step": 104380, "epoch": 0.663, "loss": 1.8465, "ppl": 6.338, "lr": 0.003, "grad": 0.1107, "tokens": 109423641600, "tok_s": 158875.4}
|
| 72 |
+
{"step": 104400, "epoch": 0.663, "loss": 1.81251, "ppl": 6.126, "lr": 0.003, "grad": 0.0807, "tokens": 109444608000, "tok_s": 158669.8}
|
| 73 |
+
{"step": 104420, "epoch": 0.663, "loss": 1.7951, "ppl": 6.02, "lr": 0.003, "grad": 0.1246, "tokens": 109465574400, "tok_s": 158742.5}
|
| 74 |
+
{"step": 104440, "epoch": 0.664, "loss": 1.73516, "ppl": 5.67, "lr": 0.003, "grad": 0.0797, "tokens": 109486540800, "tok_s": 158811.7}
|
| 75 |
+
{"step": 104460, "epoch": 0.664, "loss": 1.77739, "ppl": 5.914, "lr": 0.003, "grad": 0.2092, "tokens": 109507507200, "tok_s": 159175.4}
|
| 76 |
+
{"step": 104480, "epoch": 0.664, "loss": 1.82117, "ppl": 6.179, "lr": 0.003, "grad": 0.1147, "tokens": 109528473600, "tok_s": 158902.0}
|
| 77 |
+
{"step": 104500, "epoch": 0.664, "loss": 1.78193, "ppl": 5.941, "lr": 0.003, "grad": 0.0972, "tokens": 109549440000, "tok_s": 158571.8}
|
| 78 |
+
{"step": 104520, "epoch": 0.664, "loss": 1.78727, "ppl": 5.973, "lr": 0.003, "grad": 0.1308, "tokens": 109570406400, "tok_s": 159003.7}
|
| 79 |
+
{"step": 104540, "epoch": 0.664, "loss": 1.71035, "ppl": 5.531, "lr": 0.003, "grad": 0.0935, "tokens": 109591372800, "tok_s": 158566.8}
|
| 80 |
+
{"step": 104560, "epoch": 0.664, "loss": 1.79273, "ppl": 6.006, "lr": 0.003, "grad": 0.1619, "tokens": 109612339200, "tok_s": 159022.1}
|
| 81 |
+
{"step": 104580, "epoch": 0.664, "loss": 1.59285, "ppl": 4.918, "lr": 0.003, "grad": 0.0923, "tokens": 109633305600, "tok_s": 158996.6}
|
| 82 |
+
{"step": 104600, "epoch": 0.665, "loss": 1.76848, "ppl": 5.862, "lr": 0.003, "grad": 0.0946, "tokens": 109654272000, "tok_s": 159063.0}
|
| 83 |
+
{"step": 104620, "epoch": 0.665, "loss": 1.76793, "ppl": 5.859, "lr": 0.003, "grad": 0.0949, "tokens": 109675238400, "tok_s": 158677.9}
|
| 84 |
+
{"step": 104640, "epoch": 0.665, "loss": 1.73267, "ppl": 5.656, "lr": 0.003, "grad": 0.1246, "tokens": 109696204800, "tok_s": 159086.8}
|
| 85 |
+
{"step": 104660, "epoch": 0.665, "loss": 1.78542, "ppl": 5.962, "lr": 0.003, "grad": 0.08, "tokens": 109717171200, "tok_s": 159076.5}
|
| 86 |
+
{"step": 104680, "epoch": 0.665, "loss": 1.75886, "ppl": 5.806, "lr": 0.003, "grad": 0.125, "tokens": 109738137600, "tok_s": 159037.3}
|
| 87 |
+
{"step": 104700, "epoch": 0.665, "loss": 1.73196, "ppl": 5.652, "lr": 0.003, "grad": 0.1015, "tokens": 109759104000, "tok_s": 158854.1}
|
| 88 |
+
{"step": 104720, "epoch": 0.665, "loss": 1.7098, "ppl": 5.528, "lr": 0.003, "grad": 0.1101, "tokens": 109780070400, "tok_s": 159124.5}
|
| 89 |
+
{"step": 104740, "epoch": 0.665, "loss": 1.74681, "ppl": 5.736, "lr": 0.003, "grad": 0.1051, "tokens": 109801036800, "tok_s": 159026.5}
|
| 90 |
+
{"step": 104760, "epoch": 0.666, "loss": 1.63925, "ppl": 5.151, "lr": 0.003, "grad": 0.0543, "tokens": 109822003200, "tok_s": 158990.3}
|
| 91 |
+
{"step": 104780, "epoch": 0.666, "loss": 1.71809, "ppl": 5.574, "lr": 0.003, "grad": 0.1393, "tokens": 109842969600, "tok_s": 159137.8}
|
| 92 |
+
{"step": 104800, "epoch": 0.666, "loss": 1.74093, "ppl": 5.703, "lr": 0.003, "grad": 0.1612, "tokens": 109863936000, "tok_s": 158846.4}
|
| 93 |
+
{"step": 104820, "epoch": 0.666, "loss": 1.76485, "ppl": 5.841, "lr": 0.003, "grad": 0.1143, "tokens": 109884902400, "tok_s": 158972.5}
|
| 94 |
+
{"step": 104840, "epoch": 0.666, "loss": 1.78046, "ppl": 5.933, "lr": 0.003, "grad": 0.085, "tokens": 109905868800, "tok_s": 158689.6}
|
| 95 |
+
{"step": 104860, "epoch": 0.666, "loss": 1.79138, "ppl": 5.998, "lr": 0.003, "grad": 0.0665, "tokens": 109926835200, "tok_s": 158956.5}
|
| 96 |
+
{"step": 104880, "epoch": 0.666, "loss": 1.77218, "ppl": 5.884, "lr": 0.003, "grad": 0.1442, "tokens": 109947801600, "tok_s": 159018.8}
|
| 97 |
+
{"step": 104900, "epoch": 0.666, "loss": 1.75558, "ppl": 5.787, "lr": 0.003, "grad": 0.1406, "tokens": 109968768000, "tok_s": 158995.5}
|
| 98 |
+
{"step": 104920, "epoch": 0.667, "loss": 1.78012, "ppl": 5.931, "lr": 0.003, "grad": 0.1164, "tokens": 109989734400, "tok_s": 158956.1}
|
| 99 |
+
{"step": 104940, "epoch": 0.667, "loss": 1.7293, "ppl": 5.637, "lr": 0.003, "grad": 0.0836, "tokens": 110010700800, "tok_s": 158958.7}
|
| 100 |
+
{"step": 104960, "epoch": 0.667, "loss": 1.75256, "ppl": 5.769, "lr": 0.003, "grad": 0.145, "tokens": 110031667200, "tok_s": 158967.2}
|
| 101 |
+
{"step": 104980, "epoch": 0.667, "loss": 1.79842, "ppl": 6.04, "lr": 0.003, "grad": 0.141, "tokens": 110052633600, "tok_s": 159126.4}
|
| 102 |
+
{"step": 105000, "epoch": 0.667, "loss": 1.72704, "ppl": 5.624, "lr": 0.003, "grad": 0.1398, "tokens": 110073600000, "tok_s": 158991.1}
|
| 103 |
+
{"step": 105000, "val_loss": 1.74304, "val_ppl": 5.715, "is_best": false}
|
| 104 |
+
{"step": 105020, "epoch": 0.667, "loss": 1.76215, "ppl": 5.825, "lr": 0.003, "grad": 0.1806, "tokens": 110094566400, "tok_s": 158671.8}
|
| 105 |
+
{"step": 105040, "epoch": 0.667, "loss": 1.75137, "ppl": 5.763, "lr": 0.003, "grad": 0.0962, "tokens": 110115532800, "tok_s": 158974.6}
|
| 106 |
+
{"step": 105060, "epoch": 0.668, "loss": 1.69628, "ppl": 5.454, "lr": 0.003, "grad": 0.0863, "tokens": 110136499200, "tok_s": 158912.0}
|
| 107 |
+
{"step": 105080, "epoch": 0.668, "loss": 1.76755, "ppl": 5.856, "lr": 0.003, "grad": 0.1386, "tokens": 110157465600, "tok_s": 158756.9}
|
| 108 |
+
{"step": 105100, "epoch": 0.668, "loss": 1.75679, "ppl": 5.794, "lr": 0.003, "grad": 0.1659, "tokens": 110178432000, "tok_s": 158854.3}
|
| 109 |
+
{"step": 105120, "epoch": 0.668, "loss": 1.83078, "ppl": 6.239, "lr": 0.003, "grad": 0.0992, "tokens": 110199398400, "tok_s": 158941.0}
|
| 110 |
+
{"step": 105140, "epoch": 0.668, "loss": 1.772, "ppl": 5.883, "lr": 0.003, "grad": 0.096, "tokens": 110220364800, "tok_s": 159249.8}
|
| 111 |
+
{"step": 105160, "epoch": 0.668, "loss": 1.72506, "ppl": 5.613, "lr": 0.003, "grad": 0.1498, "tokens": 110241331200, "tok_s": 158660.2}
|
| 112 |
+
{"step": 105180, "epoch": 0.668, "loss": 1.7513, "ppl": 5.762, "lr": 0.003, "grad": 0.1525, "tokens": 110262297600, "tok_s": 158921.5}
|
| 113 |
+
{"step": 105200, "epoch": 0.668, "loss": 1.80524, "ppl": 6.081, "lr": 0.003, "grad": 0.1137, "tokens": 110283264000, "tok_s": 158794.3}
|
| 114 |
+
{"step": 105220, "epoch": 0.669, "loss": 1.7043, "ppl": 5.498, "lr": 0.003, "grad": 0.0862, "tokens": 110304230400, "tok_s": 159014.6}
|
| 115 |
+
{"step": 105240, "epoch": 0.669, "loss": 1.75034, "ppl": 5.757, "lr": 0.003, "grad": 0.1358, "tokens": 110325196800, "tok_s": 158690.7}
|
| 116 |
+
{"step": 105260, "epoch": 0.669, "loss": 1.66413, "ppl": 5.281, "lr": 0.003, "grad": 0.0687, "tokens": 110346163200, "tok_s": 158623.5}
|
| 117 |
+
{"step": 105280, "epoch": 0.669, "loss": 1.76264, "ppl": 5.828, "lr": 0.003, "grad": 0.1444, "tokens": 110367129600, "tok_s": 158682.2}
|
| 118 |
+
{"step": 105300, "epoch": 0.669, "loss": 1.78643, "ppl": 5.968, "lr": 0.003, "grad": 0.1082, "tokens": 110388096000, "tok_s": 158903.4}
|
| 119 |
+
{"step": 105320, "epoch": 0.669, "loss": 1.66896, "ppl": 5.307, "lr": 0.003, "grad": 0.0696, "tokens": 110409062400, "tok_s": 159098.4}
|
| 120 |
+
{"step": 105340, "epoch": 0.669, "loss": 1.63363, "ppl": 5.122, "lr": 0.003, "grad": 0.1139, "tokens": 110430028800, "tok_s": 158622.7}
|
| 121 |
+
{"step": 105360, "epoch": 0.669, "loss": 1.76022, "ppl": 5.814, "lr": 0.003, "grad": 0.1553, "tokens": 110450995200, "tok_s": 158832.6}
|
| 122 |
+
{"step": 105380, "epoch": 0.67, "loss": 1.73319, "ppl": 5.659, "lr": 0.003, "grad": 0.1156, "tokens": 110471961600, "tok_s": 158747.8}
|
| 123 |
+
{"step": 105400, "epoch": 0.67, "loss": 1.64827, "ppl": 5.198, "lr": 0.003, "grad": 0.0792, "tokens": 110492928000, "tok_s": 159063.9}
|
| 124 |
+
{"step": 105420, "epoch": 0.67, "loss": 1.66882, "ppl": 5.306, "lr": 0.003, "grad": 0.0799, "tokens": 110513894400, "tok_s": 158993.6}
|
| 125 |
+
{"step": 105440, "epoch": 0.67, "loss": 1.85582, "ppl": 6.397, "lr": 0.003, "grad": 0.1864, "tokens": 110534860800, "tok_s": 159145.8}
|
| 126 |
+
{"step": 105460, "epoch": 0.67, "loss": 1.64841, "ppl": 5.199, "lr": 0.003, "grad": 0.1361, "tokens": 110555827200, "tok_s": 158950.5}
|
| 127 |
+
{"step": 105480, "epoch": 0.67, "loss": 1.72625, "ppl": 5.62, "lr": 0.003, "grad": 0.107, "tokens": 110576793600, "tok_s": 159055.6}
|
| 128 |
+
{"step": 105500, "epoch": 0.67, "loss": 1.70148, "ppl": 5.482, "lr": 0.003, "grad": 0.0887, "tokens": 110597760000, "tok_s": 158735.0}
|
| 129 |
+
{"step": 105520, "epoch": 0.67, "loss": 1.71477, "ppl": 5.555, "lr": 0.003, "grad": 0.0792, "tokens": 110618726400, "tok_s": 158689.6}
|
| 130 |
+
{"step": 105540, "epoch": 0.671, "loss": 1.71728, "ppl": 5.569, "lr": 0.003, "grad": 0.123, "tokens": 110639692800, "tok_s": 158888.5}
|
| 131 |
+
{"step": 105560, "epoch": 0.671, "loss": 1.81532, "ppl": 6.143, "lr": 0.003, "grad": 0.1478, "tokens": 110660659200, "tok_s": 158992.0}
|
| 132 |
+
{"step": 105580, "epoch": 0.671, "loss": 1.74605, "ppl": 5.732, "lr": 0.003, "grad": 0.1198, "tokens": 110681625600, "tok_s": 158645.1}
|
| 133 |
+
{"step": 105600, "epoch": 0.671, "loss": 1.77535, "ppl": 5.902, "lr": 0.003, "grad": 0.0567, "tokens": 110702592000, "tok_s": 158893.2}
|
| 134 |
+
{"step": 105620, "epoch": 0.671, "loss": 1.73959, "ppl": 5.695, "lr": 0.003, "grad": 0.1804, "tokens": 110723558400, "tok_s": 158901.6}
|
| 135 |
+
{"step": 105640, "epoch": 0.671, "loss": 1.77731, "ppl": 5.914, "lr": 0.003, "grad": 0.0678, "tokens": 110744524800, "tok_s": 158973.1}
|
| 136 |
+
{"step": 105660, "epoch": 0.671, "loss": 1.64497, "ppl": 5.181, "lr": 0.003, "grad": 0.0925, "tokens": 110765491200, "tok_s": 158751.5}
|
| 137 |
+
{"step": 105680, "epoch": 0.671, "loss": 1.74163, "ppl": 5.707, "lr": 0.003, "grad": 0.1118, "tokens": 110786457600, "tok_s": 159074.0}
|
| 138 |
+
{"step": 105700, "epoch": 0.672, "loss": 1.70014, "ppl": 5.475, "lr": 0.003, "grad": 0.163, "tokens": 110807424000, "tok_s": 159020.5}
|
| 139 |
+
{"step": 105720, "epoch": 0.672, "loss": 1.7869, "ppl": 5.971, "lr": 0.003, "grad": 0.1481, "tokens": 110828390400, "tok_s": 159177.7}
|
| 140 |
+
{"step": 105740, "epoch": 0.672, "loss": 1.61031, "ppl": 5.004, "lr": 0.003, "grad": 0.0901, "tokens": 110849356800, "tok_s": 158749.6}
|
| 141 |
+
{"step": 105760, "epoch": 0.672, "loss": 1.7785, "ppl": 5.921, "lr": 0.003, "grad": 0.1427, "tokens": 110870323200, "tok_s": 159106.9}
|
| 142 |
+
{"step": 105780, "epoch": 0.672, "loss": 1.78613, "ppl": 5.966, "lr": 0.003, "grad": 0.0907, "tokens": 110891289600, "tok_s": 158747.7}
|
| 143 |
+
{"step": 105800, "epoch": 0.672, "loss": 1.75972, "ppl": 5.811, "lr": 0.003, "grad": 0.0823, "tokens": 110912256000, "tok_s": 159199.7}
|
| 144 |
+
{"step": 105820, "epoch": 0.672, "loss": 1.77934, "ppl": 5.926, "lr": 0.003, "grad": 0.1421, "tokens": 110933222400, "tok_s": 159174.4}
|
| 145 |
+
{"step": 105840, "epoch": 0.672, "loss": 1.78072, "ppl": 5.934, "lr": 0.003, "grad": 0.1411, "tokens": 110954188800, "tok_s": 159082.7}
|
| 146 |
+
{"step": 105860, "epoch": 0.673, "loss": 1.80478, "ppl": 6.079, "lr": 0.003, "grad": 0.1266, "tokens": 110975155200, "tok_s": 159265.3}
|
| 147 |
+
{"step": 105880, "epoch": 0.673, "loss": 1.71682, "ppl": 5.567, "lr": 0.003, "grad": 0.0713, "tokens": 110996121600, "tok_s": 158888.2}
|
| 148 |
+
{"step": 105900, "epoch": 0.673, "loss": 1.77119, "ppl": 5.878, "lr": 0.003, "grad": 0.1137, "tokens": 111017088000, "tok_s": 158721.0}
|
| 149 |
+
{"step": 105920, "epoch": 0.673, "loss": 1.76743, "ppl": 5.856, "lr": 0.003, "grad": 0.0879, "tokens": 111038054400, "tok_s": 159106.7}
|
| 150 |
+
{"step": 105940, "epoch": 0.673, "loss": 1.73487, "ppl": 5.668, "lr": 0.003, "grad": 0.1173, "tokens": 111059020800, "tok_s": 158721.2}
|
| 151 |
+
{"step": 105960, "epoch": 0.673, "loss": 1.79097, "ppl": 5.995, "lr": 0.003, "grad": 0.1112, "tokens": 111079987200, "tok_s": 159015.9}
|
| 152 |
+
{"step": 105980, "epoch": 0.673, "loss": 1.76332, "ppl": 5.832, "lr": 0.003, "grad": 0.1556, "tokens": 111100953600, "tok_s": 158890.5}
|
| 153 |
+
{"step": 106000, "epoch": 0.673, "loss": 1.76822, "ppl": 5.86, "lr": 0.003, "grad": 0.1682, "tokens": 111121920000, "tok_s": 159095.2}
|
| 154 |
+
{"step": 106000, "val_loss": 1.75145, "val_ppl": 5.763, "is_best": false}
|
| 155 |
+
{"step": 106020, "epoch": 0.674, "loss": 1.69846, "ppl": 5.465, "lr": 0.003, "grad": 0.1133, "tokens": 111142886400, "tok_s": 158627.0}
|
| 156 |
+
{"step": 106040, "epoch": 0.674, "loss": 1.75588, "ppl": 5.789, "lr": 0.003, "grad": 0.1398, "tokens": 111163852800, "tok_s": 158986.6}
|
| 157 |
+
{"step": 106060, "epoch": 0.674, "loss": 1.73895, "ppl": 5.691, "lr": 0.003, "grad": 0.1201, "tokens": 111184819200, "tok_s": 159077.8}
|
| 158 |
+
{"step": 106080, "epoch": 0.674, "loss": 1.77928, "ppl": 5.926, "lr": 0.003, "grad": 0.1641, "tokens": 111205785600, "tok_s": 158731.6}
|
| 159 |
+
{"step": 106100, "epoch": 0.674, "loss": 1.77578, "ppl": 5.905, "lr": 0.003, "grad": 0.0847, "tokens": 111226752000, "tok_s": 158920.3}
|
| 160 |
+
{"step": 106120, "epoch": 0.674, "loss": 1.74289, "ppl": 5.714, "lr": 0.003, "grad": 0.1248, "tokens": 111247718400, "tok_s": 159159.5}
|
| 161 |
+
{"step": 106140, "epoch": 0.674, "loss": 1.72757, "ppl": 5.627, "lr": 0.003, "grad": 0.1132, "tokens": 111268684800, "tok_s": 158656.1}
|
| 162 |
+
{"step": 106160, "epoch": 0.675, "loss": 1.73902, "ppl": 5.692, "lr": 0.003, "grad": 0.1502, "tokens": 111289651200, "tok_s": 158645.5}
|
| 163 |
+
{"step": 106180, "epoch": 0.675, "loss": 1.68355, "ppl": 5.385, "lr": 0.003, "grad": 0.093, "tokens": 111310617600, "tok_s": 158128.2}
|
| 164 |
+
{"step": 106200, "epoch": 0.675, "loss": 1.74524, "ppl": 5.727, "lr": 0.003, "grad": 0.0942, "tokens": 111331584000, "tok_s": 158672.0}
|
| 165 |
+
{"step": 106220, "epoch": 0.675, "loss": 1.73209, "ppl": 5.652, "lr": 0.003, "grad": 0.0934, "tokens": 111352550400, "tok_s": 158635.5}
|
| 166 |
+
{"step": 106240, "epoch": 0.675, "loss": 1.7352, "ppl": 5.67, "lr": 0.003, "grad": 0.1363, "tokens": 111373516800, "tok_s": 159019.7}
|
| 167 |
+
{"step": 106260, "epoch": 0.675, "loss": 1.74852, "ppl": 5.746, "lr": 0.003, "grad": 0.1467, "tokens": 111394483200, "tok_s": 158402.8}
|
| 168 |
+
{"step": 106280, "epoch": 0.675, "loss": 1.771, "ppl": 5.877, "lr": 0.003, "grad": 0.0893, "tokens": 111415449600, "tok_s": 158670.0}
|
| 169 |
+
{"step": 106300, "epoch": 0.675, "loss": 1.82433, "ppl": 6.199, "lr": 0.003, "grad": 0.0874, "tokens": 111436416000, "tok_s": 158221.7}
|
| 170 |
+
{"step": 106320, "epoch": 0.676, "loss": 1.72527, "ppl": 5.614, "lr": 0.003, "grad": 0.0792, "tokens": 111457382400, "tok_s": 158663.7}
|
| 171 |
+
{"step": 106340, "epoch": 0.676, "loss": 1.75491, "ppl": 5.783, "lr": 0.003, "grad": 0.1451, "tokens": 111478348800, "tok_s": 158730.6}
|
| 172 |
+
{"step": 106360, "epoch": 0.676, "loss": 1.74147, "ppl": 5.706, "lr": 0.003, "grad": 0.0831, "tokens": 111499315200, "tok_s": 158842.0}
|
| 173 |
+
{"step": 106380, "epoch": 0.676, "loss": 1.6952, "ppl": 5.448, "lr": 0.003, "grad": 0.1765, "tokens": 111520281600, "tok_s": 158518.0}
|
| 174 |
+
{"step": 106400, "epoch": 0.676, "loss": 1.71558, "ppl": 5.56, "lr": 0.003, "grad": 0.0933, "tokens": 111541248000, "tok_s": 159022.1}
|
| 175 |
+
{"step": 106420, "epoch": 0.676, "loss": 1.74255, "ppl": 5.712, "lr": 0.003, "grad": 0.1161, "tokens": 111562214400, "tok_s": 158900.8}
|
| 176 |
+
{"step": 106440, "epoch": 0.676, "loss": 1.72939, "ppl": 5.637, "lr": 0.003, "grad": 0.0949, "tokens": 111583180800, "tok_s": 158143.8}
|
| 177 |
+
{"step": 106460, "epoch": 0.676, "loss": 1.74077, "ppl": 5.702, "lr": 0.003, "grad": 0.056, "tokens": 111604147200, "tok_s": 158801.8}
|
| 178 |
+
{"step": 106480, "epoch": 0.677, "loss": 1.65382, "ppl": 5.227, "lr": 0.003, "grad": 0.1495, "tokens": 111625113600, "tok_s": 158843.9}
|
| 179 |
+
{"step": 106500, "epoch": 0.677, "loss": 1.86545, "ppl": 6.459, "lr": 0.003, "grad": 0.1017, "tokens": 111646080000, "tok_s": 158862.1}
|
| 180 |
+
{"step": 106520, "epoch": 0.677, "loss": 1.79127, "ppl": 5.997, "lr": 0.003, "grad": 0.0986, "tokens": 111667046400, "tok_s": 158428.3}
|
| 181 |
+
{"step": 106540, "epoch": 0.677, "loss": 1.69771, "ppl": 5.461, "lr": 0.003, "grad": 0.0667, "tokens": 111688012800, "tok_s": 159026.3}
|
| 182 |
+
{"step": 106560, "epoch": 0.677, "loss": 1.85277, "ppl": 6.377, "lr": 0.003, "grad": 0.1884, "tokens": 111708979200, "tok_s": 158904.1}
|
| 183 |
+
{"step": 106580, "epoch": 0.677, "loss": 1.73439, "ppl": 5.665, "lr": 0.003, "grad": 0.0549, "tokens": 111729945600, "tok_s": 159133.6}
|
| 184 |
+
{"step": 106600, "epoch": 0.677, "loss": 1.82285, "ppl": 6.189, "lr": 0.003, "grad": 0.1159, "tokens": 111750912000, "tok_s": 158845.7}
|
| 185 |
+
{"step": 106620, "epoch": 0.677, "loss": 1.73941, "ppl": 5.694, "lr": 0.003, "grad": 0.1109, "tokens": 111771878400, "tok_s": 159003.1}
|
| 186 |
+
{"step": 106640, "epoch": 0.678, "loss": 1.75547, "ppl": 5.786, "lr": 0.003, "grad": 0.0886, "tokens": 111792844800, "tok_s": 158787.6}
|
| 187 |
+
{"step": 106660, "epoch": 0.678, "loss": 1.6383, "ppl": 5.146, "lr": 0.003, "grad": 0.1472, "tokens": 111813811200, "tok_s": 159093.1}
|
| 188 |
+
{"step": 106680, "epoch": 0.678, "loss": 1.46855, "ppl": 4.343, "lr": 0.003, "grad": 0.0733, "tokens": 111834777600, "tok_s": 158856.7}
|
| 189 |
+
{"step": 106700, "epoch": 0.678, "loss": 1.80103, "ppl": 6.056, "lr": 0.003, "grad": 0.1077, "tokens": 111855744000, "tok_s": 159000.6}
|
| 190 |
+
{"step": 106720, "epoch": 0.678, "loss": 1.70293, "ppl": 5.49, "lr": 0.003, "grad": 0.1523, "tokens": 111876710400, "tok_s": 159060.9}
|
| 191 |
+
{"step": 106740, "epoch": 0.678, "loss": 1.71797, "ppl": 5.573, "lr": 0.003, "grad": 0.0874, "tokens": 111897676800, "tok_s": 159170.3}
|
| 192 |
+
{"step": 106760, "epoch": 0.678, "loss": 1.74612, "ppl": 5.732, "lr": 0.003, "grad": 0.1351, "tokens": 111918643200, "tok_s": 158878.2}
|
| 193 |
+
{"step": 106780, "epoch": 0.678, "loss": 1.70947, "ppl": 5.526, "lr": 0.003, "grad": 0.1471, "tokens": 111939609600, "tok_s": 159044.1}
|
| 194 |
+
{"step": 106800, "epoch": 0.679, "loss": 1.76839, "ppl": 5.861, "lr": 0.003, "grad": 0.1151, "tokens": 111960576000, "tok_s": 159015.0}
|
| 195 |
+
{"step": 106820, "epoch": 0.679, "loss": 1.75148, "ppl": 5.763, "lr": 0.003, "grad": 0.101, "tokens": 111981542400, "tok_s": 159038.3}
|
| 196 |
+
{"step": 106840, "epoch": 0.679, "loss": 1.76693, "ppl": 5.853, "lr": 0.003, "grad": 0.0988, "tokens": 112002508800, "tok_s": 158604.0}
|
| 197 |
+
{"step": 106860, "epoch": 0.679, "loss": 1.74152, "ppl": 5.706, "lr": 0.003, "grad": 0.1404, "tokens": 112023475200, "tok_s": 158987.0}
|
| 198 |
+
{"step": 106880, "epoch": 0.679, "loss": 1.7451, "ppl": 5.726, "lr": 0.003, "grad": 0.0941, "tokens": 112044441600, "tok_s": 158901.4}
|
| 199 |
+
{"step": 106900, "epoch": 0.679, "loss": 1.73282, "ppl": 5.657, "lr": 0.003, "grad": 0.1308, "tokens": 112065408000, "tok_s": 158731.6}
|
| 200 |
+
{"step": 106920, "epoch": 0.679, "loss": 1.73412, "ppl": 5.664, "lr": 0.003, "grad": 0.1138, "tokens": 112086374400, "tok_s": 158895.0}
|
| 201 |
+
{"step": 106940, "epoch": 0.679, "loss": 1.74119, "ppl": 5.704, "lr": 0.003, "grad": 0.1453, "tokens": 112107340800, "tok_s": 159026.8}
|
| 202 |
+
{"step": 106960, "epoch": 0.68, "loss": 1.77176, "ppl": 5.881, "lr": 0.003, "grad": 0.1112, "tokens": 112128307200, "tok_s": 159001.9}
|
| 203 |
+
{"step": 106980, "epoch": 0.68, "loss": 1.73934, "ppl": 5.694, "lr": 0.003, "grad": 0.143, "tokens": 112149273600, "tok_s": 159014.6}
|
| 204 |
+
{"step": 107000, "epoch": 0.68, "loss": 1.76938, "ppl": 5.867, "lr": 0.003, "grad": 0.1606, "tokens": 112170240000, "tok_s": 159003.9}
|
| 205 |
+
{"step": 107000, "val_loss": 1.75256, "val_ppl": 5.769, "is_best": false}
|
| 206 |
+
{"step": 107020, "epoch": 0.68, "loss": 1.71738, "ppl": 5.57, "lr": 0.003, "grad": 0.1159, "tokens": 112191206400, "tok_s": 158954.0}
|
| 207 |
+
{"step": 107040, "epoch": 0.68, "loss": 1.77307, "ppl": 5.889, "lr": 0.003, "grad": 0.1112, "tokens": 112212172800, "tok_s": 159058.7}
|
| 208 |
+
{"step": 107060, "epoch": 0.68, "loss": 1.71985, "ppl": 5.584, "lr": 0.003, "grad": 0.1295, "tokens": 112233139200, "tok_s": 159032.6}
|
| 209 |
+
{"step": 107080, "epoch": 0.68, "loss": 1.78339, "ppl": 5.95, "lr": 0.003, "grad": 0.1617, "tokens": 112254105600, "tok_s": 158888.6}
|
| 210 |
+
{"step": 107100, "epoch": 0.68, "loss": 1.75765, "ppl": 5.799, "lr": 0.003, "grad": 0.104, "tokens": 112275072000, "tok_s": 158920.1}
|
| 211 |
+
{"step": 107120, "epoch": 0.681, "loss": 1.77941, "ppl": 5.926, "lr": 0.003, "grad": 0.1088, "tokens": 112296038400, "tok_s": 158781.2}
|
| 212 |
+
{"step": 107140, "epoch": 0.681, "loss": 1.7181, "ppl": 5.574, "lr": 0.003, "grad": 0.1517, "tokens": 112317004800, "tok_s": 158975.7}
|
| 213 |
+
{"step": 107160, "epoch": 0.681, "loss": 1.75763, "ppl": 5.799, "lr": 0.003, "grad": 0.0944, "tokens": 112337971200, "tok_s": 158437.1}
|
| 214 |
+
{"step": 107180, "epoch": 0.681, "loss": 1.76975, "ppl": 5.869, "lr": 0.003, "grad": 0.0792, "tokens": 112358937600, "tok_s": 159063.1}
|
| 215 |
+
{"step": 107200, "epoch": 0.681, "loss": 1.80004, "ppl": 6.05, "lr": 0.003, "grad": 0.1105, "tokens": 112379904000, "tok_s": 158929.0}
|
| 216 |
+
{"step": 107220, "epoch": 0.681, "loss": 1.79442, "ppl": 6.016, "lr": 0.003, "grad": 0.2133, "tokens": 112400870400, "tok_s": 158468.4}
|
| 217 |
+
{"step": 107240, "epoch": 0.681, "loss": 1.76485, "ppl": 5.841, "lr": 0.003, "grad": 0.0674, "tokens": 112421836800, "tok_s": 158866.7}
|
| 218 |
+
{"step": 107260, "epoch": 0.681, "loss": 1.72152, "ppl": 5.593, "lr": 0.003, "grad": 0.0972, "tokens": 112442803200, "tok_s": 158169.3}
|
| 219 |
+
{"step": 107280, "epoch": 0.682, "loss": 1.80626, "ppl": 6.088, "lr": 0.003, "grad": 0.1251, "tokens": 112463769600, "tok_s": 159141.4}
|
| 220 |
+
{"step": 107300, "epoch": 0.682, "loss": 1.77453, "ppl": 5.898, "lr": 0.003, "grad": 0.1749, "tokens": 112484736000, "tok_s": 159079.3}
|
| 221 |
+
{"step": 107320, "epoch": 0.682, "loss": 1.72049, "ppl": 5.587, "lr": 0.003, "grad": 0.138, "tokens": 112505702400, "tok_s": 158712.3}
|
| 222 |
+
{"step": 107340, "epoch": 0.682, "loss": 1.78005, "ppl": 5.93, "lr": 0.003, "grad": 0.0815, "tokens": 112526668800, "tok_s": 158927.7}
|
| 223 |
+
{"step": 107360, "epoch": 0.682, "loss": 1.71806, "ppl": 5.574, "lr": 0.003, "grad": 0.1708, "tokens": 112547635200, "tok_s": 158883.4}
|
| 224 |
+
{"step": 107380, "epoch": 0.682, "loss": 1.76784, "ppl": 5.858, "lr": 0.003, "grad": 0.0705, "tokens": 112568601600, "tok_s": 158609.7}
|
| 225 |
+
{"step": 107400, "epoch": 0.682, "loss": 1.64964, "ppl": 5.205, "lr": 0.003, "grad": 0.0865, "tokens": 112589568000, "tok_s": 159051.9}
|
| 226 |
+
{"step": 107420, "epoch": 0.683, "loss": 1.76067, "ppl": 5.816, "lr": 0.003, "grad": 0.1331, "tokens": 112610534400, "tok_s": 158813.3}
|
| 227 |
+
{"step": 107440, "epoch": 0.683, "loss": 1.75632, "ppl": 5.791, "lr": 0.003, "grad": 0.1394, "tokens": 112631500800, "tok_s": 158998.2}
|
| 228 |
+
{"step": 107460, "epoch": 0.683, "loss": 1.76572, "ppl": 5.846, "lr": 0.003, "grad": 0.1189, "tokens": 112652467200, "tok_s": 158893.7}
|
| 229 |
+
{"step": 107480, "epoch": 0.683, "loss": 1.91795, "ppl": 6.807, "lr": 0.003, "grad": 0.1377, "tokens": 112673433600, "tok_s": 159012.8}
|
| 230 |
+
{"step": 107500, "epoch": 0.683, "loss": 1.79656, "ppl": 6.029, "lr": 0.003, "grad": 0.1325, "tokens": 112694400000, "tok_s": 158792.4}
|
| 231 |
+
{"step": 107520, "epoch": 0.683, "loss": 1.74773, "ppl": 5.742, "lr": 0.003, "grad": 0.1287, "tokens": 112715366400, "tok_s": 158877.2}
|
| 232 |
+
{"step": 107540, "epoch": 0.683, "loss": 1.73996, "ppl": 5.697, "lr": 0.003, "grad": 0.0803, "tokens": 112736332800, "tok_s": 158911.5}
|
| 233 |
+
{"step": 107560, "epoch": 0.683, "loss": 1.81099, "ppl": 6.117, "lr": 0.003, "grad": 0.123, "tokens": 112757299200, "tok_s": 158999.8}
|
| 234 |
+
{"step": 107580, "epoch": 0.684, "loss": 1.72162, "ppl": 5.594, "lr": 0.003, "grad": 0.1025, "tokens": 112778265600, "tok_s": 158678.4}
|
| 235 |
+
{"step": 107600, "epoch": 0.684, "loss": 1.75522, "ppl": 5.785, "lr": 0.003, "grad": 0.0854, "tokens": 112799232000, "tok_s": 158928.0}
|
| 236 |
+
{"step": 107620, "epoch": 0.684, "loss": 1.772, "ppl": 5.883, "lr": 0.003, "grad": 0.1009, "tokens": 112820198400, "tok_s": 158984.6}
|
| 237 |
+
{"step": 107640, "epoch": 0.684, "loss": 1.74086, "ppl": 5.702, "lr": 0.003, "grad": 0.0682, "tokens": 112841164800, "tok_s": 159017.5}
|
| 238 |
+
{"step": 107660, "epoch": 0.684, "loss": 1.71537, "ppl": 5.559, "lr": 0.003, "grad": 0.1334, "tokens": 112862131200, "tok_s": 159054.9}
|
| 239 |
+
{"step": 107680, "epoch": 0.684, "loss": 1.79851, "ppl": 6.041, "lr": 0.003, "grad": 0.0901, "tokens": 112883097600, "tok_s": 158959.8}
|
| 240 |
+
{"step": 107700, "epoch": 0.684, "loss": 1.71123, "ppl": 5.536, "lr": 0.003, "grad": 0.1158, "tokens": 112904064000, "tok_s": 158553.3}
|
| 241 |
+
{"step": 107720, "epoch": 0.684, "loss": 1.74093, "ppl": 5.703, "lr": 0.003, "grad": 0.09, "tokens": 112925030400, "tok_s": 159126.4}
|
| 242 |
+
{"step": 107740, "epoch": 0.685, "loss": 1.7667, "ppl": 5.852, "lr": 0.003, "grad": 0.1952, "tokens": 112945996800, "tok_s": 159010.9}
|
| 243 |
+
{"step": 107760, "epoch": 0.685, "loss": 1.78223, "ppl": 5.943, "lr": 0.003, "grad": 0.117, "tokens": 112966963200, "tok_s": 159042.2}
|
| 244 |
+
{"step": 107780, "epoch": 0.685, "loss": 1.73576, "ppl": 5.673, "lr": 0.003, "grad": 0.0806, "tokens": 112987929600, "tok_s": 158848.7}
|
| 245 |
+
{"step": 107800, "epoch": 0.685, "loss": 1.77057, "ppl": 5.874, "lr": 0.003, "grad": 0.0834, "tokens": 113008896000, "tok_s": 158816.7}
|
| 246 |
+
{"step": 107820, "epoch": 0.685, "loss": 1.70767, "ppl": 5.516, "lr": 0.003, "grad": 0.0888, "tokens": 113029862400, "tok_s": 159147.2}
|
| 247 |
+
{"step": 107840, "epoch": 0.685, "loss": 1.75052, "ppl": 5.758, "lr": 0.003, "grad": 0.108, "tokens": 113050828800, "tok_s": 159115.9}
|
| 248 |
+
{"step": 107860, "epoch": 0.685, "loss": 1.75772, "ppl": 5.799, "lr": 0.003, "grad": 0.0806, "tokens": 113071795200, "tok_s": 159115.8}
|
| 249 |
+
{"step": 107880, "epoch": 0.685, "loss": 1.66927, "ppl": 5.308, "lr": 0.003, "grad": 0.0623, "tokens": 113092761600, "tok_s": 159159.9}
|
| 250 |
+
{"step": 107900, "epoch": 0.686, "loss": 1.75434, "ppl": 5.78, "lr": 0.003, "grad": 0.1007, "tokens": 113113728000, "tok_s": 159093.2}
|
| 251 |
+
{"step": 107920, "epoch": 0.686, "loss": 1.7394, "ppl": 5.694, "lr": 0.003, "grad": 0.0918, "tokens": 113134694400, "tok_s": 159043.7}
|
| 252 |
+
{"step": 107940, "epoch": 0.686, "loss": 1.72816, "ppl": 5.63, "lr": 0.003, "grad": 0.1248, "tokens": 113155660800, "tok_s": 159028.7}
|
| 253 |
+
{"step": 107960, "epoch": 0.686, "loss": 1.70111, "ppl": 5.48, "lr": 0.003, "grad": 0.1006, "tokens": 113176627200, "tok_s": 159017.6}
|
| 254 |
+
{"step": 107980, "epoch": 0.686, "loss": 1.76833, "ppl": 5.861, "lr": 0.003, "grad": 0.09, "tokens": 113197593600, "tok_s": 158644.9}
|
| 255 |
+
{"step": 108000, "epoch": 0.686, "loss": 1.78449, "ppl": 5.957, "lr": 0.003, "grad": 0.1198, "tokens": 113218560000, "tok_s": 159013.7}
|
| 256 |
+
{"step": 108000, "val_loss": 1.7547, "val_ppl": 5.782, "is_best": false}
|
logs/log_109000.jsonl
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 108000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-04T17:47:03.162778"}
|
| 2 |
+
{"step": 108020, "epoch": 0.686, "loss": 1.74155, "ppl": 5.706, "lr": 0.003, "grad": 0.1535, "tokens": 113239526400, "tok_s": 159409.6}
|
| 3 |
+
{"step": 108040, "epoch": 0.686, "loss": 1.74208, "ppl": 5.709, "lr": 0.003, "grad": 0.1116, "tokens": 113260492800, "tok_s": 158966.0}
|
| 4 |
+
{"step": 108060, "epoch": 0.687, "loss": 1.71701, "ppl": 5.568, "lr": 0.003, "grad": 0.119, "tokens": 113281459200, "tok_s": 158764.9}
|
| 5 |
+
{"step": 108080, "epoch": 0.687, "loss": 1.61379, "ppl": 5.022, "lr": 0.003, "grad": 0.1259, "tokens": 113302425600, "tok_s": 159374.6}
|
| 6 |
+
{"step": 108100, "epoch": 0.687, "loss": 1.76912, "ppl": 5.866, "lr": 0.003, "grad": 0.1513, "tokens": 113323392000, "tok_s": 159426.1}
|
| 7 |
+
{"step": 108120, "epoch": 0.687, "loss": 1.73133, "ppl": 5.648, "lr": 0.003, "grad": 0.1181, "tokens": 113344358400, "tok_s": 159368.3}
|
| 8 |
+
{"step": 108140, "epoch": 0.687, "loss": 1.74469, "ppl": 5.724, "lr": 0.003, "grad": 0.081, "tokens": 113365324800, "tok_s": 159141.7}
|
| 9 |
+
{"step": 108160, "epoch": 0.687, "loss": 1.67668, "ppl": 5.348, "lr": 0.003, "grad": 0.097, "tokens": 113386291200, "tok_s": 159307.4}
|
| 10 |
+
{"step": 108180, "epoch": 0.687, "loss": 1.6295, "ppl": 5.101, "lr": 0.003, "grad": 0.074, "tokens": 113407257600, "tok_s": 158959.6}
|
| 11 |
+
{"step": 108200, "epoch": 0.687, "loss": 1.59394, "ppl": 4.923, "lr": 0.003, "grad": 0.1446, "tokens": 113428224000, "tok_s": 159053.4}
|
| 12 |
+
{"step": 108220, "epoch": 0.688, "loss": 1.78001, "ppl": 5.93, "lr": 0.003, "grad": 0.0736, "tokens": 113449190400, "tok_s": 159320.4}
|
| 13 |
+
{"step": 108240, "epoch": 0.688, "loss": 1.70317, "ppl": 5.491, "lr": 0.003, "grad": 0.1291, "tokens": 113470156800, "tok_s": 159284.0}
|
| 14 |
+
{"step": 108260, "epoch": 0.688, "loss": 1.76076, "ppl": 5.817, "lr": 0.003, "grad": 0.0607, "tokens": 113491123200, "tok_s": 159430.1}
|
| 15 |
+
{"step": 108280, "epoch": 0.688, "loss": 1.71242, "ppl": 5.542, "lr": 0.003, "grad": 0.0832, "tokens": 113512089600, "tok_s": 159396.6}
|
| 16 |
+
{"step": 108300, "epoch": 0.688, "loss": 1.75654, "ppl": 5.792, "lr": 0.003, "grad": 0.0942, "tokens": 113533056000, "tok_s": 159177.0}
|
| 17 |
+
{"step": 108320, "epoch": 0.688, "loss": 1.76145, "ppl": 5.821, "lr": 0.003, "grad": 0.0929, "tokens": 113554022400, "tok_s": 159418.2}
|
| 18 |
+
{"step": 108340, "epoch": 0.688, "loss": 1.72596, "ppl": 5.618, "lr": 0.003, "grad": 0.1128, "tokens": 113574988800, "tok_s": 159462.3}
|
| 19 |
+
{"step": 108360, "epoch": 0.688, "loss": 1.77282, "ppl": 5.887, "lr": 0.003, "grad": 0.0726, "tokens": 113595955200, "tok_s": 159439.0}
|
| 20 |
+
{"step": 108380, "epoch": 0.689, "loss": 1.68249, "ppl": 5.379, "lr": 0.003, "grad": 0.0773, "tokens": 113616921600, "tok_s": 158841.1}
|
| 21 |
+
{"step": 108400, "epoch": 0.689, "loss": 1.78284, "ppl": 5.947, "lr": 0.003, "grad": 0.1421, "tokens": 113637888000, "tok_s": 159390.6}
|
| 22 |
+
{"step": 108420, "epoch": 0.689, "loss": 1.76143, "ppl": 5.821, "lr": 0.003, "grad": 0.1094, "tokens": 113658854400, "tok_s": 159248.9}
|
| 23 |
+
{"step": 108440, "epoch": 0.689, "loss": 1.6718, "ppl": 5.322, "lr": 0.003, "grad": 0.0636, "tokens": 113679820800, "tok_s": 159083.0}
|
| 24 |
+
{"step": 108460, "epoch": 0.689, "loss": 1.81265, "ppl": 6.127, "lr": 0.003, "grad": 0.106, "tokens": 113700787200, "tok_s": 159288.0}
|
| 25 |
+
{"step": 108480, "epoch": 0.689, "loss": 1.80861, "ppl": 6.102, "lr": 0.003, "grad": 0.1554, "tokens": 113721753600, "tok_s": 159226.0}
|
| 26 |
+
{"step": 108500, "epoch": 0.689, "loss": 1.89807, "ppl": 6.673, "lr": 0.003, "grad": 0.119, "tokens": 113742720000, "tok_s": 158977.2}
|
| 27 |
+
{"step": 108520, "epoch": 0.689, "loss": 1.76412, "ppl": 5.836, "lr": 0.003, "grad": 0.0783, "tokens": 113763686400, "tok_s": 158959.6}
|
| 28 |
+
{"step": 108540, "epoch": 0.69, "loss": 1.65952, "ppl": 5.257, "lr": 0.003, "grad": 0.0907, "tokens": 113784652800, "tok_s": 159425.9}
|
| 29 |
+
{"step": 108560, "epoch": 0.69, "loss": 1.67979, "ppl": 5.364, "lr": 0.003, "grad": 0.1137, "tokens": 113805619200, "tok_s": 159124.8}
|
| 30 |
+
{"step": 108580, "epoch": 0.69, "loss": 1.70389, "ppl": 5.495, "lr": 0.003, "grad": 0.1058, "tokens": 113826585600, "tok_s": 159404.3}
|
| 31 |
+
{"step": 108600, "epoch": 0.69, "loss": 1.6402, "ppl": 5.156, "lr": 0.003, "grad": 0.0885, "tokens": 113847552000, "tok_s": 159333.4}
|
| 32 |
+
{"step": 108620, "epoch": 0.69, "loss": 1.71514, "ppl": 5.557, "lr": 0.003, "grad": 0.1022, "tokens": 113868518400, "tok_s": 159159.8}
|
| 33 |
+
{"step": 108640, "epoch": 0.69, "loss": 1.66351, "ppl": 5.278, "lr": 0.003, "grad": 0.1001, "tokens": 113889484800, "tok_s": 159061.3}
|
| 34 |
+
{"step": 108660, "epoch": 0.69, "loss": 1.84406, "ppl": 6.322, "lr": 0.003, "grad": 0.0975, "tokens": 113910451200, "tok_s": 159051.8}
|
| 35 |
+
{"step": 108680, "epoch": 0.691, "loss": 1.77184, "ppl": 5.882, "lr": 0.003, "grad": 0.1471, "tokens": 113931417600, "tok_s": 159358.4}
|
| 36 |
+
{"step": 108700, "epoch": 0.691, "loss": 1.74199, "ppl": 5.709, "lr": 0.003, "grad": 0.116, "tokens": 113952384000, "tok_s": 158750.2}
|
| 37 |
+
{"step": 108720, "epoch": 0.691, "loss": 1.66658, "ppl": 5.294, "lr": 0.003, "grad": 0.108, "tokens": 113973350400, "tok_s": 158885.5}
|
| 38 |
+
{"step": 108740, "epoch": 0.691, "loss": 1.69864, "ppl": 5.466, "lr": 0.003, "grad": 0.0686, "tokens": 113994316800, "tok_s": 159047.9}
|
| 39 |
+
{"step": 108760, "epoch": 0.691, "loss": 1.76744, "ppl": 5.856, "lr": 0.003, "grad": 0.0725, "tokens": 114015283200, "tok_s": 158612.8}
|
| 40 |
+
{"step": 108780, "epoch": 0.691, "loss": 1.67806, "ppl": 5.355, "lr": 0.003, "grad": 0.1065, "tokens": 114036249600, "tok_s": 159074.5}
|
| 41 |
+
{"step": 108800, "epoch": 0.691, "loss": 1.69361, "ppl": 5.439, "lr": 0.003, "grad": 0.1198, "tokens": 114057216000, "tok_s": 158311.1}
|
| 42 |
+
{"step": 108820, "epoch": 0.691, "loss": 1.74227, "ppl": 5.71, "lr": 0.003, "grad": 0.1113, "tokens": 114078182400, "tok_s": 158962.4}
|
| 43 |
+
{"step": 108840, "epoch": 0.692, "loss": 1.67661, "ppl": 5.347, "lr": 0.003, "grad": 0.0726, "tokens": 114099148800, "tok_s": 159127.3}
|
| 44 |
+
{"step": 108860, "epoch": 0.692, "loss": 1.75207, "ppl": 5.767, "lr": 0.003, "grad": 0.0926, "tokens": 114120115200, "tok_s": 159114.9}
|
| 45 |
+
{"step": 108880, "epoch": 0.692, "loss": 1.78028, "ppl": 5.932, "lr": 0.003, "grad": 0.0944, "tokens": 114141081600, "tok_s": 159095.0}
|
| 46 |
+
{"step": 108900, "epoch": 0.692, "loss": 1.45231, "ppl": 4.273, "lr": 0.003, "grad": 0.0811, "tokens": 114162048000, "tok_s": 158766.7}
|
| 47 |
+
{"step": 108920, "epoch": 0.692, "loss": 1.67896, "ppl": 5.36, "lr": 0.003, "grad": 0.1297, "tokens": 114183014400, "tok_s": 158716.9}
|
| 48 |
+
{"step": 108940, "epoch": 0.692, "loss": 1.69114, "ppl": 5.426, "lr": 0.003, "grad": 0.0714, "tokens": 114203980800, "tok_s": 159226.3}
|
| 49 |
+
{"step": 108960, "epoch": 0.692, "loss": 1.78483, "ppl": 5.959, "lr": 0.003, "grad": 0.0848, "tokens": 114224947200, "tok_s": 159024.2}
|
| 50 |
+
{"step": 108980, "epoch": 0.692, "loss": 1.7362, "ppl": 5.676, "lr": 0.003, "grad": 0.0833, "tokens": 114245913600, "tok_s": 158551.6}
|
| 51 |
+
{"step": 109000, "epoch": 0.693, "loss": 1.89243, "ppl": 6.635, "lr": 0.003, "grad": 0.1041, "tokens": 114266880000, "tok_s": 159175.6}
|
| 52 |
+
{"step": 109000, "val_loss": 1.73288, "val_ppl": 5.657, "is_best": true}
|
logs/log_11000.jsonl
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 10400, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-08-25T10:47:59.907226"}
|
| 2 |
+
{"step": 10420, "epoch": 0.066, "loss": 1.81711, "ppl": 6.154, "lr": 0.003, "grad": 0.0712, "tokens": 10923494400, "tok_s": 171148.6}
|
| 3 |
+
{"step": 10440, "epoch": 0.066, "loss": 1.81787, "ppl": 6.159, "lr": 0.003, "grad": 0.086, "tokens": 10944460800, "tok_s": 171016.2}
|
| 4 |
+
{"step": 10460, "epoch": 0.066, "loss": 1.79115, "ppl": 5.996, "lr": 0.003, "grad": 0.0605, "tokens": 10965427200, "tok_s": 170717.4}
|
| 5 |
+
{"step": 10480, "epoch": 0.067, "loss": 1.67725, "ppl": 5.351, "lr": 0.003, "grad": 0.0915, "tokens": 10986393600, "tok_s": 170321.1}
|
| 6 |
+
{"step": 10500, "epoch": 0.067, "loss": 1.84034, "ppl": 6.299, "lr": 0.003, "grad": 0.0919, "tokens": 11007360000, "tok_s": 170000.9}
|
| 7 |
+
{"step": 10520, "epoch": 0.067, "loss": 1.80401, "ppl": 6.074, "lr": 0.003, "grad": 0.1176, "tokens": 11028326400, "tok_s": 168719.0}
|
| 8 |
+
{"step": 10540, "epoch": 0.067, "loss": 1.81361, "ppl": 6.133, "lr": 0.003, "grad": 0.0807, "tokens": 11049292800, "tok_s": 169165.5}
|
| 9 |
+
{"step": 10560, "epoch": 0.067, "loss": 1.74588, "ppl": 5.731, "lr": 0.003, "grad": 0.0655, "tokens": 11070259200, "tok_s": 169849.0}
|
| 10 |
+
{"step": 10580, "epoch": 0.067, "loss": 1.69691, "ppl": 5.457, "lr": 0.003, "grad": 0.0736, "tokens": 11091225600, "tok_s": 170408.2}
|
| 11 |
+
{"step": 10600, "epoch": 0.067, "loss": 1.65753, "ppl": 5.246, "lr": 0.003, "grad": 0.1223, "tokens": 11112192000, "tok_s": 169898.8}
|
| 12 |
+
{"step": 10620, "epoch": 0.067, "loss": 1.85511, "ppl": 6.392, "lr": 0.003, "grad": 0.0676, "tokens": 11133158400, "tok_s": 170415.5}
|
| 13 |
+
{"step": 10640, "epoch": 0.068, "loss": 1.77632, "ppl": 5.908, "lr": 0.003, "grad": 0.078, "tokens": 11154124800, "tok_s": 169195.0}
|
| 14 |
+
{"step": 10660, "epoch": 0.068, "loss": 1.83195, "ppl": 6.246, "lr": 0.003, "grad": 0.0815, "tokens": 11175091200, "tok_s": 168839.8}
|
| 15 |
+
{"step": 10680, "epoch": 0.068, "loss": 1.77901, "ppl": 5.924, "lr": 0.003, "grad": 0.0816, "tokens": 11196057600, "tok_s": 168644.0}
|
| 16 |
+
{"step": 10700, "epoch": 0.068, "loss": 1.8274, "ppl": 6.218, "lr": 0.003, "grad": 0.0964, "tokens": 11217024000, "tok_s": 169844.9}
|
| 17 |
+
{"step": 10720, "epoch": 0.068, "loss": 1.83423, "ppl": 6.26, "lr": 0.003, "grad": 0.0657, "tokens": 11237990400, "tok_s": 170037.3}
|
| 18 |
+
{"step": 10740, "epoch": 0.068, "loss": 1.79705, "ppl": 6.032, "lr": 0.003, "grad": 0.0661, "tokens": 11258956800, "tok_s": 170105.2}
|
| 19 |
+
{"step": 10760, "epoch": 0.068, "loss": 1.84121, "ppl": 6.304, "lr": 0.003, "grad": 0.0637, "tokens": 11279923200, "tok_s": 170654.2}
|
| 20 |
+
{"step": 10780, "epoch": 0.068, "loss": 1.75043, "ppl": 5.757, "lr": 0.003, "grad": 0.0791, "tokens": 11300889600, "tok_s": 170585.6}
|
| 21 |
+
{"step": 10800, "epoch": 0.069, "loss": 1.85313, "ppl": 6.38, "lr": 0.003, "grad": 0.0897, "tokens": 11321856000, "tok_s": 170412.0}
|
| 22 |
+
{"step": 10820, "epoch": 0.069, "loss": 1.83289, "ppl": 6.252, "lr": 0.003, "grad": 0.093, "tokens": 11342822400, "tok_s": 169777.8}
|
| 23 |
+
{"step": 10840, "epoch": 0.069, "loss": 1.73753, "ppl": 5.683, "lr": 0.003, "grad": 0.0796, "tokens": 11363788800, "tok_s": 169871.9}
|
| 24 |
+
{"step": 10860, "epoch": 0.069, "loss": 1.88449, "ppl": 6.583, "lr": 0.003, "grad": 0.0983, "tokens": 11384755200, "tok_s": 168428.7}
|
| 25 |
+
{"step": 10880, "epoch": 0.069, "loss": 1.87887, "ppl": 6.546, "lr": 0.003, "grad": 0.1103, "tokens": 11405721600, "tok_s": 169815.4}
|
| 26 |
+
{"step": 10900, "epoch": 0.069, "loss": 1.99021, "ppl": 7.317, "lr": 0.003, "grad": 0.0932, "tokens": 11426688000, "tok_s": 169229.2}
|
| 27 |
+
{"step": 10920, "epoch": 0.069, "loss": 1.83739, "ppl": 6.28, "lr": 0.003, "grad": 0.0665, "tokens": 11447654400, "tok_s": 170114.2}
|
| 28 |
+
{"step": 10940, "epoch": 0.07, "loss": 1.72401, "ppl": 5.607, "lr": 0.003, "grad": 0.0633, "tokens": 11468620800, "tok_s": 169434.3}
|
| 29 |
+
{"step": 10960, "epoch": 0.07, "loss": 1.74373, "ppl": 5.719, "lr": 0.003, "grad": 0.0749, "tokens": 11489587200, "tok_s": 170351.3}
|
| 30 |
+
{"step": 10980, "epoch": 0.07, "loss": 1.77352, "ppl": 5.892, "lr": 0.003, "grad": 0.0824, "tokens": 11510553600, "tok_s": 170245.3}
|
| 31 |
+
{"step": 11000, "epoch": 0.07, "loss": 1.70794, "ppl": 5.518, "lr": 0.003, "grad": 0.0825, "tokens": 11531520000, "tok_s": 169701.7}
|
| 32 |
+
{"step": 11000, "val_loss": 1.78679, "val_ppl": 5.97, "is_best": true}
|
logs/log_110000.jsonl
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 108000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-04T17:47:03.162778"}
|
| 2 |
+
{"step": 108020, "epoch": 0.686, "loss": 1.74155, "ppl": 5.706, "lr": 0.003, "grad": 0.1535, "tokens": 113239526400, "tok_s": 159409.6}
|
| 3 |
+
{"step": 108040, "epoch": 0.686, "loss": 1.74208, "ppl": 5.709, "lr": 0.003, "grad": 0.1116, "tokens": 113260492800, "tok_s": 158966.0}
|
| 4 |
+
{"step": 108060, "epoch": 0.687, "loss": 1.71701, "ppl": 5.568, "lr": 0.003, "grad": 0.119, "tokens": 113281459200, "tok_s": 158764.9}
|
| 5 |
+
{"step": 108080, "epoch": 0.687, "loss": 1.61379, "ppl": 5.022, "lr": 0.003, "grad": 0.1259, "tokens": 113302425600, "tok_s": 159374.6}
|
| 6 |
+
{"step": 108100, "epoch": 0.687, "loss": 1.76912, "ppl": 5.866, "lr": 0.003, "grad": 0.1513, "tokens": 113323392000, "tok_s": 159426.1}
|
| 7 |
+
{"step": 108120, "epoch": 0.687, "loss": 1.73133, "ppl": 5.648, "lr": 0.003, "grad": 0.1181, "tokens": 113344358400, "tok_s": 159368.3}
|
| 8 |
+
{"step": 108140, "epoch": 0.687, "loss": 1.74469, "ppl": 5.724, "lr": 0.003, "grad": 0.081, "tokens": 113365324800, "tok_s": 159141.7}
|
| 9 |
+
{"step": 108160, "epoch": 0.687, "loss": 1.67668, "ppl": 5.348, "lr": 0.003, "grad": 0.097, "tokens": 113386291200, "tok_s": 159307.4}
|
| 10 |
+
{"step": 108180, "epoch": 0.687, "loss": 1.6295, "ppl": 5.101, "lr": 0.003, "grad": 0.074, "tokens": 113407257600, "tok_s": 158959.6}
|
| 11 |
+
{"step": 108200, "epoch": 0.687, "loss": 1.59394, "ppl": 4.923, "lr": 0.003, "grad": 0.1446, "tokens": 113428224000, "tok_s": 159053.4}
|
| 12 |
+
{"step": 108220, "epoch": 0.688, "loss": 1.78001, "ppl": 5.93, "lr": 0.003, "grad": 0.0736, "tokens": 113449190400, "tok_s": 159320.4}
|
| 13 |
+
{"step": 108240, "epoch": 0.688, "loss": 1.70317, "ppl": 5.491, "lr": 0.003, "grad": 0.1291, "tokens": 113470156800, "tok_s": 159284.0}
|
| 14 |
+
{"step": 108260, "epoch": 0.688, "loss": 1.76076, "ppl": 5.817, "lr": 0.003, "grad": 0.0607, "tokens": 113491123200, "tok_s": 159430.1}
|
| 15 |
+
{"step": 108280, "epoch": 0.688, "loss": 1.71242, "ppl": 5.542, "lr": 0.003, "grad": 0.0832, "tokens": 113512089600, "tok_s": 159396.6}
|
| 16 |
+
{"step": 108300, "epoch": 0.688, "loss": 1.75654, "ppl": 5.792, "lr": 0.003, "grad": 0.0942, "tokens": 113533056000, "tok_s": 159177.0}
|
| 17 |
+
{"step": 108320, "epoch": 0.688, "loss": 1.76145, "ppl": 5.821, "lr": 0.003, "grad": 0.0929, "tokens": 113554022400, "tok_s": 159418.2}
|
| 18 |
+
{"step": 108340, "epoch": 0.688, "loss": 1.72596, "ppl": 5.618, "lr": 0.003, "grad": 0.1128, "tokens": 113574988800, "tok_s": 159462.3}
|
| 19 |
+
{"step": 108360, "epoch": 0.688, "loss": 1.77282, "ppl": 5.887, "lr": 0.003, "grad": 0.0726, "tokens": 113595955200, "tok_s": 159439.0}
|
| 20 |
+
{"step": 108380, "epoch": 0.689, "loss": 1.68249, "ppl": 5.379, "lr": 0.003, "grad": 0.0773, "tokens": 113616921600, "tok_s": 158841.1}
|
| 21 |
+
{"step": 108400, "epoch": 0.689, "loss": 1.78284, "ppl": 5.947, "lr": 0.003, "grad": 0.1421, "tokens": 113637888000, "tok_s": 159390.6}
|
| 22 |
+
{"step": 108420, "epoch": 0.689, "loss": 1.76143, "ppl": 5.821, "lr": 0.003, "grad": 0.1094, "tokens": 113658854400, "tok_s": 159248.9}
|
| 23 |
+
{"step": 108440, "epoch": 0.689, "loss": 1.6718, "ppl": 5.322, "lr": 0.003, "grad": 0.0636, "tokens": 113679820800, "tok_s": 159083.0}
|
| 24 |
+
{"step": 108460, "epoch": 0.689, "loss": 1.81265, "ppl": 6.127, "lr": 0.003, "grad": 0.106, "tokens": 113700787200, "tok_s": 159288.0}
|
| 25 |
+
{"step": 108480, "epoch": 0.689, "loss": 1.80861, "ppl": 6.102, "lr": 0.003, "grad": 0.1554, "tokens": 113721753600, "tok_s": 159226.0}
|
| 26 |
+
{"step": 108500, "epoch": 0.689, "loss": 1.89807, "ppl": 6.673, "lr": 0.003, "grad": 0.119, "tokens": 113742720000, "tok_s": 158977.2}
|
| 27 |
+
{"step": 108520, "epoch": 0.689, "loss": 1.76412, "ppl": 5.836, "lr": 0.003, "grad": 0.0783, "tokens": 113763686400, "tok_s": 158959.6}
|
| 28 |
+
{"step": 108540, "epoch": 0.69, "loss": 1.65952, "ppl": 5.257, "lr": 0.003, "grad": 0.0907, "tokens": 113784652800, "tok_s": 159425.9}
|
| 29 |
+
{"step": 108560, "epoch": 0.69, "loss": 1.67979, "ppl": 5.364, "lr": 0.003, "grad": 0.1137, "tokens": 113805619200, "tok_s": 159124.8}
|
| 30 |
+
{"step": 108580, "epoch": 0.69, "loss": 1.70389, "ppl": 5.495, "lr": 0.003, "grad": 0.1058, "tokens": 113826585600, "tok_s": 159404.3}
|
| 31 |
+
{"step": 108600, "epoch": 0.69, "loss": 1.6402, "ppl": 5.156, "lr": 0.003, "grad": 0.0885, "tokens": 113847552000, "tok_s": 159333.4}
|
| 32 |
+
{"step": 108620, "epoch": 0.69, "loss": 1.71514, "ppl": 5.557, "lr": 0.003, "grad": 0.1022, "tokens": 113868518400, "tok_s": 159159.8}
|
| 33 |
+
{"step": 108640, "epoch": 0.69, "loss": 1.66351, "ppl": 5.278, "lr": 0.003, "grad": 0.1001, "tokens": 113889484800, "tok_s": 159061.3}
|
| 34 |
+
{"step": 108660, "epoch": 0.69, "loss": 1.84406, "ppl": 6.322, "lr": 0.003, "grad": 0.0975, "tokens": 113910451200, "tok_s": 159051.8}
|
| 35 |
+
{"step": 108680, "epoch": 0.691, "loss": 1.77184, "ppl": 5.882, "lr": 0.003, "grad": 0.1471, "tokens": 113931417600, "tok_s": 159358.4}
|
| 36 |
+
{"step": 108700, "epoch": 0.691, "loss": 1.74199, "ppl": 5.709, "lr": 0.003, "grad": 0.116, "tokens": 113952384000, "tok_s": 158750.2}
|
| 37 |
+
{"step": 108720, "epoch": 0.691, "loss": 1.66658, "ppl": 5.294, "lr": 0.003, "grad": 0.108, "tokens": 113973350400, "tok_s": 158885.5}
|
| 38 |
+
{"step": 108740, "epoch": 0.691, "loss": 1.69864, "ppl": 5.466, "lr": 0.003, "grad": 0.0686, "tokens": 113994316800, "tok_s": 159047.9}
|
| 39 |
+
{"step": 108760, "epoch": 0.691, "loss": 1.76744, "ppl": 5.856, "lr": 0.003, "grad": 0.0725, "tokens": 114015283200, "tok_s": 158612.8}
|
| 40 |
+
{"step": 108780, "epoch": 0.691, "loss": 1.67806, "ppl": 5.355, "lr": 0.003, "grad": 0.1065, "tokens": 114036249600, "tok_s": 159074.5}
|
| 41 |
+
{"step": 108800, "epoch": 0.691, "loss": 1.69361, "ppl": 5.439, "lr": 0.003, "grad": 0.1198, "tokens": 114057216000, "tok_s": 158311.1}
|
| 42 |
+
{"step": 108820, "epoch": 0.691, "loss": 1.74227, "ppl": 5.71, "lr": 0.003, "grad": 0.1113, "tokens": 114078182400, "tok_s": 158962.4}
|
| 43 |
+
{"step": 108840, "epoch": 0.692, "loss": 1.67661, "ppl": 5.347, "lr": 0.003, "grad": 0.0726, "tokens": 114099148800, "tok_s": 159127.3}
|
| 44 |
+
{"step": 108860, "epoch": 0.692, "loss": 1.75207, "ppl": 5.767, "lr": 0.003, "grad": 0.0926, "tokens": 114120115200, "tok_s": 159114.9}
|
| 45 |
+
{"step": 108880, "epoch": 0.692, "loss": 1.78028, "ppl": 5.932, "lr": 0.003, "grad": 0.0944, "tokens": 114141081600, "tok_s": 159095.0}
|
| 46 |
+
{"step": 108900, "epoch": 0.692, "loss": 1.45231, "ppl": 4.273, "lr": 0.003, "grad": 0.0811, "tokens": 114162048000, "tok_s": 158766.7}
|
| 47 |
+
{"step": 108920, "epoch": 0.692, "loss": 1.67896, "ppl": 5.36, "lr": 0.003, "grad": 0.1297, "tokens": 114183014400, "tok_s": 158716.9}
|
| 48 |
+
{"step": 108940, "epoch": 0.692, "loss": 1.69114, "ppl": 5.426, "lr": 0.003, "grad": 0.0714, "tokens": 114203980800, "tok_s": 159226.3}
|
| 49 |
+
{"step": 108960, "epoch": 0.692, "loss": 1.78483, "ppl": 5.959, "lr": 0.003, "grad": 0.0848, "tokens": 114224947200, "tok_s": 159024.2}
|
| 50 |
+
{"step": 108980, "epoch": 0.692, "loss": 1.7362, "ppl": 5.676, "lr": 0.003, "grad": 0.0833, "tokens": 114245913600, "tok_s": 158551.6}
|
| 51 |
+
{"step": 109000, "epoch": 0.693, "loss": 1.89243, "ppl": 6.635, "lr": 0.003, "grad": 0.1041, "tokens": 114266880000, "tok_s": 159175.6}
|
| 52 |
+
{"step": 109000, "val_loss": 1.73288, "val_ppl": 5.657, "is_best": true}
|
| 53 |
+
{"step": 109020, "epoch": 0.693, "loss": 1.73623, "ppl": 5.676, "lr": 0.003, "grad": 0.1133, "tokens": 114287846400, "tok_s": 158562.8}
|
| 54 |
+
{"step": 109040, "epoch": 0.693, "loss": 1.67899, "ppl": 5.36, "lr": 0.003, "grad": 0.122, "tokens": 114308812800, "tok_s": 158957.5}
|
| 55 |
+
{"step": 109060, "epoch": 0.693, "loss": 1.77498, "ppl": 5.9, "lr": 0.003, "grad": 0.1183, "tokens": 114329779200, "tok_s": 158635.2}
|
| 56 |
+
{"step": 109080, "epoch": 0.693, "loss": 1.72682, "ppl": 5.623, "lr": 0.003, "grad": 0.133, "tokens": 114350745600, "tok_s": 159053.0}
|
| 57 |
+
{"step": 109100, "epoch": 0.693, "loss": 1.59864, "ppl": 4.946, "lr": 0.003, "grad": 0.0731, "tokens": 114371712000, "tok_s": 158945.6}
|
| 58 |
+
{"step": 109120, "epoch": 0.693, "loss": 1.87152, "ppl": 6.498, "lr": 0.003, "grad": 0.1226, "tokens": 114392678400, "tok_s": 158979.5}
|
| 59 |
+
{"step": 109140, "epoch": 0.693, "loss": 1.7656, "ppl": 5.845, "lr": 0.003, "grad": 0.0712, "tokens": 114413644800, "tok_s": 158856.8}
|
| 60 |
+
{"step": 109160, "epoch": 0.694, "loss": 1.75175, "ppl": 5.765, "lr": 0.003, "grad": 0.1197, "tokens": 114434611200, "tok_s": 158864.0}
|
| 61 |
+
{"step": 109180, "epoch": 0.694, "loss": 1.79459, "ppl": 6.017, "lr": 0.003, "grad": 0.075, "tokens": 114455577600, "tok_s": 159128.8}
|
| 62 |
+
{"step": 109200, "epoch": 0.694, "loss": 1.70936, "ppl": 5.525, "lr": 0.003, "grad": 0.1687, "tokens": 114476544000, "tok_s": 158856.4}
|
| 63 |
+
{"step": 109220, "epoch": 0.694, "loss": 1.7816, "ppl": 5.939, "lr": 0.003, "grad": 0.0802, "tokens": 114497510400, "tok_s": 159429.2}
|
| 64 |
+
{"step": 109240, "epoch": 0.694, "loss": 1.69158, "ppl": 5.428, "lr": 0.003, "grad": 0.0868, "tokens": 114518476800, "tok_s": 159396.3}
|
| 65 |
+
{"step": 109260, "epoch": 0.694, "loss": 1.72195, "ppl": 5.595, "lr": 0.003, "grad": 0.0799, "tokens": 114539443200, "tok_s": 159192.0}
|
| 66 |
+
{"step": 109280, "epoch": 0.694, "loss": 1.60469, "ppl": 4.976, "lr": 0.003, "grad": 0.0877, "tokens": 114560409600, "tok_s": 159283.2}
|
| 67 |
+
{"step": 109300, "epoch": 0.694, "loss": 1.80401, "ppl": 6.074, "lr": 0.003, "grad": 0.0842, "tokens": 114581376000, "tok_s": 159141.0}
|
| 68 |
+
{"step": 109320, "epoch": 0.695, "loss": 1.74401, "ppl": 5.72, "lr": 0.003, "grad": 0.1062, "tokens": 114602342400, "tok_s": 159064.5}
|
| 69 |
+
{"step": 109340, "epoch": 0.695, "loss": 1.79633, "ppl": 6.027, "lr": 0.003, "grad": 0.0906, "tokens": 114623308800, "tok_s": 159188.7}
|
| 70 |
+
{"step": 109360, "epoch": 0.695, "loss": 1.73522, "ppl": 5.67, "lr": 0.003, "grad": 0.1054, "tokens": 114644275200, "tok_s": 159236.6}
|
| 71 |
+
{"step": 109380, "epoch": 0.695, "loss": 1.84514, "ppl": 6.329, "lr": 0.003, "grad": 0.0836, "tokens": 114665241600, "tok_s": 159146.2}
|
| 72 |
+
{"step": 109400, "epoch": 0.695, "loss": 1.81221, "ppl": 6.124, "lr": 0.003, "grad": 0.0795, "tokens": 114686208000, "tok_s": 158973.0}
|
| 73 |
+
{"step": 109420, "epoch": 0.695, "loss": 1.79499, "ppl": 6.019, "lr": 0.003, "grad": 0.0952, "tokens": 114707174400, "tok_s": 159163.4}
|
| 74 |
+
{"step": 109440, "epoch": 0.695, "loss": 1.73455, "ppl": 5.666, "lr": 0.003, "grad": 0.1025, "tokens": 114728140800, "tok_s": 159163.7}
|
| 75 |
+
{"step": 109460, "epoch": 0.695, "loss": 1.77711, "ppl": 5.913, "lr": 0.003, "grad": 0.1145, "tokens": 114749107200, "tok_s": 159227.8}
|
| 76 |
+
{"step": 109480, "epoch": 0.696, "loss": 1.82109, "ppl": 6.179, "lr": 0.003, "grad": 0.108, "tokens": 114770073600, "tok_s": 158520.2}
|
| 77 |
+
{"step": 109500, "epoch": 0.696, "loss": 1.78091, "ppl": 5.935, "lr": 0.003, "grad": 0.1455, "tokens": 114791040000, "tok_s": 158970.7}
|
| 78 |
+
{"step": 109520, "epoch": 0.696, "loss": 1.78594, "ppl": 5.965, "lr": 0.003, "grad": 0.0965, "tokens": 114812006400, "tok_s": 158568.5}
|
| 79 |
+
{"step": 109540, "epoch": 0.696, "loss": 1.71081, "ppl": 5.533, "lr": 0.003, "grad": 0.1095, "tokens": 114832972800, "tok_s": 158794.9}
|
| 80 |
+
{"step": 109560, "epoch": 0.696, "loss": 1.79209, "ppl": 6.002, "lr": 0.003, "grad": 0.1064, "tokens": 114853939200, "tok_s": 158785.9}
|
| 81 |
+
{"step": 109580, "epoch": 0.696, "loss": 1.59386, "ppl": 4.923, "lr": 0.003, "grad": 0.0668, "tokens": 114874905600, "tok_s": 158493.7}
|
| 82 |
+
{"step": 109600, "epoch": 0.696, "loss": 1.76839, "ppl": 5.861, "lr": 0.003, "grad": 0.1049, "tokens": 114895872000, "tok_s": 158374.2}
|
| 83 |
+
{"step": 109620, "epoch": 0.696, "loss": 1.76656, "ppl": 5.851, "lr": 0.003, "grad": 0.0699, "tokens": 114916838400, "tok_s": 159085.4}
|
| 84 |
+
{"step": 109640, "epoch": 0.697, "loss": 1.73206, "ppl": 5.652, "lr": 0.003, "grad": 0.1239, "tokens": 114937804800, "tok_s": 158970.6}
|
| 85 |
+
{"step": 109660, "epoch": 0.697, "loss": 1.78539, "ppl": 5.962, "lr": 0.003, "grad": 0.1003, "tokens": 114958771200, "tok_s": 159237.3}
|
| 86 |
+
{"step": 109680, "epoch": 0.697, "loss": 1.75903, "ppl": 5.807, "lr": 0.003, "grad": 0.1701, "tokens": 114979737600, "tok_s": 159190.0}
|
| 87 |
+
{"step": 109700, "epoch": 0.697, "loss": 1.73013, "ppl": 5.641, "lr": 0.003, "grad": 0.0824, "tokens": 115000704000, "tok_s": 159145.2}
|
| 88 |
+
{"step": 109720, "epoch": 0.697, "loss": 1.70807, "ppl": 5.518, "lr": 0.003, "grad": 0.089, "tokens": 115021670400, "tok_s": 159392.1}
|
| 89 |
+
{"step": 109740, "epoch": 0.697, "loss": 1.7454, "ppl": 5.728, "lr": 0.003, "grad": 0.0596, "tokens": 115042636800, "tok_s": 158812.2}
|
| 90 |
+
{"step": 109760, "epoch": 0.697, "loss": 1.63906, "ppl": 5.15, "lr": 0.003, "grad": 0.0936, "tokens": 115063603200, "tok_s": 158822.8}
|
| 91 |
+
{"step": 109780, "epoch": 0.698, "loss": 1.71756, "ppl": 5.571, "lr": 0.003, "grad": 0.1026, "tokens": 115084569600, "tok_s": 159321.3}
|
| 92 |
+
{"step": 109800, "epoch": 0.698, "loss": 1.74078, "ppl": 5.702, "lr": 0.003, "grad": 0.1413, "tokens": 115105536000, "tok_s": 158977.1}
|
| 93 |
+
{"step": 109820, "epoch": 0.698, "loss": 1.76512, "ppl": 5.842, "lr": 0.003, "grad": 0.0856, "tokens": 115126502400, "tok_s": 159024.3}
|
| 94 |
+
{"step": 109840, "epoch": 0.698, "loss": 1.77975, "ppl": 5.928, "lr": 0.003, "grad": 0.0778, "tokens": 115147468800, "tok_s": 158361.9}
|
| 95 |
+
{"step": 109860, "epoch": 0.698, "loss": 1.79078, "ppl": 5.994, "lr": 0.003, "grad": 0.1127, "tokens": 115168435200, "tok_s": 159277.9}
|
| 96 |
+
{"step": 109880, "epoch": 0.698, "loss": 1.76985, "ppl": 5.87, "lr": 0.003, "grad": 0.0778, "tokens": 115189401600, "tok_s": 158912.3}
|
| 97 |
+
{"step": 109900, "epoch": 0.698, "loss": 1.75561, "ppl": 5.787, "lr": 0.003, "grad": 0.0748, "tokens": 115210368000, "tok_s": 159123.7}
|
| 98 |
+
{"step": 109920, "epoch": 0.698, "loss": 1.77873, "ppl": 5.922, "lr": 0.003, "grad": 0.0943, "tokens": 115231334400, "tok_s": 159401.3}
|
| 99 |
+
{"step": 109940, "epoch": 0.699, "loss": 1.72977, "ppl": 5.639, "lr": 0.003, "grad": 0.0723, "tokens": 115252300800, "tok_s": 159292.3}
|
| 100 |
+
{"step": 109960, "epoch": 0.699, "loss": 1.75106, "ppl": 5.761, "lr": 0.003, "grad": 0.0762, "tokens": 115273267200, "tok_s": 159346.4}
|
| 101 |
+
{"step": 109980, "epoch": 0.699, "loss": 1.79941, "ppl": 6.046, "lr": 0.003, "grad": 0.1027, "tokens": 115294233600, "tok_s": 159496.4}
|
| 102 |
+
{"step": 110000, "epoch": 0.699, "loss": 1.72724, "ppl": 5.625, "lr": 0.003, "grad": 0.0953, "tokens": 115315200000, "tok_s": 159029.0}
|
| 103 |
+
{"step": 110000, "val_loss": 1.74385, "val_ppl": 5.719, "is_best": false}
|
logs/log_111000.jsonl
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 108000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-04T17:47:03.162778"}
|
| 2 |
+
{"step": 108020, "epoch": 0.686, "loss": 1.74155, "ppl": 5.706, "lr": 0.003, "grad": 0.1535, "tokens": 113239526400, "tok_s": 159409.6}
|
| 3 |
+
{"step": 108040, "epoch": 0.686, "loss": 1.74208, "ppl": 5.709, "lr": 0.003, "grad": 0.1116, "tokens": 113260492800, "tok_s": 158966.0}
|
| 4 |
+
{"step": 108060, "epoch": 0.687, "loss": 1.71701, "ppl": 5.568, "lr": 0.003, "grad": 0.119, "tokens": 113281459200, "tok_s": 158764.9}
|
| 5 |
+
{"step": 108080, "epoch": 0.687, "loss": 1.61379, "ppl": 5.022, "lr": 0.003, "grad": 0.1259, "tokens": 113302425600, "tok_s": 159374.6}
|
| 6 |
+
{"step": 108100, "epoch": 0.687, "loss": 1.76912, "ppl": 5.866, "lr": 0.003, "grad": 0.1513, "tokens": 113323392000, "tok_s": 159426.1}
|
| 7 |
+
{"step": 108120, "epoch": 0.687, "loss": 1.73133, "ppl": 5.648, "lr": 0.003, "grad": 0.1181, "tokens": 113344358400, "tok_s": 159368.3}
|
| 8 |
+
{"step": 108140, "epoch": 0.687, "loss": 1.74469, "ppl": 5.724, "lr": 0.003, "grad": 0.081, "tokens": 113365324800, "tok_s": 159141.7}
|
| 9 |
+
{"step": 108160, "epoch": 0.687, "loss": 1.67668, "ppl": 5.348, "lr": 0.003, "grad": 0.097, "tokens": 113386291200, "tok_s": 159307.4}
|
| 10 |
+
{"step": 108180, "epoch": 0.687, "loss": 1.6295, "ppl": 5.101, "lr": 0.003, "grad": 0.074, "tokens": 113407257600, "tok_s": 158959.6}
|
| 11 |
+
{"step": 108200, "epoch": 0.687, "loss": 1.59394, "ppl": 4.923, "lr": 0.003, "grad": 0.1446, "tokens": 113428224000, "tok_s": 159053.4}
|
| 12 |
+
{"step": 108220, "epoch": 0.688, "loss": 1.78001, "ppl": 5.93, "lr": 0.003, "grad": 0.0736, "tokens": 113449190400, "tok_s": 159320.4}
|
| 13 |
+
{"step": 108240, "epoch": 0.688, "loss": 1.70317, "ppl": 5.491, "lr": 0.003, "grad": 0.1291, "tokens": 113470156800, "tok_s": 159284.0}
|
| 14 |
+
{"step": 108260, "epoch": 0.688, "loss": 1.76076, "ppl": 5.817, "lr": 0.003, "grad": 0.0607, "tokens": 113491123200, "tok_s": 159430.1}
|
| 15 |
+
{"step": 108280, "epoch": 0.688, "loss": 1.71242, "ppl": 5.542, "lr": 0.003, "grad": 0.0832, "tokens": 113512089600, "tok_s": 159396.6}
|
| 16 |
+
{"step": 108300, "epoch": 0.688, "loss": 1.75654, "ppl": 5.792, "lr": 0.003, "grad": 0.0942, "tokens": 113533056000, "tok_s": 159177.0}
|
| 17 |
+
{"step": 108320, "epoch": 0.688, "loss": 1.76145, "ppl": 5.821, "lr": 0.003, "grad": 0.0929, "tokens": 113554022400, "tok_s": 159418.2}
|
| 18 |
+
{"step": 108340, "epoch": 0.688, "loss": 1.72596, "ppl": 5.618, "lr": 0.003, "grad": 0.1128, "tokens": 113574988800, "tok_s": 159462.3}
|
| 19 |
+
{"step": 108360, "epoch": 0.688, "loss": 1.77282, "ppl": 5.887, "lr": 0.003, "grad": 0.0726, "tokens": 113595955200, "tok_s": 159439.0}
|
| 20 |
+
{"step": 108380, "epoch": 0.689, "loss": 1.68249, "ppl": 5.379, "lr": 0.003, "grad": 0.0773, "tokens": 113616921600, "tok_s": 158841.1}
|
| 21 |
+
{"step": 108400, "epoch": 0.689, "loss": 1.78284, "ppl": 5.947, "lr": 0.003, "grad": 0.1421, "tokens": 113637888000, "tok_s": 159390.6}
|
| 22 |
+
{"step": 108420, "epoch": 0.689, "loss": 1.76143, "ppl": 5.821, "lr": 0.003, "grad": 0.1094, "tokens": 113658854400, "tok_s": 159248.9}
|
| 23 |
+
{"step": 108440, "epoch": 0.689, "loss": 1.6718, "ppl": 5.322, "lr": 0.003, "grad": 0.0636, "tokens": 113679820800, "tok_s": 159083.0}
|
| 24 |
+
{"step": 108460, "epoch": 0.689, "loss": 1.81265, "ppl": 6.127, "lr": 0.003, "grad": 0.106, "tokens": 113700787200, "tok_s": 159288.0}
|
| 25 |
+
{"step": 108480, "epoch": 0.689, "loss": 1.80861, "ppl": 6.102, "lr": 0.003, "grad": 0.1554, "tokens": 113721753600, "tok_s": 159226.0}
|
| 26 |
+
{"step": 108500, "epoch": 0.689, "loss": 1.89807, "ppl": 6.673, "lr": 0.003, "grad": 0.119, "tokens": 113742720000, "tok_s": 158977.2}
|
| 27 |
+
{"step": 108520, "epoch": 0.689, "loss": 1.76412, "ppl": 5.836, "lr": 0.003, "grad": 0.0783, "tokens": 113763686400, "tok_s": 158959.6}
|
| 28 |
+
{"step": 108540, "epoch": 0.69, "loss": 1.65952, "ppl": 5.257, "lr": 0.003, "grad": 0.0907, "tokens": 113784652800, "tok_s": 159425.9}
|
| 29 |
+
{"step": 108560, "epoch": 0.69, "loss": 1.67979, "ppl": 5.364, "lr": 0.003, "grad": 0.1137, "tokens": 113805619200, "tok_s": 159124.8}
|
| 30 |
+
{"step": 108580, "epoch": 0.69, "loss": 1.70389, "ppl": 5.495, "lr": 0.003, "grad": 0.1058, "tokens": 113826585600, "tok_s": 159404.3}
|
| 31 |
+
{"step": 108600, "epoch": 0.69, "loss": 1.6402, "ppl": 5.156, "lr": 0.003, "grad": 0.0885, "tokens": 113847552000, "tok_s": 159333.4}
|
| 32 |
+
{"step": 108620, "epoch": 0.69, "loss": 1.71514, "ppl": 5.557, "lr": 0.003, "grad": 0.1022, "tokens": 113868518400, "tok_s": 159159.8}
|
| 33 |
+
{"step": 108640, "epoch": 0.69, "loss": 1.66351, "ppl": 5.278, "lr": 0.003, "grad": 0.1001, "tokens": 113889484800, "tok_s": 159061.3}
|
| 34 |
+
{"step": 108660, "epoch": 0.69, "loss": 1.84406, "ppl": 6.322, "lr": 0.003, "grad": 0.0975, "tokens": 113910451200, "tok_s": 159051.8}
|
| 35 |
+
{"step": 108680, "epoch": 0.691, "loss": 1.77184, "ppl": 5.882, "lr": 0.003, "grad": 0.1471, "tokens": 113931417600, "tok_s": 159358.4}
|
| 36 |
+
{"step": 108700, "epoch": 0.691, "loss": 1.74199, "ppl": 5.709, "lr": 0.003, "grad": 0.116, "tokens": 113952384000, "tok_s": 158750.2}
|
| 37 |
+
{"step": 108720, "epoch": 0.691, "loss": 1.66658, "ppl": 5.294, "lr": 0.003, "grad": 0.108, "tokens": 113973350400, "tok_s": 158885.5}
|
| 38 |
+
{"step": 108740, "epoch": 0.691, "loss": 1.69864, "ppl": 5.466, "lr": 0.003, "grad": 0.0686, "tokens": 113994316800, "tok_s": 159047.9}
|
| 39 |
+
{"step": 108760, "epoch": 0.691, "loss": 1.76744, "ppl": 5.856, "lr": 0.003, "grad": 0.0725, "tokens": 114015283200, "tok_s": 158612.8}
|
| 40 |
+
{"step": 108780, "epoch": 0.691, "loss": 1.67806, "ppl": 5.355, "lr": 0.003, "grad": 0.1065, "tokens": 114036249600, "tok_s": 159074.5}
|
| 41 |
+
{"step": 108800, "epoch": 0.691, "loss": 1.69361, "ppl": 5.439, "lr": 0.003, "grad": 0.1198, "tokens": 114057216000, "tok_s": 158311.1}
|
| 42 |
+
{"step": 108820, "epoch": 0.691, "loss": 1.74227, "ppl": 5.71, "lr": 0.003, "grad": 0.1113, "tokens": 114078182400, "tok_s": 158962.4}
|
| 43 |
+
{"step": 108840, "epoch": 0.692, "loss": 1.67661, "ppl": 5.347, "lr": 0.003, "grad": 0.0726, "tokens": 114099148800, "tok_s": 159127.3}
|
| 44 |
+
{"step": 108860, "epoch": 0.692, "loss": 1.75207, "ppl": 5.767, "lr": 0.003, "grad": 0.0926, "tokens": 114120115200, "tok_s": 159114.9}
|
| 45 |
+
{"step": 108880, "epoch": 0.692, "loss": 1.78028, "ppl": 5.932, "lr": 0.003, "grad": 0.0944, "tokens": 114141081600, "tok_s": 159095.0}
|
| 46 |
+
{"step": 108900, "epoch": 0.692, "loss": 1.45231, "ppl": 4.273, "lr": 0.003, "grad": 0.0811, "tokens": 114162048000, "tok_s": 158766.7}
|
| 47 |
+
{"step": 108920, "epoch": 0.692, "loss": 1.67896, "ppl": 5.36, "lr": 0.003, "grad": 0.1297, "tokens": 114183014400, "tok_s": 158716.9}
|
| 48 |
+
{"step": 108940, "epoch": 0.692, "loss": 1.69114, "ppl": 5.426, "lr": 0.003, "grad": 0.0714, "tokens": 114203980800, "tok_s": 159226.3}
|
| 49 |
+
{"step": 108960, "epoch": 0.692, "loss": 1.78483, "ppl": 5.959, "lr": 0.003, "grad": 0.0848, "tokens": 114224947200, "tok_s": 159024.2}
|
| 50 |
+
{"step": 108980, "epoch": 0.692, "loss": 1.7362, "ppl": 5.676, "lr": 0.003, "grad": 0.0833, "tokens": 114245913600, "tok_s": 158551.6}
|
| 51 |
+
{"step": 109000, "epoch": 0.693, "loss": 1.89243, "ppl": 6.635, "lr": 0.003, "grad": 0.1041, "tokens": 114266880000, "tok_s": 159175.6}
|
| 52 |
+
{"step": 109000, "val_loss": 1.73288, "val_ppl": 5.657, "is_best": true}
|
| 53 |
+
{"step": 109020, "epoch": 0.693, "loss": 1.73623, "ppl": 5.676, "lr": 0.003, "grad": 0.1133, "tokens": 114287846400, "tok_s": 158562.8}
|
| 54 |
+
{"step": 109040, "epoch": 0.693, "loss": 1.67899, "ppl": 5.36, "lr": 0.003, "grad": 0.122, "tokens": 114308812800, "tok_s": 158957.5}
|
| 55 |
+
{"step": 109060, "epoch": 0.693, "loss": 1.77498, "ppl": 5.9, "lr": 0.003, "grad": 0.1183, "tokens": 114329779200, "tok_s": 158635.2}
|
| 56 |
+
{"step": 109080, "epoch": 0.693, "loss": 1.72682, "ppl": 5.623, "lr": 0.003, "grad": 0.133, "tokens": 114350745600, "tok_s": 159053.0}
|
| 57 |
+
{"step": 109100, "epoch": 0.693, "loss": 1.59864, "ppl": 4.946, "lr": 0.003, "grad": 0.0731, "tokens": 114371712000, "tok_s": 158945.6}
|
| 58 |
+
{"step": 109120, "epoch": 0.693, "loss": 1.87152, "ppl": 6.498, "lr": 0.003, "grad": 0.1226, "tokens": 114392678400, "tok_s": 158979.5}
|
| 59 |
+
{"step": 109140, "epoch": 0.693, "loss": 1.7656, "ppl": 5.845, "lr": 0.003, "grad": 0.0712, "tokens": 114413644800, "tok_s": 158856.8}
|
| 60 |
+
{"step": 109160, "epoch": 0.694, "loss": 1.75175, "ppl": 5.765, "lr": 0.003, "grad": 0.1197, "tokens": 114434611200, "tok_s": 158864.0}
|
| 61 |
+
{"step": 109180, "epoch": 0.694, "loss": 1.79459, "ppl": 6.017, "lr": 0.003, "grad": 0.075, "tokens": 114455577600, "tok_s": 159128.8}
|
| 62 |
+
{"step": 109200, "epoch": 0.694, "loss": 1.70936, "ppl": 5.525, "lr": 0.003, "grad": 0.1687, "tokens": 114476544000, "tok_s": 158856.4}
|
| 63 |
+
{"step": 109220, "epoch": 0.694, "loss": 1.7816, "ppl": 5.939, "lr": 0.003, "grad": 0.0802, "tokens": 114497510400, "tok_s": 159429.2}
|
| 64 |
+
{"step": 109240, "epoch": 0.694, "loss": 1.69158, "ppl": 5.428, "lr": 0.003, "grad": 0.0868, "tokens": 114518476800, "tok_s": 159396.3}
|
| 65 |
+
{"step": 109260, "epoch": 0.694, "loss": 1.72195, "ppl": 5.595, "lr": 0.003, "grad": 0.0799, "tokens": 114539443200, "tok_s": 159192.0}
|
| 66 |
+
{"step": 109280, "epoch": 0.694, "loss": 1.60469, "ppl": 4.976, "lr": 0.003, "grad": 0.0877, "tokens": 114560409600, "tok_s": 159283.2}
|
| 67 |
+
{"step": 109300, "epoch": 0.694, "loss": 1.80401, "ppl": 6.074, "lr": 0.003, "grad": 0.0842, "tokens": 114581376000, "tok_s": 159141.0}
|
| 68 |
+
{"step": 109320, "epoch": 0.695, "loss": 1.74401, "ppl": 5.72, "lr": 0.003, "grad": 0.1062, "tokens": 114602342400, "tok_s": 159064.5}
|
| 69 |
+
{"step": 109340, "epoch": 0.695, "loss": 1.79633, "ppl": 6.027, "lr": 0.003, "grad": 0.0906, "tokens": 114623308800, "tok_s": 159188.7}
|
| 70 |
+
{"step": 109360, "epoch": 0.695, "loss": 1.73522, "ppl": 5.67, "lr": 0.003, "grad": 0.1054, "tokens": 114644275200, "tok_s": 159236.6}
|
| 71 |
+
{"step": 109380, "epoch": 0.695, "loss": 1.84514, "ppl": 6.329, "lr": 0.003, "grad": 0.0836, "tokens": 114665241600, "tok_s": 159146.2}
|
| 72 |
+
{"step": 109400, "epoch": 0.695, "loss": 1.81221, "ppl": 6.124, "lr": 0.003, "grad": 0.0795, "tokens": 114686208000, "tok_s": 158973.0}
|
| 73 |
+
{"step": 109420, "epoch": 0.695, "loss": 1.79499, "ppl": 6.019, "lr": 0.003, "grad": 0.0952, "tokens": 114707174400, "tok_s": 159163.4}
|
| 74 |
+
{"step": 109440, "epoch": 0.695, "loss": 1.73455, "ppl": 5.666, "lr": 0.003, "grad": 0.1025, "tokens": 114728140800, "tok_s": 159163.7}
|
| 75 |
+
{"step": 109460, "epoch": 0.695, "loss": 1.77711, "ppl": 5.913, "lr": 0.003, "grad": 0.1145, "tokens": 114749107200, "tok_s": 159227.8}
|
| 76 |
+
{"step": 109480, "epoch": 0.696, "loss": 1.82109, "ppl": 6.179, "lr": 0.003, "grad": 0.108, "tokens": 114770073600, "tok_s": 158520.2}
|
| 77 |
+
{"step": 109500, "epoch": 0.696, "loss": 1.78091, "ppl": 5.935, "lr": 0.003, "grad": 0.1455, "tokens": 114791040000, "tok_s": 158970.7}
|
| 78 |
+
{"step": 109520, "epoch": 0.696, "loss": 1.78594, "ppl": 5.965, "lr": 0.003, "grad": 0.0965, "tokens": 114812006400, "tok_s": 158568.5}
|
| 79 |
+
{"step": 109540, "epoch": 0.696, "loss": 1.71081, "ppl": 5.533, "lr": 0.003, "grad": 0.1095, "tokens": 114832972800, "tok_s": 158794.9}
|
| 80 |
+
{"step": 109560, "epoch": 0.696, "loss": 1.79209, "ppl": 6.002, "lr": 0.003, "grad": 0.1064, "tokens": 114853939200, "tok_s": 158785.9}
|
| 81 |
+
{"step": 109580, "epoch": 0.696, "loss": 1.59386, "ppl": 4.923, "lr": 0.003, "grad": 0.0668, "tokens": 114874905600, "tok_s": 158493.7}
|
| 82 |
+
{"step": 109600, "epoch": 0.696, "loss": 1.76839, "ppl": 5.861, "lr": 0.003, "grad": 0.1049, "tokens": 114895872000, "tok_s": 158374.2}
|
| 83 |
+
{"step": 109620, "epoch": 0.696, "loss": 1.76656, "ppl": 5.851, "lr": 0.003, "grad": 0.0699, "tokens": 114916838400, "tok_s": 159085.4}
|
| 84 |
+
{"step": 109640, "epoch": 0.697, "loss": 1.73206, "ppl": 5.652, "lr": 0.003, "grad": 0.1239, "tokens": 114937804800, "tok_s": 158970.6}
|
| 85 |
+
{"step": 109660, "epoch": 0.697, "loss": 1.78539, "ppl": 5.962, "lr": 0.003, "grad": 0.1003, "tokens": 114958771200, "tok_s": 159237.3}
|
| 86 |
+
{"step": 109680, "epoch": 0.697, "loss": 1.75903, "ppl": 5.807, "lr": 0.003, "grad": 0.1701, "tokens": 114979737600, "tok_s": 159190.0}
|
| 87 |
+
{"step": 109700, "epoch": 0.697, "loss": 1.73013, "ppl": 5.641, "lr": 0.003, "grad": 0.0824, "tokens": 115000704000, "tok_s": 159145.2}
|
| 88 |
+
{"step": 109720, "epoch": 0.697, "loss": 1.70807, "ppl": 5.518, "lr": 0.003, "grad": 0.089, "tokens": 115021670400, "tok_s": 159392.1}
|
| 89 |
+
{"step": 109740, "epoch": 0.697, "loss": 1.7454, "ppl": 5.728, "lr": 0.003, "grad": 0.0596, "tokens": 115042636800, "tok_s": 158812.2}
|
| 90 |
+
{"step": 109760, "epoch": 0.697, "loss": 1.63906, "ppl": 5.15, "lr": 0.003, "grad": 0.0936, "tokens": 115063603200, "tok_s": 158822.8}
|
| 91 |
+
{"step": 109780, "epoch": 0.698, "loss": 1.71756, "ppl": 5.571, "lr": 0.003, "grad": 0.1026, "tokens": 115084569600, "tok_s": 159321.3}
|
| 92 |
+
{"step": 109800, "epoch": 0.698, "loss": 1.74078, "ppl": 5.702, "lr": 0.003, "grad": 0.1413, "tokens": 115105536000, "tok_s": 158977.1}
|
| 93 |
+
{"step": 109820, "epoch": 0.698, "loss": 1.76512, "ppl": 5.842, "lr": 0.003, "grad": 0.0856, "tokens": 115126502400, "tok_s": 159024.3}
|
| 94 |
+
{"step": 109840, "epoch": 0.698, "loss": 1.77975, "ppl": 5.928, "lr": 0.003, "grad": 0.0778, "tokens": 115147468800, "tok_s": 158361.9}
|
| 95 |
+
{"step": 109860, "epoch": 0.698, "loss": 1.79078, "ppl": 5.994, "lr": 0.003, "grad": 0.1127, "tokens": 115168435200, "tok_s": 159277.9}
|
| 96 |
+
{"step": 109880, "epoch": 0.698, "loss": 1.76985, "ppl": 5.87, "lr": 0.003, "grad": 0.0778, "tokens": 115189401600, "tok_s": 158912.3}
|
| 97 |
+
{"step": 109900, "epoch": 0.698, "loss": 1.75561, "ppl": 5.787, "lr": 0.003, "grad": 0.0748, "tokens": 115210368000, "tok_s": 159123.7}
|
| 98 |
+
{"step": 109920, "epoch": 0.698, "loss": 1.77873, "ppl": 5.922, "lr": 0.003, "grad": 0.0943, "tokens": 115231334400, "tok_s": 159401.3}
|
| 99 |
+
{"step": 109940, "epoch": 0.699, "loss": 1.72977, "ppl": 5.639, "lr": 0.003, "grad": 0.0723, "tokens": 115252300800, "tok_s": 159292.3}
|
| 100 |
+
{"step": 109960, "epoch": 0.699, "loss": 1.75106, "ppl": 5.761, "lr": 0.003, "grad": 0.0762, "tokens": 115273267200, "tok_s": 159346.4}
|
| 101 |
+
{"step": 109980, "epoch": 0.699, "loss": 1.79941, "ppl": 6.046, "lr": 0.003, "grad": 0.1027, "tokens": 115294233600, "tok_s": 159496.4}
|
| 102 |
+
{"step": 110000, "epoch": 0.699, "loss": 1.72724, "ppl": 5.625, "lr": 0.003, "grad": 0.0953, "tokens": 115315200000, "tok_s": 159029.0}
|
| 103 |
+
{"step": 110000, "val_loss": 1.74385, "val_ppl": 5.719, "is_best": false}
|
| 104 |
+
{"step": 110020, "epoch": 0.699, "loss": 1.76178, "ppl": 5.823, "lr": 0.003, "grad": 0.1406, "tokens": 115336166400, "tok_s": 159314.7}
|
| 105 |
+
{"step": 110040, "epoch": 0.699, "loss": 1.75121, "ppl": 5.762, "lr": 0.003, "grad": 0.0795, "tokens": 115357132800, "tok_s": 159269.8}
|
| 106 |
+
{"step": 110060, "epoch": 0.699, "loss": 1.69675, "ppl": 5.456, "lr": 0.003, "grad": 0.0868, "tokens": 115378099200, "tok_s": 159030.7}
|
| 107 |
+
{"step": 110080, "epoch": 0.699, "loss": 1.76612, "ppl": 5.848, "lr": 0.003, "grad": 0.0979, "tokens": 115399065600, "tok_s": 159206.6}
|
| 108 |
+
{"step": 110100, "epoch": 0.7, "loss": 1.75739, "ppl": 5.797, "lr": 0.003, "grad": 0.088, "tokens": 115420032000, "tok_s": 159121.2}
|
| 109 |
+
{"step": 110120, "epoch": 0.7, "loss": 1.83068, "ppl": 6.238, "lr": 0.003, "grad": 0.1548, "tokens": 115440998400, "tok_s": 159261.6}
|
| 110 |
+
{"step": 110140, "epoch": 0.7, "loss": 1.77349, "ppl": 5.891, "lr": 0.003, "grad": 0.1482, "tokens": 115461964800, "tok_s": 159150.4}
|
| 111 |
+
{"step": 110160, "epoch": 0.7, "loss": 1.72478, "ppl": 5.611, "lr": 0.003, "grad": 0.0787, "tokens": 115482931200, "tok_s": 158986.2}
|
| 112 |
+
{"step": 110180, "epoch": 0.7, "loss": 1.75132, "ppl": 5.762, "lr": 0.003, "grad": 0.1179, "tokens": 115503897600, "tok_s": 159166.4}
|
| 113 |
+
{"step": 110200, "epoch": 0.7, "loss": 1.80498, "ppl": 6.08, "lr": 0.003, "grad": 0.0891, "tokens": 115524864000, "tok_s": 159210.4}
|
| 114 |
+
{"step": 110220, "epoch": 0.7, "loss": 1.70461, "ppl": 5.499, "lr": 0.003, "grad": 0.086, "tokens": 115545830400, "tok_s": 158635.4}
|
| 115 |
+
{"step": 110240, "epoch": 0.7, "loss": 1.74953, "ppl": 5.752, "lr": 0.003, "grad": 0.0893, "tokens": 115566796800, "tok_s": 158553.4}
|
| 116 |
+
{"step": 110260, "epoch": 0.701, "loss": 1.66313, "ppl": 5.276, "lr": 0.003, "grad": 0.0676, "tokens": 115587763200, "tok_s": 159319.4}
|
| 117 |
+
{"step": 110280, "epoch": 0.701, "loss": 1.76244, "ppl": 5.827, "lr": 0.003, "grad": 0.1082, "tokens": 115608729600, "tok_s": 158709.8}
|
| 118 |
+
{"step": 110300, "epoch": 0.701, "loss": 1.78618, "ppl": 5.967, "lr": 0.003, "grad": 0.0738, "tokens": 115629696000, "tok_s": 159270.7}
|
| 119 |
+
{"step": 110320, "epoch": 0.701, "loss": 1.66907, "ppl": 5.307, "lr": 0.003, "grad": 0.1015, "tokens": 115650662400, "tok_s": 158840.8}
|
| 120 |
+
{"step": 110340, "epoch": 0.701, "loss": 1.63189, "ppl": 5.114, "lr": 0.003, "grad": 0.1245, "tokens": 115671628800, "tok_s": 159193.9}
|
| 121 |
+
{"step": 110360, "epoch": 0.701, "loss": 1.75918, "ppl": 5.808, "lr": 0.003, "grad": 0.0886, "tokens": 115692595200, "tok_s": 159022.3}
|
| 122 |
+
{"step": 110380, "epoch": 0.701, "loss": 1.73369, "ppl": 5.661, "lr": 0.003, "grad": 0.1006, "tokens": 115713561600, "tok_s": 159316.0}
|
| 123 |
+
{"step": 110400, "epoch": 0.701, "loss": 1.64915, "ppl": 5.203, "lr": 0.003, "grad": 0.0742, "tokens": 115734528000, "tok_s": 159118.4}
|
| 124 |
+
{"step": 110420, "epoch": 0.702, "loss": 1.66734, "ppl": 5.298, "lr": 0.003, "grad": 0.0914, "tokens": 115755494400, "tok_s": 158787.8}
|
| 125 |
+
{"step": 110440, "epoch": 0.702, "loss": 1.85501, "ppl": 6.392, "lr": 0.003, "grad": 0.1211, "tokens": 115776460800, "tok_s": 158711.9}
|
| 126 |
+
{"step": 110460, "epoch": 0.702, "loss": 1.64944, "ppl": 5.204, "lr": 0.003, "grad": 0.1314, "tokens": 115797427200, "tok_s": 159306.0}
|
| 127 |
+
{"step": 110480, "epoch": 0.702, "loss": 1.72494, "ppl": 5.612, "lr": 0.003, "grad": 0.0604, "tokens": 115818393600, "tok_s": 159041.1}
|
| 128 |
+
{"step": 110500, "epoch": 0.702, "loss": 1.7002, "ppl": 5.475, "lr": 0.003, "grad": 0.0801, "tokens": 115839360000, "tok_s": 158925.5}
|
| 129 |
+
{"step": 110520, "epoch": 0.702, "loss": 1.71367, "ppl": 5.549, "lr": 0.003, "grad": 0.0822, "tokens": 115860326400, "tok_s": 158937.2}
|
| 130 |
+
{"step": 110540, "epoch": 0.702, "loss": 1.71543, "ppl": 5.559, "lr": 0.003, "grad": 0.1216, "tokens": 115881292800, "tok_s": 159384.8}
|
| 131 |
+
{"step": 110560, "epoch": 0.702, "loss": 1.81401, "ppl": 6.135, "lr": 0.003, "grad": 0.1036, "tokens": 115902259200, "tok_s": 159293.5}
|
| 132 |
+
{"step": 110580, "epoch": 0.703, "loss": 1.74452, "ppl": 5.723, "lr": 0.003, "grad": 0.107, "tokens": 115923225600, "tok_s": 159081.0}
|
| 133 |
+
{"step": 110600, "epoch": 0.703, "loss": 1.77592, "ppl": 5.906, "lr": 0.003, "grad": 0.0614, "tokens": 115944192000, "tok_s": 158693.3}
|
| 134 |
+
{"step": 110620, "epoch": 0.703, "loss": 1.73993, "ppl": 5.697, "lr": 0.003, "grad": 0.1163, "tokens": 115965158400, "tok_s": 159237.2}
|
| 135 |
+
{"step": 110640, "epoch": 0.703, "loss": 1.77779, "ppl": 5.917, "lr": 0.003, "grad": 0.0967, "tokens": 115986124800, "tok_s": 159123.3}
|
| 136 |
+
{"step": 110660, "epoch": 0.703, "loss": 1.64579, "ppl": 5.185, "lr": 0.003, "grad": 0.0867, "tokens": 116007091200, "tok_s": 159020.9}
|
| 137 |
+
{"step": 110680, "epoch": 0.703, "loss": 1.74047, "ppl": 5.7, "lr": 0.003, "grad": 0.1103, "tokens": 116028057600, "tok_s": 159155.7}
|
| 138 |
+
{"step": 110700, "epoch": 0.703, "loss": 1.69972, "ppl": 5.472, "lr": 0.003, "grad": 0.1113, "tokens": 116049024000, "tok_s": 159158.5}
|
| 139 |
+
{"step": 110720, "epoch": 0.703, "loss": 1.78604, "ppl": 5.966, "lr": 0.003, "grad": 0.0857, "tokens": 116069990400, "tok_s": 159214.9}
|
| 140 |
+
{"step": 110740, "epoch": 0.704, "loss": 1.60962, "ppl": 5.001, "lr": 0.003, "grad": 0.0856, "tokens": 116090956800, "tok_s": 159302.0}
|
| 141 |
+
{"step": 110760, "epoch": 0.704, "loss": 1.778, "ppl": 5.918, "lr": 0.003, "grad": 0.0979, "tokens": 116111923200, "tok_s": 158702.2}
|
| 142 |
+
{"step": 110780, "epoch": 0.704, "loss": 1.78549, "ppl": 5.962, "lr": 0.003, "grad": 0.1108, "tokens": 116132889600, "tok_s": 158791.8}
|
| 143 |
+
{"step": 110800, "epoch": 0.704, "loss": 1.75949, "ppl": 5.81, "lr": 0.003, "grad": 0.1462, "tokens": 116153856000, "tok_s": 159378.8}
|
| 144 |
+
{"step": 110820, "epoch": 0.704, "loss": 1.77886, "ppl": 5.923, "lr": 0.003, "grad": 0.1145, "tokens": 116174822400, "tok_s": 159320.7}
|
| 145 |
+
{"step": 110840, "epoch": 0.704, "loss": 1.77943, "ppl": 5.926, "lr": 0.003, "grad": 0.0896, "tokens": 116195788800, "tok_s": 158933.4}
|
| 146 |
+
{"step": 110860, "epoch": 0.704, "loss": 1.80276, "ppl": 6.066, "lr": 0.003, "grad": 0.1157, "tokens": 116216755200, "tok_s": 159196.3}
|
| 147 |
+
{"step": 110880, "epoch": 0.704, "loss": 1.71631, "ppl": 5.564, "lr": 0.003, "grad": 0.0982, "tokens": 116237721600, "tok_s": 159403.0}
|
| 148 |
+
{"step": 110900, "epoch": 0.705, "loss": 1.77119, "ppl": 5.878, "lr": 0.003, "grad": 0.068, "tokens": 116258688000, "tok_s": 159247.9}
|
| 149 |
+
{"step": 110920, "epoch": 0.705, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.0752, "tokens": 116279654400, "tok_s": 159255.1}
|
| 150 |
+
{"step": 110940, "epoch": 0.705, "loss": 1.7345, "ppl": 5.666, "lr": 0.003, "grad": 0.0871, "tokens": 116300620800, "tok_s": 159291.1}
|
| 151 |
+
{"step": 110960, "epoch": 0.705, "loss": 1.78909, "ppl": 5.984, "lr": 0.003, "grad": 0.0908, "tokens": 116321587200, "tok_s": 159059.9}
|
| 152 |
+
{"step": 110980, "epoch": 0.705, "loss": 1.76201, "ppl": 5.824, "lr": 0.003, "grad": 0.112, "tokens": 116342553600, "tok_s": 159287.3}
|
| 153 |
+
{"step": 111000, "epoch": 0.705, "loss": 1.7672, "ppl": 5.854, "lr": 0.003, "grad": 0.1463, "tokens": 116363520000, "tok_s": 159431.0}
|
| 154 |
+
{"step": 111000, "val_loss": 1.75042, "val_ppl": 5.757, "is_best": false}
|
logs/log_112000.jsonl
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 108000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-04T17:47:03.162778"}
|
| 2 |
+
{"step": 108020, "epoch": 0.686, "loss": 1.74155, "ppl": 5.706, "lr": 0.003, "grad": 0.1535, "tokens": 113239526400, "tok_s": 159409.6}
|
| 3 |
+
{"step": 108040, "epoch": 0.686, "loss": 1.74208, "ppl": 5.709, "lr": 0.003, "grad": 0.1116, "tokens": 113260492800, "tok_s": 158966.0}
|
| 4 |
+
{"step": 108060, "epoch": 0.687, "loss": 1.71701, "ppl": 5.568, "lr": 0.003, "grad": 0.119, "tokens": 113281459200, "tok_s": 158764.9}
|
| 5 |
+
{"step": 108080, "epoch": 0.687, "loss": 1.61379, "ppl": 5.022, "lr": 0.003, "grad": 0.1259, "tokens": 113302425600, "tok_s": 159374.6}
|
| 6 |
+
{"step": 108100, "epoch": 0.687, "loss": 1.76912, "ppl": 5.866, "lr": 0.003, "grad": 0.1513, "tokens": 113323392000, "tok_s": 159426.1}
|
| 7 |
+
{"step": 108120, "epoch": 0.687, "loss": 1.73133, "ppl": 5.648, "lr": 0.003, "grad": 0.1181, "tokens": 113344358400, "tok_s": 159368.3}
|
| 8 |
+
{"step": 108140, "epoch": 0.687, "loss": 1.74469, "ppl": 5.724, "lr": 0.003, "grad": 0.081, "tokens": 113365324800, "tok_s": 159141.7}
|
| 9 |
+
{"step": 108160, "epoch": 0.687, "loss": 1.67668, "ppl": 5.348, "lr": 0.003, "grad": 0.097, "tokens": 113386291200, "tok_s": 159307.4}
|
| 10 |
+
{"step": 108180, "epoch": 0.687, "loss": 1.6295, "ppl": 5.101, "lr": 0.003, "grad": 0.074, "tokens": 113407257600, "tok_s": 158959.6}
|
| 11 |
+
{"step": 108200, "epoch": 0.687, "loss": 1.59394, "ppl": 4.923, "lr": 0.003, "grad": 0.1446, "tokens": 113428224000, "tok_s": 159053.4}
|
| 12 |
+
{"step": 108220, "epoch": 0.688, "loss": 1.78001, "ppl": 5.93, "lr": 0.003, "grad": 0.0736, "tokens": 113449190400, "tok_s": 159320.4}
|
| 13 |
+
{"step": 108240, "epoch": 0.688, "loss": 1.70317, "ppl": 5.491, "lr": 0.003, "grad": 0.1291, "tokens": 113470156800, "tok_s": 159284.0}
|
| 14 |
+
{"step": 108260, "epoch": 0.688, "loss": 1.76076, "ppl": 5.817, "lr": 0.003, "grad": 0.0607, "tokens": 113491123200, "tok_s": 159430.1}
|
| 15 |
+
{"step": 108280, "epoch": 0.688, "loss": 1.71242, "ppl": 5.542, "lr": 0.003, "grad": 0.0832, "tokens": 113512089600, "tok_s": 159396.6}
|
| 16 |
+
{"step": 108300, "epoch": 0.688, "loss": 1.75654, "ppl": 5.792, "lr": 0.003, "grad": 0.0942, "tokens": 113533056000, "tok_s": 159177.0}
|
| 17 |
+
{"step": 108320, "epoch": 0.688, "loss": 1.76145, "ppl": 5.821, "lr": 0.003, "grad": 0.0929, "tokens": 113554022400, "tok_s": 159418.2}
|
| 18 |
+
{"step": 108340, "epoch": 0.688, "loss": 1.72596, "ppl": 5.618, "lr": 0.003, "grad": 0.1128, "tokens": 113574988800, "tok_s": 159462.3}
|
| 19 |
+
{"step": 108360, "epoch": 0.688, "loss": 1.77282, "ppl": 5.887, "lr": 0.003, "grad": 0.0726, "tokens": 113595955200, "tok_s": 159439.0}
|
| 20 |
+
{"step": 108380, "epoch": 0.689, "loss": 1.68249, "ppl": 5.379, "lr": 0.003, "grad": 0.0773, "tokens": 113616921600, "tok_s": 158841.1}
|
| 21 |
+
{"step": 108400, "epoch": 0.689, "loss": 1.78284, "ppl": 5.947, "lr": 0.003, "grad": 0.1421, "tokens": 113637888000, "tok_s": 159390.6}
|
| 22 |
+
{"step": 108420, "epoch": 0.689, "loss": 1.76143, "ppl": 5.821, "lr": 0.003, "grad": 0.1094, "tokens": 113658854400, "tok_s": 159248.9}
|
| 23 |
+
{"step": 108440, "epoch": 0.689, "loss": 1.6718, "ppl": 5.322, "lr": 0.003, "grad": 0.0636, "tokens": 113679820800, "tok_s": 159083.0}
|
| 24 |
+
{"step": 108460, "epoch": 0.689, "loss": 1.81265, "ppl": 6.127, "lr": 0.003, "grad": 0.106, "tokens": 113700787200, "tok_s": 159288.0}
|
| 25 |
+
{"step": 108480, "epoch": 0.689, "loss": 1.80861, "ppl": 6.102, "lr": 0.003, "grad": 0.1554, "tokens": 113721753600, "tok_s": 159226.0}
|
| 26 |
+
{"step": 108500, "epoch": 0.689, "loss": 1.89807, "ppl": 6.673, "lr": 0.003, "grad": 0.119, "tokens": 113742720000, "tok_s": 158977.2}
|
| 27 |
+
{"step": 108520, "epoch": 0.689, "loss": 1.76412, "ppl": 5.836, "lr": 0.003, "grad": 0.0783, "tokens": 113763686400, "tok_s": 158959.6}
|
| 28 |
+
{"step": 108540, "epoch": 0.69, "loss": 1.65952, "ppl": 5.257, "lr": 0.003, "grad": 0.0907, "tokens": 113784652800, "tok_s": 159425.9}
|
| 29 |
+
{"step": 108560, "epoch": 0.69, "loss": 1.67979, "ppl": 5.364, "lr": 0.003, "grad": 0.1137, "tokens": 113805619200, "tok_s": 159124.8}
|
| 30 |
+
{"step": 108580, "epoch": 0.69, "loss": 1.70389, "ppl": 5.495, "lr": 0.003, "grad": 0.1058, "tokens": 113826585600, "tok_s": 159404.3}
|
| 31 |
+
{"step": 108600, "epoch": 0.69, "loss": 1.6402, "ppl": 5.156, "lr": 0.003, "grad": 0.0885, "tokens": 113847552000, "tok_s": 159333.4}
|
| 32 |
+
{"step": 108620, "epoch": 0.69, "loss": 1.71514, "ppl": 5.557, "lr": 0.003, "grad": 0.1022, "tokens": 113868518400, "tok_s": 159159.8}
|
| 33 |
+
{"step": 108640, "epoch": 0.69, "loss": 1.66351, "ppl": 5.278, "lr": 0.003, "grad": 0.1001, "tokens": 113889484800, "tok_s": 159061.3}
|
| 34 |
+
{"step": 108660, "epoch": 0.69, "loss": 1.84406, "ppl": 6.322, "lr": 0.003, "grad": 0.0975, "tokens": 113910451200, "tok_s": 159051.8}
|
| 35 |
+
{"step": 108680, "epoch": 0.691, "loss": 1.77184, "ppl": 5.882, "lr": 0.003, "grad": 0.1471, "tokens": 113931417600, "tok_s": 159358.4}
|
| 36 |
+
{"step": 108700, "epoch": 0.691, "loss": 1.74199, "ppl": 5.709, "lr": 0.003, "grad": 0.116, "tokens": 113952384000, "tok_s": 158750.2}
|
| 37 |
+
{"step": 108720, "epoch": 0.691, "loss": 1.66658, "ppl": 5.294, "lr": 0.003, "grad": 0.108, "tokens": 113973350400, "tok_s": 158885.5}
|
| 38 |
+
{"step": 108740, "epoch": 0.691, "loss": 1.69864, "ppl": 5.466, "lr": 0.003, "grad": 0.0686, "tokens": 113994316800, "tok_s": 159047.9}
|
| 39 |
+
{"step": 108760, "epoch": 0.691, "loss": 1.76744, "ppl": 5.856, "lr": 0.003, "grad": 0.0725, "tokens": 114015283200, "tok_s": 158612.8}
|
| 40 |
+
{"step": 108780, "epoch": 0.691, "loss": 1.67806, "ppl": 5.355, "lr": 0.003, "grad": 0.1065, "tokens": 114036249600, "tok_s": 159074.5}
|
| 41 |
+
{"step": 108800, "epoch": 0.691, "loss": 1.69361, "ppl": 5.439, "lr": 0.003, "grad": 0.1198, "tokens": 114057216000, "tok_s": 158311.1}
|
| 42 |
+
{"step": 108820, "epoch": 0.691, "loss": 1.74227, "ppl": 5.71, "lr": 0.003, "grad": 0.1113, "tokens": 114078182400, "tok_s": 158962.4}
|
| 43 |
+
{"step": 108840, "epoch": 0.692, "loss": 1.67661, "ppl": 5.347, "lr": 0.003, "grad": 0.0726, "tokens": 114099148800, "tok_s": 159127.3}
|
| 44 |
+
{"step": 108860, "epoch": 0.692, "loss": 1.75207, "ppl": 5.767, "lr": 0.003, "grad": 0.0926, "tokens": 114120115200, "tok_s": 159114.9}
|
| 45 |
+
{"step": 108880, "epoch": 0.692, "loss": 1.78028, "ppl": 5.932, "lr": 0.003, "grad": 0.0944, "tokens": 114141081600, "tok_s": 159095.0}
|
| 46 |
+
{"step": 108900, "epoch": 0.692, "loss": 1.45231, "ppl": 4.273, "lr": 0.003, "grad": 0.0811, "tokens": 114162048000, "tok_s": 158766.7}
|
| 47 |
+
{"step": 108920, "epoch": 0.692, "loss": 1.67896, "ppl": 5.36, "lr": 0.003, "grad": 0.1297, "tokens": 114183014400, "tok_s": 158716.9}
|
| 48 |
+
{"step": 108940, "epoch": 0.692, "loss": 1.69114, "ppl": 5.426, "lr": 0.003, "grad": 0.0714, "tokens": 114203980800, "tok_s": 159226.3}
|
| 49 |
+
{"step": 108960, "epoch": 0.692, "loss": 1.78483, "ppl": 5.959, "lr": 0.003, "grad": 0.0848, "tokens": 114224947200, "tok_s": 159024.2}
|
| 50 |
+
{"step": 108980, "epoch": 0.692, "loss": 1.7362, "ppl": 5.676, "lr": 0.003, "grad": 0.0833, "tokens": 114245913600, "tok_s": 158551.6}
|
| 51 |
+
{"step": 109000, "epoch": 0.693, "loss": 1.89243, "ppl": 6.635, "lr": 0.003, "grad": 0.1041, "tokens": 114266880000, "tok_s": 159175.6}
|
| 52 |
+
{"step": 109000, "val_loss": 1.73288, "val_ppl": 5.657, "is_best": true}
|
| 53 |
+
{"step": 109020, "epoch": 0.693, "loss": 1.73623, "ppl": 5.676, "lr": 0.003, "grad": 0.1133, "tokens": 114287846400, "tok_s": 158562.8}
|
| 54 |
+
{"step": 109040, "epoch": 0.693, "loss": 1.67899, "ppl": 5.36, "lr": 0.003, "grad": 0.122, "tokens": 114308812800, "tok_s": 158957.5}
|
| 55 |
+
{"step": 109060, "epoch": 0.693, "loss": 1.77498, "ppl": 5.9, "lr": 0.003, "grad": 0.1183, "tokens": 114329779200, "tok_s": 158635.2}
|
| 56 |
+
{"step": 109080, "epoch": 0.693, "loss": 1.72682, "ppl": 5.623, "lr": 0.003, "grad": 0.133, "tokens": 114350745600, "tok_s": 159053.0}
|
| 57 |
+
{"step": 109100, "epoch": 0.693, "loss": 1.59864, "ppl": 4.946, "lr": 0.003, "grad": 0.0731, "tokens": 114371712000, "tok_s": 158945.6}
|
| 58 |
+
{"step": 109120, "epoch": 0.693, "loss": 1.87152, "ppl": 6.498, "lr": 0.003, "grad": 0.1226, "tokens": 114392678400, "tok_s": 158979.5}
|
| 59 |
+
{"step": 109140, "epoch": 0.693, "loss": 1.7656, "ppl": 5.845, "lr": 0.003, "grad": 0.0712, "tokens": 114413644800, "tok_s": 158856.8}
|
| 60 |
+
{"step": 109160, "epoch": 0.694, "loss": 1.75175, "ppl": 5.765, "lr": 0.003, "grad": 0.1197, "tokens": 114434611200, "tok_s": 158864.0}
|
| 61 |
+
{"step": 109180, "epoch": 0.694, "loss": 1.79459, "ppl": 6.017, "lr": 0.003, "grad": 0.075, "tokens": 114455577600, "tok_s": 159128.8}
|
| 62 |
+
{"step": 109200, "epoch": 0.694, "loss": 1.70936, "ppl": 5.525, "lr": 0.003, "grad": 0.1687, "tokens": 114476544000, "tok_s": 158856.4}
|
| 63 |
+
{"step": 109220, "epoch": 0.694, "loss": 1.7816, "ppl": 5.939, "lr": 0.003, "grad": 0.0802, "tokens": 114497510400, "tok_s": 159429.2}
|
| 64 |
+
{"step": 109240, "epoch": 0.694, "loss": 1.69158, "ppl": 5.428, "lr": 0.003, "grad": 0.0868, "tokens": 114518476800, "tok_s": 159396.3}
|
| 65 |
+
{"step": 109260, "epoch": 0.694, "loss": 1.72195, "ppl": 5.595, "lr": 0.003, "grad": 0.0799, "tokens": 114539443200, "tok_s": 159192.0}
|
| 66 |
+
{"step": 109280, "epoch": 0.694, "loss": 1.60469, "ppl": 4.976, "lr": 0.003, "grad": 0.0877, "tokens": 114560409600, "tok_s": 159283.2}
|
| 67 |
+
{"step": 109300, "epoch": 0.694, "loss": 1.80401, "ppl": 6.074, "lr": 0.003, "grad": 0.0842, "tokens": 114581376000, "tok_s": 159141.0}
|
| 68 |
+
{"step": 109320, "epoch": 0.695, "loss": 1.74401, "ppl": 5.72, "lr": 0.003, "grad": 0.1062, "tokens": 114602342400, "tok_s": 159064.5}
|
| 69 |
+
{"step": 109340, "epoch": 0.695, "loss": 1.79633, "ppl": 6.027, "lr": 0.003, "grad": 0.0906, "tokens": 114623308800, "tok_s": 159188.7}
|
| 70 |
+
{"step": 109360, "epoch": 0.695, "loss": 1.73522, "ppl": 5.67, "lr": 0.003, "grad": 0.1054, "tokens": 114644275200, "tok_s": 159236.6}
|
| 71 |
+
{"step": 109380, "epoch": 0.695, "loss": 1.84514, "ppl": 6.329, "lr": 0.003, "grad": 0.0836, "tokens": 114665241600, "tok_s": 159146.2}
|
| 72 |
+
{"step": 109400, "epoch": 0.695, "loss": 1.81221, "ppl": 6.124, "lr": 0.003, "grad": 0.0795, "tokens": 114686208000, "tok_s": 158973.0}
|
| 73 |
+
{"step": 109420, "epoch": 0.695, "loss": 1.79499, "ppl": 6.019, "lr": 0.003, "grad": 0.0952, "tokens": 114707174400, "tok_s": 159163.4}
|
| 74 |
+
{"step": 109440, "epoch": 0.695, "loss": 1.73455, "ppl": 5.666, "lr": 0.003, "grad": 0.1025, "tokens": 114728140800, "tok_s": 159163.7}
|
| 75 |
+
{"step": 109460, "epoch": 0.695, "loss": 1.77711, "ppl": 5.913, "lr": 0.003, "grad": 0.1145, "tokens": 114749107200, "tok_s": 159227.8}
|
| 76 |
+
{"step": 109480, "epoch": 0.696, "loss": 1.82109, "ppl": 6.179, "lr": 0.003, "grad": 0.108, "tokens": 114770073600, "tok_s": 158520.2}
|
| 77 |
+
{"step": 109500, "epoch": 0.696, "loss": 1.78091, "ppl": 5.935, "lr": 0.003, "grad": 0.1455, "tokens": 114791040000, "tok_s": 158970.7}
|
| 78 |
+
{"step": 109520, "epoch": 0.696, "loss": 1.78594, "ppl": 5.965, "lr": 0.003, "grad": 0.0965, "tokens": 114812006400, "tok_s": 158568.5}
|
| 79 |
+
{"step": 109540, "epoch": 0.696, "loss": 1.71081, "ppl": 5.533, "lr": 0.003, "grad": 0.1095, "tokens": 114832972800, "tok_s": 158794.9}
|
| 80 |
+
{"step": 109560, "epoch": 0.696, "loss": 1.79209, "ppl": 6.002, "lr": 0.003, "grad": 0.1064, "tokens": 114853939200, "tok_s": 158785.9}
|
| 81 |
+
{"step": 109580, "epoch": 0.696, "loss": 1.59386, "ppl": 4.923, "lr": 0.003, "grad": 0.0668, "tokens": 114874905600, "tok_s": 158493.7}
|
| 82 |
+
{"step": 109600, "epoch": 0.696, "loss": 1.76839, "ppl": 5.861, "lr": 0.003, "grad": 0.1049, "tokens": 114895872000, "tok_s": 158374.2}
|
| 83 |
+
{"step": 109620, "epoch": 0.696, "loss": 1.76656, "ppl": 5.851, "lr": 0.003, "grad": 0.0699, "tokens": 114916838400, "tok_s": 159085.4}
|
| 84 |
+
{"step": 109640, "epoch": 0.697, "loss": 1.73206, "ppl": 5.652, "lr": 0.003, "grad": 0.1239, "tokens": 114937804800, "tok_s": 158970.6}
|
| 85 |
+
{"step": 109660, "epoch": 0.697, "loss": 1.78539, "ppl": 5.962, "lr": 0.003, "grad": 0.1003, "tokens": 114958771200, "tok_s": 159237.3}
|
| 86 |
+
{"step": 109680, "epoch": 0.697, "loss": 1.75903, "ppl": 5.807, "lr": 0.003, "grad": 0.1701, "tokens": 114979737600, "tok_s": 159190.0}
|
| 87 |
+
{"step": 109700, "epoch": 0.697, "loss": 1.73013, "ppl": 5.641, "lr": 0.003, "grad": 0.0824, "tokens": 115000704000, "tok_s": 159145.2}
|
| 88 |
+
{"step": 109720, "epoch": 0.697, "loss": 1.70807, "ppl": 5.518, "lr": 0.003, "grad": 0.089, "tokens": 115021670400, "tok_s": 159392.1}
|
| 89 |
+
{"step": 109740, "epoch": 0.697, "loss": 1.7454, "ppl": 5.728, "lr": 0.003, "grad": 0.0596, "tokens": 115042636800, "tok_s": 158812.2}
|
| 90 |
+
{"step": 109760, "epoch": 0.697, "loss": 1.63906, "ppl": 5.15, "lr": 0.003, "grad": 0.0936, "tokens": 115063603200, "tok_s": 158822.8}
|
| 91 |
+
{"step": 109780, "epoch": 0.698, "loss": 1.71756, "ppl": 5.571, "lr": 0.003, "grad": 0.1026, "tokens": 115084569600, "tok_s": 159321.3}
|
| 92 |
+
{"step": 109800, "epoch": 0.698, "loss": 1.74078, "ppl": 5.702, "lr": 0.003, "grad": 0.1413, "tokens": 115105536000, "tok_s": 158977.1}
|
| 93 |
+
{"step": 109820, "epoch": 0.698, "loss": 1.76512, "ppl": 5.842, "lr": 0.003, "grad": 0.0856, "tokens": 115126502400, "tok_s": 159024.3}
|
| 94 |
+
{"step": 109840, "epoch": 0.698, "loss": 1.77975, "ppl": 5.928, "lr": 0.003, "grad": 0.0778, "tokens": 115147468800, "tok_s": 158361.9}
|
| 95 |
+
{"step": 109860, "epoch": 0.698, "loss": 1.79078, "ppl": 5.994, "lr": 0.003, "grad": 0.1127, "tokens": 115168435200, "tok_s": 159277.9}
|
| 96 |
+
{"step": 109880, "epoch": 0.698, "loss": 1.76985, "ppl": 5.87, "lr": 0.003, "grad": 0.0778, "tokens": 115189401600, "tok_s": 158912.3}
|
| 97 |
+
{"step": 109900, "epoch": 0.698, "loss": 1.75561, "ppl": 5.787, "lr": 0.003, "grad": 0.0748, "tokens": 115210368000, "tok_s": 159123.7}
|
| 98 |
+
{"step": 109920, "epoch": 0.698, "loss": 1.77873, "ppl": 5.922, "lr": 0.003, "grad": 0.0943, "tokens": 115231334400, "tok_s": 159401.3}
|
| 99 |
+
{"step": 109940, "epoch": 0.699, "loss": 1.72977, "ppl": 5.639, "lr": 0.003, "grad": 0.0723, "tokens": 115252300800, "tok_s": 159292.3}
|
| 100 |
+
{"step": 109960, "epoch": 0.699, "loss": 1.75106, "ppl": 5.761, "lr": 0.003, "grad": 0.0762, "tokens": 115273267200, "tok_s": 159346.4}
|
| 101 |
+
{"step": 109980, "epoch": 0.699, "loss": 1.79941, "ppl": 6.046, "lr": 0.003, "grad": 0.1027, "tokens": 115294233600, "tok_s": 159496.4}
|
| 102 |
+
{"step": 110000, "epoch": 0.699, "loss": 1.72724, "ppl": 5.625, "lr": 0.003, "grad": 0.0953, "tokens": 115315200000, "tok_s": 159029.0}
|
| 103 |
+
{"step": 110000, "val_loss": 1.74385, "val_ppl": 5.719, "is_best": false}
|
| 104 |
+
{"step": 110020, "epoch": 0.699, "loss": 1.76178, "ppl": 5.823, "lr": 0.003, "grad": 0.1406, "tokens": 115336166400, "tok_s": 159314.7}
|
| 105 |
+
{"step": 110040, "epoch": 0.699, "loss": 1.75121, "ppl": 5.762, "lr": 0.003, "grad": 0.0795, "tokens": 115357132800, "tok_s": 159269.8}
|
| 106 |
+
{"step": 110060, "epoch": 0.699, "loss": 1.69675, "ppl": 5.456, "lr": 0.003, "grad": 0.0868, "tokens": 115378099200, "tok_s": 159030.7}
|
| 107 |
+
{"step": 110080, "epoch": 0.699, "loss": 1.76612, "ppl": 5.848, "lr": 0.003, "grad": 0.0979, "tokens": 115399065600, "tok_s": 159206.6}
|
| 108 |
+
{"step": 110100, "epoch": 0.7, "loss": 1.75739, "ppl": 5.797, "lr": 0.003, "grad": 0.088, "tokens": 115420032000, "tok_s": 159121.2}
|
| 109 |
+
{"step": 110120, "epoch": 0.7, "loss": 1.83068, "ppl": 6.238, "lr": 0.003, "grad": 0.1548, "tokens": 115440998400, "tok_s": 159261.6}
|
| 110 |
+
{"step": 110140, "epoch": 0.7, "loss": 1.77349, "ppl": 5.891, "lr": 0.003, "grad": 0.1482, "tokens": 115461964800, "tok_s": 159150.4}
|
| 111 |
+
{"step": 110160, "epoch": 0.7, "loss": 1.72478, "ppl": 5.611, "lr": 0.003, "grad": 0.0787, "tokens": 115482931200, "tok_s": 158986.2}
|
| 112 |
+
{"step": 110180, "epoch": 0.7, "loss": 1.75132, "ppl": 5.762, "lr": 0.003, "grad": 0.1179, "tokens": 115503897600, "tok_s": 159166.4}
|
| 113 |
+
{"step": 110200, "epoch": 0.7, "loss": 1.80498, "ppl": 6.08, "lr": 0.003, "grad": 0.0891, "tokens": 115524864000, "tok_s": 159210.4}
|
| 114 |
+
{"step": 110220, "epoch": 0.7, "loss": 1.70461, "ppl": 5.499, "lr": 0.003, "grad": 0.086, "tokens": 115545830400, "tok_s": 158635.4}
|
| 115 |
+
{"step": 110240, "epoch": 0.7, "loss": 1.74953, "ppl": 5.752, "lr": 0.003, "grad": 0.0893, "tokens": 115566796800, "tok_s": 158553.4}
|
| 116 |
+
{"step": 110260, "epoch": 0.701, "loss": 1.66313, "ppl": 5.276, "lr": 0.003, "grad": 0.0676, "tokens": 115587763200, "tok_s": 159319.4}
|
| 117 |
+
{"step": 110280, "epoch": 0.701, "loss": 1.76244, "ppl": 5.827, "lr": 0.003, "grad": 0.1082, "tokens": 115608729600, "tok_s": 158709.8}
|
| 118 |
+
{"step": 110300, "epoch": 0.701, "loss": 1.78618, "ppl": 5.967, "lr": 0.003, "grad": 0.0738, "tokens": 115629696000, "tok_s": 159270.7}
|
| 119 |
+
{"step": 110320, "epoch": 0.701, "loss": 1.66907, "ppl": 5.307, "lr": 0.003, "grad": 0.1015, "tokens": 115650662400, "tok_s": 158840.8}
|
| 120 |
+
{"step": 110340, "epoch": 0.701, "loss": 1.63189, "ppl": 5.114, "lr": 0.003, "grad": 0.1245, "tokens": 115671628800, "tok_s": 159193.9}
|
| 121 |
+
{"step": 110360, "epoch": 0.701, "loss": 1.75918, "ppl": 5.808, "lr": 0.003, "grad": 0.0886, "tokens": 115692595200, "tok_s": 159022.3}
|
| 122 |
+
{"step": 110380, "epoch": 0.701, "loss": 1.73369, "ppl": 5.661, "lr": 0.003, "grad": 0.1006, "tokens": 115713561600, "tok_s": 159316.0}
|
| 123 |
+
{"step": 110400, "epoch": 0.701, "loss": 1.64915, "ppl": 5.203, "lr": 0.003, "grad": 0.0742, "tokens": 115734528000, "tok_s": 159118.4}
|
| 124 |
+
{"step": 110420, "epoch": 0.702, "loss": 1.66734, "ppl": 5.298, "lr": 0.003, "grad": 0.0914, "tokens": 115755494400, "tok_s": 158787.8}
|
| 125 |
+
{"step": 110440, "epoch": 0.702, "loss": 1.85501, "ppl": 6.392, "lr": 0.003, "grad": 0.1211, "tokens": 115776460800, "tok_s": 158711.9}
|
| 126 |
+
{"step": 110460, "epoch": 0.702, "loss": 1.64944, "ppl": 5.204, "lr": 0.003, "grad": 0.1314, "tokens": 115797427200, "tok_s": 159306.0}
|
| 127 |
+
{"step": 110480, "epoch": 0.702, "loss": 1.72494, "ppl": 5.612, "lr": 0.003, "grad": 0.0604, "tokens": 115818393600, "tok_s": 159041.1}
|
| 128 |
+
{"step": 110500, "epoch": 0.702, "loss": 1.7002, "ppl": 5.475, "lr": 0.003, "grad": 0.0801, "tokens": 115839360000, "tok_s": 158925.5}
|
| 129 |
+
{"step": 110520, "epoch": 0.702, "loss": 1.71367, "ppl": 5.549, "lr": 0.003, "grad": 0.0822, "tokens": 115860326400, "tok_s": 158937.2}
|
| 130 |
+
{"step": 110540, "epoch": 0.702, "loss": 1.71543, "ppl": 5.559, "lr": 0.003, "grad": 0.1216, "tokens": 115881292800, "tok_s": 159384.8}
|
| 131 |
+
{"step": 110560, "epoch": 0.702, "loss": 1.81401, "ppl": 6.135, "lr": 0.003, "grad": 0.1036, "tokens": 115902259200, "tok_s": 159293.5}
|
| 132 |
+
{"step": 110580, "epoch": 0.703, "loss": 1.74452, "ppl": 5.723, "lr": 0.003, "grad": 0.107, "tokens": 115923225600, "tok_s": 159081.0}
|
| 133 |
+
{"step": 110600, "epoch": 0.703, "loss": 1.77592, "ppl": 5.906, "lr": 0.003, "grad": 0.0614, "tokens": 115944192000, "tok_s": 158693.3}
|
| 134 |
+
{"step": 110620, "epoch": 0.703, "loss": 1.73993, "ppl": 5.697, "lr": 0.003, "grad": 0.1163, "tokens": 115965158400, "tok_s": 159237.2}
|
| 135 |
+
{"step": 110640, "epoch": 0.703, "loss": 1.77779, "ppl": 5.917, "lr": 0.003, "grad": 0.0967, "tokens": 115986124800, "tok_s": 159123.3}
|
| 136 |
+
{"step": 110660, "epoch": 0.703, "loss": 1.64579, "ppl": 5.185, "lr": 0.003, "grad": 0.0867, "tokens": 116007091200, "tok_s": 159020.9}
|
| 137 |
+
{"step": 110680, "epoch": 0.703, "loss": 1.74047, "ppl": 5.7, "lr": 0.003, "grad": 0.1103, "tokens": 116028057600, "tok_s": 159155.7}
|
| 138 |
+
{"step": 110700, "epoch": 0.703, "loss": 1.69972, "ppl": 5.472, "lr": 0.003, "grad": 0.1113, "tokens": 116049024000, "tok_s": 159158.5}
|
| 139 |
+
{"step": 110720, "epoch": 0.703, "loss": 1.78604, "ppl": 5.966, "lr": 0.003, "grad": 0.0857, "tokens": 116069990400, "tok_s": 159214.9}
|
| 140 |
+
{"step": 110740, "epoch": 0.704, "loss": 1.60962, "ppl": 5.001, "lr": 0.003, "grad": 0.0856, "tokens": 116090956800, "tok_s": 159302.0}
|
| 141 |
+
{"step": 110760, "epoch": 0.704, "loss": 1.778, "ppl": 5.918, "lr": 0.003, "grad": 0.0979, "tokens": 116111923200, "tok_s": 158702.2}
|
| 142 |
+
{"step": 110780, "epoch": 0.704, "loss": 1.78549, "ppl": 5.962, "lr": 0.003, "grad": 0.1108, "tokens": 116132889600, "tok_s": 158791.8}
|
| 143 |
+
{"step": 110800, "epoch": 0.704, "loss": 1.75949, "ppl": 5.81, "lr": 0.003, "grad": 0.1462, "tokens": 116153856000, "tok_s": 159378.8}
|
| 144 |
+
{"step": 110820, "epoch": 0.704, "loss": 1.77886, "ppl": 5.923, "lr": 0.003, "grad": 0.1145, "tokens": 116174822400, "tok_s": 159320.7}
|
| 145 |
+
{"step": 110840, "epoch": 0.704, "loss": 1.77943, "ppl": 5.926, "lr": 0.003, "grad": 0.0896, "tokens": 116195788800, "tok_s": 158933.4}
|
| 146 |
+
{"step": 110860, "epoch": 0.704, "loss": 1.80276, "ppl": 6.066, "lr": 0.003, "grad": 0.1157, "tokens": 116216755200, "tok_s": 159196.3}
|
| 147 |
+
{"step": 110880, "epoch": 0.704, "loss": 1.71631, "ppl": 5.564, "lr": 0.003, "grad": 0.0982, "tokens": 116237721600, "tok_s": 159403.0}
|
| 148 |
+
{"step": 110900, "epoch": 0.705, "loss": 1.77119, "ppl": 5.878, "lr": 0.003, "grad": 0.068, "tokens": 116258688000, "tok_s": 159247.9}
|
| 149 |
+
{"step": 110920, "epoch": 0.705, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.0752, "tokens": 116279654400, "tok_s": 159255.1}
|
| 150 |
+
{"step": 110940, "epoch": 0.705, "loss": 1.7345, "ppl": 5.666, "lr": 0.003, "grad": 0.0871, "tokens": 116300620800, "tok_s": 159291.1}
|
| 151 |
+
{"step": 110960, "epoch": 0.705, "loss": 1.78909, "ppl": 5.984, "lr": 0.003, "grad": 0.0908, "tokens": 116321587200, "tok_s": 159059.9}
|
| 152 |
+
{"step": 110980, "epoch": 0.705, "loss": 1.76201, "ppl": 5.824, "lr": 0.003, "grad": 0.112, "tokens": 116342553600, "tok_s": 159287.3}
|
| 153 |
+
{"step": 111000, "epoch": 0.705, "loss": 1.7672, "ppl": 5.854, "lr": 0.003, "grad": 0.1463, "tokens": 116363520000, "tok_s": 159431.0}
|
| 154 |
+
{"step": 111000, "val_loss": 1.75042, "val_ppl": 5.757, "is_best": false}
|
| 155 |
+
{"step": 111020, "epoch": 0.705, "loss": 1.6984, "ppl": 5.465, "lr": 0.003, "grad": 0.0808, "tokens": 116384486400, "tok_s": 159150.2}
|
| 156 |
+
{"step": 111040, "epoch": 0.706, "loss": 1.75526, "ppl": 5.785, "lr": 0.003, "grad": 0.1077, "tokens": 116405452800, "tok_s": 159510.0}
|
| 157 |
+
{"step": 111060, "epoch": 0.706, "loss": 1.73815, "ppl": 5.687, "lr": 0.003, "grad": 0.0859, "tokens": 116426419200, "tok_s": 159332.7}
|
| 158 |
+
{"step": 111080, "epoch": 0.706, "loss": 1.77852, "ppl": 5.921, "lr": 0.003, "grad": 0.1268, "tokens": 116447385600, "tok_s": 159280.4}
|
| 159 |
+
{"step": 111100, "epoch": 0.706, "loss": 1.77494, "ppl": 5.9, "lr": 0.003, "grad": 0.0968, "tokens": 116468352000, "tok_s": 159332.5}
|
| 160 |
+
{"step": 111120, "epoch": 0.706, "loss": 1.74149, "ppl": 5.706, "lr": 0.003, "grad": 0.0827, "tokens": 116489318400, "tok_s": 159423.8}
|
| 161 |
+
{"step": 111140, "epoch": 0.706, "loss": 1.7278, "ppl": 5.628, "lr": 0.003, "grad": 0.1111, "tokens": 116510284800, "tok_s": 159236.6}
|
| 162 |
+
{"step": 111160, "epoch": 0.706, "loss": 1.73755, "ppl": 5.683, "lr": 0.003, "grad": 0.0862, "tokens": 116531251200, "tok_s": 159278.8}
|
| 163 |
+
{"step": 111180, "epoch": 0.706, "loss": 1.68257, "ppl": 5.379, "lr": 0.003, "grad": 0.0906, "tokens": 116552217600, "tok_s": 159097.9}
|
| 164 |
+
{"step": 111200, "epoch": 0.707, "loss": 1.74487, "ppl": 5.725, "lr": 0.003, "grad": 0.0906, "tokens": 116573184000, "tok_s": 158626.9}
|
| 165 |
+
{"step": 111220, "epoch": 0.707, "loss": 1.73152, "ppl": 5.649, "lr": 0.003, "grad": 0.1026, "tokens": 116594150400, "tok_s": 159504.5}
|
| 166 |
+
{"step": 111240, "epoch": 0.707, "loss": 1.73508, "ppl": 5.669, "lr": 0.003, "grad": 0.1041, "tokens": 116615116800, "tok_s": 159046.5}
|
| 167 |
+
{"step": 111260, "epoch": 0.707, "loss": 1.74921, "ppl": 5.75, "lr": 0.003, "grad": 0.1332, "tokens": 116636083200, "tok_s": 159197.6}
|
| 168 |
+
{"step": 111280, "epoch": 0.707, "loss": 1.77166, "ppl": 5.881, "lr": 0.003, "grad": 0.0846, "tokens": 116657049600, "tok_s": 159447.0}
|
| 169 |
+
{"step": 111300, "epoch": 0.707, "loss": 1.82379, "ppl": 6.195, "lr": 0.003, "grad": 0.082, "tokens": 116678016000, "tok_s": 159138.3}
|
| 170 |
+
{"step": 111320, "epoch": 0.707, "loss": 1.72487, "ppl": 5.612, "lr": 0.003, "grad": 0.1011, "tokens": 116698982400, "tok_s": 159408.6}
|
| 171 |
+
{"step": 111340, "epoch": 0.707, "loss": 1.75384, "ppl": 5.777, "lr": 0.003, "grad": 0.1379, "tokens": 116719948800, "tok_s": 159188.7}
|
| 172 |
+
{"step": 111360, "epoch": 0.708, "loss": 1.74064, "ppl": 5.701, "lr": 0.003, "grad": 0.1071, "tokens": 116740915200, "tok_s": 159434.4}
|
| 173 |
+
{"step": 111380, "epoch": 0.708, "loss": 1.69438, "ppl": 5.443, "lr": 0.003, "grad": 0.1395, "tokens": 116761881600, "tok_s": 159358.7}
|
| 174 |
+
{"step": 111400, "epoch": 0.708, "loss": 1.71567, "ppl": 5.56, "lr": 0.003, "grad": 0.1088, "tokens": 116782848000, "tok_s": 159073.0}
|
| 175 |
+
{"step": 111420, "epoch": 0.708, "loss": 1.74194, "ppl": 5.708, "lr": 0.003, "grad": 0.111, "tokens": 116803814400, "tok_s": 158820.6}
|
| 176 |
+
{"step": 111440, "epoch": 0.708, "loss": 1.72756, "ppl": 5.627, "lr": 0.003, "grad": 0.0669, "tokens": 116824780800, "tok_s": 159415.1}
|
| 177 |
+
{"step": 111460, "epoch": 0.708, "loss": 1.73954, "ppl": 5.695, "lr": 0.003, "grad": 0.0708, "tokens": 116845747200, "tok_s": 159146.3}
|
| 178 |
+
{"step": 111480, "epoch": 0.708, "loss": 1.65413, "ppl": 5.229, "lr": 0.003, "grad": 0.101, "tokens": 116866713600, "tok_s": 159367.7}
|
| 179 |
+
{"step": 111500, "epoch": 0.708, "loss": 1.86436, "ppl": 6.452, "lr": 0.003, "grad": 0.1122, "tokens": 116887680000, "tok_s": 159323.4}
|
| 180 |
+
{"step": 111520, "epoch": 0.709, "loss": 1.79098, "ppl": 5.995, "lr": 0.003, "grad": 0.0922, "tokens": 116908646400, "tok_s": 159110.5}
|
| 181 |
+
{"step": 111540, "epoch": 0.709, "loss": 1.69771, "ppl": 5.461, "lr": 0.003, "grad": 0.0836, "tokens": 116929612800, "tok_s": 158748.0}
|
| 182 |
+
{"step": 111560, "epoch": 0.709, "loss": 1.85084, "ppl": 6.365, "lr": 0.003, "grad": 0.1336, "tokens": 116950579200, "tok_s": 158769.3}
|
| 183 |
+
{"step": 111580, "epoch": 0.709, "loss": 1.7332, "ppl": 5.659, "lr": 0.003, "grad": 0.0547, "tokens": 116971545600, "tok_s": 158949.8}
|
| 184 |
+
{"step": 111600, "epoch": 0.709, "loss": 1.82211, "ppl": 6.185, "lr": 0.003, "grad": 0.0935, "tokens": 116992512000, "tok_s": 159577.8}
|
| 185 |
+
{"step": 111620, "epoch": 0.709, "loss": 1.73952, "ppl": 5.695, "lr": 0.003, "grad": 0.1019, "tokens": 117013478400, "tok_s": 159257.3}
|
| 186 |
+
{"step": 111640, "epoch": 0.709, "loss": 1.75399, "ppl": 5.778, "lr": 0.003, "grad": 0.0972, "tokens": 117034444800, "tok_s": 159517.7}
|
| 187 |
+
{"step": 111660, "epoch": 0.709, "loss": 1.63774, "ppl": 5.144, "lr": 0.003, "grad": 0.0868, "tokens": 117055411200, "tok_s": 159206.2}
|
| 188 |
+
{"step": 111680, "epoch": 0.71, "loss": 1.46853, "ppl": 4.343, "lr": 0.003, "grad": 0.0776, "tokens": 117076377600, "tok_s": 159410.0}
|
| 189 |
+
{"step": 111700, "epoch": 0.71, "loss": 1.80166, "ppl": 6.06, "lr": 0.003, "grad": 0.0876, "tokens": 117097344000, "tok_s": 159578.9}
|
| 190 |
+
{"step": 111720, "epoch": 0.71, "loss": 1.70327, "ppl": 5.492, "lr": 0.003, "grad": 0.0738, "tokens": 117118310400, "tok_s": 159501.8}
|
| 191 |
+
{"step": 111740, "epoch": 0.71, "loss": 1.71684, "ppl": 5.567, "lr": 0.003, "grad": 0.0744, "tokens": 117139276800, "tok_s": 159516.4}
|
| 192 |
+
{"step": 111760, "epoch": 0.71, "loss": 1.74614, "ppl": 5.732, "lr": 0.003, "grad": 0.1049, "tokens": 117160243200, "tok_s": 159549.5}
|
| 193 |
+
{"step": 111780, "epoch": 0.71, "loss": 1.71022, "ppl": 5.53, "lr": 0.003, "grad": 0.1, "tokens": 117181209600, "tok_s": 159434.6}
|
| 194 |
+
{"step": 111800, "epoch": 0.71, "loss": 1.76808, "ppl": 5.86, "lr": 0.003, "grad": 0.099, "tokens": 117202176000, "tok_s": 159530.7}
|
| 195 |
+
{"step": 111820, "epoch": 0.71, "loss": 1.75091, "ppl": 5.76, "lr": 0.003, "grad": 0.1336, "tokens": 117223142400, "tok_s": 159321.7}
|
| 196 |
+
{"step": 111840, "epoch": 0.711, "loss": 1.76696, "ppl": 5.853, "lr": 0.003, "grad": 0.0972, "tokens": 117244108800, "tok_s": 159480.5}
|
| 197 |
+
{"step": 111860, "epoch": 0.711, "loss": 1.74118, "ppl": 5.704, "lr": 0.003, "grad": 0.1202, "tokens": 117265075200, "tok_s": 159413.2}
|
| 198 |
+
{"step": 111880, "epoch": 0.711, "loss": 1.74494, "ppl": 5.726, "lr": 0.003, "grad": 0.0821, "tokens": 117286041600, "tok_s": 158970.8}
|
| 199 |
+
{"step": 111900, "epoch": 0.711, "loss": 1.73236, "ppl": 5.654, "lr": 0.003, "grad": 0.1208, "tokens": 117307008000, "tok_s": 159447.2}
|
| 200 |
+
{"step": 111920, "epoch": 0.711, "loss": 1.73324, "ppl": 5.659, "lr": 0.003, "grad": 0.096, "tokens": 117327974400, "tok_s": 159294.4}
|
| 201 |
+
{"step": 111940, "epoch": 0.711, "loss": 1.74069, "ppl": 5.701, "lr": 0.003, "grad": 0.1187, "tokens": 117348940800, "tok_s": 159487.3}
|
| 202 |
+
{"step": 111960, "epoch": 0.711, "loss": 1.77119, "ppl": 5.878, "lr": 0.003, "grad": 0.077, "tokens": 117369907200, "tok_s": 159454.8}
|
| 203 |
+
{"step": 111980, "epoch": 0.711, "loss": 1.73885, "ppl": 5.691, "lr": 0.003, "grad": 0.1331, "tokens": 117390873600, "tok_s": 159374.5}
|
| 204 |
+
{"step": 112000, "epoch": 0.712, "loss": 1.76929, "ppl": 5.867, "lr": 0.003, "grad": 0.0924, "tokens": 117411840000, "tok_s": 159310.0}
|
| 205 |
+
{"step": 112000, "val_loss": 1.75172, "val_ppl": 5.765, "is_best": false}
|
logs/log_113000.jsonl
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 108000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-04T17:47:03.162778"}
|
| 2 |
+
{"step": 108020, "epoch": 0.686, "loss": 1.74155, "ppl": 5.706, "lr": 0.003, "grad": 0.1535, "tokens": 113239526400, "tok_s": 159409.6}
|
| 3 |
+
{"step": 108040, "epoch": 0.686, "loss": 1.74208, "ppl": 5.709, "lr": 0.003, "grad": 0.1116, "tokens": 113260492800, "tok_s": 158966.0}
|
| 4 |
+
{"step": 108060, "epoch": 0.687, "loss": 1.71701, "ppl": 5.568, "lr": 0.003, "grad": 0.119, "tokens": 113281459200, "tok_s": 158764.9}
|
| 5 |
+
{"step": 108080, "epoch": 0.687, "loss": 1.61379, "ppl": 5.022, "lr": 0.003, "grad": 0.1259, "tokens": 113302425600, "tok_s": 159374.6}
|
| 6 |
+
{"step": 108100, "epoch": 0.687, "loss": 1.76912, "ppl": 5.866, "lr": 0.003, "grad": 0.1513, "tokens": 113323392000, "tok_s": 159426.1}
|
| 7 |
+
{"step": 108120, "epoch": 0.687, "loss": 1.73133, "ppl": 5.648, "lr": 0.003, "grad": 0.1181, "tokens": 113344358400, "tok_s": 159368.3}
|
| 8 |
+
{"step": 108140, "epoch": 0.687, "loss": 1.74469, "ppl": 5.724, "lr": 0.003, "grad": 0.081, "tokens": 113365324800, "tok_s": 159141.7}
|
| 9 |
+
{"step": 108160, "epoch": 0.687, "loss": 1.67668, "ppl": 5.348, "lr": 0.003, "grad": 0.097, "tokens": 113386291200, "tok_s": 159307.4}
|
| 10 |
+
{"step": 108180, "epoch": 0.687, "loss": 1.6295, "ppl": 5.101, "lr": 0.003, "grad": 0.074, "tokens": 113407257600, "tok_s": 158959.6}
|
| 11 |
+
{"step": 108200, "epoch": 0.687, "loss": 1.59394, "ppl": 4.923, "lr": 0.003, "grad": 0.1446, "tokens": 113428224000, "tok_s": 159053.4}
|
| 12 |
+
{"step": 108220, "epoch": 0.688, "loss": 1.78001, "ppl": 5.93, "lr": 0.003, "grad": 0.0736, "tokens": 113449190400, "tok_s": 159320.4}
|
| 13 |
+
{"step": 108240, "epoch": 0.688, "loss": 1.70317, "ppl": 5.491, "lr": 0.003, "grad": 0.1291, "tokens": 113470156800, "tok_s": 159284.0}
|
| 14 |
+
{"step": 108260, "epoch": 0.688, "loss": 1.76076, "ppl": 5.817, "lr": 0.003, "grad": 0.0607, "tokens": 113491123200, "tok_s": 159430.1}
|
| 15 |
+
{"step": 108280, "epoch": 0.688, "loss": 1.71242, "ppl": 5.542, "lr": 0.003, "grad": 0.0832, "tokens": 113512089600, "tok_s": 159396.6}
|
| 16 |
+
{"step": 108300, "epoch": 0.688, "loss": 1.75654, "ppl": 5.792, "lr": 0.003, "grad": 0.0942, "tokens": 113533056000, "tok_s": 159177.0}
|
| 17 |
+
{"step": 108320, "epoch": 0.688, "loss": 1.76145, "ppl": 5.821, "lr": 0.003, "grad": 0.0929, "tokens": 113554022400, "tok_s": 159418.2}
|
| 18 |
+
{"step": 108340, "epoch": 0.688, "loss": 1.72596, "ppl": 5.618, "lr": 0.003, "grad": 0.1128, "tokens": 113574988800, "tok_s": 159462.3}
|
| 19 |
+
{"step": 108360, "epoch": 0.688, "loss": 1.77282, "ppl": 5.887, "lr": 0.003, "grad": 0.0726, "tokens": 113595955200, "tok_s": 159439.0}
|
| 20 |
+
{"step": 108380, "epoch": 0.689, "loss": 1.68249, "ppl": 5.379, "lr": 0.003, "grad": 0.0773, "tokens": 113616921600, "tok_s": 158841.1}
|
| 21 |
+
{"step": 108400, "epoch": 0.689, "loss": 1.78284, "ppl": 5.947, "lr": 0.003, "grad": 0.1421, "tokens": 113637888000, "tok_s": 159390.6}
|
| 22 |
+
{"step": 108420, "epoch": 0.689, "loss": 1.76143, "ppl": 5.821, "lr": 0.003, "grad": 0.1094, "tokens": 113658854400, "tok_s": 159248.9}
|
| 23 |
+
{"step": 108440, "epoch": 0.689, "loss": 1.6718, "ppl": 5.322, "lr": 0.003, "grad": 0.0636, "tokens": 113679820800, "tok_s": 159083.0}
|
| 24 |
+
{"step": 108460, "epoch": 0.689, "loss": 1.81265, "ppl": 6.127, "lr": 0.003, "grad": 0.106, "tokens": 113700787200, "tok_s": 159288.0}
|
| 25 |
+
{"step": 108480, "epoch": 0.689, "loss": 1.80861, "ppl": 6.102, "lr": 0.003, "grad": 0.1554, "tokens": 113721753600, "tok_s": 159226.0}
|
| 26 |
+
{"step": 108500, "epoch": 0.689, "loss": 1.89807, "ppl": 6.673, "lr": 0.003, "grad": 0.119, "tokens": 113742720000, "tok_s": 158977.2}
|
| 27 |
+
{"step": 108520, "epoch": 0.689, "loss": 1.76412, "ppl": 5.836, "lr": 0.003, "grad": 0.0783, "tokens": 113763686400, "tok_s": 158959.6}
|
| 28 |
+
{"step": 108540, "epoch": 0.69, "loss": 1.65952, "ppl": 5.257, "lr": 0.003, "grad": 0.0907, "tokens": 113784652800, "tok_s": 159425.9}
|
| 29 |
+
{"step": 108560, "epoch": 0.69, "loss": 1.67979, "ppl": 5.364, "lr": 0.003, "grad": 0.1137, "tokens": 113805619200, "tok_s": 159124.8}
|
| 30 |
+
{"step": 108580, "epoch": 0.69, "loss": 1.70389, "ppl": 5.495, "lr": 0.003, "grad": 0.1058, "tokens": 113826585600, "tok_s": 159404.3}
|
| 31 |
+
{"step": 108600, "epoch": 0.69, "loss": 1.6402, "ppl": 5.156, "lr": 0.003, "grad": 0.0885, "tokens": 113847552000, "tok_s": 159333.4}
|
| 32 |
+
{"step": 108620, "epoch": 0.69, "loss": 1.71514, "ppl": 5.557, "lr": 0.003, "grad": 0.1022, "tokens": 113868518400, "tok_s": 159159.8}
|
| 33 |
+
{"step": 108640, "epoch": 0.69, "loss": 1.66351, "ppl": 5.278, "lr": 0.003, "grad": 0.1001, "tokens": 113889484800, "tok_s": 159061.3}
|
| 34 |
+
{"step": 108660, "epoch": 0.69, "loss": 1.84406, "ppl": 6.322, "lr": 0.003, "grad": 0.0975, "tokens": 113910451200, "tok_s": 159051.8}
|
| 35 |
+
{"step": 108680, "epoch": 0.691, "loss": 1.77184, "ppl": 5.882, "lr": 0.003, "grad": 0.1471, "tokens": 113931417600, "tok_s": 159358.4}
|
| 36 |
+
{"step": 108700, "epoch": 0.691, "loss": 1.74199, "ppl": 5.709, "lr": 0.003, "grad": 0.116, "tokens": 113952384000, "tok_s": 158750.2}
|
| 37 |
+
{"step": 108720, "epoch": 0.691, "loss": 1.66658, "ppl": 5.294, "lr": 0.003, "grad": 0.108, "tokens": 113973350400, "tok_s": 158885.5}
|
| 38 |
+
{"step": 108740, "epoch": 0.691, "loss": 1.69864, "ppl": 5.466, "lr": 0.003, "grad": 0.0686, "tokens": 113994316800, "tok_s": 159047.9}
|
| 39 |
+
{"step": 108760, "epoch": 0.691, "loss": 1.76744, "ppl": 5.856, "lr": 0.003, "grad": 0.0725, "tokens": 114015283200, "tok_s": 158612.8}
|
| 40 |
+
{"step": 108780, "epoch": 0.691, "loss": 1.67806, "ppl": 5.355, "lr": 0.003, "grad": 0.1065, "tokens": 114036249600, "tok_s": 159074.5}
|
| 41 |
+
{"step": 108800, "epoch": 0.691, "loss": 1.69361, "ppl": 5.439, "lr": 0.003, "grad": 0.1198, "tokens": 114057216000, "tok_s": 158311.1}
|
| 42 |
+
{"step": 108820, "epoch": 0.691, "loss": 1.74227, "ppl": 5.71, "lr": 0.003, "grad": 0.1113, "tokens": 114078182400, "tok_s": 158962.4}
|
| 43 |
+
{"step": 108840, "epoch": 0.692, "loss": 1.67661, "ppl": 5.347, "lr": 0.003, "grad": 0.0726, "tokens": 114099148800, "tok_s": 159127.3}
|
| 44 |
+
{"step": 108860, "epoch": 0.692, "loss": 1.75207, "ppl": 5.767, "lr": 0.003, "grad": 0.0926, "tokens": 114120115200, "tok_s": 159114.9}
|
| 45 |
+
{"step": 108880, "epoch": 0.692, "loss": 1.78028, "ppl": 5.932, "lr": 0.003, "grad": 0.0944, "tokens": 114141081600, "tok_s": 159095.0}
|
| 46 |
+
{"step": 108900, "epoch": 0.692, "loss": 1.45231, "ppl": 4.273, "lr": 0.003, "grad": 0.0811, "tokens": 114162048000, "tok_s": 158766.7}
|
| 47 |
+
{"step": 108920, "epoch": 0.692, "loss": 1.67896, "ppl": 5.36, "lr": 0.003, "grad": 0.1297, "tokens": 114183014400, "tok_s": 158716.9}
|
| 48 |
+
{"step": 108940, "epoch": 0.692, "loss": 1.69114, "ppl": 5.426, "lr": 0.003, "grad": 0.0714, "tokens": 114203980800, "tok_s": 159226.3}
|
| 49 |
+
{"step": 108960, "epoch": 0.692, "loss": 1.78483, "ppl": 5.959, "lr": 0.003, "grad": 0.0848, "tokens": 114224947200, "tok_s": 159024.2}
|
| 50 |
+
{"step": 108980, "epoch": 0.692, "loss": 1.7362, "ppl": 5.676, "lr": 0.003, "grad": 0.0833, "tokens": 114245913600, "tok_s": 158551.6}
|
| 51 |
+
{"step": 109000, "epoch": 0.693, "loss": 1.89243, "ppl": 6.635, "lr": 0.003, "grad": 0.1041, "tokens": 114266880000, "tok_s": 159175.6}
|
| 52 |
+
{"step": 109000, "val_loss": 1.73288, "val_ppl": 5.657, "is_best": true}
|
| 53 |
+
{"step": 109020, "epoch": 0.693, "loss": 1.73623, "ppl": 5.676, "lr": 0.003, "grad": 0.1133, "tokens": 114287846400, "tok_s": 158562.8}
|
| 54 |
+
{"step": 109040, "epoch": 0.693, "loss": 1.67899, "ppl": 5.36, "lr": 0.003, "grad": 0.122, "tokens": 114308812800, "tok_s": 158957.5}
|
| 55 |
+
{"step": 109060, "epoch": 0.693, "loss": 1.77498, "ppl": 5.9, "lr": 0.003, "grad": 0.1183, "tokens": 114329779200, "tok_s": 158635.2}
|
| 56 |
+
{"step": 109080, "epoch": 0.693, "loss": 1.72682, "ppl": 5.623, "lr": 0.003, "grad": 0.133, "tokens": 114350745600, "tok_s": 159053.0}
|
| 57 |
+
{"step": 109100, "epoch": 0.693, "loss": 1.59864, "ppl": 4.946, "lr": 0.003, "grad": 0.0731, "tokens": 114371712000, "tok_s": 158945.6}
|
| 58 |
+
{"step": 109120, "epoch": 0.693, "loss": 1.87152, "ppl": 6.498, "lr": 0.003, "grad": 0.1226, "tokens": 114392678400, "tok_s": 158979.5}
|
| 59 |
+
{"step": 109140, "epoch": 0.693, "loss": 1.7656, "ppl": 5.845, "lr": 0.003, "grad": 0.0712, "tokens": 114413644800, "tok_s": 158856.8}
|
| 60 |
+
{"step": 109160, "epoch": 0.694, "loss": 1.75175, "ppl": 5.765, "lr": 0.003, "grad": 0.1197, "tokens": 114434611200, "tok_s": 158864.0}
|
| 61 |
+
{"step": 109180, "epoch": 0.694, "loss": 1.79459, "ppl": 6.017, "lr": 0.003, "grad": 0.075, "tokens": 114455577600, "tok_s": 159128.8}
|
| 62 |
+
{"step": 109200, "epoch": 0.694, "loss": 1.70936, "ppl": 5.525, "lr": 0.003, "grad": 0.1687, "tokens": 114476544000, "tok_s": 158856.4}
|
| 63 |
+
{"step": 109220, "epoch": 0.694, "loss": 1.7816, "ppl": 5.939, "lr": 0.003, "grad": 0.0802, "tokens": 114497510400, "tok_s": 159429.2}
|
| 64 |
+
{"step": 109240, "epoch": 0.694, "loss": 1.69158, "ppl": 5.428, "lr": 0.003, "grad": 0.0868, "tokens": 114518476800, "tok_s": 159396.3}
|
| 65 |
+
{"step": 109260, "epoch": 0.694, "loss": 1.72195, "ppl": 5.595, "lr": 0.003, "grad": 0.0799, "tokens": 114539443200, "tok_s": 159192.0}
|
| 66 |
+
{"step": 109280, "epoch": 0.694, "loss": 1.60469, "ppl": 4.976, "lr": 0.003, "grad": 0.0877, "tokens": 114560409600, "tok_s": 159283.2}
|
| 67 |
+
{"step": 109300, "epoch": 0.694, "loss": 1.80401, "ppl": 6.074, "lr": 0.003, "grad": 0.0842, "tokens": 114581376000, "tok_s": 159141.0}
|
| 68 |
+
{"step": 109320, "epoch": 0.695, "loss": 1.74401, "ppl": 5.72, "lr": 0.003, "grad": 0.1062, "tokens": 114602342400, "tok_s": 159064.5}
|
| 69 |
+
{"step": 109340, "epoch": 0.695, "loss": 1.79633, "ppl": 6.027, "lr": 0.003, "grad": 0.0906, "tokens": 114623308800, "tok_s": 159188.7}
|
| 70 |
+
{"step": 109360, "epoch": 0.695, "loss": 1.73522, "ppl": 5.67, "lr": 0.003, "grad": 0.1054, "tokens": 114644275200, "tok_s": 159236.6}
|
| 71 |
+
{"step": 109380, "epoch": 0.695, "loss": 1.84514, "ppl": 6.329, "lr": 0.003, "grad": 0.0836, "tokens": 114665241600, "tok_s": 159146.2}
|
| 72 |
+
{"step": 109400, "epoch": 0.695, "loss": 1.81221, "ppl": 6.124, "lr": 0.003, "grad": 0.0795, "tokens": 114686208000, "tok_s": 158973.0}
|
| 73 |
+
{"step": 109420, "epoch": 0.695, "loss": 1.79499, "ppl": 6.019, "lr": 0.003, "grad": 0.0952, "tokens": 114707174400, "tok_s": 159163.4}
|
| 74 |
+
{"step": 109440, "epoch": 0.695, "loss": 1.73455, "ppl": 5.666, "lr": 0.003, "grad": 0.1025, "tokens": 114728140800, "tok_s": 159163.7}
|
| 75 |
+
{"step": 109460, "epoch": 0.695, "loss": 1.77711, "ppl": 5.913, "lr": 0.003, "grad": 0.1145, "tokens": 114749107200, "tok_s": 159227.8}
|
| 76 |
+
{"step": 109480, "epoch": 0.696, "loss": 1.82109, "ppl": 6.179, "lr": 0.003, "grad": 0.108, "tokens": 114770073600, "tok_s": 158520.2}
|
| 77 |
+
{"step": 109500, "epoch": 0.696, "loss": 1.78091, "ppl": 5.935, "lr": 0.003, "grad": 0.1455, "tokens": 114791040000, "tok_s": 158970.7}
|
| 78 |
+
{"step": 109520, "epoch": 0.696, "loss": 1.78594, "ppl": 5.965, "lr": 0.003, "grad": 0.0965, "tokens": 114812006400, "tok_s": 158568.5}
|
| 79 |
+
{"step": 109540, "epoch": 0.696, "loss": 1.71081, "ppl": 5.533, "lr": 0.003, "grad": 0.1095, "tokens": 114832972800, "tok_s": 158794.9}
|
| 80 |
+
{"step": 109560, "epoch": 0.696, "loss": 1.79209, "ppl": 6.002, "lr": 0.003, "grad": 0.1064, "tokens": 114853939200, "tok_s": 158785.9}
|
| 81 |
+
{"step": 109580, "epoch": 0.696, "loss": 1.59386, "ppl": 4.923, "lr": 0.003, "grad": 0.0668, "tokens": 114874905600, "tok_s": 158493.7}
|
| 82 |
+
{"step": 109600, "epoch": 0.696, "loss": 1.76839, "ppl": 5.861, "lr": 0.003, "grad": 0.1049, "tokens": 114895872000, "tok_s": 158374.2}
|
| 83 |
+
{"step": 109620, "epoch": 0.696, "loss": 1.76656, "ppl": 5.851, "lr": 0.003, "grad": 0.0699, "tokens": 114916838400, "tok_s": 159085.4}
|
| 84 |
+
{"step": 109640, "epoch": 0.697, "loss": 1.73206, "ppl": 5.652, "lr": 0.003, "grad": 0.1239, "tokens": 114937804800, "tok_s": 158970.6}
|
| 85 |
+
{"step": 109660, "epoch": 0.697, "loss": 1.78539, "ppl": 5.962, "lr": 0.003, "grad": 0.1003, "tokens": 114958771200, "tok_s": 159237.3}
|
| 86 |
+
{"step": 109680, "epoch": 0.697, "loss": 1.75903, "ppl": 5.807, "lr": 0.003, "grad": 0.1701, "tokens": 114979737600, "tok_s": 159190.0}
|
| 87 |
+
{"step": 109700, "epoch": 0.697, "loss": 1.73013, "ppl": 5.641, "lr": 0.003, "grad": 0.0824, "tokens": 115000704000, "tok_s": 159145.2}
|
| 88 |
+
{"step": 109720, "epoch": 0.697, "loss": 1.70807, "ppl": 5.518, "lr": 0.003, "grad": 0.089, "tokens": 115021670400, "tok_s": 159392.1}
|
| 89 |
+
{"step": 109740, "epoch": 0.697, "loss": 1.7454, "ppl": 5.728, "lr": 0.003, "grad": 0.0596, "tokens": 115042636800, "tok_s": 158812.2}
|
| 90 |
+
{"step": 109760, "epoch": 0.697, "loss": 1.63906, "ppl": 5.15, "lr": 0.003, "grad": 0.0936, "tokens": 115063603200, "tok_s": 158822.8}
|
| 91 |
+
{"step": 109780, "epoch": 0.698, "loss": 1.71756, "ppl": 5.571, "lr": 0.003, "grad": 0.1026, "tokens": 115084569600, "tok_s": 159321.3}
|
| 92 |
+
{"step": 109800, "epoch": 0.698, "loss": 1.74078, "ppl": 5.702, "lr": 0.003, "grad": 0.1413, "tokens": 115105536000, "tok_s": 158977.1}
|
| 93 |
+
{"step": 109820, "epoch": 0.698, "loss": 1.76512, "ppl": 5.842, "lr": 0.003, "grad": 0.0856, "tokens": 115126502400, "tok_s": 159024.3}
|
| 94 |
+
{"step": 109840, "epoch": 0.698, "loss": 1.77975, "ppl": 5.928, "lr": 0.003, "grad": 0.0778, "tokens": 115147468800, "tok_s": 158361.9}
|
| 95 |
+
{"step": 109860, "epoch": 0.698, "loss": 1.79078, "ppl": 5.994, "lr": 0.003, "grad": 0.1127, "tokens": 115168435200, "tok_s": 159277.9}
|
| 96 |
+
{"step": 109880, "epoch": 0.698, "loss": 1.76985, "ppl": 5.87, "lr": 0.003, "grad": 0.0778, "tokens": 115189401600, "tok_s": 158912.3}
|
| 97 |
+
{"step": 109900, "epoch": 0.698, "loss": 1.75561, "ppl": 5.787, "lr": 0.003, "grad": 0.0748, "tokens": 115210368000, "tok_s": 159123.7}
|
| 98 |
+
{"step": 109920, "epoch": 0.698, "loss": 1.77873, "ppl": 5.922, "lr": 0.003, "grad": 0.0943, "tokens": 115231334400, "tok_s": 159401.3}
|
| 99 |
+
{"step": 109940, "epoch": 0.699, "loss": 1.72977, "ppl": 5.639, "lr": 0.003, "grad": 0.0723, "tokens": 115252300800, "tok_s": 159292.3}
|
| 100 |
+
{"step": 109960, "epoch": 0.699, "loss": 1.75106, "ppl": 5.761, "lr": 0.003, "grad": 0.0762, "tokens": 115273267200, "tok_s": 159346.4}
|
| 101 |
+
{"step": 109980, "epoch": 0.699, "loss": 1.79941, "ppl": 6.046, "lr": 0.003, "grad": 0.1027, "tokens": 115294233600, "tok_s": 159496.4}
|
| 102 |
+
{"step": 110000, "epoch": 0.699, "loss": 1.72724, "ppl": 5.625, "lr": 0.003, "grad": 0.0953, "tokens": 115315200000, "tok_s": 159029.0}
|
| 103 |
+
{"step": 110000, "val_loss": 1.74385, "val_ppl": 5.719, "is_best": false}
|
| 104 |
+
{"step": 110020, "epoch": 0.699, "loss": 1.76178, "ppl": 5.823, "lr": 0.003, "grad": 0.1406, "tokens": 115336166400, "tok_s": 159314.7}
|
| 105 |
+
{"step": 110040, "epoch": 0.699, "loss": 1.75121, "ppl": 5.762, "lr": 0.003, "grad": 0.0795, "tokens": 115357132800, "tok_s": 159269.8}
|
| 106 |
+
{"step": 110060, "epoch": 0.699, "loss": 1.69675, "ppl": 5.456, "lr": 0.003, "grad": 0.0868, "tokens": 115378099200, "tok_s": 159030.7}
|
| 107 |
+
{"step": 110080, "epoch": 0.699, "loss": 1.76612, "ppl": 5.848, "lr": 0.003, "grad": 0.0979, "tokens": 115399065600, "tok_s": 159206.6}
|
| 108 |
+
{"step": 110100, "epoch": 0.7, "loss": 1.75739, "ppl": 5.797, "lr": 0.003, "grad": 0.088, "tokens": 115420032000, "tok_s": 159121.2}
|
| 109 |
+
{"step": 110120, "epoch": 0.7, "loss": 1.83068, "ppl": 6.238, "lr": 0.003, "grad": 0.1548, "tokens": 115440998400, "tok_s": 159261.6}
|
| 110 |
+
{"step": 110140, "epoch": 0.7, "loss": 1.77349, "ppl": 5.891, "lr": 0.003, "grad": 0.1482, "tokens": 115461964800, "tok_s": 159150.4}
|
| 111 |
+
{"step": 110160, "epoch": 0.7, "loss": 1.72478, "ppl": 5.611, "lr": 0.003, "grad": 0.0787, "tokens": 115482931200, "tok_s": 158986.2}
|
| 112 |
+
{"step": 110180, "epoch": 0.7, "loss": 1.75132, "ppl": 5.762, "lr": 0.003, "grad": 0.1179, "tokens": 115503897600, "tok_s": 159166.4}
|
| 113 |
+
{"step": 110200, "epoch": 0.7, "loss": 1.80498, "ppl": 6.08, "lr": 0.003, "grad": 0.0891, "tokens": 115524864000, "tok_s": 159210.4}
|
| 114 |
+
{"step": 110220, "epoch": 0.7, "loss": 1.70461, "ppl": 5.499, "lr": 0.003, "grad": 0.086, "tokens": 115545830400, "tok_s": 158635.4}
|
| 115 |
+
{"step": 110240, "epoch": 0.7, "loss": 1.74953, "ppl": 5.752, "lr": 0.003, "grad": 0.0893, "tokens": 115566796800, "tok_s": 158553.4}
|
| 116 |
+
{"step": 110260, "epoch": 0.701, "loss": 1.66313, "ppl": 5.276, "lr": 0.003, "grad": 0.0676, "tokens": 115587763200, "tok_s": 159319.4}
|
| 117 |
+
{"step": 110280, "epoch": 0.701, "loss": 1.76244, "ppl": 5.827, "lr": 0.003, "grad": 0.1082, "tokens": 115608729600, "tok_s": 158709.8}
|
| 118 |
+
{"step": 110300, "epoch": 0.701, "loss": 1.78618, "ppl": 5.967, "lr": 0.003, "grad": 0.0738, "tokens": 115629696000, "tok_s": 159270.7}
|
| 119 |
+
{"step": 110320, "epoch": 0.701, "loss": 1.66907, "ppl": 5.307, "lr": 0.003, "grad": 0.1015, "tokens": 115650662400, "tok_s": 158840.8}
|
| 120 |
+
{"step": 110340, "epoch": 0.701, "loss": 1.63189, "ppl": 5.114, "lr": 0.003, "grad": 0.1245, "tokens": 115671628800, "tok_s": 159193.9}
|
| 121 |
+
{"step": 110360, "epoch": 0.701, "loss": 1.75918, "ppl": 5.808, "lr": 0.003, "grad": 0.0886, "tokens": 115692595200, "tok_s": 159022.3}
|
| 122 |
+
{"step": 110380, "epoch": 0.701, "loss": 1.73369, "ppl": 5.661, "lr": 0.003, "grad": 0.1006, "tokens": 115713561600, "tok_s": 159316.0}
|
| 123 |
+
{"step": 110400, "epoch": 0.701, "loss": 1.64915, "ppl": 5.203, "lr": 0.003, "grad": 0.0742, "tokens": 115734528000, "tok_s": 159118.4}
|
| 124 |
+
{"step": 110420, "epoch": 0.702, "loss": 1.66734, "ppl": 5.298, "lr": 0.003, "grad": 0.0914, "tokens": 115755494400, "tok_s": 158787.8}
|
| 125 |
+
{"step": 110440, "epoch": 0.702, "loss": 1.85501, "ppl": 6.392, "lr": 0.003, "grad": 0.1211, "tokens": 115776460800, "tok_s": 158711.9}
|
| 126 |
+
{"step": 110460, "epoch": 0.702, "loss": 1.64944, "ppl": 5.204, "lr": 0.003, "grad": 0.1314, "tokens": 115797427200, "tok_s": 159306.0}
|
| 127 |
+
{"step": 110480, "epoch": 0.702, "loss": 1.72494, "ppl": 5.612, "lr": 0.003, "grad": 0.0604, "tokens": 115818393600, "tok_s": 159041.1}
|
| 128 |
+
{"step": 110500, "epoch": 0.702, "loss": 1.7002, "ppl": 5.475, "lr": 0.003, "grad": 0.0801, "tokens": 115839360000, "tok_s": 158925.5}
|
| 129 |
+
{"step": 110520, "epoch": 0.702, "loss": 1.71367, "ppl": 5.549, "lr": 0.003, "grad": 0.0822, "tokens": 115860326400, "tok_s": 158937.2}
|
| 130 |
+
{"step": 110540, "epoch": 0.702, "loss": 1.71543, "ppl": 5.559, "lr": 0.003, "grad": 0.1216, "tokens": 115881292800, "tok_s": 159384.8}
|
| 131 |
+
{"step": 110560, "epoch": 0.702, "loss": 1.81401, "ppl": 6.135, "lr": 0.003, "grad": 0.1036, "tokens": 115902259200, "tok_s": 159293.5}
|
| 132 |
+
{"step": 110580, "epoch": 0.703, "loss": 1.74452, "ppl": 5.723, "lr": 0.003, "grad": 0.107, "tokens": 115923225600, "tok_s": 159081.0}
|
| 133 |
+
{"step": 110600, "epoch": 0.703, "loss": 1.77592, "ppl": 5.906, "lr": 0.003, "grad": 0.0614, "tokens": 115944192000, "tok_s": 158693.3}
|
| 134 |
+
{"step": 110620, "epoch": 0.703, "loss": 1.73993, "ppl": 5.697, "lr": 0.003, "grad": 0.1163, "tokens": 115965158400, "tok_s": 159237.2}
|
| 135 |
+
{"step": 110640, "epoch": 0.703, "loss": 1.77779, "ppl": 5.917, "lr": 0.003, "grad": 0.0967, "tokens": 115986124800, "tok_s": 159123.3}
|
| 136 |
+
{"step": 110660, "epoch": 0.703, "loss": 1.64579, "ppl": 5.185, "lr": 0.003, "grad": 0.0867, "tokens": 116007091200, "tok_s": 159020.9}
|
| 137 |
+
{"step": 110680, "epoch": 0.703, "loss": 1.74047, "ppl": 5.7, "lr": 0.003, "grad": 0.1103, "tokens": 116028057600, "tok_s": 159155.7}
|
| 138 |
+
{"step": 110700, "epoch": 0.703, "loss": 1.69972, "ppl": 5.472, "lr": 0.003, "grad": 0.1113, "tokens": 116049024000, "tok_s": 159158.5}
|
| 139 |
+
{"step": 110720, "epoch": 0.703, "loss": 1.78604, "ppl": 5.966, "lr": 0.003, "grad": 0.0857, "tokens": 116069990400, "tok_s": 159214.9}
|
| 140 |
+
{"step": 110740, "epoch": 0.704, "loss": 1.60962, "ppl": 5.001, "lr": 0.003, "grad": 0.0856, "tokens": 116090956800, "tok_s": 159302.0}
|
| 141 |
+
{"step": 110760, "epoch": 0.704, "loss": 1.778, "ppl": 5.918, "lr": 0.003, "grad": 0.0979, "tokens": 116111923200, "tok_s": 158702.2}
|
| 142 |
+
{"step": 110780, "epoch": 0.704, "loss": 1.78549, "ppl": 5.962, "lr": 0.003, "grad": 0.1108, "tokens": 116132889600, "tok_s": 158791.8}
|
| 143 |
+
{"step": 110800, "epoch": 0.704, "loss": 1.75949, "ppl": 5.81, "lr": 0.003, "grad": 0.1462, "tokens": 116153856000, "tok_s": 159378.8}
|
| 144 |
+
{"step": 110820, "epoch": 0.704, "loss": 1.77886, "ppl": 5.923, "lr": 0.003, "grad": 0.1145, "tokens": 116174822400, "tok_s": 159320.7}
|
| 145 |
+
{"step": 110840, "epoch": 0.704, "loss": 1.77943, "ppl": 5.926, "lr": 0.003, "grad": 0.0896, "tokens": 116195788800, "tok_s": 158933.4}
|
| 146 |
+
{"step": 110860, "epoch": 0.704, "loss": 1.80276, "ppl": 6.066, "lr": 0.003, "grad": 0.1157, "tokens": 116216755200, "tok_s": 159196.3}
|
| 147 |
+
{"step": 110880, "epoch": 0.704, "loss": 1.71631, "ppl": 5.564, "lr": 0.003, "grad": 0.0982, "tokens": 116237721600, "tok_s": 159403.0}
|
| 148 |
+
{"step": 110900, "epoch": 0.705, "loss": 1.77119, "ppl": 5.878, "lr": 0.003, "grad": 0.068, "tokens": 116258688000, "tok_s": 159247.9}
|
| 149 |
+
{"step": 110920, "epoch": 0.705, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.0752, "tokens": 116279654400, "tok_s": 159255.1}
|
| 150 |
+
{"step": 110940, "epoch": 0.705, "loss": 1.7345, "ppl": 5.666, "lr": 0.003, "grad": 0.0871, "tokens": 116300620800, "tok_s": 159291.1}
|
| 151 |
+
{"step": 110960, "epoch": 0.705, "loss": 1.78909, "ppl": 5.984, "lr": 0.003, "grad": 0.0908, "tokens": 116321587200, "tok_s": 159059.9}
|
| 152 |
+
{"step": 110980, "epoch": 0.705, "loss": 1.76201, "ppl": 5.824, "lr": 0.003, "grad": 0.112, "tokens": 116342553600, "tok_s": 159287.3}
|
| 153 |
+
{"step": 111000, "epoch": 0.705, "loss": 1.7672, "ppl": 5.854, "lr": 0.003, "grad": 0.1463, "tokens": 116363520000, "tok_s": 159431.0}
|
| 154 |
+
{"step": 111000, "val_loss": 1.75042, "val_ppl": 5.757, "is_best": false}
|
| 155 |
+
{"step": 111020, "epoch": 0.705, "loss": 1.6984, "ppl": 5.465, "lr": 0.003, "grad": 0.0808, "tokens": 116384486400, "tok_s": 159150.2}
|
| 156 |
+
{"step": 111040, "epoch": 0.706, "loss": 1.75526, "ppl": 5.785, "lr": 0.003, "grad": 0.1077, "tokens": 116405452800, "tok_s": 159510.0}
|
| 157 |
+
{"step": 111060, "epoch": 0.706, "loss": 1.73815, "ppl": 5.687, "lr": 0.003, "grad": 0.0859, "tokens": 116426419200, "tok_s": 159332.7}
|
| 158 |
+
{"step": 111080, "epoch": 0.706, "loss": 1.77852, "ppl": 5.921, "lr": 0.003, "grad": 0.1268, "tokens": 116447385600, "tok_s": 159280.4}
|
| 159 |
+
{"step": 111100, "epoch": 0.706, "loss": 1.77494, "ppl": 5.9, "lr": 0.003, "grad": 0.0968, "tokens": 116468352000, "tok_s": 159332.5}
|
| 160 |
+
{"step": 111120, "epoch": 0.706, "loss": 1.74149, "ppl": 5.706, "lr": 0.003, "grad": 0.0827, "tokens": 116489318400, "tok_s": 159423.8}
|
| 161 |
+
{"step": 111140, "epoch": 0.706, "loss": 1.7278, "ppl": 5.628, "lr": 0.003, "grad": 0.1111, "tokens": 116510284800, "tok_s": 159236.6}
|
| 162 |
+
{"step": 111160, "epoch": 0.706, "loss": 1.73755, "ppl": 5.683, "lr": 0.003, "grad": 0.0862, "tokens": 116531251200, "tok_s": 159278.8}
|
| 163 |
+
{"step": 111180, "epoch": 0.706, "loss": 1.68257, "ppl": 5.379, "lr": 0.003, "grad": 0.0906, "tokens": 116552217600, "tok_s": 159097.9}
|
| 164 |
+
{"step": 111200, "epoch": 0.707, "loss": 1.74487, "ppl": 5.725, "lr": 0.003, "grad": 0.0906, "tokens": 116573184000, "tok_s": 158626.9}
|
| 165 |
+
{"step": 111220, "epoch": 0.707, "loss": 1.73152, "ppl": 5.649, "lr": 0.003, "grad": 0.1026, "tokens": 116594150400, "tok_s": 159504.5}
|
| 166 |
+
{"step": 111240, "epoch": 0.707, "loss": 1.73508, "ppl": 5.669, "lr": 0.003, "grad": 0.1041, "tokens": 116615116800, "tok_s": 159046.5}
|
| 167 |
+
{"step": 111260, "epoch": 0.707, "loss": 1.74921, "ppl": 5.75, "lr": 0.003, "grad": 0.1332, "tokens": 116636083200, "tok_s": 159197.6}
|
| 168 |
+
{"step": 111280, "epoch": 0.707, "loss": 1.77166, "ppl": 5.881, "lr": 0.003, "grad": 0.0846, "tokens": 116657049600, "tok_s": 159447.0}
|
| 169 |
+
{"step": 111300, "epoch": 0.707, "loss": 1.82379, "ppl": 6.195, "lr": 0.003, "grad": 0.082, "tokens": 116678016000, "tok_s": 159138.3}
|
| 170 |
+
{"step": 111320, "epoch": 0.707, "loss": 1.72487, "ppl": 5.612, "lr": 0.003, "grad": 0.1011, "tokens": 116698982400, "tok_s": 159408.6}
|
| 171 |
+
{"step": 111340, "epoch": 0.707, "loss": 1.75384, "ppl": 5.777, "lr": 0.003, "grad": 0.1379, "tokens": 116719948800, "tok_s": 159188.7}
|
| 172 |
+
{"step": 111360, "epoch": 0.708, "loss": 1.74064, "ppl": 5.701, "lr": 0.003, "grad": 0.1071, "tokens": 116740915200, "tok_s": 159434.4}
|
| 173 |
+
{"step": 111380, "epoch": 0.708, "loss": 1.69438, "ppl": 5.443, "lr": 0.003, "grad": 0.1395, "tokens": 116761881600, "tok_s": 159358.7}
|
| 174 |
+
{"step": 111400, "epoch": 0.708, "loss": 1.71567, "ppl": 5.56, "lr": 0.003, "grad": 0.1088, "tokens": 116782848000, "tok_s": 159073.0}
|
| 175 |
+
{"step": 111420, "epoch": 0.708, "loss": 1.74194, "ppl": 5.708, "lr": 0.003, "grad": 0.111, "tokens": 116803814400, "tok_s": 158820.6}
|
| 176 |
+
{"step": 111440, "epoch": 0.708, "loss": 1.72756, "ppl": 5.627, "lr": 0.003, "grad": 0.0669, "tokens": 116824780800, "tok_s": 159415.1}
|
| 177 |
+
{"step": 111460, "epoch": 0.708, "loss": 1.73954, "ppl": 5.695, "lr": 0.003, "grad": 0.0708, "tokens": 116845747200, "tok_s": 159146.3}
|
| 178 |
+
{"step": 111480, "epoch": 0.708, "loss": 1.65413, "ppl": 5.229, "lr": 0.003, "grad": 0.101, "tokens": 116866713600, "tok_s": 159367.7}
|
| 179 |
+
{"step": 111500, "epoch": 0.708, "loss": 1.86436, "ppl": 6.452, "lr": 0.003, "grad": 0.1122, "tokens": 116887680000, "tok_s": 159323.4}
|
| 180 |
+
{"step": 111520, "epoch": 0.709, "loss": 1.79098, "ppl": 5.995, "lr": 0.003, "grad": 0.0922, "tokens": 116908646400, "tok_s": 159110.5}
|
| 181 |
+
{"step": 111540, "epoch": 0.709, "loss": 1.69771, "ppl": 5.461, "lr": 0.003, "grad": 0.0836, "tokens": 116929612800, "tok_s": 158748.0}
|
| 182 |
+
{"step": 111560, "epoch": 0.709, "loss": 1.85084, "ppl": 6.365, "lr": 0.003, "grad": 0.1336, "tokens": 116950579200, "tok_s": 158769.3}
|
| 183 |
+
{"step": 111580, "epoch": 0.709, "loss": 1.7332, "ppl": 5.659, "lr": 0.003, "grad": 0.0547, "tokens": 116971545600, "tok_s": 158949.8}
|
| 184 |
+
{"step": 111600, "epoch": 0.709, "loss": 1.82211, "ppl": 6.185, "lr": 0.003, "grad": 0.0935, "tokens": 116992512000, "tok_s": 159577.8}
|
| 185 |
+
{"step": 111620, "epoch": 0.709, "loss": 1.73952, "ppl": 5.695, "lr": 0.003, "grad": 0.1019, "tokens": 117013478400, "tok_s": 159257.3}
|
| 186 |
+
{"step": 111640, "epoch": 0.709, "loss": 1.75399, "ppl": 5.778, "lr": 0.003, "grad": 0.0972, "tokens": 117034444800, "tok_s": 159517.7}
|
| 187 |
+
{"step": 111660, "epoch": 0.709, "loss": 1.63774, "ppl": 5.144, "lr": 0.003, "grad": 0.0868, "tokens": 117055411200, "tok_s": 159206.2}
|
| 188 |
+
{"step": 111680, "epoch": 0.71, "loss": 1.46853, "ppl": 4.343, "lr": 0.003, "grad": 0.0776, "tokens": 117076377600, "tok_s": 159410.0}
|
| 189 |
+
{"step": 111700, "epoch": 0.71, "loss": 1.80166, "ppl": 6.06, "lr": 0.003, "grad": 0.0876, "tokens": 117097344000, "tok_s": 159578.9}
|
| 190 |
+
{"step": 111720, "epoch": 0.71, "loss": 1.70327, "ppl": 5.492, "lr": 0.003, "grad": 0.0738, "tokens": 117118310400, "tok_s": 159501.8}
|
| 191 |
+
{"step": 111740, "epoch": 0.71, "loss": 1.71684, "ppl": 5.567, "lr": 0.003, "grad": 0.0744, "tokens": 117139276800, "tok_s": 159516.4}
|
| 192 |
+
{"step": 111760, "epoch": 0.71, "loss": 1.74614, "ppl": 5.732, "lr": 0.003, "grad": 0.1049, "tokens": 117160243200, "tok_s": 159549.5}
|
| 193 |
+
{"step": 111780, "epoch": 0.71, "loss": 1.71022, "ppl": 5.53, "lr": 0.003, "grad": 0.1, "tokens": 117181209600, "tok_s": 159434.6}
|
| 194 |
+
{"step": 111800, "epoch": 0.71, "loss": 1.76808, "ppl": 5.86, "lr": 0.003, "grad": 0.099, "tokens": 117202176000, "tok_s": 159530.7}
|
| 195 |
+
{"step": 111820, "epoch": 0.71, "loss": 1.75091, "ppl": 5.76, "lr": 0.003, "grad": 0.1336, "tokens": 117223142400, "tok_s": 159321.7}
|
| 196 |
+
{"step": 111840, "epoch": 0.711, "loss": 1.76696, "ppl": 5.853, "lr": 0.003, "grad": 0.0972, "tokens": 117244108800, "tok_s": 159480.5}
|
| 197 |
+
{"step": 111860, "epoch": 0.711, "loss": 1.74118, "ppl": 5.704, "lr": 0.003, "grad": 0.1202, "tokens": 117265075200, "tok_s": 159413.2}
|
| 198 |
+
{"step": 111880, "epoch": 0.711, "loss": 1.74494, "ppl": 5.726, "lr": 0.003, "grad": 0.0821, "tokens": 117286041600, "tok_s": 158970.8}
|
| 199 |
+
{"step": 111900, "epoch": 0.711, "loss": 1.73236, "ppl": 5.654, "lr": 0.003, "grad": 0.1208, "tokens": 117307008000, "tok_s": 159447.2}
|
| 200 |
+
{"step": 111920, "epoch": 0.711, "loss": 1.73324, "ppl": 5.659, "lr": 0.003, "grad": 0.096, "tokens": 117327974400, "tok_s": 159294.4}
|
| 201 |
+
{"step": 111940, "epoch": 0.711, "loss": 1.74069, "ppl": 5.701, "lr": 0.003, "grad": 0.1187, "tokens": 117348940800, "tok_s": 159487.3}
|
| 202 |
+
{"step": 111960, "epoch": 0.711, "loss": 1.77119, "ppl": 5.878, "lr": 0.003, "grad": 0.077, "tokens": 117369907200, "tok_s": 159454.8}
|
| 203 |
+
{"step": 111980, "epoch": 0.711, "loss": 1.73885, "ppl": 5.691, "lr": 0.003, "grad": 0.1331, "tokens": 117390873600, "tok_s": 159374.5}
|
| 204 |
+
{"step": 112000, "epoch": 0.712, "loss": 1.76929, "ppl": 5.867, "lr": 0.003, "grad": 0.0924, "tokens": 117411840000, "tok_s": 159310.0}
|
| 205 |
+
{"step": 112000, "val_loss": 1.75172, "val_ppl": 5.765, "is_best": false}
|
| 206 |
+
{"step": 112020, "epoch": 0.712, "loss": 1.71808, "ppl": 5.574, "lr": 0.003, "grad": 0.0899, "tokens": 117432806400, "tok_s": 159287.7}
|
| 207 |
+
{"step": 112040, "epoch": 0.712, "loss": 1.77222, "ppl": 5.884, "lr": 0.003, "grad": 0.0781, "tokens": 117453772800, "tok_s": 159300.9}
|
| 208 |
+
{"step": 112060, "epoch": 0.712, "loss": 1.71887, "ppl": 5.578, "lr": 0.003, "grad": 0.114, "tokens": 117474739200, "tok_s": 159331.6}
|
| 209 |
+
{"step": 112080, "epoch": 0.712, "loss": 1.78258, "ppl": 5.945, "lr": 0.003, "grad": 0.1099, "tokens": 117495705600, "tok_s": 159460.7}
|
| 210 |
+
{"step": 112100, "epoch": 0.712, "loss": 1.75808, "ppl": 5.801, "lr": 0.003, "grad": 0.0674, "tokens": 117516672000, "tok_s": 159530.0}
|
| 211 |
+
{"step": 112120, "epoch": 0.712, "loss": 1.77801, "ppl": 5.918, "lr": 0.003, "grad": 0.1279, "tokens": 117537638400, "tok_s": 159285.0}
|
| 212 |
+
{"step": 112140, "epoch": 0.712, "loss": 1.71816, "ppl": 5.574, "lr": 0.003, "grad": 0.074, "tokens": 117558604800, "tok_s": 159645.4}
|
| 213 |
+
{"step": 112160, "epoch": 0.713, "loss": 1.75756, "ppl": 5.798, "lr": 0.003, "grad": 0.0773, "tokens": 117579571200, "tok_s": 159666.7}
|
| 214 |
+
{"step": 112180, "epoch": 0.713, "loss": 1.76968, "ppl": 5.869, "lr": 0.003, "grad": 0.0857, "tokens": 117600537600, "tok_s": 159520.4}
|
| 215 |
+
{"step": 112200, "epoch": 0.713, "loss": 1.79859, "ppl": 6.041, "lr": 0.003, "grad": 0.1014, "tokens": 117621504000, "tok_s": 159421.9}
|
| 216 |
+
{"step": 112220, "epoch": 0.713, "loss": 1.79279, "ppl": 6.006, "lr": 0.003, "grad": 0.1231, "tokens": 117642470400, "tok_s": 159045.5}
|
| 217 |
+
{"step": 112240, "epoch": 0.713, "loss": 1.76364, "ppl": 5.834, "lr": 0.003, "grad": 0.059, "tokens": 117663436800, "tok_s": 159634.5}
|
| 218 |
+
{"step": 112260, "epoch": 0.713, "loss": 1.7205, "ppl": 5.587, "lr": 0.003, "grad": 0.0755, "tokens": 117684403200, "tok_s": 159674.7}
|
| 219 |
+
{"step": 112280, "epoch": 0.713, "loss": 1.80559, "ppl": 6.084, "lr": 0.003, "grad": 0.0862, "tokens": 117705369600, "tok_s": 159307.2}
|
| 220 |
+
{"step": 112300, "epoch": 0.714, "loss": 1.77187, "ppl": 5.882, "lr": 0.003, "grad": 0.067, "tokens": 117726336000, "tok_s": 159533.7}
|
| 221 |
+
{"step": 112320, "epoch": 0.714, "loss": 1.72064, "ppl": 5.588, "lr": 0.003, "grad": 0.0873, "tokens": 117747302400, "tok_s": 159528.0}
|
| 222 |
+
{"step": 112340, "epoch": 0.714, "loss": 1.77857, "ppl": 5.921, "lr": 0.003, "grad": 0.1095, "tokens": 117768268800, "tok_s": 159452.0}
|
| 223 |
+
{"step": 112360, "epoch": 0.714, "loss": 1.71787, "ppl": 5.573, "lr": 0.003, "grad": 0.1111, "tokens": 117789235200, "tok_s": 159383.7}
|
| 224 |
+
{"step": 112380, "epoch": 0.714, "loss": 1.76632, "ppl": 5.849, "lr": 0.003, "grad": 0.0862, "tokens": 117810201600, "tok_s": 159382.1}
|
| 225 |
+
{"step": 112400, "epoch": 0.714, "loss": 1.65028, "ppl": 5.208, "lr": 0.003, "grad": 0.0663, "tokens": 117831168000, "tok_s": 159471.2}
|
| 226 |
+
{"step": 112420, "epoch": 0.714, "loss": 1.75984, "ppl": 5.812, "lr": 0.003, "grad": 0.1549, "tokens": 117852134400, "tok_s": 159639.3}
|
| 227 |
+
{"step": 112440, "epoch": 0.714, "loss": 1.75543, "ppl": 5.786, "lr": 0.003, "grad": 0.1344, "tokens": 117873100800, "tok_s": 159344.7}
|
| 228 |
+
{"step": 112460, "epoch": 0.715, "loss": 1.76423, "ppl": 5.837, "lr": 0.003, "grad": 0.1024, "tokens": 117894067200, "tok_s": 159321.1}
|
| 229 |
+
{"step": 112480, "epoch": 0.715, "loss": 1.91702, "ppl": 6.801, "lr": 0.003, "grad": 0.0819, "tokens": 117915033600, "tok_s": 159037.5}
|
| 230 |
+
{"step": 112500, "epoch": 0.715, "loss": 1.79592, "ppl": 6.025, "lr": 0.003, "grad": 0.1017, "tokens": 117936000000, "tok_s": 159516.1}
|
| 231 |
+
{"step": 112520, "epoch": 0.715, "loss": 1.74587, "ppl": 5.731, "lr": 0.003, "grad": 0.1701, "tokens": 117956966400, "tok_s": 159611.4}
|
| 232 |
+
{"step": 112540, "epoch": 0.715, "loss": 1.73889, "ppl": 5.691, "lr": 0.003, "grad": 0.0783, "tokens": 117977932800, "tok_s": 159396.6}
|
| 233 |
+
{"step": 112560, "epoch": 0.715, "loss": 1.81082, "ppl": 6.115, "lr": 0.003, "grad": 0.0998, "tokens": 117998899200, "tok_s": 159623.8}
|
| 234 |
+
{"step": 112580, "epoch": 0.715, "loss": 1.72118, "ppl": 5.591, "lr": 0.003, "grad": 0.067, "tokens": 118019865600, "tok_s": 159454.9}
|
| 235 |
+
{"step": 112600, "epoch": 0.715, "loss": 1.75461, "ppl": 5.781, "lr": 0.003, "grad": 0.077, "tokens": 118040832000, "tok_s": 159684.4}
|
| 236 |
+
{"step": 112620, "epoch": 0.716, "loss": 1.77048, "ppl": 5.874, "lr": 0.003, "grad": 0.054, "tokens": 118061798400, "tok_s": 159598.4}
|
| 237 |
+
{"step": 112640, "epoch": 0.716, "loss": 1.74223, "ppl": 5.71, "lr": 0.003, "grad": 0.1479, "tokens": 118082764800, "tok_s": 159479.3}
|
| 238 |
+
{"step": 112660, "epoch": 0.716, "loss": 1.71519, "ppl": 5.558, "lr": 0.003, "grad": 0.0724, "tokens": 118103731200, "tok_s": 159291.0}
|
| 239 |
+
{"step": 112680, "epoch": 0.716, "loss": 1.79875, "ppl": 6.042, "lr": 0.003, "grad": 0.0921, "tokens": 118124697600, "tok_s": 159471.4}
|
| 240 |
+
{"step": 112700, "epoch": 0.716, "loss": 1.70996, "ppl": 5.529, "lr": 0.003, "grad": 0.1337, "tokens": 118145664000, "tok_s": 159218.8}
|
| 241 |
+
{"step": 112720, "epoch": 0.716, "loss": 1.74098, "ppl": 5.703, "lr": 0.003, "grad": 0.1494, "tokens": 118166630400, "tok_s": 159275.1}
|
| 242 |
+
{"step": 112740, "epoch": 0.716, "loss": 1.7655, "ppl": 5.844, "lr": 0.003, "grad": 0.0672, "tokens": 118187596800, "tok_s": 159096.1}
|
| 243 |
+
{"step": 112760, "epoch": 0.716, "loss": 1.78273, "ppl": 5.946, "lr": 0.003, "grad": 0.0975, "tokens": 118208563200, "tok_s": 159040.5}
|
| 244 |
+
{"step": 112780, "epoch": 0.717, "loss": 1.73538, "ppl": 5.671, "lr": 0.003, "grad": 0.0696, "tokens": 118229529600, "tok_s": 159388.5}
|
| 245 |
+
{"step": 112800, "epoch": 0.717, "loss": 1.77052, "ppl": 5.874, "lr": 0.003, "grad": 0.0829, "tokens": 118250496000, "tok_s": 159384.5}
|
| 246 |
+
{"step": 112820, "epoch": 0.717, "loss": 1.70729, "ppl": 5.514, "lr": 0.003, "grad": 0.1062, "tokens": 118271462400, "tok_s": 159150.0}
|
| 247 |
+
{"step": 112840, "epoch": 0.717, "loss": 1.75066, "ppl": 5.758, "lr": 0.003, "grad": 0.123, "tokens": 118292428800, "tok_s": 159371.2}
|
| 248 |
+
{"step": 112860, "epoch": 0.717, "loss": 1.75785, "ppl": 5.8, "lr": 0.003, "grad": 0.0776, "tokens": 118313395200, "tok_s": 159254.5}
|
| 249 |
+
{"step": 112880, "epoch": 0.717, "loss": 1.66883, "ppl": 5.306, "lr": 0.003, "grad": 0.0774, "tokens": 118334361600, "tok_s": 159194.2}
|
| 250 |
+
{"step": 112900, "epoch": 0.717, "loss": 1.75422, "ppl": 5.779, "lr": 0.003, "grad": 0.0913, "tokens": 118355328000, "tok_s": 159224.6}
|
| 251 |
+
{"step": 112920, "epoch": 0.717, "loss": 1.73858, "ppl": 5.689, "lr": 0.003, "grad": 0.0895, "tokens": 118376294400, "tok_s": 159340.9}
|
| 252 |
+
{"step": 112940, "epoch": 0.718, "loss": 1.72907, "ppl": 5.635, "lr": 0.003, "grad": 0.091, "tokens": 118397260800, "tok_s": 159530.8}
|
| 253 |
+
{"step": 112960, "epoch": 0.718, "loss": 1.70134, "ppl": 5.481, "lr": 0.003, "grad": 0.0728, "tokens": 118418227200, "tok_s": 159361.9}
|
| 254 |
+
{"step": 112980, "epoch": 0.718, "loss": 1.76709, "ppl": 5.854, "lr": 0.003, "grad": 0.0946, "tokens": 118439193600, "tok_s": 158867.4}
|
| 255 |
+
{"step": 113000, "epoch": 0.718, "loss": 1.78327, "ppl": 5.949, "lr": 0.003, "grad": 0.0988, "tokens": 118460160000, "tok_s": 158655.4}
|
| 256 |
+
{"step": 113000, "val_loss": 1.7531, "val_ppl": 5.772, "is_best": false}
|
logs/log_114000.jsonl
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 113000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-05T06:28:33.908905"}
|
| 2 |
+
{"step": 113020, "epoch": 0.718, "loss": 1.73974, "ppl": 5.696, "lr": 0.003, "grad": 0.1063, "tokens": 118481126400, "tok_s": 158492.1}
|
| 3 |
+
{"step": 113040, "epoch": 0.718, "loss": 1.74188, "ppl": 5.708, "lr": 0.003, "grad": 0.0846, "tokens": 118502092800, "tok_s": 158868.7}
|
| 4 |
+
{"step": 113060, "epoch": 0.718, "loss": 1.71566, "ppl": 5.56, "lr": 0.003, "grad": 0.1073, "tokens": 118523059200, "tok_s": 159149.1}
|
| 5 |
+
{"step": 113080, "epoch": 0.718, "loss": 1.61321, "ppl": 5.019, "lr": 0.003, "grad": 0.1108, "tokens": 118544025600, "tok_s": 159129.0}
|
| 6 |
+
{"step": 113100, "epoch": 0.719, "loss": 1.76739, "ppl": 5.856, "lr": 0.003, "grad": 0.102, "tokens": 118564992000, "tok_s": 159208.2}
|
| 7 |
+
{"step": 113120, "epoch": 0.719, "loss": 1.72873, "ppl": 5.634, "lr": 0.003, "grad": 0.0831, "tokens": 118585958400, "tok_s": 159042.0}
|
| 8 |
+
{"step": 113140, "epoch": 0.719, "loss": 1.74315, "ppl": 5.715, "lr": 0.003, "grad": 0.1, "tokens": 118606924800, "tok_s": 159134.1}
|
| 9 |
+
{"step": 113160, "epoch": 0.719, "loss": 1.67597, "ppl": 5.344, "lr": 0.003, "grad": 0.092, "tokens": 118627891200, "tok_s": 159165.1}
|
| 10 |
+
{"step": 113180, "epoch": 0.719, "loss": 1.62867, "ppl": 5.097, "lr": 0.003, "grad": 0.0778, "tokens": 118648857600, "tok_s": 158915.5}
|
| 11 |
+
{"step": 113200, "epoch": 0.719, "loss": 1.59332, "ppl": 4.92, "lr": 0.003, "grad": 0.1523, "tokens": 118669824000, "tok_s": 159228.9}
|
| 12 |
+
{"step": 113220, "epoch": 0.719, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.1081, "tokens": 118690790400, "tok_s": 159106.3}
|
| 13 |
+
{"step": 113240, "epoch": 0.719, "loss": 1.70175, "ppl": 5.484, "lr": 0.003, "grad": 0.0778, "tokens": 118711756800, "tok_s": 159104.9}
|
| 14 |
+
{"step": 113260, "epoch": 0.72, "loss": 1.76013, "ppl": 5.813, "lr": 0.003, "grad": 0.0838, "tokens": 118732723200, "tok_s": 159141.8}
|
| 15 |
+
{"step": 113280, "epoch": 0.72, "loss": 1.71039, "ppl": 5.531, "lr": 0.003, "grad": 0.0872, "tokens": 118753689600, "tok_s": 158455.7}
|
| 16 |
+
{"step": 113300, "epoch": 0.72, "loss": 1.75435, "ppl": 5.78, "lr": 0.003, "grad": 0.078, "tokens": 118774656000, "tok_s": 159162.6}
|
| 17 |
+
{"step": 113320, "epoch": 0.72, "loss": 1.7597, "ppl": 5.811, "lr": 0.003, "grad": 0.0796, "tokens": 118795622400, "tok_s": 158885.5}
|
| 18 |
+
{"step": 113340, "epoch": 0.72, "loss": 1.72363, "ppl": 5.605, "lr": 0.003, "grad": 0.1116, "tokens": 118816588800, "tok_s": 159070.6}
|
| 19 |
+
{"step": 113360, "epoch": 0.72, "loss": 1.77175, "ppl": 5.881, "lr": 0.003, "grad": 0.0751, "tokens": 118837555200, "tok_s": 158738.5}
|
| 20 |
+
{"step": 113380, "epoch": 0.72, "loss": 1.67999, "ppl": 5.366, "lr": 0.003, "grad": 0.0561, "tokens": 118858521600, "tok_s": 159053.7}
|
| 21 |
+
{"step": 113400, "epoch": 0.721, "loss": 1.78069, "ppl": 5.934, "lr": 0.003, "grad": 0.0864, "tokens": 118879488000, "tok_s": 159167.9}
|
| 22 |
+
{"step": 113420, "epoch": 0.721, "loss": 1.7595, "ppl": 5.81, "lr": 0.003, "grad": 0.0752, "tokens": 118900454400, "tok_s": 159167.7}
|
| 23 |
+
{"step": 113440, "epoch": 0.721, "loss": 1.67152, "ppl": 5.32, "lr": 0.003, "grad": 0.0591, "tokens": 118921420800, "tok_s": 159154.3}
|
| 24 |
+
{"step": 113460, "epoch": 0.721, "loss": 1.81131, "ppl": 6.118, "lr": 0.003, "grad": 0.0707, "tokens": 118942387200, "tok_s": 159200.8}
|
| 25 |
+
{"step": 113480, "epoch": 0.721, "loss": 1.80639, "ppl": 6.088, "lr": 0.003, "grad": 0.1177, "tokens": 118963353600, "tok_s": 158645.5}
|
| 26 |
+
{"step": 113500, "epoch": 0.721, "loss": 1.90369, "ppl": 6.711, "lr": 0.003, "grad": 0.1204, "tokens": 118984320000, "tok_s": 159158.8}
|
| 27 |
+
{"step": 113520, "epoch": 0.721, "loss": 1.76353, "ppl": 5.833, "lr": 0.003, "grad": 0.0801, "tokens": 119005286400, "tok_s": 159064.2}
|
| 28 |
+
{"step": 113540, "epoch": 0.721, "loss": 1.65881, "ppl": 5.253, "lr": 0.003, "grad": 0.0753, "tokens": 119026252800, "tok_s": 158729.6}
|
| 29 |
+
{"step": 113560, "epoch": 0.722, "loss": 1.6794, "ppl": 5.362, "lr": 0.003, "grad": 0.0962, "tokens": 119047219200, "tok_s": 159102.7}
|
| 30 |
+
{"step": 113580, "epoch": 0.722, "loss": 1.70352, "ppl": 5.493, "lr": 0.003, "grad": 0.0809, "tokens": 119068185600, "tok_s": 159052.4}
|
| 31 |
+
{"step": 113600, "epoch": 0.722, "loss": 1.64007, "ppl": 5.156, "lr": 0.003, "grad": 0.0822, "tokens": 119089152000, "tok_s": 159126.5}
|
| 32 |
+
{"step": 113620, "epoch": 0.722, "loss": 1.71385, "ppl": 5.55, "lr": 0.003, "grad": 0.0876, "tokens": 119110118400, "tok_s": 158751.5}
|
| 33 |
+
{"step": 113640, "epoch": 0.722, "loss": 1.66267, "ppl": 5.273, "lr": 0.003, "grad": 0.0894, "tokens": 119131084800, "tok_s": 159024.1}
|
| 34 |
+
{"step": 113660, "epoch": 0.722, "loss": 1.84263, "ppl": 6.313, "lr": 0.003, "grad": 0.0854, "tokens": 119152051200, "tok_s": 159082.8}
|
| 35 |
+
{"step": 113680, "epoch": 0.722, "loss": 1.77115, "ppl": 5.878, "lr": 0.003, "grad": 0.1382, "tokens": 119173017600, "tok_s": 158890.2}
|
| 36 |
+
{"step": 113700, "epoch": 0.722, "loss": 1.74136, "ppl": 5.705, "lr": 0.003, "grad": 0.1349, "tokens": 119193984000, "tok_s": 159019.4}
|
| 37 |
+
{"step": 113720, "epoch": 0.723, "loss": 1.66535, "ppl": 5.288, "lr": 0.003, "grad": 0.1052, "tokens": 119214950400, "tok_s": 159074.2}
|
| 38 |
+
{"step": 113740, "epoch": 0.723, "loss": 1.69789, "ppl": 5.462, "lr": 0.003, "grad": 0.0753, "tokens": 119235916800, "tok_s": 159056.5}
|
| 39 |
+
{"step": 113760, "epoch": 0.723, "loss": 1.7667, "ppl": 5.852, "lr": 0.003, "grad": 0.0999, "tokens": 119256883200, "tok_s": 159064.9}
|
| 40 |
+
{"step": 113780, "epoch": 0.723, "loss": 1.67702, "ppl": 5.35, "lr": 0.003, "grad": 0.1165, "tokens": 119277849600, "tok_s": 159030.2}
|
| 41 |
+
{"step": 113800, "epoch": 0.723, "loss": 1.693, "ppl": 5.436, "lr": 0.003, "grad": 0.0981, "tokens": 119298816000, "tok_s": 159047.8}
|
| 42 |
+
{"step": 113820, "epoch": 0.723, "loss": 1.74231, "ppl": 5.711, "lr": 0.003, "grad": 0.1045, "tokens": 119319782400, "tok_s": 159088.2}
|
| 43 |
+
{"step": 113840, "epoch": 0.723, "loss": 1.67498, "ppl": 5.339, "lr": 0.003, "grad": 0.1062, "tokens": 119340748800, "tok_s": 159079.4}
|
| 44 |
+
{"step": 113860, "epoch": 0.723, "loss": 1.7508, "ppl": 5.759, "lr": 0.003, "grad": 0.0925, "tokens": 119361715200, "tok_s": 159038.2}
|
| 45 |
+
{"step": 113880, "epoch": 0.724, "loss": 1.77965, "ppl": 5.928, "lr": 0.003, "grad": 0.1, "tokens": 119382681600, "tok_s": 158024.9}
|
| 46 |
+
{"step": 113900, "epoch": 0.724, "loss": 1.45134, "ppl": 4.269, "lr": 0.003, "grad": 0.0785, "tokens": 119403648000, "tok_s": 158567.9}
|
| 47 |
+
{"step": 113920, "epoch": 0.724, "loss": 1.67685, "ppl": 5.349, "lr": 0.003, "grad": 0.0789, "tokens": 119424614400, "tok_s": 158979.3}
|
| 48 |
+
{"step": 113940, "epoch": 0.724, "loss": 1.68904, "ppl": 5.414, "lr": 0.003, "grad": 0.0793, "tokens": 119445580800, "tok_s": 158486.4}
|
| 49 |
+
{"step": 113960, "epoch": 0.724, "loss": 1.7833, "ppl": 5.949, "lr": 0.003, "grad": 0.1064, "tokens": 119466547200, "tok_s": 158933.5}
|
| 50 |
+
{"step": 113980, "epoch": 0.724, "loss": 1.73486, "ppl": 5.668, "lr": 0.003, "grad": 0.062, "tokens": 119487513600, "tok_s": 159280.1}
|
| 51 |
+
{"step": 114000, "epoch": 0.724, "loss": 1.89109, "ppl": 6.627, "lr": 0.003, "grad": 0.157, "tokens": 119508480000, "tok_s": 159128.2}
|
| 52 |
+
{"step": 114000, "val_loss": 1.73226, "val_ppl": 5.653, "is_best": true}
|
logs/log_115000.jsonl
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 113000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-05T06:28:33.908905"}
|
| 2 |
+
{"step": 113020, "epoch": 0.718, "loss": 1.73974, "ppl": 5.696, "lr": 0.003, "grad": 0.1063, "tokens": 118481126400, "tok_s": 158492.1}
|
| 3 |
+
{"step": 113040, "epoch": 0.718, "loss": 1.74188, "ppl": 5.708, "lr": 0.003, "grad": 0.0846, "tokens": 118502092800, "tok_s": 158868.7}
|
| 4 |
+
{"step": 113060, "epoch": 0.718, "loss": 1.71566, "ppl": 5.56, "lr": 0.003, "grad": 0.1073, "tokens": 118523059200, "tok_s": 159149.1}
|
| 5 |
+
{"step": 113080, "epoch": 0.718, "loss": 1.61321, "ppl": 5.019, "lr": 0.003, "grad": 0.1108, "tokens": 118544025600, "tok_s": 159129.0}
|
| 6 |
+
{"step": 113100, "epoch": 0.719, "loss": 1.76739, "ppl": 5.856, "lr": 0.003, "grad": 0.102, "tokens": 118564992000, "tok_s": 159208.2}
|
| 7 |
+
{"step": 113120, "epoch": 0.719, "loss": 1.72873, "ppl": 5.634, "lr": 0.003, "grad": 0.0831, "tokens": 118585958400, "tok_s": 159042.0}
|
| 8 |
+
{"step": 113140, "epoch": 0.719, "loss": 1.74315, "ppl": 5.715, "lr": 0.003, "grad": 0.1, "tokens": 118606924800, "tok_s": 159134.1}
|
| 9 |
+
{"step": 113160, "epoch": 0.719, "loss": 1.67597, "ppl": 5.344, "lr": 0.003, "grad": 0.092, "tokens": 118627891200, "tok_s": 159165.1}
|
| 10 |
+
{"step": 113180, "epoch": 0.719, "loss": 1.62867, "ppl": 5.097, "lr": 0.003, "grad": 0.0778, "tokens": 118648857600, "tok_s": 158915.5}
|
| 11 |
+
{"step": 113200, "epoch": 0.719, "loss": 1.59332, "ppl": 4.92, "lr": 0.003, "grad": 0.1523, "tokens": 118669824000, "tok_s": 159228.9}
|
| 12 |
+
{"step": 113220, "epoch": 0.719, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.1081, "tokens": 118690790400, "tok_s": 159106.3}
|
| 13 |
+
{"step": 113240, "epoch": 0.719, "loss": 1.70175, "ppl": 5.484, "lr": 0.003, "grad": 0.0778, "tokens": 118711756800, "tok_s": 159104.9}
|
| 14 |
+
{"step": 113260, "epoch": 0.72, "loss": 1.76013, "ppl": 5.813, "lr": 0.003, "grad": 0.0838, "tokens": 118732723200, "tok_s": 159141.8}
|
| 15 |
+
{"step": 113280, "epoch": 0.72, "loss": 1.71039, "ppl": 5.531, "lr": 0.003, "grad": 0.0872, "tokens": 118753689600, "tok_s": 158455.7}
|
| 16 |
+
{"step": 113300, "epoch": 0.72, "loss": 1.75435, "ppl": 5.78, "lr": 0.003, "grad": 0.078, "tokens": 118774656000, "tok_s": 159162.6}
|
| 17 |
+
{"step": 113320, "epoch": 0.72, "loss": 1.7597, "ppl": 5.811, "lr": 0.003, "grad": 0.0796, "tokens": 118795622400, "tok_s": 158885.5}
|
| 18 |
+
{"step": 113340, "epoch": 0.72, "loss": 1.72363, "ppl": 5.605, "lr": 0.003, "grad": 0.1116, "tokens": 118816588800, "tok_s": 159070.6}
|
| 19 |
+
{"step": 113360, "epoch": 0.72, "loss": 1.77175, "ppl": 5.881, "lr": 0.003, "grad": 0.0751, "tokens": 118837555200, "tok_s": 158738.5}
|
| 20 |
+
{"step": 113380, "epoch": 0.72, "loss": 1.67999, "ppl": 5.366, "lr": 0.003, "grad": 0.0561, "tokens": 118858521600, "tok_s": 159053.7}
|
| 21 |
+
{"step": 113400, "epoch": 0.721, "loss": 1.78069, "ppl": 5.934, "lr": 0.003, "grad": 0.0864, "tokens": 118879488000, "tok_s": 159167.9}
|
| 22 |
+
{"step": 113420, "epoch": 0.721, "loss": 1.7595, "ppl": 5.81, "lr": 0.003, "grad": 0.0752, "tokens": 118900454400, "tok_s": 159167.7}
|
| 23 |
+
{"step": 113440, "epoch": 0.721, "loss": 1.67152, "ppl": 5.32, "lr": 0.003, "grad": 0.0591, "tokens": 118921420800, "tok_s": 159154.3}
|
| 24 |
+
{"step": 113460, "epoch": 0.721, "loss": 1.81131, "ppl": 6.118, "lr": 0.003, "grad": 0.0707, "tokens": 118942387200, "tok_s": 159200.8}
|
| 25 |
+
{"step": 113480, "epoch": 0.721, "loss": 1.80639, "ppl": 6.088, "lr": 0.003, "grad": 0.1177, "tokens": 118963353600, "tok_s": 158645.5}
|
| 26 |
+
{"step": 113500, "epoch": 0.721, "loss": 1.90369, "ppl": 6.711, "lr": 0.003, "grad": 0.1204, "tokens": 118984320000, "tok_s": 159158.8}
|
| 27 |
+
{"step": 113520, "epoch": 0.721, "loss": 1.76353, "ppl": 5.833, "lr": 0.003, "grad": 0.0801, "tokens": 119005286400, "tok_s": 159064.2}
|
| 28 |
+
{"step": 113540, "epoch": 0.721, "loss": 1.65881, "ppl": 5.253, "lr": 0.003, "grad": 0.0753, "tokens": 119026252800, "tok_s": 158729.6}
|
| 29 |
+
{"step": 113560, "epoch": 0.722, "loss": 1.6794, "ppl": 5.362, "lr": 0.003, "grad": 0.0962, "tokens": 119047219200, "tok_s": 159102.7}
|
| 30 |
+
{"step": 113580, "epoch": 0.722, "loss": 1.70352, "ppl": 5.493, "lr": 0.003, "grad": 0.0809, "tokens": 119068185600, "tok_s": 159052.4}
|
| 31 |
+
{"step": 113600, "epoch": 0.722, "loss": 1.64007, "ppl": 5.156, "lr": 0.003, "grad": 0.0822, "tokens": 119089152000, "tok_s": 159126.5}
|
| 32 |
+
{"step": 113620, "epoch": 0.722, "loss": 1.71385, "ppl": 5.55, "lr": 0.003, "grad": 0.0876, "tokens": 119110118400, "tok_s": 158751.5}
|
| 33 |
+
{"step": 113640, "epoch": 0.722, "loss": 1.66267, "ppl": 5.273, "lr": 0.003, "grad": 0.0894, "tokens": 119131084800, "tok_s": 159024.1}
|
| 34 |
+
{"step": 113660, "epoch": 0.722, "loss": 1.84263, "ppl": 6.313, "lr": 0.003, "grad": 0.0854, "tokens": 119152051200, "tok_s": 159082.8}
|
| 35 |
+
{"step": 113680, "epoch": 0.722, "loss": 1.77115, "ppl": 5.878, "lr": 0.003, "grad": 0.1382, "tokens": 119173017600, "tok_s": 158890.2}
|
| 36 |
+
{"step": 113700, "epoch": 0.722, "loss": 1.74136, "ppl": 5.705, "lr": 0.003, "grad": 0.1349, "tokens": 119193984000, "tok_s": 159019.4}
|
| 37 |
+
{"step": 113720, "epoch": 0.723, "loss": 1.66535, "ppl": 5.288, "lr": 0.003, "grad": 0.1052, "tokens": 119214950400, "tok_s": 159074.2}
|
| 38 |
+
{"step": 113740, "epoch": 0.723, "loss": 1.69789, "ppl": 5.462, "lr": 0.003, "grad": 0.0753, "tokens": 119235916800, "tok_s": 159056.5}
|
| 39 |
+
{"step": 113760, "epoch": 0.723, "loss": 1.7667, "ppl": 5.852, "lr": 0.003, "grad": 0.0999, "tokens": 119256883200, "tok_s": 159064.9}
|
| 40 |
+
{"step": 113780, "epoch": 0.723, "loss": 1.67702, "ppl": 5.35, "lr": 0.003, "grad": 0.1165, "tokens": 119277849600, "tok_s": 159030.2}
|
| 41 |
+
{"step": 113800, "epoch": 0.723, "loss": 1.693, "ppl": 5.436, "lr": 0.003, "grad": 0.0981, "tokens": 119298816000, "tok_s": 159047.8}
|
| 42 |
+
{"step": 113820, "epoch": 0.723, "loss": 1.74231, "ppl": 5.711, "lr": 0.003, "grad": 0.1045, "tokens": 119319782400, "tok_s": 159088.2}
|
| 43 |
+
{"step": 113840, "epoch": 0.723, "loss": 1.67498, "ppl": 5.339, "lr": 0.003, "grad": 0.1062, "tokens": 119340748800, "tok_s": 159079.4}
|
| 44 |
+
{"step": 113860, "epoch": 0.723, "loss": 1.7508, "ppl": 5.759, "lr": 0.003, "grad": 0.0925, "tokens": 119361715200, "tok_s": 159038.2}
|
| 45 |
+
{"step": 113880, "epoch": 0.724, "loss": 1.77965, "ppl": 5.928, "lr": 0.003, "grad": 0.1, "tokens": 119382681600, "tok_s": 158024.9}
|
| 46 |
+
{"step": 113900, "epoch": 0.724, "loss": 1.45134, "ppl": 4.269, "lr": 0.003, "grad": 0.0785, "tokens": 119403648000, "tok_s": 158567.9}
|
| 47 |
+
{"step": 113920, "epoch": 0.724, "loss": 1.67685, "ppl": 5.349, "lr": 0.003, "grad": 0.0789, "tokens": 119424614400, "tok_s": 158979.3}
|
| 48 |
+
{"step": 113940, "epoch": 0.724, "loss": 1.68904, "ppl": 5.414, "lr": 0.003, "grad": 0.0793, "tokens": 119445580800, "tok_s": 158486.4}
|
| 49 |
+
{"step": 113960, "epoch": 0.724, "loss": 1.7833, "ppl": 5.949, "lr": 0.003, "grad": 0.1064, "tokens": 119466547200, "tok_s": 158933.5}
|
| 50 |
+
{"step": 113980, "epoch": 0.724, "loss": 1.73486, "ppl": 5.668, "lr": 0.003, "grad": 0.062, "tokens": 119487513600, "tok_s": 159280.1}
|
| 51 |
+
{"step": 114000, "epoch": 0.724, "loss": 1.89109, "ppl": 6.627, "lr": 0.003, "grad": 0.157, "tokens": 119508480000, "tok_s": 159128.2}
|
| 52 |
+
{"step": 114000, "val_loss": 1.73226, "val_ppl": 5.653, "is_best": true}
|
| 53 |
+
{"step": 114020, "epoch": 0.724, "loss": 1.73621, "ppl": 5.676, "lr": 0.003, "grad": 0.1116, "tokens": 119529446400, "tok_s": 159164.3}
|
| 54 |
+
{"step": 114040, "epoch": 0.725, "loss": 1.67751, "ppl": 5.352, "lr": 0.003, "grad": 0.0817, "tokens": 119550412800, "tok_s": 158958.4}
|
| 55 |
+
{"step": 114060, "epoch": 0.725, "loss": 1.77483, "ppl": 5.899, "lr": 0.003, "grad": 0.0808, "tokens": 119571379200, "tok_s": 159128.4}
|
| 56 |
+
{"step": 114080, "epoch": 0.725, "loss": 1.72559, "ppl": 5.616, "lr": 0.003, "grad": 0.1378, "tokens": 119592345600, "tok_s": 159013.9}
|
| 57 |
+
{"step": 114100, "epoch": 0.725, "loss": 1.59786, "ppl": 4.942, "lr": 0.003, "grad": 0.1072, "tokens": 119613312000, "tok_s": 158691.3}
|
| 58 |
+
{"step": 114120, "epoch": 0.725, "loss": 1.87088, "ppl": 6.494, "lr": 0.003, "grad": 0.0884, "tokens": 119634278400, "tok_s": 159110.2}
|
| 59 |
+
{"step": 114140, "epoch": 0.725, "loss": 1.76409, "ppl": 5.836, "lr": 0.003, "grad": 0.0736, "tokens": 119655244800, "tok_s": 158581.2}
|
| 60 |
+
{"step": 114160, "epoch": 0.725, "loss": 1.74995, "ppl": 5.754, "lr": 0.003, "grad": 0.1573, "tokens": 119676211200, "tok_s": 159185.1}
|
| 61 |
+
{"step": 114180, "epoch": 0.725, "loss": 1.79485, "ppl": 6.019, "lr": 0.003, "grad": 0.1156, "tokens": 119697177600, "tok_s": 159065.4}
|
| 62 |
+
{"step": 114200, "epoch": 0.726, "loss": 1.70765, "ppl": 5.516, "lr": 0.003, "grad": 0.1655, "tokens": 119718144000, "tok_s": 158812.3}
|
| 63 |
+
{"step": 114220, "epoch": 0.726, "loss": 1.78097, "ppl": 5.936, "lr": 0.003, "grad": 0.0847, "tokens": 119739110400, "tok_s": 159085.4}
|
| 64 |
+
{"step": 114240, "epoch": 0.726, "loss": 1.69117, "ppl": 5.426, "lr": 0.003, "grad": 0.0751, "tokens": 119760076800, "tok_s": 159038.3}
|
| 65 |
+
{"step": 114260, "epoch": 0.726, "loss": 1.72168, "ppl": 5.594, "lr": 0.003, "grad": 0.0939, "tokens": 119781043200, "tok_s": 159063.8}
|
| 66 |
+
{"step": 114280, "epoch": 0.726, "loss": 1.60388, "ppl": 4.972, "lr": 0.003, "grad": 0.0936, "tokens": 119802009600, "tok_s": 159150.0}
|
| 67 |
+
{"step": 114300, "epoch": 0.726, "loss": 1.80309, "ppl": 6.068, "lr": 0.003, "grad": 0.1006, "tokens": 119822976000, "tok_s": 158938.0}
|
| 68 |
+
{"step": 114320, "epoch": 0.726, "loss": 1.74341, "ppl": 5.717, "lr": 0.003, "grad": 0.0973, "tokens": 119843942400, "tok_s": 158871.4}
|
| 69 |
+
{"step": 114340, "epoch": 0.726, "loss": 1.79538, "ppl": 6.022, "lr": 0.003, "grad": 0.1054, "tokens": 119864908800, "tok_s": 159036.5}
|
| 70 |
+
{"step": 114360, "epoch": 0.727, "loss": 1.734, "ppl": 5.663, "lr": 0.003, "grad": 0.1181, "tokens": 119885875200, "tok_s": 159074.4}
|
| 71 |
+
{"step": 114380, "epoch": 0.727, "loss": 1.84519, "ppl": 6.329, "lr": 0.003, "grad": 0.082, "tokens": 119906841600, "tok_s": 158405.4}
|
| 72 |
+
{"step": 114400, "epoch": 0.727, "loss": 1.81188, "ppl": 6.122, "lr": 0.003, "grad": 0.0674, "tokens": 119927808000, "tok_s": 159065.7}
|
| 73 |
+
{"step": 114420, "epoch": 0.727, "loss": 1.79445, "ppl": 6.016, "lr": 0.003, "grad": 0.1212, "tokens": 119948774400, "tok_s": 158971.6}
|
| 74 |
+
{"step": 114440, "epoch": 0.727, "loss": 1.73389, "ppl": 5.663, "lr": 0.003, "grad": 0.0638, "tokens": 119969740800, "tok_s": 158886.4}
|
| 75 |
+
{"step": 114460, "epoch": 0.727, "loss": 1.77551, "ppl": 5.903, "lr": 0.003, "grad": 0.1217, "tokens": 119990707200, "tok_s": 159156.8}
|
| 76 |
+
{"step": 114480, "epoch": 0.727, "loss": 1.82163, "ppl": 6.182, "lr": 0.003, "grad": 0.1224, "tokens": 120011673600, "tok_s": 158739.8}
|
| 77 |
+
{"step": 114500, "epoch": 0.727, "loss": 1.78047, "ppl": 5.933, "lr": 0.003, "grad": 0.0804, "tokens": 120032640000, "tok_s": 158808.7}
|
| 78 |
+
{"step": 114520, "epoch": 0.728, "loss": 1.78579, "ppl": 5.964, "lr": 0.003, "grad": 0.1135, "tokens": 120053606400, "tok_s": 159059.1}
|
| 79 |
+
{"step": 114540, "epoch": 0.728, "loss": 1.71035, "ppl": 5.531, "lr": 0.003, "grad": 0.0838, "tokens": 120074572800, "tok_s": 158981.3}
|
| 80 |
+
{"step": 114560, "epoch": 0.728, "loss": 1.79175, "ppl": 6.0, "lr": 0.003, "grad": 0.1555, "tokens": 120095539200, "tok_s": 158791.8}
|
| 81 |
+
{"step": 114580, "epoch": 0.728, "loss": 1.5919, "ppl": 4.913, "lr": 0.003, "grad": 0.0864, "tokens": 120116505600, "tok_s": 158876.7}
|
| 82 |
+
{"step": 114600, "epoch": 0.728, "loss": 1.7677, "ppl": 5.857, "lr": 0.003, "grad": 0.0918, "tokens": 120137472000, "tok_s": 159010.6}
|
| 83 |
+
{"step": 114620, "epoch": 0.728, "loss": 1.76809, "ppl": 5.86, "lr": 0.003, "grad": 0.0838, "tokens": 120158438400, "tok_s": 159039.8}
|
| 84 |
+
{"step": 114640, "epoch": 0.728, "loss": 1.73248, "ppl": 5.655, "lr": 0.003, "grad": 0.1019, "tokens": 120179404800, "tok_s": 158605.1}
|
| 85 |
+
{"step": 114660, "epoch": 0.729, "loss": 1.78428, "ppl": 5.955, "lr": 0.003, "grad": 0.0737, "tokens": 120200371200, "tok_s": 159053.2}
|
| 86 |
+
{"step": 114680, "epoch": 0.729, "loss": 1.75854, "ppl": 5.804, "lr": 0.003, "grad": 0.0847, "tokens": 120221337600, "tok_s": 158948.7}
|
| 87 |
+
{"step": 114700, "epoch": 0.729, "loss": 1.7305, "ppl": 5.643, "lr": 0.003, "grad": 0.0854, "tokens": 120242304000, "tok_s": 158333.8}
|
| 88 |
+
{"step": 114720, "epoch": 0.729, "loss": 1.70834, "ppl": 5.52, "lr": 0.003, "grad": 0.0769, "tokens": 120263270400, "tok_s": 158564.2}
|
| 89 |
+
{"step": 114740, "epoch": 0.729, "loss": 1.74569, "ppl": 5.73, "lr": 0.003, "grad": 0.1032, "tokens": 120284236800, "tok_s": 158797.5}
|
| 90 |
+
{"step": 114760, "epoch": 0.729, "loss": 1.63865, "ppl": 5.148, "lr": 0.003, "grad": 0.0829, "tokens": 120305203200, "tok_s": 158980.6}
|
| 91 |
+
{"step": 114780, "epoch": 0.729, "loss": 1.71827, "ppl": 5.575, "lr": 0.003, "grad": 0.1409, "tokens": 120326169600, "tok_s": 158993.3}
|
| 92 |
+
{"step": 114800, "epoch": 0.729, "loss": 1.73932, "ppl": 5.693, "lr": 0.003, "grad": 0.0752, "tokens": 120347136000, "tok_s": 159065.8}
|
| 93 |
+
{"step": 114820, "epoch": 0.73, "loss": 1.76451, "ppl": 5.839, "lr": 0.003, "grad": 0.113, "tokens": 120368102400, "tok_s": 159110.5}
|
| 94 |
+
{"step": 114840, "epoch": 0.73, "loss": 1.7788, "ppl": 5.923, "lr": 0.003, "grad": 0.0734, "tokens": 120389068800, "tok_s": 158867.6}
|
| 95 |
+
{"step": 114860, "epoch": 0.73, "loss": 1.78937, "ppl": 5.986, "lr": 0.003, "grad": 0.0778, "tokens": 120410035200, "tok_s": 158720.1}
|
| 96 |
+
{"step": 114880, "epoch": 0.73, "loss": 1.76945, "ppl": 5.868, "lr": 0.003, "grad": 0.1273, "tokens": 120431001600, "tok_s": 158880.3}
|
| 97 |
+
{"step": 114900, "epoch": 0.73, "loss": 1.75438, "ppl": 5.78, "lr": 0.003, "grad": 0.0804, "tokens": 120451968000, "tok_s": 159036.7}
|
| 98 |
+
{"step": 114920, "epoch": 0.73, "loss": 1.7785, "ppl": 5.921, "lr": 0.003, "grad": 0.1014, "tokens": 120472934400, "tok_s": 159052.1}
|
| 99 |
+
{"step": 114940, "epoch": 0.73, "loss": 1.72752, "ppl": 5.627, "lr": 0.003, "grad": 0.0834, "tokens": 120493900800, "tok_s": 158927.0}
|
| 100 |
+
{"step": 114960, "epoch": 0.73, "loss": 1.75104, "ppl": 5.761, "lr": 0.003, "grad": 0.0814, "tokens": 120514867200, "tok_s": 158793.7}
|
| 101 |
+
{"step": 114980, "epoch": 0.731, "loss": 1.79737, "ppl": 6.034, "lr": 0.003, "grad": 0.1131, "tokens": 120535833600, "tok_s": 158841.1}
|
| 102 |
+
{"step": 115000, "epoch": 0.731, "loss": 1.72563, "ppl": 5.616, "lr": 0.003, "grad": 0.0991, "tokens": 120556800000, "tok_s": 158972.4}
|
| 103 |
+
{"step": 115000, "val_loss": 1.74251, "val_ppl": 5.712, "is_best": false}
|
logs/log_116000.jsonl
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 113000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-05T06:28:33.908905"}
|
| 2 |
+
{"step": 113020, "epoch": 0.718, "loss": 1.73974, "ppl": 5.696, "lr": 0.003, "grad": 0.1063, "tokens": 118481126400, "tok_s": 158492.1}
|
| 3 |
+
{"step": 113040, "epoch": 0.718, "loss": 1.74188, "ppl": 5.708, "lr": 0.003, "grad": 0.0846, "tokens": 118502092800, "tok_s": 158868.7}
|
| 4 |
+
{"step": 113060, "epoch": 0.718, "loss": 1.71566, "ppl": 5.56, "lr": 0.003, "grad": 0.1073, "tokens": 118523059200, "tok_s": 159149.1}
|
| 5 |
+
{"step": 113080, "epoch": 0.718, "loss": 1.61321, "ppl": 5.019, "lr": 0.003, "grad": 0.1108, "tokens": 118544025600, "tok_s": 159129.0}
|
| 6 |
+
{"step": 113100, "epoch": 0.719, "loss": 1.76739, "ppl": 5.856, "lr": 0.003, "grad": 0.102, "tokens": 118564992000, "tok_s": 159208.2}
|
| 7 |
+
{"step": 113120, "epoch": 0.719, "loss": 1.72873, "ppl": 5.634, "lr": 0.003, "grad": 0.0831, "tokens": 118585958400, "tok_s": 159042.0}
|
| 8 |
+
{"step": 113140, "epoch": 0.719, "loss": 1.74315, "ppl": 5.715, "lr": 0.003, "grad": 0.1, "tokens": 118606924800, "tok_s": 159134.1}
|
| 9 |
+
{"step": 113160, "epoch": 0.719, "loss": 1.67597, "ppl": 5.344, "lr": 0.003, "grad": 0.092, "tokens": 118627891200, "tok_s": 159165.1}
|
| 10 |
+
{"step": 113180, "epoch": 0.719, "loss": 1.62867, "ppl": 5.097, "lr": 0.003, "grad": 0.0778, "tokens": 118648857600, "tok_s": 158915.5}
|
| 11 |
+
{"step": 113200, "epoch": 0.719, "loss": 1.59332, "ppl": 4.92, "lr": 0.003, "grad": 0.1523, "tokens": 118669824000, "tok_s": 159228.9}
|
| 12 |
+
{"step": 113220, "epoch": 0.719, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.1081, "tokens": 118690790400, "tok_s": 159106.3}
|
| 13 |
+
{"step": 113240, "epoch": 0.719, "loss": 1.70175, "ppl": 5.484, "lr": 0.003, "grad": 0.0778, "tokens": 118711756800, "tok_s": 159104.9}
|
| 14 |
+
{"step": 113260, "epoch": 0.72, "loss": 1.76013, "ppl": 5.813, "lr": 0.003, "grad": 0.0838, "tokens": 118732723200, "tok_s": 159141.8}
|
| 15 |
+
{"step": 113280, "epoch": 0.72, "loss": 1.71039, "ppl": 5.531, "lr": 0.003, "grad": 0.0872, "tokens": 118753689600, "tok_s": 158455.7}
|
| 16 |
+
{"step": 113300, "epoch": 0.72, "loss": 1.75435, "ppl": 5.78, "lr": 0.003, "grad": 0.078, "tokens": 118774656000, "tok_s": 159162.6}
|
| 17 |
+
{"step": 113320, "epoch": 0.72, "loss": 1.7597, "ppl": 5.811, "lr": 0.003, "grad": 0.0796, "tokens": 118795622400, "tok_s": 158885.5}
|
| 18 |
+
{"step": 113340, "epoch": 0.72, "loss": 1.72363, "ppl": 5.605, "lr": 0.003, "grad": 0.1116, "tokens": 118816588800, "tok_s": 159070.6}
|
| 19 |
+
{"step": 113360, "epoch": 0.72, "loss": 1.77175, "ppl": 5.881, "lr": 0.003, "grad": 0.0751, "tokens": 118837555200, "tok_s": 158738.5}
|
| 20 |
+
{"step": 113380, "epoch": 0.72, "loss": 1.67999, "ppl": 5.366, "lr": 0.003, "grad": 0.0561, "tokens": 118858521600, "tok_s": 159053.7}
|
| 21 |
+
{"step": 113400, "epoch": 0.721, "loss": 1.78069, "ppl": 5.934, "lr": 0.003, "grad": 0.0864, "tokens": 118879488000, "tok_s": 159167.9}
|
| 22 |
+
{"step": 113420, "epoch": 0.721, "loss": 1.7595, "ppl": 5.81, "lr": 0.003, "grad": 0.0752, "tokens": 118900454400, "tok_s": 159167.7}
|
| 23 |
+
{"step": 113440, "epoch": 0.721, "loss": 1.67152, "ppl": 5.32, "lr": 0.003, "grad": 0.0591, "tokens": 118921420800, "tok_s": 159154.3}
|
| 24 |
+
{"step": 113460, "epoch": 0.721, "loss": 1.81131, "ppl": 6.118, "lr": 0.003, "grad": 0.0707, "tokens": 118942387200, "tok_s": 159200.8}
|
| 25 |
+
{"step": 113480, "epoch": 0.721, "loss": 1.80639, "ppl": 6.088, "lr": 0.003, "grad": 0.1177, "tokens": 118963353600, "tok_s": 158645.5}
|
| 26 |
+
{"step": 113500, "epoch": 0.721, "loss": 1.90369, "ppl": 6.711, "lr": 0.003, "grad": 0.1204, "tokens": 118984320000, "tok_s": 159158.8}
|
| 27 |
+
{"step": 113520, "epoch": 0.721, "loss": 1.76353, "ppl": 5.833, "lr": 0.003, "grad": 0.0801, "tokens": 119005286400, "tok_s": 159064.2}
|
| 28 |
+
{"step": 113540, "epoch": 0.721, "loss": 1.65881, "ppl": 5.253, "lr": 0.003, "grad": 0.0753, "tokens": 119026252800, "tok_s": 158729.6}
|
| 29 |
+
{"step": 113560, "epoch": 0.722, "loss": 1.6794, "ppl": 5.362, "lr": 0.003, "grad": 0.0962, "tokens": 119047219200, "tok_s": 159102.7}
|
| 30 |
+
{"step": 113580, "epoch": 0.722, "loss": 1.70352, "ppl": 5.493, "lr": 0.003, "grad": 0.0809, "tokens": 119068185600, "tok_s": 159052.4}
|
| 31 |
+
{"step": 113600, "epoch": 0.722, "loss": 1.64007, "ppl": 5.156, "lr": 0.003, "grad": 0.0822, "tokens": 119089152000, "tok_s": 159126.5}
|
| 32 |
+
{"step": 113620, "epoch": 0.722, "loss": 1.71385, "ppl": 5.55, "lr": 0.003, "grad": 0.0876, "tokens": 119110118400, "tok_s": 158751.5}
|
| 33 |
+
{"step": 113640, "epoch": 0.722, "loss": 1.66267, "ppl": 5.273, "lr": 0.003, "grad": 0.0894, "tokens": 119131084800, "tok_s": 159024.1}
|
| 34 |
+
{"step": 113660, "epoch": 0.722, "loss": 1.84263, "ppl": 6.313, "lr": 0.003, "grad": 0.0854, "tokens": 119152051200, "tok_s": 159082.8}
|
| 35 |
+
{"step": 113680, "epoch": 0.722, "loss": 1.77115, "ppl": 5.878, "lr": 0.003, "grad": 0.1382, "tokens": 119173017600, "tok_s": 158890.2}
|
| 36 |
+
{"step": 113700, "epoch": 0.722, "loss": 1.74136, "ppl": 5.705, "lr": 0.003, "grad": 0.1349, "tokens": 119193984000, "tok_s": 159019.4}
|
| 37 |
+
{"step": 113720, "epoch": 0.723, "loss": 1.66535, "ppl": 5.288, "lr": 0.003, "grad": 0.1052, "tokens": 119214950400, "tok_s": 159074.2}
|
| 38 |
+
{"step": 113740, "epoch": 0.723, "loss": 1.69789, "ppl": 5.462, "lr": 0.003, "grad": 0.0753, "tokens": 119235916800, "tok_s": 159056.5}
|
| 39 |
+
{"step": 113760, "epoch": 0.723, "loss": 1.7667, "ppl": 5.852, "lr": 0.003, "grad": 0.0999, "tokens": 119256883200, "tok_s": 159064.9}
|
| 40 |
+
{"step": 113780, "epoch": 0.723, "loss": 1.67702, "ppl": 5.35, "lr": 0.003, "grad": 0.1165, "tokens": 119277849600, "tok_s": 159030.2}
|
| 41 |
+
{"step": 113800, "epoch": 0.723, "loss": 1.693, "ppl": 5.436, "lr": 0.003, "grad": 0.0981, "tokens": 119298816000, "tok_s": 159047.8}
|
| 42 |
+
{"step": 113820, "epoch": 0.723, "loss": 1.74231, "ppl": 5.711, "lr": 0.003, "grad": 0.1045, "tokens": 119319782400, "tok_s": 159088.2}
|
| 43 |
+
{"step": 113840, "epoch": 0.723, "loss": 1.67498, "ppl": 5.339, "lr": 0.003, "grad": 0.1062, "tokens": 119340748800, "tok_s": 159079.4}
|
| 44 |
+
{"step": 113860, "epoch": 0.723, "loss": 1.7508, "ppl": 5.759, "lr": 0.003, "grad": 0.0925, "tokens": 119361715200, "tok_s": 159038.2}
|
| 45 |
+
{"step": 113880, "epoch": 0.724, "loss": 1.77965, "ppl": 5.928, "lr": 0.003, "grad": 0.1, "tokens": 119382681600, "tok_s": 158024.9}
|
| 46 |
+
{"step": 113900, "epoch": 0.724, "loss": 1.45134, "ppl": 4.269, "lr": 0.003, "grad": 0.0785, "tokens": 119403648000, "tok_s": 158567.9}
|
| 47 |
+
{"step": 113920, "epoch": 0.724, "loss": 1.67685, "ppl": 5.349, "lr": 0.003, "grad": 0.0789, "tokens": 119424614400, "tok_s": 158979.3}
|
| 48 |
+
{"step": 113940, "epoch": 0.724, "loss": 1.68904, "ppl": 5.414, "lr": 0.003, "grad": 0.0793, "tokens": 119445580800, "tok_s": 158486.4}
|
| 49 |
+
{"step": 113960, "epoch": 0.724, "loss": 1.7833, "ppl": 5.949, "lr": 0.003, "grad": 0.1064, "tokens": 119466547200, "tok_s": 158933.5}
|
| 50 |
+
{"step": 113980, "epoch": 0.724, "loss": 1.73486, "ppl": 5.668, "lr": 0.003, "grad": 0.062, "tokens": 119487513600, "tok_s": 159280.1}
|
| 51 |
+
{"step": 114000, "epoch": 0.724, "loss": 1.89109, "ppl": 6.627, "lr": 0.003, "grad": 0.157, "tokens": 119508480000, "tok_s": 159128.2}
|
| 52 |
+
{"step": 114000, "val_loss": 1.73226, "val_ppl": 5.653, "is_best": true}
|
| 53 |
+
{"step": 114020, "epoch": 0.724, "loss": 1.73621, "ppl": 5.676, "lr": 0.003, "grad": 0.1116, "tokens": 119529446400, "tok_s": 159164.3}
|
| 54 |
+
{"step": 114040, "epoch": 0.725, "loss": 1.67751, "ppl": 5.352, "lr": 0.003, "grad": 0.0817, "tokens": 119550412800, "tok_s": 158958.4}
|
| 55 |
+
{"step": 114060, "epoch": 0.725, "loss": 1.77483, "ppl": 5.899, "lr": 0.003, "grad": 0.0808, "tokens": 119571379200, "tok_s": 159128.4}
|
| 56 |
+
{"step": 114080, "epoch": 0.725, "loss": 1.72559, "ppl": 5.616, "lr": 0.003, "grad": 0.1378, "tokens": 119592345600, "tok_s": 159013.9}
|
| 57 |
+
{"step": 114100, "epoch": 0.725, "loss": 1.59786, "ppl": 4.942, "lr": 0.003, "grad": 0.1072, "tokens": 119613312000, "tok_s": 158691.3}
|
| 58 |
+
{"step": 114120, "epoch": 0.725, "loss": 1.87088, "ppl": 6.494, "lr": 0.003, "grad": 0.0884, "tokens": 119634278400, "tok_s": 159110.2}
|
| 59 |
+
{"step": 114140, "epoch": 0.725, "loss": 1.76409, "ppl": 5.836, "lr": 0.003, "grad": 0.0736, "tokens": 119655244800, "tok_s": 158581.2}
|
| 60 |
+
{"step": 114160, "epoch": 0.725, "loss": 1.74995, "ppl": 5.754, "lr": 0.003, "grad": 0.1573, "tokens": 119676211200, "tok_s": 159185.1}
|
| 61 |
+
{"step": 114180, "epoch": 0.725, "loss": 1.79485, "ppl": 6.019, "lr": 0.003, "grad": 0.1156, "tokens": 119697177600, "tok_s": 159065.4}
|
| 62 |
+
{"step": 114200, "epoch": 0.726, "loss": 1.70765, "ppl": 5.516, "lr": 0.003, "grad": 0.1655, "tokens": 119718144000, "tok_s": 158812.3}
|
| 63 |
+
{"step": 114220, "epoch": 0.726, "loss": 1.78097, "ppl": 5.936, "lr": 0.003, "grad": 0.0847, "tokens": 119739110400, "tok_s": 159085.4}
|
| 64 |
+
{"step": 114240, "epoch": 0.726, "loss": 1.69117, "ppl": 5.426, "lr": 0.003, "grad": 0.0751, "tokens": 119760076800, "tok_s": 159038.3}
|
| 65 |
+
{"step": 114260, "epoch": 0.726, "loss": 1.72168, "ppl": 5.594, "lr": 0.003, "grad": 0.0939, "tokens": 119781043200, "tok_s": 159063.8}
|
| 66 |
+
{"step": 114280, "epoch": 0.726, "loss": 1.60388, "ppl": 4.972, "lr": 0.003, "grad": 0.0936, "tokens": 119802009600, "tok_s": 159150.0}
|
| 67 |
+
{"step": 114300, "epoch": 0.726, "loss": 1.80309, "ppl": 6.068, "lr": 0.003, "grad": 0.1006, "tokens": 119822976000, "tok_s": 158938.0}
|
| 68 |
+
{"step": 114320, "epoch": 0.726, "loss": 1.74341, "ppl": 5.717, "lr": 0.003, "grad": 0.0973, "tokens": 119843942400, "tok_s": 158871.4}
|
| 69 |
+
{"step": 114340, "epoch": 0.726, "loss": 1.79538, "ppl": 6.022, "lr": 0.003, "grad": 0.1054, "tokens": 119864908800, "tok_s": 159036.5}
|
| 70 |
+
{"step": 114360, "epoch": 0.727, "loss": 1.734, "ppl": 5.663, "lr": 0.003, "grad": 0.1181, "tokens": 119885875200, "tok_s": 159074.4}
|
| 71 |
+
{"step": 114380, "epoch": 0.727, "loss": 1.84519, "ppl": 6.329, "lr": 0.003, "grad": 0.082, "tokens": 119906841600, "tok_s": 158405.4}
|
| 72 |
+
{"step": 114400, "epoch": 0.727, "loss": 1.81188, "ppl": 6.122, "lr": 0.003, "grad": 0.0674, "tokens": 119927808000, "tok_s": 159065.7}
|
| 73 |
+
{"step": 114420, "epoch": 0.727, "loss": 1.79445, "ppl": 6.016, "lr": 0.003, "grad": 0.1212, "tokens": 119948774400, "tok_s": 158971.6}
|
| 74 |
+
{"step": 114440, "epoch": 0.727, "loss": 1.73389, "ppl": 5.663, "lr": 0.003, "grad": 0.0638, "tokens": 119969740800, "tok_s": 158886.4}
|
| 75 |
+
{"step": 114460, "epoch": 0.727, "loss": 1.77551, "ppl": 5.903, "lr": 0.003, "grad": 0.1217, "tokens": 119990707200, "tok_s": 159156.8}
|
| 76 |
+
{"step": 114480, "epoch": 0.727, "loss": 1.82163, "ppl": 6.182, "lr": 0.003, "grad": 0.1224, "tokens": 120011673600, "tok_s": 158739.8}
|
| 77 |
+
{"step": 114500, "epoch": 0.727, "loss": 1.78047, "ppl": 5.933, "lr": 0.003, "grad": 0.0804, "tokens": 120032640000, "tok_s": 158808.7}
|
| 78 |
+
{"step": 114520, "epoch": 0.728, "loss": 1.78579, "ppl": 5.964, "lr": 0.003, "grad": 0.1135, "tokens": 120053606400, "tok_s": 159059.1}
|
| 79 |
+
{"step": 114540, "epoch": 0.728, "loss": 1.71035, "ppl": 5.531, "lr": 0.003, "grad": 0.0838, "tokens": 120074572800, "tok_s": 158981.3}
|
| 80 |
+
{"step": 114560, "epoch": 0.728, "loss": 1.79175, "ppl": 6.0, "lr": 0.003, "grad": 0.1555, "tokens": 120095539200, "tok_s": 158791.8}
|
| 81 |
+
{"step": 114580, "epoch": 0.728, "loss": 1.5919, "ppl": 4.913, "lr": 0.003, "grad": 0.0864, "tokens": 120116505600, "tok_s": 158876.7}
|
| 82 |
+
{"step": 114600, "epoch": 0.728, "loss": 1.7677, "ppl": 5.857, "lr": 0.003, "grad": 0.0918, "tokens": 120137472000, "tok_s": 159010.6}
|
| 83 |
+
{"step": 114620, "epoch": 0.728, "loss": 1.76809, "ppl": 5.86, "lr": 0.003, "grad": 0.0838, "tokens": 120158438400, "tok_s": 159039.8}
|
| 84 |
+
{"step": 114640, "epoch": 0.728, "loss": 1.73248, "ppl": 5.655, "lr": 0.003, "grad": 0.1019, "tokens": 120179404800, "tok_s": 158605.1}
|
| 85 |
+
{"step": 114660, "epoch": 0.729, "loss": 1.78428, "ppl": 5.955, "lr": 0.003, "grad": 0.0737, "tokens": 120200371200, "tok_s": 159053.2}
|
| 86 |
+
{"step": 114680, "epoch": 0.729, "loss": 1.75854, "ppl": 5.804, "lr": 0.003, "grad": 0.0847, "tokens": 120221337600, "tok_s": 158948.7}
|
| 87 |
+
{"step": 114700, "epoch": 0.729, "loss": 1.7305, "ppl": 5.643, "lr": 0.003, "grad": 0.0854, "tokens": 120242304000, "tok_s": 158333.8}
|
| 88 |
+
{"step": 114720, "epoch": 0.729, "loss": 1.70834, "ppl": 5.52, "lr": 0.003, "grad": 0.0769, "tokens": 120263270400, "tok_s": 158564.2}
|
| 89 |
+
{"step": 114740, "epoch": 0.729, "loss": 1.74569, "ppl": 5.73, "lr": 0.003, "grad": 0.1032, "tokens": 120284236800, "tok_s": 158797.5}
|
| 90 |
+
{"step": 114760, "epoch": 0.729, "loss": 1.63865, "ppl": 5.148, "lr": 0.003, "grad": 0.0829, "tokens": 120305203200, "tok_s": 158980.6}
|
| 91 |
+
{"step": 114780, "epoch": 0.729, "loss": 1.71827, "ppl": 5.575, "lr": 0.003, "grad": 0.1409, "tokens": 120326169600, "tok_s": 158993.3}
|
| 92 |
+
{"step": 114800, "epoch": 0.729, "loss": 1.73932, "ppl": 5.693, "lr": 0.003, "grad": 0.0752, "tokens": 120347136000, "tok_s": 159065.8}
|
| 93 |
+
{"step": 114820, "epoch": 0.73, "loss": 1.76451, "ppl": 5.839, "lr": 0.003, "grad": 0.113, "tokens": 120368102400, "tok_s": 159110.5}
|
| 94 |
+
{"step": 114840, "epoch": 0.73, "loss": 1.7788, "ppl": 5.923, "lr": 0.003, "grad": 0.0734, "tokens": 120389068800, "tok_s": 158867.6}
|
| 95 |
+
{"step": 114860, "epoch": 0.73, "loss": 1.78937, "ppl": 5.986, "lr": 0.003, "grad": 0.0778, "tokens": 120410035200, "tok_s": 158720.1}
|
| 96 |
+
{"step": 114880, "epoch": 0.73, "loss": 1.76945, "ppl": 5.868, "lr": 0.003, "grad": 0.1273, "tokens": 120431001600, "tok_s": 158880.3}
|
| 97 |
+
{"step": 114900, "epoch": 0.73, "loss": 1.75438, "ppl": 5.78, "lr": 0.003, "grad": 0.0804, "tokens": 120451968000, "tok_s": 159036.7}
|
| 98 |
+
{"step": 114920, "epoch": 0.73, "loss": 1.7785, "ppl": 5.921, "lr": 0.003, "grad": 0.1014, "tokens": 120472934400, "tok_s": 159052.1}
|
| 99 |
+
{"step": 114940, "epoch": 0.73, "loss": 1.72752, "ppl": 5.627, "lr": 0.003, "grad": 0.0834, "tokens": 120493900800, "tok_s": 158927.0}
|
| 100 |
+
{"step": 114960, "epoch": 0.73, "loss": 1.75104, "ppl": 5.761, "lr": 0.003, "grad": 0.0814, "tokens": 120514867200, "tok_s": 158793.7}
|
| 101 |
+
{"step": 114980, "epoch": 0.731, "loss": 1.79737, "ppl": 6.034, "lr": 0.003, "grad": 0.1131, "tokens": 120535833600, "tok_s": 158841.1}
|
| 102 |
+
{"step": 115000, "epoch": 0.731, "loss": 1.72563, "ppl": 5.616, "lr": 0.003, "grad": 0.0991, "tokens": 120556800000, "tok_s": 158972.4}
|
| 103 |
+
{"step": 115000, "val_loss": 1.74251, "val_ppl": 5.712, "is_best": false}
|
| 104 |
+
{"step": 115020, "epoch": 0.731, "loss": 1.76095, "ppl": 5.818, "lr": 0.003, "grad": 0.1495, "tokens": 120577766400, "tok_s": 158306.4}
|
| 105 |
+
{"step": 115040, "epoch": 0.731, "loss": 1.75017, "ppl": 5.756, "lr": 0.003, "grad": 0.0803, "tokens": 120598732800, "tok_s": 159033.7}
|
| 106 |
+
{"step": 115060, "epoch": 0.731, "loss": 1.69637, "ppl": 5.454, "lr": 0.003, "grad": 0.0703, "tokens": 120619699200, "tok_s": 159083.2}
|
| 107 |
+
{"step": 115080, "epoch": 0.731, "loss": 1.7665, "ppl": 5.85, "lr": 0.003, "grad": 0.1583, "tokens": 120640665600, "tok_s": 158597.5}
|
| 108 |
+
{"step": 115100, "epoch": 0.731, "loss": 1.7566, "ppl": 5.793, "lr": 0.003, "grad": 0.0979, "tokens": 120661632000, "tok_s": 158933.4}
|
| 109 |
+
{"step": 115120, "epoch": 0.731, "loss": 1.82904, "ppl": 6.228, "lr": 0.003, "grad": 0.0963, "tokens": 120682598400, "tok_s": 159013.9}
|
| 110 |
+
{"step": 115140, "epoch": 0.732, "loss": 1.77106, "ppl": 5.877, "lr": 0.003, "grad": 0.0801, "tokens": 120703564800, "tok_s": 158756.2}
|
| 111 |
+
{"step": 115160, "epoch": 0.732, "loss": 1.7239, "ppl": 5.606, "lr": 0.003, "grad": 0.0624, "tokens": 120724531200, "tok_s": 158983.3}
|
| 112 |
+
{"step": 115180, "epoch": 0.732, "loss": 1.7504, "ppl": 5.757, "lr": 0.003, "grad": 0.1288, "tokens": 120745497600, "tok_s": 158951.9}
|
| 113 |
+
{"step": 115200, "epoch": 0.732, "loss": 1.80402, "ppl": 6.074, "lr": 0.003, "grad": 0.1111, "tokens": 120766464000, "tok_s": 158157.1}
|
| 114 |
+
{"step": 115220, "epoch": 0.732, "loss": 1.70762, "ppl": 5.516, "lr": 0.003, "grad": 0.0672, "tokens": 120787430400, "tok_s": 158909.4}
|
| 115 |
+
{"step": 115240, "epoch": 0.732, "loss": 1.75081, "ppl": 5.759, "lr": 0.003, "grad": 0.1099, "tokens": 120808396800, "tok_s": 158974.1}
|
| 116 |
+
{"step": 115260, "epoch": 0.732, "loss": 1.66476, "ppl": 5.284, "lr": 0.003, "grad": 0.0723, "tokens": 120829363200, "tok_s": 158565.8}
|
| 117 |
+
{"step": 115280, "epoch": 0.732, "loss": 1.76276, "ppl": 5.828, "lr": 0.003, "grad": 0.055, "tokens": 120850329600, "tok_s": 158962.6}
|
| 118 |
+
{"step": 115300, "epoch": 0.733, "loss": 1.78751, "ppl": 5.975, "lr": 0.003, "grad": 0.081, "tokens": 120871296000, "tok_s": 158890.7}
|
| 119 |
+
{"step": 115320, "epoch": 0.733, "loss": 1.66815, "ppl": 5.302, "lr": 0.003, "grad": 0.0606, "tokens": 120892262400, "tok_s": 158953.0}
|
| 120 |
+
{"step": 115340, "epoch": 0.733, "loss": 1.63292, "ppl": 5.119, "lr": 0.003, "grad": 0.0829, "tokens": 120913228800, "tok_s": 158889.8}
|
| 121 |
+
{"step": 115360, "epoch": 0.733, "loss": 1.76008, "ppl": 5.813, "lr": 0.003, "grad": 0.1001, "tokens": 120934195200, "tok_s": 158990.0}
|
| 122 |
+
{"step": 115380, "epoch": 0.733, "loss": 1.73241, "ppl": 5.654, "lr": 0.003, "grad": 0.0689, "tokens": 120955161600, "tok_s": 159126.8}
|
| 123 |
+
{"step": 115400, "epoch": 0.733, "loss": 1.65046, "ppl": 5.209, "lr": 0.003, "grad": 0.0858, "tokens": 120976128000, "tok_s": 159175.1}
|
| 124 |
+
{"step": 115420, "epoch": 0.733, "loss": 1.66761, "ppl": 5.299, "lr": 0.003, "grad": 0.0863, "tokens": 120997094400, "tok_s": 158915.4}
|
| 125 |
+
{"step": 115440, "epoch": 0.733, "loss": 1.85483, "ppl": 6.391, "lr": 0.003, "grad": 0.119, "tokens": 121018060800, "tok_s": 159069.3}
|
| 126 |
+
{"step": 115460, "epoch": 0.734, "loss": 1.64881, "ppl": 5.201, "lr": 0.003, "grad": 0.0977, "tokens": 121039027200, "tok_s": 158967.5}
|
| 127 |
+
{"step": 115480, "epoch": 0.734, "loss": 1.72542, "ppl": 5.615, "lr": 0.003, "grad": 0.0658, "tokens": 121059993600, "tok_s": 159130.9}
|
| 128 |
+
{"step": 115500, "epoch": 0.734, "loss": 1.69981, "ppl": 5.473, "lr": 0.003, "grad": 0.0547, "tokens": 121080960000, "tok_s": 159090.4}
|
| 129 |
+
{"step": 115520, "epoch": 0.734, "loss": 1.71325, "ppl": 5.547, "lr": 0.003, "grad": 0.0535, "tokens": 121101926400, "tok_s": 158661.9}
|
| 130 |
+
{"step": 115540, "epoch": 0.734, "loss": 1.71585, "ppl": 5.561, "lr": 0.003, "grad": 0.076, "tokens": 121122892800, "tok_s": 159083.5}
|
| 131 |
+
{"step": 115560, "epoch": 0.734, "loss": 1.81402, "ppl": 6.135, "lr": 0.003, "grad": 0.1009, "tokens": 121143859200, "tok_s": 159142.5}
|
| 132 |
+
{"step": 115580, "epoch": 0.734, "loss": 1.74548, "ppl": 5.729, "lr": 0.003, "grad": 0.0976, "tokens": 121164825600, "tok_s": 158682.1}
|
| 133 |
+
{"step": 115600, "epoch": 0.734, "loss": 1.77462, "ppl": 5.898, "lr": 0.003, "grad": 0.0858, "tokens": 121185792000, "tok_s": 159262.0}
|
| 134 |
+
{"step": 115620, "epoch": 0.735, "loss": 1.7396, "ppl": 5.695, "lr": 0.003, "grad": 0.1201, "tokens": 121206758400, "tok_s": 158993.1}
|
| 135 |
+
{"step": 115640, "epoch": 0.735, "loss": 1.77629, "ppl": 5.908, "lr": 0.003, "grad": 0.0664, "tokens": 121227724800, "tok_s": 159152.3}
|
| 136 |
+
{"step": 115660, "epoch": 0.735, "loss": 1.64546, "ppl": 5.183, "lr": 0.003, "grad": 0.1268, "tokens": 121248691200, "tok_s": 159114.1}
|
| 137 |
+
{"step": 115680, "epoch": 0.735, "loss": 1.7395, "ppl": 5.695, "lr": 0.003, "grad": 0.0946, "tokens": 121269657600, "tok_s": 158968.0}
|
| 138 |
+
{"step": 115700, "epoch": 0.735, "loss": 1.69873, "ppl": 5.467, "lr": 0.003, "grad": 0.1181, "tokens": 121290624000, "tok_s": 158996.3}
|
| 139 |
+
{"step": 115720, "epoch": 0.735, "loss": 1.78564, "ppl": 5.963, "lr": 0.003, "grad": 0.097, "tokens": 121311590400, "tok_s": 159080.3}
|
| 140 |
+
{"step": 115740, "epoch": 0.735, "loss": 1.60998, "ppl": 5.003, "lr": 0.003, "grad": 0.1052, "tokens": 121332556800, "tok_s": 158828.3}
|
| 141 |
+
{"step": 115760, "epoch": 0.735, "loss": 1.77713, "ppl": 5.913, "lr": 0.003, "grad": 0.0884, "tokens": 121353523200, "tok_s": 158637.6}
|
| 142 |
+
{"step": 115780, "epoch": 0.736, "loss": 1.78343, "ppl": 5.95, "lr": 0.003, "grad": 0.1031, "tokens": 121374489600, "tok_s": 158460.2}
|
| 143 |
+
{"step": 115800, "epoch": 0.736, "loss": 1.75974, "ppl": 5.811, "lr": 0.003, "grad": 0.1039, "tokens": 121395456000, "tok_s": 158956.9}
|
| 144 |
+
{"step": 115820, "epoch": 0.736, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.089, "tokens": 121416422400, "tok_s": 158579.3}
|
| 145 |
+
{"step": 115840, "epoch": 0.736, "loss": 1.77844, "ppl": 5.921, "lr": 0.003, "grad": 0.1064, "tokens": 121437388800, "tok_s": 159003.3}
|
| 146 |
+
{"step": 115860, "epoch": 0.736, "loss": 1.80231, "ppl": 6.064, "lr": 0.003, "grad": 0.078, "tokens": 121458355200, "tok_s": 159003.1}
|
| 147 |
+
{"step": 115880, "epoch": 0.736, "loss": 1.71566, "ppl": 5.56, "lr": 0.003, "grad": 0.0837, "tokens": 121479321600, "tok_s": 158575.5}
|
| 148 |
+
{"step": 115900, "epoch": 0.736, "loss": 1.77074, "ppl": 5.875, "lr": 0.003, "grad": 0.0898, "tokens": 121500288000, "tok_s": 158867.6}
|
| 149 |
+
{"step": 115920, "epoch": 0.737, "loss": 1.76584, "ppl": 5.847, "lr": 0.003, "grad": 0.086, "tokens": 121521254400, "tok_s": 158639.9}
|
| 150 |
+
{"step": 115940, "epoch": 0.737, "loss": 1.73363, "ppl": 5.661, "lr": 0.003, "grad": 0.1066, "tokens": 121542220800, "tok_s": 158912.7}
|
| 151 |
+
{"step": 115960, "epoch": 0.737, "loss": 1.78966, "ppl": 5.987, "lr": 0.003, "grad": 0.0879, "tokens": 121563187200, "tok_s": 159044.0}
|
| 152 |
+
{"step": 115980, "epoch": 0.737, "loss": 1.76167, "ppl": 5.822, "lr": 0.003, "grad": 0.1034, "tokens": 121584153600, "tok_s": 159061.2}
|
| 153 |
+
{"step": 116000, "epoch": 0.737, "loss": 1.76646, "ppl": 5.85, "lr": 0.003, "grad": 0.1287, "tokens": 121605120000, "tok_s": 159044.7}
|
| 154 |
+
{"step": 116000, "val_loss": 1.75047, "val_ppl": 5.757, "is_best": false}
|
logs/log_117000.jsonl
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 113000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-05T06:28:33.908905"}
|
| 2 |
+
{"step": 113020, "epoch": 0.718, "loss": 1.73974, "ppl": 5.696, "lr": 0.003, "grad": 0.1063, "tokens": 118481126400, "tok_s": 158492.1}
|
| 3 |
+
{"step": 113040, "epoch": 0.718, "loss": 1.74188, "ppl": 5.708, "lr": 0.003, "grad": 0.0846, "tokens": 118502092800, "tok_s": 158868.7}
|
| 4 |
+
{"step": 113060, "epoch": 0.718, "loss": 1.71566, "ppl": 5.56, "lr": 0.003, "grad": 0.1073, "tokens": 118523059200, "tok_s": 159149.1}
|
| 5 |
+
{"step": 113080, "epoch": 0.718, "loss": 1.61321, "ppl": 5.019, "lr": 0.003, "grad": 0.1108, "tokens": 118544025600, "tok_s": 159129.0}
|
| 6 |
+
{"step": 113100, "epoch": 0.719, "loss": 1.76739, "ppl": 5.856, "lr": 0.003, "grad": 0.102, "tokens": 118564992000, "tok_s": 159208.2}
|
| 7 |
+
{"step": 113120, "epoch": 0.719, "loss": 1.72873, "ppl": 5.634, "lr": 0.003, "grad": 0.0831, "tokens": 118585958400, "tok_s": 159042.0}
|
| 8 |
+
{"step": 113140, "epoch": 0.719, "loss": 1.74315, "ppl": 5.715, "lr": 0.003, "grad": 0.1, "tokens": 118606924800, "tok_s": 159134.1}
|
| 9 |
+
{"step": 113160, "epoch": 0.719, "loss": 1.67597, "ppl": 5.344, "lr": 0.003, "grad": 0.092, "tokens": 118627891200, "tok_s": 159165.1}
|
| 10 |
+
{"step": 113180, "epoch": 0.719, "loss": 1.62867, "ppl": 5.097, "lr": 0.003, "grad": 0.0778, "tokens": 118648857600, "tok_s": 158915.5}
|
| 11 |
+
{"step": 113200, "epoch": 0.719, "loss": 1.59332, "ppl": 4.92, "lr": 0.003, "grad": 0.1523, "tokens": 118669824000, "tok_s": 159228.9}
|
| 12 |
+
{"step": 113220, "epoch": 0.719, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.1081, "tokens": 118690790400, "tok_s": 159106.3}
|
| 13 |
+
{"step": 113240, "epoch": 0.719, "loss": 1.70175, "ppl": 5.484, "lr": 0.003, "grad": 0.0778, "tokens": 118711756800, "tok_s": 159104.9}
|
| 14 |
+
{"step": 113260, "epoch": 0.72, "loss": 1.76013, "ppl": 5.813, "lr": 0.003, "grad": 0.0838, "tokens": 118732723200, "tok_s": 159141.8}
|
| 15 |
+
{"step": 113280, "epoch": 0.72, "loss": 1.71039, "ppl": 5.531, "lr": 0.003, "grad": 0.0872, "tokens": 118753689600, "tok_s": 158455.7}
|
| 16 |
+
{"step": 113300, "epoch": 0.72, "loss": 1.75435, "ppl": 5.78, "lr": 0.003, "grad": 0.078, "tokens": 118774656000, "tok_s": 159162.6}
|
| 17 |
+
{"step": 113320, "epoch": 0.72, "loss": 1.7597, "ppl": 5.811, "lr": 0.003, "grad": 0.0796, "tokens": 118795622400, "tok_s": 158885.5}
|
| 18 |
+
{"step": 113340, "epoch": 0.72, "loss": 1.72363, "ppl": 5.605, "lr": 0.003, "grad": 0.1116, "tokens": 118816588800, "tok_s": 159070.6}
|
| 19 |
+
{"step": 113360, "epoch": 0.72, "loss": 1.77175, "ppl": 5.881, "lr": 0.003, "grad": 0.0751, "tokens": 118837555200, "tok_s": 158738.5}
|
| 20 |
+
{"step": 113380, "epoch": 0.72, "loss": 1.67999, "ppl": 5.366, "lr": 0.003, "grad": 0.0561, "tokens": 118858521600, "tok_s": 159053.7}
|
| 21 |
+
{"step": 113400, "epoch": 0.721, "loss": 1.78069, "ppl": 5.934, "lr": 0.003, "grad": 0.0864, "tokens": 118879488000, "tok_s": 159167.9}
|
| 22 |
+
{"step": 113420, "epoch": 0.721, "loss": 1.7595, "ppl": 5.81, "lr": 0.003, "grad": 0.0752, "tokens": 118900454400, "tok_s": 159167.7}
|
| 23 |
+
{"step": 113440, "epoch": 0.721, "loss": 1.67152, "ppl": 5.32, "lr": 0.003, "grad": 0.0591, "tokens": 118921420800, "tok_s": 159154.3}
|
| 24 |
+
{"step": 113460, "epoch": 0.721, "loss": 1.81131, "ppl": 6.118, "lr": 0.003, "grad": 0.0707, "tokens": 118942387200, "tok_s": 159200.8}
|
| 25 |
+
{"step": 113480, "epoch": 0.721, "loss": 1.80639, "ppl": 6.088, "lr": 0.003, "grad": 0.1177, "tokens": 118963353600, "tok_s": 158645.5}
|
| 26 |
+
{"step": 113500, "epoch": 0.721, "loss": 1.90369, "ppl": 6.711, "lr": 0.003, "grad": 0.1204, "tokens": 118984320000, "tok_s": 159158.8}
|
| 27 |
+
{"step": 113520, "epoch": 0.721, "loss": 1.76353, "ppl": 5.833, "lr": 0.003, "grad": 0.0801, "tokens": 119005286400, "tok_s": 159064.2}
|
| 28 |
+
{"step": 113540, "epoch": 0.721, "loss": 1.65881, "ppl": 5.253, "lr": 0.003, "grad": 0.0753, "tokens": 119026252800, "tok_s": 158729.6}
|
| 29 |
+
{"step": 113560, "epoch": 0.722, "loss": 1.6794, "ppl": 5.362, "lr": 0.003, "grad": 0.0962, "tokens": 119047219200, "tok_s": 159102.7}
|
| 30 |
+
{"step": 113580, "epoch": 0.722, "loss": 1.70352, "ppl": 5.493, "lr": 0.003, "grad": 0.0809, "tokens": 119068185600, "tok_s": 159052.4}
|
| 31 |
+
{"step": 113600, "epoch": 0.722, "loss": 1.64007, "ppl": 5.156, "lr": 0.003, "grad": 0.0822, "tokens": 119089152000, "tok_s": 159126.5}
|
| 32 |
+
{"step": 113620, "epoch": 0.722, "loss": 1.71385, "ppl": 5.55, "lr": 0.003, "grad": 0.0876, "tokens": 119110118400, "tok_s": 158751.5}
|
| 33 |
+
{"step": 113640, "epoch": 0.722, "loss": 1.66267, "ppl": 5.273, "lr": 0.003, "grad": 0.0894, "tokens": 119131084800, "tok_s": 159024.1}
|
| 34 |
+
{"step": 113660, "epoch": 0.722, "loss": 1.84263, "ppl": 6.313, "lr": 0.003, "grad": 0.0854, "tokens": 119152051200, "tok_s": 159082.8}
|
| 35 |
+
{"step": 113680, "epoch": 0.722, "loss": 1.77115, "ppl": 5.878, "lr": 0.003, "grad": 0.1382, "tokens": 119173017600, "tok_s": 158890.2}
|
| 36 |
+
{"step": 113700, "epoch": 0.722, "loss": 1.74136, "ppl": 5.705, "lr": 0.003, "grad": 0.1349, "tokens": 119193984000, "tok_s": 159019.4}
|
| 37 |
+
{"step": 113720, "epoch": 0.723, "loss": 1.66535, "ppl": 5.288, "lr": 0.003, "grad": 0.1052, "tokens": 119214950400, "tok_s": 159074.2}
|
| 38 |
+
{"step": 113740, "epoch": 0.723, "loss": 1.69789, "ppl": 5.462, "lr": 0.003, "grad": 0.0753, "tokens": 119235916800, "tok_s": 159056.5}
|
| 39 |
+
{"step": 113760, "epoch": 0.723, "loss": 1.7667, "ppl": 5.852, "lr": 0.003, "grad": 0.0999, "tokens": 119256883200, "tok_s": 159064.9}
|
| 40 |
+
{"step": 113780, "epoch": 0.723, "loss": 1.67702, "ppl": 5.35, "lr": 0.003, "grad": 0.1165, "tokens": 119277849600, "tok_s": 159030.2}
|
| 41 |
+
{"step": 113800, "epoch": 0.723, "loss": 1.693, "ppl": 5.436, "lr": 0.003, "grad": 0.0981, "tokens": 119298816000, "tok_s": 159047.8}
|
| 42 |
+
{"step": 113820, "epoch": 0.723, "loss": 1.74231, "ppl": 5.711, "lr": 0.003, "grad": 0.1045, "tokens": 119319782400, "tok_s": 159088.2}
|
| 43 |
+
{"step": 113840, "epoch": 0.723, "loss": 1.67498, "ppl": 5.339, "lr": 0.003, "grad": 0.1062, "tokens": 119340748800, "tok_s": 159079.4}
|
| 44 |
+
{"step": 113860, "epoch": 0.723, "loss": 1.7508, "ppl": 5.759, "lr": 0.003, "grad": 0.0925, "tokens": 119361715200, "tok_s": 159038.2}
|
| 45 |
+
{"step": 113880, "epoch": 0.724, "loss": 1.77965, "ppl": 5.928, "lr": 0.003, "grad": 0.1, "tokens": 119382681600, "tok_s": 158024.9}
|
| 46 |
+
{"step": 113900, "epoch": 0.724, "loss": 1.45134, "ppl": 4.269, "lr": 0.003, "grad": 0.0785, "tokens": 119403648000, "tok_s": 158567.9}
|
| 47 |
+
{"step": 113920, "epoch": 0.724, "loss": 1.67685, "ppl": 5.349, "lr": 0.003, "grad": 0.0789, "tokens": 119424614400, "tok_s": 158979.3}
|
| 48 |
+
{"step": 113940, "epoch": 0.724, "loss": 1.68904, "ppl": 5.414, "lr": 0.003, "grad": 0.0793, "tokens": 119445580800, "tok_s": 158486.4}
|
| 49 |
+
{"step": 113960, "epoch": 0.724, "loss": 1.7833, "ppl": 5.949, "lr": 0.003, "grad": 0.1064, "tokens": 119466547200, "tok_s": 158933.5}
|
| 50 |
+
{"step": 113980, "epoch": 0.724, "loss": 1.73486, "ppl": 5.668, "lr": 0.003, "grad": 0.062, "tokens": 119487513600, "tok_s": 159280.1}
|
| 51 |
+
{"step": 114000, "epoch": 0.724, "loss": 1.89109, "ppl": 6.627, "lr": 0.003, "grad": 0.157, "tokens": 119508480000, "tok_s": 159128.2}
|
| 52 |
+
{"step": 114000, "val_loss": 1.73226, "val_ppl": 5.653, "is_best": true}
|
| 53 |
+
{"step": 114020, "epoch": 0.724, "loss": 1.73621, "ppl": 5.676, "lr": 0.003, "grad": 0.1116, "tokens": 119529446400, "tok_s": 159164.3}
|
| 54 |
+
{"step": 114040, "epoch": 0.725, "loss": 1.67751, "ppl": 5.352, "lr": 0.003, "grad": 0.0817, "tokens": 119550412800, "tok_s": 158958.4}
|
| 55 |
+
{"step": 114060, "epoch": 0.725, "loss": 1.77483, "ppl": 5.899, "lr": 0.003, "grad": 0.0808, "tokens": 119571379200, "tok_s": 159128.4}
|
| 56 |
+
{"step": 114080, "epoch": 0.725, "loss": 1.72559, "ppl": 5.616, "lr": 0.003, "grad": 0.1378, "tokens": 119592345600, "tok_s": 159013.9}
|
| 57 |
+
{"step": 114100, "epoch": 0.725, "loss": 1.59786, "ppl": 4.942, "lr": 0.003, "grad": 0.1072, "tokens": 119613312000, "tok_s": 158691.3}
|
| 58 |
+
{"step": 114120, "epoch": 0.725, "loss": 1.87088, "ppl": 6.494, "lr": 0.003, "grad": 0.0884, "tokens": 119634278400, "tok_s": 159110.2}
|
| 59 |
+
{"step": 114140, "epoch": 0.725, "loss": 1.76409, "ppl": 5.836, "lr": 0.003, "grad": 0.0736, "tokens": 119655244800, "tok_s": 158581.2}
|
| 60 |
+
{"step": 114160, "epoch": 0.725, "loss": 1.74995, "ppl": 5.754, "lr": 0.003, "grad": 0.1573, "tokens": 119676211200, "tok_s": 159185.1}
|
| 61 |
+
{"step": 114180, "epoch": 0.725, "loss": 1.79485, "ppl": 6.019, "lr": 0.003, "grad": 0.1156, "tokens": 119697177600, "tok_s": 159065.4}
|
| 62 |
+
{"step": 114200, "epoch": 0.726, "loss": 1.70765, "ppl": 5.516, "lr": 0.003, "grad": 0.1655, "tokens": 119718144000, "tok_s": 158812.3}
|
| 63 |
+
{"step": 114220, "epoch": 0.726, "loss": 1.78097, "ppl": 5.936, "lr": 0.003, "grad": 0.0847, "tokens": 119739110400, "tok_s": 159085.4}
|
| 64 |
+
{"step": 114240, "epoch": 0.726, "loss": 1.69117, "ppl": 5.426, "lr": 0.003, "grad": 0.0751, "tokens": 119760076800, "tok_s": 159038.3}
|
| 65 |
+
{"step": 114260, "epoch": 0.726, "loss": 1.72168, "ppl": 5.594, "lr": 0.003, "grad": 0.0939, "tokens": 119781043200, "tok_s": 159063.8}
|
| 66 |
+
{"step": 114280, "epoch": 0.726, "loss": 1.60388, "ppl": 4.972, "lr": 0.003, "grad": 0.0936, "tokens": 119802009600, "tok_s": 159150.0}
|
| 67 |
+
{"step": 114300, "epoch": 0.726, "loss": 1.80309, "ppl": 6.068, "lr": 0.003, "grad": 0.1006, "tokens": 119822976000, "tok_s": 158938.0}
|
| 68 |
+
{"step": 114320, "epoch": 0.726, "loss": 1.74341, "ppl": 5.717, "lr": 0.003, "grad": 0.0973, "tokens": 119843942400, "tok_s": 158871.4}
|
| 69 |
+
{"step": 114340, "epoch": 0.726, "loss": 1.79538, "ppl": 6.022, "lr": 0.003, "grad": 0.1054, "tokens": 119864908800, "tok_s": 159036.5}
|
| 70 |
+
{"step": 114360, "epoch": 0.727, "loss": 1.734, "ppl": 5.663, "lr": 0.003, "grad": 0.1181, "tokens": 119885875200, "tok_s": 159074.4}
|
| 71 |
+
{"step": 114380, "epoch": 0.727, "loss": 1.84519, "ppl": 6.329, "lr": 0.003, "grad": 0.082, "tokens": 119906841600, "tok_s": 158405.4}
|
| 72 |
+
{"step": 114400, "epoch": 0.727, "loss": 1.81188, "ppl": 6.122, "lr": 0.003, "grad": 0.0674, "tokens": 119927808000, "tok_s": 159065.7}
|
| 73 |
+
{"step": 114420, "epoch": 0.727, "loss": 1.79445, "ppl": 6.016, "lr": 0.003, "grad": 0.1212, "tokens": 119948774400, "tok_s": 158971.6}
|
| 74 |
+
{"step": 114440, "epoch": 0.727, "loss": 1.73389, "ppl": 5.663, "lr": 0.003, "grad": 0.0638, "tokens": 119969740800, "tok_s": 158886.4}
|
| 75 |
+
{"step": 114460, "epoch": 0.727, "loss": 1.77551, "ppl": 5.903, "lr": 0.003, "grad": 0.1217, "tokens": 119990707200, "tok_s": 159156.8}
|
| 76 |
+
{"step": 114480, "epoch": 0.727, "loss": 1.82163, "ppl": 6.182, "lr": 0.003, "grad": 0.1224, "tokens": 120011673600, "tok_s": 158739.8}
|
| 77 |
+
{"step": 114500, "epoch": 0.727, "loss": 1.78047, "ppl": 5.933, "lr": 0.003, "grad": 0.0804, "tokens": 120032640000, "tok_s": 158808.7}
|
| 78 |
+
{"step": 114520, "epoch": 0.728, "loss": 1.78579, "ppl": 5.964, "lr": 0.003, "grad": 0.1135, "tokens": 120053606400, "tok_s": 159059.1}
|
| 79 |
+
{"step": 114540, "epoch": 0.728, "loss": 1.71035, "ppl": 5.531, "lr": 0.003, "grad": 0.0838, "tokens": 120074572800, "tok_s": 158981.3}
|
| 80 |
+
{"step": 114560, "epoch": 0.728, "loss": 1.79175, "ppl": 6.0, "lr": 0.003, "grad": 0.1555, "tokens": 120095539200, "tok_s": 158791.8}
|
| 81 |
+
{"step": 114580, "epoch": 0.728, "loss": 1.5919, "ppl": 4.913, "lr": 0.003, "grad": 0.0864, "tokens": 120116505600, "tok_s": 158876.7}
|
| 82 |
+
{"step": 114600, "epoch": 0.728, "loss": 1.7677, "ppl": 5.857, "lr": 0.003, "grad": 0.0918, "tokens": 120137472000, "tok_s": 159010.6}
|
| 83 |
+
{"step": 114620, "epoch": 0.728, "loss": 1.76809, "ppl": 5.86, "lr": 0.003, "grad": 0.0838, "tokens": 120158438400, "tok_s": 159039.8}
|
| 84 |
+
{"step": 114640, "epoch": 0.728, "loss": 1.73248, "ppl": 5.655, "lr": 0.003, "grad": 0.1019, "tokens": 120179404800, "tok_s": 158605.1}
|
| 85 |
+
{"step": 114660, "epoch": 0.729, "loss": 1.78428, "ppl": 5.955, "lr": 0.003, "grad": 0.0737, "tokens": 120200371200, "tok_s": 159053.2}
|
| 86 |
+
{"step": 114680, "epoch": 0.729, "loss": 1.75854, "ppl": 5.804, "lr": 0.003, "grad": 0.0847, "tokens": 120221337600, "tok_s": 158948.7}
|
| 87 |
+
{"step": 114700, "epoch": 0.729, "loss": 1.7305, "ppl": 5.643, "lr": 0.003, "grad": 0.0854, "tokens": 120242304000, "tok_s": 158333.8}
|
| 88 |
+
{"step": 114720, "epoch": 0.729, "loss": 1.70834, "ppl": 5.52, "lr": 0.003, "grad": 0.0769, "tokens": 120263270400, "tok_s": 158564.2}
|
| 89 |
+
{"step": 114740, "epoch": 0.729, "loss": 1.74569, "ppl": 5.73, "lr": 0.003, "grad": 0.1032, "tokens": 120284236800, "tok_s": 158797.5}
|
| 90 |
+
{"step": 114760, "epoch": 0.729, "loss": 1.63865, "ppl": 5.148, "lr": 0.003, "grad": 0.0829, "tokens": 120305203200, "tok_s": 158980.6}
|
| 91 |
+
{"step": 114780, "epoch": 0.729, "loss": 1.71827, "ppl": 5.575, "lr": 0.003, "grad": 0.1409, "tokens": 120326169600, "tok_s": 158993.3}
|
| 92 |
+
{"step": 114800, "epoch": 0.729, "loss": 1.73932, "ppl": 5.693, "lr": 0.003, "grad": 0.0752, "tokens": 120347136000, "tok_s": 159065.8}
|
| 93 |
+
{"step": 114820, "epoch": 0.73, "loss": 1.76451, "ppl": 5.839, "lr": 0.003, "grad": 0.113, "tokens": 120368102400, "tok_s": 159110.5}
|
| 94 |
+
{"step": 114840, "epoch": 0.73, "loss": 1.7788, "ppl": 5.923, "lr": 0.003, "grad": 0.0734, "tokens": 120389068800, "tok_s": 158867.6}
|
| 95 |
+
{"step": 114860, "epoch": 0.73, "loss": 1.78937, "ppl": 5.986, "lr": 0.003, "grad": 0.0778, "tokens": 120410035200, "tok_s": 158720.1}
|
| 96 |
+
{"step": 114880, "epoch": 0.73, "loss": 1.76945, "ppl": 5.868, "lr": 0.003, "grad": 0.1273, "tokens": 120431001600, "tok_s": 158880.3}
|
| 97 |
+
{"step": 114900, "epoch": 0.73, "loss": 1.75438, "ppl": 5.78, "lr": 0.003, "grad": 0.0804, "tokens": 120451968000, "tok_s": 159036.7}
|
| 98 |
+
{"step": 114920, "epoch": 0.73, "loss": 1.7785, "ppl": 5.921, "lr": 0.003, "grad": 0.1014, "tokens": 120472934400, "tok_s": 159052.1}
|
| 99 |
+
{"step": 114940, "epoch": 0.73, "loss": 1.72752, "ppl": 5.627, "lr": 0.003, "grad": 0.0834, "tokens": 120493900800, "tok_s": 158927.0}
|
| 100 |
+
{"step": 114960, "epoch": 0.73, "loss": 1.75104, "ppl": 5.761, "lr": 0.003, "grad": 0.0814, "tokens": 120514867200, "tok_s": 158793.7}
|
| 101 |
+
{"step": 114980, "epoch": 0.731, "loss": 1.79737, "ppl": 6.034, "lr": 0.003, "grad": 0.1131, "tokens": 120535833600, "tok_s": 158841.1}
|
| 102 |
+
{"step": 115000, "epoch": 0.731, "loss": 1.72563, "ppl": 5.616, "lr": 0.003, "grad": 0.0991, "tokens": 120556800000, "tok_s": 158972.4}
|
| 103 |
+
{"step": 115000, "val_loss": 1.74251, "val_ppl": 5.712, "is_best": false}
|
| 104 |
+
{"step": 115020, "epoch": 0.731, "loss": 1.76095, "ppl": 5.818, "lr": 0.003, "grad": 0.1495, "tokens": 120577766400, "tok_s": 158306.4}
|
| 105 |
+
{"step": 115040, "epoch": 0.731, "loss": 1.75017, "ppl": 5.756, "lr": 0.003, "grad": 0.0803, "tokens": 120598732800, "tok_s": 159033.7}
|
| 106 |
+
{"step": 115060, "epoch": 0.731, "loss": 1.69637, "ppl": 5.454, "lr": 0.003, "grad": 0.0703, "tokens": 120619699200, "tok_s": 159083.2}
|
| 107 |
+
{"step": 115080, "epoch": 0.731, "loss": 1.7665, "ppl": 5.85, "lr": 0.003, "grad": 0.1583, "tokens": 120640665600, "tok_s": 158597.5}
|
| 108 |
+
{"step": 115100, "epoch": 0.731, "loss": 1.7566, "ppl": 5.793, "lr": 0.003, "grad": 0.0979, "tokens": 120661632000, "tok_s": 158933.4}
|
| 109 |
+
{"step": 115120, "epoch": 0.731, "loss": 1.82904, "ppl": 6.228, "lr": 0.003, "grad": 0.0963, "tokens": 120682598400, "tok_s": 159013.9}
|
| 110 |
+
{"step": 115140, "epoch": 0.732, "loss": 1.77106, "ppl": 5.877, "lr": 0.003, "grad": 0.0801, "tokens": 120703564800, "tok_s": 158756.2}
|
| 111 |
+
{"step": 115160, "epoch": 0.732, "loss": 1.7239, "ppl": 5.606, "lr": 0.003, "grad": 0.0624, "tokens": 120724531200, "tok_s": 158983.3}
|
| 112 |
+
{"step": 115180, "epoch": 0.732, "loss": 1.7504, "ppl": 5.757, "lr": 0.003, "grad": 0.1288, "tokens": 120745497600, "tok_s": 158951.9}
|
| 113 |
+
{"step": 115200, "epoch": 0.732, "loss": 1.80402, "ppl": 6.074, "lr": 0.003, "grad": 0.1111, "tokens": 120766464000, "tok_s": 158157.1}
|
| 114 |
+
{"step": 115220, "epoch": 0.732, "loss": 1.70762, "ppl": 5.516, "lr": 0.003, "grad": 0.0672, "tokens": 120787430400, "tok_s": 158909.4}
|
| 115 |
+
{"step": 115240, "epoch": 0.732, "loss": 1.75081, "ppl": 5.759, "lr": 0.003, "grad": 0.1099, "tokens": 120808396800, "tok_s": 158974.1}
|
| 116 |
+
{"step": 115260, "epoch": 0.732, "loss": 1.66476, "ppl": 5.284, "lr": 0.003, "grad": 0.0723, "tokens": 120829363200, "tok_s": 158565.8}
|
| 117 |
+
{"step": 115280, "epoch": 0.732, "loss": 1.76276, "ppl": 5.828, "lr": 0.003, "grad": 0.055, "tokens": 120850329600, "tok_s": 158962.6}
|
| 118 |
+
{"step": 115300, "epoch": 0.733, "loss": 1.78751, "ppl": 5.975, "lr": 0.003, "grad": 0.081, "tokens": 120871296000, "tok_s": 158890.7}
|
| 119 |
+
{"step": 115320, "epoch": 0.733, "loss": 1.66815, "ppl": 5.302, "lr": 0.003, "grad": 0.0606, "tokens": 120892262400, "tok_s": 158953.0}
|
| 120 |
+
{"step": 115340, "epoch": 0.733, "loss": 1.63292, "ppl": 5.119, "lr": 0.003, "grad": 0.0829, "tokens": 120913228800, "tok_s": 158889.8}
|
| 121 |
+
{"step": 115360, "epoch": 0.733, "loss": 1.76008, "ppl": 5.813, "lr": 0.003, "grad": 0.1001, "tokens": 120934195200, "tok_s": 158990.0}
|
| 122 |
+
{"step": 115380, "epoch": 0.733, "loss": 1.73241, "ppl": 5.654, "lr": 0.003, "grad": 0.0689, "tokens": 120955161600, "tok_s": 159126.8}
|
| 123 |
+
{"step": 115400, "epoch": 0.733, "loss": 1.65046, "ppl": 5.209, "lr": 0.003, "grad": 0.0858, "tokens": 120976128000, "tok_s": 159175.1}
|
| 124 |
+
{"step": 115420, "epoch": 0.733, "loss": 1.66761, "ppl": 5.299, "lr": 0.003, "grad": 0.0863, "tokens": 120997094400, "tok_s": 158915.4}
|
| 125 |
+
{"step": 115440, "epoch": 0.733, "loss": 1.85483, "ppl": 6.391, "lr": 0.003, "grad": 0.119, "tokens": 121018060800, "tok_s": 159069.3}
|
| 126 |
+
{"step": 115460, "epoch": 0.734, "loss": 1.64881, "ppl": 5.201, "lr": 0.003, "grad": 0.0977, "tokens": 121039027200, "tok_s": 158967.5}
|
| 127 |
+
{"step": 115480, "epoch": 0.734, "loss": 1.72542, "ppl": 5.615, "lr": 0.003, "grad": 0.0658, "tokens": 121059993600, "tok_s": 159130.9}
|
| 128 |
+
{"step": 115500, "epoch": 0.734, "loss": 1.69981, "ppl": 5.473, "lr": 0.003, "grad": 0.0547, "tokens": 121080960000, "tok_s": 159090.4}
|
| 129 |
+
{"step": 115520, "epoch": 0.734, "loss": 1.71325, "ppl": 5.547, "lr": 0.003, "grad": 0.0535, "tokens": 121101926400, "tok_s": 158661.9}
|
| 130 |
+
{"step": 115540, "epoch": 0.734, "loss": 1.71585, "ppl": 5.561, "lr": 0.003, "grad": 0.076, "tokens": 121122892800, "tok_s": 159083.5}
|
| 131 |
+
{"step": 115560, "epoch": 0.734, "loss": 1.81402, "ppl": 6.135, "lr": 0.003, "grad": 0.1009, "tokens": 121143859200, "tok_s": 159142.5}
|
| 132 |
+
{"step": 115580, "epoch": 0.734, "loss": 1.74548, "ppl": 5.729, "lr": 0.003, "grad": 0.0976, "tokens": 121164825600, "tok_s": 158682.1}
|
| 133 |
+
{"step": 115600, "epoch": 0.734, "loss": 1.77462, "ppl": 5.898, "lr": 0.003, "grad": 0.0858, "tokens": 121185792000, "tok_s": 159262.0}
|
| 134 |
+
{"step": 115620, "epoch": 0.735, "loss": 1.7396, "ppl": 5.695, "lr": 0.003, "grad": 0.1201, "tokens": 121206758400, "tok_s": 158993.1}
|
| 135 |
+
{"step": 115640, "epoch": 0.735, "loss": 1.77629, "ppl": 5.908, "lr": 0.003, "grad": 0.0664, "tokens": 121227724800, "tok_s": 159152.3}
|
| 136 |
+
{"step": 115660, "epoch": 0.735, "loss": 1.64546, "ppl": 5.183, "lr": 0.003, "grad": 0.1268, "tokens": 121248691200, "tok_s": 159114.1}
|
| 137 |
+
{"step": 115680, "epoch": 0.735, "loss": 1.7395, "ppl": 5.695, "lr": 0.003, "grad": 0.0946, "tokens": 121269657600, "tok_s": 158968.0}
|
| 138 |
+
{"step": 115700, "epoch": 0.735, "loss": 1.69873, "ppl": 5.467, "lr": 0.003, "grad": 0.1181, "tokens": 121290624000, "tok_s": 158996.3}
|
| 139 |
+
{"step": 115720, "epoch": 0.735, "loss": 1.78564, "ppl": 5.963, "lr": 0.003, "grad": 0.097, "tokens": 121311590400, "tok_s": 159080.3}
|
| 140 |
+
{"step": 115740, "epoch": 0.735, "loss": 1.60998, "ppl": 5.003, "lr": 0.003, "grad": 0.1052, "tokens": 121332556800, "tok_s": 158828.3}
|
| 141 |
+
{"step": 115760, "epoch": 0.735, "loss": 1.77713, "ppl": 5.913, "lr": 0.003, "grad": 0.0884, "tokens": 121353523200, "tok_s": 158637.6}
|
| 142 |
+
{"step": 115780, "epoch": 0.736, "loss": 1.78343, "ppl": 5.95, "lr": 0.003, "grad": 0.1031, "tokens": 121374489600, "tok_s": 158460.2}
|
| 143 |
+
{"step": 115800, "epoch": 0.736, "loss": 1.75974, "ppl": 5.811, "lr": 0.003, "grad": 0.1039, "tokens": 121395456000, "tok_s": 158956.9}
|
| 144 |
+
{"step": 115820, "epoch": 0.736, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.089, "tokens": 121416422400, "tok_s": 158579.3}
|
| 145 |
+
{"step": 115840, "epoch": 0.736, "loss": 1.77844, "ppl": 5.921, "lr": 0.003, "grad": 0.1064, "tokens": 121437388800, "tok_s": 159003.3}
|
| 146 |
+
{"step": 115860, "epoch": 0.736, "loss": 1.80231, "ppl": 6.064, "lr": 0.003, "grad": 0.078, "tokens": 121458355200, "tok_s": 159003.1}
|
| 147 |
+
{"step": 115880, "epoch": 0.736, "loss": 1.71566, "ppl": 5.56, "lr": 0.003, "grad": 0.0837, "tokens": 121479321600, "tok_s": 158575.5}
|
| 148 |
+
{"step": 115900, "epoch": 0.736, "loss": 1.77074, "ppl": 5.875, "lr": 0.003, "grad": 0.0898, "tokens": 121500288000, "tok_s": 158867.6}
|
| 149 |
+
{"step": 115920, "epoch": 0.737, "loss": 1.76584, "ppl": 5.847, "lr": 0.003, "grad": 0.086, "tokens": 121521254400, "tok_s": 158639.9}
|
| 150 |
+
{"step": 115940, "epoch": 0.737, "loss": 1.73363, "ppl": 5.661, "lr": 0.003, "grad": 0.1066, "tokens": 121542220800, "tok_s": 158912.7}
|
| 151 |
+
{"step": 115960, "epoch": 0.737, "loss": 1.78966, "ppl": 5.987, "lr": 0.003, "grad": 0.0879, "tokens": 121563187200, "tok_s": 159044.0}
|
| 152 |
+
{"step": 115980, "epoch": 0.737, "loss": 1.76167, "ppl": 5.822, "lr": 0.003, "grad": 0.1034, "tokens": 121584153600, "tok_s": 159061.2}
|
| 153 |
+
{"step": 116000, "epoch": 0.737, "loss": 1.76646, "ppl": 5.85, "lr": 0.003, "grad": 0.1287, "tokens": 121605120000, "tok_s": 159044.7}
|
| 154 |
+
{"step": 116000, "val_loss": 1.75047, "val_ppl": 5.757, "is_best": false}
|
| 155 |
+
{"step": 116020, "epoch": 0.737, "loss": 1.69817, "ppl": 5.464, "lr": 0.003, "grad": 0.0588, "tokens": 121626086400, "tok_s": 159041.3}
|
| 156 |
+
{"step": 116040, "epoch": 0.737, "loss": 1.75483, "ppl": 5.782, "lr": 0.003, "grad": 0.08, "tokens": 121647052800, "tok_s": 159020.1}
|
| 157 |
+
{"step": 116060, "epoch": 0.737, "loss": 1.73774, "ppl": 5.684, "lr": 0.003, "grad": 0.0962, "tokens": 121668019200, "tok_s": 158982.9}
|
| 158 |
+
{"step": 116080, "epoch": 0.738, "loss": 1.77812, "ppl": 5.919, "lr": 0.003, "grad": 0.1196, "tokens": 121688985600, "tok_s": 159013.1}
|
| 159 |
+
{"step": 116100, "epoch": 0.738, "loss": 1.77472, "ppl": 5.899, "lr": 0.003, "grad": 0.0621, "tokens": 121709952000, "tok_s": 159054.4}
|
| 160 |
+
{"step": 116120, "epoch": 0.738, "loss": 1.74142, "ppl": 5.705, "lr": 0.003, "grad": 0.1002, "tokens": 121730918400, "tok_s": 158834.3}
|
| 161 |
+
{"step": 116140, "epoch": 0.738, "loss": 1.72689, "ppl": 5.623, "lr": 0.003, "grad": 0.0847, "tokens": 121751884800, "tok_s": 158780.7}
|
| 162 |
+
{"step": 116160, "epoch": 0.738, "loss": 1.73821, "ppl": 5.687, "lr": 0.003, "grad": 0.0998, "tokens": 121772851200, "tok_s": 158849.0}
|
| 163 |
+
{"step": 116180, "epoch": 0.738, "loss": 1.68236, "ppl": 5.378, "lr": 0.003, "grad": 0.0976, "tokens": 121793817600, "tok_s": 158891.5}
|
| 164 |
+
{"step": 116200, "epoch": 0.738, "loss": 1.74406, "ppl": 5.721, "lr": 0.003, "grad": 0.1012, "tokens": 121814784000, "tok_s": 159071.4}
|
| 165 |
+
{"step": 116220, "epoch": 0.738, "loss": 1.73084, "ppl": 5.645, "lr": 0.003, "grad": 0.1192, "tokens": 121835750400, "tok_s": 158905.5}
|
| 166 |
+
{"step": 116240, "epoch": 0.739, "loss": 1.73463, "ppl": 5.667, "lr": 0.003, "grad": 0.1083, "tokens": 121856716800, "tok_s": 158817.1}
|
| 167 |
+
{"step": 116260, "epoch": 0.739, "loss": 1.74894, "ppl": 5.749, "lr": 0.003, "grad": 0.1143, "tokens": 121877683200, "tok_s": 158958.4}
|
| 168 |
+
{"step": 116280, "epoch": 0.739, "loss": 1.77149, "ppl": 5.88, "lr": 0.003, "grad": 0.0946, "tokens": 121898649600, "tok_s": 158874.4}
|
| 169 |
+
{"step": 116300, "epoch": 0.739, "loss": 1.82361, "ppl": 6.194, "lr": 0.003, "grad": 0.0758, "tokens": 121919616000, "tok_s": 158962.9}
|
| 170 |
+
{"step": 116320, "epoch": 0.739, "loss": 1.72426, "ppl": 5.608, "lr": 0.003, "grad": 0.0706, "tokens": 121940582400, "tok_s": 158750.2}
|
| 171 |
+
{"step": 116340, "epoch": 0.739, "loss": 1.75324, "ppl": 5.773, "lr": 0.003, "grad": 0.0837, "tokens": 121961548800, "tok_s": 158796.4}
|
| 172 |
+
{"step": 116360, "epoch": 0.739, "loss": 1.74039, "ppl": 5.7, "lr": 0.003, "grad": 0.1439, "tokens": 121982515200, "tok_s": 158899.5}
|
| 173 |
+
{"step": 116380, "epoch": 0.739, "loss": 1.69343, "ppl": 5.438, "lr": 0.003, "grad": 0.1456, "tokens": 122003481600, "tok_s": 158735.1}
|
| 174 |
+
{"step": 116400, "epoch": 0.74, "loss": 1.71463, "ppl": 5.555, "lr": 0.003, "grad": 0.1132, "tokens": 122024448000, "tok_s": 158585.2}
|
| 175 |
+
{"step": 116420, "epoch": 0.74, "loss": 1.74055, "ppl": 5.7, "lr": 0.003, "grad": 0.1266, "tokens": 122045414400, "tok_s": 158491.4}
|
| 176 |
+
{"step": 116440, "epoch": 0.74, "loss": 1.72903, "ppl": 5.635, "lr": 0.003, "grad": 0.1016, "tokens": 122066380800, "tok_s": 159072.2}
|
| 177 |
+
{"step": 116460, "epoch": 0.74, "loss": 1.74042, "ppl": 5.7, "lr": 0.003, "grad": 0.0572, "tokens": 122087347200, "tok_s": 158891.6}
|
| 178 |
+
{"step": 116480, "epoch": 0.74, "loss": 1.6533, "ppl": 5.224, "lr": 0.003, "grad": 0.1325, "tokens": 122108313600, "tok_s": 158632.5}
|
| 179 |
+
{"step": 116500, "epoch": 0.74, "loss": 1.86506, "ppl": 6.456, "lr": 0.003, "grad": 0.116, "tokens": 122129280000, "tok_s": 159036.6}
|
| 180 |
+
{"step": 116520, "epoch": 0.74, "loss": 1.79135, "ppl": 5.998, "lr": 0.003, "grad": 0.0853, "tokens": 122150246400, "tok_s": 158103.0}
|
| 181 |
+
{"step": 116540, "epoch": 0.74, "loss": 1.69744, "ppl": 5.46, "lr": 0.003, "grad": 0.0947, "tokens": 122171212800, "tok_s": 158913.5}
|
| 182 |
+
{"step": 116560, "epoch": 0.741, "loss": 1.84827, "ppl": 6.349, "lr": 0.003, "grad": 0.1629, "tokens": 122192179200, "tok_s": 158852.1}
|
| 183 |
+
{"step": 116580, "epoch": 0.741, "loss": 1.73205, "ppl": 5.652, "lr": 0.003, "grad": 0.0689, "tokens": 122213145600, "tok_s": 159076.3}
|
| 184 |
+
{"step": 116600, "epoch": 0.741, "loss": 1.82115, "ppl": 6.179, "lr": 0.003, "grad": 0.0896, "tokens": 122234112000, "tok_s": 159093.4}
|
| 185 |
+
{"step": 116620, "epoch": 0.741, "loss": 1.73873, "ppl": 5.69, "lr": 0.003, "grad": 0.1122, "tokens": 122255078400, "tok_s": 158578.8}
|
| 186 |
+
{"step": 116640, "epoch": 0.741, "loss": 1.75494, "ppl": 5.783, "lr": 0.003, "grad": 0.0905, "tokens": 122276044800, "tok_s": 158821.3}
|
| 187 |
+
{"step": 116660, "epoch": 0.741, "loss": 1.6383, "ppl": 5.146, "lr": 0.003, "grad": 0.0996, "tokens": 122297011200, "tok_s": 158989.5}
|
| 188 |
+
{"step": 116680, "epoch": 0.741, "loss": 1.46931, "ppl": 4.346, "lr": 0.003, "grad": 0.0836, "tokens": 122317977600, "tok_s": 158990.2}
|
| 189 |
+
{"step": 116700, "epoch": 0.741, "loss": 1.80059, "ppl": 6.053, "lr": 0.003, "grad": 0.0724, "tokens": 122338944000, "tok_s": 158811.1}
|
| 190 |
+
{"step": 116720, "epoch": 0.742, "loss": 1.70257, "ppl": 5.488, "lr": 0.003, "grad": 0.1328, "tokens": 122359910400, "tok_s": 158979.9}
|
| 191 |
+
{"step": 116740, "epoch": 0.742, "loss": 1.71656, "ppl": 5.565, "lr": 0.003, "grad": 0.0936, "tokens": 122380876800, "tok_s": 158909.5}
|
| 192 |
+
{"step": 116760, "epoch": 0.742, "loss": 1.74442, "ppl": 5.723, "lr": 0.003, "grad": 0.0831, "tokens": 122401843200, "tok_s": 158623.7}
|
| 193 |
+
{"step": 116780, "epoch": 0.742, "loss": 1.70911, "ppl": 5.524, "lr": 0.003, "grad": 0.124, "tokens": 122422809600, "tok_s": 158474.7}
|
| 194 |
+
{"step": 116800, "epoch": 0.742, "loss": 1.76719, "ppl": 5.854, "lr": 0.003, "grad": 0.1094, "tokens": 122443776000, "tok_s": 158319.0}
|
| 195 |
+
{"step": 116820, "epoch": 0.742, "loss": 1.75072, "ppl": 5.759, "lr": 0.003, "grad": 0.0642, "tokens": 122464742400, "tok_s": 158778.0}
|
| 196 |
+
{"step": 116840, "epoch": 0.742, "loss": 1.76635, "ppl": 5.849, "lr": 0.003, "grad": 0.1284, "tokens": 122485708800, "tok_s": 158649.5}
|
| 197 |
+
{"step": 116860, "epoch": 0.742, "loss": 1.74052, "ppl": 5.7, "lr": 0.003, "grad": 0.1281, "tokens": 122506675200, "tok_s": 158699.8}
|
| 198 |
+
{"step": 116880, "epoch": 0.743, "loss": 1.74391, "ppl": 5.72, "lr": 0.003, "grad": 0.1097, "tokens": 122527641600, "tok_s": 158824.1}
|
| 199 |
+
{"step": 116900, "epoch": 0.743, "loss": 1.73173, "ppl": 5.65, "lr": 0.003, "grad": 0.0696, "tokens": 122548608000, "tok_s": 158982.9}
|
| 200 |
+
{"step": 116920, "epoch": 0.743, "loss": 1.73157, "ppl": 5.65, "lr": 0.003, "grad": 0.0991, "tokens": 122569574400, "tok_s": 158775.5}
|
| 201 |
+
{"step": 116940, "epoch": 0.743, "loss": 1.73989, "ppl": 5.697, "lr": 0.003, "grad": 0.159, "tokens": 122590540800, "tok_s": 158944.8}
|
| 202 |
+
{"step": 116960, "epoch": 0.743, "loss": 1.76898, "ppl": 5.865, "lr": 0.003, "grad": 0.1056, "tokens": 122611507200, "tok_s": 158621.4}
|
| 203 |
+
{"step": 116980, "epoch": 0.743, "loss": 1.7378, "ppl": 5.685, "lr": 0.003, "grad": 0.1382, "tokens": 122632473600, "tok_s": 159078.5}
|
| 204 |
+
{"step": 117000, "epoch": 0.743, "loss": 1.76831, "ppl": 5.861, "lr": 0.003, "grad": 0.0971, "tokens": 122653440000, "tok_s": 159003.9}
|
| 205 |
+
{"step": 117000, "val_loss": 1.75079, "val_ppl": 5.759, "is_best": false}
|
logs/log_118000.jsonl
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 113000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-05T06:28:33.908905"}
|
| 2 |
+
{"step": 113020, "epoch": 0.718, "loss": 1.73974, "ppl": 5.696, "lr": 0.003, "grad": 0.1063, "tokens": 118481126400, "tok_s": 158492.1}
|
| 3 |
+
{"step": 113040, "epoch": 0.718, "loss": 1.74188, "ppl": 5.708, "lr": 0.003, "grad": 0.0846, "tokens": 118502092800, "tok_s": 158868.7}
|
| 4 |
+
{"step": 113060, "epoch": 0.718, "loss": 1.71566, "ppl": 5.56, "lr": 0.003, "grad": 0.1073, "tokens": 118523059200, "tok_s": 159149.1}
|
| 5 |
+
{"step": 113080, "epoch": 0.718, "loss": 1.61321, "ppl": 5.019, "lr": 0.003, "grad": 0.1108, "tokens": 118544025600, "tok_s": 159129.0}
|
| 6 |
+
{"step": 113100, "epoch": 0.719, "loss": 1.76739, "ppl": 5.856, "lr": 0.003, "grad": 0.102, "tokens": 118564992000, "tok_s": 159208.2}
|
| 7 |
+
{"step": 113120, "epoch": 0.719, "loss": 1.72873, "ppl": 5.634, "lr": 0.003, "grad": 0.0831, "tokens": 118585958400, "tok_s": 159042.0}
|
| 8 |
+
{"step": 113140, "epoch": 0.719, "loss": 1.74315, "ppl": 5.715, "lr": 0.003, "grad": 0.1, "tokens": 118606924800, "tok_s": 159134.1}
|
| 9 |
+
{"step": 113160, "epoch": 0.719, "loss": 1.67597, "ppl": 5.344, "lr": 0.003, "grad": 0.092, "tokens": 118627891200, "tok_s": 159165.1}
|
| 10 |
+
{"step": 113180, "epoch": 0.719, "loss": 1.62867, "ppl": 5.097, "lr": 0.003, "grad": 0.0778, "tokens": 118648857600, "tok_s": 158915.5}
|
| 11 |
+
{"step": 113200, "epoch": 0.719, "loss": 1.59332, "ppl": 4.92, "lr": 0.003, "grad": 0.1523, "tokens": 118669824000, "tok_s": 159228.9}
|
| 12 |
+
{"step": 113220, "epoch": 0.719, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.1081, "tokens": 118690790400, "tok_s": 159106.3}
|
| 13 |
+
{"step": 113240, "epoch": 0.719, "loss": 1.70175, "ppl": 5.484, "lr": 0.003, "grad": 0.0778, "tokens": 118711756800, "tok_s": 159104.9}
|
| 14 |
+
{"step": 113260, "epoch": 0.72, "loss": 1.76013, "ppl": 5.813, "lr": 0.003, "grad": 0.0838, "tokens": 118732723200, "tok_s": 159141.8}
|
| 15 |
+
{"step": 113280, "epoch": 0.72, "loss": 1.71039, "ppl": 5.531, "lr": 0.003, "grad": 0.0872, "tokens": 118753689600, "tok_s": 158455.7}
|
| 16 |
+
{"step": 113300, "epoch": 0.72, "loss": 1.75435, "ppl": 5.78, "lr": 0.003, "grad": 0.078, "tokens": 118774656000, "tok_s": 159162.6}
|
| 17 |
+
{"step": 113320, "epoch": 0.72, "loss": 1.7597, "ppl": 5.811, "lr": 0.003, "grad": 0.0796, "tokens": 118795622400, "tok_s": 158885.5}
|
| 18 |
+
{"step": 113340, "epoch": 0.72, "loss": 1.72363, "ppl": 5.605, "lr": 0.003, "grad": 0.1116, "tokens": 118816588800, "tok_s": 159070.6}
|
| 19 |
+
{"step": 113360, "epoch": 0.72, "loss": 1.77175, "ppl": 5.881, "lr": 0.003, "grad": 0.0751, "tokens": 118837555200, "tok_s": 158738.5}
|
| 20 |
+
{"step": 113380, "epoch": 0.72, "loss": 1.67999, "ppl": 5.366, "lr": 0.003, "grad": 0.0561, "tokens": 118858521600, "tok_s": 159053.7}
|
| 21 |
+
{"step": 113400, "epoch": 0.721, "loss": 1.78069, "ppl": 5.934, "lr": 0.003, "grad": 0.0864, "tokens": 118879488000, "tok_s": 159167.9}
|
| 22 |
+
{"step": 113420, "epoch": 0.721, "loss": 1.7595, "ppl": 5.81, "lr": 0.003, "grad": 0.0752, "tokens": 118900454400, "tok_s": 159167.7}
|
| 23 |
+
{"step": 113440, "epoch": 0.721, "loss": 1.67152, "ppl": 5.32, "lr": 0.003, "grad": 0.0591, "tokens": 118921420800, "tok_s": 159154.3}
|
| 24 |
+
{"step": 113460, "epoch": 0.721, "loss": 1.81131, "ppl": 6.118, "lr": 0.003, "grad": 0.0707, "tokens": 118942387200, "tok_s": 159200.8}
|
| 25 |
+
{"step": 113480, "epoch": 0.721, "loss": 1.80639, "ppl": 6.088, "lr": 0.003, "grad": 0.1177, "tokens": 118963353600, "tok_s": 158645.5}
|
| 26 |
+
{"step": 113500, "epoch": 0.721, "loss": 1.90369, "ppl": 6.711, "lr": 0.003, "grad": 0.1204, "tokens": 118984320000, "tok_s": 159158.8}
|
| 27 |
+
{"step": 113520, "epoch": 0.721, "loss": 1.76353, "ppl": 5.833, "lr": 0.003, "grad": 0.0801, "tokens": 119005286400, "tok_s": 159064.2}
|
| 28 |
+
{"step": 113540, "epoch": 0.721, "loss": 1.65881, "ppl": 5.253, "lr": 0.003, "grad": 0.0753, "tokens": 119026252800, "tok_s": 158729.6}
|
| 29 |
+
{"step": 113560, "epoch": 0.722, "loss": 1.6794, "ppl": 5.362, "lr": 0.003, "grad": 0.0962, "tokens": 119047219200, "tok_s": 159102.7}
|
| 30 |
+
{"step": 113580, "epoch": 0.722, "loss": 1.70352, "ppl": 5.493, "lr": 0.003, "grad": 0.0809, "tokens": 119068185600, "tok_s": 159052.4}
|
| 31 |
+
{"step": 113600, "epoch": 0.722, "loss": 1.64007, "ppl": 5.156, "lr": 0.003, "grad": 0.0822, "tokens": 119089152000, "tok_s": 159126.5}
|
| 32 |
+
{"step": 113620, "epoch": 0.722, "loss": 1.71385, "ppl": 5.55, "lr": 0.003, "grad": 0.0876, "tokens": 119110118400, "tok_s": 158751.5}
|
| 33 |
+
{"step": 113640, "epoch": 0.722, "loss": 1.66267, "ppl": 5.273, "lr": 0.003, "grad": 0.0894, "tokens": 119131084800, "tok_s": 159024.1}
|
| 34 |
+
{"step": 113660, "epoch": 0.722, "loss": 1.84263, "ppl": 6.313, "lr": 0.003, "grad": 0.0854, "tokens": 119152051200, "tok_s": 159082.8}
|
| 35 |
+
{"step": 113680, "epoch": 0.722, "loss": 1.77115, "ppl": 5.878, "lr": 0.003, "grad": 0.1382, "tokens": 119173017600, "tok_s": 158890.2}
|
| 36 |
+
{"step": 113700, "epoch": 0.722, "loss": 1.74136, "ppl": 5.705, "lr": 0.003, "grad": 0.1349, "tokens": 119193984000, "tok_s": 159019.4}
|
| 37 |
+
{"step": 113720, "epoch": 0.723, "loss": 1.66535, "ppl": 5.288, "lr": 0.003, "grad": 0.1052, "tokens": 119214950400, "tok_s": 159074.2}
|
| 38 |
+
{"step": 113740, "epoch": 0.723, "loss": 1.69789, "ppl": 5.462, "lr": 0.003, "grad": 0.0753, "tokens": 119235916800, "tok_s": 159056.5}
|
| 39 |
+
{"step": 113760, "epoch": 0.723, "loss": 1.7667, "ppl": 5.852, "lr": 0.003, "grad": 0.0999, "tokens": 119256883200, "tok_s": 159064.9}
|
| 40 |
+
{"step": 113780, "epoch": 0.723, "loss": 1.67702, "ppl": 5.35, "lr": 0.003, "grad": 0.1165, "tokens": 119277849600, "tok_s": 159030.2}
|
| 41 |
+
{"step": 113800, "epoch": 0.723, "loss": 1.693, "ppl": 5.436, "lr": 0.003, "grad": 0.0981, "tokens": 119298816000, "tok_s": 159047.8}
|
| 42 |
+
{"step": 113820, "epoch": 0.723, "loss": 1.74231, "ppl": 5.711, "lr": 0.003, "grad": 0.1045, "tokens": 119319782400, "tok_s": 159088.2}
|
| 43 |
+
{"step": 113840, "epoch": 0.723, "loss": 1.67498, "ppl": 5.339, "lr": 0.003, "grad": 0.1062, "tokens": 119340748800, "tok_s": 159079.4}
|
| 44 |
+
{"step": 113860, "epoch": 0.723, "loss": 1.7508, "ppl": 5.759, "lr": 0.003, "grad": 0.0925, "tokens": 119361715200, "tok_s": 159038.2}
|
| 45 |
+
{"step": 113880, "epoch": 0.724, "loss": 1.77965, "ppl": 5.928, "lr": 0.003, "grad": 0.1, "tokens": 119382681600, "tok_s": 158024.9}
|
| 46 |
+
{"step": 113900, "epoch": 0.724, "loss": 1.45134, "ppl": 4.269, "lr": 0.003, "grad": 0.0785, "tokens": 119403648000, "tok_s": 158567.9}
|
| 47 |
+
{"step": 113920, "epoch": 0.724, "loss": 1.67685, "ppl": 5.349, "lr": 0.003, "grad": 0.0789, "tokens": 119424614400, "tok_s": 158979.3}
|
| 48 |
+
{"step": 113940, "epoch": 0.724, "loss": 1.68904, "ppl": 5.414, "lr": 0.003, "grad": 0.0793, "tokens": 119445580800, "tok_s": 158486.4}
|
| 49 |
+
{"step": 113960, "epoch": 0.724, "loss": 1.7833, "ppl": 5.949, "lr": 0.003, "grad": 0.1064, "tokens": 119466547200, "tok_s": 158933.5}
|
| 50 |
+
{"step": 113980, "epoch": 0.724, "loss": 1.73486, "ppl": 5.668, "lr": 0.003, "grad": 0.062, "tokens": 119487513600, "tok_s": 159280.1}
|
| 51 |
+
{"step": 114000, "epoch": 0.724, "loss": 1.89109, "ppl": 6.627, "lr": 0.003, "grad": 0.157, "tokens": 119508480000, "tok_s": 159128.2}
|
| 52 |
+
{"step": 114000, "val_loss": 1.73226, "val_ppl": 5.653, "is_best": true}
|
| 53 |
+
{"step": 114020, "epoch": 0.724, "loss": 1.73621, "ppl": 5.676, "lr": 0.003, "grad": 0.1116, "tokens": 119529446400, "tok_s": 159164.3}
|
| 54 |
+
{"step": 114040, "epoch": 0.725, "loss": 1.67751, "ppl": 5.352, "lr": 0.003, "grad": 0.0817, "tokens": 119550412800, "tok_s": 158958.4}
|
| 55 |
+
{"step": 114060, "epoch": 0.725, "loss": 1.77483, "ppl": 5.899, "lr": 0.003, "grad": 0.0808, "tokens": 119571379200, "tok_s": 159128.4}
|
| 56 |
+
{"step": 114080, "epoch": 0.725, "loss": 1.72559, "ppl": 5.616, "lr": 0.003, "grad": 0.1378, "tokens": 119592345600, "tok_s": 159013.9}
|
| 57 |
+
{"step": 114100, "epoch": 0.725, "loss": 1.59786, "ppl": 4.942, "lr": 0.003, "grad": 0.1072, "tokens": 119613312000, "tok_s": 158691.3}
|
| 58 |
+
{"step": 114120, "epoch": 0.725, "loss": 1.87088, "ppl": 6.494, "lr": 0.003, "grad": 0.0884, "tokens": 119634278400, "tok_s": 159110.2}
|
| 59 |
+
{"step": 114140, "epoch": 0.725, "loss": 1.76409, "ppl": 5.836, "lr": 0.003, "grad": 0.0736, "tokens": 119655244800, "tok_s": 158581.2}
|
| 60 |
+
{"step": 114160, "epoch": 0.725, "loss": 1.74995, "ppl": 5.754, "lr": 0.003, "grad": 0.1573, "tokens": 119676211200, "tok_s": 159185.1}
|
| 61 |
+
{"step": 114180, "epoch": 0.725, "loss": 1.79485, "ppl": 6.019, "lr": 0.003, "grad": 0.1156, "tokens": 119697177600, "tok_s": 159065.4}
|
| 62 |
+
{"step": 114200, "epoch": 0.726, "loss": 1.70765, "ppl": 5.516, "lr": 0.003, "grad": 0.1655, "tokens": 119718144000, "tok_s": 158812.3}
|
| 63 |
+
{"step": 114220, "epoch": 0.726, "loss": 1.78097, "ppl": 5.936, "lr": 0.003, "grad": 0.0847, "tokens": 119739110400, "tok_s": 159085.4}
|
| 64 |
+
{"step": 114240, "epoch": 0.726, "loss": 1.69117, "ppl": 5.426, "lr": 0.003, "grad": 0.0751, "tokens": 119760076800, "tok_s": 159038.3}
|
| 65 |
+
{"step": 114260, "epoch": 0.726, "loss": 1.72168, "ppl": 5.594, "lr": 0.003, "grad": 0.0939, "tokens": 119781043200, "tok_s": 159063.8}
|
| 66 |
+
{"step": 114280, "epoch": 0.726, "loss": 1.60388, "ppl": 4.972, "lr": 0.003, "grad": 0.0936, "tokens": 119802009600, "tok_s": 159150.0}
|
| 67 |
+
{"step": 114300, "epoch": 0.726, "loss": 1.80309, "ppl": 6.068, "lr": 0.003, "grad": 0.1006, "tokens": 119822976000, "tok_s": 158938.0}
|
| 68 |
+
{"step": 114320, "epoch": 0.726, "loss": 1.74341, "ppl": 5.717, "lr": 0.003, "grad": 0.0973, "tokens": 119843942400, "tok_s": 158871.4}
|
| 69 |
+
{"step": 114340, "epoch": 0.726, "loss": 1.79538, "ppl": 6.022, "lr": 0.003, "grad": 0.1054, "tokens": 119864908800, "tok_s": 159036.5}
|
| 70 |
+
{"step": 114360, "epoch": 0.727, "loss": 1.734, "ppl": 5.663, "lr": 0.003, "grad": 0.1181, "tokens": 119885875200, "tok_s": 159074.4}
|
| 71 |
+
{"step": 114380, "epoch": 0.727, "loss": 1.84519, "ppl": 6.329, "lr": 0.003, "grad": 0.082, "tokens": 119906841600, "tok_s": 158405.4}
|
| 72 |
+
{"step": 114400, "epoch": 0.727, "loss": 1.81188, "ppl": 6.122, "lr": 0.003, "grad": 0.0674, "tokens": 119927808000, "tok_s": 159065.7}
|
| 73 |
+
{"step": 114420, "epoch": 0.727, "loss": 1.79445, "ppl": 6.016, "lr": 0.003, "grad": 0.1212, "tokens": 119948774400, "tok_s": 158971.6}
|
| 74 |
+
{"step": 114440, "epoch": 0.727, "loss": 1.73389, "ppl": 5.663, "lr": 0.003, "grad": 0.0638, "tokens": 119969740800, "tok_s": 158886.4}
|
| 75 |
+
{"step": 114460, "epoch": 0.727, "loss": 1.77551, "ppl": 5.903, "lr": 0.003, "grad": 0.1217, "tokens": 119990707200, "tok_s": 159156.8}
|
| 76 |
+
{"step": 114480, "epoch": 0.727, "loss": 1.82163, "ppl": 6.182, "lr": 0.003, "grad": 0.1224, "tokens": 120011673600, "tok_s": 158739.8}
|
| 77 |
+
{"step": 114500, "epoch": 0.727, "loss": 1.78047, "ppl": 5.933, "lr": 0.003, "grad": 0.0804, "tokens": 120032640000, "tok_s": 158808.7}
|
| 78 |
+
{"step": 114520, "epoch": 0.728, "loss": 1.78579, "ppl": 5.964, "lr": 0.003, "grad": 0.1135, "tokens": 120053606400, "tok_s": 159059.1}
|
| 79 |
+
{"step": 114540, "epoch": 0.728, "loss": 1.71035, "ppl": 5.531, "lr": 0.003, "grad": 0.0838, "tokens": 120074572800, "tok_s": 158981.3}
|
| 80 |
+
{"step": 114560, "epoch": 0.728, "loss": 1.79175, "ppl": 6.0, "lr": 0.003, "grad": 0.1555, "tokens": 120095539200, "tok_s": 158791.8}
|
| 81 |
+
{"step": 114580, "epoch": 0.728, "loss": 1.5919, "ppl": 4.913, "lr": 0.003, "grad": 0.0864, "tokens": 120116505600, "tok_s": 158876.7}
|
| 82 |
+
{"step": 114600, "epoch": 0.728, "loss": 1.7677, "ppl": 5.857, "lr": 0.003, "grad": 0.0918, "tokens": 120137472000, "tok_s": 159010.6}
|
| 83 |
+
{"step": 114620, "epoch": 0.728, "loss": 1.76809, "ppl": 5.86, "lr": 0.003, "grad": 0.0838, "tokens": 120158438400, "tok_s": 159039.8}
|
| 84 |
+
{"step": 114640, "epoch": 0.728, "loss": 1.73248, "ppl": 5.655, "lr": 0.003, "grad": 0.1019, "tokens": 120179404800, "tok_s": 158605.1}
|
| 85 |
+
{"step": 114660, "epoch": 0.729, "loss": 1.78428, "ppl": 5.955, "lr": 0.003, "grad": 0.0737, "tokens": 120200371200, "tok_s": 159053.2}
|
| 86 |
+
{"step": 114680, "epoch": 0.729, "loss": 1.75854, "ppl": 5.804, "lr": 0.003, "grad": 0.0847, "tokens": 120221337600, "tok_s": 158948.7}
|
| 87 |
+
{"step": 114700, "epoch": 0.729, "loss": 1.7305, "ppl": 5.643, "lr": 0.003, "grad": 0.0854, "tokens": 120242304000, "tok_s": 158333.8}
|
| 88 |
+
{"step": 114720, "epoch": 0.729, "loss": 1.70834, "ppl": 5.52, "lr": 0.003, "grad": 0.0769, "tokens": 120263270400, "tok_s": 158564.2}
|
| 89 |
+
{"step": 114740, "epoch": 0.729, "loss": 1.74569, "ppl": 5.73, "lr": 0.003, "grad": 0.1032, "tokens": 120284236800, "tok_s": 158797.5}
|
| 90 |
+
{"step": 114760, "epoch": 0.729, "loss": 1.63865, "ppl": 5.148, "lr": 0.003, "grad": 0.0829, "tokens": 120305203200, "tok_s": 158980.6}
|
| 91 |
+
{"step": 114780, "epoch": 0.729, "loss": 1.71827, "ppl": 5.575, "lr": 0.003, "grad": 0.1409, "tokens": 120326169600, "tok_s": 158993.3}
|
| 92 |
+
{"step": 114800, "epoch": 0.729, "loss": 1.73932, "ppl": 5.693, "lr": 0.003, "grad": 0.0752, "tokens": 120347136000, "tok_s": 159065.8}
|
| 93 |
+
{"step": 114820, "epoch": 0.73, "loss": 1.76451, "ppl": 5.839, "lr": 0.003, "grad": 0.113, "tokens": 120368102400, "tok_s": 159110.5}
|
| 94 |
+
{"step": 114840, "epoch": 0.73, "loss": 1.7788, "ppl": 5.923, "lr": 0.003, "grad": 0.0734, "tokens": 120389068800, "tok_s": 158867.6}
|
| 95 |
+
{"step": 114860, "epoch": 0.73, "loss": 1.78937, "ppl": 5.986, "lr": 0.003, "grad": 0.0778, "tokens": 120410035200, "tok_s": 158720.1}
|
| 96 |
+
{"step": 114880, "epoch": 0.73, "loss": 1.76945, "ppl": 5.868, "lr": 0.003, "grad": 0.1273, "tokens": 120431001600, "tok_s": 158880.3}
|
| 97 |
+
{"step": 114900, "epoch": 0.73, "loss": 1.75438, "ppl": 5.78, "lr": 0.003, "grad": 0.0804, "tokens": 120451968000, "tok_s": 159036.7}
|
| 98 |
+
{"step": 114920, "epoch": 0.73, "loss": 1.7785, "ppl": 5.921, "lr": 0.003, "grad": 0.1014, "tokens": 120472934400, "tok_s": 159052.1}
|
| 99 |
+
{"step": 114940, "epoch": 0.73, "loss": 1.72752, "ppl": 5.627, "lr": 0.003, "grad": 0.0834, "tokens": 120493900800, "tok_s": 158927.0}
|
| 100 |
+
{"step": 114960, "epoch": 0.73, "loss": 1.75104, "ppl": 5.761, "lr": 0.003, "grad": 0.0814, "tokens": 120514867200, "tok_s": 158793.7}
|
| 101 |
+
{"step": 114980, "epoch": 0.731, "loss": 1.79737, "ppl": 6.034, "lr": 0.003, "grad": 0.1131, "tokens": 120535833600, "tok_s": 158841.1}
|
| 102 |
+
{"step": 115000, "epoch": 0.731, "loss": 1.72563, "ppl": 5.616, "lr": 0.003, "grad": 0.0991, "tokens": 120556800000, "tok_s": 158972.4}
|
| 103 |
+
{"step": 115000, "val_loss": 1.74251, "val_ppl": 5.712, "is_best": false}
|
| 104 |
+
{"step": 115020, "epoch": 0.731, "loss": 1.76095, "ppl": 5.818, "lr": 0.003, "grad": 0.1495, "tokens": 120577766400, "tok_s": 158306.4}
|
| 105 |
+
{"step": 115040, "epoch": 0.731, "loss": 1.75017, "ppl": 5.756, "lr": 0.003, "grad": 0.0803, "tokens": 120598732800, "tok_s": 159033.7}
|
| 106 |
+
{"step": 115060, "epoch": 0.731, "loss": 1.69637, "ppl": 5.454, "lr": 0.003, "grad": 0.0703, "tokens": 120619699200, "tok_s": 159083.2}
|
| 107 |
+
{"step": 115080, "epoch": 0.731, "loss": 1.7665, "ppl": 5.85, "lr": 0.003, "grad": 0.1583, "tokens": 120640665600, "tok_s": 158597.5}
|
| 108 |
+
{"step": 115100, "epoch": 0.731, "loss": 1.7566, "ppl": 5.793, "lr": 0.003, "grad": 0.0979, "tokens": 120661632000, "tok_s": 158933.4}
|
| 109 |
+
{"step": 115120, "epoch": 0.731, "loss": 1.82904, "ppl": 6.228, "lr": 0.003, "grad": 0.0963, "tokens": 120682598400, "tok_s": 159013.9}
|
| 110 |
+
{"step": 115140, "epoch": 0.732, "loss": 1.77106, "ppl": 5.877, "lr": 0.003, "grad": 0.0801, "tokens": 120703564800, "tok_s": 158756.2}
|
| 111 |
+
{"step": 115160, "epoch": 0.732, "loss": 1.7239, "ppl": 5.606, "lr": 0.003, "grad": 0.0624, "tokens": 120724531200, "tok_s": 158983.3}
|
| 112 |
+
{"step": 115180, "epoch": 0.732, "loss": 1.7504, "ppl": 5.757, "lr": 0.003, "grad": 0.1288, "tokens": 120745497600, "tok_s": 158951.9}
|
| 113 |
+
{"step": 115200, "epoch": 0.732, "loss": 1.80402, "ppl": 6.074, "lr": 0.003, "grad": 0.1111, "tokens": 120766464000, "tok_s": 158157.1}
|
| 114 |
+
{"step": 115220, "epoch": 0.732, "loss": 1.70762, "ppl": 5.516, "lr": 0.003, "grad": 0.0672, "tokens": 120787430400, "tok_s": 158909.4}
|
| 115 |
+
{"step": 115240, "epoch": 0.732, "loss": 1.75081, "ppl": 5.759, "lr": 0.003, "grad": 0.1099, "tokens": 120808396800, "tok_s": 158974.1}
|
| 116 |
+
{"step": 115260, "epoch": 0.732, "loss": 1.66476, "ppl": 5.284, "lr": 0.003, "grad": 0.0723, "tokens": 120829363200, "tok_s": 158565.8}
|
| 117 |
+
{"step": 115280, "epoch": 0.732, "loss": 1.76276, "ppl": 5.828, "lr": 0.003, "grad": 0.055, "tokens": 120850329600, "tok_s": 158962.6}
|
| 118 |
+
{"step": 115300, "epoch": 0.733, "loss": 1.78751, "ppl": 5.975, "lr": 0.003, "grad": 0.081, "tokens": 120871296000, "tok_s": 158890.7}
|
| 119 |
+
{"step": 115320, "epoch": 0.733, "loss": 1.66815, "ppl": 5.302, "lr": 0.003, "grad": 0.0606, "tokens": 120892262400, "tok_s": 158953.0}
|
| 120 |
+
{"step": 115340, "epoch": 0.733, "loss": 1.63292, "ppl": 5.119, "lr": 0.003, "grad": 0.0829, "tokens": 120913228800, "tok_s": 158889.8}
|
| 121 |
+
{"step": 115360, "epoch": 0.733, "loss": 1.76008, "ppl": 5.813, "lr": 0.003, "grad": 0.1001, "tokens": 120934195200, "tok_s": 158990.0}
|
| 122 |
+
{"step": 115380, "epoch": 0.733, "loss": 1.73241, "ppl": 5.654, "lr": 0.003, "grad": 0.0689, "tokens": 120955161600, "tok_s": 159126.8}
|
| 123 |
+
{"step": 115400, "epoch": 0.733, "loss": 1.65046, "ppl": 5.209, "lr": 0.003, "grad": 0.0858, "tokens": 120976128000, "tok_s": 159175.1}
|
| 124 |
+
{"step": 115420, "epoch": 0.733, "loss": 1.66761, "ppl": 5.299, "lr": 0.003, "grad": 0.0863, "tokens": 120997094400, "tok_s": 158915.4}
|
| 125 |
+
{"step": 115440, "epoch": 0.733, "loss": 1.85483, "ppl": 6.391, "lr": 0.003, "grad": 0.119, "tokens": 121018060800, "tok_s": 159069.3}
|
| 126 |
+
{"step": 115460, "epoch": 0.734, "loss": 1.64881, "ppl": 5.201, "lr": 0.003, "grad": 0.0977, "tokens": 121039027200, "tok_s": 158967.5}
|
| 127 |
+
{"step": 115480, "epoch": 0.734, "loss": 1.72542, "ppl": 5.615, "lr": 0.003, "grad": 0.0658, "tokens": 121059993600, "tok_s": 159130.9}
|
| 128 |
+
{"step": 115500, "epoch": 0.734, "loss": 1.69981, "ppl": 5.473, "lr": 0.003, "grad": 0.0547, "tokens": 121080960000, "tok_s": 159090.4}
|
| 129 |
+
{"step": 115520, "epoch": 0.734, "loss": 1.71325, "ppl": 5.547, "lr": 0.003, "grad": 0.0535, "tokens": 121101926400, "tok_s": 158661.9}
|
| 130 |
+
{"step": 115540, "epoch": 0.734, "loss": 1.71585, "ppl": 5.561, "lr": 0.003, "grad": 0.076, "tokens": 121122892800, "tok_s": 159083.5}
|
| 131 |
+
{"step": 115560, "epoch": 0.734, "loss": 1.81402, "ppl": 6.135, "lr": 0.003, "grad": 0.1009, "tokens": 121143859200, "tok_s": 159142.5}
|
| 132 |
+
{"step": 115580, "epoch": 0.734, "loss": 1.74548, "ppl": 5.729, "lr": 0.003, "grad": 0.0976, "tokens": 121164825600, "tok_s": 158682.1}
|
| 133 |
+
{"step": 115600, "epoch": 0.734, "loss": 1.77462, "ppl": 5.898, "lr": 0.003, "grad": 0.0858, "tokens": 121185792000, "tok_s": 159262.0}
|
| 134 |
+
{"step": 115620, "epoch": 0.735, "loss": 1.7396, "ppl": 5.695, "lr": 0.003, "grad": 0.1201, "tokens": 121206758400, "tok_s": 158993.1}
|
| 135 |
+
{"step": 115640, "epoch": 0.735, "loss": 1.77629, "ppl": 5.908, "lr": 0.003, "grad": 0.0664, "tokens": 121227724800, "tok_s": 159152.3}
|
| 136 |
+
{"step": 115660, "epoch": 0.735, "loss": 1.64546, "ppl": 5.183, "lr": 0.003, "grad": 0.1268, "tokens": 121248691200, "tok_s": 159114.1}
|
| 137 |
+
{"step": 115680, "epoch": 0.735, "loss": 1.7395, "ppl": 5.695, "lr": 0.003, "grad": 0.0946, "tokens": 121269657600, "tok_s": 158968.0}
|
| 138 |
+
{"step": 115700, "epoch": 0.735, "loss": 1.69873, "ppl": 5.467, "lr": 0.003, "grad": 0.1181, "tokens": 121290624000, "tok_s": 158996.3}
|
| 139 |
+
{"step": 115720, "epoch": 0.735, "loss": 1.78564, "ppl": 5.963, "lr": 0.003, "grad": 0.097, "tokens": 121311590400, "tok_s": 159080.3}
|
| 140 |
+
{"step": 115740, "epoch": 0.735, "loss": 1.60998, "ppl": 5.003, "lr": 0.003, "grad": 0.1052, "tokens": 121332556800, "tok_s": 158828.3}
|
| 141 |
+
{"step": 115760, "epoch": 0.735, "loss": 1.77713, "ppl": 5.913, "lr": 0.003, "grad": 0.0884, "tokens": 121353523200, "tok_s": 158637.6}
|
| 142 |
+
{"step": 115780, "epoch": 0.736, "loss": 1.78343, "ppl": 5.95, "lr": 0.003, "grad": 0.1031, "tokens": 121374489600, "tok_s": 158460.2}
|
| 143 |
+
{"step": 115800, "epoch": 0.736, "loss": 1.75974, "ppl": 5.811, "lr": 0.003, "grad": 0.1039, "tokens": 121395456000, "tok_s": 158956.9}
|
| 144 |
+
{"step": 115820, "epoch": 0.736, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.089, "tokens": 121416422400, "tok_s": 158579.3}
|
| 145 |
+
{"step": 115840, "epoch": 0.736, "loss": 1.77844, "ppl": 5.921, "lr": 0.003, "grad": 0.1064, "tokens": 121437388800, "tok_s": 159003.3}
|
| 146 |
+
{"step": 115860, "epoch": 0.736, "loss": 1.80231, "ppl": 6.064, "lr": 0.003, "grad": 0.078, "tokens": 121458355200, "tok_s": 159003.1}
|
| 147 |
+
{"step": 115880, "epoch": 0.736, "loss": 1.71566, "ppl": 5.56, "lr": 0.003, "grad": 0.0837, "tokens": 121479321600, "tok_s": 158575.5}
|
| 148 |
+
{"step": 115900, "epoch": 0.736, "loss": 1.77074, "ppl": 5.875, "lr": 0.003, "grad": 0.0898, "tokens": 121500288000, "tok_s": 158867.6}
|
| 149 |
+
{"step": 115920, "epoch": 0.737, "loss": 1.76584, "ppl": 5.847, "lr": 0.003, "grad": 0.086, "tokens": 121521254400, "tok_s": 158639.9}
|
| 150 |
+
{"step": 115940, "epoch": 0.737, "loss": 1.73363, "ppl": 5.661, "lr": 0.003, "grad": 0.1066, "tokens": 121542220800, "tok_s": 158912.7}
|
| 151 |
+
{"step": 115960, "epoch": 0.737, "loss": 1.78966, "ppl": 5.987, "lr": 0.003, "grad": 0.0879, "tokens": 121563187200, "tok_s": 159044.0}
|
| 152 |
+
{"step": 115980, "epoch": 0.737, "loss": 1.76167, "ppl": 5.822, "lr": 0.003, "grad": 0.1034, "tokens": 121584153600, "tok_s": 159061.2}
|
| 153 |
+
{"step": 116000, "epoch": 0.737, "loss": 1.76646, "ppl": 5.85, "lr": 0.003, "grad": 0.1287, "tokens": 121605120000, "tok_s": 159044.7}
|
| 154 |
+
{"step": 116000, "val_loss": 1.75047, "val_ppl": 5.757, "is_best": false}
|
| 155 |
+
{"step": 116020, "epoch": 0.737, "loss": 1.69817, "ppl": 5.464, "lr": 0.003, "grad": 0.0588, "tokens": 121626086400, "tok_s": 159041.3}
|
| 156 |
+
{"step": 116040, "epoch": 0.737, "loss": 1.75483, "ppl": 5.782, "lr": 0.003, "grad": 0.08, "tokens": 121647052800, "tok_s": 159020.1}
|
| 157 |
+
{"step": 116060, "epoch": 0.737, "loss": 1.73774, "ppl": 5.684, "lr": 0.003, "grad": 0.0962, "tokens": 121668019200, "tok_s": 158982.9}
|
| 158 |
+
{"step": 116080, "epoch": 0.738, "loss": 1.77812, "ppl": 5.919, "lr": 0.003, "grad": 0.1196, "tokens": 121688985600, "tok_s": 159013.1}
|
| 159 |
+
{"step": 116100, "epoch": 0.738, "loss": 1.77472, "ppl": 5.899, "lr": 0.003, "grad": 0.0621, "tokens": 121709952000, "tok_s": 159054.4}
|
| 160 |
+
{"step": 116120, "epoch": 0.738, "loss": 1.74142, "ppl": 5.705, "lr": 0.003, "grad": 0.1002, "tokens": 121730918400, "tok_s": 158834.3}
|
| 161 |
+
{"step": 116140, "epoch": 0.738, "loss": 1.72689, "ppl": 5.623, "lr": 0.003, "grad": 0.0847, "tokens": 121751884800, "tok_s": 158780.7}
|
| 162 |
+
{"step": 116160, "epoch": 0.738, "loss": 1.73821, "ppl": 5.687, "lr": 0.003, "grad": 0.0998, "tokens": 121772851200, "tok_s": 158849.0}
|
| 163 |
+
{"step": 116180, "epoch": 0.738, "loss": 1.68236, "ppl": 5.378, "lr": 0.003, "grad": 0.0976, "tokens": 121793817600, "tok_s": 158891.5}
|
| 164 |
+
{"step": 116200, "epoch": 0.738, "loss": 1.74406, "ppl": 5.721, "lr": 0.003, "grad": 0.1012, "tokens": 121814784000, "tok_s": 159071.4}
|
| 165 |
+
{"step": 116220, "epoch": 0.738, "loss": 1.73084, "ppl": 5.645, "lr": 0.003, "grad": 0.1192, "tokens": 121835750400, "tok_s": 158905.5}
|
| 166 |
+
{"step": 116240, "epoch": 0.739, "loss": 1.73463, "ppl": 5.667, "lr": 0.003, "grad": 0.1083, "tokens": 121856716800, "tok_s": 158817.1}
|
| 167 |
+
{"step": 116260, "epoch": 0.739, "loss": 1.74894, "ppl": 5.749, "lr": 0.003, "grad": 0.1143, "tokens": 121877683200, "tok_s": 158958.4}
|
| 168 |
+
{"step": 116280, "epoch": 0.739, "loss": 1.77149, "ppl": 5.88, "lr": 0.003, "grad": 0.0946, "tokens": 121898649600, "tok_s": 158874.4}
|
| 169 |
+
{"step": 116300, "epoch": 0.739, "loss": 1.82361, "ppl": 6.194, "lr": 0.003, "grad": 0.0758, "tokens": 121919616000, "tok_s": 158962.9}
|
| 170 |
+
{"step": 116320, "epoch": 0.739, "loss": 1.72426, "ppl": 5.608, "lr": 0.003, "grad": 0.0706, "tokens": 121940582400, "tok_s": 158750.2}
|
| 171 |
+
{"step": 116340, "epoch": 0.739, "loss": 1.75324, "ppl": 5.773, "lr": 0.003, "grad": 0.0837, "tokens": 121961548800, "tok_s": 158796.4}
|
| 172 |
+
{"step": 116360, "epoch": 0.739, "loss": 1.74039, "ppl": 5.7, "lr": 0.003, "grad": 0.1439, "tokens": 121982515200, "tok_s": 158899.5}
|
| 173 |
+
{"step": 116380, "epoch": 0.739, "loss": 1.69343, "ppl": 5.438, "lr": 0.003, "grad": 0.1456, "tokens": 122003481600, "tok_s": 158735.1}
|
| 174 |
+
{"step": 116400, "epoch": 0.74, "loss": 1.71463, "ppl": 5.555, "lr": 0.003, "grad": 0.1132, "tokens": 122024448000, "tok_s": 158585.2}
|
| 175 |
+
{"step": 116420, "epoch": 0.74, "loss": 1.74055, "ppl": 5.7, "lr": 0.003, "grad": 0.1266, "tokens": 122045414400, "tok_s": 158491.4}
|
| 176 |
+
{"step": 116440, "epoch": 0.74, "loss": 1.72903, "ppl": 5.635, "lr": 0.003, "grad": 0.1016, "tokens": 122066380800, "tok_s": 159072.2}
|
| 177 |
+
{"step": 116460, "epoch": 0.74, "loss": 1.74042, "ppl": 5.7, "lr": 0.003, "grad": 0.0572, "tokens": 122087347200, "tok_s": 158891.6}
|
| 178 |
+
{"step": 116480, "epoch": 0.74, "loss": 1.6533, "ppl": 5.224, "lr": 0.003, "grad": 0.1325, "tokens": 122108313600, "tok_s": 158632.5}
|
| 179 |
+
{"step": 116500, "epoch": 0.74, "loss": 1.86506, "ppl": 6.456, "lr": 0.003, "grad": 0.116, "tokens": 122129280000, "tok_s": 159036.6}
|
| 180 |
+
{"step": 116520, "epoch": 0.74, "loss": 1.79135, "ppl": 5.998, "lr": 0.003, "grad": 0.0853, "tokens": 122150246400, "tok_s": 158103.0}
|
| 181 |
+
{"step": 116540, "epoch": 0.74, "loss": 1.69744, "ppl": 5.46, "lr": 0.003, "grad": 0.0947, "tokens": 122171212800, "tok_s": 158913.5}
|
| 182 |
+
{"step": 116560, "epoch": 0.741, "loss": 1.84827, "ppl": 6.349, "lr": 0.003, "grad": 0.1629, "tokens": 122192179200, "tok_s": 158852.1}
|
| 183 |
+
{"step": 116580, "epoch": 0.741, "loss": 1.73205, "ppl": 5.652, "lr": 0.003, "grad": 0.0689, "tokens": 122213145600, "tok_s": 159076.3}
|
| 184 |
+
{"step": 116600, "epoch": 0.741, "loss": 1.82115, "ppl": 6.179, "lr": 0.003, "grad": 0.0896, "tokens": 122234112000, "tok_s": 159093.4}
|
| 185 |
+
{"step": 116620, "epoch": 0.741, "loss": 1.73873, "ppl": 5.69, "lr": 0.003, "grad": 0.1122, "tokens": 122255078400, "tok_s": 158578.8}
|
| 186 |
+
{"step": 116640, "epoch": 0.741, "loss": 1.75494, "ppl": 5.783, "lr": 0.003, "grad": 0.0905, "tokens": 122276044800, "tok_s": 158821.3}
|
| 187 |
+
{"step": 116660, "epoch": 0.741, "loss": 1.6383, "ppl": 5.146, "lr": 0.003, "grad": 0.0996, "tokens": 122297011200, "tok_s": 158989.5}
|
| 188 |
+
{"step": 116680, "epoch": 0.741, "loss": 1.46931, "ppl": 4.346, "lr": 0.003, "grad": 0.0836, "tokens": 122317977600, "tok_s": 158990.2}
|
| 189 |
+
{"step": 116700, "epoch": 0.741, "loss": 1.80059, "ppl": 6.053, "lr": 0.003, "grad": 0.0724, "tokens": 122338944000, "tok_s": 158811.1}
|
| 190 |
+
{"step": 116720, "epoch": 0.742, "loss": 1.70257, "ppl": 5.488, "lr": 0.003, "grad": 0.1328, "tokens": 122359910400, "tok_s": 158979.9}
|
| 191 |
+
{"step": 116740, "epoch": 0.742, "loss": 1.71656, "ppl": 5.565, "lr": 0.003, "grad": 0.0936, "tokens": 122380876800, "tok_s": 158909.5}
|
| 192 |
+
{"step": 116760, "epoch": 0.742, "loss": 1.74442, "ppl": 5.723, "lr": 0.003, "grad": 0.0831, "tokens": 122401843200, "tok_s": 158623.7}
|
| 193 |
+
{"step": 116780, "epoch": 0.742, "loss": 1.70911, "ppl": 5.524, "lr": 0.003, "grad": 0.124, "tokens": 122422809600, "tok_s": 158474.7}
|
| 194 |
+
{"step": 116800, "epoch": 0.742, "loss": 1.76719, "ppl": 5.854, "lr": 0.003, "grad": 0.1094, "tokens": 122443776000, "tok_s": 158319.0}
|
| 195 |
+
{"step": 116820, "epoch": 0.742, "loss": 1.75072, "ppl": 5.759, "lr": 0.003, "grad": 0.0642, "tokens": 122464742400, "tok_s": 158778.0}
|
| 196 |
+
{"step": 116840, "epoch": 0.742, "loss": 1.76635, "ppl": 5.849, "lr": 0.003, "grad": 0.1284, "tokens": 122485708800, "tok_s": 158649.5}
|
| 197 |
+
{"step": 116860, "epoch": 0.742, "loss": 1.74052, "ppl": 5.7, "lr": 0.003, "grad": 0.1281, "tokens": 122506675200, "tok_s": 158699.8}
|
| 198 |
+
{"step": 116880, "epoch": 0.743, "loss": 1.74391, "ppl": 5.72, "lr": 0.003, "grad": 0.1097, "tokens": 122527641600, "tok_s": 158824.1}
|
| 199 |
+
{"step": 116900, "epoch": 0.743, "loss": 1.73173, "ppl": 5.65, "lr": 0.003, "grad": 0.0696, "tokens": 122548608000, "tok_s": 158982.9}
|
| 200 |
+
{"step": 116920, "epoch": 0.743, "loss": 1.73157, "ppl": 5.65, "lr": 0.003, "grad": 0.0991, "tokens": 122569574400, "tok_s": 158775.5}
|
| 201 |
+
{"step": 116940, "epoch": 0.743, "loss": 1.73989, "ppl": 5.697, "lr": 0.003, "grad": 0.159, "tokens": 122590540800, "tok_s": 158944.8}
|
| 202 |
+
{"step": 116960, "epoch": 0.743, "loss": 1.76898, "ppl": 5.865, "lr": 0.003, "grad": 0.1056, "tokens": 122611507200, "tok_s": 158621.4}
|
| 203 |
+
{"step": 116980, "epoch": 0.743, "loss": 1.7378, "ppl": 5.685, "lr": 0.003, "grad": 0.1382, "tokens": 122632473600, "tok_s": 159078.5}
|
| 204 |
+
{"step": 117000, "epoch": 0.743, "loss": 1.76831, "ppl": 5.861, "lr": 0.003, "grad": 0.0971, "tokens": 122653440000, "tok_s": 159003.9}
|
| 205 |
+
{"step": 117000, "val_loss": 1.75079, "val_ppl": 5.759, "is_best": false}
|
| 206 |
+
{"step": 117020, "epoch": 0.744, "loss": 1.71809, "ppl": 5.574, "lr": 0.003, "grad": 0.0998, "tokens": 122674406400, "tok_s": 158644.0}
|
| 207 |
+
{"step": 117040, "epoch": 0.744, "loss": 1.7722, "ppl": 5.884, "lr": 0.003, "grad": 0.1121, "tokens": 122695372800, "tok_s": 158974.5}
|
| 208 |
+
{"step": 117060, "epoch": 0.744, "loss": 1.71916, "ppl": 5.58, "lr": 0.003, "grad": 0.0674, "tokens": 122716339200, "tok_s": 159075.8}
|
| 209 |
+
{"step": 117080, "epoch": 0.744, "loss": 1.78277, "ppl": 5.946, "lr": 0.003, "grad": 0.1477, "tokens": 122737305600, "tok_s": 158791.3}
|
| 210 |
+
{"step": 117100, "epoch": 0.744, "loss": 1.7563, "ppl": 5.791, "lr": 0.003, "grad": 0.0895, "tokens": 122758272000, "tok_s": 158468.3}
|
| 211 |
+
{"step": 117120, "epoch": 0.744, "loss": 1.77948, "ppl": 5.927, "lr": 0.003, "grad": 0.15, "tokens": 122779238400, "tok_s": 158988.1}
|
| 212 |
+
{"step": 117140, "epoch": 0.744, "loss": 1.7164, "ppl": 5.564, "lr": 0.003, "grad": 0.0726, "tokens": 122800204800, "tok_s": 158663.6}
|
| 213 |
+
{"step": 117160, "epoch": 0.744, "loss": 1.75619, "ppl": 5.79, "lr": 0.003, "grad": 0.1018, "tokens": 122821171200, "tok_s": 158860.5}
|
| 214 |
+
{"step": 117180, "epoch": 0.745, "loss": 1.76838, "ppl": 5.861, "lr": 0.003, "grad": 0.0813, "tokens": 122842137600, "tok_s": 158926.2}
|
| 215 |
+
{"step": 117200, "epoch": 0.745, "loss": 1.7982, "ppl": 6.039, "lr": 0.003, "grad": 0.0825, "tokens": 122863104000, "tok_s": 158786.2}
|
| 216 |
+
{"step": 117220, "epoch": 0.745, "loss": 1.79282, "ppl": 6.006, "lr": 0.003, "grad": 0.1358, "tokens": 122884070400, "tok_s": 158869.8}
|
| 217 |
+
{"step": 117240, "epoch": 0.745, "loss": 1.7632, "ppl": 5.831, "lr": 0.003, "grad": 0.0696, "tokens": 122905036800, "tok_s": 158771.4}
|
| 218 |
+
{"step": 117260, "epoch": 0.745, "loss": 1.72012, "ppl": 5.585, "lr": 0.003, "grad": 0.126, "tokens": 122926003200, "tok_s": 158895.6}
|
| 219 |
+
{"step": 117280, "epoch": 0.745, "loss": 1.8043, "ppl": 6.076, "lr": 0.003, "grad": 0.1057, "tokens": 122946969600, "tok_s": 158727.1}
|
| 220 |
+
{"step": 117300, "epoch": 0.745, "loss": 1.77255, "ppl": 5.886, "lr": 0.003, "grad": 0.1498, "tokens": 122967936000, "tok_s": 158824.7}
|
| 221 |
+
{"step": 117320, "epoch": 0.745, "loss": 1.71903, "ppl": 5.579, "lr": 0.003, "grad": 0.0768, "tokens": 122988902400, "tok_s": 158875.6}
|
| 222 |
+
{"step": 117340, "epoch": 0.746, "loss": 1.77827, "ppl": 5.92, "lr": 0.003, "grad": 0.1023, "tokens": 123009868800, "tok_s": 158012.6}
|
| 223 |
+
{"step": 117360, "epoch": 0.746, "loss": 1.71795, "ppl": 5.573, "lr": 0.003, "grad": 0.1437, "tokens": 123030835200, "tok_s": 158970.9}
|
| 224 |
+
{"step": 117380, "epoch": 0.746, "loss": 1.76465, "ppl": 5.84, "lr": 0.003, "grad": 0.0824, "tokens": 123051801600, "tok_s": 158822.1}
|
| 225 |
+
{"step": 117400, "epoch": 0.746, "loss": 1.64906, "ppl": 5.202, "lr": 0.003, "grad": 0.0716, "tokens": 123072768000, "tok_s": 158925.8}
|
| 226 |
+
{"step": 117420, "epoch": 0.746, "loss": 1.7589, "ppl": 5.806, "lr": 0.003, "grad": 0.1349, "tokens": 123093734400, "tok_s": 158977.8}
|
| 227 |
+
{"step": 117440, "epoch": 0.746, "loss": 1.75542, "ppl": 5.786, "lr": 0.003, "grad": 0.0861, "tokens": 123114700800, "tok_s": 158890.7}
|
| 228 |
+
{"step": 117460, "epoch": 0.746, "loss": 1.76478, "ppl": 5.84, "lr": 0.003, "grad": 0.1475, "tokens": 123135667200, "tok_s": 158597.2}
|
| 229 |
+
{"step": 117480, "epoch": 0.746, "loss": 1.91712, "ppl": 6.801, "lr": 0.003, "grad": 0.1135, "tokens": 123156633600, "tok_s": 158547.3}
|
| 230 |
+
{"step": 117500, "epoch": 0.747, "loss": 1.79511, "ppl": 6.02, "lr": 0.003, "grad": 0.0739, "tokens": 123177600000, "tok_s": 158732.4}
|
| 231 |
+
{"step": 117520, "epoch": 0.747, "loss": 1.74559, "ppl": 5.729, "lr": 0.003, "grad": 0.1338, "tokens": 123198566400, "tok_s": 158958.9}
|
| 232 |
+
{"step": 117540, "epoch": 0.747, "loss": 1.7385, "ppl": 5.689, "lr": 0.003, "grad": 0.0601, "tokens": 123219532800, "tok_s": 159248.7}
|
| 233 |
+
{"step": 117560, "epoch": 0.747, "loss": 1.80996, "ppl": 6.11, "lr": 0.003, "grad": 0.1379, "tokens": 123240499200, "tok_s": 158940.9}
|
| 234 |
+
{"step": 117580, "epoch": 0.747, "loss": 1.72163, "ppl": 5.594, "lr": 0.003, "grad": 0.1094, "tokens": 123261465600, "tok_s": 159118.4}
|
| 235 |
+
{"step": 117600, "epoch": 0.747, "loss": 1.7544, "ppl": 5.78, "lr": 0.003, "grad": 0.0721, "tokens": 123282432000, "tok_s": 158785.1}
|
| 236 |
+
{"step": 117620, "epoch": 0.747, "loss": 1.77002, "ppl": 5.871, "lr": 0.003, "grad": 0.0813, "tokens": 123303398400, "tok_s": 158885.5}
|
| 237 |
+
{"step": 117640, "epoch": 0.747, "loss": 1.73973, "ppl": 5.696, "lr": 0.003, "grad": 0.0763, "tokens": 123324364800, "tok_s": 159361.3}
|
| 238 |
+
{"step": 117660, "epoch": 0.748, "loss": 1.71485, "ppl": 5.556, "lr": 0.003, "grad": 0.1062, "tokens": 123345331200, "tok_s": 159210.8}
|
| 239 |
+
{"step": 117680, "epoch": 0.748, "loss": 1.79598, "ppl": 6.025, "lr": 0.003, "grad": 0.0735, "tokens": 123366297600, "tok_s": 159098.4}
|
| 240 |
+
{"step": 117700, "epoch": 0.748, "loss": 1.71054, "ppl": 5.532, "lr": 0.003, "grad": 0.0773, "tokens": 123387264000, "tok_s": 159263.9}
|
| 241 |
+
{"step": 117720, "epoch": 0.748, "loss": 1.73981, "ppl": 5.696, "lr": 0.003, "grad": 0.0927, "tokens": 123408230400, "tok_s": 159349.5}
|
| 242 |
+
{"step": 117740, "epoch": 0.748, "loss": 1.7662, "ppl": 5.849, "lr": 0.003, "grad": 0.159, "tokens": 123429196800, "tok_s": 159133.1}
|
| 243 |
+
{"step": 117760, "epoch": 0.748, "loss": 1.78008, "ppl": 5.93, "lr": 0.003, "grad": 0.0897, "tokens": 123450163200, "tok_s": 159172.4}
|
| 244 |
+
{"step": 117780, "epoch": 0.748, "loss": 1.73595, "ppl": 5.674, "lr": 0.003, "grad": 0.1225, "tokens": 123471129600, "tok_s": 159134.9}
|
| 245 |
+
{"step": 117800, "epoch": 0.748, "loss": 1.77009, "ppl": 5.871, "lr": 0.003, "grad": 0.0826, "tokens": 123492096000, "tok_s": 159189.9}
|
| 246 |
+
{"step": 117820, "epoch": 0.749, "loss": 1.70693, "ppl": 5.512, "lr": 0.003, "grad": 0.0736, "tokens": 123513062400, "tok_s": 159206.2}
|
| 247 |
+
{"step": 117840, "epoch": 0.749, "loss": 1.75002, "ppl": 5.755, "lr": 0.003, "grad": 0.0742, "tokens": 123534028800, "tok_s": 159167.4}
|
| 248 |
+
{"step": 117860, "epoch": 0.749, "loss": 1.75708, "ppl": 5.795, "lr": 0.003, "grad": 0.1352, "tokens": 123554995200, "tok_s": 158528.0}
|
| 249 |
+
{"step": 117880, "epoch": 0.749, "loss": 1.6667, "ppl": 5.295, "lr": 0.003, "grad": 0.0639, "tokens": 123575961600, "tok_s": 159112.7}
|
| 250 |
+
{"step": 117900, "epoch": 0.749, "loss": 1.75414, "ppl": 5.778, "lr": 0.003, "grad": 0.1051, "tokens": 123596928000, "tok_s": 159150.4}
|
| 251 |
+
{"step": 117920, "epoch": 0.749, "loss": 1.7382, "ppl": 5.687, "lr": 0.003, "grad": 0.0682, "tokens": 123617894400, "tok_s": 159112.6}
|
| 252 |
+
{"step": 117940, "epoch": 0.749, "loss": 1.72741, "ppl": 5.626, "lr": 0.003, "grad": 0.122, "tokens": 123638860800, "tok_s": 159174.2}
|
| 253 |
+
{"step": 117960, "epoch": 0.749, "loss": 1.69962, "ppl": 5.472, "lr": 0.003, "grad": 0.0788, "tokens": 123659827200, "tok_s": 158155.3}
|
| 254 |
+
{"step": 117980, "epoch": 0.75, "loss": 1.76584, "ppl": 5.846, "lr": 0.003, "grad": 0.0925, "tokens": 123680793600, "tok_s": 158932.0}
|
| 255 |
+
{"step": 118000, "epoch": 0.75, "loss": 1.78268, "ppl": 5.946, "lr": 0.003, "grad": 0.1168, "tokens": 123701760000, "tok_s": 158320.3}
|
| 256 |
+
{"step": 118000, "val_loss": 1.75262, "val_ppl": 5.77, "is_best": false}
|
logs/log_119000.jsonl
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 118000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-05T19:25:40.381447"}
|
| 2 |
+
{"step": 118020, "epoch": 0.75, "loss": 1.73979, "ppl": 5.696, "lr": 0.003, "grad": 0.0904, "tokens": 123722726400, "tok_s": 158304.5}
|
| 3 |
+
{"step": 118040, "epoch": 0.75, "loss": 1.74056, "ppl": 5.701, "lr": 0.003, "grad": 0.0638, "tokens": 123743692800, "tok_s": 158016.5}
|
| 4 |
+
{"step": 118060, "epoch": 0.75, "loss": 1.71538, "ppl": 5.559, "lr": 0.003, "grad": 0.1665, "tokens": 123764659200, "tok_s": 158294.3}
|
| 5 |
+
{"step": 118080, "epoch": 0.75, "loss": 1.61202, "ppl": 5.013, "lr": 0.003, "grad": 0.1077, "tokens": 123785625600, "tok_s": 158421.7}
|
| 6 |
+
{"step": 118100, "epoch": 0.75, "loss": 1.76723, "ppl": 5.855, "lr": 0.003, "grad": 0.1292, "tokens": 123806592000, "tok_s": 158338.1}
|
| 7 |
+
{"step": 118120, "epoch": 0.75, "loss": 1.72861, "ppl": 5.633, "lr": 0.003, "grad": 0.079, "tokens": 123827558400, "tok_s": 158489.0}
|
| 8 |
+
{"step": 118140, "epoch": 0.751, "loss": 1.74261, "ppl": 5.712, "lr": 0.003, "grad": 0.0913, "tokens": 123848524800, "tok_s": 158102.0}
|
| 9 |
+
{"step": 118160, "epoch": 0.751, "loss": 1.67597, "ppl": 5.344, "lr": 0.003, "grad": 0.0904, "tokens": 123869491200, "tok_s": 158332.4}
|
| 10 |
+
{"step": 118180, "epoch": 0.751, "loss": 1.62789, "ppl": 5.093, "lr": 0.003, "grad": 0.0735, "tokens": 123890457600, "tok_s": 157954.9}
|
| 11 |
+
{"step": 118200, "epoch": 0.751, "loss": 1.59216, "ppl": 4.914, "lr": 0.003, "grad": 0.1055, "tokens": 123911424000, "tok_s": 158124.6}
|
| 12 |
+
{"step": 118220, "epoch": 0.751, "loss": 1.77912, "ppl": 5.925, "lr": 0.003, "grad": 0.0698, "tokens": 123932390400, "tok_s": 158541.3}
|
| 13 |
+
{"step": 118240, "epoch": 0.751, "loss": 1.70235, "ppl": 5.487, "lr": 0.003, "grad": 0.118, "tokens": 123953356800, "tok_s": 158605.3}
|
| 14 |
+
{"step": 118260, "epoch": 0.751, "loss": 1.75982, "ppl": 5.811, "lr": 0.003, "grad": 0.0774, "tokens": 123974323200, "tok_s": 157719.7}
|
| 15 |
+
{"step": 118280, "epoch": 0.752, "loss": 1.70922, "ppl": 5.525, "lr": 0.003, "grad": 0.1039, "tokens": 123995289600, "tok_s": 157979.7}
|
| 16 |
+
{"step": 118300, "epoch": 0.752, "loss": 1.75378, "ppl": 5.776, "lr": 0.003, "grad": 0.0803, "tokens": 124016256000, "tok_s": 158562.7}
|
| 17 |
+
{"step": 118320, "epoch": 0.752, "loss": 1.75956, "ppl": 5.81, "lr": 0.003, "grad": 0.094, "tokens": 124037222400, "tok_s": 158133.7}
|
| 18 |
+
{"step": 118340, "epoch": 0.752, "loss": 1.72452, "ppl": 5.61, "lr": 0.003, "grad": 0.0816, "tokens": 124058188800, "tok_s": 157996.3}
|
| 19 |
+
{"step": 118360, "epoch": 0.752, "loss": 1.77153, "ppl": 5.88, "lr": 0.003, "grad": 0.0658, "tokens": 124079155200, "tok_s": 158511.8}
|
| 20 |
+
{"step": 118380, "epoch": 0.752, "loss": 1.68067, "ppl": 5.369, "lr": 0.003, "grad": 0.0788, "tokens": 124100121600, "tok_s": 157873.7}
|
| 21 |
+
{"step": 118400, "epoch": 0.752, "loss": 1.78125, "ppl": 5.937, "lr": 0.003, "grad": 0.1265, "tokens": 124121088000, "tok_s": 158508.4}
|
| 22 |
+
{"step": 118420, "epoch": 0.752, "loss": 1.75976, "ppl": 5.811, "lr": 0.003, "grad": 0.0963, "tokens": 124142054400, "tok_s": 158543.6}
|
| 23 |
+
{"step": 118440, "epoch": 0.753, "loss": 1.67067, "ppl": 5.316, "lr": 0.003, "grad": 0.0701, "tokens": 124163020800, "tok_s": 158495.1}
|
| 24 |
+
{"step": 118460, "epoch": 0.753, "loss": 1.81095, "ppl": 6.116, "lr": 0.003, "grad": 0.118, "tokens": 124183987200, "tok_s": 158618.8}
|
| 25 |
+
{"step": 118480, "epoch": 0.753, "loss": 1.80713, "ppl": 6.093, "lr": 0.003, "grad": 0.1225, "tokens": 124204953600, "tok_s": 158643.1}
|
| 26 |
+
{"step": 118500, "epoch": 0.753, "loss": 1.90087, "ppl": 6.692, "lr": 0.003, "grad": 0.0971, "tokens": 124225920000, "tok_s": 158526.0}
|
| 27 |
+
{"step": 118520, "epoch": 0.753, "loss": 1.7631, "ppl": 5.83, "lr": 0.003, "grad": 0.0917, "tokens": 124246886400, "tok_s": 158524.9}
|
| 28 |
+
{"step": 118540, "epoch": 0.753, "loss": 1.65783, "ppl": 5.248, "lr": 0.003, "grad": 0.0625, "tokens": 124267852800, "tok_s": 158043.8}
|
| 29 |
+
{"step": 118560, "epoch": 0.753, "loss": 1.67888, "ppl": 5.36, "lr": 0.003, "grad": 0.1154, "tokens": 124288819200, "tok_s": 158294.7}
|
| 30 |
+
{"step": 118580, "epoch": 0.753, "loss": 1.70275, "ppl": 5.489, "lr": 0.003, "grad": 0.1018, "tokens": 124309785600, "tok_s": 158415.3}
|
| 31 |
+
{"step": 118600, "epoch": 0.754, "loss": 1.63827, "ppl": 5.146, "lr": 0.003, "grad": 0.0825, "tokens": 124330752000, "tok_s": 158406.3}
|
| 32 |
+
{"step": 118620, "epoch": 0.754, "loss": 1.71381, "ppl": 5.55, "lr": 0.003, "grad": 0.1082, "tokens": 124351718400, "tok_s": 158419.1}
|
| 33 |
+
{"step": 118640, "epoch": 0.754, "loss": 1.6619, "ppl": 5.269, "lr": 0.003, "grad": 0.1085, "tokens": 124372684800, "tok_s": 158500.8}
|
| 34 |
+
{"step": 118660, "epoch": 0.754, "loss": 1.84244, "ppl": 6.312, "lr": 0.003, "grad": 0.1561, "tokens": 124393651200, "tok_s": 158192.5}
|
| 35 |
+
{"step": 118680, "epoch": 0.754, "loss": 1.77033, "ppl": 5.873, "lr": 0.003, "grad": 0.1412, "tokens": 124414617600, "tok_s": 157722.2}
|
| 36 |
+
{"step": 118700, "epoch": 0.754, "loss": 1.74147, "ppl": 5.706, "lr": 0.003, "grad": 0.111, "tokens": 124435584000, "tok_s": 158601.6}
|
| 37 |
+
{"step": 118720, "epoch": 0.754, "loss": 1.66524, "ppl": 5.287, "lr": 0.003, "grad": 0.0856, "tokens": 124456550400, "tok_s": 158448.0}
|
| 38 |
+
{"step": 118740, "epoch": 0.754, "loss": 1.69815, "ppl": 5.464, "lr": 0.003, "grad": 0.0807, "tokens": 124477516800, "tok_s": 158113.7}
|
| 39 |
+
{"step": 118760, "epoch": 0.755, "loss": 1.76824, "ppl": 5.861, "lr": 0.003, "grad": 0.1075, "tokens": 124498483200, "tok_s": 158253.1}
|
| 40 |
+
{"step": 118780, "epoch": 0.755, "loss": 1.67594, "ppl": 5.344, "lr": 0.003, "grad": 0.1487, "tokens": 124519449600, "tok_s": 158222.0}
|
| 41 |
+
{"step": 118800, "epoch": 0.755, "loss": 1.69363, "ppl": 5.439, "lr": 0.003, "grad": 0.1075, "tokens": 124540416000, "tok_s": 158604.0}
|
| 42 |
+
{"step": 118820, "epoch": 0.755, "loss": 1.7418, "ppl": 5.708, "lr": 0.003, "grad": 0.1089, "tokens": 124561382400, "tok_s": 158553.7}
|
| 43 |
+
{"step": 118840, "epoch": 0.755, "loss": 1.67568, "ppl": 5.342, "lr": 0.003, "grad": 0.0724, "tokens": 124582348800, "tok_s": 157825.5}
|
| 44 |
+
{"step": 118860, "epoch": 0.755, "loss": 1.75391, "ppl": 5.777, "lr": 0.003, "grad": 0.087, "tokens": 124603315200, "tok_s": 158545.7}
|
| 45 |
+
{"step": 118880, "epoch": 0.755, "loss": 1.77945, "ppl": 5.927, "lr": 0.003, "grad": 0.097, "tokens": 124624281600, "tok_s": 158515.1}
|
| 46 |
+
{"step": 118900, "epoch": 0.755, "loss": 1.44913, "ppl": 4.259, "lr": 0.003, "grad": 0.077, "tokens": 124645248000, "tok_s": 158522.8}
|
| 47 |
+
{"step": 118920, "epoch": 0.756, "loss": 1.67776, "ppl": 5.354, "lr": 0.003, "grad": 0.1038, "tokens": 124666214400, "tok_s": 158597.0}
|
| 48 |
+
{"step": 118940, "epoch": 0.756, "loss": 1.69051, "ppl": 5.422, "lr": 0.003, "grad": 0.0728, "tokens": 124687180800, "tok_s": 158127.2}
|
| 49 |
+
{"step": 118960, "epoch": 0.756, "loss": 1.78371, "ppl": 5.952, "lr": 0.003, "grad": 0.1134, "tokens": 124708147200, "tok_s": 158357.3}
|
| 50 |
+
{"step": 118980, "epoch": 0.756, "loss": 1.73447, "ppl": 5.666, "lr": 0.003, "grad": 0.0627, "tokens": 124729113600, "tok_s": 158191.1}
|
| 51 |
+
{"step": 119000, "epoch": 0.756, "loss": 1.89018, "ppl": 6.621, "lr": 0.003, "grad": 0.1249, "tokens": 124750080000, "tok_s": 158547.0}
|
| 52 |
+
{"step": 119000, "val_loss": 1.73142, "val_ppl": 5.649, "is_best": true}
|
logs/log_1200.jsonl
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"step": 0, "val_loss": 10.49104, "val_ppl": 35991.696, "event": "baseline"}
|
| 2 |
+
{"event": "run_start", "step": 0, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-08-24T08:07:55.793331"}
|
| 3 |
+
{"step": 20, "epoch": 0.0, "loss": 10.00133, "ppl": 22055.751, "lr": 1.14e-05, "grad": 37.068, "tokens": 20966400, "tok_s": 172775.5}
|
| 4 |
+
{"step": 40, "epoch": 0.0, "loss": 8.59175, "ppl": 5387.013, "lr": 2.34e-05, "grad": 28.3726, "tokens": 41932800, "tok_s": 172937.2}
|
| 5 |
+
{"step": 60, "epoch": 0.0, "loss": 6.9577, "ppl": 1051.209, "lr": 3.54e-05, "grad": 15.4672, "tokens": 62899200, "tok_s": 171954.7}
|
| 6 |
+
{"step": 80, "epoch": 0.001, "loss": 6.10022, "ppl": 445.956, "lr": 4.74e-05, "grad": 3.3802, "tokens": 83865600, "tok_s": 171593.5}
|
| 7 |
+
{"step": 100, "epoch": 0.001, "loss": 5.3088, "ppl": 202.108, "lr": 5.94e-05, "grad": 1.4898, "tokens": 104832000, "tok_s": 170499.4}
|
| 8 |
+
{"step": 120, "epoch": 0.001, "loss": 4.90389, "ppl": 134.813, "lr": 7.14e-05, "grad": 1.9621, "tokens": 125798400, "tok_s": 172173.8}
|
| 9 |
+
{"step": 140, "epoch": 0.001, "loss": 4.5892, "ppl": 98.416, "lr": 8.34e-05, "grad": 2.3138, "tokens": 146764800, "tok_s": 171461.6}
|
| 10 |
+
{"step": 160, "epoch": 0.001, "loss": 4.5499, "ppl": 94.622, "lr": 9.54e-05, "grad": 2.46, "tokens": 167731200, "tok_s": 171382.8}
|
| 11 |
+
{"step": 180, "epoch": 0.001, "loss": 4.60043, "ppl": 99.527, "lr": 0.0001074, "grad": 2.4066, "tokens": 188697600, "tok_s": 171570.0}
|
| 12 |
+
{"step": 200, "epoch": 0.001, "loss": 4.30209, "ppl": 73.854, "lr": 0.0001194, "grad": 2.4149, "tokens": 209664000, "tok_s": 171552.7}
|
| 13 |
+
{"step": 220, "epoch": 0.001, "loss": 4.09963, "ppl": 60.318, "lr": 0.0001314, "grad": 1.8715, "tokens": 230630400, "tok_s": 171712.7}
|
| 14 |
+
{"step": 240, "epoch": 0.002, "loss": 4.00958, "ppl": 55.124, "lr": 0.0001434, "grad": 1.9908, "tokens": 251596800, "tok_s": 172042.1}
|
| 15 |
+
{"step": 260, "epoch": 0.002, "loss": 3.86855, "ppl": 47.873, "lr": 0.0001554, "grad": 2.3225, "tokens": 272563200, "tok_s": 171731.6}
|
| 16 |
+
{"step": 280, "epoch": 0.002, "loss": 3.75183, "ppl": 42.599, "lr": 0.0001674, "grad": 2.0695, "tokens": 293529600, "tok_s": 172008.6}
|
| 17 |
+
{"step": 300, "epoch": 0.002, "loss": 3.69336, "ppl": 40.18, "lr": 0.0001794, "grad": 2.5492, "tokens": 314496000, "tok_s": 172326.9}
|
| 18 |
+
{"step": 320, "epoch": 0.002, "loss": 3.57319, "ppl": 35.63, "lr": 0.0001914, "grad": 2.412, "tokens": 335462400, "tok_s": 171703.9}
|
| 19 |
+
{"step": 340, "epoch": 0.002, "loss": 3.60289, "ppl": 36.704, "lr": 0.0002034, "grad": 2.0398, "tokens": 356428800, "tok_s": 171858.2}
|
| 20 |
+
{"step": 360, "epoch": 0.002, "loss": 3.34449, "ppl": 28.346, "lr": 0.0002154, "grad": 2.4563, "tokens": 377395200, "tok_s": 172282.9}
|
| 21 |
+
{"step": 380, "epoch": 0.002, "loss": 3.28026, "ppl": 26.583, "lr": 0.0002274, "grad": 2.4287, "tokens": 398361600, "tok_s": 171848.8}
|
| 22 |
+
{"step": 400, "epoch": 0.003, "loss": 3.33565, "ppl": 28.097, "lr": 0.0002394, "grad": 2.4523, "tokens": 419328000, "tok_s": 171456.9}
|
| 23 |
+
{"step": 400, "val_loss": 3.25207, "val_ppl": 25.844, "is_best": true}
|
| 24 |
+
{"step": 420, "epoch": 0.003, "loss": 3.22959, "ppl": 25.269, "lr": 0.0002514, "grad": 2.3092, "tokens": 440294400, "tok_s": 171610.1}
|
| 25 |
+
{"step": 440, "epoch": 0.003, "loss": 3.19835, "ppl": 24.492, "lr": 0.0002634, "grad": 1.8276, "tokens": 461260800, "tok_s": 171778.0}
|
| 26 |
+
{"step": 460, "epoch": 0.003, "loss": 3.10423, "ppl": 22.292, "lr": 0.0002754, "grad": 1.6567, "tokens": 482227200, "tok_s": 171556.3}
|
| 27 |
+
{"step": 480, "epoch": 0.003, "loss": 3.02305, "ppl": 20.554, "lr": 0.0002874, "grad": 1.4746, "tokens": 503193600, "tok_s": 170875.8}
|
| 28 |
+
{"step": 500, "epoch": 0.003, "loss": 3.12357, "ppl": 22.727, "lr": 0.0002994, "grad": 2.1034, "tokens": 524160000, "tok_s": 171423.9}
|
| 29 |
+
{"step": 520, "epoch": 0.003, "loss": 2.92963, "ppl": 18.721, "lr": 0.0003114, "grad": 1.4317, "tokens": 545126400, "tok_s": 171403.2}
|
| 30 |
+
{"step": 540, "epoch": 0.003, "loss": 2.89405, "ppl": 18.066, "lr": 0.0003234, "grad": 1.104, "tokens": 566092800, "tok_s": 171780.2}
|
| 31 |
+
{"step": 560, "epoch": 0.004, "loss": 2.78032, "ppl": 16.124, "lr": 0.0003354, "grad": 1.3908, "tokens": 587059200, "tok_s": 171398.1}
|
| 32 |
+
{"step": 580, "epoch": 0.004, "loss": 2.75927, "ppl": 15.788, "lr": 0.0003474, "grad": 1.1704, "tokens": 608025600, "tok_s": 170778.2}
|
| 33 |
+
{"step": 600, "epoch": 0.004, "loss": 2.66598, "ppl": 14.382, "lr": 0.0003594, "grad": 1.1193, "tokens": 628992000, "tok_s": 171633.5}
|
| 34 |
+
{"step": 620, "epoch": 0.004, "loss": 2.63012, "ppl": 13.875, "lr": 0.0003714, "grad": 1.1105, "tokens": 649958400, "tok_s": 170722.3}
|
| 35 |
+
{"step": 640, "epoch": 0.004, "loss": 2.49658, "ppl": 12.141, "lr": 0.0003834, "grad": 0.944, "tokens": 670924800, "tok_s": 170958.9}
|
| 36 |
+
{"step": 660, "epoch": 0.004, "loss": 2.65886, "ppl": 14.28, "lr": 0.0003954, "grad": 1.016, "tokens": 691891200, "tok_s": 171924.5}
|
| 37 |
+
{"step": 680, "epoch": 0.004, "loss": 2.56511, "ppl": 13.002, "lr": 0.0004074, "grad": 1.0432, "tokens": 712857600, "tok_s": 172185.5}
|
| 38 |
+
{"step": 700, "epoch": 0.004, "loss": 2.50747, "ppl": 12.274, "lr": 0.0004194, "grad": 0.8524, "tokens": 733824000, "tok_s": 171722.4}
|
| 39 |
+
{"step": 720, "epoch": 0.005, "loss": 2.41101, "ppl": 11.145, "lr": 0.0004314, "grad": 0.8144, "tokens": 754790400, "tok_s": 171379.1}
|
| 40 |
+
{"step": 740, "epoch": 0.005, "loss": 2.42836, "ppl": 11.34, "lr": 0.0004434, "grad": 0.8319, "tokens": 775756800, "tok_s": 171582.8}
|
| 41 |
+
{"step": 760, "epoch": 0.005, "loss": 2.4595, "ppl": 11.699, "lr": 0.0004554, "grad": 0.8166, "tokens": 796723200, "tok_s": 171439.1}
|
| 42 |
+
{"step": 780, "epoch": 0.005, "loss": 2.33295, "ppl": 10.308, "lr": 0.0004674, "grad": 0.7113, "tokens": 817689600, "tok_s": 171218.3}
|
| 43 |
+
{"step": 800, "epoch": 0.005, "loss": 2.38014, "ppl": 10.806, "lr": 0.0004794, "grad": 0.9203, "tokens": 838656000, "tok_s": 171959.2}
|
| 44 |
+
{"step": 800, "val_loss": 2.3876, "val_ppl": 10.887, "is_best": true}
|
| 45 |
+
{"step": 820, "epoch": 0.005, "loss": 2.37145, "ppl": 10.713, "lr": 0.0004914, "grad": 0.6725, "tokens": 859622400, "tok_s": 169138.5}
|
| 46 |
+
{"step": 840, "epoch": 0.005, "loss": 2.27809, "ppl": 9.758, "lr": 0.0005034, "grad": 0.4712, "tokens": 880588800, "tok_s": 171560.0}
|
| 47 |
+
{"step": 860, "epoch": 0.005, "loss": 2.343, "ppl": 10.412, "lr": 0.0005154, "grad": 0.5809, "tokens": 901555200, "tok_s": 171260.1}
|
| 48 |
+
{"step": 880, "epoch": 0.006, "loss": 2.37171, "ppl": 10.716, "lr": 0.0005274, "grad": 0.57, "tokens": 922521600, "tok_s": 171283.3}
|
| 49 |
+
{"step": 900, "epoch": 0.006, "loss": 1.94695, "ppl": 7.007, "lr": 0.0005394, "grad": 0.5244, "tokens": 943488000, "tok_s": 171127.8}
|
| 50 |
+
{"step": 920, "epoch": 0.006, "loss": 2.22533, "ppl": 9.257, "lr": 0.0005514, "grad": 0.5248, "tokens": 964454400, "tok_s": 170613.3}
|
| 51 |
+
{"step": 940, "epoch": 0.006, "loss": 2.20084, "ppl": 9.033, "lr": 0.0005634, "grad": 0.5166, "tokens": 985420800, "tok_s": 171306.5}
|
| 52 |
+
{"step": 960, "epoch": 0.006, "loss": 2.29976, "ppl": 9.972, "lr": 0.0005754, "grad": 0.5099, "tokens": 1006387200, "tok_s": 171391.8}
|
| 53 |
+
{"step": 980, "epoch": 0.006, "loss": 2.24655, "ppl": 9.455, "lr": 0.0005874, "grad": 0.5066, "tokens": 1027353600, "tok_s": 171600.7}
|
| 54 |
+
{"step": 1000, "epoch": 0.006, "loss": 2.36276, "ppl": 10.62, "lr": 0.0005994, "grad": 0.4524, "tokens": 1048320000, "tok_s": 170847.3}
|
| 55 |
+
{"step": 1020, "epoch": 0.006, "loss": 2.21776, "ppl": 9.187, "lr": 0.0006114, "grad": 0.4831, "tokens": 1069286400, "tok_s": 170994.4}
|
| 56 |
+
{"step": 1040, "epoch": 0.007, "loss": 2.16596, "ppl": 8.723, "lr": 0.0006234, "grad": 0.4785, "tokens": 1090252800, "tok_s": 170659.2}
|
| 57 |
+
{"step": 1060, "epoch": 0.007, "loss": 2.23978, "ppl": 9.391, "lr": 0.0006354, "grad": 0.5083, "tokens": 1111219200, "tok_s": 171385.8}
|
| 58 |
+
{"step": 1080, "epoch": 0.007, "loss": 2.19328, "ppl": 8.965, "lr": 0.0006474, "grad": 0.4415, "tokens": 1132185600, "tok_s": 171411.6}
|
| 59 |
+
{"step": 1100, "epoch": 0.007, "loss": 2.03435, "ppl": 7.647, "lr": 0.0006594, "grad": 0.4968, "tokens": 1153152000, "tok_s": 171178.1}
|
| 60 |
+
{"step": 1120, "epoch": 0.007, "loss": 2.30466, "ppl": 10.021, "lr": 0.0006714, "grad": 0.4791, "tokens": 1174118400, "tok_s": 171313.8}
|
| 61 |
+
{"step": 1140, "epoch": 0.007, "loss": 2.19647, "ppl": 8.993, "lr": 0.0006834, "grad": 0.4074, "tokens": 1195084800, "tok_s": 171308.2}
|
| 62 |
+
{"step": 1160, "epoch": 0.007, "loss": 2.182, "ppl": 8.864, "lr": 0.0006954, "grad": 0.3551, "tokens": 1216051200, "tok_s": 171488.1}
|
| 63 |
+
{"step": 1180, "epoch": 0.007, "loss": 2.21962, "ppl": 9.204, "lr": 0.0007074, "grad": 0.4049, "tokens": 1237017600, "tok_s": 171146.0}
|
| 64 |
+
{"step": 1200, "epoch": 0.008, "loss": 2.13219, "ppl": 8.433, "lr": 0.0007194, "grad": 0.4329, "tokens": 1257984000, "tok_s": 170611.8}
|
| 65 |
+
{"step": 1200, "val_loss": 2.17393, "val_ppl": 8.793, "is_best": true}
|
logs/log_12000.jsonl
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 10400, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-08-25T10:47:59.907226"}
|
| 2 |
+
{"step": 10420, "epoch": 0.066, "loss": 1.81711, "ppl": 6.154, "lr": 0.003, "grad": 0.0712, "tokens": 10923494400, "tok_s": 171148.6}
|
| 3 |
+
{"step": 10440, "epoch": 0.066, "loss": 1.81787, "ppl": 6.159, "lr": 0.003, "grad": 0.086, "tokens": 10944460800, "tok_s": 171016.2}
|
| 4 |
+
{"step": 10460, "epoch": 0.066, "loss": 1.79115, "ppl": 5.996, "lr": 0.003, "grad": 0.0605, "tokens": 10965427200, "tok_s": 170717.4}
|
| 5 |
+
{"step": 10480, "epoch": 0.067, "loss": 1.67725, "ppl": 5.351, "lr": 0.003, "grad": 0.0915, "tokens": 10986393600, "tok_s": 170321.1}
|
| 6 |
+
{"step": 10500, "epoch": 0.067, "loss": 1.84034, "ppl": 6.299, "lr": 0.003, "grad": 0.0919, "tokens": 11007360000, "tok_s": 170000.9}
|
| 7 |
+
{"step": 10520, "epoch": 0.067, "loss": 1.80401, "ppl": 6.074, "lr": 0.003, "grad": 0.1176, "tokens": 11028326400, "tok_s": 168719.0}
|
| 8 |
+
{"step": 10540, "epoch": 0.067, "loss": 1.81361, "ppl": 6.133, "lr": 0.003, "grad": 0.0807, "tokens": 11049292800, "tok_s": 169165.5}
|
| 9 |
+
{"step": 10560, "epoch": 0.067, "loss": 1.74588, "ppl": 5.731, "lr": 0.003, "grad": 0.0655, "tokens": 11070259200, "tok_s": 169849.0}
|
| 10 |
+
{"step": 10580, "epoch": 0.067, "loss": 1.69691, "ppl": 5.457, "lr": 0.003, "grad": 0.0736, "tokens": 11091225600, "tok_s": 170408.2}
|
| 11 |
+
{"step": 10600, "epoch": 0.067, "loss": 1.65753, "ppl": 5.246, "lr": 0.003, "grad": 0.1223, "tokens": 11112192000, "tok_s": 169898.8}
|
| 12 |
+
{"step": 10620, "epoch": 0.067, "loss": 1.85511, "ppl": 6.392, "lr": 0.003, "grad": 0.0676, "tokens": 11133158400, "tok_s": 170415.5}
|
| 13 |
+
{"step": 10640, "epoch": 0.068, "loss": 1.77632, "ppl": 5.908, "lr": 0.003, "grad": 0.078, "tokens": 11154124800, "tok_s": 169195.0}
|
| 14 |
+
{"step": 10660, "epoch": 0.068, "loss": 1.83195, "ppl": 6.246, "lr": 0.003, "grad": 0.0815, "tokens": 11175091200, "tok_s": 168839.8}
|
| 15 |
+
{"step": 10680, "epoch": 0.068, "loss": 1.77901, "ppl": 5.924, "lr": 0.003, "grad": 0.0816, "tokens": 11196057600, "tok_s": 168644.0}
|
| 16 |
+
{"step": 10700, "epoch": 0.068, "loss": 1.8274, "ppl": 6.218, "lr": 0.003, "grad": 0.0964, "tokens": 11217024000, "tok_s": 169844.9}
|
| 17 |
+
{"step": 10720, "epoch": 0.068, "loss": 1.83423, "ppl": 6.26, "lr": 0.003, "grad": 0.0657, "tokens": 11237990400, "tok_s": 170037.3}
|
| 18 |
+
{"step": 10740, "epoch": 0.068, "loss": 1.79705, "ppl": 6.032, "lr": 0.003, "grad": 0.0661, "tokens": 11258956800, "tok_s": 170105.2}
|
| 19 |
+
{"step": 10760, "epoch": 0.068, "loss": 1.84121, "ppl": 6.304, "lr": 0.003, "grad": 0.0637, "tokens": 11279923200, "tok_s": 170654.2}
|
| 20 |
+
{"step": 10780, "epoch": 0.068, "loss": 1.75043, "ppl": 5.757, "lr": 0.003, "grad": 0.0791, "tokens": 11300889600, "tok_s": 170585.6}
|
| 21 |
+
{"step": 10800, "epoch": 0.069, "loss": 1.85313, "ppl": 6.38, "lr": 0.003, "grad": 0.0897, "tokens": 11321856000, "tok_s": 170412.0}
|
| 22 |
+
{"step": 10820, "epoch": 0.069, "loss": 1.83289, "ppl": 6.252, "lr": 0.003, "grad": 0.093, "tokens": 11342822400, "tok_s": 169777.8}
|
| 23 |
+
{"step": 10840, "epoch": 0.069, "loss": 1.73753, "ppl": 5.683, "lr": 0.003, "grad": 0.0796, "tokens": 11363788800, "tok_s": 169871.9}
|
| 24 |
+
{"step": 10860, "epoch": 0.069, "loss": 1.88449, "ppl": 6.583, "lr": 0.003, "grad": 0.0983, "tokens": 11384755200, "tok_s": 168428.7}
|
| 25 |
+
{"step": 10880, "epoch": 0.069, "loss": 1.87887, "ppl": 6.546, "lr": 0.003, "grad": 0.1103, "tokens": 11405721600, "tok_s": 169815.4}
|
| 26 |
+
{"step": 10900, "epoch": 0.069, "loss": 1.99021, "ppl": 7.317, "lr": 0.003, "grad": 0.0932, "tokens": 11426688000, "tok_s": 169229.2}
|
| 27 |
+
{"step": 10920, "epoch": 0.069, "loss": 1.83739, "ppl": 6.28, "lr": 0.003, "grad": 0.0665, "tokens": 11447654400, "tok_s": 170114.2}
|
| 28 |
+
{"step": 10940, "epoch": 0.07, "loss": 1.72401, "ppl": 5.607, "lr": 0.003, "grad": 0.0633, "tokens": 11468620800, "tok_s": 169434.3}
|
| 29 |
+
{"step": 10960, "epoch": 0.07, "loss": 1.74373, "ppl": 5.719, "lr": 0.003, "grad": 0.0749, "tokens": 11489587200, "tok_s": 170351.3}
|
| 30 |
+
{"step": 10980, "epoch": 0.07, "loss": 1.77352, "ppl": 5.892, "lr": 0.003, "grad": 0.0824, "tokens": 11510553600, "tok_s": 170245.3}
|
| 31 |
+
{"step": 11000, "epoch": 0.07, "loss": 1.70794, "ppl": 5.518, "lr": 0.003, "grad": 0.0825, "tokens": 11531520000, "tok_s": 169701.7}
|
| 32 |
+
{"step": 11000, "val_loss": 1.78679, "val_ppl": 5.97, "is_best": true}
|
| 33 |
+
{"step": 11020, "epoch": 0.07, "loss": 1.78537, "ppl": 5.962, "lr": 0.003, "grad": 0.1114, "tokens": 11552486400, "tok_s": 168368.6}
|
| 34 |
+
{"step": 11040, "epoch": 0.07, "loss": 1.72767, "ppl": 5.628, "lr": 0.003, "grad": 0.0847, "tokens": 11573452800, "tok_s": 170038.3}
|
| 35 |
+
{"step": 11060, "epoch": 0.07, "loss": 1.91423, "ppl": 6.782, "lr": 0.003, "grad": 0.0639, "tokens": 11594419200, "tok_s": 168720.1}
|
| 36 |
+
{"step": 11080, "epoch": 0.07, "loss": 1.83942, "ppl": 6.293, "lr": 0.003, "grad": 0.1332, "tokens": 11615385600, "tok_s": 170605.0}
|
| 37 |
+
{"step": 11100, "epoch": 0.071, "loss": 1.81276, "ppl": 6.127, "lr": 0.003, "grad": 0.1053, "tokens": 11636352000, "tok_s": 169208.5}
|
| 38 |
+
{"step": 11120, "epoch": 0.071, "loss": 1.73442, "ppl": 5.666, "lr": 0.003, "grad": 0.0826, "tokens": 11657318400, "tok_s": 170306.0}
|
| 39 |
+
{"step": 11140, "epoch": 0.071, "loss": 1.76826, "ppl": 5.861, "lr": 0.003, "grad": 0.0732, "tokens": 11678284800, "tok_s": 168532.0}
|
| 40 |
+
{"step": 11160, "epoch": 0.071, "loss": 1.8351, "ppl": 6.266, "lr": 0.003, "grad": 0.087, "tokens": 11699251200, "tok_s": 169730.2}
|
| 41 |
+
{"step": 11180, "epoch": 0.071, "loss": 1.74114, "ppl": 5.704, "lr": 0.003, "grad": 0.0706, "tokens": 11720217600, "tok_s": 169184.3}
|
| 42 |
+
{"step": 11200, "epoch": 0.071, "loss": 1.76407, "ppl": 5.836, "lr": 0.003, "grad": 0.099, "tokens": 11741184000, "tok_s": 169906.0}
|
| 43 |
+
{"step": 11220, "epoch": 0.071, "loss": 1.8116, "ppl": 6.12, "lr": 0.003, "grad": 0.1374, "tokens": 11762150400, "tok_s": 169469.3}
|
| 44 |
+
{"step": 11240, "epoch": 0.071, "loss": 1.74633, "ppl": 5.734, "lr": 0.003, "grad": 0.0705, "tokens": 11783116800, "tok_s": 170350.6}
|
| 45 |
+
{"step": 11260, "epoch": 0.072, "loss": 1.82017, "ppl": 6.173, "lr": 0.003, "grad": 0.0909, "tokens": 11804083200, "tok_s": 168862.4}
|
| 46 |
+
{"step": 11280, "epoch": 0.072, "loss": 1.85324, "ppl": 6.38, "lr": 0.003, "grad": 0.0762, "tokens": 11825049600, "tok_s": 169016.8}
|
| 47 |
+
{"step": 11300, "epoch": 0.072, "loss": 1.50843, "ppl": 4.52, "lr": 0.003, "grad": 0.0973, "tokens": 11846016000, "tok_s": 170226.2}
|
| 48 |
+
{"step": 11320, "epoch": 0.072, "loss": 1.74377, "ppl": 5.719, "lr": 0.003, "grad": 0.1393, "tokens": 11866982400, "tok_s": 169696.7}
|
| 49 |
+
{"step": 11340, "epoch": 0.072, "loss": 1.75525, "ppl": 5.785, "lr": 0.003, "grad": 0.0801, "tokens": 11887948800, "tok_s": 170290.7}
|
| 50 |
+
{"step": 11360, "epoch": 0.072, "loss": 1.85043, "ppl": 6.363, "lr": 0.003, "grad": 0.0813, "tokens": 11908915200, "tok_s": 170230.4}
|
| 51 |
+
{"step": 11380, "epoch": 0.072, "loss": 1.80291, "ppl": 6.067, "lr": 0.003, "grad": 0.0578, "tokens": 11929881600, "tok_s": 170729.7}
|
| 52 |
+
{"step": 11400, "epoch": 0.072, "loss": 1.9575, "ppl": 7.082, "lr": 0.003, "grad": 0.0864, "tokens": 11950848000, "tok_s": 168668.7}
|
| 53 |
+
{"step": 11420, "epoch": 0.073, "loss": 1.7998, "ppl": 6.048, "lr": 0.003, "grad": 0.09, "tokens": 11971814400, "tok_s": 170091.5}
|
| 54 |
+
{"step": 11440, "epoch": 0.073, "loss": 1.7463, "ppl": 5.733, "lr": 0.003, "grad": 0.0852, "tokens": 11992780800, "tok_s": 169692.4}
|
| 55 |
+
{"step": 11460, "epoch": 0.073, "loss": 1.84116, "ppl": 6.304, "lr": 0.003, "grad": 0.0626, "tokens": 12013747200, "tok_s": 169299.7}
|
| 56 |
+
{"step": 11480, "epoch": 0.073, "loss": 1.79223, "ppl": 6.003, "lr": 0.003, "grad": 0.0921, "tokens": 12034713600, "tok_s": 169943.5}
|
| 57 |
+
{"step": 11500, "epoch": 0.073, "loss": 1.66165, "ppl": 5.268, "lr": 0.003, "grad": 0.0543, "tokens": 12055680000, "tok_s": 169881.5}
|
| 58 |
+
{"step": 11520, "epoch": 0.073, "loss": 1.93615, "ppl": 6.932, "lr": 0.003, "grad": 0.0918, "tokens": 12076646400, "tok_s": 170386.0}
|
| 59 |
+
{"step": 11540, "epoch": 0.073, "loss": 1.8309, "ppl": 6.24, "lr": 0.003, "grad": 0.0829, "tokens": 12097612800, "tok_s": 170129.0}
|
| 60 |
+
{"step": 11560, "epoch": 0.073, "loss": 1.82006, "ppl": 6.172, "lr": 0.003, "grad": 0.1309, "tokens": 12118579200, "tok_s": 170568.7}
|
| 61 |
+
{"step": 11580, "epoch": 0.074, "loss": 1.8625, "ppl": 6.44, "lr": 0.003, "grad": 0.1423, "tokens": 12139545600, "tok_s": 170624.8}
|
| 62 |
+
{"step": 11600, "epoch": 0.074, "loss": 1.77661, "ppl": 5.91, "lr": 0.003, "grad": 0.1357, "tokens": 12160512000, "tok_s": 170361.2}
|
| 63 |
+
{"step": 11620, "epoch": 0.074, "loss": 1.8471, "ppl": 6.341, "lr": 0.003, "grad": 0.0764, "tokens": 12181478400, "tok_s": 171363.9}
|
| 64 |
+
{"step": 11640, "epoch": 0.074, "loss": 1.76031, "ppl": 5.814, "lr": 0.003, "grad": 0.1024, "tokens": 12202444800, "tok_s": 170746.7}
|
| 65 |
+
{"step": 11660, "epoch": 0.074, "loss": 1.78822, "ppl": 5.979, "lr": 0.003, "grad": 0.0694, "tokens": 12223411200, "tok_s": 170996.5}
|
| 66 |
+
{"step": 11680, "epoch": 0.074, "loss": 1.66275, "ppl": 5.274, "lr": 0.003, "grad": 0.0948, "tokens": 12244377600, "tok_s": 170823.7}
|
| 67 |
+
{"step": 11700, "epoch": 0.074, "loss": 1.8713, "ppl": 6.497, "lr": 0.003, "grad": 0.1275, "tokens": 12265344000, "tok_s": 170435.7}
|
| 68 |
+
{"step": 11720, "epoch": 0.074, "loss": 1.8123, "ppl": 6.125, "lr": 0.003, "grad": 0.0877, "tokens": 12286310400, "tok_s": 168694.4}
|
| 69 |
+
{"step": 11740, "epoch": 0.075, "loss": 1.86078, "ppl": 6.429, "lr": 0.003, "grad": 0.1272, "tokens": 12307276800, "tok_s": 169127.9}
|
| 70 |
+
{"step": 11760, "epoch": 0.075, "loss": 1.80306, "ppl": 6.068, "lr": 0.003, "grad": 0.1265, "tokens": 12328243200, "tok_s": 169783.7}
|
| 71 |
+
{"step": 11780, "epoch": 0.075, "loss": 1.90736, "ppl": 6.735, "lr": 0.003, "grad": 0.0614, "tokens": 12349209600, "tok_s": 170112.6}
|
| 72 |
+
{"step": 11800, "epoch": 0.075, "loss": 1.87756, "ppl": 6.538, "lr": 0.003, "grad": 0.0773, "tokens": 12370176000, "tok_s": 170478.9}
|
| 73 |
+
{"step": 11820, "epoch": 0.075, "loss": 1.85864, "ppl": 6.415, "lr": 0.003, "grad": 0.0842, "tokens": 12391142400, "tok_s": 171036.7}
|
| 74 |
+
{"step": 11840, "epoch": 0.075, "loss": 1.79777, "ppl": 6.036, "lr": 0.003, "grad": 0.1024, "tokens": 12412108800, "tok_s": 171585.4}
|
| 75 |
+
{"step": 11860, "epoch": 0.075, "loss": 1.83797, "ppl": 6.284, "lr": 0.003, "grad": 0.0862, "tokens": 12433075200, "tok_s": 170427.9}
|
| 76 |
+
{"step": 11880, "epoch": 0.075, "loss": 1.88886, "ppl": 6.612, "lr": 0.003, "grad": 0.0936, "tokens": 12454041600, "tok_s": 170334.5}
|
| 77 |
+
{"step": 11900, "epoch": 0.076, "loss": 1.84497, "ppl": 6.328, "lr": 0.003, "grad": 0.0948, "tokens": 12475008000, "tok_s": 170190.5}
|
| 78 |
+
{"step": 11920, "epoch": 0.076, "loss": 1.85304, "ppl": 6.379, "lr": 0.003, "grad": 0.0761, "tokens": 12495974400, "tok_s": 170717.6}
|
| 79 |
+
{"step": 11940, "epoch": 0.076, "loss": 1.77273, "ppl": 5.887, "lr": 0.003, "grad": 0.0966, "tokens": 12516940800, "tok_s": 169644.2}
|
| 80 |
+
{"step": 11960, "epoch": 0.076, "loss": 1.85574, "ppl": 6.396, "lr": 0.003, "grad": 0.0875, "tokens": 12537907200, "tok_s": 171619.0}
|
| 81 |
+
{"step": 11980, "epoch": 0.076, "loss": 1.64952, "ppl": 5.204, "lr": 0.003, "grad": 0.0757, "tokens": 12558873600, "tok_s": 171298.4}
|
| 82 |
+
{"step": 12000, "epoch": 0.076, "loss": 1.83047, "ppl": 6.237, "lr": 0.003, "grad": 0.1106, "tokens": 12579840000, "tok_s": 170734.5}
|
| 83 |
+
{"step": 12000, "val_loss": 1.80365, "val_ppl": 6.072, "is_best": false}
|
logs/log_120000.jsonl
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 118000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-05T19:25:40.381447"}
|
| 2 |
+
{"step": 118020, "epoch": 0.75, "loss": 1.73979, "ppl": 5.696, "lr": 0.003, "grad": 0.0904, "tokens": 123722726400, "tok_s": 158304.5}
|
| 3 |
+
{"step": 118040, "epoch": 0.75, "loss": 1.74056, "ppl": 5.701, "lr": 0.003, "grad": 0.0638, "tokens": 123743692800, "tok_s": 158016.5}
|
| 4 |
+
{"step": 118060, "epoch": 0.75, "loss": 1.71538, "ppl": 5.559, "lr": 0.003, "grad": 0.1665, "tokens": 123764659200, "tok_s": 158294.3}
|
| 5 |
+
{"step": 118080, "epoch": 0.75, "loss": 1.61202, "ppl": 5.013, "lr": 0.003, "grad": 0.1077, "tokens": 123785625600, "tok_s": 158421.7}
|
| 6 |
+
{"step": 118100, "epoch": 0.75, "loss": 1.76723, "ppl": 5.855, "lr": 0.003, "grad": 0.1292, "tokens": 123806592000, "tok_s": 158338.1}
|
| 7 |
+
{"step": 118120, "epoch": 0.75, "loss": 1.72861, "ppl": 5.633, "lr": 0.003, "grad": 0.079, "tokens": 123827558400, "tok_s": 158489.0}
|
| 8 |
+
{"step": 118140, "epoch": 0.751, "loss": 1.74261, "ppl": 5.712, "lr": 0.003, "grad": 0.0913, "tokens": 123848524800, "tok_s": 158102.0}
|
| 9 |
+
{"step": 118160, "epoch": 0.751, "loss": 1.67597, "ppl": 5.344, "lr": 0.003, "grad": 0.0904, "tokens": 123869491200, "tok_s": 158332.4}
|
| 10 |
+
{"step": 118180, "epoch": 0.751, "loss": 1.62789, "ppl": 5.093, "lr": 0.003, "grad": 0.0735, "tokens": 123890457600, "tok_s": 157954.9}
|
| 11 |
+
{"step": 118200, "epoch": 0.751, "loss": 1.59216, "ppl": 4.914, "lr": 0.003, "grad": 0.1055, "tokens": 123911424000, "tok_s": 158124.6}
|
| 12 |
+
{"step": 118220, "epoch": 0.751, "loss": 1.77912, "ppl": 5.925, "lr": 0.003, "grad": 0.0698, "tokens": 123932390400, "tok_s": 158541.3}
|
| 13 |
+
{"step": 118240, "epoch": 0.751, "loss": 1.70235, "ppl": 5.487, "lr": 0.003, "grad": 0.118, "tokens": 123953356800, "tok_s": 158605.3}
|
| 14 |
+
{"step": 118260, "epoch": 0.751, "loss": 1.75982, "ppl": 5.811, "lr": 0.003, "grad": 0.0774, "tokens": 123974323200, "tok_s": 157719.7}
|
| 15 |
+
{"step": 118280, "epoch": 0.752, "loss": 1.70922, "ppl": 5.525, "lr": 0.003, "grad": 0.1039, "tokens": 123995289600, "tok_s": 157979.7}
|
| 16 |
+
{"step": 118300, "epoch": 0.752, "loss": 1.75378, "ppl": 5.776, "lr": 0.003, "grad": 0.0803, "tokens": 124016256000, "tok_s": 158562.7}
|
| 17 |
+
{"step": 118320, "epoch": 0.752, "loss": 1.75956, "ppl": 5.81, "lr": 0.003, "grad": 0.094, "tokens": 124037222400, "tok_s": 158133.7}
|
| 18 |
+
{"step": 118340, "epoch": 0.752, "loss": 1.72452, "ppl": 5.61, "lr": 0.003, "grad": 0.0816, "tokens": 124058188800, "tok_s": 157996.3}
|
| 19 |
+
{"step": 118360, "epoch": 0.752, "loss": 1.77153, "ppl": 5.88, "lr": 0.003, "grad": 0.0658, "tokens": 124079155200, "tok_s": 158511.8}
|
| 20 |
+
{"step": 118380, "epoch": 0.752, "loss": 1.68067, "ppl": 5.369, "lr": 0.003, "grad": 0.0788, "tokens": 124100121600, "tok_s": 157873.7}
|
| 21 |
+
{"step": 118400, "epoch": 0.752, "loss": 1.78125, "ppl": 5.937, "lr": 0.003, "grad": 0.1265, "tokens": 124121088000, "tok_s": 158508.4}
|
| 22 |
+
{"step": 118420, "epoch": 0.752, "loss": 1.75976, "ppl": 5.811, "lr": 0.003, "grad": 0.0963, "tokens": 124142054400, "tok_s": 158543.6}
|
| 23 |
+
{"step": 118440, "epoch": 0.753, "loss": 1.67067, "ppl": 5.316, "lr": 0.003, "grad": 0.0701, "tokens": 124163020800, "tok_s": 158495.1}
|
| 24 |
+
{"step": 118460, "epoch": 0.753, "loss": 1.81095, "ppl": 6.116, "lr": 0.003, "grad": 0.118, "tokens": 124183987200, "tok_s": 158618.8}
|
| 25 |
+
{"step": 118480, "epoch": 0.753, "loss": 1.80713, "ppl": 6.093, "lr": 0.003, "grad": 0.1225, "tokens": 124204953600, "tok_s": 158643.1}
|
| 26 |
+
{"step": 118500, "epoch": 0.753, "loss": 1.90087, "ppl": 6.692, "lr": 0.003, "grad": 0.0971, "tokens": 124225920000, "tok_s": 158526.0}
|
| 27 |
+
{"step": 118520, "epoch": 0.753, "loss": 1.7631, "ppl": 5.83, "lr": 0.003, "grad": 0.0917, "tokens": 124246886400, "tok_s": 158524.9}
|
| 28 |
+
{"step": 118540, "epoch": 0.753, "loss": 1.65783, "ppl": 5.248, "lr": 0.003, "grad": 0.0625, "tokens": 124267852800, "tok_s": 158043.8}
|
| 29 |
+
{"step": 118560, "epoch": 0.753, "loss": 1.67888, "ppl": 5.36, "lr": 0.003, "grad": 0.1154, "tokens": 124288819200, "tok_s": 158294.7}
|
| 30 |
+
{"step": 118580, "epoch": 0.753, "loss": 1.70275, "ppl": 5.489, "lr": 0.003, "grad": 0.1018, "tokens": 124309785600, "tok_s": 158415.3}
|
| 31 |
+
{"step": 118600, "epoch": 0.754, "loss": 1.63827, "ppl": 5.146, "lr": 0.003, "grad": 0.0825, "tokens": 124330752000, "tok_s": 158406.3}
|
| 32 |
+
{"step": 118620, "epoch": 0.754, "loss": 1.71381, "ppl": 5.55, "lr": 0.003, "grad": 0.1082, "tokens": 124351718400, "tok_s": 158419.1}
|
| 33 |
+
{"step": 118640, "epoch": 0.754, "loss": 1.6619, "ppl": 5.269, "lr": 0.003, "grad": 0.1085, "tokens": 124372684800, "tok_s": 158500.8}
|
| 34 |
+
{"step": 118660, "epoch": 0.754, "loss": 1.84244, "ppl": 6.312, "lr": 0.003, "grad": 0.1561, "tokens": 124393651200, "tok_s": 158192.5}
|
| 35 |
+
{"step": 118680, "epoch": 0.754, "loss": 1.77033, "ppl": 5.873, "lr": 0.003, "grad": 0.1412, "tokens": 124414617600, "tok_s": 157722.2}
|
| 36 |
+
{"step": 118700, "epoch": 0.754, "loss": 1.74147, "ppl": 5.706, "lr": 0.003, "grad": 0.111, "tokens": 124435584000, "tok_s": 158601.6}
|
| 37 |
+
{"step": 118720, "epoch": 0.754, "loss": 1.66524, "ppl": 5.287, "lr": 0.003, "grad": 0.0856, "tokens": 124456550400, "tok_s": 158448.0}
|
| 38 |
+
{"step": 118740, "epoch": 0.754, "loss": 1.69815, "ppl": 5.464, "lr": 0.003, "grad": 0.0807, "tokens": 124477516800, "tok_s": 158113.7}
|
| 39 |
+
{"step": 118760, "epoch": 0.755, "loss": 1.76824, "ppl": 5.861, "lr": 0.003, "grad": 0.1075, "tokens": 124498483200, "tok_s": 158253.1}
|
| 40 |
+
{"step": 118780, "epoch": 0.755, "loss": 1.67594, "ppl": 5.344, "lr": 0.003, "grad": 0.1487, "tokens": 124519449600, "tok_s": 158222.0}
|
| 41 |
+
{"step": 118800, "epoch": 0.755, "loss": 1.69363, "ppl": 5.439, "lr": 0.003, "grad": 0.1075, "tokens": 124540416000, "tok_s": 158604.0}
|
| 42 |
+
{"step": 118820, "epoch": 0.755, "loss": 1.7418, "ppl": 5.708, "lr": 0.003, "grad": 0.1089, "tokens": 124561382400, "tok_s": 158553.7}
|
| 43 |
+
{"step": 118840, "epoch": 0.755, "loss": 1.67568, "ppl": 5.342, "lr": 0.003, "grad": 0.0724, "tokens": 124582348800, "tok_s": 157825.5}
|
| 44 |
+
{"step": 118860, "epoch": 0.755, "loss": 1.75391, "ppl": 5.777, "lr": 0.003, "grad": 0.087, "tokens": 124603315200, "tok_s": 158545.7}
|
| 45 |
+
{"step": 118880, "epoch": 0.755, "loss": 1.77945, "ppl": 5.927, "lr": 0.003, "grad": 0.097, "tokens": 124624281600, "tok_s": 158515.1}
|
| 46 |
+
{"step": 118900, "epoch": 0.755, "loss": 1.44913, "ppl": 4.259, "lr": 0.003, "grad": 0.077, "tokens": 124645248000, "tok_s": 158522.8}
|
| 47 |
+
{"step": 118920, "epoch": 0.756, "loss": 1.67776, "ppl": 5.354, "lr": 0.003, "grad": 0.1038, "tokens": 124666214400, "tok_s": 158597.0}
|
| 48 |
+
{"step": 118940, "epoch": 0.756, "loss": 1.69051, "ppl": 5.422, "lr": 0.003, "grad": 0.0728, "tokens": 124687180800, "tok_s": 158127.2}
|
| 49 |
+
{"step": 118960, "epoch": 0.756, "loss": 1.78371, "ppl": 5.952, "lr": 0.003, "grad": 0.1134, "tokens": 124708147200, "tok_s": 158357.3}
|
| 50 |
+
{"step": 118980, "epoch": 0.756, "loss": 1.73447, "ppl": 5.666, "lr": 0.003, "grad": 0.0627, "tokens": 124729113600, "tok_s": 158191.1}
|
| 51 |
+
{"step": 119000, "epoch": 0.756, "loss": 1.89018, "ppl": 6.621, "lr": 0.003, "grad": 0.1249, "tokens": 124750080000, "tok_s": 158547.0}
|
| 52 |
+
{"step": 119000, "val_loss": 1.73142, "val_ppl": 5.649, "is_best": true}
|
| 53 |
+
{"step": 119020, "epoch": 0.756, "loss": 1.73487, "ppl": 5.668, "lr": 0.003, "grad": 0.0905, "tokens": 124771046400, "tok_s": 158219.6}
|
| 54 |
+
{"step": 119040, "epoch": 0.756, "loss": 1.6774, "ppl": 5.352, "lr": 0.003, "grad": 0.1006, "tokens": 124792012800, "tok_s": 158627.9}
|
| 55 |
+
{"step": 119060, "epoch": 0.756, "loss": 1.77446, "ppl": 5.897, "lr": 0.003, "grad": 0.1015, "tokens": 124812979200, "tok_s": 156897.4}
|
| 56 |
+
{"step": 119080, "epoch": 0.757, "loss": 1.72486, "ppl": 5.612, "lr": 0.003, "grad": 0.1353, "tokens": 124833945600, "tok_s": 158154.9}
|
| 57 |
+
{"step": 119100, "epoch": 0.757, "loss": 1.59788, "ppl": 4.943, "lr": 0.003, "grad": 0.1061, "tokens": 124854912000, "tok_s": 158116.9}
|
| 58 |
+
{"step": 119120, "epoch": 0.757, "loss": 1.86998, "ppl": 6.488, "lr": 0.003, "grad": 0.1451, "tokens": 124875878400, "tok_s": 158367.4}
|
| 59 |
+
{"step": 119140, "epoch": 0.757, "loss": 1.76439, "ppl": 5.838, "lr": 0.003, "grad": 0.0871, "tokens": 124896844800, "tok_s": 158280.7}
|
| 60 |
+
{"step": 119160, "epoch": 0.757, "loss": 1.74972, "ppl": 5.753, "lr": 0.003, "grad": 0.1081, "tokens": 124917811200, "tok_s": 158102.5}
|
| 61 |
+
{"step": 119180, "epoch": 0.757, "loss": 1.79359, "ppl": 6.011, "lr": 0.003, "grad": 0.0719, "tokens": 124938777600, "tok_s": 158504.6}
|
| 62 |
+
{"step": 119200, "epoch": 0.757, "loss": 1.70737, "ppl": 5.514, "lr": 0.003, "grad": 0.1167, "tokens": 124959744000, "tok_s": 158144.0}
|
| 63 |
+
{"step": 119220, "epoch": 0.757, "loss": 1.77966, "ppl": 5.928, "lr": 0.003, "grad": 0.0904, "tokens": 124980710400, "tok_s": 158453.4}
|
| 64 |
+
{"step": 119240, "epoch": 0.758, "loss": 1.69198, "ppl": 5.43, "lr": 0.003, "grad": 0.0899, "tokens": 125001676800, "tok_s": 158364.4}
|
| 65 |
+
{"step": 119260, "epoch": 0.758, "loss": 1.72413, "ppl": 5.608, "lr": 0.003, "grad": 0.121, "tokens": 125022643200, "tok_s": 158461.9}
|
| 66 |
+
{"step": 119280, "epoch": 0.758, "loss": 1.60305, "ppl": 4.968, "lr": 0.003, "grad": 0.11, "tokens": 125043609600, "tok_s": 158381.0}
|
| 67 |
+
{"step": 119300, "epoch": 0.758, "loss": 1.80217, "ppl": 6.063, "lr": 0.003, "grad": 0.094, "tokens": 125064576000, "tok_s": 158595.4}
|
| 68 |
+
{"step": 119320, "epoch": 0.758, "loss": 1.74326, "ppl": 5.716, "lr": 0.003, "grad": 0.0768, "tokens": 125085542400, "tok_s": 158531.8}
|
| 69 |
+
{"step": 119340, "epoch": 0.758, "loss": 1.79594, "ppl": 6.025, "lr": 0.003, "grad": 0.0855, "tokens": 125106508800, "tok_s": 158305.4}
|
| 70 |
+
{"step": 119360, "epoch": 0.758, "loss": 1.73375, "ppl": 5.662, "lr": 0.003, "grad": 0.0825, "tokens": 125127475200, "tok_s": 157920.6}
|
| 71 |
+
{"step": 119380, "epoch": 0.758, "loss": 1.84414, "ppl": 6.323, "lr": 0.003, "grad": 0.0913, "tokens": 125148441600, "tok_s": 158531.8}
|
| 72 |
+
{"step": 119400, "epoch": 0.759, "loss": 1.81026, "ppl": 6.112, "lr": 0.003, "grad": 0.0727, "tokens": 125169408000, "tok_s": 158310.9}
|
| 73 |
+
{"step": 119420, "epoch": 0.759, "loss": 1.79423, "ppl": 6.015, "lr": 0.003, "grad": 0.093, "tokens": 125190374400, "tok_s": 158200.8}
|
| 74 |
+
{"step": 119440, "epoch": 0.759, "loss": 1.73512, "ppl": 5.67, "lr": 0.003, "grad": 0.0858, "tokens": 125211340800, "tok_s": 158638.4}
|
| 75 |
+
{"step": 119460, "epoch": 0.759, "loss": 1.77697, "ppl": 5.912, "lr": 0.003, "grad": 0.1038, "tokens": 125232307200, "tok_s": 157567.2}
|
| 76 |
+
{"step": 119480, "epoch": 0.759, "loss": 1.82226, "ppl": 6.186, "lr": 0.003, "grad": 0.0759, "tokens": 125253273600, "tok_s": 157654.3}
|
| 77 |
+
{"step": 119500, "epoch": 0.759, "loss": 1.78047, "ppl": 5.933, "lr": 0.003, "grad": 0.1256, "tokens": 125274240000, "tok_s": 158489.2}
|
| 78 |
+
{"step": 119520, "epoch": 0.759, "loss": 1.78623, "ppl": 5.967, "lr": 0.003, "grad": 0.0918, "tokens": 125295206400, "tok_s": 158365.4}
|
| 79 |
+
{"step": 119540, "epoch": 0.76, "loss": 1.70974, "ppl": 5.527, "lr": 0.003, "grad": 0.0978, "tokens": 125316172800, "tok_s": 157639.6}
|
| 80 |
+
{"step": 119560, "epoch": 0.76, "loss": 1.7911, "ppl": 5.996, "lr": 0.003, "grad": 0.1486, "tokens": 125337139200, "tok_s": 157989.6}
|
| 81 |
+
{"step": 119580, "epoch": 0.76, "loss": 1.59428, "ppl": 4.925, "lr": 0.003, "grad": 0.0848, "tokens": 125358105600, "tok_s": 158460.6}
|
| 82 |
+
{"step": 119600, "epoch": 0.76, "loss": 1.76708, "ppl": 5.854, "lr": 0.003, "grad": 0.098, "tokens": 125379072000, "tok_s": 158466.4}
|
| 83 |
+
{"step": 119620, "epoch": 0.76, "loss": 1.76648, "ppl": 5.85, "lr": 0.003, "grad": 0.0845, "tokens": 125400038400, "tok_s": 158403.4}
|
| 84 |
+
{"step": 119640, "epoch": 0.76, "loss": 1.73094, "ppl": 5.646, "lr": 0.003, "grad": 0.1216, "tokens": 125421004800, "tok_s": 158445.8}
|
| 85 |
+
{"step": 119660, "epoch": 0.76, "loss": 1.7842, "ppl": 5.955, "lr": 0.003, "grad": 0.0949, "tokens": 125441971200, "tok_s": 158513.3}
|
| 86 |
+
{"step": 119680, "epoch": 0.76, "loss": 1.75771, "ppl": 5.799, "lr": 0.003, "grad": 0.0852, "tokens": 125462937600, "tok_s": 157878.6}
|
| 87 |
+
{"step": 119700, "epoch": 0.761, "loss": 1.73007, "ppl": 5.641, "lr": 0.003, "grad": 0.0806, "tokens": 125483904000, "tok_s": 158358.3}
|
| 88 |
+
{"step": 119720, "epoch": 0.761, "loss": 1.70879, "ppl": 5.522, "lr": 0.003, "grad": 0.1121, "tokens": 125504870400, "tok_s": 158528.5}
|
| 89 |
+
{"step": 119740, "epoch": 0.761, "loss": 1.74589, "ppl": 5.731, "lr": 0.003, "grad": 0.0941, "tokens": 125525836800, "tok_s": 158341.9}
|
| 90 |
+
{"step": 119760, "epoch": 0.761, "loss": 1.63881, "ppl": 5.149, "lr": 0.003, "grad": 0.0731, "tokens": 125546803200, "tok_s": 158367.5}
|
| 91 |
+
{"step": 119780, "epoch": 0.761, "loss": 1.71789, "ppl": 5.573, "lr": 0.003, "grad": 0.0898, "tokens": 125567769600, "tok_s": 158093.5}
|
| 92 |
+
{"step": 119800, "epoch": 0.761, "loss": 1.73879, "ppl": 5.69, "lr": 0.003, "grad": 0.0634, "tokens": 125588736000, "tok_s": 158062.8}
|
| 93 |
+
{"step": 119820, "epoch": 0.761, "loss": 1.76379, "ppl": 5.834, "lr": 0.003, "grad": 0.0926, "tokens": 125609702400, "tok_s": 158018.0}
|
| 94 |
+
{"step": 119840, "epoch": 0.761, "loss": 1.77844, "ppl": 5.921, "lr": 0.003, "grad": 0.0621, "tokens": 125630668800, "tok_s": 158457.5}
|
| 95 |
+
{"step": 119860, "epoch": 0.762, "loss": 1.79022, "ppl": 5.991, "lr": 0.003, "grad": 0.0978, "tokens": 125651635200, "tok_s": 157351.8}
|
| 96 |
+
{"step": 119880, "epoch": 0.762, "loss": 1.76953, "ppl": 5.868, "lr": 0.003, "grad": 0.1406, "tokens": 125672601600, "tok_s": 157745.2}
|
| 97 |
+
{"step": 119900, "epoch": 0.762, "loss": 1.75451, "ppl": 5.781, "lr": 0.003, "grad": 0.1048, "tokens": 125693568000, "tok_s": 158566.8}
|
| 98 |
+
{"step": 119920, "epoch": 0.762, "loss": 1.77878, "ppl": 5.923, "lr": 0.003, "grad": 0.1219, "tokens": 125714534400, "tok_s": 157984.7}
|
| 99 |
+
{"step": 119940, "epoch": 0.762, "loss": 1.72756, "ppl": 5.627, "lr": 0.003, "grad": 0.0799, "tokens": 125735500800, "tok_s": 158248.3}
|
| 100 |
+
{"step": 119960, "epoch": 0.762, "loss": 1.75123, "ppl": 5.762, "lr": 0.003, "grad": 0.092, "tokens": 125756467200, "tok_s": 158026.9}
|
| 101 |
+
{"step": 119980, "epoch": 0.762, "loss": 1.79766, "ppl": 6.036, "lr": 0.003, "grad": 0.0985, "tokens": 125777433600, "tok_s": 158297.1}
|
| 102 |
+
{"step": 120000, "epoch": 0.762, "loss": 1.72787, "ppl": 5.629, "lr": 0.003, "grad": 0.072, "tokens": 125798400000, "tok_s": 158454.4}
|
| 103 |
+
{"step": 120000, "val_loss": 1.74408, "val_ppl": 5.721, "is_best": false}
|
logs/log_121000.jsonl
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 118000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-05T19:25:40.381447"}
|
| 2 |
+
{"step": 118020, "epoch": 0.75, "loss": 1.73979, "ppl": 5.696, "lr": 0.003, "grad": 0.0904, "tokens": 123722726400, "tok_s": 158304.5}
|
| 3 |
+
{"step": 118040, "epoch": 0.75, "loss": 1.74056, "ppl": 5.701, "lr": 0.003, "grad": 0.0638, "tokens": 123743692800, "tok_s": 158016.5}
|
| 4 |
+
{"step": 118060, "epoch": 0.75, "loss": 1.71538, "ppl": 5.559, "lr": 0.003, "grad": 0.1665, "tokens": 123764659200, "tok_s": 158294.3}
|
| 5 |
+
{"step": 118080, "epoch": 0.75, "loss": 1.61202, "ppl": 5.013, "lr": 0.003, "grad": 0.1077, "tokens": 123785625600, "tok_s": 158421.7}
|
| 6 |
+
{"step": 118100, "epoch": 0.75, "loss": 1.76723, "ppl": 5.855, "lr": 0.003, "grad": 0.1292, "tokens": 123806592000, "tok_s": 158338.1}
|
| 7 |
+
{"step": 118120, "epoch": 0.75, "loss": 1.72861, "ppl": 5.633, "lr": 0.003, "grad": 0.079, "tokens": 123827558400, "tok_s": 158489.0}
|
| 8 |
+
{"step": 118140, "epoch": 0.751, "loss": 1.74261, "ppl": 5.712, "lr": 0.003, "grad": 0.0913, "tokens": 123848524800, "tok_s": 158102.0}
|
| 9 |
+
{"step": 118160, "epoch": 0.751, "loss": 1.67597, "ppl": 5.344, "lr": 0.003, "grad": 0.0904, "tokens": 123869491200, "tok_s": 158332.4}
|
| 10 |
+
{"step": 118180, "epoch": 0.751, "loss": 1.62789, "ppl": 5.093, "lr": 0.003, "grad": 0.0735, "tokens": 123890457600, "tok_s": 157954.9}
|
| 11 |
+
{"step": 118200, "epoch": 0.751, "loss": 1.59216, "ppl": 4.914, "lr": 0.003, "grad": 0.1055, "tokens": 123911424000, "tok_s": 158124.6}
|
| 12 |
+
{"step": 118220, "epoch": 0.751, "loss": 1.77912, "ppl": 5.925, "lr": 0.003, "grad": 0.0698, "tokens": 123932390400, "tok_s": 158541.3}
|
| 13 |
+
{"step": 118240, "epoch": 0.751, "loss": 1.70235, "ppl": 5.487, "lr": 0.003, "grad": 0.118, "tokens": 123953356800, "tok_s": 158605.3}
|
| 14 |
+
{"step": 118260, "epoch": 0.751, "loss": 1.75982, "ppl": 5.811, "lr": 0.003, "grad": 0.0774, "tokens": 123974323200, "tok_s": 157719.7}
|
| 15 |
+
{"step": 118280, "epoch": 0.752, "loss": 1.70922, "ppl": 5.525, "lr": 0.003, "grad": 0.1039, "tokens": 123995289600, "tok_s": 157979.7}
|
| 16 |
+
{"step": 118300, "epoch": 0.752, "loss": 1.75378, "ppl": 5.776, "lr": 0.003, "grad": 0.0803, "tokens": 124016256000, "tok_s": 158562.7}
|
| 17 |
+
{"step": 118320, "epoch": 0.752, "loss": 1.75956, "ppl": 5.81, "lr": 0.003, "grad": 0.094, "tokens": 124037222400, "tok_s": 158133.7}
|
| 18 |
+
{"step": 118340, "epoch": 0.752, "loss": 1.72452, "ppl": 5.61, "lr": 0.003, "grad": 0.0816, "tokens": 124058188800, "tok_s": 157996.3}
|
| 19 |
+
{"step": 118360, "epoch": 0.752, "loss": 1.77153, "ppl": 5.88, "lr": 0.003, "grad": 0.0658, "tokens": 124079155200, "tok_s": 158511.8}
|
| 20 |
+
{"step": 118380, "epoch": 0.752, "loss": 1.68067, "ppl": 5.369, "lr": 0.003, "grad": 0.0788, "tokens": 124100121600, "tok_s": 157873.7}
|
| 21 |
+
{"step": 118400, "epoch": 0.752, "loss": 1.78125, "ppl": 5.937, "lr": 0.003, "grad": 0.1265, "tokens": 124121088000, "tok_s": 158508.4}
|
| 22 |
+
{"step": 118420, "epoch": 0.752, "loss": 1.75976, "ppl": 5.811, "lr": 0.003, "grad": 0.0963, "tokens": 124142054400, "tok_s": 158543.6}
|
| 23 |
+
{"step": 118440, "epoch": 0.753, "loss": 1.67067, "ppl": 5.316, "lr": 0.003, "grad": 0.0701, "tokens": 124163020800, "tok_s": 158495.1}
|
| 24 |
+
{"step": 118460, "epoch": 0.753, "loss": 1.81095, "ppl": 6.116, "lr": 0.003, "grad": 0.118, "tokens": 124183987200, "tok_s": 158618.8}
|
| 25 |
+
{"step": 118480, "epoch": 0.753, "loss": 1.80713, "ppl": 6.093, "lr": 0.003, "grad": 0.1225, "tokens": 124204953600, "tok_s": 158643.1}
|
| 26 |
+
{"step": 118500, "epoch": 0.753, "loss": 1.90087, "ppl": 6.692, "lr": 0.003, "grad": 0.0971, "tokens": 124225920000, "tok_s": 158526.0}
|
| 27 |
+
{"step": 118520, "epoch": 0.753, "loss": 1.7631, "ppl": 5.83, "lr": 0.003, "grad": 0.0917, "tokens": 124246886400, "tok_s": 158524.9}
|
| 28 |
+
{"step": 118540, "epoch": 0.753, "loss": 1.65783, "ppl": 5.248, "lr": 0.003, "grad": 0.0625, "tokens": 124267852800, "tok_s": 158043.8}
|
| 29 |
+
{"step": 118560, "epoch": 0.753, "loss": 1.67888, "ppl": 5.36, "lr": 0.003, "grad": 0.1154, "tokens": 124288819200, "tok_s": 158294.7}
|
| 30 |
+
{"step": 118580, "epoch": 0.753, "loss": 1.70275, "ppl": 5.489, "lr": 0.003, "grad": 0.1018, "tokens": 124309785600, "tok_s": 158415.3}
|
| 31 |
+
{"step": 118600, "epoch": 0.754, "loss": 1.63827, "ppl": 5.146, "lr": 0.003, "grad": 0.0825, "tokens": 124330752000, "tok_s": 158406.3}
|
| 32 |
+
{"step": 118620, "epoch": 0.754, "loss": 1.71381, "ppl": 5.55, "lr": 0.003, "grad": 0.1082, "tokens": 124351718400, "tok_s": 158419.1}
|
| 33 |
+
{"step": 118640, "epoch": 0.754, "loss": 1.6619, "ppl": 5.269, "lr": 0.003, "grad": 0.1085, "tokens": 124372684800, "tok_s": 158500.8}
|
| 34 |
+
{"step": 118660, "epoch": 0.754, "loss": 1.84244, "ppl": 6.312, "lr": 0.003, "grad": 0.1561, "tokens": 124393651200, "tok_s": 158192.5}
|
| 35 |
+
{"step": 118680, "epoch": 0.754, "loss": 1.77033, "ppl": 5.873, "lr": 0.003, "grad": 0.1412, "tokens": 124414617600, "tok_s": 157722.2}
|
| 36 |
+
{"step": 118700, "epoch": 0.754, "loss": 1.74147, "ppl": 5.706, "lr": 0.003, "grad": 0.111, "tokens": 124435584000, "tok_s": 158601.6}
|
| 37 |
+
{"step": 118720, "epoch": 0.754, "loss": 1.66524, "ppl": 5.287, "lr": 0.003, "grad": 0.0856, "tokens": 124456550400, "tok_s": 158448.0}
|
| 38 |
+
{"step": 118740, "epoch": 0.754, "loss": 1.69815, "ppl": 5.464, "lr": 0.003, "grad": 0.0807, "tokens": 124477516800, "tok_s": 158113.7}
|
| 39 |
+
{"step": 118760, "epoch": 0.755, "loss": 1.76824, "ppl": 5.861, "lr": 0.003, "grad": 0.1075, "tokens": 124498483200, "tok_s": 158253.1}
|
| 40 |
+
{"step": 118780, "epoch": 0.755, "loss": 1.67594, "ppl": 5.344, "lr": 0.003, "grad": 0.1487, "tokens": 124519449600, "tok_s": 158222.0}
|
| 41 |
+
{"step": 118800, "epoch": 0.755, "loss": 1.69363, "ppl": 5.439, "lr": 0.003, "grad": 0.1075, "tokens": 124540416000, "tok_s": 158604.0}
|
| 42 |
+
{"step": 118820, "epoch": 0.755, "loss": 1.7418, "ppl": 5.708, "lr": 0.003, "grad": 0.1089, "tokens": 124561382400, "tok_s": 158553.7}
|
| 43 |
+
{"step": 118840, "epoch": 0.755, "loss": 1.67568, "ppl": 5.342, "lr": 0.003, "grad": 0.0724, "tokens": 124582348800, "tok_s": 157825.5}
|
| 44 |
+
{"step": 118860, "epoch": 0.755, "loss": 1.75391, "ppl": 5.777, "lr": 0.003, "grad": 0.087, "tokens": 124603315200, "tok_s": 158545.7}
|
| 45 |
+
{"step": 118880, "epoch": 0.755, "loss": 1.77945, "ppl": 5.927, "lr": 0.003, "grad": 0.097, "tokens": 124624281600, "tok_s": 158515.1}
|
| 46 |
+
{"step": 118900, "epoch": 0.755, "loss": 1.44913, "ppl": 4.259, "lr": 0.003, "grad": 0.077, "tokens": 124645248000, "tok_s": 158522.8}
|
| 47 |
+
{"step": 118920, "epoch": 0.756, "loss": 1.67776, "ppl": 5.354, "lr": 0.003, "grad": 0.1038, "tokens": 124666214400, "tok_s": 158597.0}
|
| 48 |
+
{"step": 118940, "epoch": 0.756, "loss": 1.69051, "ppl": 5.422, "lr": 0.003, "grad": 0.0728, "tokens": 124687180800, "tok_s": 158127.2}
|
| 49 |
+
{"step": 118960, "epoch": 0.756, "loss": 1.78371, "ppl": 5.952, "lr": 0.003, "grad": 0.1134, "tokens": 124708147200, "tok_s": 158357.3}
|
| 50 |
+
{"step": 118980, "epoch": 0.756, "loss": 1.73447, "ppl": 5.666, "lr": 0.003, "grad": 0.0627, "tokens": 124729113600, "tok_s": 158191.1}
|
| 51 |
+
{"step": 119000, "epoch": 0.756, "loss": 1.89018, "ppl": 6.621, "lr": 0.003, "grad": 0.1249, "tokens": 124750080000, "tok_s": 158547.0}
|
| 52 |
+
{"step": 119000, "val_loss": 1.73142, "val_ppl": 5.649, "is_best": true}
|
| 53 |
+
{"step": 119020, "epoch": 0.756, "loss": 1.73487, "ppl": 5.668, "lr": 0.003, "grad": 0.0905, "tokens": 124771046400, "tok_s": 158219.6}
|
| 54 |
+
{"step": 119040, "epoch": 0.756, "loss": 1.6774, "ppl": 5.352, "lr": 0.003, "grad": 0.1006, "tokens": 124792012800, "tok_s": 158627.9}
|
| 55 |
+
{"step": 119060, "epoch": 0.756, "loss": 1.77446, "ppl": 5.897, "lr": 0.003, "grad": 0.1015, "tokens": 124812979200, "tok_s": 156897.4}
|
| 56 |
+
{"step": 119080, "epoch": 0.757, "loss": 1.72486, "ppl": 5.612, "lr": 0.003, "grad": 0.1353, "tokens": 124833945600, "tok_s": 158154.9}
|
| 57 |
+
{"step": 119100, "epoch": 0.757, "loss": 1.59788, "ppl": 4.943, "lr": 0.003, "grad": 0.1061, "tokens": 124854912000, "tok_s": 158116.9}
|
| 58 |
+
{"step": 119120, "epoch": 0.757, "loss": 1.86998, "ppl": 6.488, "lr": 0.003, "grad": 0.1451, "tokens": 124875878400, "tok_s": 158367.4}
|
| 59 |
+
{"step": 119140, "epoch": 0.757, "loss": 1.76439, "ppl": 5.838, "lr": 0.003, "grad": 0.0871, "tokens": 124896844800, "tok_s": 158280.7}
|
| 60 |
+
{"step": 119160, "epoch": 0.757, "loss": 1.74972, "ppl": 5.753, "lr": 0.003, "grad": 0.1081, "tokens": 124917811200, "tok_s": 158102.5}
|
| 61 |
+
{"step": 119180, "epoch": 0.757, "loss": 1.79359, "ppl": 6.011, "lr": 0.003, "grad": 0.0719, "tokens": 124938777600, "tok_s": 158504.6}
|
| 62 |
+
{"step": 119200, "epoch": 0.757, "loss": 1.70737, "ppl": 5.514, "lr": 0.003, "grad": 0.1167, "tokens": 124959744000, "tok_s": 158144.0}
|
| 63 |
+
{"step": 119220, "epoch": 0.757, "loss": 1.77966, "ppl": 5.928, "lr": 0.003, "grad": 0.0904, "tokens": 124980710400, "tok_s": 158453.4}
|
| 64 |
+
{"step": 119240, "epoch": 0.758, "loss": 1.69198, "ppl": 5.43, "lr": 0.003, "grad": 0.0899, "tokens": 125001676800, "tok_s": 158364.4}
|
| 65 |
+
{"step": 119260, "epoch": 0.758, "loss": 1.72413, "ppl": 5.608, "lr": 0.003, "grad": 0.121, "tokens": 125022643200, "tok_s": 158461.9}
|
| 66 |
+
{"step": 119280, "epoch": 0.758, "loss": 1.60305, "ppl": 4.968, "lr": 0.003, "grad": 0.11, "tokens": 125043609600, "tok_s": 158381.0}
|
| 67 |
+
{"step": 119300, "epoch": 0.758, "loss": 1.80217, "ppl": 6.063, "lr": 0.003, "grad": 0.094, "tokens": 125064576000, "tok_s": 158595.4}
|
| 68 |
+
{"step": 119320, "epoch": 0.758, "loss": 1.74326, "ppl": 5.716, "lr": 0.003, "grad": 0.0768, "tokens": 125085542400, "tok_s": 158531.8}
|
| 69 |
+
{"step": 119340, "epoch": 0.758, "loss": 1.79594, "ppl": 6.025, "lr": 0.003, "grad": 0.0855, "tokens": 125106508800, "tok_s": 158305.4}
|
| 70 |
+
{"step": 119360, "epoch": 0.758, "loss": 1.73375, "ppl": 5.662, "lr": 0.003, "grad": 0.0825, "tokens": 125127475200, "tok_s": 157920.6}
|
| 71 |
+
{"step": 119380, "epoch": 0.758, "loss": 1.84414, "ppl": 6.323, "lr": 0.003, "grad": 0.0913, "tokens": 125148441600, "tok_s": 158531.8}
|
| 72 |
+
{"step": 119400, "epoch": 0.759, "loss": 1.81026, "ppl": 6.112, "lr": 0.003, "grad": 0.0727, "tokens": 125169408000, "tok_s": 158310.9}
|
| 73 |
+
{"step": 119420, "epoch": 0.759, "loss": 1.79423, "ppl": 6.015, "lr": 0.003, "grad": 0.093, "tokens": 125190374400, "tok_s": 158200.8}
|
| 74 |
+
{"step": 119440, "epoch": 0.759, "loss": 1.73512, "ppl": 5.67, "lr": 0.003, "grad": 0.0858, "tokens": 125211340800, "tok_s": 158638.4}
|
| 75 |
+
{"step": 119460, "epoch": 0.759, "loss": 1.77697, "ppl": 5.912, "lr": 0.003, "grad": 0.1038, "tokens": 125232307200, "tok_s": 157567.2}
|
| 76 |
+
{"step": 119480, "epoch": 0.759, "loss": 1.82226, "ppl": 6.186, "lr": 0.003, "grad": 0.0759, "tokens": 125253273600, "tok_s": 157654.3}
|
| 77 |
+
{"step": 119500, "epoch": 0.759, "loss": 1.78047, "ppl": 5.933, "lr": 0.003, "grad": 0.1256, "tokens": 125274240000, "tok_s": 158489.2}
|
| 78 |
+
{"step": 119520, "epoch": 0.759, "loss": 1.78623, "ppl": 5.967, "lr": 0.003, "grad": 0.0918, "tokens": 125295206400, "tok_s": 158365.4}
|
| 79 |
+
{"step": 119540, "epoch": 0.76, "loss": 1.70974, "ppl": 5.527, "lr": 0.003, "grad": 0.0978, "tokens": 125316172800, "tok_s": 157639.6}
|
| 80 |
+
{"step": 119560, "epoch": 0.76, "loss": 1.7911, "ppl": 5.996, "lr": 0.003, "grad": 0.1486, "tokens": 125337139200, "tok_s": 157989.6}
|
| 81 |
+
{"step": 119580, "epoch": 0.76, "loss": 1.59428, "ppl": 4.925, "lr": 0.003, "grad": 0.0848, "tokens": 125358105600, "tok_s": 158460.6}
|
| 82 |
+
{"step": 119600, "epoch": 0.76, "loss": 1.76708, "ppl": 5.854, "lr": 0.003, "grad": 0.098, "tokens": 125379072000, "tok_s": 158466.4}
|
| 83 |
+
{"step": 119620, "epoch": 0.76, "loss": 1.76648, "ppl": 5.85, "lr": 0.003, "grad": 0.0845, "tokens": 125400038400, "tok_s": 158403.4}
|
| 84 |
+
{"step": 119640, "epoch": 0.76, "loss": 1.73094, "ppl": 5.646, "lr": 0.003, "grad": 0.1216, "tokens": 125421004800, "tok_s": 158445.8}
|
| 85 |
+
{"step": 119660, "epoch": 0.76, "loss": 1.7842, "ppl": 5.955, "lr": 0.003, "grad": 0.0949, "tokens": 125441971200, "tok_s": 158513.3}
|
| 86 |
+
{"step": 119680, "epoch": 0.76, "loss": 1.75771, "ppl": 5.799, "lr": 0.003, "grad": 0.0852, "tokens": 125462937600, "tok_s": 157878.6}
|
| 87 |
+
{"step": 119700, "epoch": 0.761, "loss": 1.73007, "ppl": 5.641, "lr": 0.003, "grad": 0.0806, "tokens": 125483904000, "tok_s": 158358.3}
|
| 88 |
+
{"step": 119720, "epoch": 0.761, "loss": 1.70879, "ppl": 5.522, "lr": 0.003, "grad": 0.1121, "tokens": 125504870400, "tok_s": 158528.5}
|
| 89 |
+
{"step": 119740, "epoch": 0.761, "loss": 1.74589, "ppl": 5.731, "lr": 0.003, "grad": 0.0941, "tokens": 125525836800, "tok_s": 158341.9}
|
| 90 |
+
{"step": 119760, "epoch": 0.761, "loss": 1.63881, "ppl": 5.149, "lr": 0.003, "grad": 0.0731, "tokens": 125546803200, "tok_s": 158367.5}
|
| 91 |
+
{"step": 119780, "epoch": 0.761, "loss": 1.71789, "ppl": 5.573, "lr": 0.003, "grad": 0.0898, "tokens": 125567769600, "tok_s": 158093.5}
|
| 92 |
+
{"step": 119800, "epoch": 0.761, "loss": 1.73879, "ppl": 5.69, "lr": 0.003, "grad": 0.0634, "tokens": 125588736000, "tok_s": 158062.8}
|
| 93 |
+
{"step": 119820, "epoch": 0.761, "loss": 1.76379, "ppl": 5.834, "lr": 0.003, "grad": 0.0926, "tokens": 125609702400, "tok_s": 158018.0}
|
| 94 |
+
{"step": 119840, "epoch": 0.761, "loss": 1.77844, "ppl": 5.921, "lr": 0.003, "grad": 0.0621, "tokens": 125630668800, "tok_s": 158457.5}
|
| 95 |
+
{"step": 119860, "epoch": 0.762, "loss": 1.79022, "ppl": 5.991, "lr": 0.003, "grad": 0.0978, "tokens": 125651635200, "tok_s": 157351.8}
|
| 96 |
+
{"step": 119880, "epoch": 0.762, "loss": 1.76953, "ppl": 5.868, "lr": 0.003, "grad": 0.1406, "tokens": 125672601600, "tok_s": 157745.2}
|
| 97 |
+
{"step": 119900, "epoch": 0.762, "loss": 1.75451, "ppl": 5.781, "lr": 0.003, "grad": 0.1048, "tokens": 125693568000, "tok_s": 158566.8}
|
| 98 |
+
{"step": 119920, "epoch": 0.762, "loss": 1.77878, "ppl": 5.923, "lr": 0.003, "grad": 0.1219, "tokens": 125714534400, "tok_s": 157984.7}
|
| 99 |
+
{"step": 119940, "epoch": 0.762, "loss": 1.72756, "ppl": 5.627, "lr": 0.003, "grad": 0.0799, "tokens": 125735500800, "tok_s": 158248.3}
|
| 100 |
+
{"step": 119960, "epoch": 0.762, "loss": 1.75123, "ppl": 5.762, "lr": 0.003, "grad": 0.092, "tokens": 125756467200, "tok_s": 158026.9}
|
| 101 |
+
{"step": 119980, "epoch": 0.762, "loss": 1.79766, "ppl": 6.036, "lr": 0.003, "grad": 0.0985, "tokens": 125777433600, "tok_s": 158297.1}
|
| 102 |
+
{"step": 120000, "epoch": 0.762, "loss": 1.72787, "ppl": 5.629, "lr": 0.003, "grad": 0.072, "tokens": 125798400000, "tok_s": 158454.4}
|
| 103 |
+
{"step": 120000, "val_loss": 1.74408, "val_ppl": 5.721, "is_best": false}
|
| 104 |
+
{"step": 120020, "epoch": 0.763, "loss": 1.76051, "ppl": 5.815, "lr": 0.003, "grad": 0.1876, "tokens": 125819366400, "tok_s": 157867.4}
|
| 105 |
+
{"step": 120040, "epoch": 0.763, "loss": 1.74994, "ppl": 5.754, "lr": 0.003, "grad": 0.0985, "tokens": 125840332800, "tok_s": 157954.2}
|
| 106 |
+
{"step": 120060, "epoch": 0.763, "loss": 1.69562, "ppl": 5.45, "lr": 0.003, "grad": 0.0731, "tokens": 125861299200, "tok_s": 158281.6}
|
| 107 |
+
{"step": 120080, "epoch": 0.763, "loss": 1.76473, "ppl": 5.84, "lr": 0.003, "grad": 0.0962, "tokens": 125882265600, "tok_s": 157364.7}
|
| 108 |
+
{"step": 120100, "epoch": 0.763, "loss": 1.75624, "ppl": 5.791, "lr": 0.003, "grad": 0.0947, "tokens": 125903232000, "tok_s": 158207.3}
|
| 109 |
+
{"step": 120120, "epoch": 0.763, "loss": 1.82935, "ppl": 6.23, "lr": 0.003, "grad": 0.1702, "tokens": 125924198400, "tok_s": 157990.1}
|
| 110 |
+
{"step": 120140, "epoch": 0.763, "loss": 1.77181, "ppl": 5.881, "lr": 0.003, "grad": 0.1107, "tokens": 125945164800, "tok_s": 157434.3}
|
| 111 |
+
{"step": 120160, "epoch": 0.763, "loss": 1.72448, "ppl": 5.61, "lr": 0.003, "grad": 0.1443, "tokens": 125966131200, "tok_s": 158178.7}
|
| 112 |
+
{"step": 120180, "epoch": 0.764, "loss": 1.75123, "ppl": 5.762, "lr": 0.003, "grad": 0.0966, "tokens": 125987097600, "tok_s": 158345.2}
|
| 113 |
+
{"step": 120200, "epoch": 0.764, "loss": 1.80418, "ppl": 6.075, "lr": 0.003, "grad": 0.092, "tokens": 126008064000, "tok_s": 158277.5}
|
| 114 |
+
{"step": 120220, "epoch": 0.764, "loss": 1.70348, "ppl": 5.493, "lr": 0.003, "grad": 0.0668, "tokens": 126029030400, "tok_s": 158346.1}
|
| 115 |
+
{"step": 120240, "epoch": 0.764, "loss": 1.74817, "ppl": 5.744, "lr": 0.003, "grad": 0.0858, "tokens": 126049996800, "tok_s": 157902.1}
|
| 116 |
+
{"step": 120260, "epoch": 0.764, "loss": 1.6631, "ppl": 5.276, "lr": 0.003, "grad": 0.0791, "tokens": 126070963200, "tok_s": 158119.9}
|
| 117 |
+
{"step": 120280, "epoch": 0.764, "loss": 1.76204, "ppl": 5.824, "lr": 0.003, "grad": 0.0982, "tokens": 126091929600, "tok_s": 158187.1}
|
| 118 |
+
{"step": 120300, "epoch": 0.764, "loss": 1.78652, "ppl": 5.969, "lr": 0.003, "grad": 0.1254, "tokens": 126112896000, "tok_s": 157547.9}
|
| 119 |
+
{"step": 120320, "epoch": 0.764, "loss": 1.66687, "ppl": 5.296, "lr": 0.003, "grad": 0.0911, "tokens": 126133862400, "tok_s": 157968.6}
|
| 120 |
+
{"step": 120340, "epoch": 0.765, "loss": 1.63279, "ppl": 5.118, "lr": 0.003, "grad": 0.0737, "tokens": 126154828800, "tok_s": 158102.3}
|
| 121 |
+
{"step": 120360, "epoch": 0.765, "loss": 1.75871, "ppl": 5.805, "lr": 0.003, "grad": 0.0806, "tokens": 126175795200, "tok_s": 158287.5}
|
| 122 |
+
{"step": 120380, "epoch": 0.765, "loss": 1.73318, "ppl": 5.659, "lr": 0.003, "grad": 0.105, "tokens": 126196761600, "tok_s": 158290.9}
|
| 123 |
+
{"step": 120400, "epoch": 0.765, "loss": 1.64862, "ppl": 5.2, "lr": 0.003, "grad": 0.0899, "tokens": 126217728000, "tok_s": 158273.1}
|
| 124 |
+
{"step": 120420, "epoch": 0.765, "loss": 1.6669, "ppl": 5.296, "lr": 0.003, "grad": 0.0948, "tokens": 126238694400, "tok_s": 158423.4}
|
| 125 |
+
{"step": 120440, "epoch": 0.765, "loss": 1.85421, "ppl": 6.387, "lr": 0.003, "grad": 0.1484, "tokens": 126259660800, "tok_s": 158566.7}
|
| 126 |
+
{"step": 120460, "epoch": 0.765, "loss": 1.6474, "ppl": 5.193, "lr": 0.003, "grad": 0.0829, "tokens": 126280627200, "tok_s": 158433.5}
|
| 127 |
+
{"step": 120480, "epoch": 0.765, "loss": 1.72466, "ppl": 5.611, "lr": 0.003, "grad": 0.0757, "tokens": 126301593600, "tok_s": 158418.8}
|
| 128 |
+
{"step": 120500, "epoch": 0.766, "loss": 1.69928, "ppl": 5.47, "lr": 0.003, "grad": 0.0988, "tokens": 126322560000, "tok_s": 157887.0}
|
| 129 |
+
{"step": 120520, "epoch": 0.766, "loss": 1.71225, "ppl": 5.541, "lr": 0.003, "grad": 0.0648, "tokens": 126343526400, "tok_s": 158389.5}
|
| 130 |
+
{"step": 120540, "epoch": 0.766, "loss": 1.71587, "ppl": 5.562, "lr": 0.003, "grad": 0.0872, "tokens": 126364492800, "tok_s": 158433.1}
|
| 131 |
+
{"step": 120560, "epoch": 0.766, "loss": 1.81211, "ppl": 6.123, "lr": 0.003, "grad": 0.1148, "tokens": 126385459200, "tok_s": 158665.0}
|
| 132 |
+
{"step": 120580, "epoch": 0.766, "loss": 1.74413, "ppl": 5.721, "lr": 0.003, "grad": 0.1671, "tokens": 126406425600, "tok_s": 157791.9}
|
| 133 |
+
{"step": 120600, "epoch": 0.766, "loss": 1.77456, "ppl": 5.898, "lr": 0.003, "grad": 0.0833, "tokens": 126427392000, "tok_s": 158443.1}
|
| 134 |
+
{"step": 120620, "epoch": 0.766, "loss": 1.739, "ppl": 5.692, "lr": 0.003, "grad": 0.0814, "tokens": 126448358400, "tok_s": 158057.2}
|
| 135 |
+
{"step": 120640, "epoch": 0.767, "loss": 1.77647, "ppl": 5.909, "lr": 0.003, "grad": 0.0732, "tokens": 126469324800, "tok_s": 158430.0}
|
| 136 |
+
{"step": 120660, "epoch": 0.767, "loss": 1.64587, "ppl": 5.186, "lr": 0.003, "grad": 0.1168, "tokens": 126490291200, "tok_s": 158144.8}
|
| 137 |
+
{"step": 120680, "epoch": 0.767, "loss": 1.73953, "ppl": 5.695, "lr": 0.003, "grad": 0.0838, "tokens": 126511257600, "tok_s": 158193.9}
|
| 138 |
+
{"step": 120700, "epoch": 0.767, "loss": 1.69814, "ppl": 5.464, "lr": 0.003, "grad": 0.0981, "tokens": 126532224000, "tok_s": 158373.9}
|
| 139 |
+
{"step": 120720, "epoch": 0.767, "loss": 1.78551, "ppl": 5.963, "lr": 0.003, "grad": 0.1042, "tokens": 126553190400, "tok_s": 157961.8}
|
| 140 |
+
{"step": 120740, "epoch": 0.767, "loss": 1.60843, "ppl": 4.995, "lr": 0.003, "grad": 0.0756, "tokens": 126574156800, "tok_s": 158332.8}
|
| 141 |
+
{"step": 120760, "epoch": 0.767, "loss": 1.77685, "ppl": 5.911, "lr": 0.003, "grad": 0.1053, "tokens": 126595123200, "tok_s": 158314.9}
|
| 142 |
+
{"step": 120780, "epoch": 0.767, "loss": 1.78277, "ppl": 5.946, "lr": 0.003, "grad": 0.0814, "tokens": 126616089600, "tok_s": 158333.6}
|
| 143 |
+
{"step": 120800, "epoch": 0.768, "loss": 1.75826, "ppl": 5.802, "lr": 0.003, "grad": 0.1262, "tokens": 126637056000, "tok_s": 158309.5}
|
| 144 |
+
{"step": 120820, "epoch": 0.768, "loss": 1.77682, "ppl": 5.911, "lr": 0.003, "grad": 0.0963, "tokens": 126658022400, "tok_s": 157754.8}
|
| 145 |
+
{"step": 120840, "epoch": 0.768, "loss": 1.77882, "ppl": 5.923, "lr": 0.003, "grad": 0.1077, "tokens": 126678988800, "tok_s": 157839.5}
|
| 146 |
+
{"step": 120860, "epoch": 0.768, "loss": 1.80148, "ppl": 6.059, "lr": 0.003, "grad": 0.1123, "tokens": 126699955200, "tok_s": 158309.5}
|
| 147 |
+
{"step": 120880, "epoch": 0.768, "loss": 1.71568, "ppl": 5.56, "lr": 0.003, "grad": 0.092, "tokens": 126720921600, "tok_s": 158002.1}
|
| 148 |
+
{"step": 120900, "epoch": 0.768, "loss": 1.7699, "ppl": 5.87, "lr": 0.003, "grad": 0.0901, "tokens": 126741888000, "tok_s": 158141.4}
|
| 149 |
+
{"step": 120920, "epoch": 0.768, "loss": 1.76602, "ppl": 5.848, "lr": 0.003, "grad": 0.088, "tokens": 126762854400, "tok_s": 158239.9}
|
| 150 |
+
{"step": 120940, "epoch": 0.768, "loss": 1.73301, "ppl": 5.658, "lr": 0.003, "grad": 0.0793, "tokens": 126783820800, "tok_s": 158020.4}
|
| 151 |
+
{"step": 120960, "epoch": 0.769, "loss": 1.78942, "ppl": 5.986, "lr": 0.003, "grad": 0.1111, "tokens": 126804787200, "tok_s": 157801.6}
|
| 152 |
+
{"step": 120980, "epoch": 0.769, "loss": 1.76225, "ppl": 5.826, "lr": 0.003, "grad": 0.0816, "tokens": 126825753600, "tok_s": 157950.4}
|
| 153 |
+
{"step": 121000, "epoch": 0.769, "loss": 1.76714, "ppl": 5.854, "lr": 0.003, "grad": 0.1429, "tokens": 126846720000, "tok_s": 158387.1}
|
| 154 |
+
{"step": 121000, "val_loss": 1.75025, "val_ppl": 5.756, "is_best": false}
|
logs/log_122000.jsonl
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 118000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-05T19:25:40.381447"}
|
| 2 |
+
{"step": 118020, "epoch": 0.75, "loss": 1.73979, "ppl": 5.696, "lr": 0.003, "grad": 0.0904, "tokens": 123722726400, "tok_s": 158304.5}
|
| 3 |
+
{"step": 118040, "epoch": 0.75, "loss": 1.74056, "ppl": 5.701, "lr": 0.003, "grad": 0.0638, "tokens": 123743692800, "tok_s": 158016.5}
|
| 4 |
+
{"step": 118060, "epoch": 0.75, "loss": 1.71538, "ppl": 5.559, "lr": 0.003, "grad": 0.1665, "tokens": 123764659200, "tok_s": 158294.3}
|
| 5 |
+
{"step": 118080, "epoch": 0.75, "loss": 1.61202, "ppl": 5.013, "lr": 0.003, "grad": 0.1077, "tokens": 123785625600, "tok_s": 158421.7}
|
| 6 |
+
{"step": 118100, "epoch": 0.75, "loss": 1.76723, "ppl": 5.855, "lr": 0.003, "grad": 0.1292, "tokens": 123806592000, "tok_s": 158338.1}
|
| 7 |
+
{"step": 118120, "epoch": 0.75, "loss": 1.72861, "ppl": 5.633, "lr": 0.003, "grad": 0.079, "tokens": 123827558400, "tok_s": 158489.0}
|
| 8 |
+
{"step": 118140, "epoch": 0.751, "loss": 1.74261, "ppl": 5.712, "lr": 0.003, "grad": 0.0913, "tokens": 123848524800, "tok_s": 158102.0}
|
| 9 |
+
{"step": 118160, "epoch": 0.751, "loss": 1.67597, "ppl": 5.344, "lr": 0.003, "grad": 0.0904, "tokens": 123869491200, "tok_s": 158332.4}
|
| 10 |
+
{"step": 118180, "epoch": 0.751, "loss": 1.62789, "ppl": 5.093, "lr": 0.003, "grad": 0.0735, "tokens": 123890457600, "tok_s": 157954.9}
|
| 11 |
+
{"step": 118200, "epoch": 0.751, "loss": 1.59216, "ppl": 4.914, "lr": 0.003, "grad": 0.1055, "tokens": 123911424000, "tok_s": 158124.6}
|
| 12 |
+
{"step": 118220, "epoch": 0.751, "loss": 1.77912, "ppl": 5.925, "lr": 0.003, "grad": 0.0698, "tokens": 123932390400, "tok_s": 158541.3}
|
| 13 |
+
{"step": 118240, "epoch": 0.751, "loss": 1.70235, "ppl": 5.487, "lr": 0.003, "grad": 0.118, "tokens": 123953356800, "tok_s": 158605.3}
|
| 14 |
+
{"step": 118260, "epoch": 0.751, "loss": 1.75982, "ppl": 5.811, "lr": 0.003, "grad": 0.0774, "tokens": 123974323200, "tok_s": 157719.7}
|
| 15 |
+
{"step": 118280, "epoch": 0.752, "loss": 1.70922, "ppl": 5.525, "lr": 0.003, "grad": 0.1039, "tokens": 123995289600, "tok_s": 157979.7}
|
| 16 |
+
{"step": 118300, "epoch": 0.752, "loss": 1.75378, "ppl": 5.776, "lr": 0.003, "grad": 0.0803, "tokens": 124016256000, "tok_s": 158562.7}
|
| 17 |
+
{"step": 118320, "epoch": 0.752, "loss": 1.75956, "ppl": 5.81, "lr": 0.003, "grad": 0.094, "tokens": 124037222400, "tok_s": 158133.7}
|
| 18 |
+
{"step": 118340, "epoch": 0.752, "loss": 1.72452, "ppl": 5.61, "lr": 0.003, "grad": 0.0816, "tokens": 124058188800, "tok_s": 157996.3}
|
| 19 |
+
{"step": 118360, "epoch": 0.752, "loss": 1.77153, "ppl": 5.88, "lr": 0.003, "grad": 0.0658, "tokens": 124079155200, "tok_s": 158511.8}
|
| 20 |
+
{"step": 118380, "epoch": 0.752, "loss": 1.68067, "ppl": 5.369, "lr": 0.003, "grad": 0.0788, "tokens": 124100121600, "tok_s": 157873.7}
|
| 21 |
+
{"step": 118400, "epoch": 0.752, "loss": 1.78125, "ppl": 5.937, "lr": 0.003, "grad": 0.1265, "tokens": 124121088000, "tok_s": 158508.4}
|
| 22 |
+
{"step": 118420, "epoch": 0.752, "loss": 1.75976, "ppl": 5.811, "lr": 0.003, "grad": 0.0963, "tokens": 124142054400, "tok_s": 158543.6}
|
| 23 |
+
{"step": 118440, "epoch": 0.753, "loss": 1.67067, "ppl": 5.316, "lr": 0.003, "grad": 0.0701, "tokens": 124163020800, "tok_s": 158495.1}
|
| 24 |
+
{"step": 118460, "epoch": 0.753, "loss": 1.81095, "ppl": 6.116, "lr": 0.003, "grad": 0.118, "tokens": 124183987200, "tok_s": 158618.8}
|
| 25 |
+
{"step": 118480, "epoch": 0.753, "loss": 1.80713, "ppl": 6.093, "lr": 0.003, "grad": 0.1225, "tokens": 124204953600, "tok_s": 158643.1}
|
| 26 |
+
{"step": 118500, "epoch": 0.753, "loss": 1.90087, "ppl": 6.692, "lr": 0.003, "grad": 0.0971, "tokens": 124225920000, "tok_s": 158526.0}
|
| 27 |
+
{"step": 118520, "epoch": 0.753, "loss": 1.7631, "ppl": 5.83, "lr": 0.003, "grad": 0.0917, "tokens": 124246886400, "tok_s": 158524.9}
|
| 28 |
+
{"step": 118540, "epoch": 0.753, "loss": 1.65783, "ppl": 5.248, "lr": 0.003, "grad": 0.0625, "tokens": 124267852800, "tok_s": 158043.8}
|
| 29 |
+
{"step": 118560, "epoch": 0.753, "loss": 1.67888, "ppl": 5.36, "lr": 0.003, "grad": 0.1154, "tokens": 124288819200, "tok_s": 158294.7}
|
| 30 |
+
{"step": 118580, "epoch": 0.753, "loss": 1.70275, "ppl": 5.489, "lr": 0.003, "grad": 0.1018, "tokens": 124309785600, "tok_s": 158415.3}
|
| 31 |
+
{"step": 118600, "epoch": 0.754, "loss": 1.63827, "ppl": 5.146, "lr": 0.003, "grad": 0.0825, "tokens": 124330752000, "tok_s": 158406.3}
|
| 32 |
+
{"step": 118620, "epoch": 0.754, "loss": 1.71381, "ppl": 5.55, "lr": 0.003, "grad": 0.1082, "tokens": 124351718400, "tok_s": 158419.1}
|
| 33 |
+
{"step": 118640, "epoch": 0.754, "loss": 1.6619, "ppl": 5.269, "lr": 0.003, "grad": 0.1085, "tokens": 124372684800, "tok_s": 158500.8}
|
| 34 |
+
{"step": 118660, "epoch": 0.754, "loss": 1.84244, "ppl": 6.312, "lr": 0.003, "grad": 0.1561, "tokens": 124393651200, "tok_s": 158192.5}
|
| 35 |
+
{"step": 118680, "epoch": 0.754, "loss": 1.77033, "ppl": 5.873, "lr": 0.003, "grad": 0.1412, "tokens": 124414617600, "tok_s": 157722.2}
|
| 36 |
+
{"step": 118700, "epoch": 0.754, "loss": 1.74147, "ppl": 5.706, "lr": 0.003, "grad": 0.111, "tokens": 124435584000, "tok_s": 158601.6}
|
| 37 |
+
{"step": 118720, "epoch": 0.754, "loss": 1.66524, "ppl": 5.287, "lr": 0.003, "grad": 0.0856, "tokens": 124456550400, "tok_s": 158448.0}
|
| 38 |
+
{"step": 118740, "epoch": 0.754, "loss": 1.69815, "ppl": 5.464, "lr": 0.003, "grad": 0.0807, "tokens": 124477516800, "tok_s": 158113.7}
|
| 39 |
+
{"step": 118760, "epoch": 0.755, "loss": 1.76824, "ppl": 5.861, "lr": 0.003, "grad": 0.1075, "tokens": 124498483200, "tok_s": 158253.1}
|
| 40 |
+
{"step": 118780, "epoch": 0.755, "loss": 1.67594, "ppl": 5.344, "lr": 0.003, "grad": 0.1487, "tokens": 124519449600, "tok_s": 158222.0}
|
| 41 |
+
{"step": 118800, "epoch": 0.755, "loss": 1.69363, "ppl": 5.439, "lr": 0.003, "grad": 0.1075, "tokens": 124540416000, "tok_s": 158604.0}
|
| 42 |
+
{"step": 118820, "epoch": 0.755, "loss": 1.7418, "ppl": 5.708, "lr": 0.003, "grad": 0.1089, "tokens": 124561382400, "tok_s": 158553.7}
|
| 43 |
+
{"step": 118840, "epoch": 0.755, "loss": 1.67568, "ppl": 5.342, "lr": 0.003, "grad": 0.0724, "tokens": 124582348800, "tok_s": 157825.5}
|
| 44 |
+
{"step": 118860, "epoch": 0.755, "loss": 1.75391, "ppl": 5.777, "lr": 0.003, "grad": 0.087, "tokens": 124603315200, "tok_s": 158545.7}
|
| 45 |
+
{"step": 118880, "epoch": 0.755, "loss": 1.77945, "ppl": 5.927, "lr": 0.003, "grad": 0.097, "tokens": 124624281600, "tok_s": 158515.1}
|
| 46 |
+
{"step": 118900, "epoch": 0.755, "loss": 1.44913, "ppl": 4.259, "lr": 0.003, "grad": 0.077, "tokens": 124645248000, "tok_s": 158522.8}
|
| 47 |
+
{"step": 118920, "epoch": 0.756, "loss": 1.67776, "ppl": 5.354, "lr": 0.003, "grad": 0.1038, "tokens": 124666214400, "tok_s": 158597.0}
|
| 48 |
+
{"step": 118940, "epoch": 0.756, "loss": 1.69051, "ppl": 5.422, "lr": 0.003, "grad": 0.0728, "tokens": 124687180800, "tok_s": 158127.2}
|
| 49 |
+
{"step": 118960, "epoch": 0.756, "loss": 1.78371, "ppl": 5.952, "lr": 0.003, "grad": 0.1134, "tokens": 124708147200, "tok_s": 158357.3}
|
| 50 |
+
{"step": 118980, "epoch": 0.756, "loss": 1.73447, "ppl": 5.666, "lr": 0.003, "grad": 0.0627, "tokens": 124729113600, "tok_s": 158191.1}
|
| 51 |
+
{"step": 119000, "epoch": 0.756, "loss": 1.89018, "ppl": 6.621, "lr": 0.003, "grad": 0.1249, "tokens": 124750080000, "tok_s": 158547.0}
|
| 52 |
+
{"step": 119000, "val_loss": 1.73142, "val_ppl": 5.649, "is_best": true}
|
| 53 |
+
{"step": 119020, "epoch": 0.756, "loss": 1.73487, "ppl": 5.668, "lr": 0.003, "grad": 0.0905, "tokens": 124771046400, "tok_s": 158219.6}
|
| 54 |
+
{"step": 119040, "epoch": 0.756, "loss": 1.6774, "ppl": 5.352, "lr": 0.003, "grad": 0.1006, "tokens": 124792012800, "tok_s": 158627.9}
|
| 55 |
+
{"step": 119060, "epoch": 0.756, "loss": 1.77446, "ppl": 5.897, "lr": 0.003, "grad": 0.1015, "tokens": 124812979200, "tok_s": 156897.4}
|
| 56 |
+
{"step": 119080, "epoch": 0.757, "loss": 1.72486, "ppl": 5.612, "lr": 0.003, "grad": 0.1353, "tokens": 124833945600, "tok_s": 158154.9}
|
| 57 |
+
{"step": 119100, "epoch": 0.757, "loss": 1.59788, "ppl": 4.943, "lr": 0.003, "grad": 0.1061, "tokens": 124854912000, "tok_s": 158116.9}
|
| 58 |
+
{"step": 119120, "epoch": 0.757, "loss": 1.86998, "ppl": 6.488, "lr": 0.003, "grad": 0.1451, "tokens": 124875878400, "tok_s": 158367.4}
|
| 59 |
+
{"step": 119140, "epoch": 0.757, "loss": 1.76439, "ppl": 5.838, "lr": 0.003, "grad": 0.0871, "tokens": 124896844800, "tok_s": 158280.7}
|
| 60 |
+
{"step": 119160, "epoch": 0.757, "loss": 1.74972, "ppl": 5.753, "lr": 0.003, "grad": 0.1081, "tokens": 124917811200, "tok_s": 158102.5}
|
| 61 |
+
{"step": 119180, "epoch": 0.757, "loss": 1.79359, "ppl": 6.011, "lr": 0.003, "grad": 0.0719, "tokens": 124938777600, "tok_s": 158504.6}
|
| 62 |
+
{"step": 119200, "epoch": 0.757, "loss": 1.70737, "ppl": 5.514, "lr": 0.003, "grad": 0.1167, "tokens": 124959744000, "tok_s": 158144.0}
|
| 63 |
+
{"step": 119220, "epoch": 0.757, "loss": 1.77966, "ppl": 5.928, "lr": 0.003, "grad": 0.0904, "tokens": 124980710400, "tok_s": 158453.4}
|
| 64 |
+
{"step": 119240, "epoch": 0.758, "loss": 1.69198, "ppl": 5.43, "lr": 0.003, "grad": 0.0899, "tokens": 125001676800, "tok_s": 158364.4}
|
| 65 |
+
{"step": 119260, "epoch": 0.758, "loss": 1.72413, "ppl": 5.608, "lr": 0.003, "grad": 0.121, "tokens": 125022643200, "tok_s": 158461.9}
|
| 66 |
+
{"step": 119280, "epoch": 0.758, "loss": 1.60305, "ppl": 4.968, "lr": 0.003, "grad": 0.11, "tokens": 125043609600, "tok_s": 158381.0}
|
| 67 |
+
{"step": 119300, "epoch": 0.758, "loss": 1.80217, "ppl": 6.063, "lr": 0.003, "grad": 0.094, "tokens": 125064576000, "tok_s": 158595.4}
|
| 68 |
+
{"step": 119320, "epoch": 0.758, "loss": 1.74326, "ppl": 5.716, "lr": 0.003, "grad": 0.0768, "tokens": 125085542400, "tok_s": 158531.8}
|
| 69 |
+
{"step": 119340, "epoch": 0.758, "loss": 1.79594, "ppl": 6.025, "lr": 0.003, "grad": 0.0855, "tokens": 125106508800, "tok_s": 158305.4}
|
| 70 |
+
{"step": 119360, "epoch": 0.758, "loss": 1.73375, "ppl": 5.662, "lr": 0.003, "grad": 0.0825, "tokens": 125127475200, "tok_s": 157920.6}
|
| 71 |
+
{"step": 119380, "epoch": 0.758, "loss": 1.84414, "ppl": 6.323, "lr": 0.003, "grad": 0.0913, "tokens": 125148441600, "tok_s": 158531.8}
|
| 72 |
+
{"step": 119400, "epoch": 0.759, "loss": 1.81026, "ppl": 6.112, "lr": 0.003, "grad": 0.0727, "tokens": 125169408000, "tok_s": 158310.9}
|
| 73 |
+
{"step": 119420, "epoch": 0.759, "loss": 1.79423, "ppl": 6.015, "lr": 0.003, "grad": 0.093, "tokens": 125190374400, "tok_s": 158200.8}
|
| 74 |
+
{"step": 119440, "epoch": 0.759, "loss": 1.73512, "ppl": 5.67, "lr": 0.003, "grad": 0.0858, "tokens": 125211340800, "tok_s": 158638.4}
|
| 75 |
+
{"step": 119460, "epoch": 0.759, "loss": 1.77697, "ppl": 5.912, "lr": 0.003, "grad": 0.1038, "tokens": 125232307200, "tok_s": 157567.2}
|
| 76 |
+
{"step": 119480, "epoch": 0.759, "loss": 1.82226, "ppl": 6.186, "lr": 0.003, "grad": 0.0759, "tokens": 125253273600, "tok_s": 157654.3}
|
| 77 |
+
{"step": 119500, "epoch": 0.759, "loss": 1.78047, "ppl": 5.933, "lr": 0.003, "grad": 0.1256, "tokens": 125274240000, "tok_s": 158489.2}
|
| 78 |
+
{"step": 119520, "epoch": 0.759, "loss": 1.78623, "ppl": 5.967, "lr": 0.003, "grad": 0.0918, "tokens": 125295206400, "tok_s": 158365.4}
|
| 79 |
+
{"step": 119540, "epoch": 0.76, "loss": 1.70974, "ppl": 5.527, "lr": 0.003, "grad": 0.0978, "tokens": 125316172800, "tok_s": 157639.6}
|
| 80 |
+
{"step": 119560, "epoch": 0.76, "loss": 1.7911, "ppl": 5.996, "lr": 0.003, "grad": 0.1486, "tokens": 125337139200, "tok_s": 157989.6}
|
| 81 |
+
{"step": 119580, "epoch": 0.76, "loss": 1.59428, "ppl": 4.925, "lr": 0.003, "grad": 0.0848, "tokens": 125358105600, "tok_s": 158460.6}
|
| 82 |
+
{"step": 119600, "epoch": 0.76, "loss": 1.76708, "ppl": 5.854, "lr": 0.003, "grad": 0.098, "tokens": 125379072000, "tok_s": 158466.4}
|
| 83 |
+
{"step": 119620, "epoch": 0.76, "loss": 1.76648, "ppl": 5.85, "lr": 0.003, "grad": 0.0845, "tokens": 125400038400, "tok_s": 158403.4}
|
| 84 |
+
{"step": 119640, "epoch": 0.76, "loss": 1.73094, "ppl": 5.646, "lr": 0.003, "grad": 0.1216, "tokens": 125421004800, "tok_s": 158445.8}
|
| 85 |
+
{"step": 119660, "epoch": 0.76, "loss": 1.7842, "ppl": 5.955, "lr": 0.003, "grad": 0.0949, "tokens": 125441971200, "tok_s": 158513.3}
|
| 86 |
+
{"step": 119680, "epoch": 0.76, "loss": 1.75771, "ppl": 5.799, "lr": 0.003, "grad": 0.0852, "tokens": 125462937600, "tok_s": 157878.6}
|
| 87 |
+
{"step": 119700, "epoch": 0.761, "loss": 1.73007, "ppl": 5.641, "lr": 0.003, "grad": 0.0806, "tokens": 125483904000, "tok_s": 158358.3}
|
| 88 |
+
{"step": 119720, "epoch": 0.761, "loss": 1.70879, "ppl": 5.522, "lr": 0.003, "grad": 0.1121, "tokens": 125504870400, "tok_s": 158528.5}
|
| 89 |
+
{"step": 119740, "epoch": 0.761, "loss": 1.74589, "ppl": 5.731, "lr": 0.003, "grad": 0.0941, "tokens": 125525836800, "tok_s": 158341.9}
|
| 90 |
+
{"step": 119760, "epoch": 0.761, "loss": 1.63881, "ppl": 5.149, "lr": 0.003, "grad": 0.0731, "tokens": 125546803200, "tok_s": 158367.5}
|
| 91 |
+
{"step": 119780, "epoch": 0.761, "loss": 1.71789, "ppl": 5.573, "lr": 0.003, "grad": 0.0898, "tokens": 125567769600, "tok_s": 158093.5}
|
| 92 |
+
{"step": 119800, "epoch": 0.761, "loss": 1.73879, "ppl": 5.69, "lr": 0.003, "grad": 0.0634, "tokens": 125588736000, "tok_s": 158062.8}
|
| 93 |
+
{"step": 119820, "epoch": 0.761, "loss": 1.76379, "ppl": 5.834, "lr": 0.003, "grad": 0.0926, "tokens": 125609702400, "tok_s": 158018.0}
|
| 94 |
+
{"step": 119840, "epoch": 0.761, "loss": 1.77844, "ppl": 5.921, "lr": 0.003, "grad": 0.0621, "tokens": 125630668800, "tok_s": 158457.5}
|
| 95 |
+
{"step": 119860, "epoch": 0.762, "loss": 1.79022, "ppl": 5.991, "lr": 0.003, "grad": 0.0978, "tokens": 125651635200, "tok_s": 157351.8}
|
| 96 |
+
{"step": 119880, "epoch": 0.762, "loss": 1.76953, "ppl": 5.868, "lr": 0.003, "grad": 0.1406, "tokens": 125672601600, "tok_s": 157745.2}
|
| 97 |
+
{"step": 119900, "epoch": 0.762, "loss": 1.75451, "ppl": 5.781, "lr": 0.003, "grad": 0.1048, "tokens": 125693568000, "tok_s": 158566.8}
|
| 98 |
+
{"step": 119920, "epoch": 0.762, "loss": 1.77878, "ppl": 5.923, "lr": 0.003, "grad": 0.1219, "tokens": 125714534400, "tok_s": 157984.7}
|
| 99 |
+
{"step": 119940, "epoch": 0.762, "loss": 1.72756, "ppl": 5.627, "lr": 0.003, "grad": 0.0799, "tokens": 125735500800, "tok_s": 158248.3}
|
| 100 |
+
{"step": 119960, "epoch": 0.762, "loss": 1.75123, "ppl": 5.762, "lr": 0.003, "grad": 0.092, "tokens": 125756467200, "tok_s": 158026.9}
|
| 101 |
+
{"step": 119980, "epoch": 0.762, "loss": 1.79766, "ppl": 6.036, "lr": 0.003, "grad": 0.0985, "tokens": 125777433600, "tok_s": 158297.1}
|
| 102 |
+
{"step": 120000, "epoch": 0.762, "loss": 1.72787, "ppl": 5.629, "lr": 0.003, "grad": 0.072, "tokens": 125798400000, "tok_s": 158454.4}
|
| 103 |
+
{"step": 120000, "val_loss": 1.74408, "val_ppl": 5.721, "is_best": false}
|
| 104 |
+
{"step": 120020, "epoch": 0.763, "loss": 1.76051, "ppl": 5.815, "lr": 0.003, "grad": 0.1876, "tokens": 125819366400, "tok_s": 157867.4}
|
| 105 |
+
{"step": 120040, "epoch": 0.763, "loss": 1.74994, "ppl": 5.754, "lr": 0.003, "grad": 0.0985, "tokens": 125840332800, "tok_s": 157954.2}
|
| 106 |
+
{"step": 120060, "epoch": 0.763, "loss": 1.69562, "ppl": 5.45, "lr": 0.003, "grad": 0.0731, "tokens": 125861299200, "tok_s": 158281.6}
|
| 107 |
+
{"step": 120080, "epoch": 0.763, "loss": 1.76473, "ppl": 5.84, "lr": 0.003, "grad": 0.0962, "tokens": 125882265600, "tok_s": 157364.7}
|
| 108 |
+
{"step": 120100, "epoch": 0.763, "loss": 1.75624, "ppl": 5.791, "lr": 0.003, "grad": 0.0947, "tokens": 125903232000, "tok_s": 158207.3}
|
| 109 |
+
{"step": 120120, "epoch": 0.763, "loss": 1.82935, "ppl": 6.23, "lr": 0.003, "grad": 0.1702, "tokens": 125924198400, "tok_s": 157990.1}
|
| 110 |
+
{"step": 120140, "epoch": 0.763, "loss": 1.77181, "ppl": 5.881, "lr": 0.003, "grad": 0.1107, "tokens": 125945164800, "tok_s": 157434.3}
|
| 111 |
+
{"step": 120160, "epoch": 0.763, "loss": 1.72448, "ppl": 5.61, "lr": 0.003, "grad": 0.1443, "tokens": 125966131200, "tok_s": 158178.7}
|
| 112 |
+
{"step": 120180, "epoch": 0.764, "loss": 1.75123, "ppl": 5.762, "lr": 0.003, "grad": 0.0966, "tokens": 125987097600, "tok_s": 158345.2}
|
| 113 |
+
{"step": 120200, "epoch": 0.764, "loss": 1.80418, "ppl": 6.075, "lr": 0.003, "grad": 0.092, "tokens": 126008064000, "tok_s": 158277.5}
|
| 114 |
+
{"step": 120220, "epoch": 0.764, "loss": 1.70348, "ppl": 5.493, "lr": 0.003, "grad": 0.0668, "tokens": 126029030400, "tok_s": 158346.1}
|
| 115 |
+
{"step": 120240, "epoch": 0.764, "loss": 1.74817, "ppl": 5.744, "lr": 0.003, "grad": 0.0858, "tokens": 126049996800, "tok_s": 157902.1}
|
| 116 |
+
{"step": 120260, "epoch": 0.764, "loss": 1.6631, "ppl": 5.276, "lr": 0.003, "grad": 0.0791, "tokens": 126070963200, "tok_s": 158119.9}
|
| 117 |
+
{"step": 120280, "epoch": 0.764, "loss": 1.76204, "ppl": 5.824, "lr": 0.003, "grad": 0.0982, "tokens": 126091929600, "tok_s": 158187.1}
|
| 118 |
+
{"step": 120300, "epoch": 0.764, "loss": 1.78652, "ppl": 5.969, "lr": 0.003, "grad": 0.1254, "tokens": 126112896000, "tok_s": 157547.9}
|
| 119 |
+
{"step": 120320, "epoch": 0.764, "loss": 1.66687, "ppl": 5.296, "lr": 0.003, "grad": 0.0911, "tokens": 126133862400, "tok_s": 157968.6}
|
| 120 |
+
{"step": 120340, "epoch": 0.765, "loss": 1.63279, "ppl": 5.118, "lr": 0.003, "grad": 0.0737, "tokens": 126154828800, "tok_s": 158102.3}
|
| 121 |
+
{"step": 120360, "epoch": 0.765, "loss": 1.75871, "ppl": 5.805, "lr": 0.003, "grad": 0.0806, "tokens": 126175795200, "tok_s": 158287.5}
|
| 122 |
+
{"step": 120380, "epoch": 0.765, "loss": 1.73318, "ppl": 5.659, "lr": 0.003, "grad": 0.105, "tokens": 126196761600, "tok_s": 158290.9}
|
| 123 |
+
{"step": 120400, "epoch": 0.765, "loss": 1.64862, "ppl": 5.2, "lr": 0.003, "grad": 0.0899, "tokens": 126217728000, "tok_s": 158273.1}
|
| 124 |
+
{"step": 120420, "epoch": 0.765, "loss": 1.6669, "ppl": 5.296, "lr": 0.003, "grad": 0.0948, "tokens": 126238694400, "tok_s": 158423.4}
|
| 125 |
+
{"step": 120440, "epoch": 0.765, "loss": 1.85421, "ppl": 6.387, "lr": 0.003, "grad": 0.1484, "tokens": 126259660800, "tok_s": 158566.7}
|
| 126 |
+
{"step": 120460, "epoch": 0.765, "loss": 1.6474, "ppl": 5.193, "lr": 0.003, "grad": 0.0829, "tokens": 126280627200, "tok_s": 158433.5}
|
| 127 |
+
{"step": 120480, "epoch": 0.765, "loss": 1.72466, "ppl": 5.611, "lr": 0.003, "grad": 0.0757, "tokens": 126301593600, "tok_s": 158418.8}
|
| 128 |
+
{"step": 120500, "epoch": 0.766, "loss": 1.69928, "ppl": 5.47, "lr": 0.003, "grad": 0.0988, "tokens": 126322560000, "tok_s": 157887.0}
|
| 129 |
+
{"step": 120520, "epoch": 0.766, "loss": 1.71225, "ppl": 5.541, "lr": 0.003, "grad": 0.0648, "tokens": 126343526400, "tok_s": 158389.5}
|
| 130 |
+
{"step": 120540, "epoch": 0.766, "loss": 1.71587, "ppl": 5.562, "lr": 0.003, "grad": 0.0872, "tokens": 126364492800, "tok_s": 158433.1}
|
| 131 |
+
{"step": 120560, "epoch": 0.766, "loss": 1.81211, "ppl": 6.123, "lr": 0.003, "grad": 0.1148, "tokens": 126385459200, "tok_s": 158665.0}
|
| 132 |
+
{"step": 120580, "epoch": 0.766, "loss": 1.74413, "ppl": 5.721, "lr": 0.003, "grad": 0.1671, "tokens": 126406425600, "tok_s": 157791.9}
|
| 133 |
+
{"step": 120600, "epoch": 0.766, "loss": 1.77456, "ppl": 5.898, "lr": 0.003, "grad": 0.0833, "tokens": 126427392000, "tok_s": 158443.1}
|
| 134 |
+
{"step": 120620, "epoch": 0.766, "loss": 1.739, "ppl": 5.692, "lr": 0.003, "grad": 0.0814, "tokens": 126448358400, "tok_s": 158057.2}
|
| 135 |
+
{"step": 120640, "epoch": 0.767, "loss": 1.77647, "ppl": 5.909, "lr": 0.003, "grad": 0.0732, "tokens": 126469324800, "tok_s": 158430.0}
|
| 136 |
+
{"step": 120660, "epoch": 0.767, "loss": 1.64587, "ppl": 5.186, "lr": 0.003, "grad": 0.1168, "tokens": 126490291200, "tok_s": 158144.8}
|
| 137 |
+
{"step": 120680, "epoch": 0.767, "loss": 1.73953, "ppl": 5.695, "lr": 0.003, "grad": 0.0838, "tokens": 126511257600, "tok_s": 158193.9}
|
| 138 |
+
{"step": 120700, "epoch": 0.767, "loss": 1.69814, "ppl": 5.464, "lr": 0.003, "grad": 0.0981, "tokens": 126532224000, "tok_s": 158373.9}
|
| 139 |
+
{"step": 120720, "epoch": 0.767, "loss": 1.78551, "ppl": 5.963, "lr": 0.003, "grad": 0.1042, "tokens": 126553190400, "tok_s": 157961.8}
|
| 140 |
+
{"step": 120740, "epoch": 0.767, "loss": 1.60843, "ppl": 4.995, "lr": 0.003, "grad": 0.0756, "tokens": 126574156800, "tok_s": 158332.8}
|
| 141 |
+
{"step": 120760, "epoch": 0.767, "loss": 1.77685, "ppl": 5.911, "lr": 0.003, "grad": 0.1053, "tokens": 126595123200, "tok_s": 158314.9}
|
| 142 |
+
{"step": 120780, "epoch": 0.767, "loss": 1.78277, "ppl": 5.946, "lr": 0.003, "grad": 0.0814, "tokens": 126616089600, "tok_s": 158333.6}
|
| 143 |
+
{"step": 120800, "epoch": 0.768, "loss": 1.75826, "ppl": 5.802, "lr": 0.003, "grad": 0.1262, "tokens": 126637056000, "tok_s": 158309.5}
|
| 144 |
+
{"step": 120820, "epoch": 0.768, "loss": 1.77682, "ppl": 5.911, "lr": 0.003, "grad": 0.0963, "tokens": 126658022400, "tok_s": 157754.8}
|
| 145 |
+
{"step": 120840, "epoch": 0.768, "loss": 1.77882, "ppl": 5.923, "lr": 0.003, "grad": 0.1077, "tokens": 126678988800, "tok_s": 157839.5}
|
| 146 |
+
{"step": 120860, "epoch": 0.768, "loss": 1.80148, "ppl": 6.059, "lr": 0.003, "grad": 0.1123, "tokens": 126699955200, "tok_s": 158309.5}
|
| 147 |
+
{"step": 120880, "epoch": 0.768, "loss": 1.71568, "ppl": 5.56, "lr": 0.003, "grad": 0.092, "tokens": 126720921600, "tok_s": 158002.1}
|
| 148 |
+
{"step": 120900, "epoch": 0.768, "loss": 1.7699, "ppl": 5.87, "lr": 0.003, "grad": 0.0901, "tokens": 126741888000, "tok_s": 158141.4}
|
| 149 |
+
{"step": 120920, "epoch": 0.768, "loss": 1.76602, "ppl": 5.848, "lr": 0.003, "grad": 0.088, "tokens": 126762854400, "tok_s": 158239.9}
|
| 150 |
+
{"step": 120940, "epoch": 0.768, "loss": 1.73301, "ppl": 5.658, "lr": 0.003, "grad": 0.0793, "tokens": 126783820800, "tok_s": 158020.4}
|
| 151 |
+
{"step": 120960, "epoch": 0.769, "loss": 1.78942, "ppl": 5.986, "lr": 0.003, "grad": 0.1111, "tokens": 126804787200, "tok_s": 157801.6}
|
| 152 |
+
{"step": 120980, "epoch": 0.769, "loss": 1.76225, "ppl": 5.826, "lr": 0.003, "grad": 0.0816, "tokens": 126825753600, "tok_s": 157950.4}
|
| 153 |
+
{"step": 121000, "epoch": 0.769, "loss": 1.76714, "ppl": 5.854, "lr": 0.003, "grad": 0.1429, "tokens": 126846720000, "tok_s": 158387.1}
|
| 154 |
+
{"step": 121000, "val_loss": 1.75025, "val_ppl": 5.756, "is_best": false}
|
| 155 |
+
{"step": 121020, "epoch": 0.769, "loss": 1.69795, "ppl": 5.463, "lr": 0.003, "grad": 0.0895, "tokens": 126867686400, "tok_s": 158123.9}
|
| 156 |
+
{"step": 121040, "epoch": 0.769, "loss": 1.75501, "ppl": 5.784, "lr": 0.003, "grad": 0.1124, "tokens": 126888652800, "tok_s": 158291.6}
|
| 157 |
+
{"step": 121060, "epoch": 0.769, "loss": 1.73701, "ppl": 5.68, "lr": 0.003, "grad": 0.0926, "tokens": 126909619200, "tok_s": 158155.1}
|
| 158 |
+
{"step": 121080, "epoch": 0.769, "loss": 1.7783, "ppl": 5.92, "lr": 0.003, "grad": 0.1207, "tokens": 126930585600, "tok_s": 158579.7}
|
| 159 |
+
{"step": 121100, "epoch": 0.769, "loss": 1.77407, "ppl": 5.895, "lr": 0.003, "grad": 0.0697, "tokens": 126951552000, "tok_s": 158399.0}
|
| 160 |
+
{"step": 121120, "epoch": 0.77, "loss": 1.74103, "ppl": 5.703, "lr": 0.003, "grad": 0.1173, "tokens": 126972518400, "tok_s": 158234.0}
|
| 161 |
+
{"step": 121140, "epoch": 0.77, "loss": 1.72651, "ppl": 5.621, "lr": 0.003, "grad": 0.1055, "tokens": 126993484800, "tok_s": 157868.4}
|
| 162 |
+
{"step": 121160, "epoch": 0.77, "loss": 1.73743, "ppl": 5.683, "lr": 0.003, "grad": 0.0817, "tokens": 127014451200, "tok_s": 158264.6}
|
| 163 |
+
{"step": 121180, "epoch": 0.77, "loss": 1.68213, "ppl": 5.377, "lr": 0.003, "grad": 0.1247, "tokens": 127035417600, "tok_s": 158244.2}
|
| 164 |
+
{"step": 121200, "epoch": 0.77, "loss": 1.7441, "ppl": 5.721, "lr": 0.003, "grad": 0.0843, "tokens": 127056384000, "tok_s": 158130.6}
|
| 165 |
+
{"step": 121220, "epoch": 0.77, "loss": 1.73087, "ppl": 5.646, "lr": 0.003, "grad": 0.1381, "tokens": 127077350400, "tok_s": 158483.5}
|
| 166 |
+
{"step": 121240, "epoch": 0.77, "loss": 1.73485, "ppl": 5.668, "lr": 0.003, "grad": 0.0789, "tokens": 127098316800, "tok_s": 158174.2}
|
| 167 |
+
{"step": 121260, "epoch": 0.77, "loss": 1.74716, "ppl": 5.738, "lr": 0.003, "grad": 0.0979, "tokens": 127119283200, "tok_s": 158112.4}
|
| 168 |
+
{"step": 121280, "epoch": 0.771, "loss": 1.77116, "ppl": 5.878, "lr": 0.003, "grad": 0.0934, "tokens": 127140249600, "tok_s": 158262.1}
|
| 169 |
+
{"step": 121300, "epoch": 0.771, "loss": 1.82227, "ppl": 6.186, "lr": 0.003, "grad": 0.079, "tokens": 127161216000, "tok_s": 158000.1}
|
| 170 |
+
{"step": 121320, "epoch": 0.771, "loss": 1.72362, "ppl": 5.605, "lr": 0.003, "grad": 0.0794, "tokens": 127182182400, "tok_s": 157528.5}
|
| 171 |
+
{"step": 121340, "epoch": 0.771, "loss": 1.75278, "ppl": 5.771, "lr": 0.003, "grad": 0.0857, "tokens": 127203148800, "tok_s": 158048.8}
|
| 172 |
+
{"step": 121360, "epoch": 0.771, "loss": 1.74111, "ppl": 5.704, "lr": 0.003, "grad": 0.1652, "tokens": 127224115200, "tok_s": 157588.4}
|
| 173 |
+
{"step": 121380, "epoch": 0.771, "loss": 1.69439, "ppl": 5.443, "lr": 0.003, "grad": 0.1086, "tokens": 127245081600, "tok_s": 157902.3}
|
| 174 |
+
{"step": 121400, "epoch": 0.771, "loss": 1.7142, "ppl": 5.552, "lr": 0.003, "grad": 0.1142, "tokens": 127266048000, "tok_s": 158412.9}
|
| 175 |
+
{"step": 121420, "epoch": 0.771, "loss": 1.74019, "ppl": 5.698, "lr": 0.003, "grad": 0.0906, "tokens": 127287014400, "tok_s": 157836.5}
|
| 176 |
+
{"step": 121440, "epoch": 0.772, "loss": 1.72826, "ppl": 5.631, "lr": 0.003, "grad": 0.1134, "tokens": 127307980800, "tok_s": 158065.2}
|
| 177 |
+
{"step": 121460, "epoch": 0.772, "loss": 1.74003, "ppl": 5.698, "lr": 0.003, "grad": 0.0668, "tokens": 127328947200, "tok_s": 157918.4}
|
| 178 |
+
{"step": 121480, "epoch": 0.772, "loss": 1.65398, "ppl": 5.228, "lr": 0.003, "grad": 0.0794, "tokens": 127349913600, "tok_s": 158197.4}
|
| 179 |
+
{"step": 121500, "epoch": 0.772, "loss": 1.86459, "ppl": 6.453, "lr": 0.003, "grad": 0.1087, "tokens": 127370880000, "tok_s": 158063.2}
|
| 180 |
+
{"step": 121520, "epoch": 0.772, "loss": 1.79078, "ppl": 5.994, "lr": 0.003, "grad": 0.0791, "tokens": 127391846400, "tok_s": 158023.3}
|
| 181 |
+
{"step": 121540, "epoch": 0.772, "loss": 1.69626, "ppl": 5.454, "lr": 0.003, "grad": 0.0787, "tokens": 127412812800, "tok_s": 158386.1}
|
| 182 |
+
{"step": 121560, "epoch": 0.772, "loss": 1.8497, "ppl": 6.358, "lr": 0.003, "grad": 0.1216, "tokens": 127433779200, "tok_s": 158302.6}
|
| 183 |
+
{"step": 121580, "epoch": 0.772, "loss": 1.73237, "ppl": 5.654, "lr": 0.003, "grad": 0.0618, "tokens": 127454745600, "tok_s": 158010.6}
|
| 184 |
+
{"step": 121600, "epoch": 0.773, "loss": 1.822, "ppl": 6.184, "lr": 0.003, "grad": 0.1084, "tokens": 127475712000, "tok_s": 158234.0}
|
| 185 |
+
{"step": 121620, "epoch": 0.773, "loss": 1.73894, "ppl": 5.691, "lr": 0.003, "grad": 0.0955, "tokens": 127496678400, "tok_s": 158215.2}
|
| 186 |
+
{"step": 121640, "epoch": 0.773, "loss": 1.7531, "ppl": 5.772, "lr": 0.003, "grad": 0.0885, "tokens": 127517644800, "tok_s": 158137.1}
|
| 187 |
+
{"step": 121660, "epoch": 0.773, "loss": 1.63741, "ppl": 5.142, "lr": 0.003, "grad": 0.1337, "tokens": 127538611200, "tok_s": 158453.3}
|
| 188 |
+
{"step": 121680, "epoch": 0.773, "loss": 1.4681, "ppl": 4.341, "lr": 0.003, "grad": 0.0686, "tokens": 127559577600, "tok_s": 158262.4}
|
| 189 |
+
{"step": 121700, "epoch": 0.773, "loss": 1.801, "ppl": 6.056, "lr": 0.003, "grad": 0.0927, "tokens": 127580544000, "tok_s": 158580.0}
|
| 190 |
+
{"step": 121720, "epoch": 0.773, "loss": 1.70228, "ppl": 5.486, "lr": 0.003, "grad": 0.0896, "tokens": 127601510400, "tok_s": 158186.3}
|
| 191 |
+
{"step": 121740, "epoch": 0.773, "loss": 1.71666, "ppl": 5.566, "lr": 0.003, "grad": 0.0741, "tokens": 127622476800, "tok_s": 157691.4}
|
| 192 |
+
{"step": 121760, "epoch": 0.774, "loss": 1.74423, "ppl": 5.721, "lr": 0.003, "grad": 0.0835, "tokens": 127643443200, "tok_s": 158551.3}
|
| 193 |
+
{"step": 121780, "epoch": 0.774, "loss": 1.70825, "ppl": 5.519, "lr": 0.003, "grad": 0.1327, "tokens": 127664409600, "tok_s": 158006.0}
|
| 194 |
+
{"step": 121800, "epoch": 0.774, "loss": 1.76715, "ppl": 5.854, "lr": 0.003, "grad": 0.124, "tokens": 127685376000, "tok_s": 158316.2}
|
| 195 |
+
{"step": 121820, "epoch": 0.774, "loss": 1.75149, "ppl": 5.763, "lr": 0.003, "grad": 0.1251, "tokens": 127706342400, "tok_s": 158031.7}
|
| 196 |
+
{"step": 121840, "epoch": 0.774, "loss": 1.76546, "ppl": 5.844, "lr": 0.003, "grad": 0.1012, "tokens": 127727308800, "tok_s": 158312.0}
|
| 197 |
+
{"step": 121860, "epoch": 0.774, "loss": 1.74101, "ppl": 5.703, "lr": 0.003, "grad": 0.0934, "tokens": 127748275200, "tok_s": 158211.3}
|
| 198 |
+
{"step": 121880, "epoch": 0.774, "loss": 1.74427, "ppl": 5.722, "lr": 0.003, "grad": 0.0885, "tokens": 127769241600, "tok_s": 158570.9}
|
| 199 |
+
{"step": 121900, "epoch": 0.775, "loss": 1.73095, "ppl": 5.646, "lr": 0.003, "grad": 0.105, "tokens": 127790208000, "tok_s": 158065.3}
|
| 200 |
+
{"step": 121920, "epoch": 0.775, "loss": 1.73132, "ppl": 5.648, "lr": 0.003, "grad": 0.1076, "tokens": 127811174400, "tok_s": 158156.8}
|
| 201 |
+
{"step": 121940, "epoch": 0.775, "loss": 1.73839, "ppl": 5.688, "lr": 0.003, "grad": 0.0761, "tokens": 127832140800, "tok_s": 158019.0}
|
| 202 |
+
{"step": 121960, "epoch": 0.775, "loss": 1.77001, "ppl": 5.871, "lr": 0.003, "grad": 0.0775, "tokens": 127853107200, "tok_s": 158320.9}
|
| 203 |
+
{"step": 121980, "epoch": 0.775, "loss": 1.73814, "ppl": 5.687, "lr": 0.003, "grad": 0.1277, "tokens": 127874073600, "tok_s": 157767.0}
|
| 204 |
+
{"step": 122000, "epoch": 0.775, "loss": 1.76769, "ppl": 5.857, "lr": 0.003, "grad": 0.1164, "tokens": 127895040000, "tok_s": 158129.5}
|
| 205 |
+
{"step": 122000, "val_loss": 1.75038, "val_ppl": 5.757, "is_best": false}
|
logs/log_123000.jsonl
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 118000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-05T19:25:40.381447"}
|
| 2 |
+
{"step": 118020, "epoch": 0.75, "loss": 1.73979, "ppl": 5.696, "lr": 0.003, "grad": 0.0904, "tokens": 123722726400, "tok_s": 158304.5}
|
| 3 |
+
{"step": 118040, "epoch": 0.75, "loss": 1.74056, "ppl": 5.701, "lr": 0.003, "grad": 0.0638, "tokens": 123743692800, "tok_s": 158016.5}
|
| 4 |
+
{"step": 118060, "epoch": 0.75, "loss": 1.71538, "ppl": 5.559, "lr": 0.003, "grad": 0.1665, "tokens": 123764659200, "tok_s": 158294.3}
|
| 5 |
+
{"step": 118080, "epoch": 0.75, "loss": 1.61202, "ppl": 5.013, "lr": 0.003, "grad": 0.1077, "tokens": 123785625600, "tok_s": 158421.7}
|
| 6 |
+
{"step": 118100, "epoch": 0.75, "loss": 1.76723, "ppl": 5.855, "lr": 0.003, "grad": 0.1292, "tokens": 123806592000, "tok_s": 158338.1}
|
| 7 |
+
{"step": 118120, "epoch": 0.75, "loss": 1.72861, "ppl": 5.633, "lr": 0.003, "grad": 0.079, "tokens": 123827558400, "tok_s": 158489.0}
|
| 8 |
+
{"step": 118140, "epoch": 0.751, "loss": 1.74261, "ppl": 5.712, "lr": 0.003, "grad": 0.0913, "tokens": 123848524800, "tok_s": 158102.0}
|
| 9 |
+
{"step": 118160, "epoch": 0.751, "loss": 1.67597, "ppl": 5.344, "lr": 0.003, "grad": 0.0904, "tokens": 123869491200, "tok_s": 158332.4}
|
| 10 |
+
{"step": 118180, "epoch": 0.751, "loss": 1.62789, "ppl": 5.093, "lr": 0.003, "grad": 0.0735, "tokens": 123890457600, "tok_s": 157954.9}
|
| 11 |
+
{"step": 118200, "epoch": 0.751, "loss": 1.59216, "ppl": 4.914, "lr": 0.003, "grad": 0.1055, "tokens": 123911424000, "tok_s": 158124.6}
|
| 12 |
+
{"step": 118220, "epoch": 0.751, "loss": 1.77912, "ppl": 5.925, "lr": 0.003, "grad": 0.0698, "tokens": 123932390400, "tok_s": 158541.3}
|
| 13 |
+
{"step": 118240, "epoch": 0.751, "loss": 1.70235, "ppl": 5.487, "lr": 0.003, "grad": 0.118, "tokens": 123953356800, "tok_s": 158605.3}
|
| 14 |
+
{"step": 118260, "epoch": 0.751, "loss": 1.75982, "ppl": 5.811, "lr": 0.003, "grad": 0.0774, "tokens": 123974323200, "tok_s": 157719.7}
|
| 15 |
+
{"step": 118280, "epoch": 0.752, "loss": 1.70922, "ppl": 5.525, "lr": 0.003, "grad": 0.1039, "tokens": 123995289600, "tok_s": 157979.7}
|
| 16 |
+
{"step": 118300, "epoch": 0.752, "loss": 1.75378, "ppl": 5.776, "lr": 0.003, "grad": 0.0803, "tokens": 124016256000, "tok_s": 158562.7}
|
| 17 |
+
{"step": 118320, "epoch": 0.752, "loss": 1.75956, "ppl": 5.81, "lr": 0.003, "grad": 0.094, "tokens": 124037222400, "tok_s": 158133.7}
|
| 18 |
+
{"step": 118340, "epoch": 0.752, "loss": 1.72452, "ppl": 5.61, "lr": 0.003, "grad": 0.0816, "tokens": 124058188800, "tok_s": 157996.3}
|
| 19 |
+
{"step": 118360, "epoch": 0.752, "loss": 1.77153, "ppl": 5.88, "lr": 0.003, "grad": 0.0658, "tokens": 124079155200, "tok_s": 158511.8}
|
| 20 |
+
{"step": 118380, "epoch": 0.752, "loss": 1.68067, "ppl": 5.369, "lr": 0.003, "grad": 0.0788, "tokens": 124100121600, "tok_s": 157873.7}
|
| 21 |
+
{"step": 118400, "epoch": 0.752, "loss": 1.78125, "ppl": 5.937, "lr": 0.003, "grad": 0.1265, "tokens": 124121088000, "tok_s": 158508.4}
|
| 22 |
+
{"step": 118420, "epoch": 0.752, "loss": 1.75976, "ppl": 5.811, "lr": 0.003, "grad": 0.0963, "tokens": 124142054400, "tok_s": 158543.6}
|
| 23 |
+
{"step": 118440, "epoch": 0.753, "loss": 1.67067, "ppl": 5.316, "lr": 0.003, "grad": 0.0701, "tokens": 124163020800, "tok_s": 158495.1}
|
| 24 |
+
{"step": 118460, "epoch": 0.753, "loss": 1.81095, "ppl": 6.116, "lr": 0.003, "grad": 0.118, "tokens": 124183987200, "tok_s": 158618.8}
|
| 25 |
+
{"step": 118480, "epoch": 0.753, "loss": 1.80713, "ppl": 6.093, "lr": 0.003, "grad": 0.1225, "tokens": 124204953600, "tok_s": 158643.1}
|
| 26 |
+
{"step": 118500, "epoch": 0.753, "loss": 1.90087, "ppl": 6.692, "lr": 0.003, "grad": 0.0971, "tokens": 124225920000, "tok_s": 158526.0}
|
| 27 |
+
{"step": 118520, "epoch": 0.753, "loss": 1.7631, "ppl": 5.83, "lr": 0.003, "grad": 0.0917, "tokens": 124246886400, "tok_s": 158524.9}
|
| 28 |
+
{"step": 118540, "epoch": 0.753, "loss": 1.65783, "ppl": 5.248, "lr": 0.003, "grad": 0.0625, "tokens": 124267852800, "tok_s": 158043.8}
|
| 29 |
+
{"step": 118560, "epoch": 0.753, "loss": 1.67888, "ppl": 5.36, "lr": 0.003, "grad": 0.1154, "tokens": 124288819200, "tok_s": 158294.7}
|
| 30 |
+
{"step": 118580, "epoch": 0.753, "loss": 1.70275, "ppl": 5.489, "lr": 0.003, "grad": 0.1018, "tokens": 124309785600, "tok_s": 158415.3}
|
| 31 |
+
{"step": 118600, "epoch": 0.754, "loss": 1.63827, "ppl": 5.146, "lr": 0.003, "grad": 0.0825, "tokens": 124330752000, "tok_s": 158406.3}
|
| 32 |
+
{"step": 118620, "epoch": 0.754, "loss": 1.71381, "ppl": 5.55, "lr": 0.003, "grad": 0.1082, "tokens": 124351718400, "tok_s": 158419.1}
|
| 33 |
+
{"step": 118640, "epoch": 0.754, "loss": 1.6619, "ppl": 5.269, "lr": 0.003, "grad": 0.1085, "tokens": 124372684800, "tok_s": 158500.8}
|
| 34 |
+
{"step": 118660, "epoch": 0.754, "loss": 1.84244, "ppl": 6.312, "lr": 0.003, "grad": 0.1561, "tokens": 124393651200, "tok_s": 158192.5}
|
| 35 |
+
{"step": 118680, "epoch": 0.754, "loss": 1.77033, "ppl": 5.873, "lr": 0.003, "grad": 0.1412, "tokens": 124414617600, "tok_s": 157722.2}
|
| 36 |
+
{"step": 118700, "epoch": 0.754, "loss": 1.74147, "ppl": 5.706, "lr": 0.003, "grad": 0.111, "tokens": 124435584000, "tok_s": 158601.6}
|
| 37 |
+
{"step": 118720, "epoch": 0.754, "loss": 1.66524, "ppl": 5.287, "lr": 0.003, "grad": 0.0856, "tokens": 124456550400, "tok_s": 158448.0}
|
| 38 |
+
{"step": 118740, "epoch": 0.754, "loss": 1.69815, "ppl": 5.464, "lr": 0.003, "grad": 0.0807, "tokens": 124477516800, "tok_s": 158113.7}
|
| 39 |
+
{"step": 118760, "epoch": 0.755, "loss": 1.76824, "ppl": 5.861, "lr": 0.003, "grad": 0.1075, "tokens": 124498483200, "tok_s": 158253.1}
|
| 40 |
+
{"step": 118780, "epoch": 0.755, "loss": 1.67594, "ppl": 5.344, "lr": 0.003, "grad": 0.1487, "tokens": 124519449600, "tok_s": 158222.0}
|
| 41 |
+
{"step": 118800, "epoch": 0.755, "loss": 1.69363, "ppl": 5.439, "lr": 0.003, "grad": 0.1075, "tokens": 124540416000, "tok_s": 158604.0}
|
| 42 |
+
{"step": 118820, "epoch": 0.755, "loss": 1.7418, "ppl": 5.708, "lr": 0.003, "grad": 0.1089, "tokens": 124561382400, "tok_s": 158553.7}
|
| 43 |
+
{"step": 118840, "epoch": 0.755, "loss": 1.67568, "ppl": 5.342, "lr": 0.003, "grad": 0.0724, "tokens": 124582348800, "tok_s": 157825.5}
|
| 44 |
+
{"step": 118860, "epoch": 0.755, "loss": 1.75391, "ppl": 5.777, "lr": 0.003, "grad": 0.087, "tokens": 124603315200, "tok_s": 158545.7}
|
| 45 |
+
{"step": 118880, "epoch": 0.755, "loss": 1.77945, "ppl": 5.927, "lr": 0.003, "grad": 0.097, "tokens": 124624281600, "tok_s": 158515.1}
|
| 46 |
+
{"step": 118900, "epoch": 0.755, "loss": 1.44913, "ppl": 4.259, "lr": 0.003, "grad": 0.077, "tokens": 124645248000, "tok_s": 158522.8}
|
| 47 |
+
{"step": 118920, "epoch": 0.756, "loss": 1.67776, "ppl": 5.354, "lr": 0.003, "grad": 0.1038, "tokens": 124666214400, "tok_s": 158597.0}
|
| 48 |
+
{"step": 118940, "epoch": 0.756, "loss": 1.69051, "ppl": 5.422, "lr": 0.003, "grad": 0.0728, "tokens": 124687180800, "tok_s": 158127.2}
|
| 49 |
+
{"step": 118960, "epoch": 0.756, "loss": 1.78371, "ppl": 5.952, "lr": 0.003, "grad": 0.1134, "tokens": 124708147200, "tok_s": 158357.3}
|
| 50 |
+
{"step": 118980, "epoch": 0.756, "loss": 1.73447, "ppl": 5.666, "lr": 0.003, "grad": 0.0627, "tokens": 124729113600, "tok_s": 158191.1}
|
| 51 |
+
{"step": 119000, "epoch": 0.756, "loss": 1.89018, "ppl": 6.621, "lr": 0.003, "grad": 0.1249, "tokens": 124750080000, "tok_s": 158547.0}
|
| 52 |
+
{"step": 119000, "val_loss": 1.73142, "val_ppl": 5.649, "is_best": true}
|
| 53 |
+
{"step": 119020, "epoch": 0.756, "loss": 1.73487, "ppl": 5.668, "lr": 0.003, "grad": 0.0905, "tokens": 124771046400, "tok_s": 158219.6}
|
| 54 |
+
{"step": 119040, "epoch": 0.756, "loss": 1.6774, "ppl": 5.352, "lr": 0.003, "grad": 0.1006, "tokens": 124792012800, "tok_s": 158627.9}
|
| 55 |
+
{"step": 119060, "epoch": 0.756, "loss": 1.77446, "ppl": 5.897, "lr": 0.003, "grad": 0.1015, "tokens": 124812979200, "tok_s": 156897.4}
|
| 56 |
+
{"step": 119080, "epoch": 0.757, "loss": 1.72486, "ppl": 5.612, "lr": 0.003, "grad": 0.1353, "tokens": 124833945600, "tok_s": 158154.9}
|
| 57 |
+
{"step": 119100, "epoch": 0.757, "loss": 1.59788, "ppl": 4.943, "lr": 0.003, "grad": 0.1061, "tokens": 124854912000, "tok_s": 158116.9}
|
| 58 |
+
{"step": 119120, "epoch": 0.757, "loss": 1.86998, "ppl": 6.488, "lr": 0.003, "grad": 0.1451, "tokens": 124875878400, "tok_s": 158367.4}
|
| 59 |
+
{"step": 119140, "epoch": 0.757, "loss": 1.76439, "ppl": 5.838, "lr": 0.003, "grad": 0.0871, "tokens": 124896844800, "tok_s": 158280.7}
|
| 60 |
+
{"step": 119160, "epoch": 0.757, "loss": 1.74972, "ppl": 5.753, "lr": 0.003, "grad": 0.1081, "tokens": 124917811200, "tok_s": 158102.5}
|
| 61 |
+
{"step": 119180, "epoch": 0.757, "loss": 1.79359, "ppl": 6.011, "lr": 0.003, "grad": 0.0719, "tokens": 124938777600, "tok_s": 158504.6}
|
| 62 |
+
{"step": 119200, "epoch": 0.757, "loss": 1.70737, "ppl": 5.514, "lr": 0.003, "grad": 0.1167, "tokens": 124959744000, "tok_s": 158144.0}
|
| 63 |
+
{"step": 119220, "epoch": 0.757, "loss": 1.77966, "ppl": 5.928, "lr": 0.003, "grad": 0.0904, "tokens": 124980710400, "tok_s": 158453.4}
|
| 64 |
+
{"step": 119240, "epoch": 0.758, "loss": 1.69198, "ppl": 5.43, "lr": 0.003, "grad": 0.0899, "tokens": 125001676800, "tok_s": 158364.4}
|
| 65 |
+
{"step": 119260, "epoch": 0.758, "loss": 1.72413, "ppl": 5.608, "lr": 0.003, "grad": 0.121, "tokens": 125022643200, "tok_s": 158461.9}
|
| 66 |
+
{"step": 119280, "epoch": 0.758, "loss": 1.60305, "ppl": 4.968, "lr": 0.003, "grad": 0.11, "tokens": 125043609600, "tok_s": 158381.0}
|
| 67 |
+
{"step": 119300, "epoch": 0.758, "loss": 1.80217, "ppl": 6.063, "lr": 0.003, "grad": 0.094, "tokens": 125064576000, "tok_s": 158595.4}
|
| 68 |
+
{"step": 119320, "epoch": 0.758, "loss": 1.74326, "ppl": 5.716, "lr": 0.003, "grad": 0.0768, "tokens": 125085542400, "tok_s": 158531.8}
|
| 69 |
+
{"step": 119340, "epoch": 0.758, "loss": 1.79594, "ppl": 6.025, "lr": 0.003, "grad": 0.0855, "tokens": 125106508800, "tok_s": 158305.4}
|
| 70 |
+
{"step": 119360, "epoch": 0.758, "loss": 1.73375, "ppl": 5.662, "lr": 0.003, "grad": 0.0825, "tokens": 125127475200, "tok_s": 157920.6}
|
| 71 |
+
{"step": 119380, "epoch": 0.758, "loss": 1.84414, "ppl": 6.323, "lr": 0.003, "grad": 0.0913, "tokens": 125148441600, "tok_s": 158531.8}
|
| 72 |
+
{"step": 119400, "epoch": 0.759, "loss": 1.81026, "ppl": 6.112, "lr": 0.003, "grad": 0.0727, "tokens": 125169408000, "tok_s": 158310.9}
|
| 73 |
+
{"step": 119420, "epoch": 0.759, "loss": 1.79423, "ppl": 6.015, "lr": 0.003, "grad": 0.093, "tokens": 125190374400, "tok_s": 158200.8}
|
| 74 |
+
{"step": 119440, "epoch": 0.759, "loss": 1.73512, "ppl": 5.67, "lr": 0.003, "grad": 0.0858, "tokens": 125211340800, "tok_s": 158638.4}
|
| 75 |
+
{"step": 119460, "epoch": 0.759, "loss": 1.77697, "ppl": 5.912, "lr": 0.003, "grad": 0.1038, "tokens": 125232307200, "tok_s": 157567.2}
|
| 76 |
+
{"step": 119480, "epoch": 0.759, "loss": 1.82226, "ppl": 6.186, "lr": 0.003, "grad": 0.0759, "tokens": 125253273600, "tok_s": 157654.3}
|
| 77 |
+
{"step": 119500, "epoch": 0.759, "loss": 1.78047, "ppl": 5.933, "lr": 0.003, "grad": 0.1256, "tokens": 125274240000, "tok_s": 158489.2}
|
| 78 |
+
{"step": 119520, "epoch": 0.759, "loss": 1.78623, "ppl": 5.967, "lr": 0.003, "grad": 0.0918, "tokens": 125295206400, "tok_s": 158365.4}
|
| 79 |
+
{"step": 119540, "epoch": 0.76, "loss": 1.70974, "ppl": 5.527, "lr": 0.003, "grad": 0.0978, "tokens": 125316172800, "tok_s": 157639.6}
|
| 80 |
+
{"step": 119560, "epoch": 0.76, "loss": 1.7911, "ppl": 5.996, "lr": 0.003, "grad": 0.1486, "tokens": 125337139200, "tok_s": 157989.6}
|
| 81 |
+
{"step": 119580, "epoch": 0.76, "loss": 1.59428, "ppl": 4.925, "lr": 0.003, "grad": 0.0848, "tokens": 125358105600, "tok_s": 158460.6}
|
| 82 |
+
{"step": 119600, "epoch": 0.76, "loss": 1.76708, "ppl": 5.854, "lr": 0.003, "grad": 0.098, "tokens": 125379072000, "tok_s": 158466.4}
|
| 83 |
+
{"step": 119620, "epoch": 0.76, "loss": 1.76648, "ppl": 5.85, "lr": 0.003, "grad": 0.0845, "tokens": 125400038400, "tok_s": 158403.4}
|
| 84 |
+
{"step": 119640, "epoch": 0.76, "loss": 1.73094, "ppl": 5.646, "lr": 0.003, "grad": 0.1216, "tokens": 125421004800, "tok_s": 158445.8}
|
| 85 |
+
{"step": 119660, "epoch": 0.76, "loss": 1.7842, "ppl": 5.955, "lr": 0.003, "grad": 0.0949, "tokens": 125441971200, "tok_s": 158513.3}
|
| 86 |
+
{"step": 119680, "epoch": 0.76, "loss": 1.75771, "ppl": 5.799, "lr": 0.003, "grad": 0.0852, "tokens": 125462937600, "tok_s": 157878.6}
|
| 87 |
+
{"step": 119700, "epoch": 0.761, "loss": 1.73007, "ppl": 5.641, "lr": 0.003, "grad": 0.0806, "tokens": 125483904000, "tok_s": 158358.3}
|
| 88 |
+
{"step": 119720, "epoch": 0.761, "loss": 1.70879, "ppl": 5.522, "lr": 0.003, "grad": 0.1121, "tokens": 125504870400, "tok_s": 158528.5}
|
| 89 |
+
{"step": 119740, "epoch": 0.761, "loss": 1.74589, "ppl": 5.731, "lr": 0.003, "grad": 0.0941, "tokens": 125525836800, "tok_s": 158341.9}
|
| 90 |
+
{"step": 119760, "epoch": 0.761, "loss": 1.63881, "ppl": 5.149, "lr": 0.003, "grad": 0.0731, "tokens": 125546803200, "tok_s": 158367.5}
|
| 91 |
+
{"step": 119780, "epoch": 0.761, "loss": 1.71789, "ppl": 5.573, "lr": 0.003, "grad": 0.0898, "tokens": 125567769600, "tok_s": 158093.5}
|
| 92 |
+
{"step": 119800, "epoch": 0.761, "loss": 1.73879, "ppl": 5.69, "lr": 0.003, "grad": 0.0634, "tokens": 125588736000, "tok_s": 158062.8}
|
| 93 |
+
{"step": 119820, "epoch": 0.761, "loss": 1.76379, "ppl": 5.834, "lr": 0.003, "grad": 0.0926, "tokens": 125609702400, "tok_s": 158018.0}
|
| 94 |
+
{"step": 119840, "epoch": 0.761, "loss": 1.77844, "ppl": 5.921, "lr": 0.003, "grad": 0.0621, "tokens": 125630668800, "tok_s": 158457.5}
|
| 95 |
+
{"step": 119860, "epoch": 0.762, "loss": 1.79022, "ppl": 5.991, "lr": 0.003, "grad": 0.0978, "tokens": 125651635200, "tok_s": 157351.8}
|
| 96 |
+
{"step": 119880, "epoch": 0.762, "loss": 1.76953, "ppl": 5.868, "lr": 0.003, "grad": 0.1406, "tokens": 125672601600, "tok_s": 157745.2}
|
| 97 |
+
{"step": 119900, "epoch": 0.762, "loss": 1.75451, "ppl": 5.781, "lr": 0.003, "grad": 0.1048, "tokens": 125693568000, "tok_s": 158566.8}
|
| 98 |
+
{"step": 119920, "epoch": 0.762, "loss": 1.77878, "ppl": 5.923, "lr": 0.003, "grad": 0.1219, "tokens": 125714534400, "tok_s": 157984.7}
|
| 99 |
+
{"step": 119940, "epoch": 0.762, "loss": 1.72756, "ppl": 5.627, "lr": 0.003, "grad": 0.0799, "tokens": 125735500800, "tok_s": 158248.3}
|
| 100 |
+
{"step": 119960, "epoch": 0.762, "loss": 1.75123, "ppl": 5.762, "lr": 0.003, "grad": 0.092, "tokens": 125756467200, "tok_s": 158026.9}
|
| 101 |
+
{"step": 119980, "epoch": 0.762, "loss": 1.79766, "ppl": 6.036, "lr": 0.003, "grad": 0.0985, "tokens": 125777433600, "tok_s": 158297.1}
|
| 102 |
+
{"step": 120000, "epoch": 0.762, "loss": 1.72787, "ppl": 5.629, "lr": 0.003, "grad": 0.072, "tokens": 125798400000, "tok_s": 158454.4}
|
| 103 |
+
{"step": 120000, "val_loss": 1.74408, "val_ppl": 5.721, "is_best": false}
|
| 104 |
+
{"step": 120020, "epoch": 0.763, "loss": 1.76051, "ppl": 5.815, "lr": 0.003, "grad": 0.1876, "tokens": 125819366400, "tok_s": 157867.4}
|
| 105 |
+
{"step": 120040, "epoch": 0.763, "loss": 1.74994, "ppl": 5.754, "lr": 0.003, "grad": 0.0985, "tokens": 125840332800, "tok_s": 157954.2}
|
| 106 |
+
{"step": 120060, "epoch": 0.763, "loss": 1.69562, "ppl": 5.45, "lr": 0.003, "grad": 0.0731, "tokens": 125861299200, "tok_s": 158281.6}
|
| 107 |
+
{"step": 120080, "epoch": 0.763, "loss": 1.76473, "ppl": 5.84, "lr": 0.003, "grad": 0.0962, "tokens": 125882265600, "tok_s": 157364.7}
|
| 108 |
+
{"step": 120100, "epoch": 0.763, "loss": 1.75624, "ppl": 5.791, "lr": 0.003, "grad": 0.0947, "tokens": 125903232000, "tok_s": 158207.3}
|
| 109 |
+
{"step": 120120, "epoch": 0.763, "loss": 1.82935, "ppl": 6.23, "lr": 0.003, "grad": 0.1702, "tokens": 125924198400, "tok_s": 157990.1}
|
| 110 |
+
{"step": 120140, "epoch": 0.763, "loss": 1.77181, "ppl": 5.881, "lr": 0.003, "grad": 0.1107, "tokens": 125945164800, "tok_s": 157434.3}
|
| 111 |
+
{"step": 120160, "epoch": 0.763, "loss": 1.72448, "ppl": 5.61, "lr": 0.003, "grad": 0.1443, "tokens": 125966131200, "tok_s": 158178.7}
|
| 112 |
+
{"step": 120180, "epoch": 0.764, "loss": 1.75123, "ppl": 5.762, "lr": 0.003, "grad": 0.0966, "tokens": 125987097600, "tok_s": 158345.2}
|
| 113 |
+
{"step": 120200, "epoch": 0.764, "loss": 1.80418, "ppl": 6.075, "lr": 0.003, "grad": 0.092, "tokens": 126008064000, "tok_s": 158277.5}
|
| 114 |
+
{"step": 120220, "epoch": 0.764, "loss": 1.70348, "ppl": 5.493, "lr": 0.003, "grad": 0.0668, "tokens": 126029030400, "tok_s": 158346.1}
|
| 115 |
+
{"step": 120240, "epoch": 0.764, "loss": 1.74817, "ppl": 5.744, "lr": 0.003, "grad": 0.0858, "tokens": 126049996800, "tok_s": 157902.1}
|
| 116 |
+
{"step": 120260, "epoch": 0.764, "loss": 1.6631, "ppl": 5.276, "lr": 0.003, "grad": 0.0791, "tokens": 126070963200, "tok_s": 158119.9}
|
| 117 |
+
{"step": 120280, "epoch": 0.764, "loss": 1.76204, "ppl": 5.824, "lr": 0.003, "grad": 0.0982, "tokens": 126091929600, "tok_s": 158187.1}
|
| 118 |
+
{"step": 120300, "epoch": 0.764, "loss": 1.78652, "ppl": 5.969, "lr": 0.003, "grad": 0.1254, "tokens": 126112896000, "tok_s": 157547.9}
|
| 119 |
+
{"step": 120320, "epoch": 0.764, "loss": 1.66687, "ppl": 5.296, "lr": 0.003, "grad": 0.0911, "tokens": 126133862400, "tok_s": 157968.6}
|
| 120 |
+
{"step": 120340, "epoch": 0.765, "loss": 1.63279, "ppl": 5.118, "lr": 0.003, "grad": 0.0737, "tokens": 126154828800, "tok_s": 158102.3}
|
| 121 |
+
{"step": 120360, "epoch": 0.765, "loss": 1.75871, "ppl": 5.805, "lr": 0.003, "grad": 0.0806, "tokens": 126175795200, "tok_s": 158287.5}
|
| 122 |
+
{"step": 120380, "epoch": 0.765, "loss": 1.73318, "ppl": 5.659, "lr": 0.003, "grad": 0.105, "tokens": 126196761600, "tok_s": 158290.9}
|
| 123 |
+
{"step": 120400, "epoch": 0.765, "loss": 1.64862, "ppl": 5.2, "lr": 0.003, "grad": 0.0899, "tokens": 126217728000, "tok_s": 158273.1}
|
| 124 |
+
{"step": 120420, "epoch": 0.765, "loss": 1.6669, "ppl": 5.296, "lr": 0.003, "grad": 0.0948, "tokens": 126238694400, "tok_s": 158423.4}
|
| 125 |
+
{"step": 120440, "epoch": 0.765, "loss": 1.85421, "ppl": 6.387, "lr": 0.003, "grad": 0.1484, "tokens": 126259660800, "tok_s": 158566.7}
|
| 126 |
+
{"step": 120460, "epoch": 0.765, "loss": 1.6474, "ppl": 5.193, "lr": 0.003, "grad": 0.0829, "tokens": 126280627200, "tok_s": 158433.5}
|
| 127 |
+
{"step": 120480, "epoch": 0.765, "loss": 1.72466, "ppl": 5.611, "lr": 0.003, "grad": 0.0757, "tokens": 126301593600, "tok_s": 158418.8}
|
| 128 |
+
{"step": 120500, "epoch": 0.766, "loss": 1.69928, "ppl": 5.47, "lr": 0.003, "grad": 0.0988, "tokens": 126322560000, "tok_s": 157887.0}
|
| 129 |
+
{"step": 120520, "epoch": 0.766, "loss": 1.71225, "ppl": 5.541, "lr": 0.003, "grad": 0.0648, "tokens": 126343526400, "tok_s": 158389.5}
|
| 130 |
+
{"step": 120540, "epoch": 0.766, "loss": 1.71587, "ppl": 5.562, "lr": 0.003, "grad": 0.0872, "tokens": 126364492800, "tok_s": 158433.1}
|
| 131 |
+
{"step": 120560, "epoch": 0.766, "loss": 1.81211, "ppl": 6.123, "lr": 0.003, "grad": 0.1148, "tokens": 126385459200, "tok_s": 158665.0}
|
| 132 |
+
{"step": 120580, "epoch": 0.766, "loss": 1.74413, "ppl": 5.721, "lr": 0.003, "grad": 0.1671, "tokens": 126406425600, "tok_s": 157791.9}
|
| 133 |
+
{"step": 120600, "epoch": 0.766, "loss": 1.77456, "ppl": 5.898, "lr": 0.003, "grad": 0.0833, "tokens": 126427392000, "tok_s": 158443.1}
|
| 134 |
+
{"step": 120620, "epoch": 0.766, "loss": 1.739, "ppl": 5.692, "lr": 0.003, "grad": 0.0814, "tokens": 126448358400, "tok_s": 158057.2}
|
| 135 |
+
{"step": 120640, "epoch": 0.767, "loss": 1.77647, "ppl": 5.909, "lr": 0.003, "grad": 0.0732, "tokens": 126469324800, "tok_s": 158430.0}
|
| 136 |
+
{"step": 120660, "epoch": 0.767, "loss": 1.64587, "ppl": 5.186, "lr": 0.003, "grad": 0.1168, "tokens": 126490291200, "tok_s": 158144.8}
|
| 137 |
+
{"step": 120680, "epoch": 0.767, "loss": 1.73953, "ppl": 5.695, "lr": 0.003, "grad": 0.0838, "tokens": 126511257600, "tok_s": 158193.9}
|
| 138 |
+
{"step": 120700, "epoch": 0.767, "loss": 1.69814, "ppl": 5.464, "lr": 0.003, "grad": 0.0981, "tokens": 126532224000, "tok_s": 158373.9}
|
| 139 |
+
{"step": 120720, "epoch": 0.767, "loss": 1.78551, "ppl": 5.963, "lr": 0.003, "grad": 0.1042, "tokens": 126553190400, "tok_s": 157961.8}
|
| 140 |
+
{"step": 120740, "epoch": 0.767, "loss": 1.60843, "ppl": 4.995, "lr": 0.003, "grad": 0.0756, "tokens": 126574156800, "tok_s": 158332.8}
|
| 141 |
+
{"step": 120760, "epoch": 0.767, "loss": 1.77685, "ppl": 5.911, "lr": 0.003, "grad": 0.1053, "tokens": 126595123200, "tok_s": 158314.9}
|
| 142 |
+
{"step": 120780, "epoch": 0.767, "loss": 1.78277, "ppl": 5.946, "lr": 0.003, "grad": 0.0814, "tokens": 126616089600, "tok_s": 158333.6}
|
| 143 |
+
{"step": 120800, "epoch": 0.768, "loss": 1.75826, "ppl": 5.802, "lr": 0.003, "grad": 0.1262, "tokens": 126637056000, "tok_s": 158309.5}
|
| 144 |
+
{"step": 120820, "epoch": 0.768, "loss": 1.77682, "ppl": 5.911, "lr": 0.003, "grad": 0.0963, "tokens": 126658022400, "tok_s": 157754.8}
|
| 145 |
+
{"step": 120840, "epoch": 0.768, "loss": 1.77882, "ppl": 5.923, "lr": 0.003, "grad": 0.1077, "tokens": 126678988800, "tok_s": 157839.5}
|
| 146 |
+
{"step": 120860, "epoch": 0.768, "loss": 1.80148, "ppl": 6.059, "lr": 0.003, "grad": 0.1123, "tokens": 126699955200, "tok_s": 158309.5}
|
| 147 |
+
{"step": 120880, "epoch": 0.768, "loss": 1.71568, "ppl": 5.56, "lr": 0.003, "grad": 0.092, "tokens": 126720921600, "tok_s": 158002.1}
|
| 148 |
+
{"step": 120900, "epoch": 0.768, "loss": 1.7699, "ppl": 5.87, "lr": 0.003, "grad": 0.0901, "tokens": 126741888000, "tok_s": 158141.4}
|
| 149 |
+
{"step": 120920, "epoch": 0.768, "loss": 1.76602, "ppl": 5.848, "lr": 0.003, "grad": 0.088, "tokens": 126762854400, "tok_s": 158239.9}
|
| 150 |
+
{"step": 120940, "epoch": 0.768, "loss": 1.73301, "ppl": 5.658, "lr": 0.003, "grad": 0.0793, "tokens": 126783820800, "tok_s": 158020.4}
|
| 151 |
+
{"step": 120960, "epoch": 0.769, "loss": 1.78942, "ppl": 5.986, "lr": 0.003, "grad": 0.1111, "tokens": 126804787200, "tok_s": 157801.6}
|
| 152 |
+
{"step": 120980, "epoch": 0.769, "loss": 1.76225, "ppl": 5.826, "lr": 0.003, "grad": 0.0816, "tokens": 126825753600, "tok_s": 157950.4}
|
| 153 |
+
{"step": 121000, "epoch": 0.769, "loss": 1.76714, "ppl": 5.854, "lr": 0.003, "grad": 0.1429, "tokens": 126846720000, "tok_s": 158387.1}
|
| 154 |
+
{"step": 121000, "val_loss": 1.75025, "val_ppl": 5.756, "is_best": false}
|
| 155 |
+
{"step": 121020, "epoch": 0.769, "loss": 1.69795, "ppl": 5.463, "lr": 0.003, "grad": 0.0895, "tokens": 126867686400, "tok_s": 158123.9}
|
| 156 |
+
{"step": 121040, "epoch": 0.769, "loss": 1.75501, "ppl": 5.784, "lr": 0.003, "grad": 0.1124, "tokens": 126888652800, "tok_s": 158291.6}
|
| 157 |
+
{"step": 121060, "epoch": 0.769, "loss": 1.73701, "ppl": 5.68, "lr": 0.003, "grad": 0.0926, "tokens": 126909619200, "tok_s": 158155.1}
|
| 158 |
+
{"step": 121080, "epoch": 0.769, "loss": 1.7783, "ppl": 5.92, "lr": 0.003, "grad": 0.1207, "tokens": 126930585600, "tok_s": 158579.7}
|
| 159 |
+
{"step": 121100, "epoch": 0.769, "loss": 1.77407, "ppl": 5.895, "lr": 0.003, "grad": 0.0697, "tokens": 126951552000, "tok_s": 158399.0}
|
| 160 |
+
{"step": 121120, "epoch": 0.77, "loss": 1.74103, "ppl": 5.703, "lr": 0.003, "grad": 0.1173, "tokens": 126972518400, "tok_s": 158234.0}
|
| 161 |
+
{"step": 121140, "epoch": 0.77, "loss": 1.72651, "ppl": 5.621, "lr": 0.003, "grad": 0.1055, "tokens": 126993484800, "tok_s": 157868.4}
|
| 162 |
+
{"step": 121160, "epoch": 0.77, "loss": 1.73743, "ppl": 5.683, "lr": 0.003, "grad": 0.0817, "tokens": 127014451200, "tok_s": 158264.6}
|
| 163 |
+
{"step": 121180, "epoch": 0.77, "loss": 1.68213, "ppl": 5.377, "lr": 0.003, "grad": 0.1247, "tokens": 127035417600, "tok_s": 158244.2}
|
| 164 |
+
{"step": 121200, "epoch": 0.77, "loss": 1.7441, "ppl": 5.721, "lr": 0.003, "grad": 0.0843, "tokens": 127056384000, "tok_s": 158130.6}
|
| 165 |
+
{"step": 121220, "epoch": 0.77, "loss": 1.73087, "ppl": 5.646, "lr": 0.003, "grad": 0.1381, "tokens": 127077350400, "tok_s": 158483.5}
|
| 166 |
+
{"step": 121240, "epoch": 0.77, "loss": 1.73485, "ppl": 5.668, "lr": 0.003, "grad": 0.0789, "tokens": 127098316800, "tok_s": 158174.2}
|
| 167 |
+
{"step": 121260, "epoch": 0.77, "loss": 1.74716, "ppl": 5.738, "lr": 0.003, "grad": 0.0979, "tokens": 127119283200, "tok_s": 158112.4}
|
| 168 |
+
{"step": 121280, "epoch": 0.771, "loss": 1.77116, "ppl": 5.878, "lr": 0.003, "grad": 0.0934, "tokens": 127140249600, "tok_s": 158262.1}
|
| 169 |
+
{"step": 121300, "epoch": 0.771, "loss": 1.82227, "ppl": 6.186, "lr": 0.003, "grad": 0.079, "tokens": 127161216000, "tok_s": 158000.1}
|
| 170 |
+
{"step": 121320, "epoch": 0.771, "loss": 1.72362, "ppl": 5.605, "lr": 0.003, "grad": 0.0794, "tokens": 127182182400, "tok_s": 157528.5}
|
| 171 |
+
{"step": 121340, "epoch": 0.771, "loss": 1.75278, "ppl": 5.771, "lr": 0.003, "grad": 0.0857, "tokens": 127203148800, "tok_s": 158048.8}
|
| 172 |
+
{"step": 121360, "epoch": 0.771, "loss": 1.74111, "ppl": 5.704, "lr": 0.003, "grad": 0.1652, "tokens": 127224115200, "tok_s": 157588.4}
|
| 173 |
+
{"step": 121380, "epoch": 0.771, "loss": 1.69439, "ppl": 5.443, "lr": 0.003, "grad": 0.1086, "tokens": 127245081600, "tok_s": 157902.3}
|
| 174 |
+
{"step": 121400, "epoch": 0.771, "loss": 1.7142, "ppl": 5.552, "lr": 0.003, "grad": 0.1142, "tokens": 127266048000, "tok_s": 158412.9}
|
| 175 |
+
{"step": 121420, "epoch": 0.771, "loss": 1.74019, "ppl": 5.698, "lr": 0.003, "grad": 0.0906, "tokens": 127287014400, "tok_s": 157836.5}
|
| 176 |
+
{"step": 121440, "epoch": 0.772, "loss": 1.72826, "ppl": 5.631, "lr": 0.003, "grad": 0.1134, "tokens": 127307980800, "tok_s": 158065.2}
|
| 177 |
+
{"step": 121460, "epoch": 0.772, "loss": 1.74003, "ppl": 5.698, "lr": 0.003, "grad": 0.0668, "tokens": 127328947200, "tok_s": 157918.4}
|
| 178 |
+
{"step": 121480, "epoch": 0.772, "loss": 1.65398, "ppl": 5.228, "lr": 0.003, "grad": 0.0794, "tokens": 127349913600, "tok_s": 158197.4}
|
| 179 |
+
{"step": 121500, "epoch": 0.772, "loss": 1.86459, "ppl": 6.453, "lr": 0.003, "grad": 0.1087, "tokens": 127370880000, "tok_s": 158063.2}
|
| 180 |
+
{"step": 121520, "epoch": 0.772, "loss": 1.79078, "ppl": 5.994, "lr": 0.003, "grad": 0.0791, "tokens": 127391846400, "tok_s": 158023.3}
|
| 181 |
+
{"step": 121540, "epoch": 0.772, "loss": 1.69626, "ppl": 5.454, "lr": 0.003, "grad": 0.0787, "tokens": 127412812800, "tok_s": 158386.1}
|
| 182 |
+
{"step": 121560, "epoch": 0.772, "loss": 1.8497, "ppl": 6.358, "lr": 0.003, "grad": 0.1216, "tokens": 127433779200, "tok_s": 158302.6}
|
| 183 |
+
{"step": 121580, "epoch": 0.772, "loss": 1.73237, "ppl": 5.654, "lr": 0.003, "grad": 0.0618, "tokens": 127454745600, "tok_s": 158010.6}
|
| 184 |
+
{"step": 121600, "epoch": 0.773, "loss": 1.822, "ppl": 6.184, "lr": 0.003, "grad": 0.1084, "tokens": 127475712000, "tok_s": 158234.0}
|
| 185 |
+
{"step": 121620, "epoch": 0.773, "loss": 1.73894, "ppl": 5.691, "lr": 0.003, "grad": 0.0955, "tokens": 127496678400, "tok_s": 158215.2}
|
| 186 |
+
{"step": 121640, "epoch": 0.773, "loss": 1.7531, "ppl": 5.772, "lr": 0.003, "grad": 0.0885, "tokens": 127517644800, "tok_s": 158137.1}
|
| 187 |
+
{"step": 121660, "epoch": 0.773, "loss": 1.63741, "ppl": 5.142, "lr": 0.003, "grad": 0.1337, "tokens": 127538611200, "tok_s": 158453.3}
|
| 188 |
+
{"step": 121680, "epoch": 0.773, "loss": 1.4681, "ppl": 4.341, "lr": 0.003, "grad": 0.0686, "tokens": 127559577600, "tok_s": 158262.4}
|
| 189 |
+
{"step": 121700, "epoch": 0.773, "loss": 1.801, "ppl": 6.056, "lr": 0.003, "grad": 0.0927, "tokens": 127580544000, "tok_s": 158580.0}
|
| 190 |
+
{"step": 121720, "epoch": 0.773, "loss": 1.70228, "ppl": 5.486, "lr": 0.003, "grad": 0.0896, "tokens": 127601510400, "tok_s": 158186.3}
|
| 191 |
+
{"step": 121740, "epoch": 0.773, "loss": 1.71666, "ppl": 5.566, "lr": 0.003, "grad": 0.0741, "tokens": 127622476800, "tok_s": 157691.4}
|
| 192 |
+
{"step": 121760, "epoch": 0.774, "loss": 1.74423, "ppl": 5.721, "lr": 0.003, "grad": 0.0835, "tokens": 127643443200, "tok_s": 158551.3}
|
| 193 |
+
{"step": 121780, "epoch": 0.774, "loss": 1.70825, "ppl": 5.519, "lr": 0.003, "grad": 0.1327, "tokens": 127664409600, "tok_s": 158006.0}
|
| 194 |
+
{"step": 121800, "epoch": 0.774, "loss": 1.76715, "ppl": 5.854, "lr": 0.003, "grad": 0.124, "tokens": 127685376000, "tok_s": 158316.2}
|
| 195 |
+
{"step": 121820, "epoch": 0.774, "loss": 1.75149, "ppl": 5.763, "lr": 0.003, "grad": 0.1251, "tokens": 127706342400, "tok_s": 158031.7}
|
| 196 |
+
{"step": 121840, "epoch": 0.774, "loss": 1.76546, "ppl": 5.844, "lr": 0.003, "grad": 0.1012, "tokens": 127727308800, "tok_s": 158312.0}
|
| 197 |
+
{"step": 121860, "epoch": 0.774, "loss": 1.74101, "ppl": 5.703, "lr": 0.003, "grad": 0.0934, "tokens": 127748275200, "tok_s": 158211.3}
|
| 198 |
+
{"step": 121880, "epoch": 0.774, "loss": 1.74427, "ppl": 5.722, "lr": 0.003, "grad": 0.0885, "tokens": 127769241600, "tok_s": 158570.9}
|
| 199 |
+
{"step": 121900, "epoch": 0.775, "loss": 1.73095, "ppl": 5.646, "lr": 0.003, "grad": 0.105, "tokens": 127790208000, "tok_s": 158065.3}
|
| 200 |
+
{"step": 121920, "epoch": 0.775, "loss": 1.73132, "ppl": 5.648, "lr": 0.003, "grad": 0.1076, "tokens": 127811174400, "tok_s": 158156.8}
|
| 201 |
+
{"step": 121940, "epoch": 0.775, "loss": 1.73839, "ppl": 5.688, "lr": 0.003, "grad": 0.0761, "tokens": 127832140800, "tok_s": 158019.0}
|
| 202 |
+
{"step": 121960, "epoch": 0.775, "loss": 1.77001, "ppl": 5.871, "lr": 0.003, "grad": 0.0775, "tokens": 127853107200, "tok_s": 158320.9}
|
| 203 |
+
{"step": 121980, "epoch": 0.775, "loss": 1.73814, "ppl": 5.687, "lr": 0.003, "grad": 0.1277, "tokens": 127874073600, "tok_s": 157767.0}
|
| 204 |
+
{"step": 122000, "epoch": 0.775, "loss": 1.76769, "ppl": 5.857, "lr": 0.003, "grad": 0.1164, "tokens": 127895040000, "tok_s": 158129.5}
|
| 205 |
+
{"step": 122000, "val_loss": 1.75038, "val_ppl": 5.757, "is_best": false}
|
| 206 |
+
{"step": 122020, "epoch": 0.775, "loss": 1.7167, "ppl": 5.566, "lr": 0.003, "grad": 0.0901, "tokens": 127916006400, "tok_s": 157773.8}
|
| 207 |
+
{"step": 122040, "epoch": 0.775, "loss": 1.77091, "ppl": 5.876, "lr": 0.003, "grad": 0.0943, "tokens": 127936972800, "tok_s": 157870.0}
|
| 208 |
+
{"step": 122060, "epoch": 0.776, "loss": 1.71869, "ppl": 5.577, "lr": 0.003, "grad": 0.0858, "tokens": 127957939200, "tok_s": 157703.7}
|
| 209 |
+
{"step": 122080, "epoch": 0.776, "loss": 1.78222, "ppl": 5.943, "lr": 0.003, "grad": 0.1521, "tokens": 127978905600, "tok_s": 157336.3}
|
| 210 |
+
{"step": 122100, "epoch": 0.776, "loss": 1.75597, "ppl": 5.789, "lr": 0.003, "grad": 0.1343, "tokens": 127999872000, "tok_s": 157637.4}
|
| 211 |
+
{"step": 122120, "epoch": 0.776, "loss": 1.77689, "ppl": 5.911, "lr": 0.003, "grad": 0.1217, "tokens": 128020838400, "tok_s": 158246.4}
|
| 212 |
+
{"step": 122140, "epoch": 0.776, "loss": 1.71667, "ppl": 5.566, "lr": 0.003, "grad": 0.1049, "tokens": 128041804800, "tok_s": 158054.1}
|
| 213 |
+
{"step": 122160, "epoch": 0.776, "loss": 1.7559, "ppl": 5.789, "lr": 0.003, "grad": 0.0987, "tokens": 128062771200, "tok_s": 157557.1}
|
| 214 |
+
{"step": 122180, "epoch": 0.776, "loss": 1.76778, "ppl": 5.858, "lr": 0.003, "grad": 0.1119, "tokens": 128083737600, "tok_s": 158352.4}
|
| 215 |
+
{"step": 122200, "epoch": 0.776, "loss": 1.79845, "ppl": 6.04, "lr": 0.003, "grad": 0.1046, "tokens": 128104704000, "tok_s": 157933.2}
|
| 216 |
+
{"step": 122220, "epoch": 0.777, "loss": 1.79177, "ppl": 6.0, "lr": 0.003, "grad": 0.1099, "tokens": 128125670400, "tok_s": 158111.6}
|
| 217 |
+
{"step": 122240, "epoch": 0.777, "loss": 1.76298, "ppl": 5.83, "lr": 0.003, "grad": 0.0647, "tokens": 128146636800, "tok_s": 158229.2}
|
| 218 |
+
{"step": 122260, "epoch": 0.777, "loss": 1.71945, "ppl": 5.581, "lr": 0.003, "grad": 0.0903, "tokens": 128167603200, "tok_s": 157972.3}
|
| 219 |
+
{"step": 122280, "epoch": 0.777, "loss": 1.80444, "ppl": 6.077, "lr": 0.003, "grad": 0.103, "tokens": 128188569600, "tok_s": 157454.9}
|
| 220 |
+
{"step": 122300, "epoch": 0.777, "loss": 1.77054, "ppl": 5.874, "lr": 0.003, "grad": 0.086, "tokens": 128209536000, "tok_s": 158072.6}
|
| 221 |
+
{"step": 122320, "epoch": 0.777, "loss": 1.71895, "ppl": 5.579, "lr": 0.003, "grad": 0.0765, "tokens": 128230502400, "tok_s": 158081.0}
|
| 222 |
+
{"step": 122340, "epoch": 0.777, "loss": 1.77757, "ppl": 5.915, "lr": 0.003, "grad": 0.1339, "tokens": 128251468800, "tok_s": 157832.8}
|
| 223 |
+
{"step": 122360, "epoch": 0.777, "loss": 1.71717, "ppl": 5.569, "lr": 0.003, "grad": 0.1013, "tokens": 128272435200, "tok_s": 157685.4}
|
| 224 |
+
{"step": 122380, "epoch": 0.778, "loss": 1.76442, "ppl": 5.838, "lr": 0.003, "grad": 0.0771, "tokens": 128293401600, "tok_s": 158150.6}
|
| 225 |
+
{"step": 122400, "epoch": 0.778, "loss": 1.64891, "ppl": 5.201, "lr": 0.003, "grad": 0.0808, "tokens": 128314368000, "tok_s": 157571.2}
|
| 226 |
+
{"step": 122420, "epoch": 0.778, "loss": 1.75866, "ppl": 5.805, "lr": 0.003, "grad": 0.157, "tokens": 128335334400, "tok_s": 158332.5}
|
| 227 |
+
{"step": 122440, "epoch": 0.778, "loss": 1.7548, "ppl": 5.782, "lr": 0.003, "grad": 0.1038, "tokens": 128356300800, "tok_s": 158554.4}
|
| 228 |
+
{"step": 122460, "epoch": 0.778, "loss": 1.76399, "ppl": 5.836, "lr": 0.003, "grad": 0.1136, "tokens": 128377267200, "tok_s": 157816.4}
|
| 229 |
+
{"step": 122480, "epoch": 0.778, "loss": 1.91616, "ppl": 6.795, "lr": 0.003, "grad": 0.1408, "tokens": 128398233600, "tok_s": 158231.4}
|
| 230 |
+
{"step": 122500, "epoch": 0.778, "loss": 1.79431, "ppl": 6.015, "lr": 0.003, "grad": 0.1307, "tokens": 128419200000, "tok_s": 158016.5}
|
| 231 |
+
{"step": 122520, "epoch": 0.778, "loss": 1.7456, "ppl": 5.729, "lr": 0.003, "grad": 0.1246, "tokens": 128440166400, "tok_s": 158363.6}
|
| 232 |
+
{"step": 122540, "epoch": 0.779, "loss": 1.73813, "ppl": 5.687, "lr": 0.003, "grad": 0.0839, "tokens": 128461132800, "tok_s": 158288.6}
|
| 233 |
+
{"step": 122560, "epoch": 0.779, "loss": 1.80894, "ppl": 6.104, "lr": 0.003, "grad": 0.1283, "tokens": 128482099200, "tok_s": 158399.1}
|
| 234 |
+
{"step": 122580, "epoch": 0.779, "loss": 1.72077, "ppl": 5.589, "lr": 0.003, "grad": 0.0826, "tokens": 128503065600, "tok_s": 158397.2}
|
| 235 |
+
{"step": 122600, "epoch": 0.779, "loss": 1.75342, "ppl": 5.774, "lr": 0.003, "grad": 0.0904, "tokens": 128524032000, "tok_s": 158227.7}
|
| 236 |
+
{"step": 122620, "epoch": 0.779, "loss": 1.76973, "ppl": 5.869, "lr": 0.003, "grad": 0.0808, "tokens": 128544998400, "tok_s": 157976.7}
|
| 237 |
+
{"step": 122640, "epoch": 0.779, "loss": 1.74021, "ppl": 5.699, "lr": 0.003, "grad": 0.115, "tokens": 128565964800, "tok_s": 158210.6}
|
| 238 |
+
{"step": 122660, "epoch": 0.779, "loss": 1.71522, "ppl": 5.558, "lr": 0.003, "grad": 0.1062, "tokens": 128586931200, "tok_s": 158581.8}
|
| 239 |
+
{"step": 122680, "epoch": 0.779, "loss": 1.79845, "ppl": 6.04, "lr": 0.003, "grad": 0.1597, "tokens": 128607897600, "tok_s": 157934.4}
|
| 240 |
+
{"step": 122700, "epoch": 0.78, "loss": 1.71125, "ppl": 5.536, "lr": 0.003, "grad": 0.0971, "tokens": 128628864000, "tok_s": 158153.5}
|
| 241 |
+
{"step": 122720, "epoch": 0.78, "loss": 1.73974, "ppl": 5.696, "lr": 0.003, "grad": 0.0943, "tokens": 128649830400, "tok_s": 157798.0}
|
| 242 |
+
{"step": 122740, "epoch": 0.78, "loss": 1.76501, "ppl": 5.842, "lr": 0.003, "grad": 0.122, "tokens": 128670796800, "tok_s": 158457.9}
|
| 243 |
+
{"step": 122760, "epoch": 0.78, "loss": 1.7808, "ppl": 5.935, "lr": 0.003, "grad": 0.1266, "tokens": 128691763200, "tok_s": 158448.3}
|
| 244 |
+
{"step": 122780, "epoch": 0.78, "loss": 1.73599, "ppl": 5.675, "lr": 0.003, "grad": 0.0729, "tokens": 128712729600, "tok_s": 158122.2}
|
| 245 |
+
{"step": 122800, "epoch": 0.78, "loss": 1.76972, "ppl": 5.869, "lr": 0.003, "grad": 0.0847, "tokens": 128733696000, "tok_s": 158080.2}
|
| 246 |
+
{"step": 122820, "epoch": 0.78, "loss": 1.70583, "ppl": 5.506, "lr": 0.003, "grad": 0.0816, "tokens": 128754662400, "tok_s": 158305.2}
|
| 247 |
+
{"step": 122840, "epoch": 0.78, "loss": 1.74879, "ppl": 5.748, "lr": 0.003, "grad": 0.0845, "tokens": 128775628800, "tok_s": 158235.1}
|
| 248 |
+
{"step": 122860, "epoch": 0.781, "loss": 1.75606, "ppl": 5.79, "lr": 0.003, "grad": 0.0902, "tokens": 128796595200, "tok_s": 158176.0}
|
| 249 |
+
{"step": 122880, "epoch": 0.781, "loss": 1.66715, "ppl": 5.297, "lr": 0.003, "grad": 0.072, "tokens": 128817561600, "tok_s": 158347.1}
|
| 250 |
+
{"step": 122900, "epoch": 0.781, "loss": 1.7539, "ppl": 5.777, "lr": 0.003, "grad": 0.0947, "tokens": 128838528000, "tok_s": 158158.2}
|
| 251 |
+
{"step": 122920, "epoch": 0.781, "loss": 1.73822, "ppl": 5.687, "lr": 0.003, "grad": 0.1199, "tokens": 128859494400, "tok_s": 158237.5}
|
| 252 |
+
{"step": 122940, "epoch": 0.781, "loss": 1.72693, "ppl": 5.623, "lr": 0.003, "grad": 0.1023, "tokens": 128880460800, "tok_s": 158301.6}
|
| 253 |
+
{"step": 122960, "epoch": 0.781, "loss": 1.69921, "ppl": 5.47, "lr": 0.003, "grad": 0.0918, "tokens": 128901427200, "tok_s": 158193.3}
|
| 254 |
+
{"step": 122980, "epoch": 0.781, "loss": 1.76548, "ppl": 5.844, "lr": 0.003, "grad": 0.0948, "tokens": 128922393600, "tok_s": 158000.5}
|
| 255 |
+
{"step": 123000, "epoch": 0.781, "loss": 1.78278, "ppl": 5.946, "lr": 0.003, "grad": 0.0983, "tokens": 128943360000, "tok_s": 158420.4}
|
| 256 |
+
{"step": 123000, "val_loss": 1.7528, "val_ppl": 5.771, "is_best": false}
|
logs/log_124000.jsonl
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 123000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T07:17:42.347663"}
|
| 2 |
+
{"step": 123020, "epoch": 0.782, "loss": 1.73857, "ppl": 5.689, "lr": 0.003, "grad": 0.0862, "tokens": 128964326400, "tok_s": 161031.7}
|
| 3 |
+
{"step": 123040, "epoch": 0.782, "loss": 1.74074, "ppl": 5.702, "lr": 0.003, "grad": 0.1368, "tokens": 128985292800, "tok_s": 160954.1}
|
| 4 |
+
{"step": 123060, "epoch": 0.782, "loss": 1.71462, "ppl": 5.555, "lr": 0.003, "grad": 0.1204, "tokens": 129006259200, "tok_s": 160878.0}
|
| 5 |
+
{"step": 123080, "epoch": 0.782, "loss": 1.61219, "ppl": 5.014, "lr": 0.003, "grad": 0.1082, "tokens": 129027225600, "tok_s": 160909.1}
|
| 6 |
+
{"step": 123100, "epoch": 0.782, "loss": 1.76628, "ppl": 5.849, "lr": 0.003, "grad": 0.1002, "tokens": 129048192000, "tok_s": 160834.8}
|
| 7 |
+
{"step": 123120, "epoch": 0.782, "loss": 1.72774, "ppl": 5.628, "lr": 0.003, "grad": 0.1067, "tokens": 129069158400, "tok_s": 160818.5}
|
| 8 |
+
{"step": 123140, "epoch": 0.782, "loss": 1.74211, "ppl": 5.709, "lr": 0.003, "grad": 0.0941, "tokens": 129090124800, "tok_s": 160918.4}
|
| 9 |
+
{"step": 123160, "epoch": 0.783, "loss": 1.67448, "ppl": 5.336, "lr": 0.003, "grad": 0.1091, "tokens": 129111091200, "tok_s": 160449.9}
|
| 10 |
+
{"step": 123180, "epoch": 0.783, "loss": 1.62741, "ppl": 5.091, "lr": 0.003, "grad": 0.0851, "tokens": 129132057600, "tok_s": 160590.1}
|
| 11 |
+
{"step": 123200, "epoch": 0.783, "loss": 1.59223, "ppl": 4.915, "lr": 0.003, "grad": 0.1177, "tokens": 129153024000, "tok_s": 161036.6}
|
| 12 |
+
{"step": 123220, "epoch": 0.783, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.084, "tokens": 129173990400, "tok_s": 160567.9}
|
| 13 |
+
{"step": 123240, "epoch": 0.783, "loss": 1.70141, "ppl": 5.482, "lr": 0.003, "grad": 0.0896, "tokens": 129194956800, "tok_s": 160638.0}
|
| 14 |
+
{"step": 123260, "epoch": 0.783, "loss": 1.76084, "ppl": 5.817, "lr": 0.003, "grad": 0.0738, "tokens": 129215923200, "tok_s": 160679.1}
|
| 15 |
+
{"step": 123280, "epoch": 0.783, "loss": 1.7102, "ppl": 5.53, "lr": 0.003, "grad": 0.0883, "tokens": 129236889600, "tok_s": 160692.9}
|
| 16 |
+
{"step": 123300, "epoch": 0.783, "loss": 1.75342, "ppl": 5.774, "lr": 0.003, "grad": 0.0895, "tokens": 129257856000, "tok_s": 160243.8}
|
| 17 |
+
{"step": 123320, "epoch": 0.784, "loss": 1.75981, "ppl": 5.811, "lr": 0.003, "grad": 0.0953, "tokens": 129278822400, "tok_s": 160626.9}
|
| 18 |
+
{"step": 123340, "epoch": 0.784, "loss": 1.72484, "ppl": 5.612, "lr": 0.003, "grad": 0.0835, "tokens": 129299788800, "tok_s": 160704.6}
|
| 19 |
+
{"step": 123360, "epoch": 0.784, "loss": 1.77109, "ppl": 5.877, "lr": 0.003, "grad": 0.0692, "tokens": 129320755200, "tok_s": 160342.8}
|
| 20 |
+
{"step": 123380, "epoch": 0.784, "loss": 1.68046, "ppl": 5.368, "lr": 0.003, "grad": 0.0858, "tokens": 129341721600, "tok_s": 160363.0}
|
| 21 |
+
{"step": 123400, "epoch": 0.784, "loss": 1.78102, "ppl": 5.936, "lr": 0.003, "grad": 0.1139, "tokens": 129362688000, "tok_s": 160007.1}
|
| 22 |
+
{"step": 123420, "epoch": 0.784, "loss": 1.75995, "ppl": 5.812, "lr": 0.003, "grad": 0.1308, "tokens": 129383654400, "tok_s": 160252.3}
|
| 23 |
+
{"step": 123440, "epoch": 0.784, "loss": 1.66969, "ppl": 5.311, "lr": 0.003, "grad": 0.0459, "tokens": 129404620800, "tok_s": 160442.8}
|
| 24 |
+
{"step": 123460, "epoch": 0.784, "loss": 1.81077, "ppl": 6.115, "lr": 0.003, "grad": 0.138, "tokens": 129425587200, "tok_s": 160788.9}
|
| 25 |
+
{"step": 123480, "epoch": 0.785, "loss": 1.80649, "ppl": 6.089, "lr": 0.003, "grad": 0.1163, "tokens": 129446553600, "tok_s": 160351.6}
|
| 26 |
+
{"step": 123500, "epoch": 0.785, "loss": 1.89406, "ppl": 6.646, "lr": 0.003, "grad": 0.0874, "tokens": 129467520000, "tok_s": 160608.9}
|
| 27 |
+
{"step": 123520, "epoch": 0.785, "loss": 1.76213, "ppl": 5.825, "lr": 0.003, "grad": 0.1057, "tokens": 129488486400, "tok_s": 160788.4}
|
| 28 |
+
{"step": 123540, "epoch": 0.785, "loss": 1.65779, "ppl": 5.248, "lr": 0.003, "grad": 0.0677, "tokens": 129509452800, "tok_s": 160517.6}
|
| 29 |
+
{"step": 123560, "epoch": 0.785, "loss": 1.67789, "ppl": 5.354, "lr": 0.003, "grad": 0.0999, "tokens": 129530419200, "tok_s": 160237.3}
|
| 30 |
+
{"step": 123580, "epoch": 0.785, "loss": 1.70206, "ppl": 5.485, "lr": 0.003, "grad": 0.1107, "tokens": 129551385600, "tok_s": 160724.2}
|
| 31 |
+
{"step": 123600, "epoch": 0.785, "loss": 1.63826, "ppl": 5.146, "lr": 0.003, "grad": 0.0701, "tokens": 129572352000, "tok_s": 160822.5}
|
| 32 |
+
{"step": 123620, "epoch": 0.785, "loss": 1.71302, "ppl": 5.546, "lr": 0.003, "grad": 0.085, "tokens": 129593318400, "tok_s": 160096.6}
|
| 33 |
+
{"step": 123640, "epoch": 0.786, "loss": 1.66073, "ppl": 5.263, "lr": 0.003, "grad": 0.1023, "tokens": 129614284800, "tok_s": 160631.5}
|
| 34 |
+
{"step": 123660, "epoch": 0.786, "loss": 1.8423, "ppl": 6.311, "lr": 0.003, "grad": 0.1501, "tokens": 129635251200, "tok_s": 160190.0}
|
| 35 |
+
{"step": 123680, "epoch": 0.786, "loss": 1.76954, "ppl": 5.868, "lr": 0.003, "grad": 0.133, "tokens": 129656217600, "tok_s": 160086.3}
|
| 36 |
+
{"step": 123700, "epoch": 0.786, "loss": 1.74116, "ppl": 5.704, "lr": 0.003, "grad": 0.1168, "tokens": 129677184000, "tok_s": 160085.2}
|
| 37 |
+
{"step": 123720, "epoch": 0.786, "loss": 1.66455, "ppl": 5.283, "lr": 0.003, "grad": 0.0707, "tokens": 129698150400, "tok_s": 160806.9}
|
| 38 |
+
{"step": 123740, "epoch": 0.786, "loss": 1.69718, "ppl": 5.459, "lr": 0.003, "grad": 0.0964, "tokens": 129719116800, "tok_s": 160812.3}
|
| 39 |
+
{"step": 123760, "epoch": 0.786, "loss": 1.76656, "ppl": 5.851, "lr": 0.003, "grad": 0.0841, "tokens": 129740083200, "tok_s": 161029.3}
|
| 40 |
+
{"step": 123780, "epoch": 0.786, "loss": 1.675, "ppl": 5.339, "lr": 0.003, "grad": 0.1033, "tokens": 129761049600, "tok_s": 159944.2}
|
| 41 |
+
{"step": 123800, "epoch": 0.787, "loss": 1.69161, "ppl": 5.428, "lr": 0.003, "grad": 0.0943, "tokens": 129782016000, "tok_s": 160887.6}
|
| 42 |
+
{"step": 123820, "epoch": 0.787, "loss": 1.74107, "ppl": 5.703, "lr": 0.003, "grad": 0.0992, "tokens": 129802982400, "tok_s": 160383.1}
|
| 43 |
+
{"step": 123840, "epoch": 0.787, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.0678, "tokens": 129823948800, "tok_s": 160859.1}
|
| 44 |
+
{"step": 123860, "epoch": 0.787, "loss": 1.75066, "ppl": 5.758, "lr": 0.003, "grad": 0.1289, "tokens": 129844915200, "tok_s": 160687.8}
|
| 45 |
+
{"step": 123880, "epoch": 0.787, "loss": 1.77861, "ppl": 5.922, "lr": 0.003, "grad": 0.1118, "tokens": 129865881600, "tok_s": 159777.7}
|
| 46 |
+
{"step": 123900, "epoch": 0.787, "loss": 1.44937, "ppl": 4.26, "lr": 0.003, "grad": 0.0972, "tokens": 129886848000, "tok_s": 160594.5}
|
| 47 |
+
{"step": 123920, "epoch": 0.787, "loss": 1.67828, "ppl": 5.356, "lr": 0.003, "grad": 0.1003, "tokens": 129907814400, "tok_s": 160390.4}
|
| 48 |
+
{"step": 123940, "epoch": 0.787, "loss": 1.6936, "ppl": 5.439, "lr": 0.003, "grad": 0.1095, "tokens": 129928780800, "tok_s": 160885.6}
|
| 49 |
+
{"step": 123960, "epoch": 0.788, "loss": 1.78226, "ppl": 5.943, "lr": 0.003, "grad": 0.1094, "tokens": 129949747200, "tok_s": 160422.9}
|
| 50 |
+
{"step": 123980, "epoch": 0.788, "loss": 1.73459, "ppl": 5.667, "lr": 0.003, "grad": 0.0688, "tokens": 129970713600, "tok_s": 160651.5}
|
| 51 |
+
{"step": 124000, "epoch": 0.788, "loss": 1.88859, "ppl": 6.61, "lr": 0.003, "grad": 0.1302, "tokens": 129991680000, "tok_s": 159622.6}
|
| 52 |
+
{"step": 124000, "val_loss": 1.73125, "val_ppl": 5.648, "is_best": true}
|
logs/log_125000.jsonl
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 123000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T07:17:42.347663"}
|
| 2 |
+
{"step": 123020, "epoch": 0.782, "loss": 1.73857, "ppl": 5.689, "lr": 0.003, "grad": 0.0862, "tokens": 128964326400, "tok_s": 161031.7}
|
| 3 |
+
{"step": 123040, "epoch": 0.782, "loss": 1.74074, "ppl": 5.702, "lr": 0.003, "grad": 0.1368, "tokens": 128985292800, "tok_s": 160954.1}
|
| 4 |
+
{"step": 123060, "epoch": 0.782, "loss": 1.71462, "ppl": 5.555, "lr": 0.003, "grad": 0.1204, "tokens": 129006259200, "tok_s": 160878.0}
|
| 5 |
+
{"step": 123080, "epoch": 0.782, "loss": 1.61219, "ppl": 5.014, "lr": 0.003, "grad": 0.1082, "tokens": 129027225600, "tok_s": 160909.1}
|
| 6 |
+
{"step": 123100, "epoch": 0.782, "loss": 1.76628, "ppl": 5.849, "lr": 0.003, "grad": 0.1002, "tokens": 129048192000, "tok_s": 160834.8}
|
| 7 |
+
{"step": 123120, "epoch": 0.782, "loss": 1.72774, "ppl": 5.628, "lr": 0.003, "grad": 0.1067, "tokens": 129069158400, "tok_s": 160818.5}
|
| 8 |
+
{"step": 123140, "epoch": 0.782, "loss": 1.74211, "ppl": 5.709, "lr": 0.003, "grad": 0.0941, "tokens": 129090124800, "tok_s": 160918.4}
|
| 9 |
+
{"step": 123160, "epoch": 0.783, "loss": 1.67448, "ppl": 5.336, "lr": 0.003, "grad": 0.1091, "tokens": 129111091200, "tok_s": 160449.9}
|
| 10 |
+
{"step": 123180, "epoch": 0.783, "loss": 1.62741, "ppl": 5.091, "lr": 0.003, "grad": 0.0851, "tokens": 129132057600, "tok_s": 160590.1}
|
| 11 |
+
{"step": 123200, "epoch": 0.783, "loss": 1.59223, "ppl": 4.915, "lr": 0.003, "grad": 0.1177, "tokens": 129153024000, "tok_s": 161036.6}
|
| 12 |
+
{"step": 123220, "epoch": 0.783, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.084, "tokens": 129173990400, "tok_s": 160567.9}
|
| 13 |
+
{"step": 123240, "epoch": 0.783, "loss": 1.70141, "ppl": 5.482, "lr": 0.003, "grad": 0.0896, "tokens": 129194956800, "tok_s": 160638.0}
|
| 14 |
+
{"step": 123260, "epoch": 0.783, "loss": 1.76084, "ppl": 5.817, "lr": 0.003, "grad": 0.0738, "tokens": 129215923200, "tok_s": 160679.1}
|
| 15 |
+
{"step": 123280, "epoch": 0.783, "loss": 1.7102, "ppl": 5.53, "lr": 0.003, "grad": 0.0883, "tokens": 129236889600, "tok_s": 160692.9}
|
| 16 |
+
{"step": 123300, "epoch": 0.783, "loss": 1.75342, "ppl": 5.774, "lr": 0.003, "grad": 0.0895, "tokens": 129257856000, "tok_s": 160243.8}
|
| 17 |
+
{"step": 123320, "epoch": 0.784, "loss": 1.75981, "ppl": 5.811, "lr": 0.003, "grad": 0.0953, "tokens": 129278822400, "tok_s": 160626.9}
|
| 18 |
+
{"step": 123340, "epoch": 0.784, "loss": 1.72484, "ppl": 5.612, "lr": 0.003, "grad": 0.0835, "tokens": 129299788800, "tok_s": 160704.6}
|
| 19 |
+
{"step": 123360, "epoch": 0.784, "loss": 1.77109, "ppl": 5.877, "lr": 0.003, "grad": 0.0692, "tokens": 129320755200, "tok_s": 160342.8}
|
| 20 |
+
{"step": 123380, "epoch": 0.784, "loss": 1.68046, "ppl": 5.368, "lr": 0.003, "grad": 0.0858, "tokens": 129341721600, "tok_s": 160363.0}
|
| 21 |
+
{"step": 123400, "epoch": 0.784, "loss": 1.78102, "ppl": 5.936, "lr": 0.003, "grad": 0.1139, "tokens": 129362688000, "tok_s": 160007.1}
|
| 22 |
+
{"step": 123420, "epoch": 0.784, "loss": 1.75995, "ppl": 5.812, "lr": 0.003, "grad": 0.1308, "tokens": 129383654400, "tok_s": 160252.3}
|
| 23 |
+
{"step": 123440, "epoch": 0.784, "loss": 1.66969, "ppl": 5.311, "lr": 0.003, "grad": 0.0459, "tokens": 129404620800, "tok_s": 160442.8}
|
| 24 |
+
{"step": 123460, "epoch": 0.784, "loss": 1.81077, "ppl": 6.115, "lr": 0.003, "grad": 0.138, "tokens": 129425587200, "tok_s": 160788.9}
|
| 25 |
+
{"step": 123480, "epoch": 0.785, "loss": 1.80649, "ppl": 6.089, "lr": 0.003, "grad": 0.1163, "tokens": 129446553600, "tok_s": 160351.6}
|
| 26 |
+
{"step": 123500, "epoch": 0.785, "loss": 1.89406, "ppl": 6.646, "lr": 0.003, "grad": 0.0874, "tokens": 129467520000, "tok_s": 160608.9}
|
| 27 |
+
{"step": 123520, "epoch": 0.785, "loss": 1.76213, "ppl": 5.825, "lr": 0.003, "grad": 0.1057, "tokens": 129488486400, "tok_s": 160788.4}
|
| 28 |
+
{"step": 123540, "epoch": 0.785, "loss": 1.65779, "ppl": 5.248, "lr": 0.003, "grad": 0.0677, "tokens": 129509452800, "tok_s": 160517.6}
|
| 29 |
+
{"step": 123560, "epoch": 0.785, "loss": 1.67789, "ppl": 5.354, "lr": 0.003, "grad": 0.0999, "tokens": 129530419200, "tok_s": 160237.3}
|
| 30 |
+
{"step": 123580, "epoch": 0.785, "loss": 1.70206, "ppl": 5.485, "lr": 0.003, "grad": 0.1107, "tokens": 129551385600, "tok_s": 160724.2}
|
| 31 |
+
{"step": 123600, "epoch": 0.785, "loss": 1.63826, "ppl": 5.146, "lr": 0.003, "grad": 0.0701, "tokens": 129572352000, "tok_s": 160822.5}
|
| 32 |
+
{"step": 123620, "epoch": 0.785, "loss": 1.71302, "ppl": 5.546, "lr": 0.003, "grad": 0.085, "tokens": 129593318400, "tok_s": 160096.6}
|
| 33 |
+
{"step": 123640, "epoch": 0.786, "loss": 1.66073, "ppl": 5.263, "lr": 0.003, "grad": 0.1023, "tokens": 129614284800, "tok_s": 160631.5}
|
| 34 |
+
{"step": 123660, "epoch": 0.786, "loss": 1.8423, "ppl": 6.311, "lr": 0.003, "grad": 0.1501, "tokens": 129635251200, "tok_s": 160190.0}
|
| 35 |
+
{"step": 123680, "epoch": 0.786, "loss": 1.76954, "ppl": 5.868, "lr": 0.003, "grad": 0.133, "tokens": 129656217600, "tok_s": 160086.3}
|
| 36 |
+
{"step": 123700, "epoch": 0.786, "loss": 1.74116, "ppl": 5.704, "lr": 0.003, "grad": 0.1168, "tokens": 129677184000, "tok_s": 160085.2}
|
| 37 |
+
{"step": 123720, "epoch": 0.786, "loss": 1.66455, "ppl": 5.283, "lr": 0.003, "grad": 0.0707, "tokens": 129698150400, "tok_s": 160806.9}
|
| 38 |
+
{"step": 123740, "epoch": 0.786, "loss": 1.69718, "ppl": 5.459, "lr": 0.003, "grad": 0.0964, "tokens": 129719116800, "tok_s": 160812.3}
|
| 39 |
+
{"step": 123760, "epoch": 0.786, "loss": 1.76656, "ppl": 5.851, "lr": 0.003, "grad": 0.0841, "tokens": 129740083200, "tok_s": 161029.3}
|
| 40 |
+
{"step": 123780, "epoch": 0.786, "loss": 1.675, "ppl": 5.339, "lr": 0.003, "grad": 0.1033, "tokens": 129761049600, "tok_s": 159944.2}
|
| 41 |
+
{"step": 123800, "epoch": 0.787, "loss": 1.69161, "ppl": 5.428, "lr": 0.003, "grad": 0.0943, "tokens": 129782016000, "tok_s": 160887.6}
|
| 42 |
+
{"step": 123820, "epoch": 0.787, "loss": 1.74107, "ppl": 5.703, "lr": 0.003, "grad": 0.0992, "tokens": 129802982400, "tok_s": 160383.1}
|
| 43 |
+
{"step": 123840, "epoch": 0.787, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.0678, "tokens": 129823948800, "tok_s": 160859.1}
|
| 44 |
+
{"step": 123860, "epoch": 0.787, "loss": 1.75066, "ppl": 5.758, "lr": 0.003, "grad": 0.1289, "tokens": 129844915200, "tok_s": 160687.8}
|
| 45 |
+
{"step": 123880, "epoch": 0.787, "loss": 1.77861, "ppl": 5.922, "lr": 0.003, "grad": 0.1118, "tokens": 129865881600, "tok_s": 159777.7}
|
| 46 |
+
{"step": 123900, "epoch": 0.787, "loss": 1.44937, "ppl": 4.26, "lr": 0.003, "grad": 0.0972, "tokens": 129886848000, "tok_s": 160594.5}
|
| 47 |
+
{"step": 123920, "epoch": 0.787, "loss": 1.67828, "ppl": 5.356, "lr": 0.003, "grad": 0.1003, "tokens": 129907814400, "tok_s": 160390.4}
|
| 48 |
+
{"step": 123940, "epoch": 0.787, "loss": 1.6936, "ppl": 5.439, "lr": 0.003, "grad": 0.1095, "tokens": 129928780800, "tok_s": 160885.6}
|
| 49 |
+
{"step": 123960, "epoch": 0.788, "loss": 1.78226, "ppl": 5.943, "lr": 0.003, "grad": 0.1094, "tokens": 129949747200, "tok_s": 160422.9}
|
| 50 |
+
{"step": 123980, "epoch": 0.788, "loss": 1.73459, "ppl": 5.667, "lr": 0.003, "grad": 0.0688, "tokens": 129970713600, "tok_s": 160651.5}
|
| 51 |
+
{"step": 124000, "epoch": 0.788, "loss": 1.88859, "ppl": 6.61, "lr": 0.003, "grad": 0.1302, "tokens": 129991680000, "tok_s": 159622.6}
|
| 52 |
+
{"step": 124000, "val_loss": 1.73125, "val_ppl": 5.648, "is_best": true}
|
| 53 |
+
{"step": 124020, "epoch": 0.788, "loss": 1.7361, "ppl": 5.675, "lr": 0.003, "grad": 0.1751, "tokens": 130012646400, "tok_s": 160215.9}
|
| 54 |
+
{"step": 124040, "epoch": 0.788, "loss": 1.67665, "ppl": 5.348, "lr": 0.003, "grad": 0.0744, "tokens": 130033612800, "tok_s": 160225.5}
|
| 55 |
+
{"step": 124060, "epoch": 0.788, "loss": 1.77362, "ppl": 5.892, "lr": 0.003, "grad": 0.0898, "tokens": 130054579200, "tok_s": 160331.3}
|
| 56 |
+
{"step": 124080, "epoch": 0.788, "loss": 1.72503, "ppl": 5.613, "lr": 0.003, "grad": 0.0922, "tokens": 130075545600, "tok_s": 159702.9}
|
| 57 |
+
{"step": 124100, "epoch": 0.788, "loss": 1.59609, "ppl": 4.934, "lr": 0.003, "grad": 0.0762, "tokens": 130096512000, "tok_s": 160685.8}
|
| 58 |
+
{"step": 124120, "epoch": 0.789, "loss": 1.86891, "ppl": 6.481, "lr": 0.003, "grad": 0.1202, "tokens": 130117478400, "tok_s": 160504.1}
|
| 59 |
+
{"step": 124140, "epoch": 0.789, "loss": 1.76403, "ppl": 5.836, "lr": 0.003, "grad": 0.0684, "tokens": 130138444800, "tok_s": 160268.2}
|
| 60 |
+
{"step": 124160, "epoch": 0.789, "loss": 1.74983, "ppl": 5.754, "lr": 0.003, "grad": 0.1502, "tokens": 130159411200, "tok_s": 160689.6}
|
| 61 |
+
{"step": 124180, "epoch": 0.789, "loss": 1.79266, "ppl": 6.005, "lr": 0.003, "grad": 0.1325, "tokens": 130180377600, "tok_s": 160749.9}
|
| 62 |
+
{"step": 124200, "epoch": 0.789, "loss": 1.70712, "ppl": 5.513, "lr": 0.003, "grad": 0.1652, "tokens": 130201344000, "tok_s": 160972.2}
|
| 63 |
+
{"step": 124220, "epoch": 0.789, "loss": 1.77982, "ppl": 5.929, "lr": 0.003, "grad": 0.0863, "tokens": 130222310400, "tok_s": 159848.7}
|
| 64 |
+
{"step": 124240, "epoch": 0.789, "loss": 1.6902, "ppl": 5.421, "lr": 0.003, "grad": 0.0906, "tokens": 130243276800, "tok_s": 160423.3}
|
| 65 |
+
{"step": 124260, "epoch": 0.79, "loss": 1.72005, "ppl": 5.585, "lr": 0.003, "grad": 0.1148, "tokens": 130264243200, "tok_s": 160008.5}
|
| 66 |
+
{"step": 124280, "epoch": 0.79, "loss": 1.60375, "ppl": 4.972, "lr": 0.003, "grad": 0.0759, "tokens": 130285209600, "tok_s": 160501.4}
|
| 67 |
+
{"step": 124300, "epoch": 0.79, "loss": 1.80209, "ppl": 6.062, "lr": 0.003, "grad": 0.1022, "tokens": 130306176000, "tok_s": 160572.2}
|
| 68 |
+
{"step": 124320, "epoch": 0.79, "loss": 1.74269, "ppl": 5.713, "lr": 0.003, "grad": 0.0813, "tokens": 130327142400, "tok_s": 160189.3}
|
| 69 |
+
{"step": 124340, "epoch": 0.79, "loss": 1.79512, "ppl": 6.02, "lr": 0.003, "grad": 0.1168, "tokens": 130348108800, "tok_s": 160868.6}
|
| 70 |
+
{"step": 124360, "epoch": 0.79, "loss": 1.73415, "ppl": 5.664, "lr": 0.003, "grad": 0.0753, "tokens": 130369075200, "tok_s": 160812.7}
|
| 71 |
+
{"step": 124380, "epoch": 0.79, "loss": 1.84343, "ppl": 6.318, "lr": 0.003, "grad": 0.0912, "tokens": 130390041600, "tok_s": 160527.0}
|
| 72 |
+
{"step": 124400, "epoch": 0.79, "loss": 1.81286, "ppl": 6.128, "lr": 0.003, "grad": 0.069, "tokens": 130411008000, "tok_s": 160789.7}
|
| 73 |
+
{"step": 124420, "epoch": 0.791, "loss": 1.79391, "ppl": 6.013, "lr": 0.003, "grad": 0.0965, "tokens": 130431974400, "tok_s": 160630.4}
|
| 74 |
+
{"step": 124440, "epoch": 0.791, "loss": 1.73427, "ppl": 5.665, "lr": 0.003, "grad": 0.095, "tokens": 130452940800, "tok_s": 160278.9}
|
| 75 |
+
{"step": 124460, "epoch": 0.791, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.1166, "tokens": 130473907200, "tok_s": 159362.5}
|
| 76 |
+
{"step": 124480, "epoch": 0.791, "loss": 1.82161, "ppl": 6.182, "lr": 0.003, "grad": 0.0951, "tokens": 130494873600, "tok_s": 160482.4}
|
| 77 |
+
{"step": 124500, "epoch": 0.791, "loss": 1.77899, "ppl": 5.924, "lr": 0.003, "grad": 0.0911, "tokens": 130515840000, "tok_s": 160632.9}
|
| 78 |
+
{"step": 124520, "epoch": 0.791, "loss": 1.78569, "ppl": 5.964, "lr": 0.003, "grad": 0.1077, "tokens": 130536806400, "tok_s": 160596.3}
|
| 79 |
+
{"step": 124540, "epoch": 0.791, "loss": 1.7094, "ppl": 5.526, "lr": 0.003, "grad": 0.0913, "tokens": 130557772800, "tok_s": 160800.8}
|
| 80 |
+
{"step": 124560, "epoch": 0.791, "loss": 1.79031, "ppl": 5.991, "lr": 0.003, "grad": 0.1412, "tokens": 130578739200, "tok_s": 160067.8}
|
| 81 |
+
{"step": 124580, "epoch": 0.792, "loss": 1.59144, "ppl": 4.911, "lr": 0.003, "grad": 0.0821, "tokens": 130599705600, "tok_s": 160693.3}
|
| 82 |
+
{"step": 124600, "epoch": 0.792, "loss": 1.76647, "ppl": 5.85, "lr": 0.003, "grad": 0.1521, "tokens": 130620672000, "tok_s": 160653.0}
|
| 83 |
+
{"step": 124620, "epoch": 0.792, "loss": 1.76625, "ppl": 5.849, "lr": 0.003, "grad": 0.089, "tokens": 130641638400, "tok_s": 159971.8}
|
| 84 |
+
{"step": 124640, "epoch": 0.792, "loss": 1.73058, "ppl": 5.644, "lr": 0.003, "grad": 0.1279, "tokens": 130662604800, "tok_s": 160512.9}
|
| 85 |
+
{"step": 124660, "epoch": 0.792, "loss": 1.78411, "ppl": 5.954, "lr": 0.003, "grad": 0.0948, "tokens": 130683571200, "tok_s": 160282.8}
|
| 86 |
+
{"step": 124680, "epoch": 0.792, "loss": 1.7574, "ppl": 5.797, "lr": 0.003, "grad": 0.0869, "tokens": 130704537600, "tok_s": 160624.5}
|
| 87 |
+
{"step": 124700, "epoch": 0.792, "loss": 1.72977, "ppl": 5.639, "lr": 0.003, "grad": 0.0889, "tokens": 130725504000, "tok_s": 160538.3}
|
| 88 |
+
{"step": 124720, "epoch": 0.792, "loss": 1.70746, "ppl": 5.515, "lr": 0.003, "grad": 0.0753, "tokens": 130746470400, "tok_s": 160834.9}
|
| 89 |
+
{"step": 124740, "epoch": 0.793, "loss": 1.74636, "ppl": 5.734, "lr": 0.003, "grad": 0.1024, "tokens": 130767436800, "tok_s": 160732.6}
|
| 90 |
+
{"step": 124760, "epoch": 0.793, "loss": 1.63906, "ppl": 5.15, "lr": 0.003, "grad": 0.0647, "tokens": 130788403200, "tok_s": 160648.6}
|
| 91 |
+
{"step": 124780, "epoch": 0.793, "loss": 1.71628, "ppl": 5.564, "lr": 0.003, "grad": 0.1116, "tokens": 130809369600, "tok_s": 160459.3}
|
| 92 |
+
{"step": 124800, "epoch": 0.793, "loss": 1.74014, "ppl": 5.698, "lr": 0.003, "grad": 0.0762, "tokens": 130830336000, "tok_s": 160779.2}
|
| 93 |
+
{"step": 124820, "epoch": 0.793, "loss": 1.76257, "ppl": 5.827, "lr": 0.003, "grad": 0.1096, "tokens": 130851302400, "tok_s": 160502.2}
|
| 94 |
+
{"step": 124840, "epoch": 0.793, "loss": 1.77835, "ppl": 5.92, "lr": 0.003, "grad": 0.1063, "tokens": 130872268800, "tok_s": 160316.6}
|
| 95 |
+
{"step": 124860, "epoch": 0.793, "loss": 1.78944, "ppl": 5.986, "lr": 0.003, "grad": 0.0601, "tokens": 130893235200, "tok_s": 160541.8}
|
| 96 |
+
{"step": 124880, "epoch": 0.793, "loss": 1.76928, "ppl": 5.867, "lr": 0.003, "grad": 0.1254, "tokens": 130914201600, "tok_s": 160654.0}
|
| 97 |
+
{"step": 124900, "epoch": 0.794, "loss": 1.75305, "ppl": 5.772, "lr": 0.003, "grad": 0.0925, "tokens": 130935168000, "tok_s": 160492.8}
|
| 98 |
+
{"step": 124920, "epoch": 0.794, "loss": 1.77743, "ppl": 5.915, "lr": 0.003, "grad": 0.1285, "tokens": 130956134400, "tok_s": 160781.2}
|
| 99 |
+
{"step": 124940, "epoch": 0.794, "loss": 1.72792, "ppl": 5.629, "lr": 0.003, "grad": 0.0794, "tokens": 130977100800, "tok_s": 160778.9}
|
| 100 |
+
{"step": 124960, "epoch": 0.794, "loss": 1.74981, "ppl": 5.753, "lr": 0.003, "grad": 0.1085, "tokens": 130998067200, "tok_s": 159891.1}
|
| 101 |
+
{"step": 124980, "epoch": 0.794, "loss": 1.79698, "ppl": 6.031, "lr": 0.003, "grad": 0.1132, "tokens": 131019033600, "tok_s": 160698.3}
|
| 102 |
+
{"step": 125000, "epoch": 0.794, "loss": 1.72512, "ppl": 5.613, "lr": 0.003, "grad": 0.0803, "tokens": 131040000000, "tok_s": 160280.6}
|
| 103 |
+
{"step": 125000, "val_loss": 1.74215, "val_ppl": 5.71, "is_best": false}
|
logs/log_126000.jsonl
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 123000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T07:17:42.347663"}
|
| 2 |
+
{"step": 123020, "epoch": 0.782, "loss": 1.73857, "ppl": 5.689, "lr": 0.003, "grad": 0.0862, "tokens": 128964326400, "tok_s": 161031.7}
|
| 3 |
+
{"step": 123040, "epoch": 0.782, "loss": 1.74074, "ppl": 5.702, "lr": 0.003, "grad": 0.1368, "tokens": 128985292800, "tok_s": 160954.1}
|
| 4 |
+
{"step": 123060, "epoch": 0.782, "loss": 1.71462, "ppl": 5.555, "lr": 0.003, "grad": 0.1204, "tokens": 129006259200, "tok_s": 160878.0}
|
| 5 |
+
{"step": 123080, "epoch": 0.782, "loss": 1.61219, "ppl": 5.014, "lr": 0.003, "grad": 0.1082, "tokens": 129027225600, "tok_s": 160909.1}
|
| 6 |
+
{"step": 123100, "epoch": 0.782, "loss": 1.76628, "ppl": 5.849, "lr": 0.003, "grad": 0.1002, "tokens": 129048192000, "tok_s": 160834.8}
|
| 7 |
+
{"step": 123120, "epoch": 0.782, "loss": 1.72774, "ppl": 5.628, "lr": 0.003, "grad": 0.1067, "tokens": 129069158400, "tok_s": 160818.5}
|
| 8 |
+
{"step": 123140, "epoch": 0.782, "loss": 1.74211, "ppl": 5.709, "lr": 0.003, "grad": 0.0941, "tokens": 129090124800, "tok_s": 160918.4}
|
| 9 |
+
{"step": 123160, "epoch": 0.783, "loss": 1.67448, "ppl": 5.336, "lr": 0.003, "grad": 0.1091, "tokens": 129111091200, "tok_s": 160449.9}
|
| 10 |
+
{"step": 123180, "epoch": 0.783, "loss": 1.62741, "ppl": 5.091, "lr": 0.003, "grad": 0.0851, "tokens": 129132057600, "tok_s": 160590.1}
|
| 11 |
+
{"step": 123200, "epoch": 0.783, "loss": 1.59223, "ppl": 4.915, "lr": 0.003, "grad": 0.1177, "tokens": 129153024000, "tok_s": 161036.6}
|
| 12 |
+
{"step": 123220, "epoch": 0.783, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.084, "tokens": 129173990400, "tok_s": 160567.9}
|
| 13 |
+
{"step": 123240, "epoch": 0.783, "loss": 1.70141, "ppl": 5.482, "lr": 0.003, "grad": 0.0896, "tokens": 129194956800, "tok_s": 160638.0}
|
| 14 |
+
{"step": 123260, "epoch": 0.783, "loss": 1.76084, "ppl": 5.817, "lr": 0.003, "grad": 0.0738, "tokens": 129215923200, "tok_s": 160679.1}
|
| 15 |
+
{"step": 123280, "epoch": 0.783, "loss": 1.7102, "ppl": 5.53, "lr": 0.003, "grad": 0.0883, "tokens": 129236889600, "tok_s": 160692.9}
|
| 16 |
+
{"step": 123300, "epoch": 0.783, "loss": 1.75342, "ppl": 5.774, "lr": 0.003, "grad": 0.0895, "tokens": 129257856000, "tok_s": 160243.8}
|
| 17 |
+
{"step": 123320, "epoch": 0.784, "loss": 1.75981, "ppl": 5.811, "lr": 0.003, "grad": 0.0953, "tokens": 129278822400, "tok_s": 160626.9}
|
| 18 |
+
{"step": 123340, "epoch": 0.784, "loss": 1.72484, "ppl": 5.612, "lr": 0.003, "grad": 0.0835, "tokens": 129299788800, "tok_s": 160704.6}
|
| 19 |
+
{"step": 123360, "epoch": 0.784, "loss": 1.77109, "ppl": 5.877, "lr": 0.003, "grad": 0.0692, "tokens": 129320755200, "tok_s": 160342.8}
|
| 20 |
+
{"step": 123380, "epoch": 0.784, "loss": 1.68046, "ppl": 5.368, "lr": 0.003, "grad": 0.0858, "tokens": 129341721600, "tok_s": 160363.0}
|
| 21 |
+
{"step": 123400, "epoch": 0.784, "loss": 1.78102, "ppl": 5.936, "lr": 0.003, "grad": 0.1139, "tokens": 129362688000, "tok_s": 160007.1}
|
| 22 |
+
{"step": 123420, "epoch": 0.784, "loss": 1.75995, "ppl": 5.812, "lr": 0.003, "grad": 0.1308, "tokens": 129383654400, "tok_s": 160252.3}
|
| 23 |
+
{"step": 123440, "epoch": 0.784, "loss": 1.66969, "ppl": 5.311, "lr": 0.003, "grad": 0.0459, "tokens": 129404620800, "tok_s": 160442.8}
|
| 24 |
+
{"step": 123460, "epoch": 0.784, "loss": 1.81077, "ppl": 6.115, "lr": 0.003, "grad": 0.138, "tokens": 129425587200, "tok_s": 160788.9}
|
| 25 |
+
{"step": 123480, "epoch": 0.785, "loss": 1.80649, "ppl": 6.089, "lr": 0.003, "grad": 0.1163, "tokens": 129446553600, "tok_s": 160351.6}
|
| 26 |
+
{"step": 123500, "epoch": 0.785, "loss": 1.89406, "ppl": 6.646, "lr": 0.003, "grad": 0.0874, "tokens": 129467520000, "tok_s": 160608.9}
|
| 27 |
+
{"step": 123520, "epoch": 0.785, "loss": 1.76213, "ppl": 5.825, "lr": 0.003, "grad": 0.1057, "tokens": 129488486400, "tok_s": 160788.4}
|
| 28 |
+
{"step": 123540, "epoch": 0.785, "loss": 1.65779, "ppl": 5.248, "lr": 0.003, "grad": 0.0677, "tokens": 129509452800, "tok_s": 160517.6}
|
| 29 |
+
{"step": 123560, "epoch": 0.785, "loss": 1.67789, "ppl": 5.354, "lr": 0.003, "grad": 0.0999, "tokens": 129530419200, "tok_s": 160237.3}
|
| 30 |
+
{"step": 123580, "epoch": 0.785, "loss": 1.70206, "ppl": 5.485, "lr": 0.003, "grad": 0.1107, "tokens": 129551385600, "tok_s": 160724.2}
|
| 31 |
+
{"step": 123600, "epoch": 0.785, "loss": 1.63826, "ppl": 5.146, "lr": 0.003, "grad": 0.0701, "tokens": 129572352000, "tok_s": 160822.5}
|
| 32 |
+
{"step": 123620, "epoch": 0.785, "loss": 1.71302, "ppl": 5.546, "lr": 0.003, "grad": 0.085, "tokens": 129593318400, "tok_s": 160096.6}
|
| 33 |
+
{"step": 123640, "epoch": 0.786, "loss": 1.66073, "ppl": 5.263, "lr": 0.003, "grad": 0.1023, "tokens": 129614284800, "tok_s": 160631.5}
|
| 34 |
+
{"step": 123660, "epoch": 0.786, "loss": 1.8423, "ppl": 6.311, "lr": 0.003, "grad": 0.1501, "tokens": 129635251200, "tok_s": 160190.0}
|
| 35 |
+
{"step": 123680, "epoch": 0.786, "loss": 1.76954, "ppl": 5.868, "lr": 0.003, "grad": 0.133, "tokens": 129656217600, "tok_s": 160086.3}
|
| 36 |
+
{"step": 123700, "epoch": 0.786, "loss": 1.74116, "ppl": 5.704, "lr": 0.003, "grad": 0.1168, "tokens": 129677184000, "tok_s": 160085.2}
|
| 37 |
+
{"step": 123720, "epoch": 0.786, "loss": 1.66455, "ppl": 5.283, "lr": 0.003, "grad": 0.0707, "tokens": 129698150400, "tok_s": 160806.9}
|
| 38 |
+
{"step": 123740, "epoch": 0.786, "loss": 1.69718, "ppl": 5.459, "lr": 0.003, "grad": 0.0964, "tokens": 129719116800, "tok_s": 160812.3}
|
| 39 |
+
{"step": 123760, "epoch": 0.786, "loss": 1.76656, "ppl": 5.851, "lr": 0.003, "grad": 0.0841, "tokens": 129740083200, "tok_s": 161029.3}
|
| 40 |
+
{"step": 123780, "epoch": 0.786, "loss": 1.675, "ppl": 5.339, "lr": 0.003, "grad": 0.1033, "tokens": 129761049600, "tok_s": 159944.2}
|
| 41 |
+
{"step": 123800, "epoch": 0.787, "loss": 1.69161, "ppl": 5.428, "lr": 0.003, "grad": 0.0943, "tokens": 129782016000, "tok_s": 160887.6}
|
| 42 |
+
{"step": 123820, "epoch": 0.787, "loss": 1.74107, "ppl": 5.703, "lr": 0.003, "grad": 0.0992, "tokens": 129802982400, "tok_s": 160383.1}
|
| 43 |
+
{"step": 123840, "epoch": 0.787, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.0678, "tokens": 129823948800, "tok_s": 160859.1}
|
| 44 |
+
{"step": 123860, "epoch": 0.787, "loss": 1.75066, "ppl": 5.758, "lr": 0.003, "grad": 0.1289, "tokens": 129844915200, "tok_s": 160687.8}
|
| 45 |
+
{"step": 123880, "epoch": 0.787, "loss": 1.77861, "ppl": 5.922, "lr": 0.003, "grad": 0.1118, "tokens": 129865881600, "tok_s": 159777.7}
|
| 46 |
+
{"step": 123900, "epoch": 0.787, "loss": 1.44937, "ppl": 4.26, "lr": 0.003, "grad": 0.0972, "tokens": 129886848000, "tok_s": 160594.5}
|
| 47 |
+
{"step": 123920, "epoch": 0.787, "loss": 1.67828, "ppl": 5.356, "lr": 0.003, "grad": 0.1003, "tokens": 129907814400, "tok_s": 160390.4}
|
| 48 |
+
{"step": 123940, "epoch": 0.787, "loss": 1.6936, "ppl": 5.439, "lr": 0.003, "grad": 0.1095, "tokens": 129928780800, "tok_s": 160885.6}
|
| 49 |
+
{"step": 123960, "epoch": 0.788, "loss": 1.78226, "ppl": 5.943, "lr": 0.003, "grad": 0.1094, "tokens": 129949747200, "tok_s": 160422.9}
|
| 50 |
+
{"step": 123980, "epoch": 0.788, "loss": 1.73459, "ppl": 5.667, "lr": 0.003, "grad": 0.0688, "tokens": 129970713600, "tok_s": 160651.5}
|
| 51 |
+
{"step": 124000, "epoch": 0.788, "loss": 1.88859, "ppl": 6.61, "lr": 0.003, "grad": 0.1302, "tokens": 129991680000, "tok_s": 159622.6}
|
| 52 |
+
{"step": 124000, "val_loss": 1.73125, "val_ppl": 5.648, "is_best": true}
|
| 53 |
+
{"step": 124020, "epoch": 0.788, "loss": 1.7361, "ppl": 5.675, "lr": 0.003, "grad": 0.1751, "tokens": 130012646400, "tok_s": 160215.9}
|
| 54 |
+
{"step": 124040, "epoch": 0.788, "loss": 1.67665, "ppl": 5.348, "lr": 0.003, "grad": 0.0744, "tokens": 130033612800, "tok_s": 160225.5}
|
| 55 |
+
{"step": 124060, "epoch": 0.788, "loss": 1.77362, "ppl": 5.892, "lr": 0.003, "grad": 0.0898, "tokens": 130054579200, "tok_s": 160331.3}
|
| 56 |
+
{"step": 124080, "epoch": 0.788, "loss": 1.72503, "ppl": 5.613, "lr": 0.003, "grad": 0.0922, "tokens": 130075545600, "tok_s": 159702.9}
|
| 57 |
+
{"step": 124100, "epoch": 0.788, "loss": 1.59609, "ppl": 4.934, "lr": 0.003, "grad": 0.0762, "tokens": 130096512000, "tok_s": 160685.8}
|
| 58 |
+
{"step": 124120, "epoch": 0.789, "loss": 1.86891, "ppl": 6.481, "lr": 0.003, "grad": 0.1202, "tokens": 130117478400, "tok_s": 160504.1}
|
| 59 |
+
{"step": 124140, "epoch": 0.789, "loss": 1.76403, "ppl": 5.836, "lr": 0.003, "grad": 0.0684, "tokens": 130138444800, "tok_s": 160268.2}
|
| 60 |
+
{"step": 124160, "epoch": 0.789, "loss": 1.74983, "ppl": 5.754, "lr": 0.003, "grad": 0.1502, "tokens": 130159411200, "tok_s": 160689.6}
|
| 61 |
+
{"step": 124180, "epoch": 0.789, "loss": 1.79266, "ppl": 6.005, "lr": 0.003, "grad": 0.1325, "tokens": 130180377600, "tok_s": 160749.9}
|
| 62 |
+
{"step": 124200, "epoch": 0.789, "loss": 1.70712, "ppl": 5.513, "lr": 0.003, "grad": 0.1652, "tokens": 130201344000, "tok_s": 160972.2}
|
| 63 |
+
{"step": 124220, "epoch": 0.789, "loss": 1.77982, "ppl": 5.929, "lr": 0.003, "grad": 0.0863, "tokens": 130222310400, "tok_s": 159848.7}
|
| 64 |
+
{"step": 124240, "epoch": 0.789, "loss": 1.6902, "ppl": 5.421, "lr": 0.003, "grad": 0.0906, "tokens": 130243276800, "tok_s": 160423.3}
|
| 65 |
+
{"step": 124260, "epoch": 0.79, "loss": 1.72005, "ppl": 5.585, "lr": 0.003, "grad": 0.1148, "tokens": 130264243200, "tok_s": 160008.5}
|
| 66 |
+
{"step": 124280, "epoch": 0.79, "loss": 1.60375, "ppl": 4.972, "lr": 0.003, "grad": 0.0759, "tokens": 130285209600, "tok_s": 160501.4}
|
| 67 |
+
{"step": 124300, "epoch": 0.79, "loss": 1.80209, "ppl": 6.062, "lr": 0.003, "grad": 0.1022, "tokens": 130306176000, "tok_s": 160572.2}
|
| 68 |
+
{"step": 124320, "epoch": 0.79, "loss": 1.74269, "ppl": 5.713, "lr": 0.003, "grad": 0.0813, "tokens": 130327142400, "tok_s": 160189.3}
|
| 69 |
+
{"step": 124340, "epoch": 0.79, "loss": 1.79512, "ppl": 6.02, "lr": 0.003, "grad": 0.1168, "tokens": 130348108800, "tok_s": 160868.6}
|
| 70 |
+
{"step": 124360, "epoch": 0.79, "loss": 1.73415, "ppl": 5.664, "lr": 0.003, "grad": 0.0753, "tokens": 130369075200, "tok_s": 160812.7}
|
| 71 |
+
{"step": 124380, "epoch": 0.79, "loss": 1.84343, "ppl": 6.318, "lr": 0.003, "grad": 0.0912, "tokens": 130390041600, "tok_s": 160527.0}
|
| 72 |
+
{"step": 124400, "epoch": 0.79, "loss": 1.81286, "ppl": 6.128, "lr": 0.003, "grad": 0.069, "tokens": 130411008000, "tok_s": 160789.7}
|
| 73 |
+
{"step": 124420, "epoch": 0.791, "loss": 1.79391, "ppl": 6.013, "lr": 0.003, "grad": 0.0965, "tokens": 130431974400, "tok_s": 160630.4}
|
| 74 |
+
{"step": 124440, "epoch": 0.791, "loss": 1.73427, "ppl": 5.665, "lr": 0.003, "grad": 0.095, "tokens": 130452940800, "tok_s": 160278.9}
|
| 75 |
+
{"step": 124460, "epoch": 0.791, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.1166, "tokens": 130473907200, "tok_s": 159362.5}
|
| 76 |
+
{"step": 124480, "epoch": 0.791, "loss": 1.82161, "ppl": 6.182, "lr": 0.003, "grad": 0.0951, "tokens": 130494873600, "tok_s": 160482.4}
|
| 77 |
+
{"step": 124500, "epoch": 0.791, "loss": 1.77899, "ppl": 5.924, "lr": 0.003, "grad": 0.0911, "tokens": 130515840000, "tok_s": 160632.9}
|
| 78 |
+
{"step": 124520, "epoch": 0.791, "loss": 1.78569, "ppl": 5.964, "lr": 0.003, "grad": 0.1077, "tokens": 130536806400, "tok_s": 160596.3}
|
| 79 |
+
{"step": 124540, "epoch": 0.791, "loss": 1.7094, "ppl": 5.526, "lr": 0.003, "grad": 0.0913, "tokens": 130557772800, "tok_s": 160800.8}
|
| 80 |
+
{"step": 124560, "epoch": 0.791, "loss": 1.79031, "ppl": 5.991, "lr": 0.003, "grad": 0.1412, "tokens": 130578739200, "tok_s": 160067.8}
|
| 81 |
+
{"step": 124580, "epoch": 0.792, "loss": 1.59144, "ppl": 4.911, "lr": 0.003, "grad": 0.0821, "tokens": 130599705600, "tok_s": 160693.3}
|
| 82 |
+
{"step": 124600, "epoch": 0.792, "loss": 1.76647, "ppl": 5.85, "lr": 0.003, "grad": 0.1521, "tokens": 130620672000, "tok_s": 160653.0}
|
| 83 |
+
{"step": 124620, "epoch": 0.792, "loss": 1.76625, "ppl": 5.849, "lr": 0.003, "grad": 0.089, "tokens": 130641638400, "tok_s": 159971.8}
|
| 84 |
+
{"step": 124640, "epoch": 0.792, "loss": 1.73058, "ppl": 5.644, "lr": 0.003, "grad": 0.1279, "tokens": 130662604800, "tok_s": 160512.9}
|
| 85 |
+
{"step": 124660, "epoch": 0.792, "loss": 1.78411, "ppl": 5.954, "lr": 0.003, "grad": 0.0948, "tokens": 130683571200, "tok_s": 160282.8}
|
| 86 |
+
{"step": 124680, "epoch": 0.792, "loss": 1.7574, "ppl": 5.797, "lr": 0.003, "grad": 0.0869, "tokens": 130704537600, "tok_s": 160624.5}
|
| 87 |
+
{"step": 124700, "epoch": 0.792, "loss": 1.72977, "ppl": 5.639, "lr": 0.003, "grad": 0.0889, "tokens": 130725504000, "tok_s": 160538.3}
|
| 88 |
+
{"step": 124720, "epoch": 0.792, "loss": 1.70746, "ppl": 5.515, "lr": 0.003, "grad": 0.0753, "tokens": 130746470400, "tok_s": 160834.9}
|
| 89 |
+
{"step": 124740, "epoch": 0.793, "loss": 1.74636, "ppl": 5.734, "lr": 0.003, "grad": 0.1024, "tokens": 130767436800, "tok_s": 160732.6}
|
| 90 |
+
{"step": 124760, "epoch": 0.793, "loss": 1.63906, "ppl": 5.15, "lr": 0.003, "grad": 0.0647, "tokens": 130788403200, "tok_s": 160648.6}
|
| 91 |
+
{"step": 124780, "epoch": 0.793, "loss": 1.71628, "ppl": 5.564, "lr": 0.003, "grad": 0.1116, "tokens": 130809369600, "tok_s": 160459.3}
|
| 92 |
+
{"step": 124800, "epoch": 0.793, "loss": 1.74014, "ppl": 5.698, "lr": 0.003, "grad": 0.0762, "tokens": 130830336000, "tok_s": 160779.2}
|
| 93 |
+
{"step": 124820, "epoch": 0.793, "loss": 1.76257, "ppl": 5.827, "lr": 0.003, "grad": 0.1096, "tokens": 130851302400, "tok_s": 160502.2}
|
| 94 |
+
{"step": 124840, "epoch": 0.793, "loss": 1.77835, "ppl": 5.92, "lr": 0.003, "grad": 0.1063, "tokens": 130872268800, "tok_s": 160316.6}
|
| 95 |
+
{"step": 124860, "epoch": 0.793, "loss": 1.78944, "ppl": 5.986, "lr": 0.003, "grad": 0.0601, "tokens": 130893235200, "tok_s": 160541.8}
|
| 96 |
+
{"step": 124880, "epoch": 0.793, "loss": 1.76928, "ppl": 5.867, "lr": 0.003, "grad": 0.1254, "tokens": 130914201600, "tok_s": 160654.0}
|
| 97 |
+
{"step": 124900, "epoch": 0.794, "loss": 1.75305, "ppl": 5.772, "lr": 0.003, "grad": 0.0925, "tokens": 130935168000, "tok_s": 160492.8}
|
| 98 |
+
{"step": 124920, "epoch": 0.794, "loss": 1.77743, "ppl": 5.915, "lr": 0.003, "grad": 0.1285, "tokens": 130956134400, "tok_s": 160781.2}
|
| 99 |
+
{"step": 124940, "epoch": 0.794, "loss": 1.72792, "ppl": 5.629, "lr": 0.003, "grad": 0.0794, "tokens": 130977100800, "tok_s": 160778.9}
|
| 100 |
+
{"step": 124960, "epoch": 0.794, "loss": 1.74981, "ppl": 5.753, "lr": 0.003, "grad": 0.1085, "tokens": 130998067200, "tok_s": 159891.1}
|
| 101 |
+
{"step": 124980, "epoch": 0.794, "loss": 1.79698, "ppl": 6.031, "lr": 0.003, "grad": 0.1132, "tokens": 131019033600, "tok_s": 160698.3}
|
| 102 |
+
{"step": 125000, "epoch": 0.794, "loss": 1.72512, "ppl": 5.613, "lr": 0.003, "grad": 0.0803, "tokens": 131040000000, "tok_s": 160280.6}
|
| 103 |
+
{"step": 125000, "val_loss": 1.74215, "val_ppl": 5.71, "is_best": false}
|
| 104 |
+
{"step": 125020, "epoch": 0.794, "loss": 1.76033, "ppl": 5.814, "lr": 0.003, "grad": 0.1208, "tokens": 131060966400, "tok_s": 160517.3}
|
| 105 |
+
{"step": 125040, "epoch": 0.794, "loss": 1.74821, "ppl": 5.744, "lr": 0.003, "grad": 0.1219, "tokens": 131081932800, "tok_s": 160743.6}
|
| 106 |
+
{"step": 125060, "epoch": 0.795, "loss": 1.69473, "ppl": 5.445, "lr": 0.003, "grad": 0.0884, "tokens": 131102899200, "tok_s": 160707.3}
|
| 107 |
+
{"step": 125080, "epoch": 0.795, "loss": 1.76494, "ppl": 5.841, "lr": 0.003, "grad": 0.1146, "tokens": 131123865600, "tok_s": 160535.1}
|
| 108 |
+
{"step": 125100, "epoch": 0.795, "loss": 1.7554, "ppl": 5.786, "lr": 0.003, "grad": 0.1027, "tokens": 131144832000, "tok_s": 160837.8}
|
| 109 |
+
{"step": 125120, "epoch": 0.795, "loss": 1.82843, "ppl": 6.224, "lr": 0.003, "grad": 0.0815, "tokens": 131165798400, "tok_s": 159815.0}
|
| 110 |
+
{"step": 125140, "epoch": 0.795, "loss": 1.76921, "ppl": 5.866, "lr": 0.003, "grad": 0.1131, "tokens": 131186764800, "tok_s": 160652.4}
|
| 111 |
+
{"step": 125160, "epoch": 0.795, "loss": 1.72331, "ppl": 5.603, "lr": 0.003, "grad": 0.1504, "tokens": 131207731200, "tok_s": 160288.6}
|
| 112 |
+
{"step": 125180, "epoch": 0.795, "loss": 1.74794, "ppl": 5.743, "lr": 0.003, "grad": 0.0825, "tokens": 131228697600, "tok_s": 160590.8}
|
| 113 |
+
{"step": 125200, "epoch": 0.795, "loss": 1.80309, "ppl": 6.068, "lr": 0.003, "grad": 0.1297, "tokens": 131249664000, "tok_s": 160013.0}
|
| 114 |
+
{"step": 125220, "epoch": 0.796, "loss": 1.70651, "ppl": 5.51, "lr": 0.003, "grad": 0.074, "tokens": 131270630400, "tok_s": 160896.4}
|
| 115 |
+
{"step": 125240, "epoch": 0.796, "loss": 1.75076, "ppl": 5.759, "lr": 0.003, "grad": 0.1105, "tokens": 131291596800, "tok_s": 160396.9}
|
| 116 |
+
{"step": 125260, "epoch": 0.796, "loss": 1.66345, "ppl": 5.277, "lr": 0.003, "grad": 0.087, "tokens": 131312563200, "tok_s": 160563.1}
|
| 117 |
+
{"step": 125280, "epoch": 0.796, "loss": 1.76143, "ppl": 5.821, "lr": 0.003, "grad": 0.0767, "tokens": 131333529600, "tok_s": 160747.0}
|
| 118 |
+
{"step": 125300, "epoch": 0.796, "loss": 1.78602, "ppl": 5.966, "lr": 0.003, "grad": 0.0902, "tokens": 131354496000, "tok_s": 160934.3}
|
| 119 |
+
{"step": 125320, "epoch": 0.796, "loss": 1.66687, "ppl": 5.296, "lr": 0.003, "grad": 0.0875, "tokens": 131375462400, "tok_s": 159971.8}
|
| 120 |
+
{"step": 125340, "epoch": 0.796, "loss": 1.63117, "ppl": 5.11, "lr": 0.003, "grad": 0.1239, "tokens": 131396428800, "tok_s": 160658.5}
|
| 121 |
+
{"step": 125360, "epoch": 0.796, "loss": 1.75845, "ppl": 5.803, "lr": 0.003, "grad": 0.1208, "tokens": 131417395200, "tok_s": 160151.0}
|
| 122 |
+
{"step": 125380, "epoch": 0.797, "loss": 1.73367, "ppl": 5.661, "lr": 0.003, "grad": 0.0954, "tokens": 131438361600, "tok_s": 160160.2}
|
| 123 |
+
{"step": 125400, "epoch": 0.797, "loss": 1.64819, "ppl": 5.198, "lr": 0.003, "grad": 0.0774, "tokens": 131459328000, "tok_s": 160193.9}
|
| 124 |
+
{"step": 125420, "epoch": 0.797, "loss": 1.66598, "ppl": 5.291, "lr": 0.003, "grad": 0.0986, "tokens": 131480294400, "tok_s": 160053.9}
|
| 125 |
+
{"step": 125440, "epoch": 0.797, "loss": 1.8541, "ppl": 6.386, "lr": 0.003, "grad": 0.1272, "tokens": 131501260800, "tok_s": 160350.0}
|
| 126 |
+
{"step": 125460, "epoch": 0.797, "loss": 1.64714, "ppl": 5.192, "lr": 0.003, "grad": 0.0725, "tokens": 131522227200, "tok_s": 160129.8}
|
| 127 |
+
{"step": 125480, "epoch": 0.797, "loss": 1.7242, "ppl": 5.608, "lr": 0.003, "grad": 0.0687, "tokens": 131543193600, "tok_s": 160611.9}
|
| 128 |
+
{"step": 125500, "epoch": 0.797, "loss": 1.6994, "ppl": 5.471, "lr": 0.003, "grad": 0.1098, "tokens": 131564160000, "tok_s": 160332.7}
|
| 129 |
+
{"step": 125520, "epoch": 0.798, "loss": 1.71202, "ppl": 5.54, "lr": 0.003, "grad": 0.0632, "tokens": 131585126400, "tok_s": 160815.6}
|
| 130 |
+
{"step": 125540, "epoch": 0.798, "loss": 1.71523, "ppl": 5.558, "lr": 0.003, "grad": 0.0566, "tokens": 131606092800, "tok_s": 160783.7}
|
| 131 |
+
{"step": 125560, "epoch": 0.798, "loss": 1.81274, "ppl": 6.127, "lr": 0.003, "grad": 0.1067, "tokens": 131627059200, "tok_s": 160811.5}
|
| 132 |
+
{"step": 125580, "epoch": 0.798, "loss": 1.74317, "ppl": 5.715, "lr": 0.003, "grad": 0.1306, "tokens": 131648025600, "tok_s": 160707.5}
|
| 133 |
+
{"step": 125600, "epoch": 0.798, "loss": 1.77451, "ppl": 5.897, "lr": 0.003, "grad": 0.0825, "tokens": 131668992000, "tok_s": 160758.1}
|
| 134 |
+
{"step": 125620, "epoch": 0.798, "loss": 1.73877, "ppl": 5.69, "lr": 0.003, "grad": 0.082, "tokens": 131689958400, "tok_s": 160627.5}
|
| 135 |
+
{"step": 125640, "epoch": 0.798, "loss": 1.77622, "ppl": 5.907, "lr": 0.003, "grad": 0.1201, "tokens": 131710924800, "tok_s": 160920.4}
|
| 136 |
+
{"step": 125660, "epoch": 0.798, "loss": 1.64526, "ppl": 5.182, "lr": 0.003, "grad": 0.1084, "tokens": 131731891200, "tok_s": 160624.3}
|
| 137 |
+
{"step": 125680, "epoch": 0.799, "loss": 1.73881, "ppl": 5.691, "lr": 0.003, "grad": 0.1094, "tokens": 131752857600, "tok_s": 160666.0}
|
| 138 |
+
{"step": 125700, "epoch": 0.799, "loss": 1.69768, "ppl": 5.461, "lr": 0.003, "grad": 0.1167, "tokens": 131773824000, "tok_s": 160761.8}
|
| 139 |
+
{"step": 125720, "epoch": 0.799, "loss": 1.78497, "ppl": 5.959, "lr": 0.003, "grad": 0.1092, "tokens": 131794790400, "tok_s": 160875.4}
|
| 140 |
+
{"step": 125740, "epoch": 0.799, "loss": 1.60774, "ppl": 4.992, "lr": 0.003, "grad": 0.092, "tokens": 131815756800, "tok_s": 160801.6}
|
| 141 |
+
{"step": 125760, "epoch": 0.799, "loss": 1.77716, "ppl": 5.913, "lr": 0.003, "grad": 0.0894, "tokens": 131836723200, "tok_s": 160699.4}
|
| 142 |
+
{"step": 125780, "epoch": 0.799, "loss": 1.78281, "ppl": 5.947, "lr": 0.003, "grad": 0.1028, "tokens": 131857689600, "tok_s": 160806.4}
|
| 143 |
+
{"step": 125800, "epoch": 0.799, "loss": 1.75767, "ppl": 5.799, "lr": 0.003, "grad": 0.0783, "tokens": 131878656000, "tok_s": 160736.4}
|
| 144 |
+
{"step": 125820, "epoch": 0.799, "loss": 1.77649, "ppl": 5.909, "lr": 0.003, "grad": 0.0951, "tokens": 131899622400, "tok_s": 160778.6}
|
| 145 |
+
{"step": 125840, "epoch": 0.8, "loss": 1.77938, "ppl": 5.926, "lr": 0.003, "grad": 0.1144, "tokens": 131920588800, "tok_s": 160968.2}
|
| 146 |
+
{"step": 125860, "epoch": 0.8, "loss": 1.80196, "ppl": 6.062, "lr": 0.003, "grad": 0.1349, "tokens": 131941555200, "tok_s": 160726.0}
|
| 147 |
+
{"step": 125880, "epoch": 0.8, "loss": 1.71563, "ppl": 5.56, "lr": 0.003, "grad": 0.095, "tokens": 131962521600, "tok_s": 160731.7}
|
| 148 |
+
{"step": 125900, "epoch": 0.8, "loss": 1.76961, "ppl": 5.869, "lr": 0.003, "grad": 0.1057, "tokens": 131983488000, "tok_s": 160875.8}
|
| 149 |
+
{"step": 125920, "epoch": 0.8, "loss": 1.76717, "ppl": 5.854, "lr": 0.003, "grad": 0.0702, "tokens": 132004454400, "tok_s": 160778.1}
|
| 150 |
+
{"step": 125940, "epoch": 0.8, "loss": 1.73329, "ppl": 5.659, "lr": 0.003, "grad": 0.1034, "tokens": 132025420800, "tok_s": 160384.4}
|
| 151 |
+
{"step": 125960, "epoch": 0.8, "loss": 1.78953, "ppl": 5.987, "lr": 0.003, "grad": 0.082, "tokens": 132046387200, "tok_s": 160727.7}
|
| 152 |
+
{"step": 125980, "epoch": 0.8, "loss": 1.76174, "ppl": 5.823, "lr": 0.003, "grad": 0.1295, "tokens": 132067353600, "tok_s": 160876.9}
|
| 153 |
+
{"step": 126000, "epoch": 0.801, "loss": 1.76653, "ppl": 5.85, "lr": 0.003, "grad": 0.1551, "tokens": 132088320000, "tok_s": 160715.0}
|
| 154 |
+
{"step": 126000, "val_loss": 1.74991, "val_ppl": 5.754, "is_best": false}
|
logs/log_127000.jsonl
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 123000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T07:17:42.347663"}
|
| 2 |
+
{"step": 123020, "epoch": 0.782, "loss": 1.73857, "ppl": 5.689, "lr": 0.003, "grad": 0.0862, "tokens": 128964326400, "tok_s": 161031.7}
|
| 3 |
+
{"step": 123040, "epoch": 0.782, "loss": 1.74074, "ppl": 5.702, "lr": 0.003, "grad": 0.1368, "tokens": 128985292800, "tok_s": 160954.1}
|
| 4 |
+
{"step": 123060, "epoch": 0.782, "loss": 1.71462, "ppl": 5.555, "lr": 0.003, "grad": 0.1204, "tokens": 129006259200, "tok_s": 160878.0}
|
| 5 |
+
{"step": 123080, "epoch": 0.782, "loss": 1.61219, "ppl": 5.014, "lr": 0.003, "grad": 0.1082, "tokens": 129027225600, "tok_s": 160909.1}
|
| 6 |
+
{"step": 123100, "epoch": 0.782, "loss": 1.76628, "ppl": 5.849, "lr": 0.003, "grad": 0.1002, "tokens": 129048192000, "tok_s": 160834.8}
|
| 7 |
+
{"step": 123120, "epoch": 0.782, "loss": 1.72774, "ppl": 5.628, "lr": 0.003, "grad": 0.1067, "tokens": 129069158400, "tok_s": 160818.5}
|
| 8 |
+
{"step": 123140, "epoch": 0.782, "loss": 1.74211, "ppl": 5.709, "lr": 0.003, "grad": 0.0941, "tokens": 129090124800, "tok_s": 160918.4}
|
| 9 |
+
{"step": 123160, "epoch": 0.783, "loss": 1.67448, "ppl": 5.336, "lr": 0.003, "grad": 0.1091, "tokens": 129111091200, "tok_s": 160449.9}
|
| 10 |
+
{"step": 123180, "epoch": 0.783, "loss": 1.62741, "ppl": 5.091, "lr": 0.003, "grad": 0.0851, "tokens": 129132057600, "tok_s": 160590.1}
|
| 11 |
+
{"step": 123200, "epoch": 0.783, "loss": 1.59223, "ppl": 4.915, "lr": 0.003, "grad": 0.1177, "tokens": 129153024000, "tok_s": 161036.6}
|
| 12 |
+
{"step": 123220, "epoch": 0.783, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.084, "tokens": 129173990400, "tok_s": 160567.9}
|
| 13 |
+
{"step": 123240, "epoch": 0.783, "loss": 1.70141, "ppl": 5.482, "lr": 0.003, "grad": 0.0896, "tokens": 129194956800, "tok_s": 160638.0}
|
| 14 |
+
{"step": 123260, "epoch": 0.783, "loss": 1.76084, "ppl": 5.817, "lr": 0.003, "grad": 0.0738, "tokens": 129215923200, "tok_s": 160679.1}
|
| 15 |
+
{"step": 123280, "epoch": 0.783, "loss": 1.7102, "ppl": 5.53, "lr": 0.003, "grad": 0.0883, "tokens": 129236889600, "tok_s": 160692.9}
|
| 16 |
+
{"step": 123300, "epoch": 0.783, "loss": 1.75342, "ppl": 5.774, "lr": 0.003, "grad": 0.0895, "tokens": 129257856000, "tok_s": 160243.8}
|
| 17 |
+
{"step": 123320, "epoch": 0.784, "loss": 1.75981, "ppl": 5.811, "lr": 0.003, "grad": 0.0953, "tokens": 129278822400, "tok_s": 160626.9}
|
| 18 |
+
{"step": 123340, "epoch": 0.784, "loss": 1.72484, "ppl": 5.612, "lr": 0.003, "grad": 0.0835, "tokens": 129299788800, "tok_s": 160704.6}
|
| 19 |
+
{"step": 123360, "epoch": 0.784, "loss": 1.77109, "ppl": 5.877, "lr": 0.003, "grad": 0.0692, "tokens": 129320755200, "tok_s": 160342.8}
|
| 20 |
+
{"step": 123380, "epoch": 0.784, "loss": 1.68046, "ppl": 5.368, "lr": 0.003, "grad": 0.0858, "tokens": 129341721600, "tok_s": 160363.0}
|
| 21 |
+
{"step": 123400, "epoch": 0.784, "loss": 1.78102, "ppl": 5.936, "lr": 0.003, "grad": 0.1139, "tokens": 129362688000, "tok_s": 160007.1}
|
| 22 |
+
{"step": 123420, "epoch": 0.784, "loss": 1.75995, "ppl": 5.812, "lr": 0.003, "grad": 0.1308, "tokens": 129383654400, "tok_s": 160252.3}
|
| 23 |
+
{"step": 123440, "epoch": 0.784, "loss": 1.66969, "ppl": 5.311, "lr": 0.003, "grad": 0.0459, "tokens": 129404620800, "tok_s": 160442.8}
|
| 24 |
+
{"step": 123460, "epoch": 0.784, "loss": 1.81077, "ppl": 6.115, "lr": 0.003, "grad": 0.138, "tokens": 129425587200, "tok_s": 160788.9}
|
| 25 |
+
{"step": 123480, "epoch": 0.785, "loss": 1.80649, "ppl": 6.089, "lr": 0.003, "grad": 0.1163, "tokens": 129446553600, "tok_s": 160351.6}
|
| 26 |
+
{"step": 123500, "epoch": 0.785, "loss": 1.89406, "ppl": 6.646, "lr": 0.003, "grad": 0.0874, "tokens": 129467520000, "tok_s": 160608.9}
|
| 27 |
+
{"step": 123520, "epoch": 0.785, "loss": 1.76213, "ppl": 5.825, "lr": 0.003, "grad": 0.1057, "tokens": 129488486400, "tok_s": 160788.4}
|
| 28 |
+
{"step": 123540, "epoch": 0.785, "loss": 1.65779, "ppl": 5.248, "lr": 0.003, "grad": 0.0677, "tokens": 129509452800, "tok_s": 160517.6}
|
| 29 |
+
{"step": 123560, "epoch": 0.785, "loss": 1.67789, "ppl": 5.354, "lr": 0.003, "grad": 0.0999, "tokens": 129530419200, "tok_s": 160237.3}
|
| 30 |
+
{"step": 123580, "epoch": 0.785, "loss": 1.70206, "ppl": 5.485, "lr": 0.003, "grad": 0.1107, "tokens": 129551385600, "tok_s": 160724.2}
|
| 31 |
+
{"step": 123600, "epoch": 0.785, "loss": 1.63826, "ppl": 5.146, "lr": 0.003, "grad": 0.0701, "tokens": 129572352000, "tok_s": 160822.5}
|
| 32 |
+
{"step": 123620, "epoch": 0.785, "loss": 1.71302, "ppl": 5.546, "lr": 0.003, "grad": 0.085, "tokens": 129593318400, "tok_s": 160096.6}
|
| 33 |
+
{"step": 123640, "epoch": 0.786, "loss": 1.66073, "ppl": 5.263, "lr": 0.003, "grad": 0.1023, "tokens": 129614284800, "tok_s": 160631.5}
|
| 34 |
+
{"step": 123660, "epoch": 0.786, "loss": 1.8423, "ppl": 6.311, "lr": 0.003, "grad": 0.1501, "tokens": 129635251200, "tok_s": 160190.0}
|
| 35 |
+
{"step": 123680, "epoch": 0.786, "loss": 1.76954, "ppl": 5.868, "lr": 0.003, "grad": 0.133, "tokens": 129656217600, "tok_s": 160086.3}
|
| 36 |
+
{"step": 123700, "epoch": 0.786, "loss": 1.74116, "ppl": 5.704, "lr": 0.003, "grad": 0.1168, "tokens": 129677184000, "tok_s": 160085.2}
|
| 37 |
+
{"step": 123720, "epoch": 0.786, "loss": 1.66455, "ppl": 5.283, "lr": 0.003, "grad": 0.0707, "tokens": 129698150400, "tok_s": 160806.9}
|
| 38 |
+
{"step": 123740, "epoch": 0.786, "loss": 1.69718, "ppl": 5.459, "lr": 0.003, "grad": 0.0964, "tokens": 129719116800, "tok_s": 160812.3}
|
| 39 |
+
{"step": 123760, "epoch": 0.786, "loss": 1.76656, "ppl": 5.851, "lr": 0.003, "grad": 0.0841, "tokens": 129740083200, "tok_s": 161029.3}
|
| 40 |
+
{"step": 123780, "epoch": 0.786, "loss": 1.675, "ppl": 5.339, "lr": 0.003, "grad": 0.1033, "tokens": 129761049600, "tok_s": 159944.2}
|
| 41 |
+
{"step": 123800, "epoch": 0.787, "loss": 1.69161, "ppl": 5.428, "lr": 0.003, "grad": 0.0943, "tokens": 129782016000, "tok_s": 160887.6}
|
| 42 |
+
{"step": 123820, "epoch": 0.787, "loss": 1.74107, "ppl": 5.703, "lr": 0.003, "grad": 0.0992, "tokens": 129802982400, "tok_s": 160383.1}
|
| 43 |
+
{"step": 123840, "epoch": 0.787, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.0678, "tokens": 129823948800, "tok_s": 160859.1}
|
| 44 |
+
{"step": 123860, "epoch": 0.787, "loss": 1.75066, "ppl": 5.758, "lr": 0.003, "grad": 0.1289, "tokens": 129844915200, "tok_s": 160687.8}
|
| 45 |
+
{"step": 123880, "epoch": 0.787, "loss": 1.77861, "ppl": 5.922, "lr": 0.003, "grad": 0.1118, "tokens": 129865881600, "tok_s": 159777.7}
|
| 46 |
+
{"step": 123900, "epoch": 0.787, "loss": 1.44937, "ppl": 4.26, "lr": 0.003, "grad": 0.0972, "tokens": 129886848000, "tok_s": 160594.5}
|
| 47 |
+
{"step": 123920, "epoch": 0.787, "loss": 1.67828, "ppl": 5.356, "lr": 0.003, "grad": 0.1003, "tokens": 129907814400, "tok_s": 160390.4}
|
| 48 |
+
{"step": 123940, "epoch": 0.787, "loss": 1.6936, "ppl": 5.439, "lr": 0.003, "grad": 0.1095, "tokens": 129928780800, "tok_s": 160885.6}
|
| 49 |
+
{"step": 123960, "epoch": 0.788, "loss": 1.78226, "ppl": 5.943, "lr": 0.003, "grad": 0.1094, "tokens": 129949747200, "tok_s": 160422.9}
|
| 50 |
+
{"step": 123980, "epoch": 0.788, "loss": 1.73459, "ppl": 5.667, "lr": 0.003, "grad": 0.0688, "tokens": 129970713600, "tok_s": 160651.5}
|
| 51 |
+
{"step": 124000, "epoch": 0.788, "loss": 1.88859, "ppl": 6.61, "lr": 0.003, "grad": 0.1302, "tokens": 129991680000, "tok_s": 159622.6}
|
| 52 |
+
{"step": 124000, "val_loss": 1.73125, "val_ppl": 5.648, "is_best": true}
|
| 53 |
+
{"step": 124020, "epoch": 0.788, "loss": 1.7361, "ppl": 5.675, "lr": 0.003, "grad": 0.1751, "tokens": 130012646400, "tok_s": 160215.9}
|
| 54 |
+
{"step": 124040, "epoch": 0.788, "loss": 1.67665, "ppl": 5.348, "lr": 0.003, "grad": 0.0744, "tokens": 130033612800, "tok_s": 160225.5}
|
| 55 |
+
{"step": 124060, "epoch": 0.788, "loss": 1.77362, "ppl": 5.892, "lr": 0.003, "grad": 0.0898, "tokens": 130054579200, "tok_s": 160331.3}
|
| 56 |
+
{"step": 124080, "epoch": 0.788, "loss": 1.72503, "ppl": 5.613, "lr": 0.003, "grad": 0.0922, "tokens": 130075545600, "tok_s": 159702.9}
|
| 57 |
+
{"step": 124100, "epoch": 0.788, "loss": 1.59609, "ppl": 4.934, "lr": 0.003, "grad": 0.0762, "tokens": 130096512000, "tok_s": 160685.8}
|
| 58 |
+
{"step": 124120, "epoch": 0.789, "loss": 1.86891, "ppl": 6.481, "lr": 0.003, "grad": 0.1202, "tokens": 130117478400, "tok_s": 160504.1}
|
| 59 |
+
{"step": 124140, "epoch": 0.789, "loss": 1.76403, "ppl": 5.836, "lr": 0.003, "grad": 0.0684, "tokens": 130138444800, "tok_s": 160268.2}
|
| 60 |
+
{"step": 124160, "epoch": 0.789, "loss": 1.74983, "ppl": 5.754, "lr": 0.003, "grad": 0.1502, "tokens": 130159411200, "tok_s": 160689.6}
|
| 61 |
+
{"step": 124180, "epoch": 0.789, "loss": 1.79266, "ppl": 6.005, "lr": 0.003, "grad": 0.1325, "tokens": 130180377600, "tok_s": 160749.9}
|
| 62 |
+
{"step": 124200, "epoch": 0.789, "loss": 1.70712, "ppl": 5.513, "lr": 0.003, "grad": 0.1652, "tokens": 130201344000, "tok_s": 160972.2}
|
| 63 |
+
{"step": 124220, "epoch": 0.789, "loss": 1.77982, "ppl": 5.929, "lr": 0.003, "grad": 0.0863, "tokens": 130222310400, "tok_s": 159848.7}
|
| 64 |
+
{"step": 124240, "epoch": 0.789, "loss": 1.6902, "ppl": 5.421, "lr": 0.003, "grad": 0.0906, "tokens": 130243276800, "tok_s": 160423.3}
|
| 65 |
+
{"step": 124260, "epoch": 0.79, "loss": 1.72005, "ppl": 5.585, "lr": 0.003, "grad": 0.1148, "tokens": 130264243200, "tok_s": 160008.5}
|
| 66 |
+
{"step": 124280, "epoch": 0.79, "loss": 1.60375, "ppl": 4.972, "lr": 0.003, "grad": 0.0759, "tokens": 130285209600, "tok_s": 160501.4}
|
| 67 |
+
{"step": 124300, "epoch": 0.79, "loss": 1.80209, "ppl": 6.062, "lr": 0.003, "grad": 0.1022, "tokens": 130306176000, "tok_s": 160572.2}
|
| 68 |
+
{"step": 124320, "epoch": 0.79, "loss": 1.74269, "ppl": 5.713, "lr": 0.003, "grad": 0.0813, "tokens": 130327142400, "tok_s": 160189.3}
|
| 69 |
+
{"step": 124340, "epoch": 0.79, "loss": 1.79512, "ppl": 6.02, "lr": 0.003, "grad": 0.1168, "tokens": 130348108800, "tok_s": 160868.6}
|
| 70 |
+
{"step": 124360, "epoch": 0.79, "loss": 1.73415, "ppl": 5.664, "lr": 0.003, "grad": 0.0753, "tokens": 130369075200, "tok_s": 160812.7}
|
| 71 |
+
{"step": 124380, "epoch": 0.79, "loss": 1.84343, "ppl": 6.318, "lr": 0.003, "grad": 0.0912, "tokens": 130390041600, "tok_s": 160527.0}
|
| 72 |
+
{"step": 124400, "epoch": 0.79, "loss": 1.81286, "ppl": 6.128, "lr": 0.003, "grad": 0.069, "tokens": 130411008000, "tok_s": 160789.7}
|
| 73 |
+
{"step": 124420, "epoch": 0.791, "loss": 1.79391, "ppl": 6.013, "lr": 0.003, "grad": 0.0965, "tokens": 130431974400, "tok_s": 160630.4}
|
| 74 |
+
{"step": 124440, "epoch": 0.791, "loss": 1.73427, "ppl": 5.665, "lr": 0.003, "grad": 0.095, "tokens": 130452940800, "tok_s": 160278.9}
|
| 75 |
+
{"step": 124460, "epoch": 0.791, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.1166, "tokens": 130473907200, "tok_s": 159362.5}
|
| 76 |
+
{"step": 124480, "epoch": 0.791, "loss": 1.82161, "ppl": 6.182, "lr": 0.003, "grad": 0.0951, "tokens": 130494873600, "tok_s": 160482.4}
|
| 77 |
+
{"step": 124500, "epoch": 0.791, "loss": 1.77899, "ppl": 5.924, "lr": 0.003, "grad": 0.0911, "tokens": 130515840000, "tok_s": 160632.9}
|
| 78 |
+
{"step": 124520, "epoch": 0.791, "loss": 1.78569, "ppl": 5.964, "lr": 0.003, "grad": 0.1077, "tokens": 130536806400, "tok_s": 160596.3}
|
| 79 |
+
{"step": 124540, "epoch": 0.791, "loss": 1.7094, "ppl": 5.526, "lr": 0.003, "grad": 0.0913, "tokens": 130557772800, "tok_s": 160800.8}
|
| 80 |
+
{"step": 124560, "epoch": 0.791, "loss": 1.79031, "ppl": 5.991, "lr": 0.003, "grad": 0.1412, "tokens": 130578739200, "tok_s": 160067.8}
|
| 81 |
+
{"step": 124580, "epoch": 0.792, "loss": 1.59144, "ppl": 4.911, "lr": 0.003, "grad": 0.0821, "tokens": 130599705600, "tok_s": 160693.3}
|
| 82 |
+
{"step": 124600, "epoch": 0.792, "loss": 1.76647, "ppl": 5.85, "lr": 0.003, "grad": 0.1521, "tokens": 130620672000, "tok_s": 160653.0}
|
| 83 |
+
{"step": 124620, "epoch": 0.792, "loss": 1.76625, "ppl": 5.849, "lr": 0.003, "grad": 0.089, "tokens": 130641638400, "tok_s": 159971.8}
|
| 84 |
+
{"step": 124640, "epoch": 0.792, "loss": 1.73058, "ppl": 5.644, "lr": 0.003, "grad": 0.1279, "tokens": 130662604800, "tok_s": 160512.9}
|
| 85 |
+
{"step": 124660, "epoch": 0.792, "loss": 1.78411, "ppl": 5.954, "lr": 0.003, "grad": 0.0948, "tokens": 130683571200, "tok_s": 160282.8}
|
| 86 |
+
{"step": 124680, "epoch": 0.792, "loss": 1.7574, "ppl": 5.797, "lr": 0.003, "grad": 0.0869, "tokens": 130704537600, "tok_s": 160624.5}
|
| 87 |
+
{"step": 124700, "epoch": 0.792, "loss": 1.72977, "ppl": 5.639, "lr": 0.003, "grad": 0.0889, "tokens": 130725504000, "tok_s": 160538.3}
|
| 88 |
+
{"step": 124720, "epoch": 0.792, "loss": 1.70746, "ppl": 5.515, "lr": 0.003, "grad": 0.0753, "tokens": 130746470400, "tok_s": 160834.9}
|
| 89 |
+
{"step": 124740, "epoch": 0.793, "loss": 1.74636, "ppl": 5.734, "lr": 0.003, "grad": 0.1024, "tokens": 130767436800, "tok_s": 160732.6}
|
| 90 |
+
{"step": 124760, "epoch": 0.793, "loss": 1.63906, "ppl": 5.15, "lr": 0.003, "grad": 0.0647, "tokens": 130788403200, "tok_s": 160648.6}
|
| 91 |
+
{"step": 124780, "epoch": 0.793, "loss": 1.71628, "ppl": 5.564, "lr": 0.003, "grad": 0.1116, "tokens": 130809369600, "tok_s": 160459.3}
|
| 92 |
+
{"step": 124800, "epoch": 0.793, "loss": 1.74014, "ppl": 5.698, "lr": 0.003, "grad": 0.0762, "tokens": 130830336000, "tok_s": 160779.2}
|
| 93 |
+
{"step": 124820, "epoch": 0.793, "loss": 1.76257, "ppl": 5.827, "lr": 0.003, "grad": 0.1096, "tokens": 130851302400, "tok_s": 160502.2}
|
| 94 |
+
{"step": 124840, "epoch": 0.793, "loss": 1.77835, "ppl": 5.92, "lr": 0.003, "grad": 0.1063, "tokens": 130872268800, "tok_s": 160316.6}
|
| 95 |
+
{"step": 124860, "epoch": 0.793, "loss": 1.78944, "ppl": 5.986, "lr": 0.003, "grad": 0.0601, "tokens": 130893235200, "tok_s": 160541.8}
|
| 96 |
+
{"step": 124880, "epoch": 0.793, "loss": 1.76928, "ppl": 5.867, "lr": 0.003, "grad": 0.1254, "tokens": 130914201600, "tok_s": 160654.0}
|
| 97 |
+
{"step": 124900, "epoch": 0.794, "loss": 1.75305, "ppl": 5.772, "lr": 0.003, "grad": 0.0925, "tokens": 130935168000, "tok_s": 160492.8}
|
| 98 |
+
{"step": 124920, "epoch": 0.794, "loss": 1.77743, "ppl": 5.915, "lr": 0.003, "grad": 0.1285, "tokens": 130956134400, "tok_s": 160781.2}
|
| 99 |
+
{"step": 124940, "epoch": 0.794, "loss": 1.72792, "ppl": 5.629, "lr": 0.003, "grad": 0.0794, "tokens": 130977100800, "tok_s": 160778.9}
|
| 100 |
+
{"step": 124960, "epoch": 0.794, "loss": 1.74981, "ppl": 5.753, "lr": 0.003, "grad": 0.1085, "tokens": 130998067200, "tok_s": 159891.1}
|
| 101 |
+
{"step": 124980, "epoch": 0.794, "loss": 1.79698, "ppl": 6.031, "lr": 0.003, "grad": 0.1132, "tokens": 131019033600, "tok_s": 160698.3}
|
| 102 |
+
{"step": 125000, "epoch": 0.794, "loss": 1.72512, "ppl": 5.613, "lr": 0.003, "grad": 0.0803, "tokens": 131040000000, "tok_s": 160280.6}
|
| 103 |
+
{"step": 125000, "val_loss": 1.74215, "val_ppl": 5.71, "is_best": false}
|
| 104 |
+
{"step": 125020, "epoch": 0.794, "loss": 1.76033, "ppl": 5.814, "lr": 0.003, "grad": 0.1208, "tokens": 131060966400, "tok_s": 160517.3}
|
| 105 |
+
{"step": 125040, "epoch": 0.794, "loss": 1.74821, "ppl": 5.744, "lr": 0.003, "grad": 0.1219, "tokens": 131081932800, "tok_s": 160743.6}
|
| 106 |
+
{"step": 125060, "epoch": 0.795, "loss": 1.69473, "ppl": 5.445, "lr": 0.003, "grad": 0.0884, "tokens": 131102899200, "tok_s": 160707.3}
|
| 107 |
+
{"step": 125080, "epoch": 0.795, "loss": 1.76494, "ppl": 5.841, "lr": 0.003, "grad": 0.1146, "tokens": 131123865600, "tok_s": 160535.1}
|
| 108 |
+
{"step": 125100, "epoch": 0.795, "loss": 1.7554, "ppl": 5.786, "lr": 0.003, "grad": 0.1027, "tokens": 131144832000, "tok_s": 160837.8}
|
| 109 |
+
{"step": 125120, "epoch": 0.795, "loss": 1.82843, "ppl": 6.224, "lr": 0.003, "grad": 0.0815, "tokens": 131165798400, "tok_s": 159815.0}
|
| 110 |
+
{"step": 125140, "epoch": 0.795, "loss": 1.76921, "ppl": 5.866, "lr": 0.003, "grad": 0.1131, "tokens": 131186764800, "tok_s": 160652.4}
|
| 111 |
+
{"step": 125160, "epoch": 0.795, "loss": 1.72331, "ppl": 5.603, "lr": 0.003, "grad": 0.1504, "tokens": 131207731200, "tok_s": 160288.6}
|
| 112 |
+
{"step": 125180, "epoch": 0.795, "loss": 1.74794, "ppl": 5.743, "lr": 0.003, "grad": 0.0825, "tokens": 131228697600, "tok_s": 160590.8}
|
| 113 |
+
{"step": 125200, "epoch": 0.795, "loss": 1.80309, "ppl": 6.068, "lr": 0.003, "grad": 0.1297, "tokens": 131249664000, "tok_s": 160013.0}
|
| 114 |
+
{"step": 125220, "epoch": 0.796, "loss": 1.70651, "ppl": 5.51, "lr": 0.003, "grad": 0.074, "tokens": 131270630400, "tok_s": 160896.4}
|
| 115 |
+
{"step": 125240, "epoch": 0.796, "loss": 1.75076, "ppl": 5.759, "lr": 0.003, "grad": 0.1105, "tokens": 131291596800, "tok_s": 160396.9}
|
| 116 |
+
{"step": 125260, "epoch": 0.796, "loss": 1.66345, "ppl": 5.277, "lr": 0.003, "grad": 0.087, "tokens": 131312563200, "tok_s": 160563.1}
|
| 117 |
+
{"step": 125280, "epoch": 0.796, "loss": 1.76143, "ppl": 5.821, "lr": 0.003, "grad": 0.0767, "tokens": 131333529600, "tok_s": 160747.0}
|
| 118 |
+
{"step": 125300, "epoch": 0.796, "loss": 1.78602, "ppl": 5.966, "lr": 0.003, "grad": 0.0902, "tokens": 131354496000, "tok_s": 160934.3}
|
| 119 |
+
{"step": 125320, "epoch": 0.796, "loss": 1.66687, "ppl": 5.296, "lr": 0.003, "grad": 0.0875, "tokens": 131375462400, "tok_s": 159971.8}
|
| 120 |
+
{"step": 125340, "epoch": 0.796, "loss": 1.63117, "ppl": 5.11, "lr": 0.003, "grad": 0.1239, "tokens": 131396428800, "tok_s": 160658.5}
|
| 121 |
+
{"step": 125360, "epoch": 0.796, "loss": 1.75845, "ppl": 5.803, "lr": 0.003, "grad": 0.1208, "tokens": 131417395200, "tok_s": 160151.0}
|
| 122 |
+
{"step": 125380, "epoch": 0.797, "loss": 1.73367, "ppl": 5.661, "lr": 0.003, "grad": 0.0954, "tokens": 131438361600, "tok_s": 160160.2}
|
| 123 |
+
{"step": 125400, "epoch": 0.797, "loss": 1.64819, "ppl": 5.198, "lr": 0.003, "grad": 0.0774, "tokens": 131459328000, "tok_s": 160193.9}
|
| 124 |
+
{"step": 125420, "epoch": 0.797, "loss": 1.66598, "ppl": 5.291, "lr": 0.003, "grad": 0.0986, "tokens": 131480294400, "tok_s": 160053.9}
|
| 125 |
+
{"step": 125440, "epoch": 0.797, "loss": 1.8541, "ppl": 6.386, "lr": 0.003, "grad": 0.1272, "tokens": 131501260800, "tok_s": 160350.0}
|
| 126 |
+
{"step": 125460, "epoch": 0.797, "loss": 1.64714, "ppl": 5.192, "lr": 0.003, "grad": 0.0725, "tokens": 131522227200, "tok_s": 160129.8}
|
| 127 |
+
{"step": 125480, "epoch": 0.797, "loss": 1.7242, "ppl": 5.608, "lr": 0.003, "grad": 0.0687, "tokens": 131543193600, "tok_s": 160611.9}
|
| 128 |
+
{"step": 125500, "epoch": 0.797, "loss": 1.6994, "ppl": 5.471, "lr": 0.003, "grad": 0.1098, "tokens": 131564160000, "tok_s": 160332.7}
|
| 129 |
+
{"step": 125520, "epoch": 0.798, "loss": 1.71202, "ppl": 5.54, "lr": 0.003, "grad": 0.0632, "tokens": 131585126400, "tok_s": 160815.6}
|
| 130 |
+
{"step": 125540, "epoch": 0.798, "loss": 1.71523, "ppl": 5.558, "lr": 0.003, "grad": 0.0566, "tokens": 131606092800, "tok_s": 160783.7}
|
| 131 |
+
{"step": 125560, "epoch": 0.798, "loss": 1.81274, "ppl": 6.127, "lr": 0.003, "grad": 0.1067, "tokens": 131627059200, "tok_s": 160811.5}
|
| 132 |
+
{"step": 125580, "epoch": 0.798, "loss": 1.74317, "ppl": 5.715, "lr": 0.003, "grad": 0.1306, "tokens": 131648025600, "tok_s": 160707.5}
|
| 133 |
+
{"step": 125600, "epoch": 0.798, "loss": 1.77451, "ppl": 5.897, "lr": 0.003, "grad": 0.0825, "tokens": 131668992000, "tok_s": 160758.1}
|
| 134 |
+
{"step": 125620, "epoch": 0.798, "loss": 1.73877, "ppl": 5.69, "lr": 0.003, "grad": 0.082, "tokens": 131689958400, "tok_s": 160627.5}
|
| 135 |
+
{"step": 125640, "epoch": 0.798, "loss": 1.77622, "ppl": 5.907, "lr": 0.003, "grad": 0.1201, "tokens": 131710924800, "tok_s": 160920.4}
|
| 136 |
+
{"step": 125660, "epoch": 0.798, "loss": 1.64526, "ppl": 5.182, "lr": 0.003, "grad": 0.1084, "tokens": 131731891200, "tok_s": 160624.3}
|
| 137 |
+
{"step": 125680, "epoch": 0.799, "loss": 1.73881, "ppl": 5.691, "lr": 0.003, "grad": 0.1094, "tokens": 131752857600, "tok_s": 160666.0}
|
| 138 |
+
{"step": 125700, "epoch": 0.799, "loss": 1.69768, "ppl": 5.461, "lr": 0.003, "grad": 0.1167, "tokens": 131773824000, "tok_s": 160761.8}
|
| 139 |
+
{"step": 125720, "epoch": 0.799, "loss": 1.78497, "ppl": 5.959, "lr": 0.003, "grad": 0.1092, "tokens": 131794790400, "tok_s": 160875.4}
|
| 140 |
+
{"step": 125740, "epoch": 0.799, "loss": 1.60774, "ppl": 4.992, "lr": 0.003, "grad": 0.092, "tokens": 131815756800, "tok_s": 160801.6}
|
| 141 |
+
{"step": 125760, "epoch": 0.799, "loss": 1.77716, "ppl": 5.913, "lr": 0.003, "grad": 0.0894, "tokens": 131836723200, "tok_s": 160699.4}
|
| 142 |
+
{"step": 125780, "epoch": 0.799, "loss": 1.78281, "ppl": 5.947, "lr": 0.003, "grad": 0.1028, "tokens": 131857689600, "tok_s": 160806.4}
|
| 143 |
+
{"step": 125800, "epoch": 0.799, "loss": 1.75767, "ppl": 5.799, "lr": 0.003, "grad": 0.0783, "tokens": 131878656000, "tok_s": 160736.4}
|
| 144 |
+
{"step": 125820, "epoch": 0.799, "loss": 1.77649, "ppl": 5.909, "lr": 0.003, "grad": 0.0951, "tokens": 131899622400, "tok_s": 160778.6}
|
| 145 |
+
{"step": 125840, "epoch": 0.8, "loss": 1.77938, "ppl": 5.926, "lr": 0.003, "grad": 0.1144, "tokens": 131920588800, "tok_s": 160968.2}
|
| 146 |
+
{"step": 125860, "epoch": 0.8, "loss": 1.80196, "ppl": 6.062, "lr": 0.003, "grad": 0.1349, "tokens": 131941555200, "tok_s": 160726.0}
|
| 147 |
+
{"step": 125880, "epoch": 0.8, "loss": 1.71563, "ppl": 5.56, "lr": 0.003, "grad": 0.095, "tokens": 131962521600, "tok_s": 160731.7}
|
| 148 |
+
{"step": 125900, "epoch": 0.8, "loss": 1.76961, "ppl": 5.869, "lr": 0.003, "grad": 0.1057, "tokens": 131983488000, "tok_s": 160875.8}
|
| 149 |
+
{"step": 125920, "epoch": 0.8, "loss": 1.76717, "ppl": 5.854, "lr": 0.003, "grad": 0.0702, "tokens": 132004454400, "tok_s": 160778.1}
|
| 150 |
+
{"step": 125940, "epoch": 0.8, "loss": 1.73329, "ppl": 5.659, "lr": 0.003, "grad": 0.1034, "tokens": 132025420800, "tok_s": 160384.4}
|
| 151 |
+
{"step": 125960, "epoch": 0.8, "loss": 1.78953, "ppl": 5.987, "lr": 0.003, "grad": 0.082, "tokens": 132046387200, "tok_s": 160727.7}
|
| 152 |
+
{"step": 125980, "epoch": 0.8, "loss": 1.76174, "ppl": 5.823, "lr": 0.003, "grad": 0.1295, "tokens": 132067353600, "tok_s": 160876.9}
|
| 153 |
+
{"step": 126000, "epoch": 0.801, "loss": 1.76653, "ppl": 5.85, "lr": 0.003, "grad": 0.1551, "tokens": 132088320000, "tok_s": 160715.0}
|
| 154 |
+
{"step": 126000, "val_loss": 1.74991, "val_ppl": 5.754, "is_best": false}
|
| 155 |
+
{"step": 126020, "epoch": 0.801, "loss": 1.69758, "ppl": 5.461, "lr": 0.003, "grad": 0.0926, "tokens": 132109286400, "tok_s": 160773.8}
|
| 156 |
+
{"step": 126040, "epoch": 0.801, "loss": 1.75444, "ppl": 5.78, "lr": 0.003, "grad": 0.0992, "tokens": 132130252800, "tok_s": 160821.1}
|
| 157 |
+
{"step": 126060, "epoch": 0.801, "loss": 1.73691, "ppl": 5.68, "lr": 0.003, "grad": 0.1107, "tokens": 132151219200, "tok_s": 160868.3}
|
| 158 |
+
{"step": 126080, "epoch": 0.801, "loss": 1.77811, "ppl": 5.919, "lr": 0.003, "grad": 0.1458, "tokens": 132172185600, "tok_s": 160908.9}
|
| 159 |
+
{"step": 126100, "epoch": 0.801, "loss": 1.77404, "ppl": 5.895, "lr": 0.003, "grad": 0.0837, "tokens": 132193152000, "tok_s": 160594.2}
|
| 160 |
+
{"step": 126120, "epoch": 0.801, "loss": 1.7408, "ppl": 5.702, "lr": 0.003, "grad": 0.1212, "tokens": 132214118400, "tok_s": 160877.0}
|
| 161 |
+
{"step": 126140, "epoch": 0.801, "loss": 1.72606, "ppl": 5.618, "lr": 0.003, "grad": 0.0992, "tokens": 132235084800, "tok_s": 160598.3}
|
| 162 |
+
{"step": 126160, "epoch": 0.802, "loss": 1.73635, "ppl": 5.677, "lr": 0.003, "grad": 0.0989, "tokens": 132256051200, "tok_s": 160405.1}
|
| 163 |
+
{"step": 126180, "epoch": 0.802, "loss": 1.68267, "ppl": 5.38, "lr": 0.003, "grad": 0.1019, "tokens": 132277017600, "tok_s": 160378.1}
|
| 164 |
+
{"step": 126200, "epoch": 0.802, "loss": 1.74384, "ppl": 5.719, "lr": 0.003, "grad": 0.1051, "tokens": 132297984000, "tok_s": 160807.2}
|
| 165 |
+
{"step": 126220, "epoch": 0.802, "loss": 1.73014, "ppl": 5.641, "lr": 0.003, "grad": 0.1541, "tokens": 132318950400, "tok_s": 160839.3}
|
| 166 |
+
{"step": 126240, "epoch": 0.802, "loss": 1.73399, "ppl": 5.663, "lr": 0.003, "grad": 0.1039, "tokens": 132339916800, "tok_s": 160368.3}
|
| 167 |
+
{"step": 126260, "epoch": 0.802, "loss": 1.74648, "ppl": 5.734, "lr": 0.003, "grad": 0.0941, "tokens": 132360883200, "tok_s": 160590.1}
|
| 168 |
+
{"step": 126280, "epoch": 0.802, "loss": 1.77031, "ppl": 5.873, "lr": 0.003, "grad": 0.0798, "tokens": 132381849600, "tok_s": 160842.0}
|
| 169 |
+
{"step": 126300, "epoch": 0.802, "loss": 1.82219, "ppl": 6.185, "lr": 0.003, "grad": 0.0945, "tokens": 132402816000, "tok_s": 160908.6}
|
| 170 |
+
{"step": 126320, "epoch": 0.803, "loss": 1.72436, "ppl": 5.609, "lr": 0.003, "grad": 0.1298, "tokens": 132423782400, "tok_s": 160699.5}
|
| 171 |
+
{"step": 126340, "epoch": 0.803, "loss": 1.75298, "ppl": 5.772, "lr": 0.003, "grad": 0.1049, "tokens": 132444748800, "tok_s": 160776.4}
|
| 172 |
+
{"step": 126360, "epoch": 0.803, "loss": 1.74143, "ppl": 5.705, "lr": 0.003, "grad": 0.1052, "tokens": 132465715200, "tok_s": 160881.9}
|
| 173 |
+
{"step": 126380, "epoch": 0.803, "loss": 1.69539, "ppl": 5.449, "lr": 0.003, "grad": 0.122, "tokens": 132486681600, "tok_s": 160739.3}
|
| 174 |
+
{"step": 126400, "epoch": 0.803, "loss": 1.7148, "ppl": 5.556, "lr": 0.003, "grad": 0.1499, "tokens": 132507648000, "tok_s": 160947.8}
|
| 175 |
+
{"step": 126420, "epoch": 0.803, "loss": 1.74067, "ppl": 5.701, "lr": 0.003, "grad": 0.1329, "tokens": 132528614400, "tok_s": 160898.9}
|
| 176 |
+
{"step": 126440, "epoch": 0.803, "loss": 1.72883, "ppl": 5.634, "lr": 0.003, "grad": 0.1075, "tokens": 132549580800, "tok_s": 160766.4}
|
| 177 |
+
{"step": 126460, "epoch": 0.803, "loss": 1.74148, "ppl": 5.706, "lr": 0.003, "grad": 0.0728, "tokens": 132570547200, "tok_s": 160702.9}
|
| 178 |
+
{"step": 126480, "epoch": 0.804, "loss": 1.65406, "ppl": 5.228, "lr": 0.003, "grad": 0.0854, "tokens": 132591513600, "tok_s": 160717.1}
|
| 179 |
+
{"step": 126500, "epoch": 0.804, "loss": 1.86413, "ppl": 6.45, "lr": 0.003, "grad": 0.137, "tokens": 132612480000, "tok_s": 160885.4}
|
| 180 |
+
{"step": 126520, "epoch": 0.804, "loss": 1.79083, "ppl": 5.994, "lr": 0.003, "grad": 0.0864, "tokens": 132633446400, "tok_s": 160726.3}
|
| 181 |
+
{"step": 126540, "epoch": 0.804, "loss": 1.69603, "ppl": 5.452, "lr": 0.003, "grad": 0.0653, "tokens": 132654412800, "tok_s": 160595.0}
|
| 182 |
+
{"step": 126560, "epoch": 0.804, "loss": 1.84869, "ppl": 6.351, "lr": 0.003, "grad": 0.1031, "tokens": 132675379200, "tok_s": 160760.5}
|
| 183 |
+
{"step": 126580, "epoch": 0.804, "loss": 1.73397, "ppl": 5.663, "lr": 0.003, "grad": 0.0941, "tokens": 132696345600, "tok_s": 160939.5}
|
| 184 |
+
{"step": 126600, "epoch": 0.804, "loss": 1.82054, "ppl": 6.175, "lr": 0.003, "grad": 0.1074, "tokens": 132717312000, "tok_s": 160769.9}
|
| 185 |
+
{"step": 126620, "epoch": 0.804, "loss": 1.73808, "ppl": 5.686, "lr": 0.003, "grad": 0.1278, "tokens": 132738278400, "tok_s": 160636.4}
|
| 186 |
+
{"step": 126640, "epoch": 0.805, "loss": 1.75373, "ppl": 5.776, "lr": 0.003, "grad": 0.1032, "tokens": 132759244800, "tok_s": 160776.6}
|
| 187 |
+
{"step": 126660, "epoch": 0.805, "loss": 1.63663, "ppl": 5.138, "lr": 0.003, "grad": 0.0948, "tokens": 132780211200, "tok_s": 160296.1}
|
| 188 |
+
{"step": 126680, "epoch": 0.805, "loss": 1.46989, "ppl": 4.349, "lr": 0.003, "grad": 0.1914, "tokens": 132801177600, "tok_s": 160768.9}
|
| 189 |
+
{"step": 126700, "epoch": 0.805, "loss": 1.80131, "ppl": 6.058, "lr": 0.003, "grad": 0.0968, "tokens": 132822144000, "tok_s": 160553.8}
|
| 190 |
+
{"step": 126720, "epoch": 0.805, "loss": 1.70179, "ppl": 5.484, "lr": 0.003, "grad": 0.1178, "tokens": 132843110400, "tok_s": 160809.0}
|
| 191 |
+
{"step": 126740, "epoch": 0.805, "loss": 1.71646, "ppl": 5.565, "lr": 0.003, "grad": 0.1215, "tokens": 132864076800, "tok_s": 160608.5}
|
| 192 |
+
{"step": 126760, "epoch": 0.805, "loss": 1.74311, "ppl": 5.715, "lr": 0.003, "grad": 0.0742, "tokens": 132885043200, "tok_s": 160699.2}
|
| 193 |
+
{"step": 126780, "epoch": 0.806, "loss": 1.70769, "ppl": 5.516, "lr": 0.003, "grad": 0.1247, "tokens": 132906009600, "tok_s": 160496.8}
|
| 194 |
+
{"step": 126800, "epoch": 0.806, "loss": 1.76602, "ppl": 5.848, "lr": 0.003, "grad": 0.1098, "tokens": 132926976000, "tok_s": 160575.2}
|
| 195 |
+
{"step": 126820, "epoch": 0.806, "loss": 1.74984, "ppl": 5.754, "lr": 0.003, "grad": 0.1587, "tokens": 132947942400, "tok_s": 160515.9}
|
| 196 |
+
{"step": 126840, "epoch": 0.806, "loss": 1.76474, "ppl": 5.84, "lr": 0.003, "grad": 0.1143, "tokens": 132968908800, "tok_s": 160570.5}
|
| 197 |
+
{"step": 126860, "epoch": 0.806, "loss": 1.74005, "ppl": 5.698, "lr": 0.003, "grad": 0.1492, "tokens": 132989875200, "tok_s": 160764.3}
|
| 198 |
+
{"step": 126880, "epoch": 0.806, "loss": 1.74436, "ppl": 5.722, "lr": 0.003, "grad": 0.0882, "tokens": 133010841600, "tok_s": 160761.4}
|
| 199 |
+
{"step": 126900, "epoch": 0.806, "loss": 1.73074, "ppl": 5.645, "lr": 0.003, "grad": 0.0589, "tokens": 133031808000, "tok_s": 160736.3}
|
| 200 |
+
{"step": 126920, "epoch": 0.806, "loss": 1.73084, "ppl": 5.645, "lr": 0.003, "grad": 0.1323, "tokens": 133052774400, "tok_s": 160636.1}
|
| 201 |
+
{"step": 126940, "epoch": 0.807, "loss": 1.73858, "ppl": 5.689, "lr": 0.003, "grad": 0.147, "tokens": 133073740800, "tok_s": 160651.5}
|
| 202 |
+
{"step": 126960, "epoch": 0.807, "loss": 1.76887, "ppl": 5.864, "lr": 0.003, "grad": 0.0971, "tokens": 133094707200, "tok_s": 160718.8}
|
| 203 |
+
{"step": 126980, "epoch": 0.807, "loss": 1.73789, "ppl": 5.685, "lr": 0.003, "grad": 0.1209, "tokens": 133115673600, "tok_s": 160883.7}
|
| 204 |
+
{"step": 127000, "epoch": 0.807, "loss": 1.76703, "ppl": 5.853, "lr": 0.003, "grad": 0.1307, "tokens": 133136640000, "tok_s": 160722.0}
|
| 205 |
+
{"step": 127000, "val_loss": 1.74954, "val_ppl": 5.752, "is_best": false}
|
logs/log_128000.jsonl
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 123000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T07:17:42.347663"}
|
| 2 |
+
{"step": 123020, "epoch": 0.782, "loss": 1.73857, "ppl": 5.689, "lr": 0.003, "grad": 0.0862, "tokens": 128964326400, "tok_s": 161031.7}
|
| 3 |
+
{"step": 123040, "epoch": 0.782, "loss": 1.74074, "ppl": 5.702, "lr": 0.003, "grad": 0.1368, "tokens": 128985292800, "tok_s": 160954.1}
|
| 4 |
+
{"step": 123060, "epoch": 0.782, "loss": 1.71462, "ppl": 5.555, "lr": 0.003, "grad": 0.1204, "tokens": 129006259200, "tok_s": 160878.0}
|
| 5 |
+
{"step": 123080, "epoch": 0.782, "loss": 1.61219, "ppl": 5.014, "lr": 0.003, "grad": 0.1082, "tokens": 129027225600, "tok_s": 160909.1}
|
| 6 |
+
{"step": 123100, "epoch": 0.782, "loss": 1.76628, "ppl": 5.849, "lr": 0.003, "grad": 0.1002, "tokens": 129048192000, "tok_s": 160834.8}
|
| 7 |
+
{"step": 123120, "epoch": 0.782, "loss": 1.72774, "ppl": 5.628, "lr": 0.003, "grad": 0.1067, "tokens": 129069158400, "tok_s": 160818.5}
|
| 8 |
+
{"step": 123140, "epoch": 0.782, "loss": 1.74211, "ppl": 5.709, "lr": 0.003, "grad": 0.0941, "tokens": 129090124800, "tok_s": 160918.4}
|
| 9 |
+
{"step": 123160, "epoch": 0.783, "loss": 1.67448, "ppl": 5.336, "lr": 0.003, "grad": 0.1091, "tokens": 129111091200, "tok_s": 160449.9}
|
| 10 |
+
{"step": 123180, "epoch": 0.783, "loss": 1.62741, "ppl": 5.091, "lr": 0.003, "grad": 0.0851, "tokens": 129132057600, "tok_s": 160590.1}
|
| 11 |
+
{"step": 123200, "epoch": 0.783, "loss": 1.59223, "ppl": 4.915, "lr": 0.003, "grad": 0.1177, "tokens": 129153024000, "tok_s": 161036.6}
|
| 12 |
+
{"step": 123220, "epoch": 0.783, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.084, "tokens": 129173990400, "tok_s": 160567.9}
|
| 13 |
+
{"step": 123240, "epoch": 0.783, "loss": 1.70141, "ppl": 5.482, "lr": 0.003, "grad": 0.0896, "tokens": 129194956800, "tok_s": 160638.0}
|
| 14 |
+
{"step": 123260, "epoch": 0.783, "loss": 1.76084, "ppl": 5.817, "lr": 0.003, "grad": 0.0738, "tokens": 129215923200, "tok_s": 160679.1}
|
| 15 |
+
{"step": 123280, "epoch": 0.783, "loss": 1.7102, "ppl": 5.53, "lr": 0.003, "grad": 0.0883, "tokens": 129236889600, "tok_s": 160692.9}
|
| 16 |
+
{"step": 123300, "epoch": 0.783, "loss": 1.75342, "ppl": 5.774, "lr": 0.003, "grad": 0.0895, "tokens": 129257856000, "tok_s": 160243.8}
|
| 17 |
+
{"step": 123320, "epoch": 0.784, "loss": 1.75981, "ppl": 5.811, "lr": 0.003, "grad": 0.0953, "tokens": 129278822400, "tok_s": 160626.9}
|
| 18 |
+
{"step": 123340, "epoch": 0.784, "loss": 1.72484, "ppl": 5.612, "lr": 0.003, "grad": 0.0835, "tokens": 129299788800, "tok_s": 160704.6}
|
| 19 |
+
{"step": 123360, "epoch": 0.784, "loss": 1.77109, "ppl": 5.877, "lr": 0.003, "grad": 0.0692, "tokens": 129320755200, "tok_s": 160342.8}
|
| 20 |
+
{"step": 123380, "epoch": 0.784, "loss": 1.68046, "ppl": 5.368, "lr": 0.003, "grad": 0.0858, "tokens": 129341721600, "tok_s": 160363.0}
|
| 21 |
+
{"step": 123400, "epoch": 0.784, "loss": 1.78102, "ppl": 5.936, "lr": 0.003, "grad": 0.1139, "tokens": 129362688000, "tok_s": 160007.1}
|
| 22 |
+
{"step": 123420, "epoch": 0.784, "loss": 1.75995, "ppl": 5.812, "lr": 0.003, "grad": 0.1308, "tokens": 129383654400, "tok_s": 160252.3}
|
| 23 |
+
{"step": 123440, "epoch": 0.784, "loss": 1.66969, "ppl": 5.311, "lr": 0.003, "grad": 0.0459, "tokens": 129404620800, "tok_s": 160442.8}
|
| 24 |
+
{"step": 123460, "epoch": 0.784, "loss": 1.81077, "ppl": 6.115, "lr": 0.003, "grad": 0.138, "tokens": 129425587200, "tok_s": 160788.9}
|
| 25 |
+
{"step": 123480, "epoch": 0.785, "loss": 1.80649, "ppl": 6.089, "lr": 0.003, "grad": 0.1163, "tokens": 129446553600, "tok_s": 160351.6}
|
| 26 |
+
{"step": 123500, "epoch": 0.785, "loss": 1.89406, "ppl": 6.646, "lr": 0.003, "grad": 0.0874, "tokens": 129467520000, "tok_s": 160608.9}
|
| 27 |
+
{"step": 123520, "epoch": 0.785, "loss": 1.76213, "ppl": 5.825, "lr": 0.003, "grad": 0.1057, "tokens": 129488486400, "tok_s": 160788.4}
|
| 28 |
+
{"step": 123540, "epoch": 0.785, "loss": 1.65779, "ppl": 5.248, "lr": 0.003, "grad": 0.0677, "tokens": 129509452800, "tok_s": 160517.6}
|
| 29 |
+
{"step": 123560, "epoch": 0.785, "loss": 1.67789, "ppl": 5.354, "lr": 0.003, "grad": 0.0999, "tokens": 129530419200, "tok_s": 160237.3}
|
| 30 |
+
{"step": 123580, "epoch": 0.785, "loss": 1.70206, "ppl": 5.485, "lr": 0.003, "grad": 0.1107, "tokens": 129551385600, "tok_s": 160724.2}
|
| 31 |
+
{"step": 123600, "epoch": 0.785, "loss": 1.63826, "ppl": 5.146, "lr": 0.003, "grad": 0.0701, "tokens": 129572352000, "tok_s": 160822.5}
|
| 32 |
+
{"step": 123620, "epoch": 0.785, "loss": 1.71302, "ppl": 5.546, "lr": 0.003, "grad": 0.085, "tokens": 129593318400, "tok_s": 160096.6}
|
| 33 |
+
{"step": 123640, "epoch": 0.786, "loss": 1.66073, "ppl": 5.263, "lr": 0.003, "grad": 0.1023, "tokens": 129614284800, "tok_s": 160631.5}
|
| 34 |
+
{"step": 123660, "epoch": 0.786, "loss": 1.8423, "ppl": 6.311, "lr": 0.003, "grad": 0.1501, "tokens": 129635251200, "tok_s": 160190.0}
|
| 35 |
+
{"step": 123680, "epoch": 0.786, "loss": 1.76954, "ppl": 5.868, "lr": 0.003, "grad": 0.133, "tokens": 129656217600, "tok_s": 160086.3}
|
| 36 |
+
{"step": 123700, "epoch": 0.786, "loss": 1.74116, "ppl": 5.704, "lr": 0.003, "grad": 0.1168, "tokens": 129677184000, "tok_s": 160085.2}
|
| 37 |
+
{"step": 123720, "epoch": 0.786, "loss": 1.66455, "ppl": 5.283, "lr": 0.003, "grad": 0.0707, "tokens": 129698150400, "tok_s": 160806.9}
|
| 38 |
+
{"step": 123740, "epoch": 0.786, "loss": 1.69718, "ppl": 5.459, "lr": 0.003, "grad": 0.0964, "tokens": 129719116800, "tok_s": 160812.3}
|
| 39 |
+
{"step": 123760, "epoch": 0.786, "loss": 1.76656, "ppl": 5.851, "lr": 0.003, "grad": 0.0841, "tokens": 129740083200, "tok_s": 161029.3}
|
| 40 |
+
{"step": 123780, "epoch": 0.786, "loss": 1.675, "ppl": 5.339, "lr": 0.003, "grad": 0.1033, "tokens": 129761049600, "tok_s": 159944.2}
|
| 41 |
+
{"step": 123800, "epoch": 0.787, "loss": 1.69161, "ppl": 5.428, "lr": 0.003, "grad": 0.0943, "tokens": 129782016000, "tok_s": 160887.6}
|
| 42 |
+
{"step": 123820, "epoch": 0.787, "loss": 1.74107, "ppl": 5.703, "lr": 0.003, "grad": 0.0992, "tokens": 129802982400, "tok_s": 160383.1}
|
| 43 |
+
{"step": 123840, "epoch": 0.787, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.0678, "tokens": 129823948800, "tok_s": 160859.1}
|
| 44 |
+
{"step": 123860, "epoch": 0.787, "loss": 1.75066, "ppl": 5.758, "lr": 0.003, "grad": 0.1289, "tokens": 129844915200, "tok_s": 160687.8}
|
| 45 |
+
{"step": 123880, "epoch": 0.787, "loss": 1.77861, "ppl": 5.922, "lr": 0.003, "grad": 0.1118, "tokens": 129865881600, "tok_s": 159777.7}
|
| 46 |
+
{"step": 123900, "epoch": 0.787, "loss": 1.44937, "ppl": 4.26, "lr": 0.003, "grad": 0.0972, "tokens": 129886848000, "tok_s": 160594.5}
|
| 47 |
+
{"step": 123920, "epoch": 0.787, "loss": 1.67828, "ppl": 5.356, "lr": 0.003, "grad": 0.1003, "tokens": 129907814400, "tok_s": 160390.4}
|
| 48 |
+
{"step": 123940, "epoch": 0.787, "loss": 1.6936, "ppl": 5.439, "lr": 0.003, "grad": 0.1095, "tokens": 129928780800, "tok_s": 160885.6}
|
| 49 |
+
{"step": 123960, "epoch": 0.788, "loss": 1.78226, "ppl": 5.943, "lr": 0.003, "grad": 0.1094, "tokens": 129949747200, "tok_s": 160422.9}
|
| 50 |
+
{"step": 123980, "epoch": 0.788, "loss": 1.73459, "ppl": 5.667, "lr": 0.003, "grad": 0.0688, "tokens": 129970713600, "tok_s": 160651.5}
|
| 51 |
+
{"step": 124000, "epoch": 0.788, "loss": 1.88859, "ppl": 6.61, "lr": 0.003, "grad": 0.1302, "tokens": 129991680000, "tok_s": 159622.6}
|
| 52 |
+
{"step": 124000, "val_loss": 1.73125, "val_ppl": 5.648, "is_best": true}
|
| 53 |
+
{"step": 124020, "epoch": 0.788, "loss": 1.7361, "ppl": 5.675, "lr": 0.003, "grad": 0.1751, "tokens": 130012646400, "tok_s": 160215.9}
|
| 54 |
+
{"step": 124040, "epoch": 0.788, "loss": 1.67665, "ppl": 5.348, "lr": 0.003, "grad": 0.0744, "tokens": 130033612800, "tok_s": 160225.5}
|
| 55 |
+
{"step": 124060, "epoch": 0.788, "loss": 1.77362, "ppl": 5.892, "lr": 0.003, "grad": 0.0898, "tokens": 130054579200, "tok_s": 160331.3}
|
| 56 |
+
{"step": 124080, "epoch": 0.788, "loss": 1.72503, "ppl": 5.613, "lr": 0.003, "grad": 0.0922, "tokens": 130075545600, "tok_s": 159702.9}
|
| 57 |
+
{"step": 124100, "epoch": 0.788, "loss": 1.59609, "ppl": 4.934, "lr": 0.003, "grad": 0.0762, "tokens": 130096512000, "tok_s": 160685.8}
|
| 58 |
+
{"step": 124120, "epoch": 0.789, "loss": 1.86891, "ppl": 6.481, "lr": 0.003, "grad": 0.1202, "tokens": 130117478400, "tok_s": 160504.1}
|
| 59 |
+
{"step": 124140, "epoch": 0.789, "loss": 1.76403, "ppl": 5.836, "lr": 0.003, "grad": 0.0684, "tokens": 130138444800, "tok_s": 160268.2}
|
| 60 |
+
{"step": 124160, "epoch": 0.789, "loss": 1.74983, "ppl": 5.754, "lr": 0.003, "grad": 0.1502, "tokens": 130159411200, "tok_s": 160689.6}
|
| 61 |
+
{"step": 124180, "epoch": 0.789, "loss": 1.79266, "ppl": 6.005, "lr": 0.003, "grad": 0.1325, "tokens": 130180377600, "tok_s": 160749.9}
|
| 62 |
+
{"step": 124200, "epoch": 0.789, "loss": 1.70712, "ppl": 5.513, "lr": 0.003, "grad": 0.1652, "tokens": 130201344000, "tok_s": 160972.2}
|
| 63 |
+
{"step": 124220, "epoch": 0.789, "loss": 1.77982, "ppl": 5.929, "lr": 0.003, "grad": 0.0863, "tokens": 130222310400, "tok_s": 159848.7}
|
| 64 |
+
{"step": 124240, "epoch": 0.789, "loss": 1.6902, "ppl": 5.421, "lr": 0.003, "grad": 0.0906, "tokens": 130243276800, "tok_s": 160423.3}
|
| 65 |
+
{"step": 124260, "epoch": 0.79, "loss": 1.72005, "ppl": 5.585, "lr": 0.003, "grad": 0.1148, "tokens": 130264243200, "tok_s": 160008.5}
|
| 66 |
+
{"step": 124280, "epoch": 0.79, "loss": 1.60375, "ppl": 4.972, "lr": 0.003, "grad": 0.0759, "tokens": 130285209600, "tok_s": 160501.4}
|
| 67 |
+
{"step": 124300, "epoch": 0.79, "loss": 1.80209, "ppl": 6.062, "lr": 0.003, "grad": 0.1022, "tokens": 130306176000, "tok_s": 160572.2}
|
| 68 |
+
{"step": 124320, "epoch": 0.79, "loss": 1.74269, "ppl": 5.713, "lr": 0.003, "grad": 0.0813, "tokens": 130327142400, "tok_s": 160189.3}
|
| 69 |
+
{"step": 124340, "epoch": 0.79, "loss": 1.79512, "ppl": 6.02, "lr": 0.003, "grad": 0.1168, "tokens": 130348108800, "tok_s": 160868.6}
|
| 70 |
+
{"step": 124360, "epoch": 0.79, "loss": 1.73415, "ppl": 5.664, "lr": 0.003, "grad": 0.0753, "tokens": 130369075200, "tok_s": 160812.7}
|
| 71 |
+
{"step": 124380, "epoch": 0.79, "loss": 1.84343, "ppl": 6.318, "lr": 0.003, "grad": 0.0912, "tokens": 130390041600, "tok_s": 160527.0}
|
| 72 |
+
{"step": 124400, "epoch": 0.79, "loss": 1.81286, "ppl": 6.128, "lr": 0.003, "grad": 0.069, "tokens": 130411008000, "tok_s": 160789.7}
|
| 73 |
+
{"step": 124420, "epoch": 0.791, "loss": 1.79391, "ppl": 6.013, "lr": 0.003, "grad": 0.0965, "tokens": 130431974400, "tok_s": 160630.4}
|
| 74 |
+
{"step": 124440, "epoch": 0.791, "loss": 1.73427, "ppl": 5.665, "lr": 0.003, "grad": 0.095, "tokens": 130452940800, "tok_s": 160278.9}
|
| 75 |
+
{"step": 124460, "epoch": 0.791, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.1166, "tokens": 130473907200, "tok_s": 159362.5}
|
| 76 |
+
{"step": 124480, "epoch": 0.791, "loss": 1.82161, "ppl": 6.182, "lr": 0.003, "grad": 0.0951, "tokens": 130494873600, "tok_s": 160482.4}
|
| 77 |
+
{"step": 124500, "epoch": 0.791, "loss": 1.77899, "ppl": 5.924, "lr": 0.003, "grad": 0.0911, "tokens": 130515840000, "tok_s": 160632.9}
|
| 78 |
+
{"step": 124520, "epoch": 0.791, "loss": 1.78569, "ppl": 5.964, "lr": 0.003, "grad": 0.1077, "tokens": 130536806400, "tok_s": 160596.3}
|
| 79 |
+
{"step": 124540, "epoch": 0.791, "loss": 1.7094, "ppl": 5.526, "lr": 0.003, "grad": 0.0913, "tokens": 130557772800, "tok_s": 160800.8}
|
| 80 |
+
{"step": 124560, "epoch": 0.791, "loss": 1.79031, "ppl": 5.991, "lr": 0.003, "grad": 0.1412, "tokens": 130578739200, "tok_s": 160067.8}
|
| 81 |
+
{"step": 124580, "epoch": 0.792, "loss": 1.59144, "ppl": 4.911, "lr": 0.003, "grad": 0.0821, "tokens": 130599705600, "tok_s": 160693.3}
|
| 82 |
+
{"step": 124600, "epoch": 0.792, "loss": 1.76647, "ppl": 5.85, "lr": 0.003, "grad": 0.1521, "tokens": 130620672000, "tok_s": 160653.0}
|
| 83 |
+
{"step": 124620, "epoch": 0.792, "loss": 1.76625, "ppl": 5.849, "lr": 0.003, "grad": 0.089, "tokens": 130641638400, "tok_s": 159971.8}
|
| 84 |
+
{"step": 124640, "epoch": 0.792, "loss": 1.73058, "ppl": 5.644, "lr": 0.003, "grad": 0.1279, "tokens": 130662604800, "tok_s": 160512.9}
|
| 85 |
+
{"step": 124660, "epoch": 0.792, "loss": 1.78411, "ppl": 5.954, "lr": 0.003, "grad": 0.0948, "tokens": 130683571200, "tok_s": 160282.8}
|
| 86 |
+
{"step": 124680, "epoch": 0.792, "loss": 1.7574, "ppl": 5.797, "lr": 0.003, "grad": 0.0869, "tokens": 130704537600, "tok_s": 160624.5}
|
| 87 |
+
{"step": 124700, "epoch": 0.792, "loss": 1.72977, "ppl": 5.639, "lr": 0.003, "grad": 0.0889, "tokens": 130725504000, "tok_s": 160538.3}
|
| 88 |
+
{"step": 124720, "epoch": 0.792, "loss": 1.70746, "ppl": 5.515, "lr": 0.003, "grad": 0.0753, "tokens": 130746470400, "tok_s": 160834.9}
|
| 89 |
+
{"step": 124740, "epoch": 0.793, "loss": 1.74636, "ppl": 5.734, "lr": 0.003, "grad": 0.1024, "tokens": 130767436800, "tok_s": 160732.6}
|
| 90 |
+
{"step": 124760, "epoch": 0.793, "loss": 1.63906, "ppl": 5.15, "lr": 0.003, "grad": 0.0647, "tokens": 130788403200, "tok_s": 160648.6}
|
| 91 |
+
{"step": 124780, "epoch": 0.793, "loss": 1.71628, "ppl": 5.564, "lr": 0.003, "grad": 0.1116, "tokens": 130809369600, "tok_s": 160459.3}
|
| 92 |
+
{"step": 124800, "epoch": 0.793, "loss": 1.74014, "ppl": 5.698, "lr": 0.003, "grad": 0.0762, "tokens": 130830336000, "tok_s": 160779.2}
|
| 93 |
+
{"step": 124820, "epoch": 0.793, "loss": 1.76257, "ppl": 5.827, "lr": 0.003, "grad": 0.1096, "tokens": 130851302400, "tok_s": 160502.2}
|
| 94 |
+
{"step": 124840, "epoch": 0.793, "loss": 1.77835, "ppl": 5.92, "lr": 0.003, "grad": 0.1063, "tokens": 130872268800, "tok_s": 160316.6}
|
| 95 |
+
{"step": 124860, "epoch": 0.793, "loss": 1.78944, "ppl": 5.986, "lr": 0.003, "grad": 0.0601, "tokens": 130893235200, "tok_s": 160541.8}
|
| 96 |
+
{"step": 124880, "epoch": 0.793, "loss": 1.76928, "ppl": 5.867, "lr": 0.003, "grad": 0.1254, "tokens": 130914201600, "tok_s": 160654.0}
|
| 97 |
+
{"step": 124900, "epoch": 0.794, "loss": 1.75305, "ppl": 5.772, "lr": 0.003, "grad": 0.0925, "tokens": 130935168000, "tok_s": 160492.8}
|
| 98 |
+
{"step": 124920, "epoch": 0.794, "loss": 1.77743, "ppl": 5.915, "lr": 0.003, "grad": 0.1285, "tokens": 130956134400, "tok_s": 160781.2}
|
| 99 |
+
{"step": 124940, "epoch": 0.794, "loss": 1.72792, "ppl": 5.629, "lr": 0.003, "grad": 0.0794, "tokens": 130977100800, "tok_s": 160778.9}
|
| 100 |
+
{"step": 124960, "epoch": 0.794, "loss": 1.74981, "ppl": 5.753, "lr": 0.003, "grad": 0.1085, "tokens": 130998067200, "tok_s": 159891.1}
|
| 101 |
+
{"step": 124980, "epoch": 0.794, "loss": 1.79698, "ppl": 6.031, "lr": 0.003, "grad": 0.1132, "tokens": 131019033600, "tok_s": 160698.3}
|
| 102 |
+
{"step": 125000, "epoch": 0.794, "loss": 1.72512, "ppl": 5.613, "lr": 0.003, "grad": 0.0803, "tokens": 131040000000, "tok_s": 160280.6}
|
| 103 |
+
{"step": 125000, "val_loss": 1.74215, "val_ppl": 5.71, "is_best": false}
|
| 104 |
+
{"step": 125020, "epoch": 0.794, "loss": 1.76033, "ppl": 5.814, "lr": 0.003, "grad": 0.1208, "tokens": 131060966400, "tok_s": 160517.3}
|
| 105 |
+
{"step": 125040, "epoch": 0.794, "loss": 1.74821, "ppl": 5.744, "lr": 0.003, "grad": 0.1219, "tokens": 131081932800, "tok_s": 160743.6}
|
| 106 |
+
{"step": 125060, "epoch": 0.795, "loss": 1.69473, "ppl": 5.445, "lr": 0.003, "grad": 0.0884, "tokens": 131102899200, "tok_s": 160707.3}
|
| 107 |
+
{"step": 125080, "epoch": 0.795, "loss": 1.76494, "ppl": 5.841, "lr": 0.003, "grad": 0.1146, "tokens": 131123865600, "tok_s": 160535.1}
|
| 108 |
+
{"step": 125100, "epoch": 0.795, "loss": 1.7554, "ppl": 5.786, "lr": 0.003, "grad": 0.1027, "tokens": 131144832000, "tok_s": 160837.8}
|
| 109 |
+
{"step": 125120, "epoch": 0.795, "loss": 1.82843, "ppl": 6.224, "lr": 0.003, "grad": 0.0815, "tokens": 131165798400, "tok_s": 159815.0}
|
| 110 |
+
{"step": 125140, "epoch": 0.795, "loss": 1.76921, "ppl": 5.866, "lr": 0.003, "grad": 0.1131, "tokens": 131186764800, "tok_s": 160652.4}
|
| 111 |
+
{"step": 125160, "epoch": 0.795, "loss": 1.72331, "ppl": 5.603, "lr": 0.003, "grad": 0.1504, "tokens": 131207731200, "tok_s": 160288.6}
|
| 112 |
+
{"step": 125180, "epoch": 0.795, "loss": 1.74794, "ppl": 5.743, "lr": 0.003, "grad": 0.0825, "tokens": 131228697600, "tok_s": 160590.8}
|
| 113 |
+
{"step": 125200, "epoch": 0.795, "loss": 1.80309, "ppl": 6.068, "lr": 0.003, "grad": 0.1297, "tokens": 131249664000, "tok_s": 160013.0}
|
| 114 |
+
{"step": 125220, "epoch": 0.796, "loss": 1.70651, "ppl": 5.51, "lr": 0.003, "grad": 0.074, "tokens": 131270630400, "tok_s": 160896.4}
|
| 115 |
+
{"step": 125240, "epoch": 0.796, "loss": 1.75076, "ppl": 5.759, "lr": 0.003, "grad": 0.1105, "tokens": 131291596800, "tok_s": 160396.9}
|
| 116 |
+
{"step": 125260, "epoch": 0.796, "loss": 1.66345, "ppl": 5.277, "lr": 0.003, "grad": 0.087, "tokens": 131312563200, "tok_s": 160563.1}
|
| 117 |
+
{"step": 125280, "epoch": 0.796, "loss": 1.76143, "ppl": 5.821, "lr": 0.003, "grad": 0.0767, "tokens": 131333529600, "tok_s": 160747.0}
|
| 118 |
+
{"step": 125300, "epoch": 0.796, "loss": 1.78602, "ppl": 5.966, "lr": 0.003, "grad": 0.0902, "tokens": 131354496000, "tok_s": 160934.3}
|
| 119 |
+
{"step": 125320, "epoch": 0.796, "loss": 1.66687, "ppl": 5.296, "lr": 0.003, "grad": 0.0875, "tokens": 131375462400, "tok_s": 159971.8}
|
| 120 |
+
{"step": 125340, "epoch": 0.796, "loss": 1.63117, "ppl": 5.11, "lr": 0.003, "grad": 0.1239, "tokens": 131396428800, "tok_s": 160658.5}
|
| 121 |
+
{"step": 125360, "epoch": 0.796, "loss": 1.75845, "ppl": 5.803, "lr": 0.003, "grad": 0.1208, "tokens": 131417395200, "tok_s": 160151.0}
|
| 122 |
+
{"step": 125380, "epoch": 0.797, "loss": 1.73367, "ppl": 5.661, "lr": 0.003, "grad": 0.0954, "tokens": 131438361600, "tok_s": 160160.2}
|
| 123 |
+
{"step": 125400, "epoch": 0.797, "loss": 1.64819, "ppl": 5.198, "lr": 0.003, "grad": 0.0774, "tokens": 131459328000, "tok_s": 160193.9}
|
| 124 |
+
{"step": 125420, "epoch": 0.797, "loss": 1.66598, "ppl": 5.291, "lr": 0.003, "grad": 0.0986, "tokens": 131480294400, "tok_s": 160053.9}
|
| 125 |
+
{"step": 125440, "epoch": 0.797, "loss": 1.8541, "ppl": 6.386, "lr": 0.003, "grad": 0.1272, "tokens": 131501260800, "tok_s": 160350.0}
|
| 126 |
+
{"step": 125460, "epoch": 0.797, "loss": 1.64714, "ppl": 5.192, "lr": 0.003, "grad": 0.0725, "tokens": 131522227200, "tok_s": 160129.8}
|
| 127 |
+
{"step": 125480, "epoch": 0.797, "loss": 1.7242, "ppl": 5.608, "lr": 0.003, "grad": 0.0687, "tokens": 131543193600, "tok_s": 160611.9}
|
| 128 |
+
{"step": 125500, "epoch": 0.797, "loss": 1.6994, "ppl": 5.471, "lr": 0.003, "grad": 0.1098, "tokens": 131564160000, "tok_s": 160332.7}
|
| 129 |
+
{"step": 125520, "epoch": 0.798, "loss": 1.71202, "ppl": 5.54, "lr": 0.003, "grad": 0.0632, "tokens": 131585126400, "tok_s": 160815.6}
|
| 130 |
+
{"step": 125540, "epoch": 0.798, "loss": 1.71523, "ppl": 5.558, "lr": 0.003, "grad": 0.0566, "tokens": 131606092800, "tok_s": 160783.7}
|
| 131 |
+
{"step": 125560, "epoch": 0.798, "loss": 1.81274, "ppl": 6.127, "lr": 0.003, "grad": 0.1067, "tokens": 131627059200, "tok_s": 160811.5}
|
| 132 |
+
{"step": 125580, "epoch": 0.798, "loss": 1.74317, "ppl": 5.715, "lr": 0.003, "grad": 0.1306, "tokens": 131648025600, "tok_s": 160707.5}
|
| 133 |
+
{"step": 125600, "epoch": 0.798, "loss": 1.77451, "ppl": 5.897, "lr": 0.003, "grad": 0.0825, "tokens": 131668992000, "tok_s": 160758.1}
|
| 134 |
+
{"step": 125620, "epoch": 0.798, "loss": 1.73877, "ppl": 5.69, "lr": 0.003, "grad": 0.082, "tokens": 131689958400, "tok_s": 160627.5}
|
| 135 |
+
{"step": 125640, "epoch": 0.798, "loss": 1.77622, "ppl": 5.907, "lr": 0.003, "grad": 0.1201, "tokens": 131710924800, "tok_s": 160920.4}
|
| 136 |
+
{"step": 125660, "epoch": 0.798, "loss": 1.64526, "ppl": 5.182, "lr": 0.003, "grad": 0.1084, "tokens": 131731891200, "tok_s": 160624.3}
|
| 137 |
+
{"step": 125680, "epoch": 0.799, "loss": 1.73881, "ppl": 5.691, "lr": 0.003, "grad": 0.1094, "tokens": 131752857600, "tok_s": 160666.0}
|
| 138 |
+
{"step": 125700, "epoch": 0.799, "loss": 1.69768, "ppl": 5.461, "lr": 0.003, "grad": 0.1167, "tokens": 131773824000, "tok_s": 160761.8}
|
| 139 |
+
{"step": 125720, "epoch": 0.799, "loss": 1.78497, "ppl": 5.959, "lr": 0.003, "grad": 0.1092, "tokens": 131794790400, "tok_s": 160875.4}
|
| 140 |
+
{"step": 125740, "epoch": 0.799, "loss": 1.60774, "ppl": 4.992, "lr": 0.003, "grad": 0.092, "tokens": 131815756800, "tok_s": 160801.6}
|
| 141 |
+
{"step": 125760, "epoch": 0.799, "loss": 1.77716, "ppl": 5.913, "lr": 0.003, "grad": 0.0894, "tokens": 131836723200, "tok_s": 160699.4}
|
| 142 |
+
{"step": 125780, "epoch": 0.799, "loss": 1.78281, "ppl": 5.947, "lr": 0.003, "grad": 0.1028, "tokens": 131857689600, "tok_s": 160806.4}
|
| 143 |
+
{"step": 125800, "epoch": 0.799, "loss": 1.75767, "ppl": 5.799, "lr": 0.003, "grad": 0.0783, "tokens": 131878656000, "tok_s": 160736.4}
|
| 144 |
+
{"step": 125820, "epoch": 0.799, "loss": 1.77649, "ppl": 5.909, "lr": 0.003, "grad": 0.0951, "tokens": 131899622400, "tok_s": 160778.6}
|
| 145 |
+
{"step": 125840, "epoch": 0.8, "loss": 1.77938, "ppl": 5.926, "lr": 0.003, "grad": 0.1144, "tokens": 131920588800, "tok_s": 160968.2}
|
| 146 |
+
{"step": 125860, "epoch": 0.8, "loss": 1.80196, "ppl": 6.062, "lr": 0.003, "grad": 0.1349, "tokens": 131941555200, "tok_s": 160726.0}
|
| 147 |
+
{"step": 125880, "epoch": 0.8, "loss": 1.71563, "ppl": 5.56, "lr": 0.003, "grad": 0.095, "tokens": 131962521600, "tok_s": 160731.7}
|
| 148 |
+
{"step": 125900, "epoch": 0.8, "loss": 1.76961, "ppl": 5.869, "lr": 0.003, "grad": 0.1057, "tokens": 131983488000, "tok_s": 160875.8}
|
| 149 |
+
{"step": 125920, "epoch": 0.8, "loss": 1.76717, "ppl": 5.854, "lr": 0.003, "grad": 0.0702, "tokens": 132004454400, "tok_s": 160778.1}
|
| 150 |
+
{"step": 125940, "epoch": 0.8, "loss": 1.73329, "ppl": 5.659, "lr": 0.003, "grad": 0.1034, "tokens": 132025420800, "tok_s": 160384.4}
|
| 151 |
+
{"step": 125960, "epoch": 0.8, "loss": 1.78953, "ppl": 5.987, "lr": 0.003, "grad": 0.082, "tokens": 132046387200, "tok_s": 160727.7}
|
| 152 |
+
{"step": 125980, "epoch": 0.8, "loss": 1.76174, "ppl": 5.823, "lr": 0.003, "grad": 0.1295, "tokens": 132067353600, "tok_s": 160876.9}
|
| 153 |
+
{"step": 126000, "epoch": 0.801, "loss": 1.76653, "ppl": 5.85, "lr": 0.003, "grad": 0.1551, "tokens": 132088320000, "tok_s": 160715.0}
|
| 154 |
+
{"step": 126000, "val_loss": 1.74991, "val_ppl": 5.754, "is_best": false}
|
| 155 |
+
{"step": 126020, "epoch": 0.801, "loss": 1.69758, "ppl": 5.461, "lr": 0.003, "grad": 0.0926, "tokens": 132109286400, "tok_s": 160773.8}
|
| 156 |
+
{"step": 126040, "epoch": 0.801, "loss": 1.75444, "ppl": 5.78, "lr": 0.003, "grad": 0.0992, "tokens": 132130252800, "tok_s": 160821.1}
|
| 157 |
+
{"step": 126060, "epoch": 0.801, "loss": 1.73691, "ppl": 5.68, "lr": 0.003, "grad": 0.1107, "tokens": 132151219200, "tok_s": 160868.3}
|
| 158 |
+
{"step": 126080, "epoch": 0.801, "loss": 1.77811, "ppl": 5.919, "lr": 0.003, "grad": 0.1458, "tokens": 132172185600, "tok_s": 160908.9}
|
| 159 |
+
{"step": 126100, "epoch": 0.801, "loss": 1.77404, "ppl": 5.895, "lr": 0.003, "grad": 0.0837, "tokens": 132193152000, "tok_s": 160594.2}
|
| 160 |
+
{"step": 126120, "epoch": 0.801, "loss": 1.7408, "ppl": 5.702, "lr": 0.003, "grad": 0.1212, "tokens": 132214118400, "tok_s": 160877.0}
|
| 161 |
+
{"step": 126140, "epoch": 0.801, "loss": 1.72606, "ppl": 5.618, "lr": 0.003, "grad": 0.0992, "tokens": 132235084800, "tok_s": 160598.3}
|
| 162 |
+
{"step": 126160, "epoch": 0.802, "loss": 1.73635, "ppl": 5.677, "lr": 0.003, "grad": 0.0989, "tokens": 132256051200, "tok_s": 160405.1}
|
| 163 |
+
{"step": 126180, "epoch": 0.802, "loss": 1.68267, "ppl": 5.38, "lr": 0.003, "grad": 0.1019, "tokens": 132277017600, "tok_s": 160378.1}
|
| 164 |
+
{"step": 126200, "epoch": 0.802, "loss": 1.74384, "ppl": 5.719, "lr": 0.003, "grad": 0.1051, "tokens": 132297984000, "tok_s": 160807.2}
|
| 165 |
+
{"step": 126220, "epoch": 0.802, "loss": 1.73014, "ppl": 5.641, "lr": 0.003, "grad": 0.1541, "tokens": 132318950400, "tok_s": 160839.3}
|
| 166 |
+
{"step": 126240, "epoch": 0.802, "loss": 1.73399, "ppl": 5.663, "lr": 0.003, "grad": 0.1039, "tokens": 132339916800, "tok_s": 160368.3}
|
| 167 |
+
{"step": 126260, "epoch": 0.802, "loss": 1.74648, "ppl": 5.734, "lr": 0.003, "grad": 0.0941, "tokens": 132360883200, "tok_s": 160590.1}
|
| 168 |
+
{"step": 126280, "epoch": 0.802, "loss": 1.77031, "ppl": 5.873, "lr": 0.003, "grad": 0.0798, "tokens": 132381849600, "tok_s": 160842.0}
|
| 169 |
+
{"step": 126300, "epoch": 0.802, "loss": 1.82219, "ppl": 6.185, "lr": 0.003, "grad": 0.0945, "tokens": 132402816000, "tok_s": 160908.6}
|
| 170 |
+
{"step": 126320, "epoch": 0.803, "loss": 1.72436, "ppl": 5.609, "lr": 0.003, "grad": 0.1298, "tokens": 132423782400, "tok_s": 160699.5}
|
| 171 |
+
{"step": 126340, "epoch": 0.803, "loss": 1.75298, "ppl": 5.772, "lr": 0.003, "grad": 0.1049, "tokens": 132444748800, "tok_s": 160776.4}
|
| 172 |
+
{"step": 126360, "epoch": 0.803, "loss": 1.74143, "ppl": 5.705, "lr": 0.003, "grad": 0.1052, "tokens": 132465715200, "tok_s": 160881.9}
|
| 173 |
+
{"step": 126380, "epoch": 0.803, "loss": 1.69539, "ppl": 5.449, "lr": 0.003, "grad": 0.122, "tokens": 132486681600, "tok_s": 160739.3}
|
| 174 |
+
{"step": 126400, "epoch": 0.803, "loss": 1.7148, "ppl": 5.556, "lr": 0.003, "grad": 0.1499, "tokens": 132507648000, "tok_s": 160947.8}
|
| 175 |
+
{"step": 126420, "epoch": 0.803, "loss": 1.74067, "ppl": 5.701, "lr": 0.003, "grad": 0.1329, "tokens": 132528614400, "tok_s": 160898.9}
|
| 176 |
+
{"step": 126440, "epoch": 0.803, "loss": 1.72883, "ppl": 5.634, "lr": 0.003, "grad": 0.1075, "tokens": 132549580800, "tok_s": 160766.4}
|
| 177 |
+
{"step": 126460, "epoch": 0.803, "loss": 1.74148, "ppl": 5.706, "lr": 0.003, "grad": 0.0728, "tokens": 132570547200, "tok_s": 160702.9}
|
| 178 |
+
{"step": 126480, "epoch": 0.804, "loss": 1.65406, "ppl": 5.228, "lr": 0.003, "grad": 0.0854, "tokens": 132591513600, "tok_s": 160717.1}
|
| 179 |
+
{"step": 126500, "epoch": 0.804, "loss": 1.86413, "ppl": 6.45, "lr": 0.003, "grad": 0.137, "tokens": 132612480000, "tok_s": 160885.4}
|
| 180 |
+
{"step": 126520, "epoch": 0.804, "loss": 1.79083, "ppl": 5.994, "lr": 0.003, "grad": 0.0864, "tokens": 132633446400, "tok_s": 160726.3}
|
| 181 |
+
{"step": 126540, "epoch": 0.804, "loss": 1.69603, "ppl": 5.452, "lr": 0.003, "grad": 0.0653, "tokens": 132654412800, "tok_s": 160595.0}
|
| 182 |
+
{"step": 126560, "epoch": 0.804, "loss": 1.84869, "ppl": 6.351, "lr": 0.003, "grad": 0.1031, "tokens": 132675379200, "tok_s": 160760.5}
|
| 183 |
+
{"step": 126580, "epoch": 0.804, "loss": 1.73397, "ppl": 5.663, "lr": 0.003, "grad": 0.0941, "tokens": 132696345600, "tok_s": 160939.5}
|
| 184 |
+
{"step": 126600, "epoch": 0.804, "loss": 1.82054, "ppl": 6.175, "lr": 0.003, "grad": 0.1074, "tokens": 132717312000, "tok_s": 160769.9}
|
| 185 |
+
{"step": 126620, "epoch": 0.804, "loss": 1.73808, "ppl": 5.686, "lr": 0.003, "grad": 0.1278, "tokens": 132738278400, "tok_s": 160636.4}
|
| 186 |
+
{"step": 126640, "epoch": 0.805, "loss": 1.75373, "ppl": 5.776, "lr": 0.003, "grad": 0.1032, "tokens": 132759244800, "tok_s": 160776.6}
|
| 187 |
+
{"step": 126660, "epoch": 0.805, "loss": 1.63663, "ppl": 5.138, "lr": 0.003, "grad": 0.0948, "tokens": 132780211200, "tok_s": 160296.1}
|
| 188 |
+
{"step": 126680, "epoch": 0.805, "loss": 1.46989, "ppl": 4.349, "lr": 0.003, "grad": 0.1914, "tokens": 132801177600, "tok_s": 160768.9}
|
| 189 |
+
{"step": 126700, "epoch": 0.805, "loss": 1.80131, "ppl": 6.058, "lr": 0.003, "grad": 0.0968, "tokens": 132822144000, "tok_s": 160553.8}
|
| 190 |
+
{"step": 126720, "epoch": 0.805, "loss": 1.70179, "ppl": 5.484, "lr": 0.003, "grad": 0.1178, "tokens": 132843110400, "tok_s": 160809.0}
|
| 191 |
+
{"step": 126740, "epoch": 0.805, "loss": 1.71646, "ppl": 5.565, "lr": 0.003, "grad": 0.1215, "tokens": 132864076800, "tok_s": 160608.5}
|
| 192 |
+
{"step": 126760, "epoch": 0.805, "loss": 1.74311, "ppl": 5.715, "lr": 0.003, "grad": 0.0742, "tokens": 132885043200, "tok_s": 160699.2}
|
| 193 |
+
{"step": 126780, "epoch": 0.806, "loss": 1.70769, "ppl": 5.516, "lr": 0.003, "grad": 0.1247, "tokens": 132906009600, "tok_s": 160496.8}
|
| 194 |
+
{"step": 126800, "epoch": 0.806, "loss": 1.76602, "ppl": 5.848, "lr": 0.003, "grad": 0.1098, "tokens": 132926976000, "tok_s": 160575.2}
|
| 195 |
+
{"step": 126820, "epoch": 0.806, "loss": 1.74984, "ppl": 5.754, "lr": 0.003, "grad": 0.1587, "tokens": 132947942400, "tok_s": 160515.9}
|
| 196 |
+
{"step": 126840, "epoch": 0.806, "loss": 1.76474, "ppl": 5.84, "lr": 0.003, "grad": 0.1143, "tokens": 132968908800, "tok_s": 160570.5}
|
| 197 |
+
{"step": 126860, "epoch": 0.806, "loss": 1.74005, "ppl": 5.698, "lr": 0.003, "grad": 0.1492, "tokens": 132989875200, "tok_s": 160764.3}
|
| 198 |
+
{"step": 126880, "epoch": 0.806, "loss": 1.74436, "ppl": 5.722, "lr": 0.003, "grad": 0.0882, "tokens": 133010841600, "tok_s": 160761.4}
|
| 199 |
+
{"step": 126900, "epoch": 0.806, "loss": 1.73074, "ppl": 5.645, "lr": 0.003, "grad": 0.0589, "tokens": 133031808000, "tok_s": 160736.3}
|
| 200 |
+
{"step": 126920, "epoch": 0.806, "loss": 1.73084, "ppl": 5.645, "lr": 0.003, "grad": 0.1323, "tokens": 133052774400, "tok_s": 160636.1}
|
| 201 |
+
{"step": 126940, "epoch": 0.807, "loss": 1.73858, "ppl": 5.689, "lr": 0.003, "grad": 0.147, "tokens": 133073740800, "tok_s": 160651.5}
|
| 202 |
+
{"step": 126960, "epoch": 0.807, "loss": 1.76887, "ppl": 5.864, "lr": 0.003, "grad": 0.0971, "tokens": 133094707200, "tok_s": 160718.8}
|
| 203 |
+
{"step": 126980, "epoch": 0.807, "loss": 1.73789, "ppl": 5.685, "lr": 0.003, "grad": 0.1209, "tokens": 133115673600, "tok_s": 160883.7}
|
| 204 |
+
{"step": 127000, "epoch": 0.807, "loss": 1.76703, "ppl": 5.853, "lr": 0.003, "grad": 0.1307, "tokens": 133136640000, "tok_s": 160722.0}
|
| 205 |
+
{"step": 127000, "val_loss": 1.74954, "val_ppl": 5.752, "is_best": false}
|
| 206 |
+
{"step": 127020, "epoch": 0.807, "loss": 1.71579, "ppl": 5.561, "lr": 0.003, "grad": 0.102, "tokens": 133157606400, "tok_s": 160766.1}
|
| 207 |
+
{"step": 127040, "epoch": 0.807, "loss": 1.77087, "ppl": 5.876, "lr": 0.003, "grad": 0.0898, "tokens": 133178572800, "tok_s": 160680.0}
|
| 208 |
+
{"step": 127060, "epoch": 0.807, "loss": 1.71844, "ppl": 5.576, "lr": 0.003, "grad": 0.0975, "tokens": 133199539200, "tok_s": 160644.6}
|
| 209 |
+
{"step": 127080, "epoch": 0.807, "loss": 1.78155, "ppl": 5.939, "lr": 0.003, "grad": 0.1483, "tokens": 133220505600, "tok_s": 160604.4}
|
| 210 |
+
{"step": 127100, "epoch": 0.808, "loss": 1.75617, "ppl": 5.79, "lr": 0.003, "grad": 0.1597, "tokens": 133241472000, "tok_s": 160749.7}
|
| 211 |
+
{"step": 127120, "epoch": 0.808, "loss": 1.77712, "ppl": 5.913, "lr": 0.003, "grad": 0.1027, "tokens": 133262438400, "tok_s": 160905.2}
|
| 212 |
+
{"step": 127140, "epoch": 0.808, "loss": 1.71541, "ppl": 5.559, "lr": 0.003, "grad": 0.1281, "tokens": 133283404800, "tok_s": 160795.6}
|
| 213 |
+
{"step": 127160, "epoch": 0.808, "loss": 1.75601, "ppl": 5.789, "lr": 0.003, "grad": 0.1017, "tokens": 133304371200, "tok_s": 160512.0}
|
| 214 |
+
{"step": 127180, "epoch": 0.808, "loss": 1.76761, "ppl": 5.857, "lr": 0.003, "grad": 0.1163, "tokens": 133325337600, "tok_s": 160617.4}
|
| 215 |
+
{"step": 127200, "epoch": 0.808, "loss": 1.79759, "ppl": 6.035, "lr": 0.003, "grad": 0.0861, "tokens": 133346304000, "tok_s": 160649.9}
|
| 216 |
+
{"step": 127220, "epoch": 0.808, "loss": 1.79177, "ppl": 6.0, "lr": 0.003, "grad": 0.1538, "tokens": 133367270400, "tok_s": 160278.2}
|
| 217 |
+
{"step": 127240, "epoch": 0.808, "loss": 1.76259, "ppl": 5.828, "lr": 0.003, "grad": 0.0611, "tokens": 133388236800, "tok_s": 160633.6}
|
| 218 |
+
{"step": 127260, "epoch": 0.809, "loss": 1.71993, "ppl": 5.584, "lr": 0.003, "grad": 0.0778, "tokens": 133409203200, "tok_s": 160828.5}
|
| 219 |
+
{"step": 127280, "epoch": 0.809, "loss": 1.80326, "ppl": 6.069, "lr": 0.003, "grad": 0.1167, "tokens": 133430169600, "tok_s": 160539.9}
|
| 220 |
+
{"step": 127300, "epoch": 0.809, "loss": 1.77138, "ppl": 5.879, "lr": 0.003, "grad": 0.1078, "tokens": 133451136000, "tok_s": 160149.2}
|
| 221 |
+
{"step": 127320, "epoch": 0.809, "loss": 1.71873, "ppl": 5.577, "lr": 0.003, "grad": 0.0965, "tokens": 133472102400, "tok_s": 159725.7}
|
| 222 |
+
{"step": 127340, "epoch": 0.809, "loss": 1.77756, "ppl": 5.915, "lr": 0.003, "grad": 0.0985, "tokens": 133493068800, "tok_s": 160079.5}
|
| 223 |
+
{"step": 127360, "epoch": 0.809, "loss": 1.71584, "ppl": 5.561, "lr": 0.003, "grad": 0.0905, "tokens": 133514035200, "tok_s": 160626.0}
|
| 224 |
+
{"step": 127380, "epoch": 0.809, "loss": 1.76355, "ppl": 5.833, "lr": 0.003, "grad": 0.1103, "tokens": 133535001600, "tok_s": 160364.2}
|
| 225 |
+
{"step": 127400, "epoch": 0.809, "loss": 1.64867, "ppl": 5.2, "lr": 0.003, "grad": 0.0974, "tokens": 133555968000, "tok_s": 160454.0}
|
| 226 |
+
{"step": 127420, "epoch": 0.81, "loss": 1.75716, "ppl": 5.796, "lr": 0.003, "grad": 0.1482, "tokens": 133576934400, "tok_s": 160848.7}
|
| 227 |
+
{"step": 127440, "epoch": 0.81, "loss": 1.75484, "ppl": 5.783, "lr": 0.003, "grad": 0.1026, "tokens": 133597900800, "tok_s": 160479.9}
|
| 228 |
+
{"step": 127460, "epoch": 0.81, "loss": 1.76275, "ppl": 5.828, "lr": 0.003, "grad": 0.1338, "tokens": 133618867200, "tok_s": 160800.3}
|
| 229 |
+
{"step": 127480, "epoch": 0.81, "loss": 1.91545, "ppl": 6.79, "lr": 0.003, "grad": 0.1262, "tokens": 133639833600, "tok_s": 160676.1}
|
| 230 |
+
{"step": 127500, "epoch": 0.81, "loss": 1.794, "ppl": 6.013, "lr": 0.003, "grad": 0.1437, "tokens": 133660800000, "tok_s": 160438.4}
|
| 231 |
+
{"step": 127520, "epoch": 0.81, "loss": 1.7449, "ppl": 5.725, "lr": 0.003, "grad": 0.0922, "tokens": 133681766400, "tok_s": 160435.7}
|
| 232 |
+
{"step": 127540, "epoch": 0.81, "loss": 1.73878, "ppl": 5.69, "lr": 0.003, "grad": 0.1031, "tokens": 133702732800, "tok_s": 160324.9}
|
| 233 |
+
{"step": 127560, "epoch": 0.81, "loss": 1.80916, "ppl": 6.105, "lr": 0.003, "grad": 0.13, "tokens": 133723699200, "tok_s": 159754.0}
|
| 234 |
+
{"step": 127580, "epoch": 0.811, "loss": 1.72088, "ppl": 5.589, "lr": 0.003, "grad": 0.1295, "tokens": 133744665600, "tok_s": 159800.5}
|
| 235 |
+
{"step": 127600, "epoch": 0.811, "loss": 1.75382, "ppl": 5.777, "lr": 0.003, "grad": 0.0752, "tokens": 133765632000, "tok_s": 160349.6}
|
| 236 |
+
{"step": 127620, "epoch": 0.811, "loss": 1.76942, "ppl": 5.867, "lr": 0.003, "grad": 0.1343, "tokens": 133786598400, "tok_s": 160526.8}
|
| 237 |
+
{"step": 127640, "epoch": 0.811, "loss": 1.74053, "ppl": 5.7, "lr": 0.003, "grad": 0.1066, "tokens": 133807564800, "tok_s": 160317.6}
|
| 238 |
+
{"step": 127660, "epoch": 0.811, "loss": 1.71334, "ppl": 5.547, "lr": 0.003, "grad": 0.1572, "tokens": 133828531200, "tok_s": 160039.8}
|
| 239 |
+
{"step": 127680, "epoch": 0.811, "loss": 1.7977, "ppl": 6.036, "lr": 0.003, "grad": 0.0828, "tokens": 133849497600, "tok_s": 160702.9}
|
| 240 |
+
{"step": 127700, "epoch": 0.811, "loss": 1.71036, "ppl": 5.531, "lr": 0.003, "grad": 0.141, "tokens": 133870464000, "tok_s": 160307.8}
|
| 241 |
+
{"step": 127720, "epoch": 0.811, "loss": 1.7398, "ppl": 5.696, "lr": 0.003, "grad": 0.1005, "tokens": 133891430400, "tok_s": 160200.0}
|
| 242 |
+
{"step": 127740, "epoch": 0.812, "loss": 1.7658, "ppl": 5.846, "lr": 0.003, "grad": 0.141, "tokens": 133912396800, "tok_s": 160177.9}
|
| 243 |
+
{"step": 127760, "epoch": 0.812, "loss": 1.77974, "ppl": 5.928, "lr": 0.003, "grad": 0.1217, "tokens": 133933363200, "tok_s": 159698.8}
|
| 244 |
+
{"step": 127780, "epoch": 0.812, "loss": 1.7341, "ppl": 5.664, "lr": 0.003, "grad": 0.1014, "tokens": 133954329600, "tok_s": 160135.3}
|
| 245 |
+
{"step": 127800, "epoch": 0.812, "loss": 1.76945, "ppl": 5.868, "lr": 0.003, "grad": 0.1303, "tokens": 133975296000, "tok_s": 160387.4}
|
| 246 |
+
{"step": 127820, "epoch": 0.812, "loss": 1.70424, "ppl": 5.497, "lr": 0.003, "grad": 0.0919, "tokens": 133996262400, "tok_s": 160082.2}
|
| 247 |
+
{"step": 127840, "epoch": 0.812, "loss": 1.74908, "ppl": 5.749, "lr": 0.003, "grad": 0.0998, "tokens": 134017228800, "tok_s": 160647.0}
|
| 248 |
+
{"step": 127860, "epoch": 0.812, "loss": 1.75608, "ppl": 5.79, "lr": 0.003, "grad": 0.0981, "tokens": 134038195200, "tok_s": 160741.8}
|
| 249 |
+
{"step": 127880, "epoch": 0.813, "loss": 1.66695, "ppl": 5.296, "lr": 0.003, "grad": 0.1051, "tokens": 134059161600, "tok_s": 160717.6}
|
| 250 |
+
{"step": 127900, "epoch": 0.813, "loss": 1.75347, "ppl": 5.775, "lr": 0.003, "grad": 0.1086, "tokens": 134080128000, "tok_s": 160835.0}
|
| 251 |
+
{"step": 127920, "epoch": 0.813, "loss": 1.7374, "ppl": 5.683, "lr": 0.003, "grad": 0.1161, "tokens": 134101094400, "tok_s": 160739.6}
|
| 252 |
+
{"step": 127940, "epoch": 0.813, "loss": 1.72691, "ppl": 5.623, "lr": 0.003, "grad": 0.0864, "tokens": 134122060800, "tok_s": 160788.3}
|
| 253 |
+
{"step": 127960, "epoch": 0.813, "loss": 1.69924, "ppl": 5.47, "lr": 0.003, "grad": 0.098, "tokens": 134143027200, "tok_s": 160634.9}
|
| 254 |
+
{"step": 127980, "epoch": 0.813, "loss": 1.7638, "ppl": 5.835, "lr": 0.003, "grad": 0.0866, "tokens": 134163993600, "tok_s": 160787.1}
|
| 255 |
+
{"step": 128000, "epoch": 0.813, "loss": 1.78116, "ppl": 5.937, "lr": 0.003, "grad": 0.1388, "tokens": 134184960000, "tok_s": 160974.9}
|
| 256 |
+
{"step": 128000, "val_loss": 1.7506, "val_ppl": 5.758, "is_best": false}
|
logs/log_129000.jsonl
ADDED
|
@@ -0,0 +1,307 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 123000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T07:17:42.347663"}
|
| 2 |
+
{"step": 123020, "epoch": 0.782, "loss": 1.73857, "ppl": 5.689, "lr": 0.003, "grad": 0.0862, "tokens": 128964326400, "tok_s": 161031.7}
|
| 3 |
+
{"step": 123040, "epoch": 0.782, "loss": 1.74074, "ppl": 5.702, "lr": 0.003, "grad": 0.1368, "tokens": 128985292800, "tok_s": 160954.1}
|
| 4 |
+
{"step": 123060, "epoch": 0.782, "loss": 1.71462, "ppl": 5.555, "lr": 0.003, "grad": 0.1204, "tokens": 129006259200, "tok_s": 160878.0}
|
| 5 |
+
{"step": 123080, "epoch": 0.782, "loss": 1.61219, "ppl": 5.014, "lr": 0.003, "grad": 0.1082, "tokens": 129027225600, "tok_s": 160909.1}
|
| 6 |
+
{"step": 123100, "epoch": 0.782, "loss": 1.76628, "ppl": 5.849, "lr": 0.003, "grad": 0.1002, "tokens": 129048192000, "tok_s": 160834.8}
|
| 7 |
+
{"step": 123120, "epoch": 0.782, "loss": 1.72774, "ppl": 5.628, "lr": 0.003, "grad": 0.1067, "tokens": 129069158400, "tok_s": 160818.5}
|
| 8 |
+
{"step": 123140, "epoch": 0.782, "loss": 1.74211, "ppl": 5.709, "lr": 0.003, "grad": 0.0941, "tokens": 129090124800, "tok_s": 160918.4}
|
| 9 |
+
{"step": 123160, "epoch": 0.783, "loss": 1.67448, "ppl": 5.336, "lr": 0.003, "grad": 0.1091, "tokens": 129111091200, "tok_s": 160449.9}
|
| 10 |
+
{"step": 123180, "epoch": 0.783, "loss": 1.62741, "ppl": 5.091, "lr": 0.003, "grad": 0.0851, "tokens": 129132057600, "tok_s": 160590.1}
|
| 11 |
+
{"step": 123200, "epoch": 0.783, "loss": 1.59223, "ppl": 4.915, "lr": 0.003, "grad": 0.1177, "tokens": 129153024000, "tok_s": 161036.6}
|
| 12 |
+
{"step": 123220, "epoch": 0.783, "loss": 1.77914, "ppl": 5.925, "lr": 0.003, "grad": 0.084, "tokens": 129173990400, "tok_s": 160567.9}
|
| 13 |
+
{"step": 123240, "epoch": 0.783, "loss": 1.70141, "ppl": 5.482, "lr": 0.003, "grad": 0.0896, "tokens": 129194956800, "tok_s": 160638.0}
|
| 14 |
+
{"step": 123260, "epoch": 0.783, "loss": 1.76084, "ppl": 5.817, "lr": 0.003, "grad": 0.0738, "tokens": 129215923200, "tok_s": 160679.1}
|
| 15 |
+
{"step": 123280, "epoch": 0.783, "loss": 1.7102, "ppl": 5.53, "lr": 0.003, "grad": 0.0883, "tokens": 129236889600, "tok_s": 160692.9}
|
| 16 |
+
{"step": 123300, "epoch": 0.783, "loss": 1.75342, "ppl": 5.774, "lr": 0.003, "grad": 0.0895, "tokens": 129257856000, "tok_s": 160243.8}
|
| 17 |
+
{"step": 123320, "epoch": 0.784, "loss": 1.75981, "ppl": 5.811, "lr": 0.003, "grad": 0.0953, "tokens": 129278822400, "tok_s": 160626.9}
|
| 18 |
+
{"step": 123340, "epoch": 0.784, "loss": 1.72484, "ppl": 5.612, "lr": 0.003, "grad": 0.0835, "tokens": 129299788800, "tok_s": 160704.6}
|
| 19 |
+
{"step": 123360, "epoch": 0.784, "loss": 1.77109, "ppl": 5.877, "lr": 0.003, "grad": 0.0692, "tokens": 129320755200, "tok_s": 160342.8}
|
| 20 |
+
{"step": 123380, "epoch": 0.784, "loss": 1.68046, "ppl": 5.368, "lr": 0.003, "grad": 0.0858, "tokens": 129341721600, "tok_s": 160363.0}
|
| 21 |
+
{"step": 123400, "epoch": 0.784, "loss": 1.78102, "ppl": 5.936, "lr": 0.003, "grad": 0.1139, "tokens": 129362688000, "tok_s": 160007.1}
|
| 22 |
+
{"step": 123420, "epoch": 0.784, "loss": 1.75995, "ppl": 5.812, "lr": 0.003, "grad": 0.1308, "tokens": 129383654400, "tok_s": 160252.3}
|
| 23 |
+
{"step": 123440, "epoch": 0.784, "loss": 1.66969, "ppl": 5.311, "lr": 0.003, "grad": 0.0459, "tokens": 129404620800, "tok_s": 160442.8}
|
| 24 |
+
{"step": 123460, "epoch": 0.784, "loss": 1.81077, "ppl": 6.115, "lr": 0.003, "grad": 0.138, "tokens": 129425587200, "tok_s": 160788.9}
|
| 25 |
+
{"step": 123480, "epoch": 0.785, "loss": 1.80649, "ppl": 6.089, "lr": 0.003, "grad": 0.1163, "tokens": 129446553600, "tok_s": 160351.6}
|
| 26 |
+
{"step": 123500, "epoch": 0.785, "loss": 1.89406, "ppl": 6.646, "lr": 0.003, "grad": 0.0874, "tokens": 129467520000, "tok_s": 160608.9}
|
| 27 |
+
{"step": 123520, "epoch": 0.785, "loss": 1.76213, "ppl": 5.825, "lr": 0.003, "grad": 0.1057, "tokens": 129488486400, "tok_s": 160788.4}
|
| 28 |
+
{"step": 123540, "epoch": 0.785, "loss": 1.65779, "ppl": 5.248, "lr": 0.003, "grad": 0.0677, "tokens": 129509452800, "tok_s": 160517.6}
|
| 29 |
+
{"step": 123560, "epoch": 0.785, "loss": 1.67789, "ppl": 5.354, "lr": 0.003, "grad": 0.0999, "tokens": 129530419200, "tok_s": 160237.3}
|
| 30 |
+
{"step": 123580, "epoch": 0.785, "loss": 1.70206, "ppl": 5.485, "lr": 0.003, "grad": 0.1107, "tokens": 129551385600, "tok_s": 160724.2}
|
| 31 |
+
{"step": 123600, "epoch": 0.785, "loss": 1.63826, "ppl": 5.146, "lr": 0.003, "grad": 0.0701, "tokens": 129572352000, "tok_s": 160822.5}
|
| 32 |
+
{"step": 123620, "epoch": 0.785, "loss": 1.71302, "ppl": 5.546, "lr": 0.003, "grad": 0.085, "tokens": 129593318400, "tok_s": 160096.6}
|
| 33 |
+
{"step": 123640, "epoch": 0.786, "loss": 1.66073, "ppl": 5.263, "lr": 0.003, "grad": 0.1023, "tokens": 129614284800, "tok_s": 160631.5}
|
| 34 |
+
{"step": 123660, "epoch": 0.786, "loss": 1.8423, "ppl": 6.311, "lr": 0.003, "grad": 0.1501, "tokens": 129635251200, "tok_s": 160190.0}
|
| 35 |
+
{"step": 123680, "epoch": 0.786, "loss": 1.76954, "ppl": 5.868, "lr": 0.003, "grad": 0.133, "tokens": 129656217600, "tok_s": 160086.3}
|
| 36 |
+
{"step": 123700, "epoch": 0.786, "loss": 1.74116, "ppl": 5.704, "lr": 0.003, "grad": 0.1168, "tokens": 129677184000, "tok_s": 160085.2}
|
| 37 |
+
{"step": 123720, "epoch": 0.786, "loss": 1.66455, "ppl": 5.283, "lr": 0.003, "grad": 0.0707, "tokens": 129698150400, "tok_s": 160806.9}
|
| 38 |
+
{"step": 123740, "epoch": 0.786, "loss": 1.69718, "ppl": 5.459, "lr": 0.003, "grad": 0.0964, "tokens": 129719116800, "tok_s": 160812.3}
|
| 39 |
+
{"step": 123760, "epoch": 0.786, "loss": 1.76656, "ppl": 5.851, "lr": 0.003, "grad": 0.0841, "tokens": 129740083200, "tok_s": 161029.3}
|
| 40 |
+
{"step": 123780, "epoch": 0.786, "loss": 1.675, "ppl": 5.339, "lr": 0.003, "grad": 0.1033, "tokens": 129761049600, "tok_s": 159944.2}
|
| 41 |
+
{"step": 123800, "epoch": 0.787, "loss": 1.69161, "ppl": 5.428, "lr": 0.003, "grad": 0.0943, "tokens": 129782016000, "tok_s": 160887.6}
|
| 42 |
+
{"step": 123820, "epoch": 0.787, "loss": 1.74107, "ppl": 5.703, "lr": 0.003, "grad": 0.0992, "tokens": 129802982400, "tok_s": 160383.1}
|
| 43 |
+
{"step": 123840, "epoch": 0.787, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.0678, "tokens": 129823948800, "tok_s": 160859.1}
|
| 44 |
+
{"step": 123860, "epoch": 0.787, "loss": 1.75066, "ppl": 5.758, "lr": 0.003, "grad": 0.1289, "tokens": 129844915200, "tok_s": 160687.8}
|
| 45 |
+
{"step": 123880, "epoch": 0.787, "loss": 1.77861, "ppl": 5.922, "lr": 0.003, "grad": 0.1118, "tokens": 129865881600, "tok_s": 159777.7}
|
| 46 |
+
{"step": 123900, "epoch": 0.787, "loss": 1.44937, "ppl": 4.26, "lr": 0.003, "grad": 0.0972, "tokens": 129886848000, "tok_s": 160594.5}
|
| 47 |
+
{"step": 123920, "epoch": 0.787, "loss": 1.67828, "ppl": 5.356, "lr": 0.003, "grad": 0.1003, "tokens": 129907814400, "tok_s": 160390.4}
|
| 48 |
+
{"step": 123940, "epoch": 0.787, "loss": 1.6936, "ppl": 5.439, "lr": 0.003, "grad": 0.1095, "tokens": 129928780800, "tok_s": 160885.6}
|
| 49 |
+
{"step": 123960, "epoch": 0.788, "loss": 1.78226, "ppl": 5.943, "lr": 0.003, "grad": 0.1094, "tokens": 129949747200, "tok_s": 160422.9}
|
| 50 |
+
{"step": 123980, "epoch": 0.788, "loss": 1.73459, "ppl": 5.667, "lr": 0.003, "grad": 0.0688, "tokens": 129970713600, "tok_s": 160651.5}
|
| 51 |
+
{"step": 124000, "epoch": 0.788, "loss": 1.88859, "ppl": 6.61, "lr": 0.003, "grad": 0.1302, "tokens": 129991680000, "tok_s": 159622.6}
|
| 52 |
+
{"step": 124000, "val_loss": 1.73125, "val_ppl": 5.648, "is_best": true}
|
| 53 |
+
{"step": 124020, "epoch": 0.788, "loss": 1.7361, "ppl": 5.675, "lr": 0.003, "grad": 0.1751, "tokens": 130012646400, "tok_s": 160215.9}
|
| 54 |
+
{"step": 124040, "epoch": 0.788, "loss": 1.67665, "ppl": 5.348, "lr": 0.003, "grad": 0.0744, "tokens": 130033612800, "tok_s": 160225.5}
|
| 55 |
+
{"step": 124060, "epoch": 0.788, "loss": 1.77362, "ppl": 5.892, "lr": 0.003, "grad": 0.0898, "tokens": 130054579200, "tok_s": 160331.3}
|
| 56 |
+
{"step": 124080, "epoch": 0.788, "loss": 1.72503, "ppl": 5.613, "lr": 0.003, "grad": 0.0922, "tokens": 130075545600, "tok_s": 159702.9}
|
| 57 |
+
{"step": 124100, "epoch": 0.788, "loss": 1.59609, "ppl": 4.934, "lr": 0.003, "grad": 0.0762, "tokens": 130096512000, "tok_s": 160685.8}
|
| 58 |
+
{"step": 124120, "epoch": 0.789, "loss": 1.86891, "ppl": 6.481, "lr": 0.003, "grad": 0.1202, "tokens": 130117478400, "tok_s": 160504.1}
|
| 59 |
+
{"step": 124140, "epoch": 0.789, "loss": 1.76403, "ppl": 5.836, "lr": 0.003, "grad": 0.0684, "tokens": 130138444800, "tok_s": 160268.2}
|
| 60 |
+
{"step": 124160, "epoch": 0.789, "loss": 1.74983, "ppl": 5.754, "lr": 0.003, "grad": 0.1502, "tokens": 130159411200, "tok_s": 160689.6}
|
| 61 |
+
{"step": 124180, "epoch": 0.789, "loss": 1.79266, "ppl": 6.005, "lr": 0.003, "grad": 0.1325, "tokens": 130180377600, "tok_s": 160749.9}
|
| 62 |
+
{"step": 124200, "epoch": 0.789, "loss": 1.70712, "ppl": 5.513, "lr": 0.003, "grad": 0.1652, "tokens": 130201344000, "tok_s": 160972.2}
|
| 63 |
+
{"step": 124220, "epoch": 0.789, "loss": 1.77982, "ppl": 5.929, "lr": 0.003, "grad": 0.0863, "tokens": 130222310400, "tok_s": 159848.7}
|
| 64 |
+
{"step": 124240, "epoch": 0.789, "loss": 1.6902, "ppl": 5.421, "lr": 0.003, "grad": 0.0906, "tokens": 130243276800, "tok_s": 160423.3}
|
| 65 |
+
{"step": 124260, "epoch": 0.79, "loss": 1.72005, "ppl": 5.585, "lr": 0.003, "grad": 0.1148, "tokens": 130264243200, "tok_s": 160008.5}
|
| 66 |
+
{"step": 124280, "epoch": 0.79, "loss": 1.60375, "ppl": 4.972, "lr": 0.003, "grad": 0.0759, "tokens": 130285209600, "tok_s": 160501.4}
|
| 67 |
+
{"step": 124300, "epoch": 0.79, "loss": 1.80209, "ppl": 6.062, "lr": 0.003, "grad": 0.1022, "tokens": 130306176000, "tok_s": 160572.2}
|
| 68 |
+
{"step": 124320, "epoch": 0.79, "loss": 1.74269, "ppl": 5.713, "lr": 0.003, "grad": 0.0813, "tokens": 130327142400, "tok_s": 160189.3}
|
| 69 |
+
{"step": 124340, "epoch": 0.79, "loss": 1.79512, "ppl": 6.02, "lr": 0.003, "grad": 0.1168, "tokens": 130348108800, "tok_s": 160868.6}
|
| 70 |
+
{"step": 124360, "epoch": 0.79, "loss": 1.73415, "ppl": 5.664, "lr": 0.003, "grad": 0.0753, "tokens": 130369075200, "tok_s": 160812.7}
|
| 71 |
+
{"step": 124380, "epoch": 0.79, "loss": 1.84343, "ppl": 6.318, "lr": 0.003, "grad": 0.0912, "tokens": 130390041600, "tok_s": 160527.0}
|
| 72 |
+
{"step": 124400, "epoch": 0.79, "loss": 1.81286, "ppl": 6.128, "lr": 0.003, "grad": 0.069, "tokens": 130411008000, "tok_s": 160789.7}
|
| 73 |
+
{"step": 124420, "epoch": 0.791, "loss": 1.79391, "ppl": 6.013, "lr": 0.003, "grad": 0.0965, "tokens": 130431974400, "tok_s": 160630.4}
|
| 74 |
+
{"step": 124440, "epoch": 0.791, "loss": 1.73427, "ppl": 5.665, "lr": 0.003, "grad": 0.095, "tokens": 130452940800, "tok_s": 160278.9}
|
| 75 |
+
{"step": 124460, "epoch": 0.791, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.1166, "tokens": 130473907200, "tok_s": 159362.5}
|
| 76 |
+
{"step": 124480, "epoch": 0.791, "loss": 1.82161, "ppl": 6.182, "lr": 0.003, "grad": 0.0951, "tokens": 130494873600, "tok_s": 160482.4}
|
| 77 |
+
{"step": 124500, "epoch": 0.791, "loss": 1.77899, "ppl": 5.924, "lr": 0.003, "grad": 0.0911, "tokens": 130515840000, "tok_s": 160632.9}
|
| 78 |
+
{"step": 124520, "epoch": 0.791, "loss": 1.78569, "ppl": 5.964, "lr": 0.003, "grad": 0.1077, "tokens": 130536806400, "tok_s": 160596.3}
|
| 79 |
+
{"step": 124540, "epoch": 0.791, "loss": 1.7094, "ppl": 5.526, "lr": 0.003, "grad": 0.0913, "tokens": 130557772800, "tok_s": 160800.8}
|
| 80 |
+
{"step": 124560, "epoch": 0.791, "loss": 1.79031, "ppl": 5.991, "lr": 0.003, "grad": 0.1412, "tokens": 130578739200, "tok_s": 160067.8}
|
| 81 |
+
{"step": 124580, "epoch": 0.792, "loss": 1.59144, "ppl": 4.911, "lr": 0.003, "grad": 0.0821, "tokens": 130599705600, "tok_s": 160693.3}
|
| 82 |
+
{"step": 124600, "epoch": 0.792, "loss": 1.76647, "ppl": 5.85, "lr": 0.003, "grad": 0.1521, "tokens": 130620672000, "tok_s": 160653.0}
|
| 83 |
+
{"step": 124620, "epoch": 0.792, "loss": 1.76625, "ppl": 5.849, "lr": 0.003, "grad": 0.089, "tokens": 130641638400, "tok_s": 159971.8}
|
| 84 |
+
{"step": 124640, "epoch": 0.792, "loss": 1.73058, "ppl": 5.644, "lr": 0.003, "grad": 0.1279, "tokens": 130662604800, "tok_s": 160512.9}
|
| 85 |
+
{"step": 124660, "epoch": 0.792, "loss": 1.78411, "ppl": 5.954, "lr": 0.003, "grad": 0.0948, "tokens": 130683571200, "tok_s": 160282.8}
|
| 86 |
+
{"step": 124680, "epoch": 0.792, "loss": 1.7574, "ppl": 5.797, "lr": 0.003, "grad": 0.0869, "tokens": 130704537600, "tok_s": 160624.5}
|
| 87 |
+
{"step": 124700, "epoch": 0.792, "loss": 1.72977, "ppl": 5.639, "lr": 0.003, "grad": 0.0889, "tokens": 130725504000, "tok_s": 160538.3}
|
| 88 |
+
{"step": 124720, "epoch": 0.792, "loss": 1.70746, "ppl": 5.515, "lr": 0.003, "grad": 0.0753, "tokens": 130746470400, "tok_s": 160834.9}
|
| 89 |
+
{"step": 124740, "epoch": 0.793, "loss": 1.74636, "ppl": 5.734, "lr": 0.003, "grad": 0.1024, "tokens": 130767436800, "tok_s": 160732.6}
|
| 90 |
+
{"step": 124760, "epoch": 0.793, "loss": 1.63906, "ppl": 5.15, "lr": 0.003, "grad": 0.0647, "tokens": 130788403200, "tok_s": 160648.6}
|
| 91 |
+
{"step": 124780, "epoch": 0.793, "loss": 1.71628, "ppl": 5.564, "lr": 0.003, "grad": 0.1116, "tokens": 130809369600, "tok_s": 160459.3}
|
| 92 |
+
{"step": 124800, "epoch": 0.793, "loss": 1.74014, "ppl": 5.698, "lr": 0.003, "grad": 0.0762, "tokens": 130830336000, "tok_s": 160779.2}
|
| 93 |
+
{"step": 124820, "epoch": 0.793, "loss": 1.76257, "ppl": 5.827, "lr": 0.003, "grad": 0.1096, "tokens": 130851302400, "tok_s": 160502.2}
|
| 94 |
+
{"step": 124840, "epoch": 0.793, "loss": 1.77835, "ppl": 5.92, "lr": 0.003, "grad": 0.1063, "tokens": 130872268800, "tok_s": 160316.6}
|
| 95 |
+
{"step": 124860, "epoch": 0.793, "loss": 1.78944, "ppl": 5.986, "lr": 0.003, "grad": 0.0601, "tokens": 130893235200, "tok_s": 160541.8}
|
| 96 |
+
{"step": 124880, "epoch": 0.793, "loss": 1.76928, "ppl": 5.867, "lr": 0.003, "grad": 0.1254, "tokens": 130914201600, "tok_s": 160654.0}
|
| 97 |
+
{"step": 124900, "epoch": 0.794, "loss": 1.75305, "ppl": 5.772, "lr": 0.003, "grad": 0.0925, "tokens": 130935168000, "tok_s": 160492.8}
|
| 98 |
+
{"step": 124920, "epoch": 0.794, "loss": 1.77743, "ppl": 5.915, "lr": 0.003, "grad": 0.1285, "tokens": 130956134400, "tok_s": 160781.2}
|
| 99 |
+
{"step": 124940, "epoch": 0.794, "loss": 1.72792, "ppl": 5.629, "lr": 0.003, "grad": 0.0794, "tokens": 130977100800, "tok_s": 160778.9}
|
| 100 |
+
{"step": 124960, "epoch": 0.794, "loss": 1.74981, "ppl": 5.753, "lr": 0.003, "grad": 0.1085, "tokens": 130998067200, "tok_s": 159891.1}
|
| 101 |
+
{"step": 124980, "epoch": 0.794, "loss": 1.79698, "ppl": 6.031, "lr": 0.003, "grad": 0.1132, "tokens": 131019033600, "tok_s": 160698.3}
|
| 102 |
+
{"step": 125000, "epoch": 0.794, "loss": 1.72512, "ppl": 5.613, "lr": 0.003, "grad": 0.0803, "tokens": 131040000000, "tok_s": 160280.6}
|
| 103 |
+
{"step": 125000, "val_loss": 1.74215, "val_ppl": 5.71, "is_best": false}
|
| 104 |
+
{"step": 125020, "epoch": 0.794, "loss": 1.76033, "ppl": 5.814, "lr": 0.003, "grad": 0.1208, "tokens": 131060966400, "tok_s": 160517.3}
|
| 105 |
+
{"step": 125040, "epoch": 0.794, "loss": 1.74821, "ppl": 5.744, "lr": 0.003, "grad": 0.1219, "tokens": 131081932800, "tok_s": 160743.6}
|
| 106 |
+
{"step": 125060, "epoch": 0.795, "loss": 1.69473, "ppl": 5.445, "lr": 0.003, "grad": 0.0884, "tokens": 131102899200, "tok_s": 160707.3}
|
| 107 |
+
{"step": 125080, "epoch": 0.795, "loss": 1.76494, "ppl": 5.841, "lr": 0.003, "grad": 0.1146, "tokens": 131123865600, "tok_s": 160535.1}
|
| 108 |
+
{"step": 125100, "epoch": 0.795, "loss": 1.7554, "ppl": 5.786, "lr": 0.003, "grad": 0.1027, "tokens": 131144832000, "tok_s": 160837.8}
|
| 109 |
+
{"step": 125120, "epoch": 0.795, "loss": 1.82843, "ppl": 6.224, "lr": 0.003, "grad": 0.0815, "tokens": 131165798400, "tok_s": 159815.0}
|
| 110 |
+
{"step": 125140, "epoch": 0.795, "loss": 1.76921, "ppl": 5.866, "lr": 0.003, "grad": 0.1131, "tokens": 131186764800, "tok_s": 160652.4}
|
| 111 |
+
{"step": 125160, "epoch": 0.795, "loss": 1.72331, "ppl": 5.603, "lr": 0.003, "grad": 0.1504, "tokens": 131207731200, "tok_s": 160288.6}
|
| 112 |
+
{"step": 125180, "epoch": 0.795, "loss": 1.74794, "ppl": 5.743, "lr": 0.003, "grad": 0.0825, "tokens": 131228697600, "tok_s": 160590.8}
|
| 113 |
+
{"step": 125200, "epoch": 0.795, "loss": 1.80309, "ppl": 6.068, "lr": 0.003, "grad": 0.1297, "tokens": 131249664000, "tok_s": 160013.0}
|
| 114 |
+
{"step": 125220, "epoch": 0.796, "loss": 1.70651, "ppl": 5.51, "lr": 0.003, "grad": 0.074, "tokens": 131270630400, "tok_s": 160896.4}
|
| 115 |
+
{"step": 125240, "epoch": 0.796, "loss": 1.75076, "ppl": 5.759, "lr": 0.003, "grad": 0.1105, "tokens": 131291596800, "tok_s": 160396.9}
|
| 116 |
+
{"step": 125260, "epoch": 0.796, "loss": 1.66345, "ppl": 5.277, "lr": 0.003, "grad": 0.087, "tokens": 131312563200, "tok_s": 160563.1}
|
| 117 |
+
{"step": 125280, "epoch": 0.796, "loss": 1.76143, "ppl": 5.821, "lr": 0.003, "grad": 0.0767, "tokens": 131333529600, "tok_s": 160747.0}
|
| 118 |
+
{"step": 125300, "epoch": 0.796, "loss": 1.78602, "ppl": 5.966, "lr": 0.003, "grad": 0.0902, "tokens": 131354496000, "tok_s": 160934.3}
|
| 119 |
+
{"step": 125320, "epoch": 0.796, "loss": 1.66687, "ppl": 5.296, "lr": 0.003, "grad": 0.0875, "tokens": 131375462400, "tok_s": 159971.8}
|
| 120 |
+
{"step": 125340, "epoch": 0.796, "loss": 1.63117, "ppl": 5.11, "lr": 0.003, "grad": 0.1239, "tokens": 131396428800, "tok_s": 160658.5}
|
| 121 |
+
{"step": 125360, "epoch": 0.796, "loss": 1.75845, "ppl": 5.803, "lr": 0.003, "grad": 0.1208, "tokens": 131417395200, "tok_s": 160151.0}
|
| 122 |
+
{"step": 125380, "epoch": 0.797, "loss": 1.73367, "ppl": 5.661, "lr": 0.003, "grad": 0.0954, "tokens": 131438361600, "tok_s": 160160.2}
|
| 123 |
+
{"step": 125400, "epoch": 0.797, "loss": 1.64819, "ppl": 5.198, "lr": 0.003, "grad": 0.0774, "tokens": 131459328000, "tok_s": 160193.9}
|
| 124 |
+
{"step": 125420, "epoch": 0.797, "loss": 1.66598, "ppl": 5.291, "lr": 0.003, "grad": 0.0986, "tokens": 131480294400, "tok_s": 160053.9}
|
| 125 |
+
{"step": 125440, "epoch": 0.797, "loss": 1.8541, "ppl": 6.386, "lr": 0.003, "grad": 0.1272, "tokens": 131501260800, "tok_s": 160350.0}
|
| 126 |
+
{"step": 125460, "epoch": 0.797, "loss": 1.64714, "ppl": 5.192, "lr": 0.003, "grad": 0.0725, "tokens": 131522227200, "tok_s": 160129.8}
|
| 127 |
+
{"step": 125480, "epoch": 0.797, "loss": 1.7242, "ppl": 5.608, "lr": 0.003, "grad": 0.0687, "tokens": 131543193600, "tok_s": 160611.9}
|
| 128 |
+
{"step": 125500, "epoch": 0.797, "loss": 1.6994, "ppl": 5.471, "lr": 0.003, "grad": 0.1098, "tokens": 131564160000, "tok_s": 160332.7}
|
| 129 |
+
{"step": 125520, "epoch": 0.798, "loss": 1.71202, "ppl": 5.54, "lr": 0.003, "grad": 0.0632, "tokens": 131585126400, "tok_s": 160815.6}
|
| 130 |
+
{"step": 125540, "epoch": 0.798, "loss": 1.71523, "ppl": 5.558, "lr": 0.003, "grad": 0.0566, "tokens": 131606092800, "tok_s": 160783.7}
|
| 131 |
+
{"step": 125560, "epoch": 0.798, "loss": 1.81274, "ppl": 6.127, "lr": 0.003, "grad": 0.1067, "tokens": 131627059200, "tok_s": 160811.5}
|
| 132 |
+
{"step": 125580, "epoch": 0.798, "loss": 1.74317, "ppl": 5.715, "lr": 0.003, "grad": 0.1306, "tokens": 131648025600, "tok_s": 160707.5}
|
| 133 |
+
{"step": 125600, "epoch": 0.798, "loss": 1.77451, "ppl": 5.897, "lr": 0.003, "grad": 0.0825, "tokens": 131668992000, "tok_s": 160758.1}
|
| 134 |
+
{"step": 125620, "epoch": 0.798, "loss": 1.73877, "ppl": 5.69, "lr": 0.003, "grad": 0.082, "tokens": 131689958400, "tok_s": 160627.5}
|
| 135 |
+
{"step": 125640, "epoch": 0.798, "loss": 1.77622, "ppl": 5.907, "lr": 0.003, "grad": 0.1201, "tokens": 131710924800, "tok_s": 160920.4}
|
| 136 |
+
{"step": 125660, "epoch": 0.798, "loss": 1.64526, "ppl": 5.182, "lr": 0.003, "grad": 0.1084, "tokens": 131731891200, "tok_s": 160624.3}
|
| 137 |
+
{"step": 125680, "epoch": 0.799, "loss": 1.73881, "ppl": 5.691, "lr": 0.003, "grad": 0.1094, "tokens": 131752857600, "tok_s": 160666.0}
|
| 138 |
+
{"step": 125700, "epoch": 0.799, "loss": 1.69768, "ppl": 5.461, "lr": 0.003, "grad": 0.1167, "tokens": 131773824000, "tok_s": 160761.8}
|
| 139 |
+
{"step": 125720, "epoch": 0.799, "loss": 1.78497, "ppl": 5.959, "lr": 0.003, "grad": 0.1092, "tokens": 131794790400, "tok_s": 160875.4}
|
| 140 |
+
{"step": 125740, "epoch": 0.799, "loss": 1.60774, "ppl": 4.992, "lr": 0.003, "grad": 0.092, "tokens": 131815756800, "tok_s": 160801.6}
|
| 141 |
+
{"step": 125760, "epoch": 0.799, "loss": 1.77716, "ppl": 5.913, "lr": 0.003, "grad": 0.0894, "tokens": 131836723200, "tok_s": 160699.4}
|
| 142 |
+
{"step": 125780, "epoch": 0.799, "loss": 1.78281, "ppl": 5.947, "lr": 0.003, "grad": 0.1028, "tokens": 131857689600, "tok_s": 160806.4}
|
| 143 |
+
{"step": 125800, "epoch": 0.799, "loss": 1.75767, "ppl": 5.799, "lr": 0.003, "grad": 0.0783, "tokens": 131878656000, "tok_s": 160736.4}
|
| 144 |
+
{"step": 125820, "epoch": 0.799, "loss": 1.77649, "ppl": 5.909, "lr": 0.003, "grad": 0.0951, "tokens": 131899622400, "tok_s": 160778.6}
|
| 145 |
+
{"step": 125840, "epoch": 0.8, "loss": 1.77938, "ppl": 5.926, "lr": 0.003, "grad": 0.1144, "tokens": 131920588800, "tok_s": 160968.2}
|
| 146 |
+
{"step": 125860, "epoch": 0.8, "loss": 1.80196, "ppl": 6.062, "lr": 0.003, "grad": 0.1349, "tokens": 131941555200, "tok_s": 160726.0}
|
| 147 |
+
{"step": 125880, "epoch": 0.8, "loss": 1.71563, "ppl": 5.56, "lr": 0.003, "grad": 0.095, "tokens": 131962521600, "tok_s": 160731.7}
|
| 148 |
+
{"step": 125900, "epoch": 0.8, "loss": 1.76961, "ppl": 5.869, "lr": 0.003, "grad": 0.1057, "tokens": 131983488000, "tok_s": 160875.8}
|
| 149 |
+
{"step": 125920, "epoch": 0.8, "loss": 1.76717, "ppl": 5.854, "lr": 0.003, "grad": 0.0702, "tokens": 132004454400, "tok_s": 160778.1}
|
| 150 |
+
{"step": 125940, "epoch": 0.8, "loss": 1.73329, "ppl": 5.659, "lr": 0.003, "grad": 0.1034, "tokens": 132025420800, "tok_s": 160384.4}
|
| 151 |
+
{"step": 125960, "epoch": 0.8, "loss": 1.78953, "ppl": 5.987, "lr": 0.003, "grad": 0.082, "tokens": 132046387200, "tok_s": 160727.7}
|
| 152 |
+
{"step": 125980, "epoch": 0.8, "loss": 1.76174, "ppl": 5.823, "lr": 0.003, "grad": 0.1295, "tokens": 132067353600, "tok_s": 160876.9}
|
| 153 |
+
{"step": 126000, "epoch": 0.801, "loss": 1.76653, "ppl": 5.85, "lr": 0.003, "grad": 0.1551, "tokens": 132088320000, "tok_s": 160715.0}
|
| 154 |
+
{"step": 126000, "val_loss": 1.74991, "val_ppl": 5.754, "is_best": false}
|
| 155 |
+
{"step": 126020, "epoch": 0.801, "loss": 1.69758, "ppl": 5.461, "lr": 0.003, "grad": 0.0926, "tokens": 132109286400, "tok_s": 160773.8}
|
| 156 |
+
{"step": 126040, "epoch": 0.801, "loss": 1.75444, "ppl": 5.78, "lr": 0.003, "grad": 0.0992, "tokens": 132130252800, "tok_s": 160821.1}
|
| 157 |
+
{"step": 126060, "epoch": 0.801, "loss": 1.73691, "ppl": 5.68, "lr": 0.003, "grad": 0.1107, "tokens": 132151219200, "tok_s": 160868.3}
|
| 158 |
+
{"step": 126080, "epoch": 0.801, "loss": 1.77811, "ppl": 5.919, "lr": 0.003, "grad": 0.1458, "tokens": 132172185600, "tok_s": 160908.9}
|
| 159 |
+
{"step": 126100, "epoch": 0.801, "loss": 1.77404, "ppl": 5.895, "lr": 0.003, "grad": 0.0837, "tokens": 132193152000, "tok_s": 160594.2}
|
| 160 |
+
{"step": 126120, "epoch": 0.801, "loss": 1.7408, "ppl": 5.702, "lr": 0.003, "grad": 0.1212, "tokens": 132214118400, "tok_s": 160877.0}
|
| 161 |
+
{"step": 126140, "epoch": 0.801, "loss": 1.72606, "ppl": 5.618, "lr": 0.003, "grad": 0.0992, "tokens": 132235084800, "tok_s": 160598.3}
|
| 162 |
+
{"step": 126160, "epoch": 0.802, "loss": 1.73635, "ppl": 5.677, "lr": 0.003, "grad": 0.0989, "tokens": 132256051200, "tok_s": 160405.1}
|
| 163 |
+
{"step": 126180, "epoch": 0.802, "loss": 1.68267, "ppl": 5.38, "lr": 0.003, "grad": 0.1019, "tokens": 132277017600, "tok_s": 160378.1}
|
| 164 |
+
{"step": 126200, "epoch": 0.802, "loss": 1.74384, "ppl": 5.719, "lr": 0.003, "grad": 0.1051, "tokens": 132297984000, "tok_s": 160807.2}
|
| 165 |
+
{"step": 126220, "epoch": 0.802, "loss": 1.73014, "ppl": 5.641, "lr": 0.003, "grad": 0.1541, "tokens": 132318950400, "tok_s": 160839.3}
|
| 166 |
+
{"step": 126240, "epoch": 0.802, "loss": 1.73399, "ppl": 5.663, "lr": 0.003, "grad": 0.1039, "tokens": 132339916800, "tok_s": 160368.3}
|
| 167 |
+
{"step": 126260, "epoch": 0.802, "loss": 1.74648, "ppl": 5.734, "lr": 0.003, "grad": 0.0941, "tokens": 132360883200, "tok_s": 160590.1}
|
| 168 |
+
{"step": 126280, "epoch": 0.802, "loss": 1.77031, "ppl": 5.873, "lr": 0.003, "grad": 0.0798, "tokens": 132381849600, "tok_s": 160842.0}
|
| 169 |
+
{"step": 126300, "epoch": 0.802, "loss": 1.82219, "ppl": 6.185, "lr": 0.003, "grad": 0.0945, "tokens": 132402816000, "tok_s": 160908.6}
|
| 170 |
+
{"step": 126320, "epoch": 0.803, "loss": 1.72436, "ppl": 5.609, "lr": 0.003, "grad": 0.1298, "tokens": 132423782400, "tok_s": 160699.5}
|
| 171 |
+
{"step": 126340, "epoch": 0.803, "loss": 1.75298, "ppl": 5.772, "lr": 0.003, "grad": 0.1049, "tokens": 132444748800, "tok_s": 160776.4}
|
| 172 |
+
{"step": 126360, "epoch": 0.803, "loss": 1.74143, "ppl": 5.705, "lr": 0.003, "grad": 0.1052, "tokens": 132465715200, "tok_s": 160881.9}
|
| 173 |
+
{"step": 126380, "epoch": 0.803, "loss": 1.69539, "ppl": 5.449, "lr": 0.003, "grad": 0.122, "tokens": 132486681600, "tok_s": 160739.3}
|
| 174 |
+
{"step": 126400, "epoch": 0.803, "loss": 1.7148, "ppl": 5.556, "lr": 0.003, "grad": 0.1499, "tokens": 132507648000, "tok_s": 160947.8}
|
| 175 |
+
{"step": 126420, "epoch": 0.803, "loss": 1.74067, "ppl": 5.701, "lr": 0.003, "grad": 0.1329, "tokens": 132528614400, "tok_s": 160898.9}
|
| 176 |
+
{"step": 126440, "epoch": 0.803, "loss": 1.72883, "ppl": 5.634, "lr": 0.003, "grad": 0.1075, "tokens": 132549580800, "tok_s": 160766.4}
|
| 177 |
+
{"step": 126460, "epoch": 0.803, "loss": 1.74148, "ppl": 5.706, "lr": 0.003, "grad": 0.0728, "tokens": 132570547200, "tok_s": 160702.9}
|
| 178 |
+
{"step": 126480, "epoch": 0.804, "loss": 1.65406, "ppl": 5.228, "lr": 0.003, "grad": 0.0854, "tokens": 132591513600, "tok_s": 160717.1}
|
| 179 |
+
{"step": 126500, "epoch": 0.804, "loss": 1.86413, "ppl": 6.45, "lr": 0.003, "grad": 0.137, "tokens": 132612480000, "tok_s": 160885.4}
|
| 180 |
+
{"step": 126520, "epoch": 0.804, "loss": 1.79083, "ppl": 5.994, "lr": 0.003, "grad": 0.0864, "tokens": 132633446400, "tok_s": 160726.3}
|
| 181 |
+
{"step": 126540, "epoch": 0.804, "loss": 1.69603, "ppl": 5.452, "lr": 0.003, "grad": 0.0653, "tokens": 132654412800, "tok_s": 160595.0}
|
| 182 |
+
{"step": 126560, "epoch": 0.804, "loss": 1.84869, "ppl": 6.351, "lr": 0.003, "grad": 0.1031, "tokens": 132675379200, "tok_s": 160760.5}
|
| 183 |
+
{"step": 126580, "epoch": 0.804, "loss": 1.73397, "ppl": 5.663, "lr": 0.003, "grad": 0.0941, "tokens": 132696345600, "tok_s": 160939.5}
|
| 184 |
+
{"step": 126600, "epoch": 0.804, "loss": 1.82054, "ppl": 6.175, "lr": 0.003, "grad": 0.1074, "tokens": 132717312000, "tok_s": 160769.9}
|
| 185 |
+
{"step": 126620, "epoch": 0.804, "loss": 1.73808, "ppl": 5.686, "lr": 0.003, "grad": 0.1278, "tokens": 132738278400, "tok_s": 160636.4}
|
| 186 |
+
{"step": 126640, "epoch": 0.805, "loss": 1.75373, "ppl": 5.776, "lr": 0.003, "grad": 0.1032, "tokens": 132759244800, "tok_s": 160776.6}
|
| 187 |
+
{"step": 126660, "epoch": 0.805, "loss": 1.63663, "ppl": 5.138, "lr": 0.003, "grad": 0.0948, "tokens": 132780211200, "tok_s": 160296.1}
|
| 188 |
+
{"step": 126680, "epoch": 0.805, "loss": 1.46989, "ppl": 4.349, "lr": 0.003, "grad": 0.1914, "tokens": 132801177600, "tok_s": 160768.9}
|
| 189 |
+
{"step": 126700, "epoch": 0.805, "loss": 1.80131, "ppl": 6.058, "lr": 0.003, "grad": 0.0968, "tokens": 132822144000, "tok_s": 160553.8}
|
| 190 |
+
{"step": 126720, "epoch": 0.805, "loss": 1.70179, "ppl": 5.484, "lr": 0.003, "grad": 0.1178, "tokens": 132843110400, "tok_s": 160809.0}
|
| 191 |
+
{"step": 126740, "epoch": 0.805, "loss": 1.71646, "ppl": 5.565, "lr": 0.003, "grad": 0.1215, "tokens": 132864076800, "tok_s": 160608.5}
|
| 192 |
+
{"step": 126760, "epoch": 0.805, "loss": 1.74311, "ppl": 5.715, "lr": 0.003, "grad": 0.0742, "tokens": 132885043200, "tok_s": 160699.2}
|
| 193 |
+
{"step": 126780, "epoch": 0.806, "loss": 1.70769, "ppl": 5.516, "lr": 0.003, "grad": 0.1247, "tokens": 132906009600, "tok_s": 160496.8}
|
| 194 |
+
{"step": 126800, "epoch": 0.806, "loss": 1.76602, "ppl": 5.848, "lr": 0.003, "grad": 0.1098, "tokens": 132926976000, "tok_s": 160575.2}
|
| 195 |
+
{"step": 126820, "epoch": 0.806, "loss": 1.74984, "ppl": 5.754, "lr": 0.003, "grad": 0.1587, "tokens": 132947942400, "tok_s": 160515.9}
|
| 196 |
+
{"step": 126840, "epoch": 0.806, "loss": 1.76474, "ppl": 5.84, "lr": 0.003, "grad": 0.1143, "tokens": 132968908800, "tok_s": 160570.5}
|
| 197 |
+
{"step": 126860, "epoch": 0.806, "loss": 1.74005, "ppl": 5.698, "lr": 0.003, "grad": 0.1492, "tokens": 132989875200, "tok_s": 160764.3}
|
| 198 |
+
{"step": 126880, "epoch": 0.806, "loss": 1.74436, "ppl": 5.722, "lr": 0.003, "grad": 0.0882, "tokens": 133010841600, "tok_s": 160761.4}
|
| 199 |
+
{"step": 126900, "epoch": 0.806, "loss": 1.73074, "ppl": 5.645, "lr": 0.003, "grad": 0.0589, "tokens": 133031808000, "tok_s": 160736.3}
|
| 200 |
+
{"step": 126920, "epoch": 0.806, "loss": 1.73084, "ppl": 5.645, "lr": 0.003, "grad": 0.1323, "tokens": 133052774400, "tok_s": 160636.1}
|
| 201 |
+
{"step": 126940, "epoch": 0.807, "loss": 1.73858, "ppl": 5.689, "lr": 0.003, "grad": 0.147, "tokens": 133073740800, "tok_s": 160651.5}
|
| 202 |
+
{"step": 126960, "epoch": 0.807, "loss": 1.76887, "ppl": 5.864, "lr": 0.003, "grad": 0.0971, "tokens": 133094707200, "tok_s": 160718.8}
|
| 203 |
+
{"step": 126980, "epoch": 0.807, "loss": 1.73789, "ppl": 5.685, "lr": 0.003, "grad": 0.1209, "tokens": 133115673600, "tok_s": 160883.7}
|
| 204 |
+
{"step": 127000, "epoch": 0.807, "loss": 1.76703, "ppl": 5.853, "lr": 0.003, "grad": 0.1307, "tokens": 133136640000, "tok_s": 160722.0}
|
| 205 |
+
{"step": 127000, "val_loss": 1.74954, "val_ppl": 5.752, "is_best": false}
|
| 206 |
+
{"step": 127020, "epoch": 0.807, "loss": 1.71579, "ppl": 5.561, "lr": 0.003, "grad": 0.102, "tokens": 133157606400, "tok_s": 160766.1}
|
| 207 |
+
{"step": 127040, "epoch": 0.807, "loss": 1.77087, "ppl": 5.876, "lr": 0.003, "grad": 0.0898, "tokens": 133178572800, "tok_s": 160680.0}
|
| 208 |
+
{"step": 127060, "epoch": 0.807, "loss": 1.71844, "ppl": 5.576, "lr": 0.003, "grad": 0.0975, "tokens": 133199539200, "tok_s": 160644.6}
|
| 209 |
+
{"step": 127080, "epoch": 0.807, "loss": 1.78155, "ppl": 5.939, "lr": 0.003, "grad": 0.1483, "tokens": 133220505600, "tok_s": 160604.4}
|
| 210 |
+
{"step": 127100, "epoch": 0.808, "loss": 1.75617, "ppl": 5.79, "lr": 0.003, "grad": 0.1597, "tokens": 133241472000, "tok_s": 160749.7}
|
| 211 |
+
{"step": 127120, "epoch": 0.808, "loss": 1.77712, "ppl": 5.913, "lr": 0.003, "grad": 0.1027, "tokens": 133262438400, "tok_s": 160905.2}
|
| 212 |
+
{"step": 127140, "epoch": 0.808, "loss": 1.71541, "ppl": 5.559, "lr": 0.003, "grad": 0.1281, "tokens": 133283404800, "tok_s": 160795.6}
|
| 213 |
+
{"step": 127160, "epoch": 0.808, "loss": 1.75601, "ppl": 5.789, "lr": 0.003, "grad": 0.1017, "tokens": 133304371200, "tok_s": 160512.0}
|
| 214 |
+
{"step": 127180, "epoch": 0.808, "loss": 1.76761, "ppl": 5.857, "lr": 0.003, "grad": 0.1163, "tokens": 133325337600, "tok_s": 160617.4}
|
| 215 |
+
{"step": 127200, "epoch": 0.808, "loss": 1.79759, "ppl": 6.035, "lr": 0.003, "grad": 0.0861, "tokens": 133346304000, "tok_s": 160649.9}
|
| 216 |
+
{"step": 127220, "epoch": 0.808, "loss": 1.79177, "ppl": 6.0, "lr": 0.003, "grad": 0.1538, "tokens": 133367270400, "tok_s": 160278.2}
|
| 217 |
+
{"step": 127240, "epoch": 0.808, "loss": 1.76259, "ppl": 5.828, "lr": 0.003, "grad": 0.0611, "tokens": 133388236800, "tok_s": 160633.6}
|
| 218 |
+
{"step": 127260, "epoch": 0.809, "loss": 1.71993, "ppl": 5.584, "lr": 0.003, "grad": 0.0778, "tokens": 133409203200, "tok_s": 160828.5}
|
| 219 |
+
{"step": 127280, "epoch": 0.809, "loss": 1.80326, "ppl": 6.069, "lr": 0.003, "grad": 0.1167, "tokens": 133430169600, "tok_s": 160539.9}
|
| 220 |
+
{"step": 127300, "epoch": 0.809, "loss": 1.77138, "ppl": 5.879, "lr": 0.003, "grad": 0.1078, "tokens": 133451136000, "tok_s": 160149.2}
|
| 221 |
+
{"step": 127320, "epoch": 0.809, "loss": 1.71873, "ppl": 5.577, "lr": 0.003, "grad": 0.0965, "tokens": 133472102400, "tok_s": 159725.7}
|
| 222 |
+
{"step": 127340, "epoch": 0.809, "loss": 1.77756, "ppl": 5.915, "lr": 0.003, "grad": 0.0985, "tokens": 133493068800, "tok_s": 160079.5}
|
| 223 |
+
{"step": 127360, "epoch": 0.809, "loss": 1.71584, "ppl": 5.561, "lr": 0.003, "grad": 0.0905, "tokens": 133514035200, "tok_s": 160626.0}
|
| 224 |
+
{"step": 127380, "epoch": 0.809, "loss": 1.76355, "ppl": 5.833, "lr": 0.003, "grad": 0.1103, "tokens": 133535001600, "tok_s": 160364.2}
|
| 225 |
+
{"step": 127400, "epoch": 0.809, "loss": 1.64867, "ppl": 5.2, "lr": 0.003, "grad": 0.0974, "tokens": 133555968000, "tok_s": 160454.0}
|
| 226 |
+
{"step": 127420, "epoch": 0.81, "loss": 1.75716, "ppl": 5.796, "lr": 0.003, "grad": 0.1482, "tokens": 133576934400, "tok_s": 160848.7}
|
| 227 |
+
{"step": 127440, "epoch": 0.81, "loss": 1.75484, "ppl": 5.783, "lr": 0.003, "grad": 0.1026, "tokens": 133597900800, "tok_s": 160479.9}
|
| 228 |
+
{"step": 127460, "epoch": 0.81, "loss": 1.76275, "ppl": 5.828, "lr": 0.003, "grad": 0.1338, "tokens": 133618867200, "tok_s": 160800.3}
|
| 229 |
+
{"step": 127480, "epoch": 0.81, "loss": 1.91545, "ppl": 6.79, "lr": 0.003, "grad": 0.1262, "tokens": 133639833600, "tok_s": 160676.1}
|
| 230 |
+
{"step": 127500, "epoch": 0.81, "loss": 1.794, "ppl": 6.013, "lr": 0.003, "grad": 0.1437, "tokens": 133660800000, "tok_s": 160438.4}
|
| 231 |
+
{"step": 127520, "epoch": 0.81, "loss": 1.7449, "ppl": 5.725, "lr": 0.003, "grad": 0.0922, "tokens": 133681766400, "tok_s": 160435.7}
|
| 232 |
+
{"step": 127540, "epoch": 0.81, "loss": 1.73878, "ppl": 5.69, "lr": 0.003, "grad": 0.1031, "tokens": 133702732800, "tok_s": 160324.9}
|
| 233 |
+
{"step": 127560, "epoch": 0.81, "loss": 1.80916, "ppl": 6.105, "lr": 0.003, "grad": 0.13, "tokens": 133723699200, "tok_s": 159754.0}
|
| 234 |
+
{"step": 127580, "epoch": 0.811, "loss": 1.72088, "ppl": 5.589, "lr": 0.003, "grad": 0.1295, "tokens": 133744665600, "tok_s": 159800.5}
|
| 235 |
+
{"step": 127600, "epoch": 0.811, "loss": 1.75382, "ppl": 5.777, "lr": 0.003, "grad": 0.0752, "tokens": 133765632000, "tok_s": 160349.6}
|
| 236 |
+
{"step": 127620, "epoch": 0.811, "loss": 1.76942, "ppl": 5.867, "lr": 0.003, "grad": 0.1343, "tokens": 133786598400, "tok_s": 160526.8}
|
| 237 |
+
{"step": 127640, "epoch": 0.811, "loss": 1.74053, "ppl": 5.7, "lr": 0.003, "grad": 0.1066, "tokens": 133807564800, "tok_s": 160317.6}
|
| 238 |
+
{"step": 127660, "epoch": 0.811, "loss": 1.71334, "ppl": 5.547, "lr": 0.003, "grad": 0.1572, "tokens": 133828531200, "tok_s": 160039.8}
|
| 239 |
+
{"step": 127680, "epoch": 0.811, "loss": 1.7977, "ppl": 6.036, "lr": 0.003, "grad": 0.0828, "tokens": 133849497600, "tok_s": 160702.9}
|
| 240 |
+
{"step": 127700, "epoch": 0.811, "loss": 1.71036, "ppl": 5.531, "lr": 0.003, "grad": 0.141, "tokens": 133870464000, "tok_s": 160307.8}
|
| 241 |
+
{"step": 127720, "epoch": 0.811, "loss": 1.7398, "ppl": 5.696, "lr": 0.003, "grad": 0.1005, "tokens": 133891430400, "tok_s": 160200.0}
|
| 242 |
+
{"step": 127740, "epoch": 0.812, "loss": 1.7658, "ppl": 5.846, "lr": 0.003, "grad": 0.141, "tokens": 133912396800, "tok_s": 160177.9}
|
| 243 |
+
{"step": 127760, "epoch": 0.812, "loss": 1.77974, "ppl": 5.928, "lr": 0.003, "grad": 0.1217, "tokens": 133933363200, "tok_s": 159698.8}
|
| 244 |
+
{"step": 127780, "epoch": 0.812, "loss": 1.7341, "ppl": 5.664, "lr": 0.003, "grad": 0.1014, "tokens": 133954329600, "tok_s": 160135.3}
|
| 245 |
+
{"step": 127800, "epoch": 0.812, "loss": 1.76945, "ppl": 5.868, "lr": 0.003, "grad": 0.1303, "tokens": 133975296000, "tok_s": 160387.4}
|
| 246 |
+
{"step": 127820, "epoch": 0.812, "loss": 1.70424, "ppl": 5.497, "lr": 0.003, "grad": 0.0919, "tokens": 133996262400, "tok_s": 160082.2}
|
| 247 |
+
{"step": 127840, "epoch": 0.812, "loss": 1.74908, "ppl": 5.749, "lr": 0.003, "grad": 0.0998, "tokens": 134017228800, "tok_s": 160647.0}
|
| 248 |
+
{"step": 127860, "epoch": 0.812, "loss": 1.75608, "ppl": 5.79, "lr": 0.003, "grad": 0.0981, "tokens": 134038195200, "tok_s": 160741.8}
|
| 249 |
+
{"step": 127880, "epoch": 0.813, "loss": 1.66695, "ppl": 5.296, "lr": 0.003, "grad": 0.1051, "tokens": 134059161600, "tok_s": 160717.6}
|
| 250 |
+
{"step": 127900, "epoch": 0.813, "loss": 1.75347, "ppl": 5.775, "lr": 0.003, "grad": 0.1086, "tokens": 134080128000, "tok_s": 160835.0}
|
| 251 |
+
{"step": 127920, "epoch": 0.813, "loss": 1.7374, "ppl": 5.683, "lr": 0.003, "grad": 0.1161, "tokens": 134101094400, "tok_s": 160739.6}
|
| 252 |
+
{"step": 127940, "epoch": 0.813, "loss": 1.72691, "ppl": 5.623, "lr": 0.003, "grad": 0.0864, "tokens": 134122060800, "tok_s": 160788.3}
|
| 253 |
+
{"step": 127960, "epoch": 0.813, "loss": 1.69924, "ppl": 5.47, "lr": 0.003, "grad": 0.098, "tokens": 134143027200, "tok_s": 160634.9}
|
| 254 |
+
{"step": 127980, "epoch": 0.813, "loss": 1.7638, "ppl": 5.835, "lr": 0.003, "grad": 0.0866, "tokens": 134163993600, "tok_s": 160787.1}
|
| 255 |
+
{"step": 128000, "epoch": 0.813, "loss": 1.78116, "ppl": 5.937, "lr": 0.003, "grad": 0.1388, "tokens": 134184960000, "tok_s": 160974.9}
|
| 256 |
+
{"step": 128000, "val_loss": 1.7506, "val_ppl": 5.758, "is_best": false}
|
| 257 |
+
{"step": 128020, "epoch": 0.813, "loss": 1.85085, "ppl": 6.365, "lr": 0.003, "grad": 0.1359, "tokens": 134205926400, "tok_s": 160756.2}
|
| 258 |
+
{"step": 128040, "epoch": 0.814, "loss": 1.59879, "ppl": 4.947, "lr": 0.003, "grad": 0.2, "tokens": 134226892800, "tok_s": 160936.7}
|
| 259 |
+
{"step": 128060, "epoch": 0.814, "loss": 1.79925, "ppl": 6.045, "lr": 0.003, "grad": 0.0925, "tokens": 134247859200, "tok_s": 160906.6}
|
| 260 |
+
{"step": 128080, "epoch": 0.814, "loss": 1.8617, "ppl": 6.435, "lr": 0.003, "grad": 0.1302, "tokens": 134268825600, "tok_s": 160512.0}
|
| 261 |
+
{"step": 128100, "epoch": 0.814, "loss": 1.78102, "ppl": 5.936, "lr": 0.003, "grad": 0.0622, "tokens": 134289792000, "tok_s": 160901.4}
|
| 262 |
+
{"step": 128120, "epoch": 0.814, "loss": 1.81264, "ppl": 6.127, "lr": 0.003, "grad": 0.1206, "tokens": 134310758400, "tok_s": 160857.5}
|
| 263 |
+
{"step": 128140, "epoch": 0.814, "loss": 1.78959, "ppl": 5.987, "lr": 0.003, "grad": 0.1066, "tokens": 134331724800, "tok_s": 160846.0}
|
| 264 |
+
{"step": 128160, "epoch": 0.814, "loss": 1.78255, "ppl": 5.945, "lr": 0.003, "grad": 0.0878, "tokens": 134352691200, "tok_s": 160820.3}
|
| 265 |
+
{"step": 128180, "epoch": 0.814, "loss": 1.75908, "ppl": 5.807, "lr": 0.003, "grad": 0.1328, "tokens": 134373657600, "tok_s": 160696.6}
|
| 266 |
+
{"step": 128200, "epoch": 0.815, "loss": 1.81457, "ppl": 6.138, "lr": 0.003, "grad": 0.1396, "tokens": 134394624000, "tok_s": 160662.1}
|
| 267 |
+
{"step": 128220, "epoch": 0.815, "loss": 1.6476, "ppl": 5.195, "lr": 0.003, "grad": 0.0684, "tokens": 134415590400, "tok_s": 160729.7}
|
| 268 |
+
{"step": 128240, "epoch": 0.815, "loss": 1.76589, "ppl": 5.847, "lr": 0.003, "grad": 0.1395, "tokens": 134436556800, "tok_s": 160891.6}
|
| 269 |
+
{"step": 128260, "epoch": 0.815, "loss": 1.77899, "ppl": 5.924, "lr": 0.003, "grad": 0.0915, "tokens": 134457523200, "tok_s": 160759.9}
|
| 270 |
+
{"step": 128280, "epoch": 0.815, "loss": 1.69956, "ppl": 5.472, "lr": 0.003, "grad": 0.1477, "tokens": 134478489600, "tok_s": 160736.4}
|
| 271 |
+
{"step": 128300, "epoch": 0.815, "loss": 1.71109, "ppl": 5.535, "lr": 0.003, "grad": 0.1351, "tokens": 134499456000, "tok_s": 160821.1}
|
| 272 |
+
{"step": 128320, "epoch": 0.815, "loss": 1.73063, "ppl": 5.644, "lr": 0.003, "grad": 0.0619, "tokens": 134520422400, "tok_s": 160789.5}
|
| 273 |
+
{"step": 128340, "epoch": 0.815, "loss": 1.7474, "ppl": 5.74, "lr": 0.003, "grad": 0.1584, "tokens": 134541388800, "tok_s": 160813.4}
|
| 274 |
+
{"step": 128360, "epoch": 0.816, "loss": 1.79195, "ppl": 6.001, "lr": 0.003, "grad": 0.1447, "tokens": 134562355200, "tok_s": 160702.7}
|
| 275 |
+
{"step": 128380, "epoch": 0.816, "loss": 1.71244, "ppl": 5.542, "lr": 0.003, "grad": 0.1063, "tokens": 134583321600, "tok_s": 160898.9}
|
| 276 |
+
{"step": 128400, "epoch": 0.816, "loss": 1.75266, "ppl": 5.77, "lr": 0.003, "grad": 0.1657, "tokens": 134604288000, "tok_s": 160870.7}
|
| 277 |
+
{"step": 128420, "epoch": 0.816, "loss": 1.75168, "ppl": 5.764, "lr": 0.003, "grad": 0.0889, "tokens": 134625254400, "tok_s": 160582.5}
|
| 278 |
+
{"step": 128440, "epoch": 0.816, "loss": 1.74443, "ppl": 5.723, "lr": 0.003, "grad": 0.0925, "tokens": 134646220800, "tok_s": 161073.9}
|
| 279 |
+
{"step": 128460, "epoch": 0.816, "loss": 1.62631, "ppl": 5.085, "lr": 0.003, "grad": 0.1345, "tokens": 134667187200, "tok_s": 160791.9}
|
| 280 |
+
{"step": 128480, "epoch": 0.816, "loss": 1.75591, "ppl": 5.789, "lr": 0.003, "grad": 0.1186, "tokens": 134688153600, "tok_s": 161012.8}
|
| 281 |
+
{"step": 128500, "epoch": 0.816, "loss": 1.7579, "ppl": 5.8, "lr": 0.003, "grad": 0.0744, "tokens": 134709120000, "tok_s": 160930.7}
|
| 282 |
+
{"step": 128520, "epoch": 0.817, "loss": 1.74393, "ppl": 5.72, "lr": 0.003, "grad": 0.0949, "tokens": 134730086400, "tok_s": 160836.4}
|
| 283 |
+
{"step": 128540, "epoch": 0.817, "loss": 1.76127, "ppl": 5.82, "lr": 0.003, "grad": 0.1142, "tokens": 134751052800, "tok_s": 160890.1}
|
| 284 |
+
{"step": 128560, "epoch": 0.817, "loss": 1.80022, "ppl": 6.051, "lr": 0.003, "grad": 0.1217, "tokens": 134772019200, "tok_s": 160791.1}
|
| 285 |
+
{"step": 128580, "epoch": 0.817, "loss": 1.80679, "ppl": 6.091, "lr": 0.003, "grad": 0.1175, "tokens": 134792985600, "tok_s": 160844.9}
|
| 286 |
+
{"step": 128600, "epoch": 0.817, "loss": 1.7443, "ppl": 5.722, "lr": 0.003, "grad": 0.0966, "tokens": 134813952000, "tok_s": 160932.8}
|
| 287 |
+
{"step": 128620, "epoch": 0.817, "loss": 1.75702, "ppl": 5.795, "lr": 0.003, "grad": 0.1249, "tokens": 134834918400, "tok_s": 160555.8}
|
| 288 |
+
{"step": 128640, "epoch": 0.817, "loss": 1.68286, "ppl": 5.381, "lr": 0.003, "grad": 0.0989, "tokens": 134855884800, "tok_s": 161004.5}
|
| 289 |
+
{"step": 128660, "epoch": 0.817, "loss": 1.75465, "ppl": 5.781, "lr": 0.003, "grad": 0.1042, "tokens": 134876851200, "tok_s": 160844.7}
|
| 290 |
+
{"step": 128680, "epoch": 0.818, "loss": 1.7471, "ppl": 5.738, "lr": 0.003, "grad": 0.1053, "tokens": 134897817600, "tok_s": 160572.5}
|
| 291 |
+
{"step": 128700, "epoch": 0.818, "loss": 1.80047, "ppl": 6.052, "lr": 0.003, "grad": 0.1113, "tokens": 134918784000, "tok_s": 160812.4}
|
| 292 |
+
{"step": 128720, "epoch": 0.818, "loss": 1.71832, "ppl": 5.575, "lr": 0.003, "grad": 0.1494, "tokens": 134939750400, "tok_s": 160803.9}
|
| 293 |
+
{"step": 128740, "epoch": 0.818, "loss": 1.79292, "ppl": 6.007, "lr": 0.003, "grad": 0.1386, "tokens": 134960716800, "tok_s": 160712.4}
|
| 294 |
+
{"step": 128760, "epoch": 0.818, "loss": 1.69755, "ppl": 5.461, "lr": 0.003, "grad": 0.111, "tokens": 134981683200, "tok_s": 160792.2}
|
| 295 |
+
{"step": 128780, "epoch": 0.818, "loss": 1.7924, "ppl": 6.004, "lr": 0.003, "grad": 0.1079, "tokens": 135002649600, "tok_s": 160630.6}
|
| 296 |
+
{"step": 128800, "epoch": 0.818, "loss": 1.61462, "ppl": 5.026, "lr": 0.003, "grad": 0.1435, "tokens": 135023616000, "tok_s": 160569.4}
|
| 297 |
+
{"step": 128820, "epoch": 0.818, "loss": 1.75843, "ppl": 5.803, "lr": 0.003, "grad": 0.1503, "tokens": 135044582400, "tok_s": 160551.9}
|
| 298 |
+
{"step": 128840, "epoch": 0.819, "loss": 1.74922, "ppl": 5.75, "lr": 0.003, "grad": 0.1433, "tokens": 135065548800, "tok_s": 160764.2}
|
| 299 |
+
{"step": 128860, "epoch": 0.819, "loss": 1.73169, "ppl": 5.65, "lr": 0.003, "grad": 0.1143, "tokens": 135086515200, "tok_s": 160840.0}
|
| 300 |
+
{"step": 128880, "epoch": 0.819, "loss": 1.74227, "ppl": 5.71, "lr": 0.003, "grad": 0.0969, "tokens": 135107481600, "tok_s": 160916.1}
|
| 301 |
+
{"step": 128900, "epoch": 0.819, "loss": 1.78146, "ppl": 5.939, "lr": 0.003, "grad": 0.1311, "tokens": 135128448000, "tok_s": 160900.2}
|
| 302 |
+
{"step": 128920, "epoch": 0.819, "loss": 1.73835, "ppl": 5.688, "lr": 0.003, "grad": 0.1197, "tokens": 135149414400, "tok_s": 160580.5}
|
| 303 |
+
{"step": 128940, "epoch": 0.819, "loss": 1.75658, "ppl": 5.793, "lr": 0.003, "grad": 0.1288, "tokens": 135170380800, "tok_s": 160810.9}
|
| 304 |
+
{"step": 128960, "epoch": 0.819, "loss": 1.73507, "ppl": 5.669, "lr": 0.003, "grad": 0.1106, "tokens": 135191347200, "tok_s": 160762.3}
|
| 305 |
+
{"step": 128980, "epoch": 0.819, "loss": 1.50046, "ppl": 4.484, "lr": 0.003, "grad": 0.0709, "tokens": 135212313600, "tok_s": 160821.7}
|
| 306 |
+
{"step": 129000, "epoch": 0.82, "loss": 1.78163, "ppl": 5.94, "lr": 0.003, "grad": 0.1057, "tokens": 135233280000, "tok_s": 160813.6}
|
| 307 |
+
{"step": 129000, "val_loss": 1.76312, "val_ppl": 5.831, "is_best": false}
|
logs/log_13000.jsonl
ADDED
|
@@ -0,0 +1,134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 10400, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-08-25T10:47:59.907226"}
|
| 2 |
+
{"step": 10420, "epoch": 0.066, "loss": 1.81711, "ppl": 6.154, "lr": 0.003, "grad": 0.0712, "tokens": 10923494400, "tok_s": 171148.6}
|
| 3 |
+
{"step": 10440, "epoch": 0.066, "loss": 1.81787, "ppl": 6.159, "lr": 0.003, "grad": 0.086, "tokens": 10944460800, "tok_s": 171016.2}
|
| 4 |
+
{"step": 10460, "epoch": 0.066, "loss": 1.79115, "ppl": 5.996, "lr": 0.003, "grad": 0.0605, "tokens": 10965427200, "tok_s": 170717.4}
|
| 5 |
+
{"step": 10480, "epoch": 0.067, "loss": 1.67725, "ppl": 5.351, "lr": 0.003, "grad": 0.0915, "tokens": 10986393600, "tok_s": 170321.1}
|
| 6 |
+
{"step": 10500, "epoch": 0.067, "loss": 1.84034, "ppl": 6.299, "lr": 0.003, "grad": 0.0919, "tokens": 11007360000, "tok_s": 170000.9}
|
| 7 |
+
{"step": 10520, "epoch": 0.067, "loss": 1.80401, "ppl": 6.074, "lr": 0.003, "grad": 0.1176, "tokens": 11028326400, "tok_s": 168719.0}
|
| 8 |
+
{"step": 10540, "epoch": 0.067, "loss": 1.81361, "ppl": 6.133, "lr": 0.003, "grad": 0.0807, "tokens": 11049292800, "tok_s": 169165.5}
|
| 9 |
+
{"step": 10560, "epoch": 0.067, "loss": 1.74588, "ppl": 5.731, "lr": 0.003, "grad": 0.0655, "tokens": 11070259200, "tok_s": 169849.0}
|
| 10 |
+
{"step": 10580, "epoch": 0.067, "loss": 1.69691, "ppl": 5.457, "lr": 0.003, "grad": 0.0736, "tokens": 11091225600, "tok_s": 170408.2}
|
| 11 |
+
{"step": 10600, "epoch": 0.067, "loss": 1.65753, "ppl": 5.246, "lr": 0.003, "grad": 0.1223, "tokens": 11112192000, "tok_s": 169898.8}
|
| 12 |
+
{"step": 10620, "epoch": 0.067, "loss": 1.85511, "ppl": 6.392, "lr": 0.003, "grad": 0.0676, "tokens": 11133158400, "tok_s": 170415.5}
|
| 13 |
+
{"step": 10640, "epoch": 0.068, "loss": 1.77632, "ppl": 5.908, "lr": 0.003, "grad": 0.078, "tokens": 11154124800, "tok_s": 169195.0}
|
| 14 |
+
{"step": 10660, "epoch": 0.068, "loss": 1.83195, "ppl": 6.246, "lr": 0.003, "grad": 0.0815, "tokens": 11175091200, "tok_s": 168839.8}
|
| 15 |
+
{"step": 10680, "epoch": 0.068, "loss": 1.77901, "ppl": 5.924, "lr": 0.003, "grad": 0.0816, "tokens": 11196057600, "tok_s": 168644.0}
|
| 16 |
+
{"step": 10700, "epoch": 0.068, "loss": 1.8274, "ppl": 6.218, "lr": 0.003, "grad": 0.0964, "tokens": 11217024000, "tok_s": 169844.9}
|
| 17 |
+
{"step": 10720, "epoch": 0.068, "loss": 1.83423, "ppl": 6.26, "lr": 0.003, "grad": 0.0657, "tokens": 11237990400, "tok_s": 170037.3}
|
| 18 |
+
{"step": 10740, "epoch": 0.068, "loss": 1.79705, "ppl": 6.032, "lr": 0.003, "grad": 0.0661, "tokens": 11258956800, "tok_s": 170105.2}
|
| 19 |
+
{"step": 10760, "epoch": 0.068, "loss": 1.84121, "ppl": 6.304, "lr": 0.003, "grad": 0.0637, "tokens": 11279923200, "tok_s": 170654.2}
|
| 20 |
+
{"step": 10780, "epoch": 0.068, "loss": 1.75043, "ppl": 5.757, "lr": 0.003, "grad": 0.0791, "tokens": 11300889600, "tok_s": 170585.6}
|
| 21 |
+
{"step": 10800, "epoch": 0.069, "loss": 1.85313, "ppl": 6.38, "lr": 0.003, "grad": 0.0897, "tokens": 11321856000, "tok_s": 170412.0}
|
| 22 |
+
{"step": 10820, "epoch": 0.069, "loss": 1.83289, "ppl": 6.252, "lr": 0.003, "grad": 0.093, "tokens": 11342822400, "tok_s": 169777.8}
|
| 23 |
+
{"step": 10840, "epoch": 0.069, "loss": 1.73753, "ppl": 5.683, "lr": 0.003, "grad": 0.0796, "tokens": 11363788800, "tok_s": 169871.9}
|
| 24 |
+
{"step": 10860, "epoch": 0.069, "loss": 1.88449, "ppl": 6.583, "lr": 0.003, "grad": 0.0983, "tokens": 11384755200, "tok_s": 168428.7}
|
| 25 |
+
{"step": 10880, "epoch": 0.069, "loss": 1.87887, "ppl": 6.546, "lr": 0.003, "grad": 0.1103, "tokens": 11405721600, "tok_s": 169815.4}
|
| 26 |
+
{"step": 10900, "epoch": 0.069, "loss": 1.99021, "ppl": 7.317, "lr": 0.003, "grad": 0.0932, "tokens": 11426688000, "tok_s": 169229.2}
|
| 27 |
+
{"step": 10920, "epoch": 0.069, "loss": 1.83739, "ppl": 6.28, "lr": 0.003, "grad": 0.0665, "tokens": 11447654400, "tok_s": 170114.2}
|
| 28 |
+
{"step": 10940, "epoch": 0.07, "loss": 1.72401, "ppl": 5.607, "lr": 0.003, "grad": 0.0633, "tokens": 11468620800, "tok_s": 169434.3}
|
| 29 |
+
{"step": 10960, "epoch": 0.07, "loss": 1.74373, "ppl": 5.719, "lr": 0.003, "grad": 0.0749, "tokens": 11489587200, "tok_s": 170351.3}
|
| 30 |
+
{"step": 10980, "epoch": 0.07, "loss": 1.77352, "ppl": 5.892, "lr": 0.003, "grad": 0.0824, "tokens": 11510553600, "tok_s": 170245.3}
|
| 31 |
+
{"step": 11000, "epoch": 0.07, "loss": 1.70794, "ppl": 5.518, "lr": 0.003, "grad": 0.0825, "tokens": 11531520000, "tok_s": 169701.7}
|
| 32 |
+
{"step": 11000, "val_loss": 1.78679, "val_ppl": 5.97, "is_best": true}
|
| 33 |
+
{"step": 11020, "epoch": 0.07, "loss": 1.78537, "ppl": 5.962, "lr": 0.003, "grad": 0.1114, "tokens": 11552486400, "tok_s": 168368.6}
|
| 34 |
+
{"step": 11040, "epoch": 0.07, "loss": 1.72767, "ppl": 5.628, "lr": 0.003, "grad": 0.0847, "tokens": 11573452800, "tok_s": 170038.3}
|
| 35 |
+
{"step": 11060, "epoch": 0.07, "loss": 1.91423, "ppl": 6.782, "lr": 0.003, "grad": 0.0639, "tokens": 11594419200, "tok_s": 168720.1}
|
| 36 |
+
{"step": 11080, "epoch": 0.07, "loss": 1.83942, "ppl": 6.293, "lr": 0.003, "grad": 0.1332, "tokens": 11615385600, "tok_s": 170605.0}
|
| 37 |
+
{"step": 11100, "epoch": 0.071, "loss": 1.81276, "ppl": 6.127, "lr": 0.003, "grad": 0.1053, "tokens": 11636352000, "tok_s": 169208.5}
|
| 38 |
+
{"step": 11120, "epoch": 0.071, "loss": 1.73442, "ppl": 5.666, "lr": 0.003, "grad": 0.0826, "tokens": 11657318400, "tok_s": 170306.0}
|
| 39 |
+
{"step": 11140, "epoch": 0.071, "loss": 1.76826, "ppl": 5.861, "lr": 0.003, "grad": 0.0732, "tokens": 11678284800, "tok_s": 168532.0}
|
| 40 |
+
{"step": 11160, "epoch": 0.071, "loss": 1.8351, "ppl": 6.266, "lr": 0.003, "grad": 0.087, "tokens": 11699251200, "tok_s": 169730.2}
|
| 41 |
+
{"step": 11180, "epoch": 0.071, "loss": 1.74114, "ppl": 5.704, "lr": 0.003, "grad": 0.0706, "tokens": 11720217600, "tok_s": 169184.3}
|
| 42 |
+
{"step": 11200, "epoch": 0.071, "loss": 1.76407, "ppl": 5.836, "lr": 0.003, "grad": 0.099, "tokens": 11741184000, "tok_s": 169906.0}
|
| 43 |
+
{"step": 11220, "epoch": 0.071, "loss": 1.8116, "ppl": 6.12, "lr": 0.003, "grad": 0.1374, "tokens": 11762150400, "tok_s": 169469.3}
|
| 44 |
+
{"step": 11240, "epoch": 0.071, "loss": 1.74633, "ppl": 5.734, "lr": 0.003, "grad": 0.0705, "tokens": 11783116800, "tok_s": 170350.6}
|
| 45 |
+
{"step": 11260, "epoch": 0.072, "loss": 1.82017, "ppl": 6.173, "lr": 0.003, "grad": 0.0909, "tokens": 11804083200, "tok_s": 168862.4}
|
| 46 |
+
{"step": 11280, "epoch": 0.072, "loss": 1.85324, "ppl": 6.38, "lr": 0.003, "grad": 0.0762, "tokens": 11825049600, "tok_s": 169016.8}
|
| 47 |
+
{"step": 11300, "epoch": 0.072, "loss": 1.50843, "ppl": 4.52, "lr": 0.003, "grad": 0.0973, "tokens": 11846016000, "tok_s": 170226.2}
|
| 48 |
+
{"step": 11320, "epoch": 0.072, "loss": 1.74377, "ppl": 5.719, "lr": 0.003, "grad": 0.1393, "tokens": 11866982400, "tok_s": 169696.7}
|
| 49 |
+
{"step": 11340, "epoch": 0.072, "loss": 1.75525, "ppl": 5.785, "lr": 0.003, "grad": 0.0801, "tokens": 11887948800, "tok_s": 170290.7}
|
| 50 |
+
{"step": 11360, "epoch": 0.072, "loss": 1.85043, "ppl": 6.363, "lr": 0.003, "grad": 0.0813, "tokens": 11908915200, "tok_s": 170230.4}
|
| 51 |
+
{"step": 11380, "epoch": 0.072, "loss": 1.80291, "ppl": 6.067, "lr": 0.003, "grad": 0.0578, "tokens": 11929881600, "tok_s": 170729.7}
|
| 52 |
+
{"step": 11400, "epoch": 0.072, "loss": 1.9575, "ppl": 7.082, "lr": 0.003, "grad": 0.0864, "tokens": 11950848000, "tok_s": 168668.7}
|
| 53 |
+
{"step": 11420, "epoch": 0.073, "loss": 1.7998, "ppl": 6.048, "lr": 0.003, "grad": 0.09, "tokens": 11971814400, "tok_s": 170091.5}
|
| 54 |
+
{"step": 11440, "epoch": 0.073, "loss": 1.7463, "ppl": 5.733, "lr": 0.003, "grad": 0.0852, "tokens": 11992780800, "tok_s": 169692.4}
|
| 55 |
+
{"step": 11460, "epoch": 0.073, "loss": 1.84116, "ppl": 6.304, "lr": 0.003, "grad": 0.0626, "tokens": 12013747200, "tok_s": 169299.7}
|
| 56 |
+
{"step": 11480, "epoch": 0.073, "loss": 1.79223, "ppl": 6.003, "lr": 0.003, "grad": 0.0921, "tokens": 12034713600, "tok_s": 169943.5}
|
| 57 |
+
{"step": 11500, "epoch": 0.073, "loss": 1.66165, "ppl": 5.268, "lr": 0.003, "grad": 0.0543, "tokens": 12055680000, "tok_s": 169881.5}
|
| 58 |
+
{"step": 11520, "epoch": 0.073, "loss": 1.93615, "ppl": 6.932, "lr": 0.003, "grad": 0.0918, "tokens": 12076646400, "tok_s": 170386.0}
|
| 59 |
+
{"step": 11540, "epoch": 0.073, "loss": 1.8309, "ppl": 6.24, "lr": 0.003, "grad": 0.0829, "tokens": 12097612800, "tok_s": 170129.0}
|
| 60 |
+
{"step": 11560, "epoch": 0.073, "loss": 1.82006, "ppl": 6.172, "lr": 0.003, "grad": 0.1309, "tokens": 12118579200, "tok_s": 170568.7}
|
| 61 |
+
{"step": 11580, "epoch": 0.074, "loss": 1.8625, "ppl": 6.44, "lr": 0.003, "grad": 0.1423, "tokens": 12139545600, "tok_s": 170624.8}
|
| 62 |
+
{"step": 11600, "epoch": 0.074, "loss": 1.77661, "ppl": 5.91, "lr": 0.003, "grad": 0.1357, "tokens": 12160512000, "tok_s": 170361.2}
|
| 63 |
+
{"step": 11620, "epoch": 0.074, "loss": 1.8471, "ppl": 6.341, "lr": 0.003, "grad": 0.0764, "tokens": 12181478400, "tok_s": 171363.9}
|
| 64 |
+
{"step": 11640, "epoch": 0.074, "loss": 1.76031, "ppl": 5.814, "lr": 0.003, "grad": 0.1024, "tokens": 12202444800, "tok_s": 170746.7}
|
| 65 |
+
{"step": 11660, "epoch": 0.074, "loss": 1.78822, "ppl": 5.979, "lr": 0.003, "grad": 0.0694, "tokens": 12223411200, "tok_s": 170996.5}
|
| 66 |
+
{"step": 11680, "epoch": 0.074, "loss": 1.66275, "ppl": 5.274, "lr": 0.003, "grad": 0.0948, "tokens": 12244377600, "tok_s": 170823.7}
|
| 67 |
+
{"step": 11700, "epoch": 0.074, "loss": 1.8713, "ppl": 6.497, "lr": 0.003, "grad": 0.1275, "tokens": 12265344000, "tok_s": 170435.7}
|
| 68 |
+
{"step": 11720, "epoch": 0.074, "loss": 1.8123, "ppl": 6.125, "lr": 0.003, "grad": 0.0877, "tokens": 12286310400, "tok_s": 168694.4}
|
| 69 |
+
{"step": 11740, "epoch": 0.075, "loss": 1.86078, "ppl": 6.429, "lr": 0.003, "grad": 0.1272, "tokens": 12307276800, "tok_s": 169127.9}
|
| 70 |
+
{"step": 11760, "epoch": 0.075, "loss": 1.80306, "ppl": 6.068, "lr": 0.003, "grad": 0.1265, "tokens": 12328243200, "tok_s": 169783.7}
|
| 71 |
+
{"step": 11780, "epoch": 0.075, "loss": 1.90736, "ppl": 6.735, "lr": 0.003, "grad": 0.0614, "tokens": 12349209600, "tok_s": 170112.6}
|
| 72 |
+
{"step": 11800, "epoch": 0.075, "loss": 1.87756, "ppl": 6.538, "lr": 0.003, "grad": 0.0773, "tokens": 12370176000, "tok_s": 170478.9}
|
| 73 |
+
{"step": 11820, "epoch": 0.075, "loss": 1.85864, "ppl": 6.415, "lr": 0.003, "grad": 0.0842, "tokens": 12391142400, "tok_s": 171036.7}
|
| 74 |
+
{"step": 11840, "epoch": 0.075, "loss": 1.79777, "ppl": 6.036, "lr": 0.003, "grad": 0.1024, "tokens": 12412108800, "tok_s": 171585.4}
|
| 75 |
+
{"step": 11860, "epoch": 0.075, "loss": 1.83797, "ppl": 6.284, "lr": 0.003, "grad": 0.0862, "tokens": 12433075200, "tok_s": 170427.9}
|
| 76 |
+
{"step": 11880, "epoch": 0.075, "loss": 1.88886, "ppl": 6.612, "lr": 0.003, "grad": 0.0936, "tokens": 12454041600, "tok_s": 170334.5}
|
| 77 |
+
{"step": 11900, "epoch": 0.076, "loss": 1.84497, "ppl": 6.328, "lr": 0.003, "grad": 0.0948, "tokens": 12475008000, "tok_s": 170190.5}
|
| 78 |
+
{"step": 11920, "epoch": 0.076, "loss": 1.85304, "ppl": 6.379, "lr": 0.003, "grad": 0.0761, "tokens": 12495974400, "tok_s": 170717.6}
|
| 79 |
+
{"step": 11940, "epoch": 0.076, "loss": 1.77273, "ppl": 5.887, "lr": 0.003, "grad": 0.0966, "tokens": 12516940800, "tok_s": 169644.2}
|
| 80 |
+
{"step": 11960, "epoch": 0.076, "loss": 1.85574, "ppl": 6.396, "lr": 0.003, "grad": 0.0875, "tokens": 12537907200, "tok_s": 171619.0}
|
| 81 |
+
{"step": 11980, "epoch": 0.076, "loss": 1.64952, "ppl": 5.204, "lr": 0.003, "grad": 0.0757, "tokens": 12558873600, "tok_s": 171298.4}
|
| 82 |
+
{"step": 12000, "epoch": 0.076, "loss": 1.83047, "ppl": 6.237, "lr": 0.003, "grad": 0.1106, "tokens": 12579840000, "tok_s": 170734.5}
|
| 83 |
+
{"step": 12000, "val_loss": 1.80365, "val_ppl": 6.072, "is_best": false}
|
| 84 |
+
{"step": 12020, "epoch": 0.076, "loss": 1.83109, "ppl": 6.241, "lr": 0.003, "grad": 0.1094, "tokens": 12600806400, "tok_s": 170121.8}
|
| 85 |
+
{"step": 12040, "epoch": 0.076, "loss": 1.79588, "ppl": 6.025, "lr": 0.003, "grad": 0.0887, "tokens": 12621772800, "tok_s": 170837.7}
|
| 86 |
+
{"step": 12060, "epoch": 0.077, "loss": 1.84927, "ppl": 6.355, "lr": 0.003, "grad": 0.0604, "tokens": 12642739200, "tok_s": 170276.4}
|
| 87 |
+
{"step": 12080, "epoch": 0.077, "loss": 1.82097, "ppl": 6.178, "lr": 0.003, "grad": 0.1206, "tokens": 12663705600, "tok_s": 170932.5}
|
| 88 |
+
{"step": 12100, "epoch": 0.077, "loss": 1.7941, "ppl": 6.014, "lr": 0.003, "grad": 0.0754, "tokens": 12684672000, "tok_s": 170540.9}
|
| 89 |
+
{"step": 12120, "epoch": 0.077, "loss": 1.76931, "ppl": 5.867, "lr": 0.003, "grad": 0.0561, "tokens": 12705638400, "tok_s": 170201.0}
|
| 90 |
+
{"step": 12140, "epoch": 0.077, "loss": 1.81077, "ppl": 6.115, "lr": 0.003, "grad": 0.0569, "tokens": 12726604800, "tok_s": 170980.3}
|
| 91 |
+
{"step": 12160, "epoch": 0.077, "loss": 1.69938, "ppl": 5.471, "lr": 0.003, "grad": 0.0747, "tokens": 12747571200, "tok_s": 170431.2}
|
| 92 |
+
{"step": 12180, "epoch": 0.077, "loss": 1.78135, "ppl": 5.938, "lr": 0.003, "grad": 0.0932, "tokens": 12768537600, "tok_s": 170579.7}
|
| 93 |
+
{"step": 12200, "epoch": 0.078, "loss": 1.80014, "ppl": 6.051, "lr": 0.003, "grad": 0.0494, "tokens": 12789504000, "tok_s": 170534.8}
|
| 94 |
+
{"step": 12220, "epoch": 0.078, "loss": 1.82373, "ppl": 6.195, "lr": 0.003, "grad": 0.0681, "tokens": 12810470400, "tok_s": 170110.1}
|
| 95 |
+
{"step": 12240, "epoch": 0.078, "loss": 1.84308, "ppl": 6.316, "lr": 0.003, "grad": 0.0732, "tokens": 12831436800, "tok_s": 171319.2}
|
| 96 |
+
{"step": 12260, "epoch": 0.078, "loss": 1.85336, "ppl": 6.381, "lr": 0.003, "grad": 0.0711, "tokens": 12852403200, "tok_s": 171169.0}
|
| 97 |
+
{"step": 12280, "epoch": 0.078, "loss": 1.83318, "ppl": 6.254, "lr": 0.003, "grad": 0.0855, "tokens": 12873369600, "tok_s": 170281.5}
|
| 98 |
+
{"step": 12300, "epoch": 0.078, "loss": 1.8187, "ppl": 6.164, "lr": 0.003, "grad": 0.108, "tokens": 12894336000, "tok_s": 170191.1}
|
| 99 |
+
{"step": 12320, "epoch": 0.078, "loss": 1.84291, "ppl": 6.315, "lr": 0.003, "grad": 0.0976, "tokens": 12915302400, "tok_s": 170729.6}
|
| 100 |
+
{"step": 12340, "epoch": 0.078, "loss": 1.79197, "ppl": 6.001, "lr": 0.003, "grad": 0.0701, "tokens": 12936268800, "tok_s": 169684.2}
|
| 101 |
+
{"step": 12360, "epoch": 0.079, "loss": 1.81507, "ppl": 6.141, "lr": 0.003, "grad": 0.1075, "tokens": 12957235200, "tok_s": 171061.5}
|
| 102 |
+
{"step": 12380, "epoch": 0.079, "loss": 1.86015, "ppl": 6.425, "lr": 0.003, "grad": 0.086, "tokens": 12978201600, "tok_s": 170000.4}
|
| 103 |
+
{"step": 12400, "epoch": 0.079, "loss": 1.78974, "ppl": 5.988, "lr": 0.003, "grad": 0.0615, "tokens": 12999168000, "tok_s": 170352.7}
|
| 104 |
+
{"step": 12420, "epoch": 0.079, "loss": 1.8221, "ppl": 6.185, "lr": 0.003, "grad": 0.114, "tokens": 13020134400, "tok_s": 169677.2}
|
| 105 |
+
{"step": 12440, "epoch": 0.079, "loss": 1.81202, "ppl": 6.123, "lr": 0.003, "grad": 0.1018, "tokens": 13041100800, "tok_s": 170489.8}
|
| 106 |
+
{"step": 12460, "epoch": 0.079, "loss": 1.75402, "ppl": 5.778, "lr": 0.003, "grad": 0.0811, "tokens": 13062067200, "tok_s": 171146.9}
|
| 107 |
+
{"step": 12480, "epoch": 0.079, "loss": 1.82761, "ppl": 6.219, "lr": 0.003, "grad": 0.164, "tokens": 13083033600, "tok_s": 170348.3}
|
| 108 |
+
{"step": 12500, "epoch": 0.079, "loss": 1.81807, "ppl": 6.16, "lr": 0.003, "grad": 0.0929, "tokens": 13104000000, "tok_s": 170184.2}
|
| 109 |
+
{"step": 12520, "epoch": 0.08, "loss": 1.88766, "ppl": 6.604, "lr": 0.003, "grad": 0.1072, "tokens": 13124966400, "tok_s": 170370.9}
|
| 110 |
+
{"step": 12540, "epoch": 0.08, "loss": 1.83344, "ppl": 6.255, "lr": 0.003, "grad": 0.0642, "tokens": 13145932800, "tok_s": 171019.4}
|
| 111 |
+
{"step": 12560, "epoch": 0.08, "loss": 1.78591, "ppl": 5.965, "lr": 0.003, "grad": 0.1378, "tokens": 13166899200, "tok_s": 170168.5}
|
| 112 |
+
{"step": 12580, "epoch": 0.08, "loss": 1.81145, "ppl": 6.119, "lr": 0.003, "grad": 0.0856, "tokens": 13187865600, "tok_s": 170319.6}
|
| 113 |
+
{"step": 12600, "epoch": 0.08, "loss": 1.86732, "ppl": 6.471, "lr": 0.003, "grad": 0.1236, "tokens": 13208832000, "tok_s": 170917.1}
|
| 114 |
+
{"step": 12620, "epoch": 0.08, "loss": 1.76488, "ppl": 5.841, "lr": 0.003, "grad": 0.0597, "tokens": 13229798400, "tok_s": 170674.6}
|
| 115 |
+
{"step": 12640, "epoch": 0.08, "loss": 1.80873, "ppl": 6.103, "lr": 0.003, "grad": 0.0897, "tokens": 13250764800, "tok_s": 170703.7}
|
| 116 |
+
{"step": 12660, "epoch": 0.08, "loss": 1.72325, "ppl": 5.603, "lr": 0.003, "grad": 0.0985, "tokens": 13271731200, "tok_s": 170812.9}
|
| 117 |
+
{"step": 12680, "epoch": 0.081, "loss": 1.82215, "ppl": 6.185, "lr": 0.003, "grad": 0.0491, "tokens": 13292697600, "tok_s": 170692.7}
|
| 118 |
+
{"step": 12700, "epoch": 0.081, "loss": 1.84781, "ppl": 6.346, "lr": 0.003, "grad": 0.0779, "tokens": 13313664000, "tok_s": 170019.0}
|
| 119 |
+
{"step": 12720, "epoch": 0.081, "loss": 1.72912, "ppl": 5.636, "lr": 0.003, "grad": 0.0719, "tokens": 13334630400, "tok_s": 169956.2}
|
| 120 |
+
{"step": 12740, "epoch": 0.081, "loss": 1.68796, "ppl": 5.408, "lr": 0.003, "grad": 0.0618, "tokens": 13355596800, "tok_s": 169846.1}
|
| 121 |
+
{"step": 12760, "epoch": 0.081, "loss": 1.81992, "ppl": 6.171, "lr": 0.003, "grad": 0.1042, "tokens": 13376563200, "tok_s": 170400.3}
|
| 122 |
+
{"step": 12780, "epoch": 0.081, "loss": 1.79435, "ppl": 6.016, "lr": 0.003, "grad": 0.0685, "tokens": 13397529600, "tok_s": 170614.2}
|
| 123 |
+
{"step": 12800, "epoch": 0.081, "loss": 1.70796, "ppl": 5.518, "lr": 0.003, "grad": 0.0764, "tokens": 13418496000, "tok_s": 170580.3}
|
| 124 |
+
{"step": 12820, "epoch": 0.081, "loss": 1.72027, "ppl": 5.586, "lr": 0.003, "grad": 0.0862, "tokens": 13439462400, "tok_s": 170364.2}
|
| 125 |
+
{"step": 12840, "epoch": 0.082, "loss": 1.91353, "ppl": 6.777, "lr": 0.003, "grad": 0.1413, "tokens": 13460428800, "tok_s": 170605.2}
|
| 126 |
+
{"step": 12860, "epoch": 0.082, "loss": 1.70709, "ppl": 5.513, "lr": 0.003, "grad": 0.0728, "tokens": 13481395200, "tok_s": 169251.9}
|
| 127 |
+
{"step": 12880, "epoch": 0.082, "loss": 1.78023, "ppl": 5.931, "lr": 0.003, "grad": 0.0539, "tokens": 13502361600, "tok_s": 169984.2}
|
| 128 |
+
{"step": 12900, "epoch": 0.082, "loss": 1.75698, "ppl": 5.795, "lr": 0.003, "grad": 0.1274, "tokens": 13523328000, "tok_s": 170392.0}
|
| 129 |
+
{"step": 12920, "epoch": 0.082, "loss": 1.77285, "ppl": 5.888, "lr": 0.003, "grad": 0.0722, "tokens": 13544294400, "tok_s": 170865.6}
|
| 130 |
+
{"step": 12940, "epoch": 0.082, "loss": 1.77217, "ppl": 5.884, "lr": 0.003, "grad": 0.0547, "tokens": 13565260800, "tok_s": 170708.5}
|
| 131 |
+
{"step": 12960, "epoch": 0.082, "loss": 1.87023, "ppl": 6.49, "lr": 0.003, "grad": 0.1145, "tokens": 13586227200, "tok_s": 170689.1}
|
| 132 |
+
{"step": 12980, "epoch": 0.082, "loss": 1.80693, "ppl": 6.092, "lr": 0.003, "grad": 0.0941, "tokens": 13607193600, "tok_s": 170329.6}
|
| 133 |
+
{"step": 13000, "epoch": 0.083, "loss": 1.83257, "ppl": 6.25, "lr": 0.003, "grad": 0.0466, "tokens": 13628160000, "tok_s": 170577.1}
|
| 134 |
+
{"step": 13000, "val_loss": 1.8078, "val_ppl": 6.097, "is_best": false}
|
logs/log_130000.jsonl
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 129000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T20:51:27.189113"}
|
| 2 |
+
{"step": 129020, "epoch": 0.82, "loss": 1.7484, "ppl": 5.745, "lr": 0.003, "grad": 0.128, "tokens": 135254246400, "tok_s": 157033.6}
|
| 3 |
+
{"step": 129040, "epoch": 0.82, "loss": 1.7463, "ppl": 5.733, "lr": 0.003, "grad": 0.1339, "tokens": 135275212800, "tok_s": 157455.3}
|
| 4 |
+
{"step": 129060, "epoch": 0.82, "loss": 1.72289, "ppl": 5.601, "lr": 0.003, "grad": 0.0914, "tokens": 135296179200, "tok_s": 157658.8}
|
| 5 |
+
{"step": 129080, "epoch": 0.82, "loss": 1.61329, "ppl": 5.019, "lr": 0.003, "grad": 0.0695, "tokens": 135317145600, "tok_s": 157571.0}
|
| 6 |
+
{"step": 129100, "epoch": 0.82, "loss": 1.7691, "ppl": 5.866, "lr": 0.003, "grad": 0.0851, "tokens": 135338112000, "tok_s": 157376.2}
|
| 7 |
+
{"step": 129120, "epoch": 0.82, "loss": 1.73223, "ppl": 5.653, "lr": 0.003, "grad": 0.1258, "tokens": 135359078400, "tok_s": 157535.3}
|
| 8 |
+
{"step": 129140, "epoch": 0.821, "loss": 1.74594, "ppl": 5.731, "lr": 0.003, "grad": 0.1169, "tokens": 135380044800, "tok_s": 157194.1}
|
| 9 |
+
{"step": 129160, "epoch": 0.821, "loss": 1.67829, "ppl": 5.356, "lr": 0.003, "grad": 0.1458, "tokens": 135401011200, "tok_s": 157471.7}
|
| 10 |
+
{"step": 129180, "epoch": 0.821, "loss": 1.62889, "ppl": 5.098, "lr": 0.003, "grad": 0.0851, "tokens": 135421977600, "tok_s": 157698.5}
|
| 11 |
+
{"step": 129200, "epoch": 0.821, "loss": 1.58919, "ppl": 4.9, "lr": 0.003, "grad": 0.0721, "tokens": 135442944000, "tok_s": 157629.3}
|
| 12 |
+
{"step": 129220, "epoch": 0.821, "loss": 1.78037, "ppl": 5.932, "lr": 0.003, "grad": 0.104, "tokens": 135463910400, "tok_s": 157497.6}
|
| 13 |
+
{"step": 129240, "epoch": 0.821, "loss": 1.70018, "ppl": 5.475, "lr": 0.003, "grad": 0.1103, "tokens": 135484876800, "tok_s": 157761.0}
|
| 14 |
+
{"step": 129260, "epoch": 0.821, "loss": 1.76303, "ppl": 5.83, "lr": 0.003, "grad": 0.0733, "tokens": 135505843200, "tok_s": 157716.0}
|
| 15 |
+
{"step": 129280, "epoch": 0.821, "loss": 1.7109, "ppl": 5.534, "lr": 0.003, "grad": 0.0864, "tokens": 135526809600, "tok_s": 157454.0}
|
| 16 |
+
{"step": 129300, "epoch": 0.822, "loss": 1.75566, "ppl": 5.787, "lr": 0.003, "grad": 0.1019, "tokens": 135547776000, "tok_s": 157428.3}
|
| 17 |
+
{"step": 129320, "epoch": 0.822, "loss": 1.76169, "ppl": 5.822, "lr": 0.003, "grad": 0.0998, "tokens": 135568742400, "tok_s": 157312.0}
|
| 18 |
+
{"step": 129340, "epoch": 0.822, "loss": 1.72612, "ppl": 5.619, "lr": 0.003, "grad": 0.0813, "tokens": 135589708800, "tok_s": 157126.1}
|
| 19 |
+
{"step": 129360, "epoch": 0.822, "loss": 1.77206, "ppl": 5.883, "lr": 0.003, "grad": 0.0782, "tokens": 135610675200, "tok_s": 156806.1}
|
| 20 |
+
{"step": 129380, "epoch": 0.822, "loss": 1.68123, "ppl": 5.372, "lr": 0.003, "grad": 0.1173, "tokens": 135631641600, "tok_s": 157407.9}
|
| 21 |
+
{"step": 129400, "epoch": 0.822, "loss": 1.78315, "ppl": 5.949, "lr": 0.003, "grad": 0.122, "tokens": 135652608000, "tok_s": 157273.9}
|
| 22 |
+
{"step": 129420, "epoch": 0.822, "loss": 1.7614, "ppl": 5.821, "lr": 0.003, "grad": 0.1357, "tokens": 135673574400, "tok_s": 157234.6}
|
| 23 |
+
{"step": 129440, "epoch": 0.822, "loss": 1.67073, "ppl": 5.316, "lr": 0.003, "grad": 0.0705, "tokens": 135694540800, "tok_s": 157421.7}
|
| 24 |
+
{"step": 129460, "epoch": 0.823, "loss": 1.8125, "ppl": 6.126, "lr": 0.003, "grad": 0.1151, "tokens": 135715507200, "tok_s": 157245.2}
|
| 25 |
+
{"step": 129480, "epoch": 0.823, "loss": 1.80825, "ppl": 6.1, "lr": 0.003, "grad": 0.1427, "tokens": 135736473600, "tok_s": 157396.8}
|
| 26 |
+
{"step": 129500, "epoch": 0.823, "loss": 1.90675, "ppl": 6.731, "lr": 0.003, "grad": 0.1583, "tokens": 135757440000, "tok_s": 157256.3}
|
| 27 |
+
{"step": 129520, "epoch": 0.823, "loss": 1.76329, "ppl": 5.832, "lr": 0.003, "grad": 0.1181, "tokens": 135778406400, "tok_s": 157268.5}
|
| 28 |
+
{"step": 129540, "epoch": 0.823, "loss": 1.65928, "ppl": 5.256, "lr": 0.003, "grad": 0.0893, "tokens": 135799372800, "tok_s": 157524.4}
|
| 29 |
+
{"step": 129560, "epoch": 0.823, "loss": 1.67935, "ppl": 5.362, "lr": 0.003, "grad": 0.0811, "tokens": 135820339200, "tok_s": 157585.8}
|
| 30 |
+
{"step": 129580, "epoch": 0.823, "loss": 1.70283, "ppl": 5.489, "lr": 0.003, "grad": 0.0908, "tokens": 135841305600, "tok_s": 157641.4}
|
| 31 |
+
{"step": 129600, "epoch": 0.823, "loss": 1.63922, "ppl": 5.151, "lr": 0.003, "grad": 0.0788, "tokens": 135862272000, "tok_s": 157853.0}
|
| 32 |
+
{"step": 129620, "epoch": 0.824, "loss": 1.715, "ppl": 5.557, "lr": 0.003, "grad": 0.1425, "tokens": 135883238400, "tok_s": 157261.9}
|
| 33 |
+
{"step": 129640, "epoch": 0.824, "loss": 1.66125, "ppl": 5.266, "lr": 0.003, "grad": 0.1515, "tokens": 135904204800, "tok_s": 157824.0}
|
| 34 |
+
{"step": 129660, "epoch": 0.824, "loss": 1.8425, "ppl": 6.312, "lr": 0.003, "grad": 0.0936, "tokens": 135925171200, "tok_s": 157414.2}
|
| 35 |
+
{"step": 129680, "epoch": 0.824, "loss": 1.77156, "ppl": 5.88, "lr": 0.003, "grad": 0.1027, "tokens": 135946137600, "tok_s": 157952.8}
|
| 36 |
+
{"step": 129700, "epoch": 0.824, "loss": 1.74271, "ppl": 5.713, "lr": 0.003, "grad": 0.1877, "tokens": 135967104000, "tok_s": 157854.5}
|
| 37 |
+
{"step": 129720, "epoch": 0.824, "loss": 1.66564, "ppl": 5.289, "lr": 0.003, "grad": 0.0791, "tokens": 135988070400, "tok_s": 158021.8}
|
| 38 |
+
{"step": 129740, "epoch": 0.824, "loss": 1.69832, "ppl": 5.465, "lr": 0.003, "grad": 0.0909, "tokens": 136009036800, "tok_s": 157578.1}
|
| 39 |
+
{"step": 129760, "epoch": 0.824, "loss": 1.76803, "ppl": 5.859, "lr": 0.003, "grad": 0.1282, "tokens": 136030003200, "tok_s": 157033.8}
|
| 40 |
+
{"step": 129780, "epoch": 0.825, "loss": 1.67652, "ppl": 5.347, "lr": 0.003, "grad": 0.1203, "tokens": 136050969600, "tok_s": 157782.2}
|
| 41 |
+
{"step": 129800, "epoch": 0.825, "loss": 1.69139, "ppl": 5.427, "lr": 0.003, "grad": 0.0993, "tokens": 136071936000, "tok_s": 157805.7}
|
| 42 |
+
{"step": 129820, "epoch": 0.825, "loss": 1.74188, "ppl": 5.708, "lr": 0.003, "grad": 0.1586, "tokens": 136092902400, "tok_s": 157652.6}
|
| 43 |
+
{"step": 129840, "epoch": 0.825, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.1048, "tokens": 136113868800, "tok_s": 157892.9}
|
| 44 |
+
{"step": 129860, "epoch": 0.825, "loss": 1.75256, "ppl": 5.769, "lr": 0.003, "grad": 0.1189, "tokens": 136134835200, "tok_s": 157781.2}
|
| 45 |
+
{"step": 129880, "epoch": 0.825, "loss": 1.77965, "ppl": 5.928, "lr": 0.003, "grad": 0.1049, "tokens": 136155801600, "tok_s": 157693.3}
|
| 46 |
+
{"step": 129900, "epoch": 0.825, "loss": 1.45431, "ppl": 4.282, "lr": 0.003, "grad": 0.1174, "tokens": 136176768000, "tok_s": 157650.5}
|
| 47 |
+
{"step": 129920, "epoch": 0.825, "loss": 1.67703, "ppl": 5.35, "lr": 0.003, "grad": 0.1193, "tokens": 136197734400, "tok_s": 157459.6}
|
| 48 |
+
{"step": 129940, "epoch": 0.826, "loss": 1.68942, "ppl": 5.416, "lr": 0.003, "grad": 0.1002, "tokens": 136218700800, "tok_s": 157493.8}
|
| 49 |
+
{"step": 129960, "epoch": 0.826, "loss": 1.78371, "ppl": 5.952, "lr": 0.003, "grad": 0.0927, "tokens": 136239667200, "tok_s": 157312.5}
|
| 50 |
+
{"step": 129980, "epoch": 0.826, "loss": 1.73478, "ppl": 5.668, "lr": 0.003, "grad": 0.0805, "tokens": 136260633600, "tok_s": 157586.0}
|
| 51 |
+
{"step": 130000, "epoch": 0.826, "loss": 1.88894, "ppl": 6.612, "lr": 0.003, "grad": 0.1294, "tokens": 136281600000, "tok_s": 157467.5}
|
| 52 |
+
{"step": 130000, "val_loss": 1.73054, "val_ppl": 5.644, "is_best": true}
|
logs/log_131000.jsonl
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 129000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T20:51:27.189113"}
|
| 2 |
+
{"step": 129020, "epoch": 0.82, "loss": 1.7484, "ppl": 5.745, "lr": 0.003, "grad": 0.128, "tokens": 135254246400, "tok_s": 157033.6}
|
| 3 |
+
{"step": 129040, "epoch": 0.82, "loss": 1.7463, "ppl": 5.733, "lr": 0.003, "grad": 0.1339, "tokens": 135275212800, "tok_s": 157455.3}
|
| 4 |
+
{"step": 129060, "epoch": 0.82, "loss": 1.72289, "ppl": 5.601, "lr": 0.003, "grad": 0.0914, "tokens": 135296179200, "tok_s": 157658.8}
|
| 5 |
+
{"step": 129080, "epoch": 0.82, "loss": 1.61329, "ppl": 5.019, "lr": 0.003, "grad": 0.0695, "tokens": 135317145600, "tok_s": 157571.0}
|
| 6 |
+
{"step": 129100, "epoch": 0.82, "loss": 1.7691, "ppl": 5.866, "lr": 0.003, "grad": 0.0851, "tokens": 135338112000, "tok_s": 157376.2}
|
| 7 |
+
{"step": 129120, "epoch": 0.82, "loss": 1.73223, "ppl": 5.653, "lr": 0.003, "grad": 0.1258, "tokens": 135359078400, "tok_s": 157535.3}
|
| 8 |
+
{"step": 129140, "epoch": 0.821, "loss": 1.74594, "ppl": 5.731, "lr": 0.003, "grad": 0.1169, "tokens": 135380044800, "tok_s": 157194.1}
|
| 9 |
+
{"step": 129160, "epoch": 0.821, "loss": 1.67829, "ppl": 5.356, "lr": 0.003, "grad": 0.1458, "tokens": 135401011200, "tok_s": 157471.7}
|
| 10 |
+
{"step": 129180, "epoch": 0.821, "loss": 1.62889, "ppl": 5.098, "lr": 0.003, "grad": 0.0851, "tokens": 135421977600, "tok_s": 157698.5}
|
| 11 |
+
{"step": 129200, "epoch": 0.821, "loss": 1.58919, "ppl": 4.9, "lr": 0.003, "grad": 0.0721, "tokens": 135442944000, "tok_s": 157629.3}
|
| 12 |
+
{"step": 129220, "epoch": 0.821, "loss": 1.78037, "ppl": 5.932, "lr": 0.003, "grad": 0.104, "tokens": 135463910400, "tok_s": 157497.6}
|
| 13 |
+
{"step": 129240, "epoch": 0.821, "loss": 1.70018, "ppl": 5.475, "lr": 0.003, "grad": 0.1103, "tokens": 135484876800, "tok_s": 157761.0}
|
| 14 |
+
{"step": 129260, "epoch": 0.821, "loss": 1.76303, "ppl": 5.83, "lr": 0.003, "grad": 0.0733, "tokens": 135505843200, "tok_s": 157716.0}
|
| 15 |
+
{"step": 129280, "epoch": 0.821, "loss": 1.7109, "ppl": 5.534, "lr": 0.003, "grad": 0.0864, "tokens": 135526809600, "tok_s": 157454.0}
|
| 16 |
+
{"step": 129300, "epoch": 0.822, "loss": 1.75566, "ppl": 5.787, "lr": 0.003, "grad": 0.1019, "tokens": 135547776000, "tok_s": 157428.3}
|
| 17 |
+
{"step": 129320, "epoch": 0.822, "loss": 1.76169, "ppl": 5.822, "lr": 0.003, "grad": 0.0998, "tokens": 135568742400, "tok_s": 157312.0}
|
| 18 |
+
{"step": 129340, "epoch": 0.822, "loss": 1.72612, "ppl": 5.619, "lr": 0.003, "grad": 0.0813, "tokens": 135589708800, "tok_s": 157126.1}
|
| 19 |
+
{"step": 129360, "epoch": 0.822, "loss": 1.77206, "ppl": 5.883, "lr": 0.003, "grad": 0.0782, "tokens": 135610675200, "tok_s": 156806.1}
|
| 20 |
+
{"step": 129380, "epoch": 0.822, "loss": 1.68123, "ppl": 5.372, "lr": 0.003, "grad": 0.1173, "tokens": 135631641600, "tok_s": 157407.9}
|
| 21 |
+
{"step": 129400, "epoch": 0.822, "loss": 1.78315, "ppl": 5.949, "lr": 0.003, "grad": 0.122, "tokens": 135652608000, "tok_s": 157273.9}
|
| 22 |
+
{"step": 129420, "epoch": 0.822, "loss": 1.7614, "ppl": 5.821, "lr": 0.003, "grad": 0.1357, "tokens": 135673574400, "tok_s": 157234.6}
|
| 23 |
+
{"step": 129440, "epoch": 0.822, "loss": 1.67073, "ppl": 5.316, "lr": 0.003, "grad": 0.0705, "tokens": 135694540800, "tok_s": 157421.7}
|
| 24 |
+
{"step": 129460, "epoch": 0.823, "loss": 1.8125, "ppl": 6.126, "lr": 0.003, "grad": 0.1151, "tokens": 135715507200, "tok_s": 157245.2}
|
| 25 |
+
{"step": 129480, "epoch": 0.823, "loss": 1.80825, "ppl": 6.1, "lr": 0.003, "grad": 0.1427, "tokens": 135736473600, "tok_s": 157396.8}
|
| 26 |
+
{"step": 129500, "epoch": 0.823, "loss": 1.90675, "ppl": 6.731, "lr": 0.003, "grad": 0.1583, "tokens": 135757440000, "tok_s": 157256.3}
|
| 27 |
+
{"step": 129520, "epoch": 0.823, "loss": 1.76329, "ppl": 5.832, "lr": 0.003, "grad": 0.1181, "tokens": 135778406400, "tok_s": 157268.5}
|
| 28 |
+
{"step": 129540, "epoch": 0.823, "loss": 1.65928, "ppl": 5.256, "lr": 0.003, "grad": 0.0893, "tokens": 135799372800, "tok_s": 157524.4}
|
| 29 |
+
{"step": 129560, "epoch": 0.823, "loss": 1.67935, "ppl": 5.362, "lr": 0.003, "grad": 0.0811, "tokens": 135820339200, "tok_s": 157585.8}
|
| 30 |
+
{"step": 129580, "epoch": 0.823, "loss": 1.70283, "ppl": 5.489, "lr": 0.003, "grad": 0.0908, "tokens": 135841305600, "tok_s": 157641.4}
|
| 31 |
+
{"step": 129600, "epoch": 0.823, "loss": 1.63922, "ppl": 5.151, "lr": 0.003, "grad": 0.0788, "tokens": 135862272000, "tok_s": 157853.0}
|
| 32 |
+
{"step": 129620, "epoch": 0.824, "loss": 1.715, "ppl": 5.557, "lr": 0.003, "grad": 0.1425, "tokens": 135883238400, "tok_s": 157261.9}
|
| 33 |
+
{"step": 129640, "epoch": 0.824, "loss": 1.66125, "ppl": 5.266, "lr": 0.003, "grad": 0.1515, "tokens": 135904204800, "tok_s": 157824.0}
|
| 34 |
+
{"step": 129660, "epoch": 0.824, "loss": 1.8425, "ppl": 6.312, "lr": 0.003, "grad": 0.0936, "tokens": 135925171200, "tok_s": 157414.2}
|
| 35 |
+
{"step": 129680, "epoch": 0.824, "loss": 1.77156, "ppl": 5.88, "lr": 0.003, "grad": 0.1027, "tokens": 135946137600, "tok_s": 157952.8}
|
| 36 |
+
{"step": 129700, "epoch": 0.824, "loss": 1.74271, "ppl": 5.713, "lr": 0.003, "grad": 0.1877, "tokens": 135967104000, "tok_s": 157854.5}
|
| 37 |
+
{"step": 129720, "epoch": 0.824, "loss": 1.66564, "ppl": 5.289, "lr": 0.003, "grad": 0.0791, "tokens": 135988070400, "tok_s": 158021.8}
|
| 38 |
+
{"step": 129740, "epoch": 0.824, "loss": 1.69832, "ppl": 5.465, "lr": 0.003, "grad": 0.0909, "tokens": 136009036800, "tok_s": 157578.1}
|
| 39 |
+
{"step": 129760, "epoch": 0.824, "loss": 1.76803, "ppl": 5.859, "lr": 0.003, "grad": 0.1282, "tokens": 136030003200, "tok_s": 157033.8}
|
| 40 |
+
{"step": 129780, "epoch": 0.825, "loss": 1.67652, "ppl": 5.347, "lr": 0.003, "grad": 0.1203, "tokens": 136050969600, "tok_s": 157782.2}
|
| 41 |
+
{"step": 129800, "epoch": 0.825, "loss": 1.69139, "ppl": 5.427, "lr": 0.003, "grad": 0.0993, "tokens": 136071936000, "tok_s": 157805.7}
|
| 42 |
+
{"step": 129820, "epoch": 0.825, "loss": 1.74188, "ppl": 5.708, "lr": 0.003, "grad": 0.1586, "tokens": 136092902400, "tok_s": 157652.6}
|
| 43 |
+
{"step": 129840, "epoch": 0.825, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.1048, "tokens": 136113868800, "tok_s": 157892.9}
|
| 44 |
+
{"step": 129860, "epoch": 0.825, "loss": 1.75256, "ppl": 5.769, "lr": 0.003, "grad": 0.1189, "tokens": 136134835200, "tok_s": 157781.2}
|
| 45 |
+
{"step": 129880, "epoch": 0.825, "loss": 1.77965, "ppl": 5.928, "lr": 0.003, "grad": 0.1049, "tokens": 136155801600, "tok_s": 157693.3}
|
| 46 |
+
{"step": 129900, "epoch": 0.825, "loss": 1.45431, "ppl": 4.282, "lr": 0.003, "grad": 0.1174, "tokens": 136176768000, "tok_s": 157650.5}
|
| 47 |
+
{"step": 129920, "epoch": 0.825, "loss": 1.67703, "ppl": 5.35, "lr": 0.003, "grad": 0.1193, "tokens": 136197734400, "tok_s": 157459.6}
|
| 48 |
+
{"step": 129940, "epoch": 0.826, "loss": 1.68942, "ppl": 5.416, "lr": 0.003, "grad": 0.1002, "tokens": 136218700800, "tok_s": 157493.8}
|
| 49 |
+
{"step": 129960, "epoch": 0.826, "loss": 1.78371, "ppl": 5.952, "lr": 0.003, "grad": 0.0927, "tokens": 136239667200, "tok_s": 157312.5}
|
| 50 |
+
{"step": 129980, "epoch": 0.826, "loss": 1.73478, "ppl": 5.668, "lr": 0.003, "grad": 0.0805, "tokens": 136260633600, "tok_s": 157586.0}
|
| 51 |
+
{"step": 130000, "epoch": 0.826, "loss": 1.88894, "ppl": 6.612, "lr": 0.003, "grad": 0.1294, "tokens": 136281600000, "tok_s": 157467.5}
|
| 52 |
+
{"step": 130000, "val_loss": 1.73054, "val_ppl": 5.644, "is_best": true}
|
| 53 |
+
{"step": 130020, "epoch": 0.826, "loss": 1.73526, "ppl": 5.67, "lr": 0.003, "grad": 0.129, "tokens": 136302566400, "tok_s": 157572.7}
|
| 54 |
+
{"step": 130040, "epoch": 0.826, "loss": 1.67846, "ppl": 5.357, "lr": 0.003, "grad": 0.1445, "tokens": 136323532800, "tok_s": 157713.9}
|
| 55 |
+
{"step": 130060, "epoch": 0.826, "loss": 1.77431, "ppl": 5.896, "lr": 0.003, "grad": 0.1509, "tokens": 136344499200, "tok_s": 157621.4}
|
| 56 |
+
{"step": 130080, "epoch": 0.826, "loss": 1.72493, "ppl": 5.612, "lr": 0.003, "grad": 0.1217, "tokens": 136365465600, "tok_s": 157750.6}
|
| 57 |
+
{"step": 130100, "epoch": 0.827, "loss": 1.59641, "ppl": 4.935, "lr": 0.003, "grad": 0.1226, "tokens": 136386432000, "tok_s": 157654.8}
|
| 58 |
+
{"step": 130120, "epoch": 0.827, "loss": 1.86963, "ppl": 6.486, "lr": 0.003, "grad": 0.126, "tokens": 136407398400, "tok_s": 157206.8}
|
| 59 |
+
{"step": 130140, "epoch": 0.827, "loss": 1.76439, "ppl": 5.838, "lr": 0.003, "grad": 0.0794, "tokens": 136428364800, "tok_s": 157463.5}
|
| 60 |
+
{"step": 130160, "epoch": 0.827, "loss": 1.75045, "ppl": 5.757, "lr": 0.003, "grad": 0.1228, "tokens": 136449331200, "tok_s": 157764.7}
|
| 61 |
+
{"step": 130180, "epoch": 0.827, "loss": 1.79344, "ppl": 6.01, "lr": 0.003, "grad": 0.1249, "tokens": 136470297600, "tok_s": 157403.3}
|
| 62 |
+
{"step": 130200, "epoch": 0.827, "loss": 1.7078, "ppl": 5.517, "lr": 0.003, "grad": 0.1528, "tokens": 136491264000, "tok_s": 157600.0}
|
| 63 |
+
{"step": 130220, "epoch": 0.827, "loss": 1.7805, "ppl": 5.933, "lr": 0.003, "grad": 0.1495, "tokens": 136512230400, "tok_s": 157095.7}
|
| 64 |
+
{"step": 130240, "epoch": 0.827, "loss": 1.69056, "ppl": 5.423, "lr": 0.003, "grad": 0.0973, "tokens": 136533196800, "tok_s": 157330.4}
|
| 65 |
+
{"step": 130260, "epoch": 0.828, "loss": 1.72071, "ppl": 5.589, "lr": 0.003, "grad": 0.1227, "tokens": 136554163200, "tok_s": 157583.4}
|
| 66 |
+
{"step": 130280, "epoch": 0.828, "loss": 1.60413, "ppl": 4.974, "lr": 0.003, "grad": 0.0853, "tokens": 136575129600, "tok_s": 157614.5}
|
| 67 |
+
{"step": 130300, "epoch": 0.828, "loss": 1.80194, "ppl": 6.061, "lr": 0.003, "grad": 0.1207, "tokens": 136596096000, "tok_s": 157752.1}
|
| 68 |
+
{"step": 130320, "epoch": 0.828, "loss": 1.74305, "ppl": 5.715, "lr": 0.003, "grad": 0.0819, "tokens": 136617062400, "tok_s": 157633.7}
|
| 69 |
+
{"step": 130340, "epoch": 0.828, "loss": 1.79549, "ppl": 6.022, "lr": 0.003, "grad": 0.1231, "tokens": 136638028800, "tok_s": 157535.5}
|
| 70 |
+
{"step": 130360, "epoch": 0.828, "loss": 1.73445, "ppl": 5.666, "lr": 0.003, "grad": 0.1615, "tokens": 136658995200, "tok_s": 157510.3}
|
| 71 |
+
{"step": 130380, "epoch": 0.828, "loss": 1.84461, "ppl": 6.326, "lr": 0.003, "grad": 0.1089, "tokens": 136679961600, "tok_s": 157324.6}
|
| 72 |
+
{"step": 130400, "epoch": 0.829, "loss": 1.81211, "ppl": 6.123, "lr": 0.003, "grad": 0.0719, "tokens": 136700928000, "tok_s": 157495.8}
|
| 73 |
+
{"step": 130420, "epoch": 0.829, "loss": 1.79467, "ppl": 6.017, "lr": 0.003, "grad": 0.1391, "tokens": 136721894400, "tok_s": 157411.2}
|
| 74 |
+
{"step": 130440, "epoch": 0.829, "loss": 1.73476, "ppl": 5.668, "lr": 0.003, "grad": 0.1071, "tokens": 136742860800, "tok_s": 157766.3}
|
| 75 |
+
{"step": 130460, "epoch": 0.829, "loss": 1.77554, "ppl": 5.903, "lr": 0.003, "grad": 0.1642, "tokens": 136763827200, "tok_s": 157367.3}
|
| 76 |
+
{"step": 130480, "epoch": 0.829, "loss": 1.82101, "ppl": 6.178, "lr": 0.003, "grad": 0.152, "tokens": 136784793600, "tok_s": 157044.7}
|
| 77 |
+
{"step": 130500, "epoch": 0.829, "loss": 1.77909, "ppl": 5.924, "lr": 0.003, "grad": 0.0888, "tokens": 136805760000, "tok_s": 157331.6}
|
| 78 |
+
{"step": 130520, "epoch": 0.829, "loss": 1.78449, "ppl": 5.957, "lr": 0.003, "grad": 0.1207, "tokens": 136826726400, "tok_s": 157559.0}
|
| 79 |
+
{"step": 130540, "epoch": 0.829, "loss": 1.70914, "ppl": 5.524, "lr": 0.003, "grad": 0.0981, "tokens": 136847692800, "tok_s": 157448.7}
|
| 80 |
+
{"step": 130560, "epoch": 0.83, "loss": 1.79092, "ppl": 5.995, "lr": 0.003, "grad": 0.15, "tokens": 136868659200, "tok_s": 157276.3}
|
| 81 |
+
{"step": 130580, "epoch": 0.83, "loss": 1.59137, "ppl": 4.91, "lr": 0.003, "grad": 0.0904, "tokens": 136889625600, "tok_s": 157370.7}
|
| 82 |
+
{"step": 130600, "epoch": 0.83, "loss": 1.76625, "ppl": 5.849, "lr": 0.003, "grad": 0.1367, "tokens": 136910592000, "tok_s": 157680.7}
|
| 83 |
+
{"step": 130620, "epoch": 0.83, "loss": 1.76693, "ppl": 5.853, "lr": 0.003, "grad": 0.0967, "tokens": 136931558400, "tok_s": 157881.4}
|
| 84 |
+
{"step": 130640, "epoch": 0.83, "loss": 1.73096, "ppl": 5.646, "lr": 0.003, "grad": 0.1168, "tokens": 136952524800, "tok_s": 157890.0}
|
| 85 |
+
{"step": 130660, "epoch": 0.83, "loss": 1.78401, "ppl": 5.954, "lr": 0.003, "grad": 0.0815, "tokens": 136973491200, "tok_s": 157896.6}
|
| 86 |
+
{"step": 130680, "epoch": 0.83, "loss": 1.75759, "ppl": 5.798, "lr": 0.003, "grad": 0.1412, "tokens": 136994457600, "tok_s": 157487.0}
|
| 87 |
+
{"step": 130700, "epoch": 0.83, "loss": 1.72975, "ppl": 5.639, "lr": 0.003, "grad": 0.0976, "tokens": 137015424000, "tok_s": 157535.5}
|
| 88 |
+
{"step": 130720, "epoch": 0.831, "loss": 1.70747, "ppl": 5.515, "lr": 0.003, "grad": 0.0945, "tokens": 137036390400, "tok_s": 157837.2}
|
| 89 |
+
{"step": 130740, "epoch": 0.831, "loss": 1.74526, "ppl": 5.727, "lr": 0.003, "grad": 0.0914, "tokens": 137057356800, "tok_s": 157859.8}
|
| 90 |
+
{"step": 130760, "epoch": 0.831, "loss": 1.63925, "ppl": 5.151, "lr": 0.003, "grad": 0.1153, "tokens": 137078323200, "tok_s": 158056.6}
|
| 91 |
+
{"step": 130780, "epoch": 0.831, "loss": 1.71553, "ppl": 5.56, "lr": 0.003, "grad": 0.1075, "tokens": 137099289600, "tok_s": 158017.2}
|
| 92 |
+
{"step": 130800, "epoch": 0.831, "loss": 1.73857, "ppl": 5.689, "lr": 0.003, "grad": 0.0948, "tokens": 137120256000, "tok_s": 157914.3}
|
| 93 |
+
{"step": 130820, "epoch": 0.831, "loss": 1.76271, "ppl": 5.828, "lr": 0.003, "grad": 0.1691, "tokens": 137141222400, "tok_s": 157998.3}
|
| 94 |
+
{"step": 130840, "epoch": 0.831, "loss": 1.7782, "ppl": 5.919, "lr": 0.003, "grad": 0.1244, "tokens": 137162188800, "tok_s": 157819.2}
|
| 95 |
+
{"step": 130860, "epoch": 0.831, "loss": 1.78937, "ppl": 5.986, "lr": 0.003, "grad": 0.0636, "tokens": 137183155200, "tok_s": 158018.9}
|
| 96 |
+
{"step": 130880, "epoch": 0.832, "loss": 1.76957, "ppl": 5.868, "lr": 0.003, "grad": 0.1611, "tokens": 137204121600, "tok_s": 157905.5}
|
| 97 |
+
{"step": 130900, "epoch": 0.832, "loss": 1.75428, "ppl": 5.779, "lr": 0.003, "grad": 0.1247, "tokens": 137225088000, "tok_s": 157896.3}
|
| 98 |
+
{"step": 130920, "epoch": 0.832, "loss": 1.77733, "ppl": 5.914, "lr": 0.003, "grad": 0.1442, "tokens": 137246054400, "tok_s": 157771.9}
|
| 99 |
+
{"step": 130940, "epoch": 0.832, "loss": 1.72573, "ppl": 5.617, "lr": 0.003, "grad": 0.0854, "tokens": 137267020800, "tok_s": 157898.0}
|
| 100 |
+
{"step": 130960, "epoch": 0.832, "loss": 1.7495, "ppl": 5.752, "lr": 0.003, "grad": 0.1204, "tokens": 137287987200, "tok_s": 157906.9}
|
| 101 |
+
{"step": 130980, "epoch": 0.832, "loss": 1.79697, "ppl": 6.031, "lr": 0.003, "grad": 0.1363, "tokens": 137308953600, "tok_s": 157812.5}
|
| 102 |
+
{"step": 131000, "epoch": 0.832, "loss": 1.72455, "ppl": 5.61, "lr": 0.003, "grad": 0.0756, "tokens": 137329920000, "tok_s": 157721.2}
|
| 103 |
+
{"step": 131000, "val_loss": 1.74218, "val_ppl": 5.71, "is_best": false}
|
logs/log_132000.jsonl
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 129000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T20:51:27.189113"}
|
| 2 |
+
{"step": 129020, "epoch": 0.82, "loss": 1.7484, "ppl": 5.745, "lr": 0.003, "grad": 0.128, "tokens": 135254246400, "tok_s": 157033.6}
|
| 3 |
+
{"step": 129040, "epoch": 0.82, "loss": 1.7463, "ppl": 5.733, "lr": 0.003, "grad": 0.1339, "tokens": 135275212800, "tok_s": 157455.3}
|
| 4 |
+
{"step": 129060, "epoch": 0.82, "loss": 1.72289, "ppl": 5.601, "lr": 0.003, "grad": 0.0914, "tokens": 135296179200, "tok_s": 157658.8}
|
| 5 |
+
{"step": 129080, "epoch": 0.82, "loss": 1.61329, "ppl": 5.019, "lr": 0.003, "grad": 0.0695, "tokens": 135317145600, "tok_s": 157571.0}
|
| 6 |
+
{"step": 129100, "epoch": 0.82, "loss": 1.7691, "ppl": 5.866, "lr": 0.003, "grad": 0.0851, "tokens": 135338112000, "tok_s": 157376.2}
|
| 7 |
+
{"step": 129120, "epoch": 0.82, "loss": 1.73223, "ppl": 5.653, "lr": 0.003, "grad": 0.1258, "tokens": 135359078400, "tok_s": 157535.3}
|
| 8 |
+
{"step": 129140, "epoch": 0.821, "loss": 1.74594, "ppl": 5.731, "lr": 0.003, "grad": 0.1169, "tokens": 135380044800, "tok_s": 157194.1}
|
| 9 |
+
{"step": 129160, "epoch": 0.821, "loss": 1.67829, "ppl": 5.356, "lr": 0.003, "grad": 0.1458, "tokens": 135401011200, "tok_s": 157471.7}
|
| 10 |
+
{"step": 129180, "epoch": 0.821, "loss": 1.62889, "ppl": 5.098, "lr": 0.003, "grad": 0.0851, "tokens": 135421977600, "tok_s": 157698.5}
|
| 11 |
+
{"step": 129200, "epoch": 0.821, "loss": 1.58919, "ppl": 4.9, "lr": 0.003, "grad": 0.0721, "tokens": 135442944000, "tok_s": 157629.3}
|
| 12 |
+
{"step": 129220, "epoch": 0.821, "loss": 1.78037, "ppl": 5.932, "lr": 0.003, "grad": 0.104, "tokens": 135463910400, "tok_s": 157497.6}
|
| 13 |
+
{"step": 129240, "epoch": 0.821, "loss": 1.70018, "ppl": 5.475, "lr": 0.003, "grad": 0.1103, "tokens": 135484876800, "tok_s": 157761.0}
|
| 14 |
+
{"step": 129260, "epoch": 0.821, "loss": 1.76303, "ppl": 5.83, "lr": 0.003, "grad": 0.0733, "tokens": 135505843200, "tok_s": 157716.0}
|
| 15 |
+
{"step": 129280, "epoch": 0.821, "loss": 1.7109, "ppl": 5.534, "lr": 0.003, "grad": 0.0864, "tokens": 135526809600, "tok_s": 157454.0}
|
| 16 |
+
{"step": 129300, "epoch": 0.822, "loss": 1.75566, "ppl": 5.787, "lr": 0.003, "grad": 0.1019, "tokens": 135547776000, "tok_s": 157428.3}
|
| 17 |
+
{"step": 129320, "epoch": 0.822, "loss": 1.76169, "ppl": 5.822, "lr": 0.003, "grad": 0.0998, "tokens": 135568742400, "tok_s": 157312.0}
|
| 18 |
+
{"step": 129340, "epoch": 0.822, "loss": 1.72612, "ppl": 5.619, "lr": 0.003, "grad": 0.0813, "tokens": 135589708800, "tok_s": 157126.1}
|
| 19 |
+
{"step": 129360, "epoch": 0.822, "loss": 1.77206, "ppl": 5.883, "lr": 0.003, "grad": 0.0782, "tokens": 135610675200, "tok_s": 156806.1}
|
| 20 |
+
{"step": 129380, "epoch": 0.822, "loss": 1.68123, "ppl": 5.372, "lr": 0.003, "grad": 0.1173, "tokens": 135631641600, "tok_s": 157407.9}
|
| 21 |
+
{"step": 129400, "epoch": 0.822, "loss": 1.78315, "ppl": 5.949, "lr": 0.003, "grad": 0.122, "tokens": 135652608000, "tok_s": 157273.9}
|
| 22 |
+
{"step": 129420, "epoch": 0.822, "loss": 1.7614, "ppl": 5.821, "lr": 0.003, "grad": 0.1357, "tokens": 135673574400, "tok_s": 157234.6}
|
| 23 |
+
{"step": 129440, "epoch": 0.822, "loss": 1.67073, "ppl": 5.316, "lr": 0.003, "grad": 0.0705, "tokens": 135694540800, "tok_s": 157421.7}
|
| 24 |
+
{"step": 129460, "epoch": 0.823, "loss": 1.8125, "ppl": 6.126, "lr": 0.003, "grad": 0.1151, "tokens": 135715507200, "tok_s": 157245.2}
|
| 25 |
+
{"step": 129480, "epoch": 0.823, "loss": 1.80825, "ppl": 6.1, "lr": 0.003, "grad": 0.1427, "tokens": 135736473600, "tok_s": 157396.8}
|
| 26 |
+
{"step": 129500, "epoch": 0.823, "loss": 1.90675, "ppl": 6.731, "lr": 0.003, "grad": 0.1583, "tokens": 135757440000, "tok_s": 157256.3}
|
| 27 |
+
{"step": 129520, "epoch": 0.823, "loss": 1.76329, "ppl": 5.832, "lr": 0.003, "grad": 0.1181, "tokens": 135778406400, "tok_s": 157268.5}
|
| 28 |
+
{"step": 129540, "epoch": 0.823, "loss": 1.65928, "ppl": 5.256, "lr": 0.003, "grad": 0.0893, "tokens": 135799372800, "tok_s": 157524.4}
|
| 29 |
+
{"step": 129560, "epoch": 0.823, "loss": 1.67935, "ppl": 5.362, "lr": 0.003, "grad": 0.0811, "tokens": 135820339200, "tok_s": 157585.8}
|
| 30 |
+
{"step": 129580, "epoch": 0.823, "loss": 1.70283, "ppl": 5.489, "lr": 0.003, "grad": 0.0908, "tokens": 135841305600, "tok_s": 157641.4}
|
| 31 |
+
{"step": 129600, "epoch": 0.823, "loss": 1.63922, "ppl": 5.151, "lr": 0.003, "grad": 0.0788, "tokens": 135862272000, "tok_s": 157853.0}
|
| 32 |
+
{"step": 129620, "epoch": 0.824, "loss": 1.715, "ppl": 5.557, "lr": 0.003, "grad": 0.1425, "tokens": 135883238400, "tok_s": 157261.9}
|
| 33 |
+
{"step": 129640, "epoch": 0.824, "loss": 1.66125, "ppl": 5.266, "lr": 0.003, "grad": 0.1515, "tokens": 135904204800, "tok_s": 157824.0}
|
| 34 |
+
{"step": 129660, "epoch": 0.824, "loss": 1.8425, "ppl": 6.312, "lr": 0.003, "grad": 0.0936, "tokens": 135925171200, "tok_s": 157414.2}
|
| 35 |
+
{"step": 129680, "epoch": 0.824, "loss": 1.77156, "ppl": 5.88, "lr": 0.003, "grad": 0.1027, "tokens": 135946137600, "tok_s": 157952.8}
|
| 36 |
+
{"step": 129700, "epoch": 0.824, "loss": 1.74271, "ppl": 5.713, "lr": 0.003, "grad": 0.1877, "tokens": 135967104000, "tok_s": 157854.5}
|
| 37 |
+
{"step": 129720, "epoch": 0.824, "loss": 1.66564, "ppl": 5.289, "lr": 0.003, "grad": 0.0791, "tokens": 135988070400, "tok_s": 158021.8}
|
| 38 |
+
{"step": 129740, "epoch": 0.824, "loss": 1.69832, "ppl": 5.465, "lr": 0.003, "grad": 0.0909, "tokens": 136009036800, "tok_s": 157578.1}
|
| 39 |
+
{"step": 129760, "epoch": 0.824, "loss": 1.76803, "ppl": 5.859, "lr": 0.003, "grad": 0.1282, "tokens": 136030003200, "tok_s": 157033.8}
|
| 40 |
+
{"step": 129780, "epoch": 0.825, "loss": 1.67652, "ppl": 5.347, "lr": 0.003, "grad": 0.1203, "tokens": 136050969600, "tok_s": 157782.2}
|
| 41 |
+
{"step": 129800, "epoch": 0.825, "loss": 1.69139, "ppl": 5.427, "lr": 0.003, "grad": 0.0993, "tokens": 136071936000, "tok_s": 157805.7}
|
| 42 |
+
{"step": 129820, "epoch": 0.825, "loss": 1.74188, "ppl": 5.708, "lr": 0.003, "grad": 0.1586, "tokens": 136092902400, "tok_s": 157652.6}
|
| 43 |
+
{"step": 129840, "epoch": 0.825, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.1048, "tokens": 136113868800, "tok_s": 157892.9}
|
| 44 |
+
{"step": 129860, "epoch": 0.825, "loss": 1.75256, "ppl": 5.769, "lr": 0.003, "grad": 0.1189, "tokens": 136134835200, "tok_s": 157781.2}
|
| 45 |
+
{"step": 129880, "epoch": 0.825, "loss": 1.77965, "ppl": 5.928, "lr": 0.003, "grad": 0.1049, "tokens": 136155801600, "tok_s": 157693.3}
|
| 46 |
+
{"step": 129900, "epoch": 0.825, "loss": 1.45431, "ppl": 4.282, "lr": 0.003, "grad": 0.1174, "tokens": 136176768000, "tok_s": 157650.5}
|
| 47 |
+
{"step": 129920, "epoch": 0.825, "loss": 1.67703, "ppl": 5.35, "lr": 0.003, "grad": 0.1193, "tokens": 136197734400, "tok_s": 157459.6}
|
| 48 |
+
{"step": 129940, "epoch": 0.826, "loss": 1.68942, "ppl": 5.416, "lr": 0.003, "grad": 0.1002, "tokens": 136218700800, "tok_s": 157493.8}
|
| 49 |
+
{"step": 129960, "epoch": 0.826, "loss": 1.78371, "ppl": 5.952, "lr": 0.003, "grad": 0.0927, "tokens": 136239667200, "tok_s": 157312.5}
|
| 50 |
+
{"step": 129980, "epoch": 0.826, "loss": 1.73478, "ppl": 5.668, "lr": 0.003, "grad": 0.0805, "tokens": 136260633600, "tok_s": 157586.0}
|
| 51 |
+
{"step": 130000, "epoch": 0.826, "loss": 1.88894, "ppl": 6.612, "lr": 0.003, "grad": 0.1294, "tokens": 136281600000, "tok_s": 157467.5}
|
| 52 |
+
{"step": 130000, "val_loss": 1.73054, "val_ppl": 5.644, "is_best": true}
|
| 53 |
+
{"step": 130020, "epoch": 0.826, "loss": 1.73526, "ppl": 5.67, "lr": 0.003, "grad": 0.129, "tokens": 136302566400, "tok_s": 157572.7}
|
| 54 |
+
{"step": 130040, "epoch": 0.826, "loss": 1.67846, "ppl": 5.357, "lr": 0.003, "grad": 0.1445, "tokens": 136323532800, "tok_s": 157713.9}
|
| 55 |
+
{"step": 130060, "epoch": 0.826, "loss": 1.77431, "ppl": 5.896, "lr": 0.003, "grad": 0.1509, "tokens": 136344499200, "tok_s": 157621.4}
|
| 56 |
+
{"step": 130080, "epoch": 0.826, "loss": 1.72493, "ppl": 5.612, "lr": 0.003, "grad": 0.1217, "tokens": 136365465600, "tok_s": 157750.6}
|
| 57 |
+
{"step": 130100, "epoch": 0.827, "loss": 1.59641, "ppl": 4.935, "lr": 0.003, "grad": 0.1226, "tokens": 136386432000, "tok_s": 157654.8}
|
| 58 |
+
{"step": 130120, "epoch": 0.827, "loss": 1.86963, "ppl": 6.486, "lr": 0.003, "grad": 0.126, "tokens": 136407398400, "tok_s": 157206.8}
|
| 59 |
+
{"step": 130140, "epoch": 0.827, "loss": 1.76439, "ppl": 5.838, "lr": 0.003, "grad": 0.0794, "tokens": 136428364800, "tok_s": 157463.5}
|
| 60 |
+
{"step": 130160, "epoch": 0.827, "loss": 1.75045, "ppl": 5.757, "lr": 0.003, "grad": 0.1228, "tokens": 136449331200, "tok_s": 157764.7}
|
| 61 |
+
{"step": 130180, "epoch": 0.827, "loss": 1.79344, "ppl": 6.01, "lr": 0.003, "grad": 0.1249, "tokens": 136470297600, "tok_s": 157403.3}
|
| 62 |
+
{"step": 130200, "epoch": 0.827, "loss": 1.7078, "ppl": 5.517, "lr": 0.003, "grad": 0.1528, "tokens": 136491264000, "tok_s": 157600.0}
|
| 63 |
+
{"step": 130220, "epoch": 0.827, "loss": 1.7805, "ppl": 5.933, "lr": 0.003, "grad": 0.1495, "tokens": 136512230400, "tok_s": 157095.7}
|
| 64 |
+
{"step": 130240, "epoch": 0.827, "loss": 1.69056, "ppl": 5.423, "lr": 0.003, "grad": 0.0973, "tokens": 136533196800, "tok_s": 157330.4}
|
| 65 |
+
{"step": 130260, "epoch": 0.828, "loss": 1.72071, "ppl": 5.589, "lr": 0.003, "grad": 0.1227, "tokens": 136554163200, "tok_s": 157583.4}
|
| 66 |
+
{"step": 130280, "epoch": 0.828, "loss": 1.60413, "ppl": 4.974, "lr": 0.003, "grad": 0.0853, "tokens": 136575129600, "tok_s": 157614.5}
|
| 67 |
+
{"step": 130300, "epoch": 0.828, "loss": 1.80194, "ppl": 6.061, "lr": 0.003, "grad": 0.1207, "tokens": 136596096000, "tok_s": 157752.1}
|
| 68 |
+
{"step": 130320, "epoch": 0.828, "loss": 1.74305, "ppl": 5.715, "lr": 0.003, "grad": 0.0819, "tokens": 136617062400, "tok_s": 157633.7}
|
| 69 |
+
{"step": 130340, "epoch": 0.828, "loss": 1.79549, "ppl": 6.022, "lr": 0.003, "grad": 0.1231, "tokens": 136638028800, "tok_s": 157535.5}
|
| 70 |
+
{"step": 130360, "epoch": 0.828, "loss": 1.73445, "ppl": 5.666, "lr": 0.003, "grad": 0.1615, "tokens": 136658995200, "tok_s": 157510.3}
|
| 71 |
+
{"step": 130380, "epoch": 0.828, "loss": 1.84461, "ppl": 6.326, "lr": 0.003, "grad": 0.1089, "tokens": 136679961600, "tok_s": 157324.6}
|
| 72 |
+
{"step": 130400, "epoch": 0.829, "loss": 1.81211, "ppl": 6.123, "lr": 0.003, "grad": 0.0719, "tokens": 136700928000, "tok_s": 157495.8}
|
| 73 |
+
{"step": 130420, "epoch": 0.829, "loss": 1.79467, "ppl": 6.017, "lr": 0.003, "grad": 0.1391, "tokens": 136721894400, "tok_s": 157411.2}
|
| 74 |
+
{"step": 130440, "epoch": 0.829, "loss": 1.73476, "ppl": 5.668, "lr": 0.003, "grad": 0.1071, "tokens": 136742860800, "tok_s": 157766.3}
|
| 75 |
+
{"step": 130460, "epoch": 0.829, "loss": 1.77554, "ppl": 5.903, "lr": 0.003, "grad": 0.1642, "tokens": 136763827200, "tok_s": 157367.3}
|
| 76 |
+
{"step": 130480, "epoch": 0.829, "loss": 1.82101, "ppl": 6.178, "lr": 0.003, "grad": 0.152, "tokens": 136784793600, "tok_s": 157044.7}
|
| 77 |
+
{"step": 130500, "epoch": 0.829, "loss": 1.77909, "ppl": 5.924, "lr": 0.003, "grad": 0.0888, "tokens": 136805760000, "tok_s": 157331.6}
|
| 78 |
+
{"step": 130520, "epoch": 0.829, "loss": 1.78449, "ppl": 5.957, "lr": 0.003, "grad": 0.1207, "tokens": 136826726400, "tok_s": 157559.0}
|
| 79 |
+
{"step": 130540, "epoch": 0.829, "loss": 1.70914, "ppl": 5.524, "lr": 0.003, "grad": 0.0981, "tokens": 136847692800, "tok_s": 157448.7}
|
| 80 |
+
{"step": 130560, "epoch": 0.83, "loss": 1.79092, "ppl": 5.995, "lr": 0.003, "grad": 0.15, "tokens": 136868659200, "tok_s": 157276.3}
|
| 81 |
+
{"step": 130580, "epoch": 0.83, "loss": 1.59137, "ppl": 4.91, "lr": 0.003, "grad": 0.0904, "tokens": 136889625600, "tok_s": 157370.7}
|
| 82 |
+
{"step": 130600, "epoch": 0.83, "loss": 1.76625, "ppl": 5.849, "lr": 0.003, "grad": 0.1367, "tokens": 136910592000, "tok_s": 157680.7}
|
| 83 |
+
{"step": 130620, "epoch": 0.83, "loss": 1.76693, "ppl": 5.853, "lr": 0.003, "grad": 0.0967, "tokens": 136931558400, "tok_s": 157881.4}
|
| 84 |
+
{"step": 130640, "epoch": 0.83, "loss": 1.73096, "ppl": 5.646, "lr": 0.003, "grad": 0.1168, "tokens": 136952524800, "tok_s": 157890.0}
|
| 85 |
+
{"step": 130660, "epoch": 0.83, "loss": 1.78401, "ppl": 5.954, "lr": 0.003, "grad": 0.0815, "tokens": 136973491200, "tok_s": 157896.6}
|
| 86 |
+
{"step": 130680, "epoch": 0.83, "loss": 1.75759, "ppl": 5.798, "lr": 0.003, "grad": 0.1412, "tokens": 136994457600, "tok_s": 157487.0}
|
| 87 |
+
{"step": 130700, "epoch": 0.83, "loss": 1.72975, "ppl": 5.639, "lr": 0.003, "grad": 0.0976, "tokens": 137015424000, "tok_s": 157535.5}
|
| 88 |
+
{"step": 130720, "epoch": 0.831, "loss": 1.70747, "ppl": 5.515, "lr": 0.003, "grad": 0.0945, "tokens": 137036390400, "tok_s": 157837.2}
|
| 89 |
+
{"step": 130740, "epoch": 0.831, "loss": 1.74526, "ppl": 5.727, "lr": 0.003, "grad": 0.0914, "tokens": 137057356800, "tok_s": 157859.8}
|
| 90 |
+
{"step": 130760, "epoch": 0.831, "loss": 1.63925, "ppl": 5.151, "lr": 0.003, "grad": 0.1153, "tokens": 137078323200, "tok_s": 158056.6}
|
| 91 |
+
{"step": 130780, "epoch": 0.831, "loss": 1.71553, "ppl": 5.56, "lr": 0.003, "grad": 0.1075, "tokens": 137099289600, "tok_s": 158017.2}
|
| 92 |
+
{"step": 130800, "epoch": 0.831, "loss": 1.73857, "ppl": 5.689, "lr": 0.003, "grad": 0.0948, "tokens": 137120256000, "tok_s": 157914.3}
|
| 93 |
+
{"step": 130820, "epoch": 0.831, "loss": 1.76271, "ppl": 5.828, "lr": 0.003, "grad": 0.1691, "tokens": 137141222400, "tok_s": 157998.3}
|
| 94 |
+
{"step": 130840, "epoch": 0.831, "loss": 1.7782, "ppl": 5.919, "lr": 0.003, "grad": 0.1244, "tokens": 137162188800, "tok_s": 157819.2}
|
| 95 |
+
{"step": 130860, "epoch": 0.831, "loss": 1.78937, "ppl": 5.986, "lr": 0.003, "grad": 0.0636, "tokens": 137183155200, "tok_s": 158018.9}
|
| 96 |
+
{"step": 130880, "epoch": 0.832, "loss": 1.76957, "ppl": 5.868, "lr": 0.003, "grad": 0.1611, "tokens": 137204121600, "tok_s": 157905.5}
|
| 97 |
+
{"step": 130900, "epoch": 0.832, "loss": 1.75428, "ppl": 5.779, "lr": 0.003, "grad": 0.1247, "tokens": 137225088000, "tok_s": 157896.3}
|
| 98 |
+
{"step": 130920, "epoch": 0.832, "loss": 1.77733, "ppl": 5.914, "lr": 0.003, "grad": 0.1442, "tokens": 137246054400, "tok_s": 157771.9}
|
| 99 |
+
{"step": 130940, "epoch": 0.832, "loss": 1.72573, "ppl": 5.617, "lr": 0.003, "grad": 0.0854, "tokens": 137267020800, "tok_s": 157898.0}
|
| 100 |
+
{"step": 130960, "epoch": 0.832, "loss": 1.7495, "ppl": 5.752, "lr": 0.003, "grad": 0.1204, "tokens": 137287987200, "tok_s": 157906.9}
|
| 101 |
+
{"step": 130980, "epoch": 0.832, "loss": 1.79697, "ppl": 6.031, "lr": 0.003, "grad": 0.1363, "tokens": 137308953600, "tok_s": 157812.5}
|
| 102 |
+
{"step": 131000, "epoch": 0.832, "loss": 1.72455, "ppl": 5.61, "lr": 0.003, "grad": 0.0756, "tokens": 137329920000, "tok_s": 157721.2}
|
| 103 |
+
{"step": 131000, "val_loss": 1.74218, "val_ppl": 5.71, "is_best": false}
|
| 104 |
+
{"step": 131020, "epoch": 0.832, "loss": 1.75914, "ppl": 5.807, "lr": 0.003, "grad": 0.1509, "tokens": 137350886400, "tok_s": 157385.2}
|
| 105 |
+
{"step": 131040, "epoch": 0.833, "loss": 1.74864, "ppl": 5.747, "lr": 0.003, "grad": 0.1302, "tokens": 137371852800, "tok_s": 157666.7}
|
| 106 |
+
{"step": 131060, "epoch": 0.833, "loss": 1.6946, "ppl": 5.444, "lr": 0.003, "grad": 0.1333, "tokens": 137392819200, "tok_s": 157782.2}
|
| 107 |
+
{"step": 131080, "epoch": 0.833, "loss": 1.76508, "ppl": 5.842, "lr": 0.003, "grad": 0.1296, "tokens": 137413785600, "tok_s": 157676.3}
|
| 108 |
+
{"step": 131100, "epoch": 0.833, "loss": 1.75585, "ppl": 5.788, "lr": 0.003, "grad": 0.1434, "tokens": 137434752000, "tok_s": 157604.7}
|
| 109 |
+
{"step": 131120, "epoch": 0.833, "loss": 1.82968, "ppl": 6.232, "lr": 0.003, "grad": 0.1498, "tokens": 137455718400, "tok_s": 157303.2}
|
| 110 |
+
{"step": 131140, "epoch": 0.833, "loss": 1.76963, "ppl": 5.869, "lr": 0.003, "grad": 0.0649, "tokens": 137476684800, "tok_s": 157501.5}
|
| 111 |
+
{"step": 131160, "epoch": 0.833, "loss": 1.72302, "ppl": 5.601, "lr": 0.003, "grad": 0.1315, "tokens": 137497651200, "tok_s": 157501.2}
|
| 112 |
+
{"step": 131180, "epoch": 0.833, "loss": 1.74954, "ppl": 5.752, "lr": 0.003, "grad": 0.0876, "tokens": 137518617600, "tok_s": 157444.7}
|
| 113 |
+
{"step": 131200, "epoch": 0.834, "loss": 1.80421, "ppl": 6.075, "lr": 0.003, "grad": 0.1363, "tokens": 137539584000, "tok_s": 157558.4}
|
| 114 |
+
{"step": 131220, "epoch": 0.834, "loss": 1.70377, "ppl": 5.495, "lr": 0.003, "grad": 0.0805, "tokens": 137560550400, "tok_s": 157853.4}
|
| 115 |
+
{"step": 131240, "epoch": 0.834, "loss": 1.74897, "ppl": 5.749, "lr": 0.003, "grad": 0.119, "tokens": 137581516800, "tok_s": 157869.2}
|
| 116 |
+
{"step": 131260, "epoch": 0.834, "loss": 1.66217, "ppl": 5.271, "lr": 0.003, "grad": 0.0881, "tokens": 137602483200, "tok_s": 157851.7}
|
| 117 |
+
{"step": 131280, "epoch": 0.834, "loss": 1.76037, "ppl": 5.815, "lr": 0.003, "grad": 0.1217, "tokens": 137623449600, "tok_s": 157460.8}
|
| 118 |
+
{"step": 131300, "epoch": 0.834, "loss": 1.78582, "ppl": 5.964, "lr": 0.003, "grad": 0.1115, "tokens": 137644416000, "tok_s": 157650.1}
|
| 119 |
+
{"step": 131320, "epoch": 0.834, "loss": 1.66715, "ppl": 5.297, "lr": 0.003, "grad": 0.0933, "tokens": 137665382400, "tok_s": 158072.0}
|
| 120 |
+
{"step": 131340, "epoch": 0.834, "loss": 1.632, "ppl": 5.114, "lr": 0.003, "grad": 0.1561, "tokens": 137686348800, "tok_s": 157772.4}
|
| 121 |
+
{"step": 131360, "epoch": 0.835, "loss": 1.75856, "ppl": 5.804, "lr": 0.003, "grad": 0.136, "tokens": 137707315200, "tok_s": 157630.9}
|
| 122 |
+
{"step": 131380, "epoch": 0.835, "loss": 1.73083, "ppl": 5.645, "lr": 0.003, "grad": 0.0941, "tokens": 137728281600, "tok_s": 157560.5}
|
| 123 |
+
{"step": 131400, "epoch": 0.835, "loss": 1.64808, "ppl": 5.197, "lr": 0.003, "grad": 0.0823, "tokens": 137749248000, "tok_s": 157519.3}
|
| 124 |
+
{"step": 131420, "epoch": 0.835, "loss": 1.66477, "ppl": 5.284, "lr": 0.003, "grad": 0.0848, "tokens": 137770214400, "tok_s": 157734.5}
|
| 125 |
+
{"step": 131440, "epoch": 0.835, "loss": 1.85442, "ppl": 6.388, "lr": 0.003, "grad": 0.1732, "tokens": 137791180800, "tok_s": 157179.6}
|
| 126 |
+
{"step": 131460, "epoch": 0.835, "loss": 1.64687, "ppl": 5.191, "lr": 0.003, "grad": 0.129, "tokens": 137812147200, "tok_s": 157549.2}
|
| 127 |
+
{"step": 131480, "epoch": 0.835, "loss": 1.7237, "ppl": 5.605, "lr": 0.003, "grad": 0.0647, "tokens": 137833113600, "tok_s": 157528.5}
|
| 128 |
+
{"step": 131500, "epoch": 0.836, "loss": 1.69868, "ppl": 5.467, "lr": 0.003, "grad": 0.1381, "tokens": 137854080000, "tok_s": 157468.9}
|
| 129 |
+
{"step": 131520, "epoch": 0.836, "loss": 1.71161, "ppl": 5.538, "lr": 0.003, "grad": 0.0726, "tokens": 137875046400, "tok_s": 157284.6}
|
| 130 |
+
{"step": 131540, "epoch": 0.836, "loss": 1.71424, "ppl": 5.552, "lr": 0.003, "grad": 0.0749, "tokens": 137896012800, "tok_s": 157645.1}
|
| 131 |
+
{"step": 131560, "epoch": 0.836, "loss": 1.8113, "ppl": 6.118, "lr": 0.003, "grad": 0.1154, "tokens": 137916979200, "tok_s": 157399.5}
|
| 132 |
+
{"step": 131580, "epoch": 0.836, "loss": 1.74297, "ppl": 5.714, "lr": 0.003, "grad": 0.125, "tokens": 137937945600, "tok_s": 157590.2}
|
| 133 |
+
{"step": 131600, "epoch": 0.836, "loss": 1.77429, "ppl": 5.896, "lr": 0.003, "grad": 0.0997, "tokens": 137958912000, "tok_s": 157668.1}
|
| 134 |
+
{"step": 131620, "epoch": 0.836, "loss": 1.73877, "ppl": 5.69, "lr": 0.003, "grad": 0.1868, "tokens": 137979878400, "tok_s": 157699.2}
|
| 135 |
+
{"step": 131640, "epoch": 0.836, "loss": 1.77573, "ppl": 5.905, "lr": 0.003, "grad": 0.077, "tokens": 138000844800, "tok_s": 157620.5}
|
| 136 |
+
{"step": 131660, "epoch": 0.837, "loss": 1.64417, "ppl": 5.177, "lr": 0.003, "grad": 0.0972, "tokens": 138021811200, "tok_s": 157780.4}
|
| 137 |
+
{"step": 131680, "epoch": 0.837, "loss": 1.73902, "ppl": 5.692, "lr": 0.003, "grad": 0.1179, "tokens": 138042777600, "tok_s": 157643.1}
|
| 138 |
+
{"step": 131700, "epoch": 0.837, "loss": 1.69839, "ppl": 5.465, "lr": 0.003, "grad": 0.1525, "tokens": 138063744000, "tok_s": 157643.8}
|
| 139 |
+
{"step": 131720, "epoch": 0.837, "loss": 1.78522, "ppl": 5.961, "lr": 0.003, "grad": 0.1456, "tokens": 138084710400, "tok_s": 157688.3}
|
| 140 |
+
{"step": 131740, "epoch": 0.837, "loss": 1.60758, "ppl": 4.991, "lr": 0.003, "grad": 0.1177, "tokens": 138105676800, "tok_s": 157962.8}
|
| 141 |
+
{"step": 131760, "epoch": 0.837, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.145, "tokens": 138126643200, "tok_s": 158007.3}
|
| 142 |
+
{"step": 131780, "epoch": 0.837, "loss": 1.78108, "ppl": 5.936, "lr": 0.003, "grad": 0.074, "tokens": 138147609600, "tok_s": 158050.7}
|
| 143 |
+
{"step": 131800, "epoch": 0.837, "loss": 1.75782, "ppl": 5.8, "lr": 0.003, "grad": 0.1127, "tokens": 138168576000, "tok_s": 157976.4}
|
| 144 |
+
{"step": 131820, "epoch": 0.838, "loss": 1.77594, "ppl": 5.906, "lr": 0.003, "grad": 0.1154, "tokens": 138189542400, "tok_s": 157906.9}
|
| 145 |
+
{"step": 131840, "epoch": 0.838, "loss": 1.77775, "ppl": 5.917, "lr": 0.003, "grad": 0.1757, "tokens": 138210508800, "tok_s": 158068.5}
|
| 146 |
+
{"step": 131860, "epoch": 0.838, "loss": 1.80142, "ppl": 6.058, "lr": 0.003, "grad": 0.0993, "tokens": 138231475200, "tok_s": 157823.5}
|
| 147 |
+
{"step": 131880, "epoch": 0.838, "loss": 1.71506, "ppl": 5.557, "lr": 0.003, "grad": 0.0822, "tokens": 138252441600, "tok_s": 157898.3}
|
| 148 |
+
{"step": 131900, "epoch": 0.838, "loss": 1.76876, "ppl": 5.864, "lr": 0.003, "grad": 0.136, "tokens": 138273408000, "tok_s": 157977.2}
|
| 149 |
+
{"step": 131920, "epoch": 0.838, "loss": 1.76676, "ppl": 5.852, "lr": 0.003, "grad": 0.126, "tokens": 138294374400, "tok_s": 157946.6}
|
| 150 |
+
{"step": 131940, "epoch": 0.838, "loss": 1.73315, "ppl": 5.658, "lr": 0.003, "grad": 0.1036, "tokens": 138315340800, "tok_s": 158005.4}
|
| 151 |
+
{"step": 131960, "epoch": 0.838, "loss": 1.78912, "ppl": 5.984, "lr": 0.003, "grad": 0.1326, "tokens": 138336307200, "tok_s": 157480.7}
|
| 152 |
+
{"step": 131980, "epoch": 0.839, "loss": 1.76096, "ppl": 5.818, "lr": 0.003, "grad": 0.1085, "tokens": 138357273600, "tok_s": 157867.0}
|
| 153 |
+
{"step": 132000, "epoch": 0.839, "loss": 1.76569, "ppl": 5.846, "lr": 0.003, "grad": 0.1584, "tokens": 138378240000, "tok_s": 157850.0}
|
| 154 |
+
{"step": 132000, "val_loss": 1.74875, "val_ppl": 5.747, "is_best": false}
|
logs/log_133000.jsonl
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 129000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T20:51:27.189113"}
|
| 2 |
+
{"step": 129020, "epoch": 0.82, "loss": 1.7484, "ppl": 5.745, "lr": 0.003, "grad": 0.128, "tokens": 135254246400, "tok_s": 157033.6}
|
| 3 |
+
{"step": 129040, "epoch": 0.82, "loss": 1.7463, "ppl": 5.733, "lr": 0.003, "grad": 0.1339, "tokens": 135275212800, "tok_s": 157455.3}
|
| 4 |
+
{"step": 129060, "epoch": 0.82, "loss": 1.72289, "ppl": 5.601, "lr": 0.003, "grad": 0.0914, "tokens": 135296179200, "tok_s": 157658.8}
|
| 5 |
+
{"step": 129080, "epoch": 0.82, "loss": 1.61329, "ppl": 5.019, "lr": 0.003, "grad": 0.0695, "tokens": 135317145600, "tok_s": 157571.0}
|
| 6 |
+
{"step": 129100, "epoch": 0.82, "loss": 1.7691, "ppl": 5.866, "lr": 0.003, "grad": 0.0851, "tokens": 135338112000, "tok_s": 157376.2}
|
| 7 |
+
{"step": 129120, "epoch": 0.82, "loss": 1.73223, "ppl": 5.653, "lr": 0.003, "grad": 0.1258, "tokens": 135359078400, "tok_s": 157535.3}
|
| 8 |
+
{"step": 129140, "epoch": 0.821, "loss": 1.74594, "ppl": 5.731, "lr": 0.003, "grad": 0.1169, "tokens": 135380044800, "tok_s": 157194.1}
|
| 9 |
+
{"step": 129160, "epoch": 0.821, "loss": 1.67829, "ppl": 5.356, "lr": 0.003, "grad": 0.1458, "tokens": 135401011200, "tok_s": 157471.7}
|
| 10 |
+
{"step": 129180, "epoch": 0.821, "loss": 1.62889, "ppl": 5.098, "lr": 0.003, "grad": 0.0851, "tokens": 135421977600, "tok_s": 157698.5}
|
| 11 |
+
{"step": 129200, "epoch": 0.821, "loss": 1.58919, "ppl": 4.9, "lr": 0.003, "grad": 0.0721, "tokens": 135442944000, "tok_s": 157629.3}
|
| 12 |
+
{"step": 129220, "epoch": 0.821, "loss": 1.78037, "ppl": 5.932, "lr": 0.003, "grad": 0.104, "tokens": 135463910400, "tok_s": 157497.6}
|
| 13 |
+
{"step": 129240, "epoch": 0.821, "loss": 1.70018, "ppl": 5.475, "lr": 0.003, "grad": 0.1103, "tokens": 135484876800, "tok_s": 157761.0}
|
| 14 |
+
{"step": 129260, "epoch": 0.821, "loss": 1.76303, "ppl": 5.83, "lr": 0.003, "grad": 0.0733, "tokens": 135505843200, "tok_s": 157716.0}
|
| 15 |
+
{"step": 129280, "epoch": 0.821, "loss": 1.7109, "ppl": 5.534, "lr": 0.003, "grad": 0.0864, "tokens": 135526809600, "tok_s": 157454.0}
|
| 16 |
+
{"step": 129300, "epoch": 0.822, "loss": 1.75566, "ppl": 5.787, "lr": 0.003, "grad": 0.1019, "tokens": 135547776000, "tok_s": 157428.3}
|
| 17 |
+
{"step": 129320, "epoch": 0.822, "loss": 1.76169, "ppl": 5.822, "lr": 0.003, "grad": 0.0998, "tokens": 135568742400, "tok_s": 157312.0}
|
| 18 |
+
{"step": 129340, "epoch": 0.822, "loss": 1.72612, "ppl": 5.619, "lr": 0.003, "grad": 0.0813, "tokens": 135589708800, "tok_s": 157126.1}
|
| 19 |
+
{"step": 129360, "epoch": 0.822, "loss": 1.77206, "ppl": 5.883, "lr": 0.003, "grad": 0.0782, "tokens": 135610675200, "tok_s": 156806.1}
|
| 20 |
+
{"step": 129380, "epoch": 0.822, "loss": 1.68123, "ppl": 5.372, "lr": 0.003, "grad": 0.1173, "tokens": 135631641600, "tok_s": 157407.9}
|
| 21 |
+
{"step": 129400, "epoch": 0.822, "loss": 1.78315, "ppl": 5.949, "lr": 0.003, "grad": 0.122, "tokens": 135652608000, "tok_s": 157273.9}
|
| 22 |
+
{"step": 129420, "epoch": 0.822, "loss": 1.7614, "ppl": 5.821, "lr": 0.003, "grad": 0.1357, "tokens": 135673574400, "tok_s": 157234.6}
|
| 23 |
+
{"step": 129440, "epoch": 0.822, "loss": 1.67073, "ppl": 5.316, "lr": 0.003, "grad": 0.0705, "tokens": 135694540800, "tok_s": 157421.7}
|
| 24 |
+
{"step": 129460, "epoch": 0.823, "loss": 1.8125, "ppl": 6.126, "lr": 0.003, "grad": 0.1151, "tokens": 135715507200, "tok_s": 157245.2}
|
| 25 |
+
{"step": 129480, "epoch": 0.823, "loss": 1.80825, "ppl": 6.1, "lr": 0.003, "grad": 0.1427, "tokens": 135736473600, "tok_s": 157396.8}
|
| 26 |
+
{"step": 129500, "epoch": 0.823, "loss": 1.90675, "ppl": 6.731, "lr": 0.003, "grad": 0.1583, "tokens": 135757440000, "tok_s": 157256.3}
|
| 27 |
+
{"step": 129520, "epoch": 0.823, "loss": 1.76329, "ppl": 5.832, "lr": 0.003, "grad": 0.1181, "tokens": 135778406400, "tok_s": 157268.5}
|
| 28 |
+
{"step": 129540, "epoch": 0.823, "loss": 1.65928, "ppl": 5.256, "lr": 0.003, "grad": 0.0893, "tokens": 135799372800, "tok_s": 157524.4}
|
| 29 |
+
{"step": 129560, "epoch": 0.823, "loss": 1.67935, "ppl": 5.362, "lr": 0.003, "grad": 0.0811, "tokens": 135820339200, "tok_s": 157585.8}
|
| 30 |
+
{"step": 129580, "epoch": 0.823, "loss": 1.70283, "ppl": 5.489, "lr": 0.003, "grad": 0.0908, "tokens": 135841305600, "tok_s": 157641.4}
|
| 31 |
+
{"step": 129600, "epoch": 0.823, "loss": 1.63922, "ppl": 5.151, "lr": 0.003, "grad": 0.0788, "tokens": 135862272000, "tok_s": 157853.0}
|
| 32 |
+
{"step": 129620, "epoch": 0.824, "loss": 1.715, "ppl": 5.557, "lr": 0.003, "grad": 0.1425, "tokens": 135883238400, "tok_s": 157261.9}
|
| 33 |
+
{"step": 129640, "epoch": 0.824, "loss": 1.66125, "ppl": 5.266, "lr": 0.003, "grad": 0.1515, "tokens": 135904204800, "tok_s": 157824.0}
|
| 34 |
+
{"step": 129660, "epoch": 0.824, "loss": 1.8425, "ppl": 6.312, "lr": 0.003, "grad": 0.0936, "tokens": 135925171200, "tok_s": 157414.2}
|
| 35 |
+
{"step": 129680, "epoch": 0.824, "loss": 1.77156, "ppl": 5.88, "lr": 0.003, "grad": 0.1027, "tokens": 135946137600, "tok_s": 157952.8}
|
| 36 |
+
{"step": 129700, "epoch": 0.824, "loss": 1.74271, "ppl": 5.713, "lr": 0.003, "grad": 0.1877, "tokens": 135967104000, "tok_s": 157854.5}
|
| 37 |
+
{"step": 129720, "epoch": 0.824, "loss": 1.66564, "ppl": 5.289, "lr": 0.003, "grad": 0.0791, "tokens": 135988070400, "tok_s": 158021.8}
|
| 38 |
+
{"step": 129740, "epoch": 0.824, "loss": 1.69832, "ppl": 5.465, "lr": 0.003, "grad": 0.0909, "tokens": 136009036800, "tok_s": 157578.1}
|
| 39 |
+
{"step": 129760, "epoch": 0.824, "loss": 1.76803, "ppl": 5.859, "lr": 0.003, "grad": 0.1282, "tokens": 136030003200, "tok_s": 157033.8}
|
| 40 |
+
{"step": 129780, "epoch": 0.825, "loss": 1.67652, "ppl": 5.347, "lr": 0.003, "grad": 0.1203, "tokens": 136050969600, "tok_s": 157782.2}
|
| 41 |
+
{"step": 129800, "epoch": 0.825, "loss": 1.69139, "ppl": 5.427, "lr": 0.003, "grad": 0.0993, "tokens": 136071936000, "tok_s": 157805.7}
|
| 42 |
+
{"step": 129820, "epoch": 0.825, "loss": 1.74188, "ppl": 5.708, "lr": 0.003, "grad": 0.1586, "tokens": 136092902400, "tok_s": 157652.6}
|
| 43 |
+
{"step": 129840, "epoch": 0.825, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.1048, "tokens": 136113868800, "tok_s": 157892.9}
|
| 44 |
+
{"step": 129860, "epoch": 0.825, "loss": 1.75256, "ppl": 5.769, "lr": 0.003, "grad": 0.1189, "tokens": 136134835200, "tok_s": 157781.2}
|
| 45 |
+
{"step": 129880, "epoch": 0.825, "loss": 1.77965, "ppl": 5.928, "lr": 0.003, "grad": 0.1049, "tokens": 136155801600, "tok_s": 157693.3}
|
| 46 |
+
{"step": 129900, "epoch": 0.825, "loss": 1.45431, "ppl": 4.282, "lr": 0.003, "grad": 0.1174, "tokens": 136176768000, "tok_s": 157650.5}
|
| 47 |
+
{"step": 129920, "epoch": 0.825, "loss": 1.67703, "ppl": 5.35, "lr": 0.003, "grad": 0.1193, "tokens": 136197734400, "tok_s": 157459.6}
|
| 48 |
+
{"step": 129940, "epoch": 0.826, "loss": 1.68942, "ppl": 5.416, "lr": 0.003, "grad": 0.1002, "tokens": 136218700800, "tok_s": 157493.8}
|
| 49 |
+
{"step": 129960, "epoch": 0.826, "loss": 1.78371, "ppl": 5.952, "lr": 0.003, "grad": 0.0927, "tokens": 136239667200, "tok_s": 157312.5}
|
| 50 |
+
{"step": 129980, "epoch": 0.826, "loss": 1.73478, "ppl": 5.668, "lr": 0.003, "grad": 0.0805, "tokens": 136260633600, "tok_s": 157586.0}
|
| 51 |
+
{"step": 130000, "epoch": 0.826, "loss": 1.88894, "ppl": 6.612, "lr": 0.003, "grad": 0.1294, "tokens": 136281600000, "tok_s": 157467.5}
|
| 52 |
+
{"step": 130000, "val_loss": 1.73054, "val_ppl": 5.644, "is_best": true}
|
| 53 |
+
{"step": 130020, "epoch": 0.826, "loss": 1.73526, "ppl": 5.67, "lr": 0.003, "grad": 0.129, "tokens": 136302566400, "tok_s": 157572.7}
|
| 54 |
+
{"step": 130040, "epoch": 0.826, "loss": 1.67846, "ppl": 5.357, "lr": 0.003, "grad": 0.1445, "tokens": 136323532800, "tok_s": 157713.9}
|
| 55 |
+
{"step": 130060, "epoch": 0.826, "loss": 1.77431, "ppl": 5.896, "lr": 0.003, "grad": 0.1509, "tokens": 136344499200, "tok_s": 157621.4}
|
| 56 |
+
{"step": 130080, "epoch": 0.826, "loss": 1.72493, "ppl": 5.612, "lr": 0.003, "grad": 0.1217, "tokens": 136365465600, "tok_s": 157750.6}
|
| 57 |
+
{"step": 130100, "epoch": 0.827, "loss": 1.59641, "ppl": 4.935, "lr": 0.003, "grad": 0.1226, "tokens": 136386432000, "tok_s": 157654.8}
|
| 58 |
+
{"step": 130120, "epoch": 0.827, "loss": 1.86963, "ppl": 6.486, "lr": 0.003, "grad": 0.126, "tokens": 136407398400, "tok_s": 157206.8}
|
| 59 |
+
{"step": 130140, "epoch": 0.827, "loss": 1.76439, "ppl": 5.838, "lr": 0.003, "grad": 0.0794, "tokens": 136428364800, "tok_s": 157463.5}
|
| 60 |
+
{"step": 130160, "epoch": 0.827, "loss": 1.75045, "ppl": 5.757, "lr": 0.003, "grad": 0.1228, "tokens": 136449331200, "tok_s": 157764.7}
|
| 61 |
+
{"step": 130180, "epoch": 0.827, "loss": 1.79344, "ppl": 6.01, "lr": 0.003, "grad": 0.1249, "tokens": 136470297600, "tok_s": 157403.3}
|
| 62 |
+
{"step": 130200, "epoch": 0.827, "loss": 1.7078, "ppl": 5.517, "lr": 0.003, "grad": 0.1528, "tokens": 136491264000, "tok_s": 157600.0}
|
| 63 |
+
{"step": 130220, "epoch": 0.827, "loss": 1.7805, "ppl": 5.933, "lr": 0.003, "grad": 0.1495, "tokens": 136512230400, "tok_s": 157095.7}
|
| 64 |
+
{"step": 130240, "epoch": 0.827, "loss": 1.69056, "ppl": 5.423, "lr": 0.003, "grad": 0.0973, "tokens": 136533196800, "tok_s": 157330.4}
|
| 65 |
+
{"step": 130260, "epoch": 0.828, "loss": 1.72071, "ppl": 5.589, "lr": 0.003, "grad": 0.1227, "tokens": 136554163200, "tok_s": 157583.4}
|
| 66 |
+
{"step": 130280, "epoch": 0.828, "loss": 1.60413, "ppl": 4.974, "lr": 0.003, "grad": 0.0853, "tokens": 136575129600, "tok_s": 157614.5}
|
| 67 |
+
{"step": 130300, "epoch": 0.828, "loss": 1.80194, "ppl": 6.061, "lr": 0.003, "grad": 0.1207, "tokens": 136596096000, "tok_s": 157752.1}
|
| 68 |
+
{"step": 130320, "epoch": 0.828, "loss": 1.74305, "ppl": 5.715, "lr": 0.003, "grad": 0.0819, "tokens": 136617062400, "tok_s": 157633.7}
|
| 69 |
+
{"step": 130340, "epoch": 0.828, "loss": 1.79549, "ppl": 6.022, "lr": 0.003, "grad": 0.1231, "tokens": 136638028800, "tok_s": 157535.5}
|
| 70 |
+
{"step": 130360, "epoch": 0.828, "loss": 1.73445, "ppl": 5.666, "lr": 0.003, "grad": 0.1615, "tokens": 136658995200, "tok_s": 157510.3}
|
| 71 |
+
{"step": 130380, "epoch": 0.828, "loss": 1.84461, "ppl": 6.326, "lr": 0.003, "grad": 0.1089, "tokens": 136679961600, "tok_s": 157324.6}
|
| 72 |
+
{"step": 130400, "epoch": 0.829, "loss": 1.81211, "ppl": 6.123, "lr": 0.003, "grad": 0.0719, "tokens": 136700928000, "tok_s": 157495.8}
|
| 73 |
+
{"step": 130420, "epoch": 0.829, "loss": 1.79467, "ppl": 6.017, "lr": 0.003, "grad": 0.1391, "tokens": 136721894400, "tok_s": 157411.2}
|
| 74 |
+
{"step": 130440, "epoch": 0.829, "loss": 1.73476, "ppl": 5.668, "lr": 0.003, "grad": 0.1071, "tokens": 136742860800, "tok_s": 157766.3}
|
| 75 |
+
{"step": 130460, "epoch": 0.829, "loss": 1.77554, "ppl": 5.903, "lr": 0.003, "grad": 0.1642, "tokens": 136763827200, "tok_s": 157367.3}
|
| 76 |
+
{"step": 130480, "epoch": 0.829, "loss": 1.82101, "ppl": 6.178, "lr": 0.003, "grad": 0.152, "tokens": 136784793600, "tok_s": 157044.7}
|
| 77 |
+
{"step": 130500, "epoch": 0.829, "loss": 1.77909, "ppl": 5.924, "lr": 0.003, "grad": 0.0888, "tokens": 136805760000, "tok_s": 157331.6}
|
| 78 |
+
{"step": 130520, "epoch": 0.829, "loss": 1.78449, "ppl": 5.957, "lr": 0.003, "grad": 0.1207, "tokens": 136826726400, "tok_s": 157559.0}
|
| 79 |
+
{"step": 130540, "epoch": 0.829, "loss": 1.70914, "ppl": 5.524, "lr": 0.003, "grad": 0.0981, "tokens": 136847692800, "tok_s": 157448.7}
|
| 80 |
+
{"step": 130560, "epoch": 0.83, "loss": 1.79092, "ppl": 5.995, "lr": 0.003, "grad": 0.15, "tokens": 136868659200, "tok_s": 157276.3}
|
| 81 |
+
{"step": 130580, "epoch": 0.83, "loss": 1.59137, "ppl": 4.91, "lr": 0.003, "grad": 0.0904, "tokens": 136889625600, "tok_s": 157370.7}
|
| 82 |
+
{"step": 130600, "epoch": 0.83, "loss": 1.76625, "ppl": 5.849, "lr": 0.003, "grad": 0.1367, "tokens": 136910592000, "tok_s": 157680.7}
|
| 83 |
+
{"step": 130620, "epoch": 0.83, "loss": 1.76693, "ppl": 5.853, "lr": 0.003, "grad": 0.0967, "tokens": 136931558400, "tok_s": 157881.4}
|
| 84 |
+
{"step": 130640, "epoch": 0.83, "loss": 1.73096, "ppl": 5.646, "lr": 0.003, "grad": 0.1168, "tokens": 136952524800, "tok_s": 157890.0}
|
| 85 |
+
{"step": 130660, "epoch": 0.83, "loss": 1.78401, "ppl": 5.954, "lr": 0.003, "grad": 0.0815, "tokens": 136973491200, "tok_s": 157896.6}
|
| 86 |
+
{"step": 130680, "epoch": 0.83, "loss": 1.75759, "ppl": 5.798, "lr": 0.003, "grad": 0.1412, "tokens": 136994457600, "tok_s": 157487.0}
|
| 87 |
+
{"step": 130700, "epoch": 0.83, "loss": 1.72975, "ppl": 5.639, "lr": 0.003, "grad": 0.0976, "tokens": 137015424000, "tok_s": 157535.5}
|
| 88 |
+
{"step": 130720, "epoch": 0.831, "loss": 1.70747, "ppl": 5.515, "lr": 0.003, "grad": 0.0945, "tokens": 137036390400, "tok_s": 157837.2}
|
| 89 |
+
{"step": 130740, "epoch": 0.831, "loss": 1.74526, "ppl": 5.727, "lr": 0.003, "grad": 0.0914, "tokens": 137057356800, "tok_s": 157859.8}
|
| 90 |
+
{"step": 130760, "epoch": 0.831, "loss": 1.63925, "ppl": 5.151, "lr": 0.003, "grad": 0.1153, "tokens": 137078323200, "tok_s": 158056.6}
|
| 91 |
+
{"step": 130780, "epoch": 0.831, "loss": 1.71553, "ppl": 5.56, "lr": 0.003, "grad": 0.1075, "tokens": 137099289600, "tok_s": 158017.2}
|
| 92 |
+
{"step": 130800, "epoch": 0.831, "loss": 1.73857, "ppl": 5.689, "lr": 0.003, "grad": 0.0948, "tokens": 137120256000, "tok_s": 157914.3}
|
| 93 |
+
{"step": 130820, "epoch": 0.831, "loss": 1.76271, "ppl": 5.828, "lr": 0.003, "grad": 0.1691, "tokens": 137141222400, "tok_s": 157998.3}
|
| 94 |
+
{"step": 130840, "epoch": 0.831, "loss": 1.7782, "ppl": 5.919, "lr": 0.003, "grad": 0.1244, "tokens": 137162188800, "tok_s": 157819.2}
|
| 95 |
+
{"step": 130860, "epoch": 0.831, "loss": 1.78937, "ppl": 5.986, "lr": 0.003, "grad": 0.0636, "tokens": 137183155200, "tok_s": 158018.9}
|
| 96 |
+
{"step": 130880, "epoch": 0.832, "loss": 1.76957, "ppl": 5.868, "lr": 0.003, "grad": 0.1611, "tokens": 137204121600, "tok_s": 157905.5}
|
| 97 |
+
{"step": 130900, "epoch": 0.832, "loss": 1.75428, "ppl": 5.779, "lr": 0.003, "grad": 0.1247, "tokens": 137225088000, "tok_s": 157896.3}
|
| 98 |
+
{"step": 130920, "epoch": 0.832, "loss": 1.77733, "ppl": 5.914, "lr": 0.003, "grad": 0.1442, "tokens": 137246054400, "tok_s": 157771.9}
|
| 99 |
+
{"step": 130940, "epoch": 0.832, "loss": 1.72573, "ppl": 5.617, "lr": 0.003, "grad": 0.0854, "tokens": 137267020800, "tok_s": 157898.0}
|
| 100 |
+
{"step": 130960, "epoch": 0.832, "loss": 1.7495, "ppl": 5.752, "lr": 0.003, "grad": 0.1204, "tokens": 137287987200, "tok_s": 157906.9}
|
| 101 |
+
{"step": 130980, "epoch": 0.832, "loss": 1.79697, "ppl": 6.031, "lr": 0.003, "grad": 0.1363, "tokens": 137308953600, "tok_s": 157812.5}
|
| 102 |
+
{"step": 131000, "epoch": 0.832, "loss": 1.72455, "ppl": 5.61, "lr": 0.003, "grad": 0.0756, "tokens": 137329920000, "tok_s": 157721.2}
|
| 103 |
+
{"step": 131000, "val_loss": 1.74218, "val_ppl": 5.71, "is_best": false}
|
| 104 |
+
{"step": 131020, "epoch": 0.832, "loss": 1.75914, "ppl": 5.807, "lr": 0.003, "grad": 0.1509, "tokens": 137350886400, "tok_s": 157385.2}
|
| 105 |
+
{"step": 131040, "epoch": 0.833, "loss": 1.74864, "ppl": 5.747, "lr": 0.003, "grad": 0.1302, "tokens": 137371852800, "tok_s": 157666.7}
|
| 106 |
+
{"step": 131060, "epoch": 0.833, "loss": 1.6946, "ppl": 5.444, "lr": 0.003, "grad": 0.1333, "tokens": 137392819200, "tok_s": 157782.2}
|
| 107 |
+
{"step": 131080, "epoch": 0.833, "loss": 1.76508, "ppl": 5.842, "lr": 0.003, "grad": 0.1296, "tokens": 137413785600, "tok_s": 157676.3}
|
| 108 |
+
{"step": 131100, "epoch": 0.833, "loss": 1.75585, "ppl": 5.788, "lr": 0.003, "grad": 0.1434, "tokens": 137434752000, "tok_s": 157604.7}
|
| 109 |
+
{"step": 131120, "epoch": 0.833, "loss": 1.82968, "ppl": 6.232, "lr": 0.003, "grad": 0.1498, "tokens": 137455718400, "tok_s": 157303.2}
|
| 110 |
+
{"step": 131140, "epoch": 0.833, "loss": 1.76963, "ppl": 5.869, "lr": 0.003, "grad": 0.0649, "tokens": 137476684800, "tok_s": 157501.5}
|
| 111 |
+
{"step": 131160, "epoch": 0.833, "loss": 1.72302, "ppl": 5.601, "lr": 0.003, "grad": 0.1315, "tokens": 137497651200, "tok_s": 157501.2}
|
| 112 |
+
{"step": 131180, "epoch": 0.833, "loss": 1.74954, "ppl": 5.752, "lr": 0.003, "grad": 0.0876, "tokens": 137518617600, "tok_s": 157444.7}
|
| 113 |
+
{"step": 131200, "epoch": 0.834, "loss": 1.80421, "ppl": 6.075, "lr": 0.003, "grad": 0.1363, "tokens": 137539584000, "tok_s": 157558.4}
|
| 114 |
+
{"step": 131220, "epoch": 0.834, "loss": 1.70377, "ppl": 5.495, "lr": 0.003, "grad": 0.0805, "tokens": 137560550400, "tok_s": 157853.4}
|
| 115 |
+
{"step": 131240, "epoch": 0.834, "loss": 1.74897, "ppl": 5.749, "lr": 0.003, "grad": 0.119, "tokens": 137581516800, "tok_s": 157869.2}
|
| 116 |
+
{"step": 131260, "epoch": 0.834, "loss": 1.66217, "ppl": 5.271, "lr": 0.003, "grad": 0.0881, "tokens": 137602483200, "tok_s": 157851.7}
|
| 117 |
+
{"step": 131280, "epoch": 0.834, "loss": 1.76037, "ppl": 5.815, "lr": 0.003, "grad": 0.1217, "tokens": 137623449600, "tok_s": 157460.8}
|
| 118 |
+
{"step": 131300, "epoch": 0.834, "loss": 1.78582, "ppl": 5.964, "lr": 0.003, "grad": 0.1115, "tokens": 137644416000, "tok_s": 157650.1}
|
| 119 |
+
{"step": 131320, "epoch": 0.834, "loss": 1.66715, "ppl": 5.297, "lr": 0.003, "grad": 0.0933, "tokens": 137665382400, "tok_s": 158072.0}
|
| 120 |
+
{"step": 131340, "epoch": 0.834, "loss": 1.632, "ppl": 5.114, "lr": 0.003, "grad": 0.1561, "tokens": 137686348800, "tok_s": 157772.4}
|
| 121 |
+
{"step": 131360, "epoch": 0.835, "loss": 1.75856, "ppl": 5.804, "lr": 0.003, "grad": 0.136, "tokens": 137707315200, "tok_s": 157630.9}
|
| 122 |
+
{"step": 131380, "epoch": 0.835, "loss": 1.73083, "ppl": 5.645, "lr": 0.003, "grad": 0.0941, "tokens": 137728281600, "tok_s": 157560.5}
|
| 123 |
+
{"step": 131400, "epoch": 0.835, "loss": 1.64808, "ppl": 5.197, "lr": 0.003, "grad": 0.0823, "tokens": 137749248000, "tok_s": 157519.3}
|
| 124 |
+
{"step": 131420, "epoch": 0.835, "loss": 1.66477, "ppl": 5.284, "lr": 0.003, "grad": 0.0848, "tokens": 137770214400, "tok_s": 157734.5}
|
| 125 |
+
{"step": 131440, "epoch": 0.835, "loss": 1.85442, "ppl": 6.388, "lr": 0.003, "grad": 0.1732, "tokens": 137791180800, "tok_s": 157179.6}
|
| 126 |
+
{"step": 131460, "epoch": 0.835, "loss": 1.64687, "ppl": 5.191, "lr": 0.003, "grad": 0.129, "tokens": 137812147200, "tok_s": 157549.2}
|
| 127 |
+
{"step": 131480, "epoch": 0.835, "loss": 1.7237, "ppl": 5.605, "lr": 0.003, "grad": 0.0647, "tokens": 137833113600, "tok_s": 157528.5}
|
| 128 |
+
{"step": 131500, "epoch": 0.836, "loss": 1.69868, "ppl": 5.467, "lr": 0.003, "grad": 0.1381, "tokens": 137854080000, "tok_s": 157468.9}
|
| 129 |
+
{"step": 131520, "epoch": 0.836, "loss": 1.71161, "ppl": 5.538, "lr": 0.003, "grad": 0.0726, "tokens": 137875046400, "tok_s": 157284.6}
|
| 130 |
+
{"step": 131540, "epoch": 0.836, "loss": 1.71424, "ppl": 5.552, "lr": 0.003, "grad": 0.0749, "tokens": 137896012800, "tok_s": 157645.1}
|
| 131 |
+
{"step": 131560, "epoch": 0.836, "loss": 1.8113, "ppl": 6.118, "lr": 0.003, "grad": 0.1154, "tokens": 137916979200, "tok_s": 157399.5}
|
| 132 |
+
{"step": 131580, "epoch": 0.836, "loss": 1.74297, "ppl": 5.714, "lr": 0.003, "grad": 0.125, "tokens": 137937945600, "tok_s": 157590.2}
|
| 133 |
+
{"step": 131600, "epoch": 0.836, "loss": 1.77429, "ppl": 5.896, "lr": 0.003, "grad": 0.0997, "tokens": 137958912000, "tok_s": 157668.1}
|
| 134 |
+
{"step": 131620, "epoch": 0.836, "loss": 1.73877, "ppl": 5.69, "lr": 0.003, "grad": 0.1868, "tokens": 137979878400, "tok_s": 157699.2}
|
| 135 |
+
{"step": 131640, "epoch": 0.836, "loss": 1.77573, "ppl": 5.905, "lr": 0.003, "grad": 0.077, "tokens": 138000844800, "tok_s": 157620.5}
|
| 136 |
+
{"step": 131660, "epoch": 0.837, "loss": 1.64417, "ppl": 5.177, "lr": 0.003, "grad": 0.0972, "tokens": 138021811200, "tok_s": 157780.4}
|
| 137 |
+
{"step": 131680, "epoch": 0.837, "loss": 1.73902, "ppl": 5.692, "lr": 0.003, "grad": 0.1179, "tokens": 138042777600, "tok_s": 157643.1}
|
| 138 |
+
{"step": 131700, "epoch": 0.837, "loss": 1.69839, "ppl": 5.465, "lr": 0.003, "grad": 0.1525, "tokens": 138063744000, "tok_s": 157643.8}
|
| 139 |
+
{"step": 131720, "epoch": 0.837, "loss": 1.78522, "ppl": 5.961, "lr": 0.003, "grad": 0.1456, "tokens": 138084710400, "tok_s": 157688.3}
|
| 140 |
+
{"step": 131740, "epoch": 0.837, "loss": 1.60758, "ppl": 4.991, "lr": 0.003, "grad": 0.1177, "tokens": 138105676800, "tok_s": 157962.8}
|
| 141 |
+
{"step": 131760, "epoch": 0.837, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.145, "tokens": 138126643200, "tok_s": 158007.3}
|
| 142 |
+
{"step": 131780, "epoch": 0.837, "loss": 1.78108, "ppl": 5.936, "lr": 0.003, "grad": 0.074, "tokens": 138147609600, "tok_s": 158050.7}
|
| 143 |
+
{"step": 131800, "epoch": 0.837, "loss": 1.75782, "ppl": 5.8, "lr": 0.003, "grad": 0.1127, "tokens": 138168576000, "tok_s": 157976.4}
|
| 144 |
+
{"step": 131820, "epoch": 0.838, "loss": 1.77594, "ppl": 5.906, "lr": 0.003, "grad": 0.1154, "tokens": 138189542400, "tok_s": 157906.9}
|
| 145 |
+
{"step": 131840, "epoch": 0.838, "loss": 1.77775, "ppl": 5.917, "lr": 0.003, "grad": 0.1757, "tokens": 138210508800, "tok_s": 158068.5}
|
| 146 |
+
{"step": 131860, "epoch": 0.838, "loss": 1.80142, "ppl": 6.058, "lr": 0.003, "grad": 0.0993, "tokens": 138231475200, "tok_s": 157823.5}
|
| 147 |
+
{"step": 131880, "epoch": 0.838, "loss": 1.71506, "ppl": 5.557, "lr": 0.003, "grad": 0.0822, "tokens": 138252441600, "tok_s": 157898.3}
|
| 148 |
+
{"step": 131900, "epoch": 0.838, "loss": 1.76876, "ppl": 5.864, "lr": 0.003, "grad": 0.136, "tokens": 138273408000, "tok_s": 157977.2}
|
| 149 |
+
{"step": 131920, "epoch": 0.838, "loss": 1.76676, "ppl": 5.852, "lr": 0.003, "grad": 0.126, "tokens": 138294374400, "tok_s": 157946.6}
|
| 150 |
+
{"step": 131940, "epoch": 0.838, "loss": 1.73315, "ppl": 5.658, "lr": 0.003, "grad": 0.1036, "tokens": 138315340800, "tok_s": 158005.4}
|
| 151 |
+
{"step": 131960, "epoch": 0.838, "loss": 1.78912, "ppl": 5.984, "lr": 0.003, "grad": 0.1326, "tokens": 138336307200, "tok_s": 157480.7}
|
| 152 |
+
{"step": 131980, "epoch": 0.839, "loss": 1.76096, "ppl": 5.818, "lr": 0.003, "grad": 0.1085, "tokens": 138357273600, "tok_s": 157867.0}
|
| 153 |
+
{"step": 132000, "epoch": 0.839, "loss": 1.76569, "ppl": 5.846, "lr": 0.003, "grad": 0.1584, "tokens": 138378240000, "tok_s": 157850.0}
|
| 154 |
+
{"step": 132000, "val_loss": 1.74875, "val_ppl": 5.747, "is_best": false}
|
| 155 |
+
{"step": 132020, "epoch": 0.839, "loss": 1.69698, "ppl": 5.457, "lr": 0.003, "grad": 0.1421, "tokens": 138399206400, "tok_s": 157601.8}
|
| 156 |
+
{"step": 132040, "epoch": 0.839, "loss": 1.75525, "ppl": 5.785, "lr": 0.003, "grad": 0.1078, "tokens": 138420172800, "tok_s": 157739.3}
|
| 157 |
+
{"step": 132060, "epoch": 0.839, "loss": 1.73777, "ppl": 5.685, "lr": 0.003, "grad": 0.1162, "tokens": 138441139200, "tok_s": 157525.8}
|
| 158 |
+
{"step": 132080, "epoch": 0.839, "loss": 1.7778, "ppl": 5.917, "lr": 0.003, "grad": 0.1763, "tokens": 138462105600, "tok_s": 157671.1}
|
| 159 |
+
{"step": 132100, "epoch": 0.839, "loss": 1.7743, "ppl": 5.896, "lr": 0.003, "grad": 0.0966, "tokens": 138483072000, "tok_s": 157618.2}
|
| 160 |
+
{"step": 132120, "epoch": 0.839, "loss": 1.74049, "ppl": 5.7, "lr": 0.003, "grad": 0.1043, "tokens": 138504038400, "tok_s": 157679.9}
|
| 161 |
+
{"step": 132140, "epoch": 0.84, "loss": 1.72584, "ppl": 5.617, "lr": 0.003, "grad": 0.1767, "tokens": 138525004800, "tok_s": 157262.9}
|
| 162 |
+
{"step": 132160, "epoch": 0.84, "loss": 1.73587, "ppl": 5.674, "lr": 0.003, "grad": 0.0999, "tokens": 138545971200, "tok_s": 157501.8}
|
| 163 |
+
{"step": 132180, "epoch": 0.84, "loss": 1.68203, "ppl": 5.376, "lr": 0.003, "grad": 0.1062, "tokens": 138566937600, "tok_s": 157359.5}
|
| 164 |
+
{"step": 132200, "epoch": 0.84, "loss": 1.74314, "ppl": 5.715, "lr": 0.003, "grad": 0.1354, "tokens": 138587904000, "tok_s": 157072.1}
|
| 165 |
+
{"step": 132220, "epoch": 0.84, "loss": 1.72971, "ppl": 5.639, "lr": 0.003, "grad": 0.1387, "tokens": 138608870400, "tok_s": 157576.1}
|
| 166 |
+
{"step": 132240, "epoch": 0.84, "loss": 1.73357, "ppl": 5.661, "lr": 0.003, "grad": 0.098, "tokens": 138629836800, "tok_s": 157649.8}
|
| 167 |
+
{"step": 132260, "epoch": 0.84, "loss": 1.74675, "ppl": 5.736, "lr": 0.003, "grad": 0.1068, "tokens": 138650803200, "tok_s": 157764.2}
|
| 168 |
+
{"step": 132280, "epoch": 0.84, "loss": 1.77038, "ppl": 5.873, "lr": 0.003, "grad": 0.1456, "tokens": 138671769600, "tok_s": 157967.1}
|
| 169 |
+
{"step": 132300, "epoch": 0.841, "loss": 1.8218, "ppl": 6.183, "lr": 0.003, "grad": 0.0853, "tokens": 138692736000, "tok_s": 157682.7}
|
| 170 |
+
{"step": 132320, "epoch": 0.841, "loss": 1.72384, "ppl": 5.606, "lr": 0.003, "grad": 0.1439, "tokens": 138713702400, "tok_s": 157883.0}
|
| 171 |
+
{"step": 132340, "epoch": 0.841, "loss": 1.75353, "ppl": 5.775, "lr": 0.003, "grad": 0.1557, "tokens": 138734668800, "tok_s": 157829.6}
|
| 172 |
+
{"step": 132360, "epoch": 0.841, "loss": 1.73972, "ppl": 5.696, "lr": 0.003, "grad": 0.1058, "tokens": 138755635200, "tok_s": 157442.5}
|
| 173 |
+
{"step": 132380, "epoch": 0.841, "loss": 1.69361, "ppl": 5.439, "lr": 0.003, "grad": 0.1688, "tokens": 138776601600, "tok_s": 157621.1}
|
| 174 |
+
{"step": 132400, "epoch": 0.841, "loss": 1.71355, "ppl": 5.549, "lr": 0.003, "grad": 0.145, "tokens": 138797568000, "tok_s": 157569.8}
|
| 175 |
+
{"step": 132420, "epoch": 0.841, "loss": 1.73959, "ppl": 5.695, "lr": 0.003, "grad": 0.1209, "tokens": 138818534400, "tok_s": 157470.4}
|
| 176 |
+
{"step": 132440, "epoch": 0.841, "loss": 1.72795, "ppl": 5.629, "lr": 0.003, "grad": 0.0694, "tokens": 138839500800, "tok_s": 157427.6}
|
| 177 |
+
{"step": 132460, "epoch": 0.842, "loss": 1.73898, "ppl": 5.692, "lr": 0.003, "grad": 0.0875, "tokens": 138860467200, "tok_s": 157108.8}
|
| 178 |
+
{"step": 132480, "epoch": 0.842, "loss": 1.65345, "ppl": 5.225, "lr": 0.003, "grad": 0.1577, "tokens": 138881433600, "tok_s": 157311.1}
|
| 179 |
+
{"step": 132500, "epoch": 0.842, "loss": 1.86423, "ppl": 6.451, "lr": 0.003, "grad": 0.1284, "tokens": 138902400000, "tok_s": 157609.8}
|
| 180 |
+
{"step": 132520, "epoch": 0.842, "loss": 1.79026, "ppl": 5.991, "lr": 0.003, "grad": 0.0932, "tokens": 138923366400, "tok_s": 157613.0}
|
| 181 |
+
{"step": 132540, "epoch": 0.842, "loss": 1.69567, "ppl": 5.45, "lr": 0.003, "grad": 0.0825, "tokens": 138944332800, "tok_s": 157481.8}
|
| 182 |
+
{"step": 132560, "epoch": 0.842, "loss": 1.849, "ppl": 6.353, "lr": 0.003, "grad": 0.187, "tokens": 138965299200, "tok_s": 157603.3}
|
| 183 |
+
{"step": 132580, "epoch": 0.842, "loss": 1.73277, "ppl": 5.656, "lr": 0.003, "grad": 0.0583, "tokens": 138986265600, "tok_s": 157578.2}
|
| 184 |
+
{"step": 132600, "epoch": 0.842, "loss": 1.82164, "ppl": 6.182, "lr": 0.003, "grad": 0.135, "tokens": 139007232000, "tok_s": 157121.3}
|
| 185 |
+
{"step": 132620, "epoch": 0.843, "loss": 1.73835, "ppl": 5.688, "lr": 0.003, "grad": 0.1451, "tokens": 139028198400, "tok_s": 157685.5}
|
| 186 |
+
{"step": 132640, "epoch": 0.843, "loss": 1.75239, "ppl": 5.768, "lr": 0.003, "grad": 0.0742, "tokens": 139049164800, "tok_s": 157357.0}
|
| 187 |
+
{"step": 132660, "epoch": 0.843, "loss": 1.63576, "ppl": 5.133, "lr": 0.003, "grad": 0.0914, "tokens": 139070131200, "tok_s": 157522.7}
|
| 188 |
+
{"step": 132680, "epoch": 0.843, "loss": 1.46719, "ppl": 4.337, "lr": 0.003, "grad": 0.1026, "tokens": 139091097600, "tok_s": 157461.0}
|
| 189 |
+
{"step": 132700, "epoch": 0.843, "loss": 1.80041, "ppl": 6.052, "lr": 0.003, "grad": 0.0887, "tokens": 139112064000, "tok_s": 157475.2}
|
| 190 |
+
{"step": 132720, "epoch": 0.843, "loss": 1.70084, "ppl": 5.479, "lr": 0.003, "grad": 0.1375, "tokens": 139133030400, "tok_s": 157471.6}
|
| 191 |
+
{"step": 132740, "epoch": 0.843, "loss": 1.71568, "ppl": 5.56, "lr": 0.003, "grad": 0.0952, "tokens": 139153996800, "tok_s": 157569.9}
|
| 192 |
+
{"step": 132760, "epoch": 0.844, "loss": 1.74289, "ppl": 5.714, "lr": 0.003, "grad": 0.123, "tokens": 139174963200, "tok_s": 157878.1}
|
| 193 |
+
{"step": 132780, "epoch": 0.844, "loss": 1.7079, "ppl": 5.517, "lr": 0.003, "grad": 0.1535, "tokens": 139195929600, "tok_s": 158043.0}
|
| 194 |
+
{"step": 132800, "epoch": 0.844, "loss": 1.76652, "ppl": 5.85, "lr": 0.003, "grad": 0.1081, "tokens": 139216896000, "tok_s": 157879.3}
|
| 195 |
+
{"step": 132820, "epoch": 0.844, "loss": 1.75004, "ppl": 5.755, "lr": 0.003, "grad": 0.1422, "tokens": 139237862400, "tok_s": 157829.7}
|
| 196 |
+
{"step": 132840, "epoch": 0.844, "loss": 1.76497, "ppl": 5.841, "lr": 0.003, "grad": 0.1095, "tokens": 139258828800, "tok_s": 157770.3}
|
| 197 |
+
{"step": 132860, "epoch": 0.844, "loss": 1.73989, "ppl": 5.697, "lr": 0.003, "grad": 0.1555, "tokens": 139279795200, "tok_s": 157835.4}
|
| 198 |
+
{"step": 132880, "epoch": 0.844, "loss": 1.74324, "ppl": 5.716, "lr": 0.003, "grad": 0.11, "tokens": 139300761600, "tok_s": 158061.5}
|
| 199 |
+
{"step": 132900, "epoch": 0.844, "loss": 1.7311, "ppl": 5.647, "lr": 0.003, "grad": 0.1025, "tokens": 139321728000, "tok_s": 157447.3}
|
| 200 |
+
{"step": 132920, "epoch": 0.845, "loss": 1.73094, "ppl": 5.646, "lr": 0.003, "grad": 0.1042, "tokens": 139342694400, "tok_s": 157224.2}
|
| 201 |
+
{"step": 132940, "epoch": 0.845, "loss": 1.73889, "ppl": 5.691, "lr": 0.003, "grad": 0.1608, "tokens": 139363660800, "tok_s": 157202.8}
|
| 202 |
+
{"step": 132960, "epoch": 0.845, "loss": 1.76878, "ppl": 5.864, "lr": 0.003, "grad": 0.1568, "tokens": 139384627200, "tok_s": 157899.8}
|
| 203 |
+
{"step": 132980, "epoch": 0.845, "loss": 1.73773, "ppl": 5.684, "lr": 0.003, "grad": 0.0842, "tokens": 139405593600, "tok_s": 157754.9}
|
| 204 |
+
{"step": 133000, "epoch": 0.845, "loss": 1.76731, "ppl": 5.855, "lr": 0.003, "grad": 0.1676, "tokens": 139426560000, "tok_s": 156927.4}
|
| 205 |
+
{"step": 133000, "val_loss": 1.74935, "val_ppl": 5.751, "is_best": false}
|
logs/log_134000.jsonl
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 129000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-06T20:51:27.189113"}
|
| 2 |
+
{"step": 129020, "epoch": 0.82, "loss": 1.7484, "ppl": 5.745, "lr": 0.003, "grad": 0.128, "tokens": 135254246400, "tok_s": 157033.6}
|
| 3 |
+
{"step": 129040, "epoch": 0.82, "loss": 1.7463, "ppl": 5.733, "lr": 0.003, "grad": 0.1339, "tokens": 135275212800, "tok_s": 157455.3}
|
| 4 |
+
{"step": 129060, "epoch": 0.82, "loss": 1.72289, "ppl": 5.601, "lr": 0.003, "grad": 0.0914, "tokens": 135296179200, "tok_s": 157658.8}
|
| 5 |
+
{"step": 129080, "epoch": 0.82, "loss": 1.61329, "ppl": 5.019, "lr": 0.003, "grad": 0.0695, "tokens": 135317145600, "tok_s": 157571.0}
|
| 6 |
+
{"step": 129100, "epoch": 0.82, "loss": 1.7691, "ppl": 5.866, "lr": 0.003, "grad": 0.0851, "tokens": 135338112000, "tok_s": 157376.2}
|
| 7 |
+
{"step": 129120, "epoch": 0.82, "loss": 1.73223, "ppl": 5.653, "lr": 0.003, "grad": 0.1258, "tokens": 135359078400, "tok_s": 157535.3}
|
| 8 |
+
{"step": 129140, "epoch": 0.821, "loss": 1.74594, "ppl": 5.731, "lr": 0.003, "grad": 0.1169, "tokens": 135380044800, "tok_s": 157194.1}
|
| 9 |
+
{"step": 129160, "epoch": 0.821, "loss": 1.67829, "ppl": 5.356, "lr": 0.003, "grad": 0.1458, "tokens": 135401011200, "tok_s": 157471.7}
|
| 10 |
+
{"step": 129180, "epoch": 0.821, "loss": 1.62889, "ppl": 5.098, "lr": 0.003, "grad": 0.0851, "tokens": 135421977600, "tok_s": 157698.5}
|
| 11 |
+
{"step": 129200, "epoch": 0.821, "loss": 1.58919, "ppl": 4.9, "lr": 0.003, "grad": 0.0721, "tokens": 135442944000, "tok_s": 157629.3}
|
| 12 |
+
{"step": 129220, "epoch": 0.821, "loss": 1.78037, "ppl": 5.932, "lr": 0.003, "grad": 0.104, "tokens": 135463910400, "tok_s": 157497.6}
|
| 13 |
+
{"step": 129240, "epoch": 0.821, "loss": 1.70018, "ppl": 5.475, "lr": 0.003, "grad": 0.1103, "tokens": 135484876800, "tok_s": 157761.0}
|
| 14 |
+
{"step": 129260, "epoch": 0.821, "loss": 1.76303, "ppl": 5.83, "lr": 0.003, "grad": 0.0733, "tokens": 135505843200, "tok_s": 157716.0}
|
| 15 |
+
{"step": 129280, "epoch": 0.821, "loss": 1.7109, "ppl": 5.534, "lr": 0.003, "grad": 0.0864, "tokens": 135526809600, "tok_s": 157454.0}
|
| 16 |
+
{"step": 129300, "epoch": 0.822, "loss": 1.75566, "ppl": 5.787, "lr": 0.003, "grad": 0.1019, "tokens": 135547776000, "tok_s": 157428.3}
|
| 17 |
+
{"step": 129320, "epoch": 0.822, "loss": 1.76169, "ppl": 5.822, "lr": 0.003, "grad": 0.0998, "tokens": 135568742400, "tok_s": 157312.0}
|
| 18 |
+
{"step": 129340, "epoch": 0.822, "loss": 1.72612, "ppl": 5.619, "lr": 0.003, "grad": 0.0813, "tokens": 135589708800, "tok_s": 157126.1}
|
| 19 |
+
{"step": 129360, "epoch": 0.822, "loss": 1.77206, "ppl": 5.883, "lr": 0.003, "grad": 0.0782, "tokens": 135610675200, "tok_s": 156806.1}
|
| 20 |
+
{"step": 129380, "epoch": 0.822, "loss": 1.68123, "ppl": 5.372, "lr": 0.003, "grad": 0.1173, "tokens": 135631641600, "tok_s": 157407.9}
|
| 21 |
+
{"step": 129400, "epoch": 0.822, "loss": 1.78315, "ppl": 5.949, "lr": 0.003, "grad": 0.122, "tokens": 135652608000, "tok_s": 157273.9}
|
| 22 |
+
{"step": 129420, "epoch": 0.822, "loss": 1.7614, "ppl": 5.821, "lr": 0.003, "grad": 0.1357, "tokens": 135673574400, "tok_s": 157234.6}
|
| 23 |
+
{"step": 129440, "epoch": 0.822, "loss": 1.67073, "ppl": 5.316, "lr": 0.003, "grad": 0.0705, "tokens": 135694540800, "tok_s": 157421.7}
|
| 24 |
+
{"step": 129460, "epoch": 0.823, "loss": 1.8125, "ppl": 6.126, "lr": 0.003, "grad": 0.1151, "tokens": 135715507200, "tok_s": 157245.2}
|
| 25 |
+
{"step": 129480, "epoch": 0.823, "loss": 1.80825, "ppl": 6.1, "lr": 0.003, "grad": 0.1427, "tokens": 135736473600, "tok_s": 157396.8}
|
| 26 |
+
{"step": 129500, "epoch": 0.823, "loss": 1.90675, "ppl": 6.731, "lr": 0.003, "grad": 0.1583, "tokens": 135757440000, "tok_s": 157256.3}
|
| 27 |
+
{"step": 129520, "epoch": 0.823, "loss": 1.76329, "ppl": 5.832, "lr": 0.003, "grad": 0.1181, "tokens": 135778406400, "tok_s": 157268.5}
|
| 28 |
+
{"step": 129540, "epoch": 0.823, "loss": 1.65928, "ppl": 5.256, "lr": 0.003, "grad": 0.0893, "tokens": 135799372800, "tok_s": 157524.4}
|
| 29 |
+
{"step": 129560, "epoch": 0.823, "loss": 1.67935, "ppl": 5.362, "lr": 0.003, "grad": 0.0811, "tokens": 135820339200, "tok_s": 157585.8}
|
| 30 |
+
{"step": 129580, "epoch": 0.823, "loss": 1.70283, "ppl": 5.489, "lr": 0.003, "grad": 0.0908, "tokens": 135841305600, "tok_s": 157641.4}
|
| 31 |
+
{"step": 129600, "epoch": 0.823, "loss": 1.63922, "ppl": 5.151, "lr": 0.003, "grad": 0.0788, "tokens": 135862272000, "tok_s": 157853.0}
|
| 32 |
+
{"step": 129620, "epoch": 0.824, "loss": 1.715, "ppl": 5.557, "lr": 0.003, "grad": 0.1425, "tokens": 135883238400, "tok_s": 157261.9}
|
| 33 |
+
{"step": 129640, "epoch": 0.824, "loss": 1.66125, "ppl": 5.266, "lr": 0.003, "grad": 0.1515, "tokens": 135904204800, "tok_s": 157824.0}
|
| 34 |
+
{"step": 129660, "epoch": 0.824, "loss": 1.8425, "ppl": 6.312, "lr": 0.003, "grad": 0.0936, "tokens": 135925171200, "tok_s": 157414.2}
|
| 35 |
+
{"step": 129680, "epoch": 0.824, "loss": 1.77156, "ppl": 5.88, "lr": 0.003, "grad": 0.1027, "tokens": 135946137600, "tok_s": 157952.8}
|
| 36 |
+
{"step": 129700, "epoch": 0.824, "loss": 1.74271, "ppl": 5.713, "lr": 0.003, "grad": 0.1877, "tokens": 135967104000, "tok_s": 157854.5}
|
| 37 |
+
{"step": 129720, "epoch": 0.824, "loss": 1.66564, "ppl": 5.289, "lr": 0.003, "grad": 0.0791, "tokens": 135988070400, "tok_s": 158021.8}
|
| 38 |
+
{"step": 129740, "epoch": 0.824, "loss": 1.69832, "ppl": 5.465, "lr": 0.003, "grad": 0.0909, "tokens": 136009036800, "tok_s": 157578.1}
|
| 39 |
+
{"step": 129760, "epoch": 0.824, "loss": 1.76803, "ppl": 5.859, "lr": 0.003, "grad": 0.1282, "tokens": 136030003200, "tok_s": 157033.8}
|
| 40 |
+
{"step": 129780, "epoch": 0.825, "loss": 1.67652, "ppl": 5.347, "lr": 0.003, "grad": 0.1203, "tokens": 136050969600, "tok_s": 157782.2}
|
| 41 |
+
{"step": 129800, "epoch": 0.825, "loss": 1.69139, "ppl": 5.427, "lr": 0.003, "grad": 0.0993, "tokens": 136071936000, "tok_s": 157805.7}
|
| 42 |
+
{"step": 129820, "epoch": 0.825, "loss": 1.74188, "ppl": 5.708, "lr": 0.003, "grad": 0.1586, "tokens": 136092902400, "tok_s": 157652.6}
|
| 43 |
+
{"step": 129840, "epoch": 0.825, "loss": 1.67522, "ppl": 5.34, "lr": 0.003, "grad": 0.1048, "tokens": 136113868800, "tok_s": 157892.9}
|
| 44 |
+
{"step": 129860, "epoch": 0.825, "loss": 1.75256, "ppl": 5.769, "lr": 0.003, "grad": 0.1189, "tokens": 136134835200, "tok_s": 157781.2}
|
| 45 |
+
{"step": 129880, "epoch": 0.825, "loss": 1.77965, "ppl": 5.928, "lr": 0.003, "grad": 0.1049, "tokens": 136155801600, "tok_s": 157693.3}
|
| 46 |
+
{"step": 129900, "epoch": 0.825, "loss": 1.45431, "ppl": 4.282, "lr": 0.003, "grad": 0.1174, "tokens": 136176768000, "tok_s": 157650.5}
|
| 47 |
+
{"step": 129920, "epoch": 0.825, "loss": 1.67703, "ppl": 5.35, "lr": 0.003, "grad": 0.1193, "tokens": 136197734400, "tok_s": 157459.6}
|
| 48 |
+
{"step": 129940, "epoch": 0.826, "loss": 1.68942, "ppl": 5.416, "lr": 0.003, "grad": 0.1002, "tokens": 136218700800, "tok_s": 157493.8}
|
| 49 |
+
{"step": 129960, "epoch": 0.826, "loss": 1.78371, "ppl": 5.952, "lr": 0.003, "grad": 0.0927, "tokens": 136239667200, "tok_s": 157312.5}
|
| 50 |
+
{"step": 129980, "epoch": 0.826, "loss": 1.73478, "ppl": 5.668, "lr": 0.003, "grad": 0.0805, "tokens": 136260633600, "tok_s": 157586.0}
|
| 51 |
+
{"step": 130000, "epoch": 0.826, "loss": 1.88894, "ppl": 6.612, "lr": 0.003, "grad": 0.1294, "tokens": 136281600000, "tok_s": 157467.5}
|
| 52 |
+
{"step": 130000, "val_loss": 1.73054, "val_ppl": 5.644, "is_best": true}
|
| 53 |
+
{"step": 130020, "epoch": 0.826, "loss": 1.73526, "ppl": 5.67, "lr": 0.003, "grad": 0.129, "tokens": 136302566400, "tok_s": 157572.7}
|
| 54 |
+
{"step": 130040, "epoch": 0.826, "loss": 1.67846, "ppl": 5.357, "lr": 0.003, "grad": 0.1445, "tokens": 136323532800, "tok_s": 157713.9}
|
| 55 |
+
{"step": 130060, "epoch": 0.826, "loss": 1.77431, "ppl": 5.896, "lr": 0.003, "grad": 0.1509, "tokens": 136344499200, "tok_s": 157621.4}
|
| 56 |
+
{"step": 130080, "epoch": 0.826, "loss": 1.72493, "ppl": 5.612, "lr": 0.003, "grad": 0.1217, "tokens": 136365465600, "tok_s": 157750.6}
|
| 57 |
+
{"step": 130100, "epoch": 0.827, "loss": 1.59641, "ppl": 4.935, "lr": 0.003, "grad": 0.1226, "tokens": 136386432000, "tok_s": 157654.8}
|
| 58 |
+
{"step": 130120, "epoch": 0.827, "loss": 1.86963, "ppl": 6.486, "lr": 0.003, "grad": 0.126, "tokens": 136407398400, "tok_s": 157206.8}
|
| 59 |
+
{"step": 130140, "epoch": 0.827, "loss": 1.76439, "ppl": 5.838, "lr": 0.003, "grad": 0.0794, "tokens": 136428364800, "tok_s": 157463.5}
|
| 60 |
+
{"step": 130160, "epoch": 0.827, "loss": 1.75045, "ppl": 5.757, "lr": 0.003, "grad": 0.1228, "tokens": 136449331200, "tok_s": 157764.7}
|
| 61 |
+
{"step": 130180, "epoch": 0.827, "loss": 1.79344, "ppl": 6.01, "lr": 0.003, "grad": 0.1249, "tokens": 136470297600, "tok_s": 157403.3}
|
| 62 |
+
{"step": 130200, "epoch": 0.827, "loss": 1.7078, "ppl": 5.517, "lr": 0.003, "grad": 0.1528, "tokens": 136491264000, "tok_s": 157600.0}
|
| 63 |
+
{"step": 130220, "epoch": 0.827, "loss": 1.7805, "ppl": 5.933, "lr": 0.003, "grad": 0.1495, "tokens": 136512230400, "tok_s": 157095.7}
|
| 64 |
+
{"step": 130240, "epoch": 0.827, "loss": 1.69056, "ppl": 5.423, "lr": 0.003, "grad": 0.0973, "tokens": 136533196800, "tok_s": 157330.4}
|
| 65 |
+
{"step": 130260, "epoch": 0.828, "loss": 1.72071, "ppl": 5.589, "lr": 0.003, "grad": 0.1227, "tokens": 136554163200, "tok_s": 157583.4}
|
| 66 |
+
{"step": 130280, "epoch": 0.828, "loss": 1.60413, "ppl": 4.974, "lr": 0.003, "grad": 0.0853, "tokens": 136575129600, "tok_s": 157614.5}
|
| 67 |
+
{"step": 130300, "epoch": 0.828, "loss": 1.80194, "ppl": 6.061, "lr": 0.003, "grad": 0.1207, "tokens": 136596096000, "tok_s": 157752.1}
|
| 68 |
+
{"step": 130320, "epoch": 0.828, "loss": 1.74305, "ppl": 5.715, "lr": 0.003, "grad": 0.0819, "tokens": 136617062400, "tok_s": 157633.7}
|
| 69 |
+
{"step": 130340, "epoch": 0.828, "loss": 1.79549, "ppl": 6.022, "lr": 0.003, "grad": 0.1231, "tokens": 136638028800, "tok_s": 157535.5}
|
| 70 |
+
{"step": 130360, "epoch": 0.828, "loss": 1.73445, "ppl": 5.666, "lr": 0.003, "grad": 0.1615, "tokens": 136658995200, "tok_s": 157510.3}
|
| 71 |
+
{"step": 130380, "epoch": 0.828, "loss": 1.84461, "ppl": 6.326, "lr": 0.003, "grad": 0.1089, "tokens": 136679961600, "tok_s": 157324.6}
|
| 72 |
+
{"step": 130400, "epoch": 0.829, "loss": 1.81211, "ppl": 6.123, "lr": 0.003, "grad": 0.0719, "tokens": 136700928000, "tok_s": 157495.8}
|
| 73 |
+
{"step": 130420, "epoch": 0.829, "loss": 1.79467, "ppl": 6.017, "lr": 0.003, "grad": 0.1391, "tokens": 136721894400, "tok_s": 157411.2}
|
| 74 |
+
{"step": 130440, "epoch": 0.829, "loss": 1.73476, "ppl": 5.668, "lr": 0.003, "grad": 0.1071, "tokens": 136742860800, "tok_s": 157766.3}
|
| 75 |
+
{"step": 130460, "epoch": 0.829, "loss": 1.77554, "ppl": 5.903, "lr": 0.003, "grad": 0.1642, "tokens": 136763827200, "tok_s": 157367.3}
|
| 76 |
+
{"step": 130480, "epoch": 0.829, "loss": 1.82101, "ppl": 6.178, "lr": 0.003, "grad": 0.152, "tokens": 136784793600, "tok_s": 157044.7}
|
| 77 |
+
{"step": 130500, "epoch": 0.829, "loss": 1.77909, "ppl": 5.924, "lr": 0.003, "grad": 0.0888, "tokens": 136805760000, "tok_s": 157331.6}
|
| 78 |
+
{"step": 130520, "epoch": 0.829, "loss": 1.78449, "ppl": 5.957, "lr": 0.003, "grad": 0.1207, "tokens": 136826726400, "tok_s": 157559.0}
|
| 79 |
+
{"step": 130540, "epoch": 0.829, "loss": 1.70914, "ppl": 5.524, "lr": 0.003, "grad": 0.0981, "tokens": 136847692800, "tok_s": 157448.7}
|
| 80 |
+
{"step": 130560, "epoch": 0.83, "loss": 1.79092, "ppl": 5.995, "lr": 0.003, "grad": 0.15, "tokens": 136868659200, "tok_s": 157276.3}
|
| 81 |
+
{"step": 130580, "epoch": 0.83, "loss": 1.59137, "ppl": 4.91, "lr": 0.003, "grad": 0.0904, "tokens": 136889625600, "tok_s": 157370.7}
|
| 82 |
+
{"step": 130600, "epoch": 0.83, "loss": 1.76625, "ppl": 5.849, "lr": 0.003, "grad": 0.1367, "tokens": 136910592000, "tok_s": 157680.7}
|
| 83 |
+
{"step": 130620, "epoch": 0.83, "loss": 1.76693, "ppl": 5.853, "lr": 0.003, "grad": 0.0967, "tokens": 136931558400, "tok_s": 157881.4}
|
| 84 |
+
{"step": 130640, "epoch": 0.83, "loss": 1.73096, "ppl": 5.646, "lr": 0.003, "grad": 0.1168, "tokens": 136952524800, "tok_s": 157890.0}
|
| 85 |
+
{"step": 130660, "epoch": 0.83, "loss": 1.78401, "ppl": 5.954, "lr": 0.003, "grad": 0.0815, "tokens": 136973491200, "tok_s": 157896.6}
|
| 86 |
+
{"step": 130680, "epoch": 0.83, "loss": 1.75759, "ppl": 5.798, "lr": 0.003, "grad": 0.1412, "tokens": 136994457600, "tok_s": 157487.0}
|
| 87 |
+
{"step": 130700, "epoch": 0.83, "loss": 1.72975, "ppl": 5.639, "lr": 0.003, "grad": 0.0976, "tokens": 137015424000, "tok_s": 157535.5}
|
| 88 |
+
{"step": 130720, "epoch": 0.831, "loss": 1.70747, "ppl": 5.515, "lr": 0.003, "grad": 0.0945, "tokens": 137036390400, "tok_s": 157837.2}
|
| 89 |
+
{"step": 130740, "epoch": 0.831, "loss": 1.74526, "ppl": 5.727, "lr": 0.003, "grad": 0.0914, "tokens": 137057356800, "tok_s": 157859.8}
|
| 90 |
+
{"step": 130760, "epoch": 0.831, "loss": 1.63925, "ppl": 5.151, "lr": 0.003, "grad": 0.1153, "tokens": 137078323200, "tok_s": 158056.6}
|
| 91 |
+
{"step": 130780, "epoch": 0.831, "loss": 1.71553, "ppl": 5.56, "lr": 0.003, "grad": 0.1075, "tokens": 137099289600, "tok_s": 158017.2}
|
| 92 |
+
{"step": 130800, "epoch": 0.831, "loss": 1.73857, "ppl": 5.689, "lr": 0.003, "grad": 0.0948, "tokens": 137120256000, "tok_s": 157914.3}
|
| 93 |
+
{"step": 130820, "epoch": 0.831, "loss": 1.76271, "ppl": 5.828, "lr": 0.003, "grad": 0.1691, "tokens": 137141222400, "tok_s": 157998.3}
|
| 94 |
+
{"step": 130840, "epoch": 0.831, "loss": 1.7782, "ppl": 5.919, "lr": 0.003, "grad": 0.1244, "tokens": 137162188800, "tok_s": 157819.2}
|
| 95 |
+
{"step": 130860, "epoch": 0.831, "loss": 1.78937, "ppl": 5.986, "lr": 0.003, "grad": 0.0636, "tokens": 137183155200, "tok_s": 158018.9}
|
| 96 |
+
{"step": 130880, "epoch": 0.832, "loss": 1.76957, "ppl": 5.868, "lr": 0.003, "grad": 0.1611, "tokens": 137204121600, "tok_s": 157905.5}
|
| 97 |
+
{"step": 130900, "epoch": 0.832, "loss": 1.75428, "ppl": 5.779, "lr": 0.003, "grad": 0.1247, "tokens": 137225088000, "tok_s": 157896.3}
|
| 98 |
+
{"step": 130920, "epoch": 0.832, "loss": 1.77733, "ppl": 5.914, "lr": 0.003, "grad": 0.1442, "tokens": 137246054400, "tok_s": 157771.9}
|
| 99 |
+
{"step": 130940, "epoch": 0.832, "loss": 1.72573, "ppl": 5.617, "lr": 0.003, "grad": 0.0854, "tokens": 137267020800, "tok_s": 157898.0}
|
| 100 |
+
{"step": 130960, "epoch": 0.832, "loss": 1.7495, "ppl": 5.752, "lr": 0.003, "grad": 0.1204, "tokens": 137287987200, "tok_s": 157906.9}
|
| 101 |
+
{"step": 130980, "epoch": 0.832, "loss": 1.79697, "ppl": 6.031, "lr": 0.003, "grad": 0.1363, "tokens": 137308953600, "tok_s": 157812.5}
|
| 102 |
+
{"step": 131000, "epoch": 0.832, "loss": 1.72455, "ppl": 5.61, "lr": 0.003, "grad": 0.0756, "tokens": 137329920000, "tok_s": 157721.2}
|
| 103 |
+
{"step": 131000, "val_loss": 1.74218, "val_ppl": 5.71, "is_best": false}
|
| 104 |
+
{"step": 131020, "epoch": 0.832, "loss": 1.75914, "ppl": 5.807, "lr": 0.003, "grad": 0.1509, "tokens": 137350886400, "tok_s": 157385.2}
|
| 105 |
+
{"step": 131040, "epoch": 0.833, "loss": 1.74864, "ppl": 5.747, "lr": 0.003, "grad": 0.1302, "tokens": 137371852800, "tok_s": 157666.7}
|
| 106 |
+
{"step": 131060, "epoch": 0.833, "loss": 1.6946, "ppl": 5.444, "lr": 0.003, "grad": 0.1333, "tokens": 137392819200, "tok_s": 157782.2}
|
| 107 |
+
{"step": 131080, "epoch": 0.833, "loss": 1.76508, "ppl": 5.842, "lr": 0.003, "grad": 0.1296, "tokens": 137413785600, "tok_s": 157676.3}
|
| 108 |
+
{"step": 131100, "epoch": 0.833, "loss": 1.75585, "ppl": 5.788, "lr": 0.003, "grad": 0.1434, "tokens": 137434752000, "tok_s": 157604.7}
|
| 109 |
+
{"step": 131120, "epoch": 0.833, "loss": 1.82968, "ppl": 6.232, "lr": 0.003, "grad": 0.1498, "tokens": 137455718400, "tok_s": 157303.2}
|
| 110 |
+
{"step": 131140, "epoch": 0.833, "loss": 1.76963, "ppl": 5.869, "lr": 0.003, "grad": 0.0649, "tokens": 137476684800, "tok_s": 157501.5}
|
| 111 |
+
{"step": 131160, "epoch": 0.833, "loss": 1.72302, "ppl": 5.601, "lr": 0.003, "grad": 0.1315, "tokens": 137497651200, "tok_s": 157501.2}
|
| 112 |
+
{"step": 131180, "epoch": 0.833, "loss": 1.74954, "ppl": 5.752, "lr": 0.003, "grad": 0.0876, "tokens": 137518617600, "tok_s": 157444.7}
|
| 113 |
+
{"step": 131200, "epoch": 0.834, "loss": 1.80421, "ppl": 6.075, "lr": 0.003, "grad": 0.1363, "tokens": 137539584000, "tok_s": 157558.4}
|
| 114 |
+
{"step": 131220, "epoch": 0.834, "loss": 1.70377, "ppl": 5.495, "lr": 0.003, "grad": 0.0805, "tokens": 137560550400, "tok_s": 157853.4}
|
| 115 |
+
{"step": 131240, "epoch": 0.834, "loss": 1.74897, "ppl": 5.749, "lr": 0.003, "grad": 0.119, "tokens": 137581516800, "tok_s": 157869.2}
|
| 116 |
+
{"step": 131260, "epoch": 0.834, "loss": 1.66217, "ppl": 5.271, "lr": 0.003, "grad": 0.0881, "tokens": 137602483200, "tok_s": 157851.7}
|
| 117 |
+
{"step": 131280, "epoch": 0.834, "loss": 1.76037, "ppl": 5.815, "lr": 0.003, "grad": 0.1217, "tokens": 137623449600, "tok_s": 157460.8}
|
| 118 |
+
{"step": 131300, "epoch": 0.834, "loss": 1.78582, "ppl": 5.964, "lr": 0.003, "grad": 0.1115, "tokens": 137644416000, "tok_s": 157650.1}
|
| 119 |
+
{"step": 131320, "epoch": 0.834, "loss": 1.66715, "ppl": 5.297, "lr": 0.003, "grad": 0.0933, "tokens": 137665382400, "tok_s": 158072.0}
|
| 120 |
+
{"step": 131340, "epoch": 0.834, "loss": 1.632, "ppl": 5.114, "lr": 0.003, "grad": 0.1561, "tokens": 137686348800, "tok_s": 157772.4}
|
| 121 |
+
{"step": 131360, "epoch": 0.835, "loss": 1.75856, "ppl": 5.804, "lr": 0.003, "grad": 0.136, "tokens": 137707315200, "tok_s": 157630.9}
|
| 122 |
+
{"step": 131380, "epoch": 0.835, "loss": 1.73083, "ppl": 5.645, "lr": 0.003, "grad": 0.0941, "tokens": 137728281600, "tok_s": 157560.5}
|
| 123 |
+
{"step": 131400, "epoch": 0.835, "loss": 1.64808, "ppl": 5.197, "lr": 0.003, "grad": 0.0823, "tokens": 137749248000, "tok_s": 157519.3}
|
| 124 |
+
{"step": 131420, "epoch": 0.835, "loss": 1.66477, "ppl": 5.284, "lr": 0.003, "grad": 0.0848, "tokens": 137770214400, "tok_s": 157734.5}
|
| 125 |
+
{"step": 131440, "epoch": 0.835, "loss": 1.85442, "ppl": 6.388, "lr": 0.003, "grad": 0.1732, "tokens": 137791180800, "tok_s": 157179.6}
|
| 126 |
+
{"step": 131460, "epoch": 0.835, "loss": 1.64687, "ppl": 5.191, "lr": 0.003, "grad": 0.129, "tokens": 137812147200, "tok_s": 157549.2}
|
| 127 |
+
{"step": 131480, "epoch": 0.835, "loss": 1.7237, "ppl": 5.605, "lr": 0.003, "grad": 0.0647, "tokens": 137833113600, "tok_s": 157528.5}
|
| 128 |
+
{"step": 131500, "epoch": 0.836, "loss": 1.69868, "ppl": 5.467, "lr": 0.003, "grad": 0.1381, "tokens": 137854080000, "tok_s": 157468.9}
|
| 129 |
+
{"step": 131520, "epoch": 0.836, "loss": 1.71161, "ppl": 5.538, "lr": 0.003, "grad": 0.0726, "tokens": 137875046400, "tok_s": 157284.6}
|
| 130 |
+
{"step": 131540, "epoch": 0.836, "loss": 1.71424, "ppl": 5.552, "lr": 0.003, "grad": 0.0749, "tokens": 137896012800, "tok_s": 157645.1}
|
| 131 |
+
{"step": 131560, "epoch": 0.836, "loss": 1.8113, "ppl": 6.118, "lr": 0.003, "grad": 0.1154, "tokens": 137916979200, "tok_s": 157399.5}
|
| 132 |
+
{"step": 131580, "epoch": 0.836, "loss": 1.74297, "ppl": 5.714, "lr": 0.003, "grad": 0.125, "tokens": 137937945600, "tok_s": 157590.2}
|
| 133 |
+
{"step": 131600, "epoch": 0.836, "loss": 1.77429, "ppl": 5.896, "lr": 0.003, "grad": 0.0997, "tokens": 137958912000, "tok_s": 157668.1}
|
| 134 |
+
{"step": 131620, "epoch": 0.836, "loss": 1.73877, "ppl": 5.69, "lr": 0.003, "grad": 0.1868, "tokens": 137979878400, "tok_s": 157699.2}
|
| 135 |
+
{"step": 131640, "epoch": 0.836, "loss": 1.77573, "ppl": 5.905, "lr": 0.003, "grad": 0.077, "tokens": 138000844800, "tok_s": 157620.5}
|
| 136 |
+
{"step": 131660, "epoch": 0.837, "loss": 1.64417, "ppl": 5.177, "lr": 0.003, "grad": 0.0972, "tokens": 138021811200, "tok_s": 157780.4}
|
| 137 |
+
{"step": 131680, "epoch": 0.837, "loss": 1.73902, "ppl": 5.692, "lr": 0.003, "grad": 0.1179, "tokens": 138042777600, "tok_s": 157643.1}
|
| 138 |
+
{"step": 131700, "epoch": 0.837, "loss": 1.69839, "ppl": 5.465, "lr": 0.003, "grad": 0.1525, "tokens": 138063744000, "tok_s": 157643.8}
|
| 139 |
+
{"step": 131720, "epoch": 0.837, "loss": 1.78522, "ppl": 5.961, "lr": 0.003, "grad": 0.1456, "tokens": 138084710400, "tok_s": 157688.3}
|
| 140 |
+
{"step": 131740, "epoch": 0.837, "loss": 1.60758, "ppl": 4.991, "lr": 0.003, "grad": 0.1177, "tokens": 138105676800, "tok_s": 157962.8}
|
| 141 |
+
{"step": 131760, "epoch": 0.837, "loss": 1.77645, "ppl": 5.909, "lr": 0.003, "grad": 0.145, "tokens": 138126643200, "tok_s": 158007.3}
|
| 142 |
+
{"step": 131780, "epoch": 0.837, "loss": 1.78108, "ppl": 5.936, "lr": 0.003, "grad": 0.074, "tokens": 138147609600, "tok_s": 158050.7}
|
| 143 |
+
{"step": 131800, "epoch": 0.837, "loss": 1.75782, "ppl": 5.8, "lr": 0.003, "grad": 0.1127, "tokens": 138168576000, "tok_s": 157976.4}
|
| 144 |
+
{"step": 131820, "epoch": 0.838, "loss": 1.77594, "ppl": 5.906, "lr": 0.003, "grad": 0.1154, "tokens": 138189542400, "tok_s": 157906.9}
|
| 145 |
+
{"step": 131840, "epoch": 0.838, "loss": 1.77775, "ppl": 5.917, "lr": 0.003, "grad": 0.1757, "tokens": 138210508800, "tok_s": 158068.5}
|
| 146 |
+
{"step": 131860, "epoch": 0.838, "loss": 1.80142, "ppl": 6.058, "lr": 0.003, "grad": 0.0993, "tokens": 138231475200, "tok_s": 157823.5}
|
| 147 |
+
{"step": 131880, "epoch": 0.838, "loss": 1.71506, "ppl": 5.557, "lr": 0.003, "grad": 0.0822, "tokens": 138252441600, "tok_s": 157898.3}
|
| 148 |
+
{"step": 131900, "epoch": 0.838, "loss": 1.76876, "ppl": 5.864, "lr": 0.003, "grad": 0.136, "tokens": 138273408000, "tok_s": 157977.2}
|
| 149 |
+
{"step": 131920, "epoch": 0.838, "loss": 1.76676, "ppl": 5.852, "lr": 0.003, "grad": 0.126, "tokens": 138294374400, "tok_s": 157946.6}
|
| 150 |
+
{"step": 131940, "epoch": 0.838, "loss": 1.73315, "ppl": 5.658, "lr": 0.003, "grad": 0.1036, "tokens": 138315340800, "tok_s": 158005.4}
|
| 151 |
+
{"step": 131960, "epoch": 0.838, "loss": 1.78912, "ppl": 5.984, "lr": 0.003, "grad": 0.1326, "tokens": 138336307200, "tok_s": 157480.7}
|
| 152 |
+
{"step": 131980, "epoch": 0.839, "loss": 1.76096, "ppl": 5.818, "lr": 0.003, "grad": 0.1085, "tokens": 138357273600, "tok_s": 157867.0}
|
| 153 |
+
{"step": 132000, "epoch": 0.839, "loss": 1.76569, "ppl": 5.846, "lr": 0.003, "grad": 0.1584, "tokens": 138378240000, "tok_s": 157850.0}
|
| 154 |
+
{"step": 132000, "val_loss": 1.74875, "val_ppl": 5.747, "is_best": false}
|
| 155 |
+
{"step": 132020, "epoch": 0.839, "loss": 1.69698, "ppl": 5.457, "lr": 0.003, "grad": 0.1421, "tokens": 138399206400, "tok_s": 157601.8}
|
| 156 |
+
{"step": 132040, "epoch": 0.839, "loss": 1.75525, "ppl": 5.785, "lr": 0.003, "grad": 0.1078, "tokens": 138420172800, "tok_s": 157739.3}
|
| 157 |
+
{"step": 132060, "epoch": 0.839, "loss": 1.73777, "ppl": 5.685, "lr": 0.003, "grad": 0.1162, "tokens": 138441139200, "tok_s": 157525.8}
|
| 158 |
+
{"step": 132080, "epoch": 0.839, "loss": 1.7778, "ppl": 5.917, "lr": 0.003, "grad": 0.1763, "tokens": 138462105600, "tok_s": 157671.1}
|
| 159 |
+
{"step": 132100, "epoch": 0.839, "loss": 1.7743, "ppl": 5.896, "lr": 0.003, "grad": 0.0966, "tokens": 138483072000, "tok_s": 157618.2}
|
| 160 |
+
{"step": 132120, "epoch": 0.839, "loss": 1.74049, "ppl": 5.7, "lr": 0.003, "grad": 0.1043, "tokens": 138504038400, "tok_s": 157679.9}
|
| 161 |
+
{"step": 132140, "epoch": 0.84, "loss": 1.72584, "ppl": 5.617, "lr": 0.003, "grad": 0.1767, "tokens": 138525004800, "tok_s": 157262.9}
|
| 162 |
+
{"step": 132160, "epoch": 0.84, "loss": 1.73587, "ppl": 5.674, "lr": 0.003, "grad": 0.0999, "tokens": 138545971200, "tok_s": 157501.8}
|
| 163 |
+
{"step": 132180, "epoch": 0.84, "loss": 1.68203, "ppl": 5.376, "lr": 0.003, "grad": 0.1062, "tokens": 138566937600, "tok_s": 157359.5}
|
| 164 |
+
{"step": 132200, "epoch": 0.84, "loss": 1.74314, "ppl": 5.715, "lr": 0.003, "grad": 0.1354, "tokens": 138587904000, "tok_s": 157072.1}
|
| 165 |
+
{"step": 132220, "epoch": 0.84, "loss": 1.72971, "ppl": 5.639, "lr": 0.003, "grad": 0.1387, "tokens": 138608870400, "tok_s": 157576.1}
|
| 166 |
+
{"step": 132240, "epoch": 0.84, "loss": 1.73357, "ppl": 5.661, "lr": 0.003, "grad": 0.098, "tokens": 138629836800, "tok_s": 157649.8}
|
| 167 |
+
{"step": 132260, "epoch": 0.84, "loss": 1.74675, "ppl": 5.736, "lr": 0.003, "grad": 0.1068, "tokens": 138650803200, "tok_s": 157764.2}
|
| 168 |
+
{"step": 132280, "epoch": 0.84, "loss": 1.77038, "ppl": 5.873, "lr": 0.003, "grad": 0.1456, "tokens": 138671769600, "tok_s": 157967.1}
|
| 169 |
+
{"step": 132300, "epoch": 0.841, "loss": 1.8218, "ppl": 6.183, "lr": 0.003, "grad": 0.0853, "tokens": 138692736000, "tok_s": 157682.7}
|
| 170 |
+
{"step": 132320, "epoch": 0.841, "loss": 1.72384, "ppl": 5.606, "lr": 0.003, "grad": 0.1439, "tokens": 138713702400, "tok_s": 157883.0}
|
| 171 |
+
{"step": 132340, "epoch": 0.841, "loss": 1.75353, "ppl": 5.775, "lr": 0.003, "grad": 0.1557, "tokens": 138734668800, "tok_s": 157829.6}
|
| 172 |
+
{"step": 132360, "epoch": 0.841, "loss": 1.73972, "ppl": 5.696, "lr": 0.003, "grad": 0.1058, "tokens": 138755635200, "tok_s": 157442.5}
|
| 173 |
+
{"step": 132380, "epoch": 0.841, "loss": 1.69361, "ppl": 5.439, "lr": 0.003, "grad": 0.1688, "tokens": 138776601600, "tok_s": 157621.1}
|
| 174 |
+
{"step": 132400, "epoch": 0.841, "loss": 1.71355, "ppl": 5.549, "lr": 0.003, "grad": 0.145, "tokens": 138797568000, "tok_s": 157569.8}
|
| 175 |
+
{"step": 132420, "epoch": 0.841, "loss": 1.73959, "ppl": 5.695, "lr": 0.003, "grad": 0.1209, "tokens": 138818534400, "tok_s": 157470.4}
|
| 176 |
+
{"step": 132440, "epoch": 0.841, "loss": 1.72795, "ppl": 5.629, "lr": 0.003, "grad": 0.0694, "tokens": 138839500800, "tok_s": 157427.6}
|
| 177 |
+
{"step": 132460, "epoch": 0.842, "loss": 1.73898, "ppl": 5.692, "lr": 0.003, "grad": 0.0875, "tokens": 138860467200, "tok_s": 157108.8}
|
| 178 |
+
{"step": 132480, "epoch": 0.842, "loss": 1.65345, "ppl": 5.225, "lr": 0.003, "grad": 0.1577, "tokens": 138881433600, "tok_s": 157311.1}
|
| 179 |
+
{"step": 132500, "epoch": 0.842, "loss": 1.86423, "ppl": 6.451, "lr": 0.003, "grad": 0.1284, "tokens": 138902400000, "tok_s": 157609.8}
|
| 180 |
+
{"step": 132520, "epoch": 0.842, "loss": 1.79026, "ppl": 5.991, "lr": 0.003, "grad": 0.0932, "tokens": 138923366400, "tok_s": 157613.0}
|
| 181 |
+
{"step": 132540, "epoch": 0.842, "loss": 1.69567, "ppl": 5.45, "lr": 0.003, "grad": 0.0825, "tokens": 138944332800, "tok_s": 157481.8}
|
| 182 |
+
{"step": 132560, "epoch": 0.842, "loss": 1.849, "ppl": 6.353, "lr": 0.003, "grad": 0.187, "tokens": 138965299200, "tok_s": 157603.3}
|
| 183 |
+
{"step": 132580, "epoch": 0.842, "loss": 1.73277, "ppl": 5.656, "lr": 0.003, "grad": 0.0583, "tokens": 138986265600, "tok_s": 157578.2}
|
| 184 |
+
{"step": 132600, "epoch": 0.842, "loss": 1.82164, "ppl": 6.182, "lr": 0.003, "grad": 0.135, "tokens": 139007232000, "tok_s": 157121.3}
|
| 185 |
+
{"step": 132620, "epoch": 0.843, "loss": 1.73835, "ppl": 5.688, "lr": 0.003, "grad": 0.1451, "tokens": 139028198400, "tok_s": 157685.5}
|
| 186 |
+
{"step": 132640, "epoch": 0.843, "loss": 1.75239, "ppl": 5.768, "lr": 0.003, "grad": 0.0742, "tokens": 139049164800, "tok_s": 157357.0}
|
| 187 |
+
{"step": 132660, "epoch": 0.843, "loss": 1.63576, "ppl": 5.133, "lr": 0.003, "grad": 0.0914, "tokens": 139070131200, "tok_s": 157522.7}
|
| 188 |
+
{"step": 132680, "epoch": 0.843, "loss": 1.46719, "ppl": 4.337, "lr": 0.003, "grad": 0.1026, "tokens": 139091097600, "tok_s": 157461.0}
|
| 189 |
+
{"step": 132700, "epoch": 0.843, "loss": 1.80041, "ppl": 6.052, "lr": 0.003, "grad": 0.0887, "tokens": 139112064000, "tok_s": 157475.2}
|
| 190 |
+
{"step": 132720, "epoch": 0.843, "loss": 1.70084, "ppl": 5.479, "lr": 0.003, "grad": 0.1375, "tokens": 139133030400, "tok_s": 157471.6}
|
| 191 |
+
{"step": 132740, "epoch": 0.843, "loss": 1.71568, "ppl": 5.56, "lr": 0.003, "grad": 0.0952, "tokens": 139153996800, "tok_s": 157569.9}
|
| 192 |
+
{"step": 132760, "epoch": 0.844, "loss": 1.74289, "ppl": 5.714, "lr": 0.003, "grad": 0.123, "tokens": 139174963200, "tok_s": 157878.1}
|
| 193 |
+
{"step": 132780, "epoch": 0.844, "loss": 1.7079, "ppl": 5.517, "lr": 0.003, "grad": 0.1535, "tokens": 139195929600, "tok_s": 158043.0}
|
| 194 |
+
{"step": 132800, "epoch": 0.844, "loss": 1.76652, "ppl": 5.85, "lr": 0.003, "grad": 0.1081, "tokens": 139216896000, "tok_s": 157879.3}
|
| 195 |
+
{"step": 132820, "epoch": 0.844, "loss": 1.75004, "ppl": 5.755, "lr": 0.003, "grad": 0.1422, "tokens": 139237862400, "tok_s": 157829.7}
|
| 196 |
+
{"step": 132840, "epoch": 0.844, "loss": 1.76497, "ppl": 5.841, "lr": 0.003, "grad": 0.1095, "tokens": 139258828800, "tok_s": 157770.3}
|
| 197 |
+
{"step": 132860, "epoch": 0.844, "loss": 1.73989, "ppl": 5.697, "lr": 0.003, "grad": 0.1555, "tokens": 139279795200, "tok_s": 157835.4}
|
| 198 |
+
{"step": 132880, "epoch": 0.844, "loss": 1.74324, "ppl": 5.716, "lr": 0.003, "grad": 0.11, "tokens": 139300761600, "tok_s": 158061.5}
|
| 199 |
+
{"step": 132900, "epoch": 0.844, "loss": 1.7311, "ppl": 5.647, "lr": 0.003, "grad": 0.1025, "tokens": 139321728000, "tok_s": 157447.3}
|
| 200 |
+
{"step": 132920, "epoch": 0.845, "loss": 1.73094, "ppl": 5.646, "lr": 0.003, "grad": 0.1042, "tokens": 139342694400, "tok_s": 157224.2}
|
| 201 |
+
{"step": 132940, "epoch": 0.845, "loss": 1.73889, "ppl": 5.691, "lr": 0.003, "grad": 0.1608, "tokens": 139363660800, "tok_s": 157202.8}
|
| 202 |
+
{"step": 132960, "epoch": 0.845, "loss": 1.76878, "ppl": 5.864, "lr": 0.003, "grad": 0.1568, "tokens": 139384627200, "tok_s": 157899.8}
|
| 203 |
+
{"step": 132980, "epoch": 0.845, "loss": 1.73773, "ppl": 5.684, "lr": 0.003, "grad": 0.0842, "tokens": 139405593600, "tok_s": 157754.9}
|
| 204 |
+
{"step": 133000, "epoch": 0.845, "loss": 1.76731, "ppl": 5.855, "lr": 0.003, "grad": 0.1676, "tokens": 139426560000, "tok_s": 156927.4}
|
| 205 |
+
{"step": 133000, "val_loss": 1.74935, "val_ppl": 5.751, "is_best": false}
|
| 206 |
+
{"step": 133020, "epoch": 0.845, "loss": 1.71589, "ppl": 5.562, "lr": 0.003, "grad": 0.116, "tokens": 139447526400, "tok_s": 155888.6}
|
| 207 |
+
{"step": 133040, "epoch": 0.845, "loss": 1.77139, "ppl": 5.879, "lr": 0.003, "grad": 0.0885, "tokens": 139468492800, "tok_s": 155911.8}
|
| 208 |
+
{"step": 133060, "epoch": 0.845, "loss": 1.71762, "ppl": 5.571, "lr": 0.003, "grad": 0.1101, "tokens": 139489459200, "tok_s": 156229.3}
|
| 209 |
+
{"step": 133080, "epoch": 0.846, "loss": 1.78086, "ppl": 5.935, "lr": 0.003, "grad": 0.1669, "tokens": 139510425600, "tok_s": 156493.0}
|
| 210 |
+
{"step": 133100, "epoch": 0.846, "loss": 1.75595, "ppl": 5.789, "lr": 0.003, "grad": 0.148, "tokens": 139531392000, "tok_s": 156006.4}
|
| 211 |
+
{"step": 133120, "epoch": 0.846, "loss": 1.77838, "ppl": 5.92, "lr": 0.003, "grad": 0.1719, "tokens": 139552358400, "tok_s": 156473.5}
|
| 212 |
+
{"step": 133140, "epoch": 0.846, "loss": 1.71512, "ppl": 5.557, "lr": 0.003, "grad": 0.1124, "tokens": 139573324800, "tok_s": 156182.7}
|
| 213 |
+
{"step": 133160, "epoch": 0.846, "loss": 1.75647, "ppl": 5.792, "lr": 0.003, "grad": 0.0921, "tokens": 139594291200, "tok_s": 156361.7}
|
| 214 |
+
{"step": 133180, "epoch": 0.846, "loss": 1.7681, "ppl": 5.86, "lr": 0.003, "grad": 0.0908, "tokens": 139615257600, "tok_s": 156635.9}
|
| 215 |
+
{"step": 133200, "epoch": 0.846, "loss": 1.79762, "ppl": 6.035, "lr": 0.003, "grad": 0.1339, "tokens": 139636224000, "tok_s": 156218.7}
|
| 216 |
+
{"step": 133220, "epoch": 0.846, "loss": 1.79144, "ppl": 5.998, "lr": 0.003, "grad": 0.1946, "tokens": 139657190400, "tok_s": 156295.0}
|
| 217 |
+
{"step": 133240, "epoch": 0.847, "loss": 1.76294, "ppl": 5.83, "lr": 0.003, "grad": 0.0721, "tokens": 139678156800, "tok_s": 156045.6}
|
| 218 |
+
{"step": 133260, "epoch": 0.847, "loss": 1.71992, "ppl": 5.584, "lr": 0.003, "grad": 0.0899, "tokens": 139699123200, "tok_s": 156229.7}
|
| 219 |
+
{"step": 133280, "epoch": 0.847, "loss": 1.80439, "ppl": 6.076, "lr": 0.003, "grad": 0.1273, "tokens": 139720089600, "tok_s": 156484.1}
|
| 220 |
+
{"step": 133300, "epoch": 0.847, "loss": 1.77137, "ppl": 5.879, "lr": 0.003, "grad": 0.1391, "tokens": 139741056000, "tok_s": 156351.8}
|
| 221 |
+
{"step": 133320, "epoch": 0.847, "loss": 1.71897, "ppl": 5.579, "lr": 0.003, "grad": 0.0903, "tokens": 139762022400, "tok_s": 156485.3}
|
| 222 |
+
{"step": 133340, "epoch": 0.847, "loss": 1.77755, "ppl": 5.915, "lr": 0.003, "grad": 0.1383, "tokens": 139782988800, "tok_s": 155781.1}
|
| 223 |
+
{"step": 133360, "epoch": 0.847, "loss": 1.7165, "ppl": 5.565, "lr": 0.003, "grad": 0.1146, "tokens": 139803955200, "tok_s": 156343.1}
|
| 224 |
+
{"step": 133380, "epoch": 0.847, "loss": 1.7643, "ppl": 5.837, "lr": 0.003, "grad": 0.1039, "tokens": 139824921600, "tok_s": 156333.8}
|
| 225 |
+
{"step": 133400, "epoch": 0.848, "loss": 1.64961, "ppl": 5.205, "lr": 0.003, "grad": 0.1178, "tokens": 139845888000, "tok_s": 157076.4}
|
| 226 |
+
{"step": 133420, "epoch": 0.848, "loss": 1.75802, "ppl": 5.801, "lr": 0.003, "grad": 0.1537, "tokens": 139866854400, "tok_s": 156602.3}
|
| 227 |
+
{"step": 133440, "epoch": 0.848, "loss": 1.75413, "ppl": 5.778, "lr": 0.003, "grad": 0.1562, "tokens": 139887820800, "tok_s": 156160.5}
|
| 228 |
+
{"step": 133460, "epoch": 0.848, "loss": 1.76284, "ppl": 5.829, "lr": 0.003, "grad": 0.1487, "tokens": 139908787200, "tok_s": 155201.2}
|
| 229 |
+
{"step": 133480, "epoch": 0.848, "loss": 1.919, "ppl": 6.814, "lr": 0.003, "grad": 0.1375, "tokens": 139929753600, "tok_s": 155166.0}
|
| 230 |
+
{"step": 133500, "epoch": 0.848, "loss": 1.79405, "ppl": 6.014, "lr": 0.003, "grad": 0.1435, "tokens": 139950720000, "tok_s": 155893.6}
|
| 231 |
+
{"step": 133520, "epoch": 0.848, "loss": 1.7448, "ppl": 5.725, "lr": 0.003, "grad": 0.1241, "tokens": 139971686400, "tok_s": 156360.8}
|
| 232 |
+
{"step": 133540, "epoch": 0.848, "loss": 1.73801, "ppl": 5.686, "lr": 0.003, "grad": 0.0601, "tokens": 139992652800, "tok_s": 156578.9}
|
| 233 |
+
{"step": 133560, "epoch": 0.849, "loss": 1.80901, "ppl": 6.104, "lr": 0.003, "grad": 0.1831, "tokens": 140013619200, "tok_s": 156186.8}
|
| 234 |
+
{"step": 133580, "epoch": 0.849, "loss": 1.71973, "ppl": 5.583, "lr": 0.003, "grad": 0.1288, "tokens": 140034585600, "tok_s": 155855.1}
|
| 235 |
+
{"step": 133600, "epoch": 0.849, "loss": 1.75342, "ppl": 5.774, "lr": 0.003, "grad": 0.1135, "tokens": 140055552000, "tok_s": 156038.1}
|
| 236 |
+
{"step": 133620, "epoch": 0.849, "loss": 1.76872, "ppl": 5.863, "lr": 0.003, "grad": 0.0985, "tokens": 140076518400, "tok_s": 156125.2}
|
| 237 |
+
{"step": 133640, "epoch": 0.849, "loss": 1.73844, "ppl": 5.688, "lr": 0.003, "grad": 0.1047, "tokens": 140097484800, "tok_s": 155992.3}
|
| 238 |
+
{"step": 133660, "epoch": 0.849, "loss": 1.71374, "ppl": 5.55, "lr": 0.003, "grad": 0.0896, "tokens": 140118451200, "tok_s": 155617.3}
|
| 239 |
+
{"step": 133680, "epoch": 0.849, "loss": 1.79869, "ppl": 6.042, "lr": 0.003, "grad": 0.2182, "tokens": 140139417600, "tok_s": 155720.1}
|
| 240 |
+
{"step": 133700, "epoch": 0.849, "loss": 1.71006, "ppl": 5.529, "lr": 0.003, "grad": 0.0957, "tokens": 140160384000, "tok_s": 155079.5}
|
| 241 |
+
{"step": 133720, "epoch": 0.85, "loss": 1.73949, "ppl": 5.694, "lr": 0.003, "grad": 0.0824, "tokens": 140181350400, "tok_s": 157168.5}
|
| 242 |
+
{"step": 133740, "epoch": 0.85, "loss": 1.76622, "ppl": 5.849, "lr": 0.003, "grad": 0.1322, "tokens": 140202316800, "tok_s": 157095.1}
|
| 243 |
+
{"step": 133760, "epoch": 0.85, "loss": 1.78084, "ppl": 5.935, "lr": 0.003, "grad": 0.1237, "tokens": 140223283200, "tok_s": 157285.2}
|
| 244 |
+
{"step": 133780, "epoch": 0.85, "loss": 1.73463, "ppl": 5.667, "lr": 0.003, "grad": 0.0851, "tokens": 140244249600, "tok_s": 156736.2}
|
| 245 |
+
{"step": 133800, "epoch": 0.85, "loss": 1.77028, "ppl": 5.873, "lr": 0.003, "grad": 0.0845, "tokens": 140265216000, "tok_s": 156983.0}
|
| 246 |
+
{"step": 133820, "epoch": 0.85, "loss": 1.70532, "ppl": 5.503, "lr": 0.003, "grad": 0.0818, "tokens": 140286182400, "tok_s": 157032.1}
|
| 247 |
+
{"step": 133840, "epoch": 0.85, "loss": 1.74943, "ppl": 5.751, "lr": 0.003, "grad": 0.1318, "tokens": 140307148800, "tok_s": 156413.0}
|
| 248 |
+
{"step": 133860, "epoch": 0.85, "loss": 1.75663, "ppl": 5.793, "lr": 0.003, "grad": 0.111, "tokens": 140328115200, "tok_s": 155821.1}
|
| 249 |
+
{"step": 133880, "epoch": 0.851, "loss": 1.66766, "ppl": 5.3, "lr": 0.003, "grad": 0.0819, "tokens": 140349081600, "tok_s": 156265.6}
|
| 250 |
+
{"step": 133900, "epoch": 0.851, "loss": 1.75285, "ppl": 5.771, "lr": 0.003, "grad": 0.0992, "tokens": 140370048000, "tok_s": 156555.9}
|
| 251 |
+
{"step": 133920, "epoch": 0.851, "loss": 1.73752, "ppl": 5.683, "lr": 0.003, "grad": 0.1252, "tokens": 140391014400, "tok_s": 156384.0}
|
| 252 |
+
{"step": 133940, "epoch": 0.851, "loss": 1.72633, "ppl": 5.62, "lr": 0.003, "grad": 0.1091, "tokens": 140411980800, "tok_s": 156431.6}
|
| 253 |
+
{"step": 133960, "epoch": 0.851, "loss": 1.69868, "ppl": 5.467, "lr": 0.003, "grad": 0.1141, "tokens": 140432947200, "tok_s": 155959.9}
|
| 254 |
+
{"step": 133980, "epoch": 0.851, "loss": 1.76599, "ppl": 5.847, "lr": 0.003, "grad": 0.129, "tokens": 140453913600, "tok_s": 155446.3}
|
| 255 |
+
{"step": 134000, "epoch": 0.851, "loss": 1.78261, "ppl": 5.945, "lr": 0.003, "grad": 0.1638, "tokens": 140474880000, "tok_s": 154600.0}
|
| 256 |
+
{"step": 134000, "val_loss": 1.75235, "val_ppl": 5.768, "is_best": false}
|
logs/log_135000.jsonl
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 134000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-07T09:11:07.088730"}
|
| 2 |
+
{"step": 134020, "epoch": 0.852, "loss": 1.73915, "ppl": 5.693, "lr": 0.003, "grad": 0.1314, "tokens": 140495846400, "tok_s": 158946.5}
|
| 3 |
+
{"step": 134040, "epoch": 0.852, "loss": 1.74058, "ppl": 5.701, "lr": 0.003, "grad": 0.1493, "tokens": 140516812800, "tok_s": 158671.7}
|
| 4 |
+
{"step": 134060, "epoch": 0.852, "loss": 1.71345, "ppl": 5.548, "lr": 0.003, "grad": 0.1534, "tokens": 140537779200, "tok_s": 158796.4}
|
| 5 |
+
{"step": 134080, "epoch": 0.852, "loss": 1.61197, "ppl": 5.013, "lr": 0.003, "grad": 0.1372, "tokens": 140558745600, "tok_s": 159108.0}
|
| 6 |
+
{"step": 134100, "epoch": 0.852, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.1787, "tokens": 140579712000, "tok_s": 158732.6}
|
| 7 |
+
{"step": 134120, "epoch": 0.852, "loss": 1.72855, "ppl": 5.632, "lr": 0.003, "grad": 0.0935, "tokens": 140600678400, "tok_s": 158605.2}
|
| 8 |
+
{"step": 134140, "epoch": 0.852, "loss": 1.74189, "ppl": 5.708, "lr": 0.003, "grad": 0.1236, "tokens": 140621644800, "tok_s": 159005.8}
|
| 9 |
+
{"step": 134160, "epoch": 0.852, "loss": 1.67525, "ppl": 5.34, "lr": 0.003, "grad": 0.1527, "tokens": 140642611200, "tok_s": 159084.3}
|
| 10 |
+
{"step": 134180, "epoch": 0.853, "loss": 1.62648, "ppl": 5.086, "lr": 0.003, "grad": 0.0906, "tokens": 140663577600, "tok_s": 158623.3}
|
| 11 |
+
{"step": 134200, "epoch": 0.853, "loss": 1.59189, "ppl": 4.913, "lr": 0.003, "grad": 0.1882, "tokens": 140684544000, "tok_s": 158785.6}
|
| 12 |
+
{"step": 134220, "epoch": 0.853, "loss": 1.77783, "ppl": 5.917, "lr": 0.003, "grad": 0.1395, "tokens": 140705510400, "tok_s": 158856.6}
|
| 13 |
+
{"step": 134240, "epoch": 0.853, "loss": 1.70045, "ppl": 5.476, "lr": 0.003, "grad": 0.1261, "tokens": 140726476800, "tok_s": 158458.1}
|
| 14 |
+
{"step": 134260, "epoch": 0.853, "loss": 1.75715, "ppl": 5.796, "lr": 0.003, "grad": 0.1034, "tokens": 140747443200, "tok_s": 158770.2}
|
| 15 |
+
{"step": 134280, "epoch": 0.853, "loss": 1.70857, "ppl": 5.521, "lr": 0.003, "grad": 0.1472, "tokens": 140768409600, "tok_s": 158818.1}
|
| 16 |
+
{"step": 134300, "epoch": 0.853, "loss": 1.75325, "ppl": 5.773, "lr": 0.003, "grad": 0.1138, "tokens": 140789376000, "tok_s": 159085.8}
|
| 17 |
+
{"step": 134320, "epoch": 0.853, "loss": 1.75828, "ppl": 5.802, "lr": 0.003, "grad": 0.0805, "tokens": 140810342400, "tok_s": 158803.0}
|
| 18 |
+
{"step": 134340, "epoch": 0.854, "loss": 1.7238, "ppl": 5.606, "lr": 0.003, "grad": 0.0596, "tokens": 140831308800, "tok_s": 159133.6}
|
| 19 |
+
{"step": 134360, "epoch": 0.854, "loss": 1.77065, "ppl": 5.875, "lr": 0.003, "grad": 0.0746, "tokens": 140852275200, "tok_s": 158990.9}
|
| 20 |
+
{"step": 134380, "epoch": 0.854, "loss": 1.68014, "ppl": 5.366, "lr": 0.003, "grad": 0.1349, "tokens": 140873241600, "tok_s": 158607.1}
|
| 21 |
+
{"step": 134400, "epoch": 0.854, "loss": 1.78004, "ppl": 5.93, "lr": 0.003, "grad": 0.1395, "tokens": 140894208000, "tok_s": 158637.2}
|
| 22 |
+
{"step": 134420, "epoch": 0.854, "loss": 1.75988, "ppl": 5.812, "lr": 0.003, "grad": 0.1203, "tokens": 140915174400, "tok_s": 158998.3}
|
| 23 |
+
{"step": 134440, "epoch": 0.854, "loss": 1.66996, "ppl": 5.312, "lr": 0.003, "grad": 0.0853, "tokens": 140936140800, "tok_s": 158874.5}
|
| 24 |
+
{"step": 134460, "epoch": 0.854, "loss": 1.80972, "ppl": 6.109, "lr": 0.003, "grad": 0.1433, "tokens": 140957107200, "tok_s": 158495.5}
|
| 25 |
+
{"step": 134480, "epoch": 0.854, "loss": 1.80559, "ppl": 6.084, "lr": 0.003, "grad": 0.1328, "tokens": 140978073600, "tok_s": 158634.0}
|
| 26 |
+
{"step": 134500, "epoch": 0.855, "loss": 1.89966, "ppl": 6.684, "lr": 0.003, "grad": 0.1402, "tokens": 140999040000, "tok_s": 158670.6}
|
| 27 |
+
{"step": 134520, "epoch": 0.855, "loss": 1.76167, "ppl": 5.822, "lr": 0.003, "grad": 0.143, "tokens": 141020006400, "tok_s": 158476.8}
|
| 28 |
+
{"step": 134540, "epoch": 0.855, "loss": 1.65701, "ppl": 5.244, "lr": 0.003, "grad": 0.0632, "tokens": 141040972800, "tok_s": 158695.2}
|
| 29 |
+
{"step": 134560, "epoch": 0.855, "loss": 1.67767, "ppl": 5.353, "lr": 0.003, "grad": 0.1067, "tokens": 141061939200, "tok_s": 158984.2}
|
| 30 |
+
{"step": 134580, "epoch": 0.855, "loss": 1.70119, "ppl": 5.48, "lr": 0.003, "grad": 0.1326, "tokens": 141082905600, "tok_s": 158918.2}
|
| 31 |
+
{"step": 134600, "epoch": 0.855, "loss": 1.63792, "ppl": 5.144, "lr": 0.003, "grad": 0.0625, "tokens": 141103872000, "tok_s": 158936.4}
|
| 32 |
+
{"step": 134620, "epoch": 0.855, "loss": 1.71296, "ppl": 5.545, "lr": 0.003, "grad": 0.1238, "tokens": 141124838400, "tok_s": 158931.3}
|
| 33 |
+
{"step": 134640, "epoch": 0.855, "loss": 1.66066, "ppl": 5.263, "lr": 0.003, "grad": 0.1076, "tokens": 141145804800, "tok_s": 158962.1}
|
| 34 |
+
{"step": 134660, "epoch": 0.856, "loss": 1.84109, "ppl": 6.303, "lr": 0.003, "grad": 0.0734, "tokens": 141166771200, "tok_s": 158544.4}
|
| 35 |
+
{"step": 134680, "epoch": 0.856, "loss": 1.76961, "ppl": 5.869, "lr": 0.003, "grad": 0.1689, "tokens": 141187737600, "tok_s": 158655.0}
|
| 36 |
+
{"step": 134700, "epoch": 0.856, "loss": 1.73919, "ppl": 5.693, "lr": 0.003, "grad": 0.177, "tokens": 141208704000, "tok_s": 158892.8}
|
| 37 |
+
{"step": 134720, "epoch": 0.856, "loss": 1.66473, "ppl": 5.284, "lr": 0.003, "grad": 0.0623, "tokens": 141229670400, "tok_s": 158647.1}
|
| 38 |
+
{"step": 134740, "epoch": 0.856, "loss": 1.69772, "ppl": 5.461, "lr": 0.003, "grad": 0.1711, "tokens": 141250636800, "tok_s": 158892.5}
|
| 39 |
+
{"step": 134760, "epoch": 0.856, "loss": 1.76702, "ppl": 5.853, "lr": 0.003, "grad": 0.17, "tokens": 141271603200, "tok_s": 158875.0}
|
| 40 |
+
{"step": 134780, "epoch": 0.856, "loss": 1.67563, "ppl": 5.342, "lr": 0.003, "grad": 0.1607, "tokens": 141292569600, "tok_s": 158463.9}
|
| 41 |
+
{"step": 134800, "epoch": 0.856, "loss": 1.69027, "ppl": 5.421, "lr": 0.003, "grad": 0.152, "tokens": 141313536000, "tok_s": 158878.9}
|
| 42 |
+
{"step": 134820, "epoch": 0.857, "loss": 1.74088, "ppl": 5.702, "lr": 0.003, "grad": 0.1549, "tokens": 141334502400, "tok_s": 158885.8}
|
| 43 |
+
{"step": 134840, "epoch": 0.857, "loss": 1.67324, "ppl": 5.329, "lr": 0.003, "grad": 0.1088, "tokens": 141355468800, "tok_s": 158892.8}
|
| 44 |
+
{"step": 134860, "epoch": 0.857, "loss": 1.7503, "ppl": 5.756, "lr": 0.003, "grad": 0.1535, "tokens": 141376435200, "tok_s": 158755.0}
|
| 45 |
+
{"step": 134880, "epoch": 0.857, "loss": 1.77764, "ppl": 5.916, "lr": 0.003, "grad": 0.1162, "tokens": 141397401600, "tok_s": 158783.2}
|
| 46 |
+
{"step": 134900, "epoch": 0.857, "loss": 1.44819, "ppl": 4.255, "lr": 0.003, "grad": 0.0835, "tokens": 141418368000, "tok_s": 158740.3}
|
| 47 |
+
{"step": 134920, "epoch": 0.857, "loss": 1.67507, "ppl": 5.339, "lr": 0.003, "grad": 0.1616, "tokens": 141439334400, "tok_s": 158822.9}
|
| 48 |
+
{"step": 134940, "epoch": 0.857, "loss": 1.68746, "ppl": 5.406, "lr": 0.003, "grad": 0.0619, "tokens": 141460300800, "tok_s": 158406.8}
|
| 49 |
+
{"step": 134960, "epoch": 0.857, "loss": 1.78197, "ppl": 5.942, "lr": 0.003, "grad": 0.1268, "tokens": 141481267200, "tok_s": 158734.0}
|
| 50 |
+
{"step": 134980, "epoch": 0.858, "loss": 1.73323, "ppl": 5.659, "lr": 0.003, "grad": 0.0818, "tokens": 141502233600, "tok_s": 158566.0}
|
| 51 |
+
{"step": 135000, "epoch": 0.858, "loss": 1.88906, "ppl": 6.613, "lr": 0.003, "grad": 0.131, "tokens": 141523200000, "tok_s": 158977.3}
|
| 52 |
+
{"step": 135000, "val_loss": 1.73029, "val_ppl": 5.642, "is_best": true}
|
logs/log_136000.jsonl
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 134000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-07T09:11:07.088730"}
|
| 2 |
+
{"step": 134020, "epoch": 0.852, "loss": 1.73915, "ppl": 5.693, "lr": 0.003, "grad": 0.1314, "tokens": 140495846400, "tok_s": 158946.5}
|
| 3 |
+
{"step": 134040, "epoch": 0.852, "loss": 1.74058, "ppl": 5.701, "lr": 0.003, "grad": 0.1493, "tokens": 140516812800, "tok_s": 158671.7}
|
| 4 |
+
{"step": 134060, "epoch": 0.852, "loss": 1.71345, "ppl": 5.548, "lr": 0.003, "grad": 0.1534, "tokens": 140537779200, "tok_s": 158796.4}
|
| 5 |
+
{"step": 134080, "epoch": 0.852, "loss": 1.61197, "ppl": 5.013, "lr": 0.003, "grad": 0.1372, "tokens": 140558745600, "tok_s": 159108.0}
|
| 6 |
+
{"step": 134100, "epoch": 0.852, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.1787, "tokens": 140579712000, "tok_s": 158732.6}
|
| 7 |
+
{"step": 134120, "epoch": 0.852, "loss": 1.72855, "ppl": 5.632, "lr": 0.003, "grad": 0.0935, "tokens": 140600678400, "tok_s": 158605.2}
|
| 8 |
+
{"step": 134140, "epoch": 0.852, "loss": 1.74189, "ppl": 5.708, "lr": 0.003, "grad": 0.1236, "tokens": 140621644800, "tok_s": 159005.8}
|
| 9 |
+
{"step": 134160, "epoch": 0.852, "loss": 1.67525, "ppl": 5.34, "lr": 0.003, "grad": 0.1527, "tokens": 140642611200, "tok_s": 159084.3}
|
| 10 |
+
{"step": 134180, "epoch": 0.853, "loss": 1.62648, "ppl": 5.086, "lr": 0.003, "grad": 0.0906, "tokens": 140663577600, "tok_s": 158623.3}
|
| 11 |
+
{"step": 134200, "epoch": 0.853, "loss": 1.59189, "ppl": 4.913, "lr": 0.003, "grad": 0.1882, "tokens": 140684544000, "tok_s": 158785.6}
|
| 12 |
+
{"step": 134220, "epoch": 0.853, "loss": 1.77783, "ppl": 5.917, "lr": 0.003, "grad": 0.1395, "tokens": 140705510400, "tok_s": 158856.6}
|
| 13 |
+
{"step": 134240, "epoch": 0.853, "loss": 1.70045, "ppl": 5.476, "lr": 0.003, "grad": 0.1261, "tokens": 140726476800, "tok_s": 158458.1}
|
| 14 |
+
{"step": 134260, "epoch": 0.853, "loss": 1.75715, "ppl": 5.796, "lr": 0.003, "grad": 0.1034, "tokens": 140747443200, "tok_s": 158770.2}
|
| 15 |
+
{"step": 134280, "epoch": 0.853, "loss": 1.70857, "ppl": 5.521, "lr": 0.003, "grad": 0.1472, "tokens": 140768409600, "tok_s": 158818.1}
|
| 16 |
+
{"step": 134300, "epoch": 0.853, "loss": 1.75325, "ppl": 5.773, "lr": 0.003, "grad": 0.1138, "tokens": 140789376000, "tok_s": 159085.8}
|
| 17 |
+
{"step": 134320, "epoch": 0.853, "loss": 1.75828, "ppl": 5.802, "lr": 0.003, "grad": 0.0805, "tokens": 140810342400, "tok_s": 158803.0}
|
| 18 |
+
{"step": 134340, "epoch": 0.854, "loss": 1.7238, "ppl": 5.606, "lr": 0.003, "grad": 0.0596, "tokens": 140831308800, "tok_s": 159133.6}
|
| 19 |
+
{"step": 134360, "epoch": 0.854, "loss": 1.77065, "ppl": 5.875, "lr": 0.003, "grad": 0.0746, "tokens": 140852275200, "tok_s": 158990.9}
|
| 20 |
+
{"step": 134380, "epoch": 0.854, "loss": 1.68014, "ppl": 5.366, "lr": 0.003, "grad": 0.1349, "tokens": 140873241600, "tok_s": 158607.1}
|
| 21 |
+
{"step": 134400, "epoch": 0.854, "loss": 1.78004, "ppl": 5.93, "lr": 0.003, "grad": 0.1395, "tokens": 140894208000, "tok_s": 158637.2}
|
| 22 |
+
{"step": 134420, "epoch": 0.854, "loss": 1.75988, "ppl": 5.812, "lr": 0.003, "grad": 0.1203, "tokens": 140915174400, "tok_s": 158998.3}
|
| 23 |
+
{"step": 134440, "epoch": 0.854, "loss": 1.66996, "ppl": 5.312, "lr": 0.003, "grad": 0.0853, "tokens": 140936140800, "tok_s": 158874.5}
|
| 24 |
+
{"step": 134460, "epoch": 0.854, "loss": 1.80972, "ppl": 6.109, "lr": 0.003, "grad": 0.1433, "tokens": 140957107200, "tok_s": 158495.5}
|
| 25 |
+
{"step": 134480, "epoch": 0.854, "loss": 1.80559, "ppl": 6.084, "lr": 0.003, "grad": 0.1328, "tokens": 140978073600, "tok_s": 158634.0}
|
| 26 |
+
{"step": 134500, "epoch": 0.855, "loss": 1.89966, "ppl": 6.684, "lr": 0.003, "grad": 0.1402, "tokens": 140999040000, "tok_s": 158670.6}
|
| 27 |
+
{"step": 134520, "epoch": 0.855, "loss": 1.76167, "ppl": 5.822, "lr": 0.003, "grad": 0.143, "tokens": 141020006400, "tok_s": 158476.8}
|
| 28 |
+
{"step": 134540, "epoch": 0.855, "loss": 1.65701, "ppl": 5.244, "lr": 0.003, "grad": 0.0632, "tokens": 141040972800, "tok_s": 158695.2}
|
| 29 |
+
{"step": 134560, "epoch": 0.855, "loss": 1.67767, "ppl": 5.353, "lr": 0.003, "grad": 0.1067, "tokens": 141061939200, "tok_s": 158984.2}
|
| 30 |
+
{"step": 134580, "epoch": 0.855, "loss": 1.70119, "ppl": 5.48, "lr": 0.003, "grad": 0.1326, "tokens": 141082905600, "tok_s": 158918.2}
|
| 31 |
+
{"step": 134600, "epoch": 0.855, "loss": 1.63792, "ppl": 5.144, "lr": 0.003, "grad": 0.0625, "tokens": 141103872000, "tok_s": 158936.4}
|
| 32 |
+
{"step": 134620, "epoch": 0.855, "loss": 1.71296, "ppl": 5.545, "lr": 0.003, "grad": 0.1238, "tokens": 141124838400, "tok_s": 158931.3}
|
| 33 |
+
{"step": 134640, "epoch": 0.855, "loss": 1.66066, "ppl": 5.263, "lr": 0.003, "grad": 0.1076, "tokens": 141145804800, "tok_s": 158962.1}
|
| 34 |
+
{"step": 134660, "epoch": 0.856, "loss": 1.84109, "ppl": 6.303, "lr": 0.003, "grad": 0.0734, "tokens": 141166771200, "tok_s": 158544.4}
|
| 35 |
+
{"step": 134680, "epoch": 0.856, "loss": 1.76961, "ppl": 5.869, "lr": 0.003, "grad": 0.1689, "tokens": 141187737600, "tok_s": 158655.0}
|
| 36 |
+
{"step": 134700, "epoch": 0.856, "loss": 1.73919, "ppl": 5.693, "lr": 0.003, "grad": 0.177, "tokens": 141208704000, "tok_s": 158892.8}
|
| 37 |
+
{"step": 134720, "epoch": 0.856, "loss": 1.66473, "ppl": 5.284, "lr": 0.003, "grad": 0.0623, "tokens": 141229670400, "tok_s": 158647.1}
|
| 38 |
+
{"step": 134740, "epoch": 0.856, "loss": 1.69772, "ppl": 5.461, "lr": 0.003, "grad": 0.1711, "tokens": 141250636800, "tok_s": 158892.5}
|
| 39 |
+
{"step": 134760, "epoch": 0.856, "loss": 1.76702, "ppl": 5.853, "lr": 0.003, "grad": 0.17, "tokens": 141271603200, "tok_s": 158875.0}
|
| 40 |
+
{"step": 134780, "epoch": 0.856, "loss": 1.67563, "ppl": 5.342, "lr": 0.003, "grad": 0.1607, "tokens": 141292569600, "tok_s": 158463.9}
|
| 41 |
+
{"step": 134800, "epoch": 0.856, "loss": 1.69027, "ppl": 5.421, "lr": 0.003, "grad": 0.152, "tokens": 141313536000, "tok_s": 158878.9}
|
| 42 |
+
{"step": 134820, "epoch": 0.857, "loss": 1.74088, "ppl": 5.702, "lr": 0.003, "grad": 0.1549, "tokens": 141334502400, "tok_s": 158885.8}
|
| 43 |
+
{"step": 134840, "epoch": 0.857, "loss": 1.67324, "ppl": 5.329, "lr": 0.003, "grad": 0.1088, "tokens": 141355468800, "tok_s": 158892.8}
|
| 44 |
+
{"step": 134860, "epoch": 0.857, "loss": 1.7503, "ppl": 5.756, "lr": 0.003, "grad": 0.1535, "tokens": 141376435200, "tok_s": 158755.0}
|
| 45 |
+
{"step": 134880, "epoch": 0.857, "loss": 1.77764, "ppl": 5.916, "lr": 0.003, "grad": 0.1162, "tokens": 141397401600, "tok_s": 158783.2}
|
| 46 |
+
{"step": 134900, "epoch": 0.857, "loss": 1.44819, "ppl": 4.255, "lr": 0.003, "grad": 0.0835, "tokens": 141418368000, "tok_s": 158740.3}
|
| 47 |
+
{"step": 134920, "epoch": 0.857, "loss": 1.67507, "ppl": 5.339, "lr": 0.003, "grad": 0.1616, "tokens": 141439334400, "tok_s": 158822.9}
|
| 48 |
+
{"step": 134940, "epoch": 0.857, "loss": 1.68746, "ppl": 5.406, "lr": 0.003, "grad": 0.0619, "tokens": 141460300800, "tok_s": 158406.8}
|
| 49 |
+
{"step": 134960, "epoch": 0.857, "loss": 1.78197, "ppl": 5.942, "lr": 0.003, "grad": 0.1268, "tokens": 141481267200, "tok_s": 158734.0}
|
| 50 |
+
{"step": 134980, "epoch": 0.858, "loss": 1.73323, "ppl": 5.659, "lr": 0.003, "grad": 0.0818, "tokens": 141502233600, "tok_s": 158566.0}
|
| 51 |
+
{"step": 135000, "epoch": 0.858, "loss": 1.88906, "ppl": 6.613, "lr": 0.003, "grad": 0.131, "tokens": 141523200000, "tok_s": 158977.3}
|
| 52 |
+
{"step": 135000, "val_loss": 1.73029, "val_ppl": 5.642, "is_best": true}
|
| 53 |
+
{"step": 135020, "epoch": 0.858, "loss": 1.73367, "ppl": 5.661, "lr": 0.003, "grad": 0.1441, "tokens": 141544166400, "tok_s": 159079.5}
|
| 54 |
+
{"step": 135040, "epoch": 0.858, "loss": 1.67592, "ppl": 5.344, "lr": 0.003, "grad": 0.1368, "tokens": 141565132800, "tok_s": 158914.3}
|
| 55 |
+
{"step": 135060, "epoch": 0.858, "loss": 1.77242, "ppl": 5.885, "lr": 0.003, "grad": 0.0903, "tokens": 141586099200, "tok_s": 158408.0}
|
| 56 |
+
{"step": 135080, "epoch": 0.858, "loss": 1.72404, "ppl": 5.607, "lr": 0.003, "grad": 0.1064, "tokens": 141607065600, "tok_s": 158531.0}
|
| 57 |
+
{"step": 135100, "epoch": 0.858, "loss": 1.59571, "ppl": 4.932, "lr": 0.003, "grad": 0.1797, "tokens": 141628032000, "tok_s": 158782.7}
|
| 58 |
+
{"step": 135120, "epoch": 0.859, "loss": 1.86924, "ppl": 6.483, "lr": 0.003, "grad": 0.0803, "tokens": 141648998400, "tok_s": 158989.4}
|
| 59 |
+
{"step": 135140, "epoch": 0.859, "loss": 1.76329, "ppl": 5.832, "lr": 0.003, "grad": 0.0811, "tokens": 141669964800, "tok_s": 158857.4}
|
| 60 |
+
{"step": 135160, "epoch": 0.859, "loss": 1.74841, "ppl": 5.745, "lr": 0.003, "grad": 0.1672, "tokens": 141690931200, "tok_s": 158263.2}
|
| 61 |
+
{"step": 135180, "epoch": 0.859, "loss": 1.79252, "ppl": 6.005, "lr": 0.003, "grad": 0.1816, "tokens": 141711897600, "tok_s": 158210.8}
|
| 62 |
+
{"step": 135200, "epoch": 0.859, "loss": 1.7063, "ppl": 5.509, "lr": 0.003, "grad": 0.1524, "tokens": 141732864000, "tok_s": 158643.8}
|
| 63 |
+
{"step": 135220, "epoch": 0.859, "loss": 1.7795, "ppl": 5.927, "lr": 0.003, "grad": 0.1494, "tokens": 141753830400, "tok_s": 158146.8}
|
| 64 |
+
{"step": 135240, "epoch": 0.859, "loss": 1.69001, "ppl": 5.42, "lr": 0.003, "grad": 0.1483, "tokens": 141774796800, "tok_s": 158465.0}
|
| 65 |
+
{"step": 135260, "epoch": 0.859, "loss": 1.71986, "ppl": 5.584, "lr": 0.003, "grad": 0.1368, "tokens": 141795763200, "tok_s": 158611.3}
|
| 66 |
+
{"step": 135280, "epoch": 0.86, "loss": 1.60245, "ppl": 4.965, "lr": 0.003, "grad": 0.1467, "tokens": 141816729600, "tok_s": 158646.7}
|
| 67 |
+
{"step": 135300, "epoch": 0.86, "loss": 1.80123, "ppl": 6.057, "lr": 0.003, "grad": 0.16, "tokens": 141837696000, "tok_s": 157959.8}
|
| 68 |
+
{"step": 135320, "epoch": 0.86, "loss": 1.74224, "ppl": 5.71, "lr": 0.003, "grad": 0.1249, "tokens": 141858662400, "tok_s": 158642.0}
|
| 69 |
+
{"step": 135340, "epoch": 0.86, "loss": 1.79372, "ppl": 6.012, "lr": 0.003, "grad": 0.1294, "tokens": 141879628800, "tok_s": 158457.2}
|
| 70 |
+
{"step": 135360, "epoch": 0.86, "loss": 1.73338, "ppl": 5.66, "lr": 0.003, "grad": 0.0985, "tokens": 141900595200, "tok_s": 158449.1}
|
| 71 |
+
{"step": 135380, "epoch": 0.86, "loss": 1.8432, "ppl": 6.317, "lr": 0.003, "grad": 0.1308, "tokens": 141921561600, "tok_s": 158213.4}
|
| 72 |
+
{"step": 135400, "epoch": 0.86, "loss": 1.81236, "ppl": 6.125, "lr": 0.003, "grad": 0.1074, "tokens": 141942528000, "tok_s": 158708.9}
|
| 73 |
+
{"step": 135420, "epoch": 0.86, "loss": 1.7933, "ppl": 6.009, "lr": 0.003, "grad": 0.1478, "tokens": 141963494400, "tok_s": 157697.2}
|
| 74 |
+
{"step": 135440, "epoch": 0.861, "loss": 1.73316, "ppl": 5.658, "lr": 0.003, "grad": 0.1342, "tokens": 141984460800, "tok_s": 158018.8}
|
| 75 |
+
{"step": 135460, "epoch": 0.861, "loss": 1.77488, "ppl": 5.9, "lr": 0.003, "grad": 0.1795, "tokens": 142005427200, "tok_s": 157889.1}
|
| 76 |
+
{"step": 135480, "epoch": 0.861, "loss": 1.82011, "ppl": 6.173, "lr": 0.003, "grad": 0.1056, "tokens": 142026393600, "tok_s": 158322.5}
|
| 77 |
+
{"step": 135500, "epoch": 0.861, "loss": 1.77863, "ppl": 5.922, "lr": 0.003, "grad": 0.1832, "tokens": 142047360000, "tok_s": 158042.2}
|
| 78 |
+
{"step": 135520, "epoch": 0.861, "loss": 1.78413, "ppl": 5.954, "lr": 0.003, "grad": 0.1536, "tokens": 142068326400, "tok_s": 158673.0}
|
| 79 |
+
{"step": 135540, "epoch": 0.861, "loss": 1.70772, "ppl": 5.516, "lr": 0.003, "grad": 0.0843, "tokens": 142089292800, "tok_s": 158958.3}
|
| 80 |
+
{"step": 135560, "epoch": 0.861, "loss": 1.78955, "ppl": 5.987, "lr": 0.003, "grad": 0.1293, "tokens": 142110259200, "tok_s": 158665.9}
|
| 81 |
+
{"step": 135580, "epoch": 0.861, "loss": 1.59136, "ppl": 4.91, "lr": 0.003, "grad": 0.0907, "tokens": 142131225600, "tok_s": 159040.3}
|
| 82 |
+
{"step": 135600, "epoch": 0.862, "loss": 1.76557, "ppl": 5.845, "lr": 0.003, "grad": 0.2092, "tokens": 142152192000, "tok_s": 158737.9}
|
| 83 |
+
{"step": 135620, "epoch": 0.862, "loss": 1.76489, "ppl": 5.841, "lr": 0.003, "grad": 0.1062, "tokens": 142173158400, "tok_s": 158712.5}
|
| 84 |
+
{"step": 135640, "epoch": 0.862, "loss": 1.73009, "ppl": 5.641, "lr": 0.003, "grad": 0.1506, "tokens": 142194124800, "tok_s": 158317.3}
|
| 85 |
+
{"step": 135660, "epoch": 0.862, "loss": 1.7837, "ppl": 5.952, "lr": 0.003, "grad": 0.1079, "tokens": 142215091200, "tok_s": 158571.7}
|
| 86 |
+
{"step": 135680, "epoch": 0.862, "loss": 1.75596, "ppl": 5.789, "lr": 0.003, "grad": 0.1572, "tokens": 142236057600, "tok_s": 159043.1}
|
| 87 |
+
{"step": 135700, "epoch": 0.862, "loss": 1.72901, "ppl": 5.635, "lr": 0.003, "grad": 0.0894, "tokens": 142257024000, "tok_s": 158197.8}
|
| 88 |
+
{"step": 135720, "epoch": 0.862, "loss": 1.70585, "ppl": 5.506, "lr": 0.003, "grad": 0.0847, "tokens": 142277990400, "tok_s": 158216.5}
|
| 89 |
+
{"step": 135740, "epoch": 0.862, "loss": 1.74374, "ppl": 5.719, "lr": 0.003, "grad": 0.1025, "tokens": 142298956800, "tok_s": 158516.9}
|
| 90 |
+
{"step": 135760, "epoch": 0.863, "loss": 1.63712, "ppl": 5.14, "lr": 0.003, "grad": 0.0958, "tokens": 142319923200, "tok_s": 158641.7}
|
| 91 |
+
{"step": 135780, "epoch": 0.863, "loss": 1.71328, "ppl": 5.547, "lr": 0.003, "grad": 0.1285, "tokens": 142340889600, "tok_s": 158410.9}
|
| 92 |
+
{"step": 135800, "epoch": 0.863, "loss": 1.73741, "ppl": 5.683, "lr": 0.003, "grad": 0.1426, "tokens": 142361856000, "tok_s": 157787.7}
|
| 93 |
+
{"step": 135820, "epoch": 0.863, "loss": 1.76231, "ppl": 5.826, "lr": 0.003, "grad": 0.091, "tokens": 142382822400, "tok_s": 158115.8}
|
| 94 |
+
{"step": 135840, "epoch": 0.863, "loss": 1.77817, "ppl": 5.919, "lr": 0.003, "grad": 0.0874, "tokens": 142403788800, "tok_s": 158443.3}
|
| 95 |
+
{"step": 135860, "epoch": 0.863, "loss": 1.78924, "ppl": 5.985, "lr": 0.003, "grad": 0.0722, "tokens": 142424755200, "tok_s": 158144.8}
|
| 96 |
+
{"step": 135880, "epoch": 0.863, "loss": 1.76683, "ppl": 5.852, "lr": 0.003, "grad": 0.111, "tokens": 142445721600, "tok_s": 158275.9}
|
| 97 |
+
{"step": 135900, "epoch": 0.863, "loss": 1.75377, "ppl": 5.776, "lr": 0.003, "grad": 0.1197, "tokens": 142466688000, "tok_s": 158584.0}
|
| 98 |
+
{"step": 135920, "epoch": 0.864, "loss": 1.77688, "ppl": 5.911, "lr": 0.003, "grad": 0.1725, "tokens": 142487654400, "tok_s": 158295.6}
|
| 99 |
+
{"step": 135940, "epoch": 0.864, "loss": 1.72879, "ppl": 5.634, "lr": 0.003, "grad": 0.1104, "tokens": 142508620800, "tok_s": 158561.0}
|
| 100 |
+
{"step": 135960, "epoch": 0.864, "loss": 1.74945, "ppl": 5.751, "lr": 0.003, "grad": 0.1739, "tokens": 142529587200, "tok_s": 158718.5}
|
| 101 |
+
{"step": 135980, "epoch": 0.864, "loss": 1.79746, "ppl": 6.034, "lr": 0.003, "grad": 0.1522, "tokens": 142550553600, "tok_s": 158185.0}
|
| 102 |
+
{"step": 136000, "epoch": 0.864, "loss": 1.72563, "ppl": 5.616, "lr": 0.003, "grad": 0.1532, "tokens": 142571520000, "tok_s": 158740.0}
|
| 103 |
+
{"step": 136000, "val_loss": 1.74202, "val_ppl": 5.709, "is_best": false}
|
logs/log_137000.jsonl
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 134000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-07T09:11:07.088730"}
|
| 2 |
+
{"step": 134020, "epoch": 0.852, "loss": 1.73915, "ppl": 5.693, "lr": 0.003, "grad": 0.1314, "tokens": 140495846400, "tok_s": 158946.5}
|
| 3 |
+
{"step": 134040, "epoch": 0.852, "loss": 1.74058, "ppl": 5.701, "lr": 0.003, "grad": 0.1493, "tokens": 140516812800, "tok_s": 158671.7}
|
| 4 |
+
{"step": 134060, "epoch": 0.852, "loss": 1.71345, "ppl": 5.548, "lr": 0.003, "grad": 0.1534, "tokens": 140537779200, "tok_s": 158796.4}
|
| 5 |
+
{"step": 134080, "epoch": 0.852, "loss": 1.61197, "ppl": 5.013, "lr": 0.003, "grad": 0.1372, "tokens": 140558745600, "tok_s": 159108.0}
|
| 6 |
+
{"step": 134100, "epoch": 0.852, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.1787, "tokens": 140579712000, "tok_s": 158732.6}
|
| 7 |
+
{"step": 134120, "epoch": 0.852, "loss": 1.72855, "ppl": 5.632, "lr": 0.003, "grad": 0.0935, "tokens": 140600678400, "tok_s": 158605.2}
|
| 8 |
+
{"step": 134140, "epoch": 0.852, "loss": 1.74189, "ppl": 5.708, "lr": 0.003, "grad": 0.1236, "tokens": 140621644800, "tok_s": 159005.8}
|
| 9 |
+
{"step": 134160, "epoch": 0.852, "loss": 1.67525, "ppl": 5.34, "lr": 0.003, "grad": 0.1527, "tokens": 140642611200, "tok_s": 159084.3}
|
| 10 |
+
{"step": 134180, "epoch": 0.853, "loss": 1.62648, "ppl": 5.086, "lr": 0.003, "grad": 0.0906, "tokens": 140663577600, "tok_s": 158623.3}
|
| 11 |
+
{"step": 134200, "epoch": 0.853, "loss": 1.59189, "ppl": 4.913, "lr": 0.003, "grad": 0.1882, "tokens": 140684544000, "tok_s": 158785.6}
|
| 12 |
+
{"step": 134220, "epoch": 0.853, "loss": 1.77783, "ppl": 5.917, "lr": 0.003, "grad": 0.1395, "tokens": 140705510400, "tok_s": 158856.6}
|
| 13 |
+
{"step": 134240, "epoch": 0.853, "loss": 1.70045, "ppl": 5.476, "lr": 0.003, "grad": 0.1261, "tokens": 140726476800, "tok_s": 158458.1}
|
| 14 |
+
{"step": 134260, "epoch": 0.853, "loss": 1.75715, "ppl": 5.796, "lr": 0.003, "grad": 0.1034, "tokens": 140747443200, "tok_s": 158770.2}
|
| 15 |
+
{"step": 134280, "epoch": 0.853, "loss": 1.70857, "ppl": 5.521, "lr": 0.003, "grad": 0.1472, "tokens": 140768409600, "tok_s": 158818.1}
|
| 16 |
+
{"step": 134300, "epoch": 0.853, "loss": 1.75325, "ppl": 5.773, "lr": 0.003, "grad": 0.1138, "tokens": 140789376000, "tok_s": 159085.8}
|
| 17 |
+
{"step": 134320, "epoch": 0.853, "loss": 1.75828, "ppl": 5.802, "lr": 0.003, "grad": 0.0805, "tokens": 140810342400, "tok_s": 158803.0}
|
| 18 |
+
{"step": 134340, "epoch": 0.854, "loss": 1.7238, "ppl": 5.606, "lr": 0.003, "grad": 0.0596, "tokens": 140831308800, "tok_s": 159133.6}
|
| 19 |
+
{"step": 134360, "epoch": 0.854, "loss": 1.77065, "ppl": 5.875, "lr": 0.003, "grad": 0.0746, "tokens": 140852275200, "tok_s": 158990.9}
|
| 20 |
+
{"step": 134380, "epoch": 0.854, "loss": 1.68014, "ppl": 5.366, "lr": 0.003, "grad": 0.1349, "tokens": 140873241600, "tok_s": 158607.1}
|
| 21 |
+
{"step": 134400, "epoch": 0.854, "loss": 1.78004, "ppl": 5.93, "lr": 0.003, "grad": 0.1395, "tokens": 140894208000, "tok_s": 158637.2}
|
| 22 |
+
{"step": 134420, "epoch": 0.854, "loss": 1.75988, "ppl": 5.812, "lr": 0.003, "grad": 0.1203, "tokens": 140915174400, "tok_s": 158998.3}
|
| 23 |
+
{"step": 134440, "epoch": 0.854, "loss": 1.66996, "ppl": 5.312, "lr": 0.003, "grad": 0.0853, "tokens": 140936140800, "tok_s": 158874.5}
|
| 24 |
+
{"step": 134460, "epoch": 0.854, "loss": 1.80972, "ppl": 6.109, "lr": 0.003, "grad": 0.1433, "tokens": 140957107200, "tok_s": 158495.5}
|
| 25 |
+
{"step": 134480, "epoch": 0.854, "loss": 1.80559, "ppl": 6.084, "lr": 0.003, "grad": 0.1328, "tokens": 140978073600, "tok_s": 158634.0}
|
| 26 |
+
{"step": 134500, "epoch": 0.855, "loss": 1.89966, "ppl": 6.684, "lr": 0.003, "grad": 0.1402, "tokens": 140999040000, "tok_s": 158670.6}
|
| 27 |
+
{"step": 134520, "epoch": 0.855, "loss": 1.76167, "ppl": 5.822, "lr": 0.003, "grad": 0.143, "tokens": 141020006400, "tok_s": 158476.8}
|
| 28 |
+
{"step": 134540, "epoch": 0.855, "loss": 1.65701, "ppl": 5.244, "lr": 0.003, "grad": 0.0632, "tokens": 141040972800, "tok_s": 158695.2}
|
| 29 |
+
{"step": 134560, "epoch": 0.855, "loss": 1.67767, "ppl": 5.353, "lr": 0.003, "grad": 0.1067, "tokens": 141061939200, "tok_s": 158984.2}
|
| 30 |
+
{"step": 134580, "epoch": 0.855, "loss": 1.70119, "ppl": 5.48, "lr": 0.003, "grad": 0.1326, "tokens": 141082905600, "tok_s": 158918.2}
|
| 31 |
+
{"step": 134600, "epoch": 0.855, "loss": 1.63792, "ppl": 5.144, "lr": 0.003, "grad": 0.0625, "tokens": 141103872000, "tok_s": 158936.4}
|
| 32 |
+
{"step": 134620, "epoch": 0.855, "loss": 1.71296, "ppl": 5.545, "lr": 0.003, "grad": 0.1238, "tokens": 141124838400, "tok_s": 158931.3}
|
| 33 |
+
{"step": 134640, "epoch": 0.855, "loss": 1.66066, "ppl": 5.263, "lr": 0.003, "grad": 0.1076, "tokens": 141145804800, "tok_s": 158962.1}
|
| 34 |
+
{"step": 134660, "epoch": 0.856, "loss": 1.84109, "ppl": 6.303, "lr": 0.003, "grad": 0.0734, "tokens": 141166771200, "tok_s": 158544.4}
|
| 35 |
+
{"step": 134680, "epoch": 0.856, "loss": 1.76961, "ppl": 5.869, "lr": 0.003, "grad": 0.1689, "tokens": 141187737600, "tok_s": 158655.0}
|
| 36 |
+
{"step": 134700, "epoch": 0.856, "loss": 1.73919, "ppl": 5.693, "lr": 0.003, "grad": 0.177, "tokens": 141208704000, "tok_s": 158892.8}
|
| 37 |
+
{"step": 134720, "epoch": 0.856, "loss": 1.66473, "ppl": 5.284, "lr": 0.003, "grad": 0.0623, "tokens": 141229670400, "tok_s": 158647.1}
|
| 38 |
+
{"step": 134740, "epoch": 0.856, "loss": 1.69772, "ppl": 5.461, "lr": 0.003, "grad": 0.1711, "tokens": 141250636800, "tok_s": 158892.5}
|
| 39 |
+
{"step": 134760, "epoch": 0.856, "loss": 1.76702, "ppl": 5.853, "lr": 0.003, "grad": 0.17, "tokens": 141271603200, "tok_s": 158875.0}
|
| 40 |
+
{"step": 134780, "epoch": 0.856, "loss": 1.67563, "ppl": 5.342, "lr": 0.003, "grad": 0.1607, "tokens": 141292569600, "tok_s": 158463.9}
|
| 41 |
+
{"step": 134800, "epoch": 0.856, "loss": 1.69027, "ppl": 5.421, "lr": 0.003, "grad": 0.152, "tokens": 141313536000, "tok_s": 158878.9}
|
| 42 |
+
{"step": 134820, "epoch": 0.857, "loss": 1.74088, "ppl": 5.702, "lr": 0.003, "grad": 0.1549, "tokens": 141334502400, "tok_s": 158885.8}
|
| 43 |
+
{"step": 134840, "epoch": 0.857, "loss": 1.67324, "ppl": 5.329, "lr": 0.003, "grad": 0.1088, "tokens": 141355468800, "tok_s": 158892.8}
|
| 44 |
+
{"step": 134860, "epoch": 0.857, "loss": 1.7503, "ppl": 5.756, "lr": 0.003, "grad": 0.1535, "tokens": 141376435200, "tok_s": 158755.0}
|
| 45 |
+
{"step": 134880, "epoch": 0.857, "loss": 1.77764, "ppl": 5.916, "lr": 0.003, "grad": 0.1162, "tokens": 141397401600, "tok_s": 158783.2}
|
| 46 |
+
{"step": 134900, "epoch": 0.857, "loss": 1.44819, "ppl": 4.255, "lr": 0.003, "grad": 0.0835, "tokens": 141418368000, "tok_s": 158740.3}
|
| 47 |
+
{"step": 134920, "epoch": 0.857, "loss": 1.67507, "ppl": 5.339, "lr": 0.003, "grad": 0.1616, "tokens": 141439334400, "tok_s": 158822.9}
|
| 48 |
+
{"step": 134940, "epoch": 0.857, "loss": 1.68746, "ppl": 5.406, "lr": 0.003, "grad": 0.0619, "tokens": 141460300800, "tok_s": 158406.8}
|
| 49 |
+
{"step": 134960, "epoch": 0.857, "loss": 1.78197, "ppl": 5.942, "lr": 0.003, "grad": 0.1268, "tokens": 141481267200, "tok_s": 158734.0}
|
| 50 |
+
{"step": 134980, "epoch": 0.858, "loss": 1.73323, "ppl": 5.659, "lr": 0.003, "grad": 0.0818, "tokens": 141502233600, "tok_s": 158566.0}
|
| 51 |
+
{"step": 135000, "epoch": 0.858, "loss": 1.88906, "ppl": 6.613, "lr": 0.003, "grad": 0.131, "tokens": 141523200000, "tok_s": 158977.3}
|
| 52 |
+
{"step": 135000, "val_loss": 1.73029, "val_ppl": 5.642, "is_best": true}
|
| 53 |
+
{"step": 135020, "epoch": 0.858, "loss": 1.73367, "ppl": 5.661, "lr": 0.003, "grad": 0.1441, "tokens": 141544166400, "tok_s": 159079.5}
|
| 54 |
+
{"step": 135040, "epoch": 0.858, "loss": 1.67592, "ppl": 5.344, "lr": 0.003, "grad": 0.1368, "tokens": 141565132800, "tok_s": 158914.3}
|
| 55 |
+
{"step": 135060, "epoch": 0.858, "loss": 1.77242, "ppl": 5.885, "lr": 0.003, "grad": 0.0903, "tokens": 141586099200, "tok_s": 158408.0}
|
| 56 |
+
{"step": 135080, "epoch": 0.858, "loss": 1.72404, "ppl": 5.607, "lr": 0.003, "grad": 0.1064, "tokens": 141607065600, "tok_s": 158531.0}
|
| 57 |
+
{"step": 135100, "epoch": 0.858, "loss": 1.59571, "ppl": 4.932, "lr": 0.003, "grad": 0.1797, "tokens": 141628032000, "tok_s": 158782.7}
|
| 58 |
+
{"step": 135120, "epoch": 0.859, "loss": 1.86924, "ppl": 6.483, "lr": 0.003, "grad": 0.0803, "tokens": 141648998400, "tok_s": 158989.4}
|
| 59 |
+
{"step": 135140, "epoch": 0.859, "loss": 1.76329, "ppl": 5.832, "lr": 0.003, "grad": 0.0811, "tokens": 141669964800, "tok_s": 158857.4}
|
| 60 |
+
{"step": 135160, "epoch": 0.859, "loss": 1.74841, "ppl": 5.745, "lr": 0.003, "grad": 0.1672, "tokens": 141690931200, "tok_s": 158263.2}
|
| 61 |
+
{"step": 135180, "epoch": 0.859, "loss": 1.79252, "ppl": 6.005, "lr": 0.003, "grad": 0.1816, "tokens": 141711897600, "tok_s": 158210.8}
|
| 62 |
+
{"step": 135200, "epoch": 0.859, "loss": 1.7063, "ppl": 5.509, "lr": 0.003, "grad": 0.1524, "tokens": 141732864000, "tok_s": 158643.8}
|
| 63 |
+
{"step": 135220, "epoch": 0.859, "loss": 1.7795, "ppl": 5.927, "lr": 0.003, "grad": 0.1494, "tokens": 141753830400, "tok_s": 158146.8}
|
| 64 |
+
{"step": 135240, "epoch": 0.859, "loss": 1.69001, "ppl": 5.42, "lr": 0.003, "grad": 0.1483, "tokens": 141774796800, "tok_s": 158465.0}
|
| 65 |
+
{"step": 135260, "epoch": 0.859, "loss": 1.71986, "ppl": 5.584, "lr": 0.003, "grad": 0.1368, "tokens": 141795763200, "tok_s": 158611.3}
|
| 66 |
+
{"step": 135280, "epoch": 0.86, "loss": 1.60245, "ppl": 4.965, "lr": 0.003, "grad": 0.1467, "tokens": 141816729600, "tok_s": 158646.7}
|
| 67 |
+
{"step": 135300, "epoch": 0.86, "loss": 1.80123, "ppl": 6.057, "lr": 0.003, "grad": 0.16, "tokens": 141837696000, "tok_s": 157959.8}
|
| 68 |
+
{"step": 135320, "epoch": 0.86, "loss": 1.74224, "ppl": 5.71, "lr": 0.003, "grad": 0.1249, "tokens": 141858662400, "tok_s": 158642.0}
|
| 69 |
+
{"step": 135340, "epoch": 0.86, "loss": 1.79372, "ppl": 6.012, "lr": 0.003, "grad": 0.1294, "tokens": 141879628800, "tok_s": 158457.2}
|
| 70 |
+
{"step": 135360, "epoch": 0.86, "loss": 1.73338, "ppl": 5.66, "lr": 0.003, "grad": 0.0985, "tokens": 141900595200, "tok_s": 158449.1}
|
| 71 |
+
{"step": 135380, "epoch": 0.86, "loss": 1.8432, "ppl": 6.317, "lr": 0.003, "grad": 0.1308, "tokens": 141921561600, "tok_s": 158213.4}
|
| 72 |
+
{"step": 135400, "epoch": 0.86, "loss": 1.81236, "ppl": 6.125, "lr": 0.003, "grad": 0.1074, "tokens": 141942528000, "tok_s": 158708.9}
|
| 73 |
+
{"step": 135420, "epoch": 0.86, "loss": 1.7933, "ppl": 6.009, "lr": 0.003, "grad": 0.1478, "tokens": 141963494400, "tok_s": 157697.2}
|
| 74 |
+
{"step": 135440, "epoch": 0.861, "loss": 1.73316, "ppl": 5.658, "lr": 0.003, "grad": 0.1342, "tokens": 141984460800, "tok_s": 158018.8}
|
| 75 |
+
{"step": 135460, "epoch": 0.861, "loss": 1.77488, "ppl": 5.9, "lr": 0.003, "grad": 0.1795, "tokens": 142005427200, "tok_s": 157889.1}
|
| 76 |
+
{"step": 135480, "epoch": 0.861, "loss": 1.82011, "ppl": 6.173, "lr": 0.003, "grad": 0.1056, "tokens": 142026393600, "tok_s": 158322.5}
|
| 77 |
+
{"step": 135500, "epoch": 0.861, "loss": 1.77863, "ppl": 5.922, "lr": 0.003, "grad": 0.1832, "tokens": 142047360000, "tok_s": 158042.2}
|
| 78 |
+
{"step": 135520, "epoch": 0.861, "loss": 1.78413, "ppl": 5.954, "lr": 0.003, "grad": 0.1536, "tokens": 142068326400, "tok_s": 158673.0}
|
| 79 |
+
{"step": 135540, "epoch": 0.861, "loss": 1.70772, "ppl": 5.516, "lr": 0.003, "grad": 0.0843, "tokens": 142089292800, "tok_s": 158958.3}
|
| 80 |
+
{"step": 135560, "epoch": 0.861, "loss": 1.78955, "ppl": 5.987, "lr": 0.003, "grad": 0.1293, "tokens": 142110259200, "tok_s": 158665.9}
|
| 81 |
+
{"step": 135580, "epoch": 0.861, "loss": 1.59136, "ppl": 4.91, "lr": 0.003, "grad": 0.0907, "tokens": 142131225600, "tok_s": 159040.3}
|
| 82 |
+
{"step": 135600, "epoch": 0.862, "loss": 1.76557, "ppl": 5.845, "lr": 0.003, "grad": 0.2092, "tokens": 142152192000, "tok_s": 158737.9}
|
| 83 |
+
{"step": 135620, "epoch": 0.862, "loss": 1.76489, "ppl": 5.841, "lr": 0.003, "grad": 0.1062, "tokens": 142173158400, "tok_s": 158712.5}
|
| 84 |
+
{"step": 135640, "epoch": 0.862, "loss": 1.73009, "ppl": 5.641, "lr": 0.003, "grad": 0.1506, "tokens": 142194124800, "tok_s": 158317.3}
|
| 85 |
+
{"step": 135660, "epoch": 0.862, "loss": 1.7837, "ppl": 5.952, "lr": 0.003, "grad": 0.1079, "tokens": 142215091200, "tok_s": 158571.7}
|
| 86 |
+
{"step": 135680, "epoch": 0.862, "loss": 1.75596, "ppl": 5.789, "lr": 0.003, "grad": 0.1572, "tokens": 142236057600, "tok_s": 159043.1}
|
| 87 |
+
{"step": 135700, "epoch": 0.862, "loss": 1.72901, "ppl": 5.635, "lr": 0.003, "grad": 0.0894, "tokens": 142257024000, "tok_s": 158197.8}
|
| 88 |
+
{"step": 135720, "epoch": 0.862, "loss": 1.70585, "ppl": 5.506, "lr": 0.003, "grad": 0.0847, "tokens": 142277990400, "tok_s": 158216.5}
|
| 89 |
+
{"step": 135740, "epoch": 0.862, "loss": 1.74374, "ppl": 5.719, "lr": 0.003, "grad": 0.1025, "tokens": 142298956800, "tok_s": 158516.9}
|
| 90 |
+
{"step": 135760, "epoch": 0.863, "loss": 1.63712, "ppl": 5.14, "lr": 0.003, "grad": 0.0958, "tokens": 142319923200, "tok_s": 158641.7}
|
| 91 |
+
{"step": 135780, "epoch": 0.863, "loss": 1.71328, "ppl": 5.547, "lr": 0.003, "grad": 0.1285, "tokens": 142340889600, "tok_s": 158410.9}
|
| 92 |
+
{"step": 135800, "epoch": 0.863, "loss": 1.73741, "ppl": 5.683, "lr": 0.003, "grad": 0.1426, "tokens": 142361856000, "tok_s": 157787.7}
|
| 93 |
+
{"step": 135820, "epoch": 0.863, "loss": 1.76231, "ppl": 5.826, "lr": 0.003, "grad": 0.091, "tokens": 142382822400, "tok_s": 158115.8}
|
| 94 |
+
{"step": 135840, "epoch": 0.863, "loss": 1.77817, "ppl": 5.919, "lr": 0.003, "grad": 0.0874, "tokens": 142403788800, "tok_s": 158443.3}
|
| 95 |
+
{"step": 135860, "epoch": 0.863, "loss": 1.78924, "ppl": 5.985, "lr": 0.003, "grad": 0.0722, "tokens": 142424755200, "tok_s": 158144.8}
|
| 96 |
+
{"step": 135880, "epoch": 0.863, "loss": 1.76683, "ppl": 5.852, "lr": 0.003, "grad": 0.111, "tokens": 142445721600, "tok_s": 158275.9}
|
| 97 |
+
{"step": 135900, "epoch": 0.863, "loss": 1.75377, "ppl": 5.776, "lr": 0.003, "grad": 0.1197, "tokens": 142466688000, "tok_s": 158584.0}
|
| 98 |
+
{"step": 135920, "epoch": 0.864, "loss": 1.77688, "ppl": 5.911, "lr": 0.003, "grad": 0.1725, "tokens": 142487654400, "tok_s": 158295.6}
|
| 99 |
+
{"step": 135940, "epoch": 0.864, "loss": 1.72879, "ppl": 5.634, "lr": 0.003, "grad": 0.1104, "tokens": 142508620800, "tok_s": 158561.0}
|
| 100 |
+
{"step": 135960, "epoch": 0.864, "loss": 1.74945, "ppl": 5.751, "lr": 0.003, "grad": 0.1739, "tokens": 142529587200, "tok_s": 158718.5}
|
| 101 |
+
{"step": 135980, "epoch": 0.864, "loss": 1.79746, "ppl": 6.034, "lr": 0.003, "grad": 0.1522, "tokens": 142550553600, "tok_s": 158185.0}
|
| 102 |
+
{"step": 136000, "epoch": 0.864, "loss": 1.72563, "ppl": 5.616, "lr": 0.003, "grad": 0.1532, "tokens": 142571520000, "tok_s": 158740.0}
|
| 103 |
+
{"step": 136000, "val_loss": 1.74202, "val_ppl": 5.709, "is_best": false}
|
| 104 |
+
{"step": 136020, "epoch": 0.864, "loss": 1.75843, "ppl": 5.803, "lr": 0.003, "grad": 0.1781, "tokens": 142592486400, "tok_s": 158663.3}
|
| 105 |
+
{"step": 136040, "epoch": 0.864, "loss": 1.74861, "ppl": 5.747, "lr": 0.003, "grad": 0.1462, "tokens": 142613452800, "tok_s": 158699.6}
|
| 106 |
+
{"step": 136060, "epoch": 0.864, "loss": 1.69362, "ppl": 5.439, "lr": 0.003, "grad": 0.135, "tokens": 142634419200, "tok_s": 158621.9}
|
| 107 |
+
{"step": 136080, "epoch": 0.865, "loss": 1.76345, "ppl": 5.833, "lr": 0.003, "grad": 0.0947, "tokens": 142655385600, "tok_s": 158364.8}
|
| 108 |
+
{"step": 136100, "epoch": 0.865, "loss": 1.75454, "ppl": 5.781, "lr": 0.003, "grad": 0.18, "tokens": 142676352000, "tok_s": 158264.2}
|
| 109 |
+
{"step": 136120, "epoch": 0.865, "loss": 1.82854, "ppl": 6.225, "lr": 0.003, "grad": 0.1676, "tokens": 142697318400, "tok_s": 157987.1}
|
| 110 |
+
{"step": 136140, "epoch": 0.865, "loss": 1.76845, "ppl": 5.862, "lr": 0.003, "grad": 0.0843, "tokens": 142718284800, "tok_s": 158118.1}
|
| 111 |
+
{"step": 136160, "epoch": 0.865, "loss": 1.72296, "ppl": 5.601, "lr": 0.003, "grad": 0.176, "tokens": 142739251200, "tok_s": 158442.1}
|
| 112 |
+
{"step": 136180, "epoch": 0.865, "loss": 1.74815, "ppl": 5.744, "lr": 0.003, "grad": 0.1405, "tokens": 142760217600, "tok_s": 158194.7}
|
| 113 |
+
{"step": 136200, "epoch": 0.865, "loss": 1.80326, "ppl": 6.069, "lr": 0.003, "grad": 0.0948, "tokens": 142781184000, "tok_s": 158224.5}
|
| 114 |
+
{"step": 136220, "epoch": 0.865, "loss": 1.70281, "ppl": 5.489, "lr": 0.003, "grad": 0.1113, "tokens": 142802150400, "tok_s": 158327.2}
|
| 115 |
+
{"step": 136240, "epoch": 0.866, "loss": 1.74675, "ppl": 5.736, "lr": 0.003, "grad": 0.1546, "tokens": 142823116800, "tok_s": 157984.6}
|
| 116 |
+
{"step": 136260, "epoch": 0.866, "loss": 1.66236, "ppl": 5.272, "lr": 0.003, "grad": 0.0813, "tokens": 142844083200, "tok_s": 158506.8}
|
| 117 |
+
{"step": 136280, "epoch": 0.866, "loss": 1.75967, "ppl": 5.81, "lr": 0.003, "grad": 0.0964, "tokens": 142865049600, "tok_s": 158299.0}
|
| 118 |
+
{"step": 136300, "epoch": 0.866, "loss": 1.78479, "ppl": 5.958, "lr": 0.003, "grad": 0.148, "tokens": 142886016000, "tok_s": 158591.0}
|
| 119 |
+
{"step": 136320, "epoch": 0.866, "loss": 1.6665, "ppl": 5.294, "lr": 0.003, "grad": 0.1016, "tokens": 142906982400, "tok_s": 157951.3}
|
| 120 |
+
{"step": 136340, "epoch": 0.866, "loss": 1.63116, "ppl": 5.11, "lr": 0.003, "grad": 0.1379, "tokens": 142927948800, "tok_s": 158554.8}
|
| 121 |
+
{"step": 136360, "epoch": 0.866, "loss": 1.75756, "ppl": 5.798, "lr": 0.003, "grad": 0.1514, "tokens": 142948915200, "tok_s": 158181.3}
|
| 122 |
+
{"step": 136380, "epoch": 0.867, "loss": 1.73176, "ppl": 5.651, "lr": 0.003, "grad": 0.1467, "tokens": 142969881600, "tok_s": 158870.2}
|
| 123 |
+
{"step": 136400, "epoch": 0.867, "loss": 1.64669, "ppl": 5.19, "lr": 0.003, "grad": 0.0968, "tokens": 142990848000, "tok_s": 158550.9}
|
| 124 |
+
{"step": 136420, "epoch": 0.867, "loss": 1.66401, "ppl": 5.28, "lr": 0.003, "grad": 0.1058, "tokens": 143011814400, "tok_s": 158557.8}
|
| 125 |
+
{"step": 136440, "epoch": 0.867, "loss": 1.85301, "ppl": 6.379, "lr": 0.003, "grad": 0.18, "tokens": 143032780800, "tok_s": 158534.3}
|
| 126 |
+
{"step": 136460, "epoch": 0.867, "loss": 1.64618, "ppl": 5.187, "lr": 0.003, "grad": 0.1353, "tokens": 143053747200, "tok_s": 158586.7}
|
| 127 |
+
{"step": 136480, "epoch": 0.867, "loss": 1.72332, "ppl": 5.603, "lr": 0.003, "grad": 0.0988, "tokens": 143074713600, "tok_s": 157946.5}
|
| 128 |
+
{"step": 136500, "epoch": 0.867, "loss": 1.69851, "ppl": 5.466, "lr": 0.003, "grad": 0.1401, "tokens": 143095680000, "tok_s": 158600.0}
|
| 129 |
+
{"step": 136520, "epoch": 0.867, "loss": 1.71151, "ppl": 5.537, "lr": 0.003, "grad": 0.0697, "tokens": 143116646400, "tok_s": 157957.1}
|
| 130 |
+
{"step": 136540, "epoch": 0.868, "loss": 1.71388, "ppl": 5.55, "lr": 0.003, "grad": 0.0634, "tokens": 143137612800, "tok_s": 158648.3}
|
| 131 |
+
{"step": 136560, "epoch": 0.868, "loss": 1.81126, "ppl": 6.118, "lr": 0.003, "grad": 0.1091, "tokens": 143158579200, "tok_s": 158493.0}
|
| 132 |
+
{"step": 136580, "epoch": 0.868, "loss": 1.74338, "ppl": 5.717, "lr": 0.003, "grad": 0.1446, "tokens": 143179545600, "tok_s": 158514.3}
|
| 133 |
+
{"step": 136600, "epoch": 0.868, "loss": 1.77354, "ppl": 5.892, "lr": 0.003, "grad": 0.1281, "tokens": 143200512000, "tok_s": 158319.2}
|
| 134 |
+
{"step": 136620, "epoch": 0.868, "loss": 1.73766, "ppl": 5.684, "lr": 0.003, "grad": 0.1713, "tokens": 143221478400, "tok_s": 158398.1}
|
| 135 |
+
{"step": 136640, "epoch": 0.868, "loss": 1.77489, "ppl": 5.9, "lr": 0.003, "grad": 0.1737, "tokens": 143242444800, "tok_s": 157759.6}
|
| 136 |
+
{"step": 136660, "epoch": 0.868, "loss": 1.64392, "ppl": 5.175, "lr": 0.003, "grad": 0.1054, "tokens": 143263411200, "tok_s": 158197.0}
|
| 137 |
+
{"step": 136680, "epoch": 0.868, "loss": 1.73884, "ppl": 5.691, "lr": 0.003, "grad": 0.1757, "tokens": 143284377600, "tok_s": 158386.2}
|
| 138 |
+
{"step": 136700, "epoch": 0.869, "loss": 1.69751, "ppl": 5.46, "lr": 0.003, "grad": 0.1424, "tokens": 143305344000, "tok_s": 158670.9}
|
| 139 |
+
{"step": 136720, "epoch": 0.869, "loss": 1.78563, "ppl": 5.963, "lr": 0.003, "grad": 0.175, "tokens": 143326310400, "tok_s": 158472.9}
|
| 140 |
+
{"step": 136740, "epoch": 0.869, "loss": 1.60733, "ppl": 4.989, "lr": 0.003, "grad": 0.0688, "tokens": 143347276800, "tok_s": 158249.7}
|
| 141 |
+
{"step": 136760, "epoch": 0.869, "loss": 1.77521, "ppl": 5.902, "lr": 0.003, "grad": 0.1283, "tokens": 143368243200, "tok_s": 158285.5}
|
| 142 |
+
{"step": 136780, "epoch": 0.869, "loss": 1.78194, "ppl": 5.941, "lr": 0.003, "grad": 0.1114, "tokens": 143389209600, "tok_s": 158617.4}
|
| 143 |
+
{"step": 136800, "epoch": 0.869, "loss": 1.75711, "ppl": 5.796, "lr": 0.003, "grad": 0.1507, "tokens": 143410176000, "tok_s": 158340.3}
|
| 144 |
+
{"step": 136820, "epoch": 0.869, "loss": 1.77529, "ppl": 5.902, "lr": 0.003, "grad": 0.1195, "tokens": 143431142400, "tok_s": 157685.2}
|
| 145 |
+
{"step": 136840, "epoch": 0.869, "loss": 1.77701, "ppl": 5.912, "lr": 0.003, "grad": 0.1705, "tokens": 143452108800, "tok_s": 158694.2}
|
| 146 |
+
{"step": 136860, "epoch": 0.87, "loss": 1.79988, "ppl": 6.049, "lr": 0.003, "grad": 0.1647, "tokens": 143473075200, "tok_s": 157892.0}
|
| 147 |
+
{"step": 136880, "epoch": 0.87, "loss": 1.71402, "ppl": 5.551, "lr": 0.003, "grad": 0.1141, "tokens": 143494041600, "tok_s": 158531.3}
|
| 148 |
+
{"step": 136900, "epoch": 0.87, "loss": 1.76826, "ppl": 5.861, "lr": 0.003, "grad": 0.1351, "tokens": 143515008000, "tok_s": 158442.3}
|
| 149 |
+
{"step": 136920, "epoch": 0.87, "loss": 1.76653, "ppl": 5.851, "lr": 0.003, "grad": 0.0923, "tokens": 143535974400, "tok_s": 158293.2}
|
| 150 |
+
{"step": 136940, "epoch": 0.87, "loss": 1.73223, "ppl": 5.653, "lr": 0.003, "grad": 0.0959, "tokens": 143556940800, "tok_s": 158431.9}
|
| 151 |
+
{"step": 136960, "epoch": 0.87, "loss": 1.78792, "ppl": 5.977, "lr": 0.003, "grad": 0.0756, "tokens": 143577907200, "tok_s": 158427.8}
|
| 152 |
+
{"step": 136980, "epoch": 0.87, "loss": 1.76046, "ppl": 5.815, "lr": 0.003, "grad": 0.1437, "tokens": 143598873600, "tok_s": 158254.7}
|
| 153 |
+
{"step": 137000, "epoch": 0.87, "loss": 1.76545, "ppl": 5.844, "lr": 0.003, "grad": 0.1232, "tokens": 143619840000, "tok_s": 158465.4}
|
| 154 |
+
{"step": 137000, "val_loss": 1.74862, "val_ppl": 5.747, "is_best": false}
|
logs/log_138000.jsonl
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 134000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-07T09:11:07.088730"}
|
| 2 |
+
{"step": 134020, "epoch": 0.852, "loss": 1.73915, "ppl": 5.693, "lr": 0.003, "grad": 0.1314, "tokens": 140495846400, "tok_s": 158946.5}
|
| 3 |
+
{"step": 134040, "epoch": 0.852, "loss": 1.74058, "ppl": 5.701, "lr": 0.003, "grad": 0.1493, "tokens": 140516812800, "tok_s": 158671.7}
|
| 4 |
+
{"step": 134060, "epoch": 0.852, "loss": 1.71345, "ppl": 5.548, "lr": 0.003, "grad": 0.1534, "tokens": 140537779200, "tok_s": 158796.4}
|
| 5 |
+
{"step": 134080, "epoch": 0.852, "loss": 1.61197, "ppl": 5.013, "lr": 0.003, "grad": 0.1372, "tokens": 140558745600, "tok_s": 159108.0}
|
| 6 |
+
{"step": 134100, "epoch": 0.852, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.1787, "tokens": 140579712000, "tok_s": 158732.6}
|
| 7 |
+
{"step": 134120, "epoch": 0.852, "loss": 1.72855, "ppl": 5.632, "lr": 0.003, "grad": 0.0935, "tokens": 140600678400, "tok_s": 158605.2}
|
| 8 |
+
{"step": 134140, "epoch": 0.852, "loss": 1.74189, "ppl": 5.708, "lr": 0.003, "grad": 0.1236, "tokens": 140621644800, "tok_s": 159005.8}
|
| 9 |
+
{"step": 134160, "epoch": 0.852, "loss": 1.67525, "ppl": 5.34, "lr": 0.003, "grad": 0.1527, "tokens": 140642611200, "tok_s": 159084.3}
|
| 10 |
+
{"step": 134180, "epoch": 0.853, "loss": 1.62648, "ppl": 5.086, "lr": 0.003, "grad": 0.0906, "tokens": 140663577600, "tok_s": 158623.3}
|
| 11 |
+
{"step": 134200, "epoch": 0.853, "loss": 1.59189, "ppl": 4.913, "lr": 0.003, "grad": 0.1882, "tokens": 140684544000, "tok_s": 158785.6}
|
| 12 |
+
{"step": 134220, "epoch": 0.853, "loss": 1.77783, "ppl": 5.917, "lr": 0.003, "grad": 0.1395, "tokens": 140705510400, "tok_s": 158856.6}
|
| 13 |
+
{"step": 134240, "epoch": 0.853, "loss": 1.70045, "ppl": 5.476, "lr": 0.003, "grad": 0.1261, "tokens": 140726476800, "tok_s": 158458.1}
|
| 14 |
+
{"step": 134260, "epoch": 0.853, "loss": 1.75715, "ppl": 5.796, "lr": 0.003, "grad": 0.1034, "tokens": 140747443200, "tok_s": 158770.2}
|
| 15 |
+
{"step": 134280, "epoch": 0.853, "loss": 1.70857, "ppl": 5.521, "lr": 0.003, "grad": 0.1472, "tokens": 140768409600, "tok_s": 158818.1}
|
| 16 |
+
{"step": 134300, "epoch": 0.853, "loss": 1.75325, "ppl": 5.773, "lr": 0.003, "grad": 0.1138, "tokens": 140789376000, "tok_s": 159085.8}
|
| 17 |
+
{"step": 134320, "epoch": 0.853, "loss": 1.75828, "ppl": 5.802, "lr": 0.003, "grad": 0.0805, "tokens": 140810342400, "tok_s": 158803.0}
|
| 18 |
+
{"step": 134340, "epoch": 0.854, "loss": 1.7238, "ppl": 5.606, "lr": 0.003, "grad": 0.0596, "tokens": 140831308800, "tok_s": 159133.6}
|
| 19 |
+
{"step": 134360, "epoch": 0.854, "loss": 1.77065, "ppl": 5.875, "lr": 0.003, "grad": 0.0746, "tokens": 140852275200, "tok_s": 158990.9}
|
| 20 |
+
{"step": 134380, "epoch": 0.854, "loss": 1.68014, "ppl": 5.366, "lr": 0.003, "grad": 0.1349, "tokens": 140873241600, "tok_s": 158607.1}
|
| 21 |
+
{"step": 134400, "epoch": 0.854, "loss": 1.78004, "ppl": 5.93, "lr": 0.003, "grad": 0.1395, "tokens": 140894208000, "tok_s": 158637.2}
|
| 22 |
+
{"step": 134420, "epoch": 0.854, "loss": 1.75988, "ppl": 5.812, "lr": 0.003, "grad": 0.1203, "tokens": 140915174400, "tok_s": 158998.3}
|
| 23 |
+
{"step": 134440, "epoch": 0.854, "loss": 1.66996, "ppl": 5.312, "lr": 0.003, "grad": 0.0853, "tokens": 140936140800, "tok_s": 158874.5}
|
| 24 |
+
{"step": 134460, "epoch": 0.854, "loss": 1.80972, "ppl": 6.109, "lr": 0.003, "grad": 0.1433, "tokens": 140957107200, "tok_s": 158495.5}
|
| 25 |
+
{"step": 134480, "epoch": 0.854, "loss": 1.80559, "ppl": 6.084, "lr": 0.003, "grad": 0.1328, "tokens": 140978073600, "tok_s": 158634.0}
|
| 26 |
+
{"step": 134500, "epoch": 0.855, "loss": 1.89966, "ppl": 6.684, "lr": 0.003, "grad": 0.1402, "tokens": 140999040000, "tok_s": 158670.6}
|
| 27 |
+
{"step": 134520, "epoch": 0.855, "loss": 1.76167, "ppl": 5.822, "lr": 0.003, "grad": 0.143, "tokens": 141020006400, "tok_s": 158476.8}
|
| 28 |
+
{"step": 134540, "epoch": 0.855, "loss": 1.65701, "ppl": 5.244, "lr": 0.003, "grad": 0.0632, "tokens": 141040972800, "tok_s": 158695.2}
|
| 29 |
+
{"step": 134560, "epoch": 0.855, "loss": 1.67767, "ppl": 5.353, "lr": 0.003, "grad": 0.1067, "tokens": 141061939200, "tok_s": 158984.2}
|
| 30 |
+
{"step": 134580, "epoch": 0.855, "loss": 1.70119, "ppl": 5.48, "lr": 0.003, "grad": 0.1326, "tokens": 141082905600, "tok_s": 158918.2}
|
| 31 |
+
{"step": 134600, "epoch": 0.855, "loss": 1.63792, "ppl": 5.144, "lr": 0.003, "grad": 0.0625, "tokens": 141103872000, "tok_s": 158936.4}
|
| 32 |
+
{"step": 134620, "epoch": 0.855, "loss": 1.71296, "ppl": 5.545, "lr": 0.003, "grad": 0.1238, "tokens": 141124838400, "tok_s": 158931.3}
|
| 33 |
+
{"step": 134640, "epoch": 0.855, "loss": 1.66066, "ppl": 5.263, "lr": 0.003, "grad": 0.1076, "tokens": 141145804800, "tok_s": 158962.1}
|
| 34 |
+
{"step": 134660, "epoch": 0.856, "loss": 1.84109, "ppl": 6.303, "lr": 0.003, "grad": 0.0734, "tokens": 141166771200, "tok_s": 158544.4}
|
| 35 |
+
{"step": 134680, "epoch": 0.856, "loss": 1.76961, "ppl": 5.869, "lr": 0.003, "grad": 0.1689, "tokens": 141187737600, "tok_s": 158655.0}
|
| 36 |
+
{"step": 134700, "epoch": 0.856, "loss": 1.73919, "ppl": 5.693, "lr": 0.003, "grad": 0.177, "tokens": 141208704000, "tok_s": 158892.8}
|
| 37 |
+
{"step": 134720, "epoch": 0.856, "loss": 1.66473, "ppl": 5.284, "lr": 0.003, "grad": 0.0623, "tokens": 141229670400, "tok_s": 158647.1}
|
| 38 |
+
{"step": 134740, "epoch": 0.856, "loss": 1.69772, "ppl": 5.461, "lr": 0.003, "grad": 0.1711, "tokens": 141250636800, "tok_s": 158892.5}
|
| 39 |
+
{"step": 134760, "epoch": 0.856, "loss": 1.76702, "ppl": 5.853, "lr": 0.003, "grad": 0.17, "tokens": 141271603200, "tok_s": 158875.0}
|
| 40 |
+
{"step": 134780, "epoch": 0.856, "loss": 1.67563, "ppl": 5.342, "lr": 0.003, "grad": 0.1607, "tokens": 141292569600, "tok_s": 158463.9}
|
| 41 |
+
{"step": 134800, "epoch": 0.856, "loss": 1.69027, "ppl": 5.421, "lr": 0.003, "grad": 0.152, "tokens": 141313536000, "tok_s": 158878.9}
|
| 42 |
+
{"step": 134820, "epoch": 0.857, "loss": 1.74088, "ppl": 5.702, "lr": 0.003, "grad": 0.1549, "tokens": 141334502400, "tok_s": 158885.8}
|
| 43 |
+
{"step": 134840, "epoch": 0.857, "loss": 1.67324, "ppl": 5.329, "lr": 0.003, "grad": 0.1088, "tokens": 141355468800, "tok_s": 158892.8}
|
| 44 |
+
{"step": 134860, "epoch": 0.857, "loss": 1.7503, "ppl": 5.756, "lr": 0.003, "grad": 0.1535, "tokens": 141376435200, "tok_s": 158755.0}
|
| 45 |
+
{"step": 134880, "epoch": 0.857, "loss": 1.77764, "ppl": 5.916, "lr": 0.003, "grad": 0.1162, "tokens": 141397401600, "tok_s": 158783.2}
|
| 46 |
+
{"step": 134900, "epoch": 0.857, "loss": 1.44819, "ppl": 4.255, "lr": 0.003, "grad": 0.0835, "tokens": 141418368000, "tok_s": 158740.3}
|
| 47 |
+
{"step": 134920, "epoch": 0.857, "loss": 1.67507, "ppl": 5.339, "lr": 0.003, "grad": 0.1616, "tokens": 141439334400, "tok_s": 158822.9}
|
| 48 |
+
{"step": 134940, "epoch": 0.857, "loss": 1.68746, "ppl": 5.406, "lr": 0.003, "grad": 0.0619, "tokens": 141460300800, "tok_s": 158406.8}
|
| 49 |
+
{"step": 134960, "epoch": 0.857, "loss": 1.78197, "ppl": 5.942, "lr": 0.003, "grad": 0.1268, "tokens": 141481267200, "tok_s": 158734.0}
|
| 50 |
+
{"step": 134980, "epoch": 0.858, "loss": 1.73323, "ppl": 5.659, "lr": 0.003, "grad": 0.0818, "tokens": 141502233600, "tok_s": 158566.0}
|
| 51 |
+
{"step": 135000, "epoch": 0.858, "loss": 1.88906, "ppl": 6.613, "lr": 0.003, "grad": 0.131, "tokens": 141523200000, "tok_s": 158977.3}
|
| 52 |
+
{"step": 135000, "val_loss": 1.73029, "val_ppl": 5.642, "is_best": true}
|
| 53 |
+
{"step": 135020, "epoch": 0.858, "loss": 1.73367, "ppl": 5.661, "lr": 0.003, "grad": 0.1441, "tokens": 141544166400, "tok_s": 159079.5}
|
| 54 |
+
{"step": 135040, "epoch": 0.858, "loss": 1.67592, "ppl": 5.344, "lr": 0.003, "grad": 0.1368, "tokens": 141565132800, "tok_s": 158914.3}
|
| 55 |
+
{"step": 135060, "epoch": 0.858, "loss": 1.77242, "ppl": 5.885, "lr": 0.003, "grad": 0.0903, "tokens": 141586099200, "tok_s": 158408.0}
|
| 56 |
+
{"step": 135080, "epoch": 0.858, "loss": 1.72404, "ppl": 5.607, "lr": 0.003, "grad": 0.1064, "tokens": 141607065600, "tok_s": 158531.0}
|
| 57 |
+
{"step": 135100, "epoch": 0.858, "loss": 1.59571, "ppl": 4.932, "lr": 0.003, "grad": 0.1797, "tokens": 141628032000, "tok_s": 158782.7}
|
| 58 |
+
{"step": 135120, "epoch": 0.859, "loss": 1.86924, "ppl": 6.483, "lr": 0.003, "grad": 0.0803, "tokens": 141648998400, "tok_s": 158989.4}
|
| 59 |
+
{"step": 135140, "epoch": 0.859, "loss": 1.76329, "ppl": 5.832, "lr": 0.003, "grad": 0.0811, "tokens": 141669964800, "tok_s": 158857.4}
|
| 60 |
+
{"step": 135160, "epoch": 0.859, "loss": 1.74841, "ppl": 5.745, "lr": 0.003, "grad": 0.1672, "tokens": 141690931200, "tok_s": 158263.2}
|
| 61 |
+
{"step": 135180, "epoch": 0.859, "loss": 1.79252, "ppl": 6.005, "lr": 0.003, "grad": 0.1816, "tokens": 141711897600, "tok_s": 158210.8}
|
| 62 |
+
{"step": 135200, "epoch": 0.859, "loss": 1.7063, "ppl": 5.509, "lr": 0.003, "grad": 0.1524, "tokens": 141732864000, "tok_s": 158643.8}
|
| 63 |
+
{"step": 135220, "epoch": 0.859, "loss": 1.7795, "ppl": 5.927, "lr": 0.003, "grad": 0.1494, "tokens": 141753830400, "tok_s": 158146.8}
|
| 64 |
+
{"step": 135240, "epoch": 0.859, "loss": 1.69001, "ppl": 5.42, "lr": 0.003, "grad": 0.1483, "tokens": 141774796800, "tok_s": 158465.0}
|
| 65 |
+
{"step": 135260, "epoch": 0.859, "loss": 1.71986, "ppl": 5.584, "lr": 0.003, "grad": 0.1368, "tokens": 141795763200, "tok_s": 158611.3}
|
| 66 |
+
{"step": 135280, "epoch": 0.86, "loss": 1.60245, "ppl": 4.965, "lr": 0.003, "grad": 0.1467, "tokens": 141816729600, "tok_s": 158646.7}
|
| 67 |
+
{"step": 135300, "epoch": 0.86, "loss": 1.80123, "ppl": 6.057, "lr": 0.003, "grad": 0.16, "tokens": 141837696000, "tok_s": 157959.8}
|
| 68 |
+
{"step": 135320, "epoch": 0.86, "loss": 1.74224, "ppl": 5.71, "lr": 0.003, "grad": 0.1249, "tokens": 141858662400, "tok_s": 158642.0}
|
| 69 |
+
{"step": 135340, "epoch": 0.86, "loss": 1.79372, "ppl": 6.012, "lr": 0.003, "grad": 0.1294, "tokens": 141879628800, "tok_s": 158457.2}
|
| 70 |
+
{"step": 135360, "epoch": 0.86, "loss": 1.73338, "ppl": 5.66, "lr": 0.003, "grad": 0.0985, "tokens": 141900595200, "tok_s": 158449.1}
|
| 71 |
+
{"step": 135380, "epoch": 0.86, "loss": 1.8432, "ppl": 6.317, "lr": 0.003, "grad": 0.1308, "tokens": 141921561600, "tok_s": 158213.4}
|
| 72 |
+
{"step": 135400, "epoch": 0.86, "loss": 1.81236, "ppl": 6.125, "lr": 0.003, "grad": 0.1074, "tokens": 141942528000, "tok_s": 158708.9}
|
| 73 |
+
{"step": 135420, "epoch": 0.86, "loss": 1.7933, "ppl": 6.009, "lr": 0.003, "grad": 0.1478, "tokens": 141963494400, "tok_s": 157697.2}
|
| 74 |
+
{"step": 135440, "epoch": 0.861, "loss": 1.73316, "ppl": 5.658, "lr": 0.003, "grad": 0.1342, "tokens": 141984460800, "tok_s": 158018.8}
|
| 75 |
+
{"step": 135460, "epoch": 0.861, "loss": 1.77488, "ppl": 5.9, "lr": 0.003, "grad": 0.1795, "tokens": 142005427200, "tok_s": 157889.1}
|
| 76 |
+
{"step": 135480, "epoch": 0.861, "loss": 1.82011, "ppl": 6.173, "lr": 0.003, "grad": 0.1056, "tokens": 142026393600, "tok_s": 158322.5}
|
| 77 |
+
{"step": 135500, "epoch": 0.861, "loss": 1.77863, "ppl": 5.922, "lr": 0.003, "grad": 0.1832, "tokens": 142047360000, "tok_s": 158042.2}
|
| 78 |
+
{"step": 135520, "epoch": 0.861, "loss": 1.78413, "ppl": 5.954, "lr": 0.003, "grad": 0.1536, "tokens": 142068326400, "tok_s": 158673.0}
|
| 79 |
+
{"step": 135540, "epoch": 0.861, "loss": 1.70772, "ppl": 5.516, "lr": 0.003, "grad": 0.0843, "tokens": 142089292800, "tok_s": 158958.3}
|
| 80 |
+
{"step": 135560, "epoch": 0.861, "loss": 1.78955, "ppl": 5.987, "lr": 0.003, "grad": 0.1293, "tokens": 142110259200, "tok_s": 158665.9}
|
| 81 |
+
{"step": 135580, "epoch": 0.861, "loss": 1.59136, "ppl": 4.91, "lr": 0.003, "grad": 0.0907, "tokens": 142131225600, "tok_s": 159040.3}
|
| 82 |
+
{"step": 135600, "epoch": 0.862, "loss": 1.76557, "ppl": 5.845, "lr": 0.003, "grad": 0.2092, "tokens": 142152192000, "tok_s": 158737.9}
|
| 83 |
+
{"step": 135620, "epoch": 0.862, "loss": 1.76489, "ppl": 5.841, "lr": 0.003, "grad": 0.1062, "tokens": 142173158400, "tok_s": 158712.5}
|
| 84 |
+
{"step": 135640, "epoch": 0.862, "loss": 1.73009, "ppl": 5.641, "lr": 0.003, "grad": 0.1506, "tokens": 142194124800, "tok_s": 158317.3}
|
| 85 |
+
{"step": 135660, "epoch": 0.862, "loss": 1.7837, "ppl": 5.952, "lr": 0.003, "grad": 0.1079, "tokens": 142215091200, "tok_s": 158571.7}
|
| 86 |
+
{"step": 135680, "epoch": 0.862, "loss": 1.75596, "ppl": 5.789, "lr": 0.003, "grad": 0.1572, "tokens": 142236057600, "tok_s": 159043.1}
|
| 87 |
+
{"step": 135700, "epoch": 0.862, "loss": 1.72901, "ppl": 5.635, "lr": 0.003, "grad": 0.0894, "tokens": 142257024000, "tok_s": 158197.8}
|
| 88 |
+
{"step": 135720, "epoch": 0.862, "loss": 1.70585, "ppl": 5.506, "lr": 0.003, "grad": 0.0847, "tokens": 142277990400, "tok_s": 158216.5}
|
| 89 |
+
{"step": 135740, "epoch": 0.862, "loss": 1.74374, "ppl": 5.719, "lr": 0.003, "grad": 0.1025, "tokens": 142298956800, "tok_s": 158516.9}
|
| 90 |
+
{"step": 135760, "epoch": 0.863, "loss": 1.63712, "ppl": 5.14, "lr": 0.003, "grad": 0.0958, "tokens": 142319923200, "tok_s": 158641.7}
|
| 91 |
+
{"step": 135780, "epoch": 0.863, "loss": 1.71328, "ppl": 5.547, "lr": 0.003, "grad": 0.1285, "tokens": 142340889600, "tok_s": 158410.9}
|
| 92 |
+
{"step": 135800, "epoch": 0.863, "loss": 1.73741, "ppl": 5.683, "lr": 0.003, "grad": 0.1426, "tokens": 142361856000, "tok_s": 157787.7}
|
| 93 |
+
{"step": 135820, "epoch": 0.863, "loss": 1.76231, "ppl": 5.826, "lr": 0.003, "grad": 0.091, "tokens": 142382822400, "tok_s": 158115.8}
|
| 94 |
+
{"step": 135840, "epoch": 0.863, "loss": 1.77817, "ppl": 5.919, "lr": 0.003, "grad": 0.0874, "tokens": 142403788800, "tok_s": 158443.3}
|
| 95 |
+
{"step": 135860, "epoch": 0.863, "loss": 1.78924, "ppl": 5.985, "lr": 0.003, "grad": 0.0722, "tokens": 142424755200, "tok_s": 158144.8}
|
| 96 |
+
{"step": 135880, "epoch": 0.863, "loss": 1.76683, "ppl": 5.852, "lr": 0.003, "grad": 0.111, "tokens": 142445721600, "tok_s": 158275.9}
|
| 97 |
+
{"step": 135900, "epoch": 0.863, "loss": 1.75377, "ppl": 5.776, "lr": 0.003, "grad": 0.1197, "tokens": 142466688000, "tok_s": 158584.0}
|
| 98 |
+
{"step": 135920, "epoch": 0.864, "loss": 1.77688, "ppl": 5.911, "lr": 0.003, "grad": 0.1725, "tokens": 142487654400, "tok_s": 158295.6}
|
| 99 |
+
{"step": 135940, "epoch": 0.864, "loss": 1.72879, "ppl": 5.634, "lr": 0.003, "grad": 0.1104, "tokens": 142508620800, "tok_s": 158561.0}
|
| 100 |
+
{"step": 135960, "epoch": 0.864, "loss": 1.74945, "ppl": 5.751, "lr": 0.003, "grad": 0.1739, "tokens": 142529587200, "tok_s": 158718.5}
|
| 101 |
+
{"step": 135980, "epoch": 0.864, "loss": 1.79746, "ppl": 6.034, "lr": 0.003, "grad": 0.1522, "tokens": 142550553600, "tok_s": 158185.0}
|
| 102 |
+
{"step": 136000, "epoch": 0.864, "loss": 1.72563, "ppl": 5.616, "lr": 0.003, "grad": 0.1532, "tokens": 142571520000, "tok_s": 158740.0}
|
| 103 |
+
{"step": 136000, "val_loss": 1.74202, "val_ppl": 5.709, "is_best": false}
|
| 104 |
+
{"step": 136020, "epoch": 0.864, "loss": 1.75843, "ppl": 5.803, "lr": 0.003, "grad": 0.1781, "tokens": 142592486400, "tok_s": 158663.3}
|
| 105 |
+
{"step": 136040, "epoch": 0.864, "loss": 1.74861, "ppl": 5.747, "lr": 0.003, "grad": 0.1462, "tokens": 142613452800, "tok_s": 158699.6}
|
| 106 |
+
{"step": 136060, "epoch": 0.864, "loss": 1.69362, "ppl": 5.439, "lr": 0.003, "grad": 0.135, "tokens": 142634419200, "tok_s": 158621.9}
|
| 107 |
+
{"step": 136080, "epoch": 0.865, "loss": 1.76345, "ppl": 5.833, "lr": 0.003, "grad": 0.0947, "tokens": 142655385600, "tok_s": 158364.8}
|
| 108 |
+
{"step": 136100, "epoch": 0.865, "loss": 1.75454, "ppl": 5.781, "lr": 0.003, "grad": 0.18, "tokens": 142676352000, "tok_s": 158264.2}
|
| 109 |
+
{"step": 136120, "epoch": 0.865, "loss": 1.82854, "ppl": 6.225, "lr": 0.003, "grad": 0.1676, "tokens": 142697318400, "tok_s": 157987.1}
|
| 110 |
+
{"step": 136140, "epoch": 0.865, "loss": 1.76845, "ppl": 5.862, "lr": 0.003, "grad": 0.0843, "tokens": 142718284800, "tok_s": 158118.1}
|
| 111 |
+
{"step": 136160, "epoch": 0.865, "loss": 1.72296, "ppl": 5.601, "lr": 0.003, "grad": 0.176, "tokens": 142739251200, "tok_s": 158442.1}
|
| 112 |
+
{"step": 136180, "epoch": 0.865, "loss": 1.74815, "ppl": 5.744, "lr": 0.003, "grad": 0.1405, "tokens": 142760217600, "tok_s": 158194.7}
|
| 113 |
+
{"step": 136200, "epoch": 0.865, "loss": 1.80326, "ppl": 6.069, "lr": 0.003, "grad": 0.0948, "tokens": 142781184000, "tok_s": 158224.5}
|
| 114 |
+
{"step": 136220, "epoch": 0.865, "loss": 1.70281, "ppl": 5.489, "lr": 0.003, "grad": 0.1113, "tokens": 142802150400, "tok_s": 158327.2}
|
| 115 |
+
{"step": 136240, "epoch": 0.866, "loss": 1.74675, "ppl": 5.736, "lr": 0.003, "grad": 0.1546, "tokens": 142823116800, "tok_s": 157984.6}
|
| 116 |
+
{"step": 136260, "epoch": 0.866, "loss": 1.66236, "ppl": 5.272, "lr": 0.003, "grad": 0.0813, "tokens": 142844083200, "tok_s": 158506.8}
|
| 117 |
+
{"step": 136280, "epoch": 0.866, "loss": 1.75967, "ppl": 5.81, "lr": 0.003, "grad": 0.0964, "tokens": 142865049600, "tok_s": 158299.0}
|
| 118 |
+
{"step": 136300, "epoch": 0.866, "loss": 1.78479, "ppl": 5.958, "lr": 0.003, "grad": 0.148, "tokens": 142886016000, "tok_s": 158591.0}
|
| 119 |
+
{"step": 136320, "epoch": 0.866, "loss": 1.6665, "ppl": 5.294, "lr": 0.003, "grad": 0.1016, "tokens": 142906982400, "tok_s": 157951.3}
|
| 120 |
+
{"step": 136340, "epoch": 0.866, "loss": 1.63116, "ppl": 5.11, "lr": 0.003, "grad": 0.1379, "tokens": 142927948800, "tok_s": 158554.8}
|
| 121 |
+
{"step": 136360, "epoch": 0.866, "loss": 1.75756, "ppl": 5.798, "lr": 0.003, "grad": 0.1514, "tokens": 142948915200, "tok_s": 158181.3}
|
| 122 |
+
{"step": 136380, "epoch": 0.867, "loss": 1.73176, "ppl": 5.651, "lr": 0.003, "grad": 0.1467, "tokens": 142969881600, "tok_s": 158870.2}
|
| 123 |
+
{"step": 136400, "epoch": 0.867, "loss": 1.64669, "ppl": 5.19, "lr": 0.003, "grad": 0.0968, "tokens": 142990848000, "tok_s": 158550.9}
|
| 124 |
+
{"step": 136420, "epoch": 0.867, "loss": 1.66401, "ppl": 5.28, "lr": 0.003, "grad": 0.1058, "tokens": 143011814400, "tok_s": 158557.8}
|
| 125 |
+
{"step": 136440, "epoch": 0.867, "loss": 1.85301, "ppl": 6.379, "lr": 0.003, "grad": 0.18, "tokens": 143032780800, "tok_s": 158534.3}
|
| 126 |
+
{"step": 136460, "epoch": 0.867, "loss": 1.64618, "ppl": 5.187, "lr": 0.003, "grad": 0.1353, "tokens": 143053747200, "tok_s": 158586.7}
|
| 127 |
+
{"step": 136480, "epoch": 0.867, "loss": 1.72332, "ppl": 5.603, "lr": 0.003, "grad": 0.0988, "tokens": 143074713600, "tok_s": 157946.5}
|
| 128 |
+
{"step": 136500, "epoch": 0.867, "loss": 1.69851, "ppl": 5.466, "lr": 0.003, "grad": 0.1401, "tokens": 143095680000, "tok_s": 158600.0}
|
| 129 |
+
{"step": 136520, "epoch": 0.867, "loss": 1.71151, "ppl": 5.537, "lr": 0.003, "grad": 0.0697, "tokens": 143116646400, "tok_s": 157957.1}
|
| 130 |
+
{"step": 136540, "epoch": 0.868, "loss": 1.71388, "ppl": 5.55, "lr": 0.003, "grad": 0.0634, "tokens": 143137612800, "tok_s": 158648.3}
|
| 131 |
+
{"step": 136560, "epoch": 0.868, "loss": 1.81126, "ppl": 6.118, "lr": 0.003, "grad": 0.1091, "tokens": 143158579200, "tok_s": 158493.0}
|
| 132 |
+
{"step": 136580, "epoch": 0.868, "loss": 1.74338, "ppl": 5.717, "lr": 0.003, "grad": 0.1446, "tokens": 143179545600, "tok_s": 158514.3}
|
| 133 |
+
{"step": 136600, "epoch": 0.868, "loss": 1.77354, "ppl": 5.892, "lr": 0.003, "grad": 0.1281, "tokens": 143200512000, "tok_s": 158319.2}
|
| 134 |
+
{"step": 136620, "epoch": 0.868, "loss": 1.73766, "ppl": 5.684, "lr": 0.003, "grad": 0.1713, "tokens": 143221478400, "tok_s": 158398.1}
|
| 135 |
+
{"step": 136640, "epoch": 0.868, "loss": 1.77489, "ppl": 5.9, "lr": 0.003, "grad": 0.1737, "tokens": 143242444800, "tok_s": 157759.6}
|
| 136 |
+
{"step": 136660, "epoch": 0.868, "loss": 1.64392, "ppl": 5.175, "lr": 0.003, "grad": 0.1054, "tokens": 143263411200, "tok_s": 158197.0}
|
| 137 |
+
{"step": 136680, "epoch": 0.868, "loss": 1.73884, "ppl": 5.691, "lr": 0.003, "grad": 0.1757, "tokens": 143284377600, "tok_s": 158386.2}
|
| 138 |
+
{"step": 136700, "epoch": 0.869, "loss": 1.69751, "ppl": 5.46, "lr": 0.003, "grad": 0.1424, "tokens": 143305344000, "tok_s": 158670.9}
|
| 139 |
+
{"step": 136720, "epoch": 0.869, "loss": 1.78563, "ppl": 5.963, "lr": 0.003, "grad": 0.175, "tokens": 143326310400, "tok_s": 158472.9}
|
| 140 |
+
{"step": 136740, "epoch": 0.869, "loss": 1.60733, "ppl": 4.989, "lr": 0.003, "grad": 0.0688, "tokens": 143347276800, "tok_s": 158249.7}
|
| 141 |
+
{"step": 136760, "epoch": 0.869, "loss": 1.77521, "ppl": 5.902, "lr": 0.003, "grad": 0.1283, "tokens": 143368243200, "tok_s": 158285.5}
|
| 142 |
+
{"step": 136780, "epoch": 0.869, "loss": 1.78194, "ppl": 5.941, "lr": 0.003, "grad": 0.1114, "tokens": 143389209600, "tok_s": 158617.4}
|
| 143 |
+
{"step": 136800, "epoch": 0.869, "loss": 1.75711, "ppl": 5.796, "lr": 0.003, "grad": 0.1507, "tokens": 143410176000, "tok_s": 158340.3}
|
| 144 |
+
{"step": 136820, "epoch": 0.869, "loss": 1.77529, "ppl": 5.902, "lr": 0.003, "grad": 0.1195, "tokens": 143431142400, "tok_s": 157685.2}
|
| 145 |
+
{"step": 136840, "epoch": 0.869, "loss": 1.77701, "ppl": 5.912, "lr": 0.003, "grad": 0.1705, "tokens": 143452108800, "tok_s": 158694.2}
|
| 146 |
+
{"step": 136860, "epoch": 0.87, "loss": 1.79988, "ppl": 6.049, "lr": 0.003, "grad": 0.1647, "tokens": 143473075200, "tok_s": 157892.0}
|
| 147 |
+
{"step": 136880, "epoch": 0.87, "loss": 1.71402, "ppl": 5.551, "lr": 0.003, "grad": 0.1141, "tokens": 143494041600, "tok_s": 158531.3}
|
| 148 |
+
{"step": 136900, "epoch": 0.87, "loss": 1.76826, "ppl": 5.861, "lr": 0.003, "grad": 0.1351, "tokens": 143515008000, "tok_s": 158442.3}
|
| 149 |
+
{"step": 136920, "epoch": 0.87, "loss": 1.76653, "ppl": 5.851, "lr": 0.003, "grad": 0.0923, "tokens": 143535974400, "tok_s": 158293.2}
|
| 150 |
+
{"step": 136940, "epoch": 0.87, "loss": 1.73223, "ppl": 5.653, "lr": 0.003, "grad": 0.0959, "tokens": 143556940800, "tok_s": 158431.9}
|
| 151 |
+
{"step": 136960, "epoch": 0.87, "loss": 1.78792, "ppl": 5.977, "lr": 0.003, "grad": 0.0756, "tokens": 143577907200, "tok_s": 158427.8}
|
| 152 |
+
{"step": 136980, "epoch": 0.87, "loss": 1.76046, "ppl": 5.815, "lr": 0.003, "grad": 0.1437, "tokens": 143598873600, "tok_s": 158254.7}
|
| 153 |
+
{"step": 137000, "epoch": 0.87, "loss": 1.76545, "ppl": 5.844, "lr": 0.003, "grad": 0.1232, "tokens": 143619840000, "tok_s": 158465.4}
|
| 154 |
+
{"step": 137000, "val_loss": 1.74862, "val_ppl": 5.747, "is_best": false}
|
| 155 |
+
{"step": 137020, "epoch": 0.871, "loss": 1.69586, "ppl": 5.451, "lr": 0.003, "grad": 0.1336, "tokens": 143640806400, "tok_s": 157715.9}
|
| 156 |
+
{"step": 137040, "epoch": 0.871, "loss": 1.7544, "ppl": 5.78, "lr": 0.003, "grad": 0.155, "tokens": 143661772800, "tok_s": 158466.7}
|
| 157 |
+
{"step": 137060, "epoch": 0.871, "loss": 1.73644, "ppl": 5.677, "lr": 0.003, "grad": 0.1435, "tokens": 143682739200, "tok_s": 158272.2}
|
| 158 |
+
{"step": 137080, "epoch": 0.871, "loss": 1.77659, "ppl": 5.91, "lr": 0.003, "grad": 0.1744, "tokens": 143703705600, "tok_s": 158504.4}
|
| 159 |
+
{"step": 137100, "epoch": 0.871, "loss": 1.77339, "ppl": 5.891, "lr": 0.003, "grad": 0.0996, "tokens": 143724672000, "tok_s": 158377.3}
|
| 160 |
+
{"step": 137120, "epoch": 0.871, "loss": 1.7388, "ppl": 5.69, "lr": 0.003, "grad": 0.1476, "tokens": 143745638400, "tok_s": 158340.1}
|
| 161 |
+
{"step": 137140, "epoch": 0.871, "loss": 1.72498, "ppl": 5.612, "lr": 0.003, "grad": 0.1553, "tokens": 143766604800, "tok_s": 158073.9}
|
| 162 |
+
{"step": 137160, "epoch": 0.871, "loss": 1.7359, "ppl": 5.674, "lr": 0.003, "grad": 0.2135, "tokens": 143787571200, "tok_s": 158249.9}
|
| 163 |
+
{"step": 137180, "epoch": 0.872, "loss": 1.68078, "ppl": 5.37, "lr": 0.003, "grad": 0.1378, "tokens": 143808537600, "tok_s": 158428.9}
|
| 164 |
+
{"step": 137200, "epoch": 0.872, "loss": 1.74298, "ppl": 5.714, "lr": 0.003, "grad": 0.1114, "tokens": 143829504000, "tok_s": 157890.9}
|
| 165 |
+
{"step": 137220, "epoch": 0.872, "loss": 1.72794, "ppl": 5.629, "lr": 0.003, "grad": 0.1224, "tokens": 143850470400, "tok_s": 158133.6}
|
| 166 |
+
{"step": 137240, "epoch": 0.872, "loss": 1.73312, "ppl": 5.658, "lr": 0.003, "grad": 0.1522, "tokens": 143871436800, "tok_s": 157950.4}
|
| 167 |
+
{"step": 137260, "epoch": 0.872, "loss": 1.74592, "ppl": 5.731, "lr": 0.003, "grad": 0.15, "tokens": 143892403200, "tok_s": 157869.6}
|
| 168 |
+
{"step": 137280, "epoch": 0.872, "loss": 1.76882, "ppl": 5.864, "lr": 0.003, "grad": 0.1283, "tokens": 143913369600, "tok_s": 157129.6}
|
| 169 |
+
{"step": 137300, "epoch": 0.872, "loss": 1.8218, "ppl": 6.183, "lr": 0.003, "grad": 0.1212, "tokens": 143934336000, "tok_s": 158232.5}
|
| 170 |
+
{"step": 137320, "epoch": 0.872, "loss": 1.72289, "ppl": 5.601, "lr": 0.003, "grad": 0.1539, "tokens": 143955302400, "tok_s": 158136.7}
|
| 171 |
+
{"step": 137340, "epoch": 0.873, "loss": 1.75198, "ppl": 5.766, "lr": 0.003, "grad": 0.1395, "tokens": 143976268800, "tok_s": 158536.6}
|
| 172 |
+
{"step": 137360, "epoch": 0.873, "loss": 1.73914, "ppl": 5.692, "lr": 0.003, "grad": 0.2149, "tokens": 143997235200, "tok_s": 158341.6}
|
| 173 |
+
{"step": 137380, "epoch": 0.873, "loss": 1.69216, "ppl": 5.431, "lr": 0.003, "grad": 0.1378, "tokens": 144018201600, "tok_s": 158656.1}
|
| 174 |
+
{"step": 137400, "epoch": 0.873, "loss": 1.71252, "ppl": 5.543, "lr": 0.003, "grad": 0.1043, "tokens": 144039168000, "tok_s": 158229.8}
|
| 175 |
+
{"step": 137420, "epoch": 0.873, "loss": 1.73799, "ppl": 5.686, "lr": 0.003, "grad": 0.1692, "tokens": 144060134400, "tok_s": 158144.2}
|
| 176 |
+
{"step": 137440, "epoch": 0.873, "loss": 1.72699, "ppl": 5.624, "lr": 0.003, "grad": 0.1749, "tokens": 144081100800, "tok_s": 158414.8}
|
| 177 |
+
{"step": 137460, "epoch": 0.873, "loss": 1.73799, "ppl": 5.686, "lr": 0.003, "grad": 0.0488, "tokens": 144102067200, "tok_s": 158571.4}
|
| 178 |
+
{"step": 137480, "epoch": 0.873, "loss": 1.6541, "ppl": 5.228, "lr": 0.003, "grad": 0.0879, "tokens": 144123033600, "tok_s": 157962.3}
|
| 179 |
+
{"step": 137500, "epoch": 0.874, "loss": 1.86429, "ppl": 6.451, "lr": 0.003, "grad": 0.1504, "tokens": 144144000000, "tok_s": 157780.4}
|
| 180 |
+
{"step": 137520, "epoch": 0.874, "loss": 1.78945, "ppl": 5.986, "lr": 0.003, "grad": 0.0978, "tokens": 144164966400, "tok_s": 158081.4}
|
| 181 |
+
{"step": 137540, "epoch": 0.874, "loss": 1.69507, "ppl": 5.447, "lr": 0.003, "grad": 0.0734, "tokens": 144185932800, "tok_s": 158524.1}
|
| 182 |
+
{"step": 137560, "epoch": 0.874, "loss": 1.84758, "ppl": 6.344, "lr": 0.003, "grad": 0.1672, "tokens": 144206899200, "tok_s": 158376.4}
|
| 183 |
+
{"step": 137580, "epoch": 0.874, "loss": 1.7319, "ppl": 5.651, "lr": 0.003, "grad": 0.0553, "tokens": 144227865600, "tok_s": 158443.7}
|
| 184 |
+
{"step": 137600, "epoch": 0.874, "loss": 1.82056, "ppl": 6.175, "lr": 0.003, "grad": 0.1537, "tokens": 144248832000, "tok_s": 158343.1}
|
| 185 |
+
{"step": 137620, "epoch": 0.874, "loss": 1.73735, "ppl": 5.682, "lr": 0.003, "grad": 0.1823, "tokens": 144269798400, "tok_s": 158639.2}
|
| 186 |
+
{"step": 137640, "epoch": 0.875, "loss": 1.7525, "ppl": 5.769, "lr": 0.003, "grad": 0.1815, "tokens": 144290764800, "tok_s": 158422.0}
|
| 187 |
+
{"step": 137660, "epoch": 0.875, "loss": 1.63551, "ppl": 5.132, "lr": 0.003, "grad": 0.1612, "tokens": 144311731200, "tok_s": 158201.6}
|
| 188 |
+
{"step": 137680, "epoch": 0.875, "loss": 1.46667, "ppl": 4.335, "lr": 0.003, "grad": 0.103, "tokens": 144332697600, "tok_s": 158393.0}
|
| 189 |
+
{"step": 137700, "epoch": 0.875, "loss": 1.79922, "ppl": 6.045, "lr": 0.003, "grad": 0.1234, "tokens": 144353664000, "tok_s": 158516.4}
|
| 190 |
+
{"step": 137720, "epoch": 0.875, "loss": 1.70018, "ppl": 5.475, "lr": 0.003, "grad": 0.0856, "tokens": 144374630400, "tok_s": 158745.6}
|
| 191 |
+
{"step": 137740, "epoch": 0.875, "loss": 1.71576, "ppl": 5.561, "lr": 0.003, "grad": 0.179, "tokens": 144395596800, "tok_s": 158612.0}
|
| 192 |
+
{"step": 137760, "epoch": 0.875, "loss": 1.74338, "ppl": 5.717, "lr": 0.003, "grad": 0.1073, "tokens": 144416563200, "tok_s": 158320.8}
|
| 193 |
+
{"step": 137780, "epoch": 0.875, "loss": 1.70745, "ppl": 5.515, "lr": 0.003, "grad": 0.1821, "tokens": 144437529600, "tok_s": 158450.2}
|
| 194 |
+
{"step": 137800, "epoch": 0.876, "loss": 1.76647, "ppl": 5.85, "lr": 0.003, "grad": 0.1793, "tokens": 144458496000, "tok_s": 158438.8}
|
| 195 |
+
{"step": 137820, "epoch": 0.876, "loss": 1.74871, "ppl": 5.747, "lr": 0.003, "grad": 0.1605, "tokens": 144479462400, "tok_s": 158671.0}
|
| 196 |
+
{"step": 137840, "epoch": 0.876, "loss": 1.76401, "ppl": 5.836, "lr": 0.003, "grad": 0.1955, "tokens": 144500428800, "tok_s": 158767.3}
|
| 197 |
+
{"step": 137860, "epoch": 0.876, "loss": 1.73977, "ppl": 5.696, "lr": 0.003, "grad": 0.1223, "tokens": 144521395200, "tok_s": 158676.1}
|
| 198 |
+
{"step": 137880, "epoch": 0.876, "loss": 1.74292, "ppl": 5.714, "lr": 0.003, "grad": 0.1003, "tokens": 144542361600, "tok_s": 158625.2}
|
| 199 |
+
{"step": 137900, "epoch": 0.876, "loss": 1.72952, "ppl": 5.638, "lr": 0.003, "grad": 0.1267, "tokens": 144563328000, "tok_s": 158767.2}
|
| 200 |
+
{"step": 137920, "epoch": 0.876, "loss": 1.7301, "ppl": 5.641, "lr": 0.003, "grad": 0.165, "tokens": 144584294400, "tok_s": 158593.8}
|
| 201 |
+
{"step": 137940, "epoch": 0.876, "loss": 1.73744, "ppl": 5.683, "lr": 0.003, "grad": 0.2431, "tokens": 144605260800, "tok_s": 158430.0}
|
| 202 |
+
{"step": 137960, "epoch": 0.877, "loss": 1.76873, "ppl": 5.863, "lr": 0.003, "grad": 0.1378, "tokens": 144626227200, "tok_s": 158215.3}
|
| 203 |
+
{"step": 137980, "epoch": 0.877, "loss": 1.73628, "ppl": 5.676, "lr": 0.003, "grad": 0.1311, "tokens": 144647193600, "tok_s": 158089.1}
|
| 204 |
+
{"step": 138000, "epoch": 0.877, "loss": 1.76601, "ppl": 5.847, "lr": 0.003, "grad": 0.1838, "tokens": 144668160000, "tok_s": 158530.4}
|
| 205 |
+
{"step": 138000, "val_loss": 1.74912, "val_ppl": 5.75, "is_best": false}
|
logs/log_139000.jsonl
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"event": "run_start", "step": 134000, "max_steps": 157500, "optimizer": "muon_adamw", "arch": "Rose X1.5", "started_at": "2026-09-07T09:11:07.088730"}
|
| 2 |
+
{"step": 134020, "epoch": 0.852, "loss": 1.73915, "ppl": 5.693, "lr": 0.003, "grad": 0.1314, "tokens": 140495846400, "tok_s": 158946.5}
|
| 3 |
+
{"step": 134040, "epoch": 0.852, "loss": 1.74058, "ppl": 5.701, "lr": 0.003, "grad": 0.1493, "tokens": 140516812800, "tok_s": 158671.7}
|
| 4 |
+
{"step": 134060, "epoch": 0.852, "loss": 1.71345, "ppl": 5.548, "lr": 0.003, "grad": 0.1534, "tokens": 140537779200, "tok_s": 158796.4}
|
| 5 |
+
{"step": 134080, "epoch": 0.852, "loss": 1.61197, "ppl": 5.013, "lr": 0.003, "grad": 0.1372, "tokens": 140558745600, "tok_s": 159108.0}
|
| 6 |
+
{"step": 134100, "epoch": 0.852, "loss": 1.76606, "ppl": 5.848, "lr": 0.003, "grad": 0.1787, "tokens": 140579712000, "tok_s": 158732.6}
|
| 7 |
+
{"step": 134120, "epoch": 0.852, "loss": 1.72855, "ppl": 5.632, "lr": 0.003, "grad": 0.0935, "tokens": 140600678400, "tok_s": 158605.2}
|
| 8 |
+
{"step": 134140, "epoch": 0.852, "loss": 1.74189, "ppl": 5.708, "lr": 0.003, "grad": 0.1236, "tokens": 140621644800, "tok_s": 159005.8}
|
| 9 |
+
{"step": 134160, "epoch": 0.852, "loss": 1.67525, "ppl": 5.34, "lr": 0.003, "grad": 0.1527, "tokens": 140642611200, "tok_s": 159084.3}
|
| 10 |
+
{"step": 134180, "epoch": 0.853, "loss": 1.62648, "ppl": 5.086, "lr": 0.003, "grad": 0.0906, "tokens": 140663577600, "tok_s": 158623.3}
|
| 11 |
+
{"step": 134200, "epoch": 0.853, "loss": 1.59189, "ppl": 4.913, "lr": 0.003, "grad": 0.1882, "tokens": 140684544000, "tok_s": 158785.6}
|
| 12 |
+
{"step": 134220, "epoch": 0.853, "loss": 1.77783, "ppl": 5.917, "lr": 0.003, "grad": 0.1395, "tokens": 140705510400, "tok_s": 158856.6}
|
| 13 |
+
{"step": 134240, "epoch": 0.853, "loss": 1.70045, "ppl": 5.476, "lr": 0.003, "grad": 0.1261, "tokens": 140726476800, "tok_s": 158458.1}
|
| 14 |
+
{"step": 134260, "epoch": 0.853, "loss": 1.75715, "ppl": 5.796, "lr": 0.003, "grad": 0.1034, "tokens": 140747443200, "tok_s": 158770.2}
|
| 15 |
+
{"step": 134280, "epoch": 0.853, "loss": 1.70857, "ppl": 5.521, "lr": 0.003, "grad": 0.1472, "tokens": 140768409600, "tok_s": 158818.1}
|
| 16 |
+
{"step": 134300, "epoch": 0.853, "loss": 1.75325, "ppl": 5.773, "lr": 0.003, "grad": 0.1138, "tokens": 140789376000, "tok_s": 159085.8}
|
| 17 |
+
{"step": 134320, "epoch": 0.853, "loss": 1.75828, "ppl": 5.802, "lr": 0.003, "grad": 0.0805, "tokens": 140810342400, "tok_s": 158803.0}
|
| 18 |
+
{"step": 134340, "epoch": 0.854, "loss": 1.7238, "ppl": 5.606, "lr": 0.003, "grad": 0.0596, "tokens": 140831308800, "tok_s": 159133.6}
|
| 19 |
+
{"step": 134360, "epoch": 0.854, "loss": 1.77065, "ppl": 5.875, "lr": 0.003, "grad": 0.0746, "tokens": 140852275200, "tok_s": 158990.9}
|
| 20 |
+
{"step": 134380, "epoch": 0.854, "loss": 1.68014, "ppl": 5.366, "lr": 0.003, "grad": 0.1349, "tokens": 140873241600, "tok_s": 158607.1}
|
| 21 |
+
{"step": 134400, "epoch": 0.854, "loss": 1.78004, "ppl": 5.93, "lr": 0.003, "grad": 0.1395, "tokens": 140894208000, "tok_s": 158637.2}
|
| 22 |
+
{"step": 134420, "epoch": 0.854, "loss": 1.75988, "ppl": 5.812, "lr": 0.003, "grad": 0.1203, "tokens": 140915174400, "tok_s": 158998.3}
|
| 23 |
+
{"step": 134440, "epoch": 0.854, "loss": 1.66996, "ppl": 5.312, "lr": 0.003, "grad": 0.0853, "tokens": 140936140800, "tok_s": 158874.5}
|
| 24 |
+
{"step": 134460, "epoch": 0.854, "loss": 1.80972, "ppl": 6.109, "lr": 0.003, "grad": 0.1433, "tokens": 140957107200, "tok_s": 158495.5}
|
| 25 |
+
{"step": 134480, "epoch": 0.854, "loss": 1.80559, "ppl": 6.084, "lr": 0.003, "grad": 0.1328, "tokens": 140978073600, "tok_s": 158634.0}
|
| 26 |
+
{"step": 134500, "epoch": 0.855, "loss": 1.89966, "ppl": 6.684, "lr": 0.003, "grad": 0.1402, "tokens": 140999040000, "tok_s": 158670.6}
|
| 27 |
+
{"step": 134520, "epoch": 0.855, "loss": 1.76167, "ppl": 5.822, "lr": 0.003, "grad": 0.143, "tokens": 141020006400, "tok_s": 158476.8}
|
| 28 |
+
{"step": 134540, "epoch": 0.855, "loss": 1.65701, "ppl": 5.244, "lr": 0.003, "grad": 0.0632, "tokens": 141040972800, "tok_s": 158695.2}
|
| 29 |
+
{"step": 134560, "epoch": 0.855, "loss": 1.67767, "ppl": 5.353, "lr": 0.003, "grad": 0.1067, "tokens": 141061939200, "tok_s": 158984.2}
|
| 30 |
+
{"step": 134580, "epoch": 0.855, "loss": 1.70119, "ppl": 5.48, "lr": 0.003, "grad": 0.1326, "tokens": 141082905600, "tok_s": 158918.2}
|
| 31 |
+
{"step": 134600, "epoch": 0.855, "loss": 1.63792, "ppl": 5.144, "lr": 0.003, "grad": 0.0625, "tokens": 141103872000, "tok_s": 158936.4}
|
| 32 |
+
{"step": 134620, "epoch": 0.855, "loss": 1.71296, "ppl": 5.545, "lr": 0.003, "grad": 0.1238, "tokens": 141124838400, "tok_s": 158931.3}
|
| 33 |
+
{"step": 134640, "epoch": 0.855, "loss": 1.66066, "ppl": 5.263, "lr": 0.003, "grad": 0.1076, "tokens": 141145804800, "tok_s": 158962.1}
|
| 34 |
+
{"step": 134660, "epoch": 0.856, "loss": 1.84109, "ppl": 6.303, "lr": 0.003, "grad": 0.0734, "tokens": 141166771200, "tok_s": 158544.4}
|
| 35 |
+
{"step": 134680, "epoch": 0.856, "loss": 1.76961, "ppl": 5.869, "lr": 0.003, "grad": 0.1689, "tokens": 141187737600, "tok_s": 158655.0}
|
| 36 |
+
{"step": 134700, "epoch": 0.856, "loss": 1.73919, "ppl": 5.693, "lr": 0.003, "grad": 0.177, "tokens": 141208704000, "tok_s": 158892.8}
|
| 37 |
+
{"step": 134720, "epoch": 0.856, "loss": 1.66473, "ppl": 5.284, "lr": 0.003, "grad": 0.0623, "tokens": 141229670400, "tok_s": 158647.1}
|
| 38 |
+
{"step": 134740, "epoch": 0.856, "loss": 1.69772, "ppl": 5.461, "lr": 0.003, "grad": 0.1711, "tokens": 141250636800, "tok_s": 158892.5}
|
| 39 |
+
{"step": 134760, "epoch": 0.856, "loss": 1.76702, "ppl": 5.853, "lr": 0.003, "grad": 0.17, "tokens": 141271603200, "tok_s": 158875.0}
|
| 40 |
+
{"step": 134780, "epoch": 0.856, "loss": 1.67563, "ppl": 5.342, "lr": 0.003, "grad": 0.1607, "tokens": 141292569600, "tok_s": 158463.9}
|
| 41 |
+
{"step": 134800, "epoch": 0.856, "loss": 1.69027, "ppl": 5.421, "lr": 0.003, "grad": 0.152, "tokens": 141313536000, "tok_s": 158878.9}
|
| 42 |
+
{"step": 134820, "epoch": 0.857, "loss": 1.74088, "ppl": 5.702, "lr": 0.003, "grad": 0.1549, "tokens": 141334502400, "tok_s": 158885.8}
|
| 43 |
+
{"step": 134840, "epoch": 0.857, "loss": 1.67324, "ppl": 5.329, "lr": 0.003, "grad": 0.1088, "tokens": 141355468800, "tok_s": 158892.8}
|
| 44 |
+
{"step": 134860, "epoch": 0.857, "loss": 1.7503, "ppl": 5.756, "lr": 0.003, "grad": 0.1535, "tokens": 141376435200, "tok_s": 158755.0}
|
| 45 |
+
{"step": 134880, "epoch": 0.857, "loss": 1.77764, "ppl": 5.916, "lr": 0.003, "grad": 0.1162, "tokens": 141397401600, "tok_s": 158783.2}
|
| 46 |
+
{"step": 134900, "epoch": 0.857, "loss": 1.44819, "ppl": 4.255, "lr": 0.003, "grad": 0.0835, "tokens": 141418368000, "tok_s": 158740.3}
|
| 47 |
+
{"step": 134920, "epoch": 0.857, "loss": 1.67507, "ppl": 5.339, "lr": 0.003, "grad": 0.1616, "tokens": 141439334400, "tok_s": 158822.9}
|
| 48 |
+
{"step": 134940, "epoch": 0.857, "loss": 1.68746, "ppl": 5.406, "lr": 0.003, "grad": 0.0619, "tokens": 141460300800, "tok_s": 158406.8}
|
| 49 |
+
{"step": 134960, "epoch": 0.857, "loss": 1.78197, "ppl": 5.942, "lr": 0.003, "grad": 0.1268, "tokens": 141481267200, "tok_s": 158734.0}
|
| 50 |
+
{"step": 134980, "epoch": 0.858, "loss": 1.73323, "ppl": 5.659, "lr": 0.003, "grad": 0.0818, "tokens": 141502233600, "tok_s": 158566.0}
|
| 51 |
+
{"step": 135000, "epoch": 0.858, "loss": 1.88906, "ppl": 6.613, "lr": 0.003, "grad": 0.131, "tokens": 141523200000, "tok_s": 158977.3}
|
| 52 |
+
{"step": 135000, "val_loss": 1.73029, "val_ppl": 5.642, "is_best": true}
|
| 53 |
+
{"step": 135020, "epoch": 0.858, "loss": 1.73367, "ppl": 5.661, "lr": 0.003, "grad": 0.1441, "tokens": 141544166400, "tok_s": 159079.5}
|
| 54 |
+
{"step": 135040, "epoch": 0.858, "loss": 1.67592, "ppl": 5.344, "lr": 0.003, "grad": 0.1368, "tokens": 141565132800, "tok_s": 158914.3}
|
| 55 |
+
{"step": 135060, "epoch": 0.858, "loss": 1.77242, "ppl": 5.885, "lr": 0.003, "grad": 0.0903, "tokens": 141586099200, "tok_s": 158408.0}
|
| 56 |
+
{"step": 135080, "epoch": 0.858, "loss": 1.72404, "ppl": 5.607, "lr": 0.003, "grad": 0.1064, "tokens": 141607065600, "tok_s": 158531.0}
|
| 57 |
+
{"step": 135100, "epoch": 0.858, "loss": 1.59571, "ppl": 4.932, "lr": 0.003, "grad": 0.1797, "tokens": 141628032000, "tok_s": 158782.7}
|
| 58 |
+
{"step": 135120, "epoch": 0.859, "loss": 1.86924, "ppl": 6.483, "lr": 0.003, "grad": 0.0803, "tokens": 141648998400, "tok_s": 158989.4}
|
| 59 |
+
{"step": 135140, "epoch": 0.859, "loss": 1.76329, "ppl": 5.832, "lr": 0.003, "grad": 0.0811, "tokens": 141669964800, "tok_s": 158857.4}
|
| 60 |
+
{"step": 135160, "epoch": 0.859, "loss": 1.74841, "ppl": 5.745, "lr": 0.003, "grad": 0.1672, "tokens": 141690931200, "tok_s": 158263.2}
|
| 61 |
+
{"step": 135180, "epoch": 0.859, "loss": 1.79252, "ppl": 6.005, "lr": 0.003, "grad": 0.1816, "tokens": 141711897600, "tok_s": 158210.8}
|
| 62 |
+
{"step": 135200, "epoch": 0.859, "loss": 1.7063, "ppl": 5.509, "lr": 0.003, "grad": 0.1524, "tokens": 141732864000, "tok_s": 158643.8}
|
| 63 |
+
{"step": 135220, "epoch": 0.859, "loss": 1.7795, "ppl": 5.927, "lr": 0.003, "grad": 0.1494, "tokens": 141753830400, "tok_s": 158146.8}
|
| 64 |
+
{"step": 135240, "epoch": 0.859, "loss": 1.69001, "ppl": 5.42, "lr": 0.003, "grad": 0.1483, "tokens": 141774796800, "tok_s": 158465.0}
|
| 65 |
+
{"step": 135260, "epoch": 0.859, "loss": 1.71986, "ppl": 5.584, "lr": 0.003, "grad": 0.1368, "tokens": 141795763200, "tok_s": 158611.3}
|
| 66 |
+
{"step": 135280, "epoch": 0.86, "loss": 1.60245, "ppl": 4.965, "lr": 0.003, "grad": 0.1467, "tokens": 141816729600, "tok_s": 158646.7}
|
| 67 |
+
{"step": 135300, "epoch": 0.86, "loss": 1.80123, "ppl": 6.057, "lr": 0.003, "grad": 0.16, "tokens": 141837696000, "tok_s": 157959.8}
|
| 68 |
+
{"step": 135320, "epoch": 0.86, "loss": 1.74224, "ppl": 5.71, "lr": 0.003, "grad": 0.1249, "tokens": 141858662400, "tok_s": 158642.0}
|
| 69 |
+
{"step": 135340, "epoch": 0.86, "loss": 1.79372, "ppl": 6.012, "lr": 0.003, "grad": 0.1294, "tokens": 141879628800, "tok_s": 158457.2}
|
| 70 |
+
{"step": 135360, "epoch": 0.86, "loss": 1.73338, "ppl": 5.66, "lr": 0.003, "grad": 0.0985, "tokens": 141900595200, "tok_s": 158449.1}
|
| 71 |
+
{"step": 135380, "epoch": 0.86, "loss": 1.8432, "ppl": 6.317, "lr": 0.003, "grad": 0.1308, "tokens": 141921561600, "tok_s": 158213.4}
|
| 72 |
+
{"step": 135400, "epoch": 0.86, "loss": 1.81236, "ppl": 6.125, "lr": 0.003, "grad": 0.1074, "tokens": 141942528000, "tok_s": 158708.9}
|
| 73 |
+
{"step": 135420, "epoch": 0.86, "loss": 1.7933, "ppl": 6.009, "lr": 0.003, "grad": 0.1478, "tokens": 141963494400, "tok_s": 157697.2}
|
| 74 |
+
{"step": 135440, "epoch": 0.861, "loss": 1.73316, "ppl": 5.658, "lr": 0.003, "grad": 0.1342, "tokens": 141984460800, "tok_s": 158018.8}
|
| 75 |
+
{"step": 135460, "epoch": 0.861, "loss": 1.77488, "ppl": 5.9, "lr": 0.003, "grad": 0.1795, "tokens": 142005427200, "tok_s": 157889.1}
|
| 76 |
+
{"step": 135480, "epoch": 0.861, "loss": 1.82011, "ppl": 6.173, "lr": 0.003, "grad": 0.1056, "tokens": 142026393600, "tok_s": 158322.5}
|
| 77 |
+
{"step": 135500, "epoch": 0.861, "loss": 1.77863, "ppl": 5.922, "lr": 0.003, "grad": 0.1832, "tokens": 142047360000, "tok_s": 158042.2}
|
| 78 |
+
{"step": 135520, "epoch": 0.861, "loss": 1.78413, "ppl": 5.954, "lr": 0.003, "grad": 0.1536, "tokens": 142068326400, "tok_s": 158673.0}
|
| 79 |
+
{"step": 135540, "epoch": 0.861, "loss": 1.70772, "ppl": 5.516, "lr": 0.003, "grad": 0.0843, "tokens": 142089292800, "tok_s": 158958.3}
|
| 80 |
+
{"step": 135560, "epoch": 0.861, "loss": 1.78955, "ppl": 5.987, "lr": 0.003, "grad": 0.1293, "tokens": 142110259200, "tok_s": 158665.9}
|
| 81 |
+
{"step": 135580, "epoch": 0.861, "loss": 1.59136, "ppl": 4.91, "lr": 0.003, "grad": 0.0907, "tokens": 142131225600, "tok_s": 159040.3}
|
| 82 |
+
{"step": 135600, "epoch": 0.862, "loss": 1.76557, "ppl": 5.845, "lr": 0.003, "grad": 0.2092, "tokens": 142152192000, "tok_s": 158737.9}
|
| 83 |
+
{"step": 135620, "epoch": 0.862, "loss": 1.76489, "ppl": 5.841, "lr": 0.003, "grad": 0.1062, "tokens": 142173158400, "tok_s": 158712.5}
|
| 84 |
+
{"step": 135640, "epoch": 0.862, "loss": 1.73009, "ppl": 5.641, "lr": 0.003, "grad": 0.1506, "tokens": 142194124800, "tok_s": 158317.3}
|
| 85 |
+
{"step": 135660, "epoch": 0.862, "loss": 1.7837, "ppl": 5.952, "lr": 0.003, "grad": 0.1079, "tokens": 142215091200, "tok_s": 158571.7}
|
| 86 |
+
{"step": 135680, "epoch": 0.862, "loss": 1.75596, "ppl": 5.789, "lr": 0.003, "grad": 0.1572, "tokens": 142236057600, "tok_s": 159043.1}
|
| 87 |
+
{"step": 135700, "epoch": 0.862, "loss": 1.72901, "ppl": 5.635, "lr": 0.003, "grad": 0.0894, "tokens": 142257024000, "tok_s": 158197.8}
|
| 88 |
+
{"step": 135720, "epoch": 0.862, "loss": 1.70585, "ppl": 5.506, "lr": 0.003, "grad": 0.0847, "tokens": 142277990400, "tok_s": 158216.5}
|
| 89 |
+
{"step": 135740, "epoch": 0.862, "loss": 1.74374, "ppl": 5.719, "lr": 0.003, "grad": 0.1025, "tokens": 142298956800, "tok_s": 158516.9}
|
| 90 |
+
{"step": 135760, "epoch": 0.863, "loss": 1.63712, "ppl": 5.14, "lr": 0.003, "grad": 0.0958, "tokens": 142319923200, "tok_s": 158641.7}
|
| 91 |
+
{"step": 135780, "epoch": 0.863, "loss": 1.71328, "ppl": 5.547, "lr": 0.003, "grad": 0.1285, "tokens": 142340889600, "tok_s": 158410.9}
|
| 92 |
+
{"step": 135800, "epoch": 0.863, "loss": 1.73741, "ppl": 5.683, "lr": 0.003, "grad": 0.1426, "tokens": 142361856000, "tok_s": 157787.7}
|
| 93 |
+
{"step": 135820, "epoch": 0.863, "loss": 1.76231, "ppl": 5.826, "lr": 0.003, "grad": 0.091, "tokens": 142382822400, "tok_s": 158115.8}
|
| 94 |
+
{"step": 135840, "epoch": 0.863, "loss": 1.77817, "ppl": 5.919, "lr": 0.003, "grad": 0.0874, "tokens": 142403788800, "tok_s": 158443.3}
|
| 95 |
+
{"step": 135860, "epoch": 0.863, "loss": 1.78924, "ppl": 5.985, "lr": 0.003, "grad": 0.0722, "tokens": 142424755200, "tok_s": 158144.8}
|
| 96 |
+
{"step": 135880, "epoch": 0.863, "loss": 1.76683, "ppl": 5.852, "lr": 0.003, "grad": 0.111, "tokens": 142445721600, "tok_s": 158275.9}
|
| 97 |
+
{"step": 135900, "epoch": 0.863, "loss": 1.75377, "ppl": 5.776, "lr": 0.003, "grad": 0.1197, "tokens": 142466688000, "tok_s": 158584.0}
|
| 98 |
+
{"step": 135920, "epoch": 0.864, "loss": 1.77688, "ppl": 5.911, "lr": 0.003, "grad": 0.1725, "tokens": 142487654400, "tok_s": 158295.6}
|
| 99 |
+
{"step": 135940, "epoch": 0.864, "loss": 1.72879, "ppl": 5.634, "lr": 0.003, "grad": 0.1104, "tokens": 142508620800, "tok_s": 158561.0}
|
| 100 |
+
{"step": 135960, "epoch": 0.864, "loss": 1.74945, "ppl": 5.751, "lr": 0.003, "grad": 0.1739, "tokens": 142529587200, "tok_s": 158718.5}
|
| 101 |
+
{"step": 135980, "epoch": 0.864, "loss": 1.79746, "ppl": 6.034, "lr": 0.003, "grad": 0.1522, "tokens": 142550553600, "tok_s": 158185.0}
|
| 102 |
+
{"step": 136000, "epoch": 0.864, "loss": 1.72563, "ppl": 5.616, "lr": 0.003, "grad": 0.1532, "tokens": 142571520000, "tok_s": 158740.0}
|
| 103 |
+
{"step": 136000, "val_loss": 1.74202, "val_ppl": 5.709, "is_best": false}
|
| 104 |
+
{"step": 136020, "epoch": 0.864, "loss": 1.75843, "ppl": 5.803, "lr": 0.003, "grad": 0.1781, "tokens": 142592486400, "tok_s": 158663.3}
|
| 105 |
+
{"step": 136040, "epoch": 0.864, "loss": 1.74861, "ppl": 5.747, "lr": 0.003, "grad": 0.1462, "tokens": 142613452800, "tok_s": 158699.6}
|
| 106 |
+
{"step": 136060, "epoch": 0.864, "loss": 1.69362, "ppl": 5.439, "lr": 0.003, "grad": 0.135, "tokens": 142634419200, "tok_s": 158621.9}
|
| 107 |
+
{"step": 136080, "epoch": 0.865, "loss": 1.76345, "ppl": 5.833, "lr": 0.003, "grad": 0.0947, "tokens": 142655385600, "tok_s": 158364.8}
|
| 108 |
+
{"step": 136100, "epoch": 0.865, "loss": 1.75454, "ppl": 5.781, "lr": 0.003, "grad": 0.18, "tokens": 142676352000, "tok_s": 158264.2}
|
| 109 |
+
{"step": 136120, "epoch": 0.865, "loss": 1.82854, "ppl": 6.225, "lr": 0.003, "grad": 0.1676, "tokens": 142697318400, "tok_s": 157987.1}
|
| 110 |
+
{"step": 136140, "epoch": 0.865, "loss": 1.76845, "ppl": 5.862, "lr": 0.003, "grad": 0.0843, "tokens": 142718284800, "tok_s": 158118.1}
|
| 111 |
+
{"step": 136160, "epoch": 0.865, "loss": 1.72296, "ppl": 5.601, "lr": 0.003, "grad": 0.176, "tokens": 142739251200, "tok_s": 158442.1}
|
| 112 |
+
{"step": 136180, "epoch": 0.865, "loss": 1.74815, "ppl": 5.744, "lr": 0.003, "grad": 0.1405, "tokens": 142760217600, "tok_s": 158194.7}
|
| 113 |
+
{"step": 136200, "epoch": 0.865, "loss": 1.80326, "ppl": 6.069, "lr": 0.003, "grad": 0.0948, "tokens": 142781184000, "tok_s": 158224.5}
|
| 114 |
+
{"step": 136220, "epoch": 0.865, "loss": 1.70281, "ppl": 5.489, "lr": 0.003, "grad": 0.1113, "tokens": 142802150400, "tok_s": 158327.2}
|
| 115 |
+
{"step": 136240, "epoch": 0.866, "loss": 1.74675, "ppl": 5.736, "lr": 0.003, "grad": 0.1546, "tokens": 142823116800, "tok_s": 157984.6}
|
| 116 |
+
{"step": 136260, "epoch": 0.866, "loss": 1.66236, "ppl": 5.272, "lr": 0.003, "grad": 0.0813, "tokens": 142844083200, "tok_s": 158506.8}
|
| 117 |
+
{"step": 136280, "epoch": 0.866, "loss": 1.75967, "ppl": 5.81, "lr": 0.003, "grad": 0.0964, "tokens": 142865049600, "tok_s": 158299.0}
|
| 118 |
+
{"step": 136300, "epoch": 0.866, "loss": 1.78479, "ppl": 5.958, "lr": 0.003, "grad": 0.148, "tokens": 142886016000, "tok_s": 158591.0}
|
| 119 |
+
{"step": 136320, "epoch": 0.866, "loss": 1.6665, "ppl": 5.294, "lr": 0.003, "grad": 0.1016, "tokens": 142906982400, "tok_s": 157951.3}
|
| 120 |
+
{"step": 136340, "epoch": 0.866, "loss": 1.63116, "ppl": 5.11, "lr": 0.003, "grad": 0.1379, "tokens": 142927948800, "tok_s": 158554.8}
|
| 121 |
+
{"step": 136360, "epoch": 0.866, "loss": 1.75756, "ppl": 5.798, "lr": 0.003, "grad": 0.1514, "tokens": 142948915200, "tok_s": 158181.3}
|
| 122 |
+
{"step": 136380, "epoch": 0.867, "loss": 1.73176, "ppl": 5.651, "lr": 0.003, "grad": 0.1467, "tokens": 142969881600, "tok_s": 158870.2}
|
| 123 |
+
{"step": 136400, "epoch": 0.867, "loss": 1.64669, "ppl": 5.19, "lr": 0.003, "grad": 0.0968, "tokens": 142990848000, "tok_s": 158550.9}
|
| 124 |
+
{"step": 136420, "epoch": 0.867, "loss": 1.66401, "ppl": 5.28, "lr": 0.003, "grad": 0.1058, "tokens": 143011814400, "tok_s": 158557.8}
|
| 125 |
+
{"step": 136440, "epoch": 0.867, "loss": 1.85301, "ppl": 6.379, "lr": 0.003, "grad": 0.18, "tokens": 143032780800, "tok_s": 158534.3}
|
| 126 |
+
{"step": 136460, "epoch": 0.867, "loss": 1.64618, "ppl": 5.187, "lr": 0.003, "grad": 0.1353, "tokens": 143053747200, "tok_s": 158586.7}
|
| 127 |
+
{"step": 136480, "epoch": 0.867, "loss": 1.72332, "ppl": 5.603, "lr": 0.003, "grad": 0.0988, "tokens": 143074713600, "tok_s": 157946.5}
|
| 128 |
+
{"step": 136500, "epoch": 0.867, "loss": 1.69851, "ppl": 5.466, "lr": 0.003, "grad": 0.1401, "tokens": 143095680000, "tok_s": 158600.0}
|
| 129 |
+
{"step": 136520, "epoch": 0.867, "loss": 1.71151, "ppl": 5.537, "lr": 0.003, "grad": 0.0697, "tokens": 143116646400, "tok_s": 157957.1}
|
| 130 |
+
{"step": 136540, "epoch": 0.868, "loss": 1.71388, "ppl": 5.55, "lr": 0.003, "grad": 0.0634, "tokens": 143137612800, "tok_s": 158648.3}
|
| 131 |
+
{"step": 136560, "epoch": 0.868, "loss": 1.81126, "ppl": 6.118, "lr": 0.003, "grad": 0.1091, "tokens": 143158579200, "tok_s": 158493.0}
|
| 132 |
+
{"step": 136580, "epoch": 0.868, "loss": 1.74338, "ppl": 5.717, "lr": 0.003, "grad": 0.1446, "tokens": 143179545600, "tok_s": 158514.3}
|
| 133 |
+
{"step": 136600, "epoch": 0.868, "loss": 1.77354, "ppl": 5.892, "lr": 0.003, "grad": 0.1281, "tokens": 143200512000, "tok_s": 158319.2}
|
| 134 |
+
{"step": 136620, "epoch": 0.868, "loss": 1.73766, "ppl": 5.684, "lr": 0.003, "grad": 0.1713, "tokens": 143221478400, "tok_s": 158398.1}
|
| 135 |
+
{"step": 136640, "epoch": 0.868, "loss": 1.77489, "ppl": 5.9, "lr": 0.003, "grad": 0.1737, "tokens": 143242444800, "tok_s": 157759.6}
|
| 136 |
+
{"step": 136660, "epoch": 0.868, "loss": 1.64392, "ppl": 5.175, "lr": 0.003, "grad": 0.1054, "tokens": 143263411200, "tok_s": 158197.0}
|
| 137 |
+
{"step": 136680, "epoch": 0.868, "loss": 1.73884, "ppl": 5.691, "lr": 0.003, "grad": 0.1757, "tokens": 143284377600, "tok_s": 158386.2}
|
| 138 |
+
{"step": 136700, "epoch": 0.869, "loss": 1.69751, "ppl": 5.46, "lr": 0.003, "grad": 0.1424, "tokens": 143305344000, "tok_s": 158670.9}
|
| 139 |
+
{"step": 136720, "epoch": 0.869, "loss": 1.78563, "ppl": 5.963, "lr": 0.003, "grad": 0.175, "tokens": 143326310400, "tok_s": 158472.9}
|
| 140 |
+
{"step": 136740, "epoch": 0.869, "loss": 1.60733, "ppl": 4.989, "lr": 0.003, "grad": 0.0688, "tokens": 143347276800, "tok_s": 158249.7}
|
| 141 |
+
{"step": 136760, "epoch": 0.869, "loss": 1.77521, "ppl": 5.902, "lr": 0.003, "grad": 0.1283, "tokens": 143368243200, "tok_s": 158285.5}
|
| 142 |
+
{"step": 136780, "epoch": 0.869, "loss": 1.78194, "ppl": 5.941, "lr": 0.003, "grad": 0.1114, "tokens": 143389209600, "tok_s": 158617.4}
|
| 143 |
+
{"step": 136800, "epoch": 0.869, "loss": 1.75711, "ppl": 5.796, "lr": 0.003, "grad": 0.1507, "tokens": 143410176000, "tok_s": 158340.3}
|
| 144 |
+
{"step": 136820, "epoch": 0.869, "loss": 1.77529, "ppl": 5.902, "lr": 0.003, "grad": 0.1195, "tokens": 143431142400, "tok_s": 157685.2}
|
| 145 |
+
{"step": 136840, "epoch": 0.869, "loss": 1.77701, "ppl": 5.912, "lr": 0.003, "grad": 0.1705, "tokens": 143452108800, "tok_s": 158694.2}
|
| 146 |
+
{"step": 136860, "epoch": 0.87, "loss": 1.79988, "ppl": 6.049, "lr": 0.003, "grad": 0.1647, "tokens": 143473075200, "tok_s": 157892.0}
|
| 147 |
+
{"step": 136880, "epoch": 0.87, "loss": 1.71402, "ppl": 5.551, "lr": 0.003, "grad": 0.1141, "tokens": 143494041600, "tok_s": 158531.3}
|
| 148 |
+
{"step": 136900, "epoch": 0.87, "loss": 1.76826, "ppl": 5.861, "lr": 0.003, "grad": 0.1351, "tokens": 143515008000, "tok_s": 158442.3}
|
| 149 |
+
{"step": 136920, "epoch": 0.87, "loss": 1.76653, "ppl": 5.851, "lr": 0.003, "grad": 0.0923, "tokens": 143535974400, "tok_s": 158293.2}
|
| 150 |
+
{"step": 136940, "epoch": 0.87, "loss": 1.73223, "ppl": 5.653, "lr": 0.003, "grad": 0.0959, "tokens": 143556940800, "tok_s": 158431.9}
|
| 151 |
+
{"step": 136960, "epoch": 0.87, "loss": 1.78792, "ppl": 5.977, "lr": 0.003, "grad": 0.0756, "tokens": 143577907200, "tok_s": 158427.8}
|
| 152 |
+
{"step": 136980, "epoch": 0.87, "loss": 1.76046, "ppl": 5.815, "lr": 0.003, "grad": 0.1437, "tokens": 143598873600, "tok_s": 158254.7}
|
| 153 |
+
{"step": 137000, "epoch": 0.87, "loss": 1.76545, "ppl": 5.844, "lr": 0.003, "grad": 0.1232, "tokens": 143619840000, "tok_s": 158465.4}
|
| 154 |
+
{"step": 137000, "val_loss": 1.74862, "val_ppl": 5.747, "is_best": false}
|
| 155 |
+
{"step": 137020, "epoch": 0.871, "loss": 1.69586, "ppl": 5.451, "lr": 0.003, "grad": 0.1336, "tokens": 143640806400, "tok_s": 157715.9}
|
| 156 |
+
{"step": 137040, "epoch": 0.871, "loss": 1.7544, "ppl": 5.78, "lr": 0.003, "grad": 0.155, "tokens": 143661772800, "tok_s": 158466.7}
|
| 157 |
+
{"step": 137060, "epoch": 0.871, "loss": 1.73644, "ppl": 5.677, "lr": 0.003, "grad": 0.1435, "tokens": 143682739200, "tok_s": 158272.2}
|
| 158 |
+
{"step": 137080, "epoch": 0.871, "loss": 1.77659, "ppl": 5.91, "lr": 0.003, "grad": 0.1744, "tokens": 143703705600, "tok_s": 158504.4}
|
| 159 |
+
{"step": 137100, "epoch": 0.871, "loss": 1.77339, "ppl": 5.891, "lr": 0.003, "grad": 0.0996, "tokens": 143724672000, "tok_s": 158377.3}
|
| 160 |
+
{"step": 137120, "epoch": 0.871, "loss": 1.7388, "ppl": 5.69, "lr": 0.003, "grad": 0.1476, "tokens": 143745638400, "tok_s": 158340.1}
|
| 161 |
+
{"step": 137140, "epoch": 0.871, "loss": 1.72498, "ppl": 5.612, "lr": 0.003, "grad": 0.1553, "tokens": 143766604800, "tok_s": 158073.9}
|
| 162 |
+
{"step": 137160, "epoch": 0.871, "loss": 1.7359, "ppl": 5.674, "lr": 0.003, "grad": 0.2135, "tokens": 143787571200, "tok_s": 158249.9}
|
| 163 |
+
{"step": 137180, "epoch": 0.872, "loss": 1.68078, "ppl": 5.37, "lr": 0.003, "grad": 0.1378, "tokens": 143808537600, "tok_s": 158428.9}
|
| 164 |
+
{"step": 137200, "epoch": 0.872, "loss": 1.74298, "ppl": 5.714, "lr": 0.003, "grad": 0.1114, "tokens": 143829504000, "tok_s": 157890.9}
|
| 165 |
+
{"step": 137220, "epoch": 0.872, "loss": 1.72794, "ppl": 5.629, "lr": 0.003, "grad": 0.1224, "tokens": 143850470400, "tok_s": 158133.6}
|
| 166 |
+
{"step": 137240, "epoch": 0.872, "loss": 1.73312, "ppl": 5.658, "lr": 0.003, "grad": 0.1522, "tokens": 143871436800, "tok_s": 157950.4}
|
| 167 |
+
{"step": 137260, "epoch": 0.872, "loss": 1.74592, "ppl": 5.731, "lr": 0.003, "grad": 0.15, "tokens": 143892403200, "tok_s": 157869.6}
|
| 168 |
+
{"step": 137280, "epoch": 0.872, "loss": 1.76882, "ppl": 5.864, "lr": 0.003, "grad": 0.1283, "tokens": 143913369600, "tok_s": 157129.6}
|
| 169 |
+
{"step": 137300, "epoch": 0.872, "loss": 1.8218, "ppl": 6.183, "lr": 0.003, "grad": 0.1212, "tokens": 143934336000, "tok_s": 158232.5}
|
| 170 |
+
{"step": 137320, "epoch": 0.872, "loss": 1.72289, "ppl": 5.601, "lr": 0.003, "grad": 0.1539, "tokens": 143955302400, "tok_s": 158136.7}
|
| 171 |
+
{"step": 137340, "epoch": 0.873, "loss": 1.75198, "ppl": 5.766, "lr": 0.003, "grad": 0.1395, "tokens": 143976268800, "tok_s": 158536.6}
|
| 172 |
+
{"step": 137360, "epoch": 0.873, "loss": 1.73914, "ppl": 5.692, "lr": 0.003, "grad": 0.2149, "tokens": 143997235200, "tok_s": 158341.6}
|
| 173 |
+
{"step": 137380, "epoch": 0.873, "loss": 1.69216, "ppl": 5.431, "lr": 0.003, "grad": 0.1378, "tokens": 144018201600, "tok_s": 158656.1}
|
| 174 |
+
{"step": 137400, "epoch": 0.873, "loss": 1.71252, "ppl": 5.543, "lr": 0.003, "grad": 0.1043, "tokens": 144039168000, "tok_s": 158229.8}
|
| 175 |
+
{"step": 137420, "epoch": 0.873, "loss": 1.73799, "ppl": 5.686, "lr": 0.003, "grad": 0.1692, "tokens": 144060134400, "tok_s": 158144.2}
|
| 176 |
+
{"step": 137440, "epoch": 0.873, "loss": 1.72699, "ppl": 5.624, "lr": 0.003, "grad": 0.1749, "tokens": 144081100800, "tok_s": 158414.8}
|
| 177 |
+
{"step": 137460, "epoch": 0.873, "loss": 1.73799, "ppl": 5.686, "lr": 0.003, "grad": 0.0488, "tokens": 144102067200, "tok_s": 158571.4}
|
| 178 |
+
{"step": 137480, "epoch": 0.873, "loss": 1.6541, "ppl": 5.228, "lr": 0.003, "grad": 0.0879, "tokens": 144123033600, "tok_s": 157962.3}
|
| 179 |
+
{"step": 137500, "epoch": 0.874, "loss": 1.86429, "ppl": 6.451, "lr": 0.003, "grad": 0.1504, "tokens": 144144000000, "tok_s": 157780.4}
|
| 180 |
+
{"step": 137520, "epoch": 0.874, "loss": 1.78945, "ppl": 5.986, "lr": 0.003, "grad": 0.0978, "tokens": 144164966400, "tok_s": 158081.4}
|
| 181 |
+
{"step": 137540, "epoch": 0.874, "loss": 1.69507, "ppl": 5.447, "lr": 0.003, "grad": 0.0734, "tokens": 144185932800, "tok_s": 158524.1}
|
| 182 |
+
{"step": 137560, "epoch": 0.874, "loss": 1.84758, "ppl": 6.344, "lr": 0.003, "grad": 0.1672, "tokens": 144206899200, "tok_s": 158376.4}
|
| 183 |
+
{"step": 137580, "epoch": 0.874, "loss": 1.7319, "ppl": 5.651, "lr": 0.003, "grad": 0.0553, "tokens": 144227865600, "tok_s": 158443.7}
|
| 184 |
+
{"step": 137600, "epoch": 0.874, "loss": 1.82056, "ppl": 6.175, "lr": 0.003, "grad": 0.1537, "tokens": 144248832000, "tok_s": 158343.1}
|
| 185 |
+
{"step": 137620, "epoch": 0.874, "loss": 1.73735, "ppl": 5.682, "lr": 0.003, "grad": 0.1823, "tokens": 144269798400, "tok_s": 158639.2}
|
| 186 |
+
{"step": 137640, "epoch": 0.875, "loss": 1.7525, "ppl": 5.769, "lr": 0.003, "grad": 0.1815, "tokens": 144290764800, "tok_s": 158422.0}
|
| 187 |
+
{"step": 137660, "epoch": 0.875, "loss": 1.63551, "ppl": 5.132, "lr": 0.003, "grad": 0.1612, "tokens": 144311731200, "tok_s": 158201.6}
|
| 188 |
+
{"step": 137680, "epoch": 0.875, "loss": 1.46667, "ppl": 4.335, "lr": 0.003, "grad": 0.103, "tokens": 144332697600, "tok_s": 158393.0}
|
| 189 |
+
{"step": 137700, "epoch": 0.875, "loss": 1.79922, "ppl": 6.045, "lr": 0.003, "grad": 0.1234, "tokens": 144353664000, "tok_s": 158516.4}
|
| 190 |
+
{"step": 137720, "epoch": 0.875, "loss": 1.70018, "ppl": 5.475, "lr": 0.003, "grad": 0.0856, "tokens": 144374630400, "tok_s": 158745.6}
|
| 191 |
+
{"step": 137740, "epoch": 0.875, "loss": 1.71576, "ppl": 5.561, "lr": 0.003, "grad": 0.179, "tokens": 144395596800, "tok_s": 158612.0}
|
| 192 |
+
{"step": 137760, "epoch": 0.875, "loss": 1.74338, "ppl": 5.717, "lr": 0.003, "grad": 0.1073, "tokens": 144416563200, "tok_s": 158320.8}
|
| 193 |
+
{"step": 137780, "epoch": 0.875, "loss": 1.70745, "ppl": 5.515, "lr": 0.003, "grad": 0.1821, "tokens": 144437529600, "tok_s": 158450.2}
|
| 194 |
+
{"step": 137800, "epoch": 0.876, "loss": 1.76647, "ppl": 5.85, "lr": 0.003, "grad": 0.1793, "tokens": 144458496000, "tok_s": 158438.8}
|
| 195 |
+
{"step": 137820, "epoch": 0.876, "loss": 1.74871, "ppl": 5.747, "lr": 0.003, "grad": 0.1605, "tokens": 144479462400, "tok_s": 158671.0}
|
| 196 |
+
{"step": 137840, "epoch": 0.876, "loss": 1.76401, "ppl": 5.836, "lr": 0.003, "grad": 0.1955, "tokens": 144500428800, "tok_s": 158767.3}
|
| 197 |
+
{"step": 137860, "epoch": 0.876, "loss": 1.73977, "ppl": 5.696, "lr": 0.003, "grad": 0.1223, "tokens": 144521395200, "tok_s": 158676.1}
|
| 198 |
+
{"step": 137880, "epoch": 0.876, "loss": 1.74292, "ppl": 5.714, "lr": 0.003, "grad": 0.1003, "tokens": 144542361600, "tok_s": 158625.2}
|
| 199 |
+
{"step": 137900, "epoch": 0.876, "loss": 1.72952, "ppl": 5.638, "lr": 0.003, "grad": 0.1267, "tokens": 144563328000, "tok_s": 158767.2}
|
| 200 |
+
{"step": 137920, "epoch": 0.876, "loss": 1.7301, "ppl": 5.641, "lr": 0.003, "grad": 0.165, "tokens": 144584294400, "tok_s": 158593.8}
|
| 201 |
+
{"step": 137940, "epoch": 0.876, "loss": 1.73744, "ppl": 5.683, "lr": 0.003, "grad": 0.2431, "tokens": 144605260800, "tok_s": 158430.0}
|
| 202 |
+
{"step": 137960, "epoch": 0.877, "loss": 1.76873, "ppl": 5.863, "lr": 0.003, "grad": 0.1378, "tokens": 144626227200, "tok_s": 158215.3}
|
| 203 |
+
{"step": 137980, "epoch": 0.877, "loss": 1.73628, "ppl": 5.676, "lr": 0.003, "grad": 0.1311, "tokens": 144647193600, "tok_s": 158089.1}
|
| 204 |
+
{"step": 138000, "epoch": 0.877, "loss": 1.76601, "ppl": 5.847, "lr": 0.003, "grad": 0.1838, "tokens": 144668160000, "tok_s": 158530.4}
|
| 205 |
+
{"step": 138000, "val_loss": 1.74912, "val_ppl": 5.75, "is_best": false}
|
| 206 |
+
{"step": 138020, "epoch": 0.877, "loss": 1.71473, "ppl": 5.555, "lr": 0.003, "grad": 0.1608, "tokens": 144689126400, "tok_s": 158164.9}
|
| 207 |
+
{"step": 138040, "epoch": 0.877, "loss": 1.77017, "ppl": 5.872, "lr": 0.003, "grad": 0.1794, "tokens": 144710092800, "tok_s": 158291.1}
|
| 208 |
+
{"step": 138060, "epoch": 0.877, "loss": 1.71653, "ppl": 5.565, "lr": 0.003, "grad": 0.1588, "tokens": 144731059200, "tok_s": 158308.9}
|
| 209 |
+
{"step": 138080, "epoch": 0.877, "loss": 1.77979, "ppl": 5.929, "lr": 0.003, "grad": 0.1696, "tokens": 144752025600, "tok_s": 158803.5}
|
| 210 |
+
{"step": 138100, "epoch": 0.877, "loss": 1.75495, "ppl": 5.783, "lr": 0.003, "grad": 0.0963, "tokens": 144772992000, "tok_s": 158296.1}
|
| 211 |
+
{"step": 138120, "epoch": 0.878, "loss": 1.77678, "ppl": 5.911, "lr": 0.003, "grad": 0.1319, "tokens": 144793958400, "tok_s": 158520.3}
|
| 212 |
+
{"step": 138140, "epoch": 0.878, "loss": 1.71595, "ppl": 5.562, "lr": 0.003, "grad": 0.1297, "tokens": 144814924800, "tok_s": 158441.7}
|
| 213 |
+
{"step": 138160, "epoch": 0.878, "loss": 1.75468, "ppl": 5.782, "lr": 0.003, "grad": 0.1016, "tokens": 144835891200, "tok_s": 158113.3}
|
| 214 |
+
{"step": 138180, "epoch": 0.878, "loss": 1.7673, "ppl": 5.855, "lr": 0.003, "grad": 0.1151, "tokens": 144856857600, "tok_s": 158279.1}
|
| 215 |
+
{"step": 138200, "epoch": 0.878, "loss": 1.79694, "ppl": 6.031, "lr": 0.003, "grad": 0.1485, "tokens": 144877824000, "tok_s": 158105.5}
|
| 216 |
+
{"step": 138220, "epoch": 0.878, "loss": 1.79025, "ppl": 5.991, "lr": 0.003, "grad": 0.2127, "tokens": 144898790400, "tok_s": 158058.5}
|
| 217 |
+
{"step": 138240, "epoch": 0.878, "loss": 1.76156, "ppl": 5.822, "lr": 0.003, "grad": 0.06, "tokens": 144919756800, "tok_s": 158325.4}
|
| 218 |
+
{"step": 138260, "epoch": 0.878, "loss": 1.71875, "ppl": 5.578, "lr": 0.003, "grad": 0.163, "tokens": 144940723200, "tok_s": 158605.0}
|
| 219 |
+
{"step": 138280, "epoch": 0.879, "loss": 1.80205, "ppl": 6.062, "lr": 0.003, "grad": 0.1388, "tokens": 144961689600, "tok_s": 158454.2}
|
| 220 |
+
{"step": 138300, "epoch": 0.879, "loss": 1.77021, "ppl": 5.872, "lr": 0.003, "grad": 0.1626, "tokens": 144982656000, "tok_s": 158625.8}
|
| 221 |
+
{"step": 138320, "epoch": 0.879, "loss": 1.71702, "ppl": 5.568, "lr": 0.003, "grad": 0.0578, "tokens": 145003622400, "tok_s": 158279.4}
|
| 222 |
+
{"step": 138340, "epoch": 0.879, "loss": 1.77698, "ppl": 5.912, "lr": 0.003, "grad": 0.1874, "tokens": 145024588800, "tok_s": 158461.1}
|
| 223 |
+
{"step": 138360, "epoch": 0.879, "loss": 1.71574, "ppl": 5.561, "lr": 0.003, "grad": 0.114, "tokens": 145045555200, "tok_s": 158341.1}
|
| 224 |
+
{"step": 138380, "epoch": 0.879, "loss": 1.76323, "ppl": 5.831, "lr": 0.003, "grad": 0.1219, "tokens": 145066521600, "tok_s": 157930.8}
|
| 225 |
+
{"step": 138400, "epoch": 0.879, "loss": 1.64769, "ppl": 5.195, "lr": 0.003, "grad": 0.1049, "tokens": 145087488000, "tok_s": 158383.7}
|
| 226 |
+
{"step": 138420, "epoch": 0.879, "loss": 1.75636, "ppl": 5.791, "lr": 0.003, "grad": 0.1688, "tokens": 145108454400, "tok_s": 158092.1}
|
| 227 |
+
{"step": 138440, "epoch": 0.88, "loss": 1.75333, "ppl": 5.774, "lr": 0.003, "grad": 0.125, "tokens": 145129420800, "tok_s": 158719.6}
|
| 228 |
+
{"step": 138460, "epoch": 0.88, "loss": 1.76239, "ppl": 5.826, "lr": 0.003, "grad": 0.1511, "tokens": 145150387200, "tok_s": 158102.0}
|
| 229 |
+
{"step": 138480, "epoch": 0.88, "loss": 1.91455, "ppl": 6.784, "lr": 0.003, "grad": 0.1478, "tokens": 145171353600, "tok_s": 158654.2}
|
| 230 |
+
{"step": 138500, "epoch": 0.88, "loss": 1.79344, "ppl": 6.01, "lr": 0.003, "grad": 0.1774, "tokens": 145192320000, "tok_s": 158592.2}
|
| 231 |
+
{"step": 138520, "epoch": 0.88, "loss": 1.74366, "ppl": 5.718, "lr": 0.003, "grad": 0.1403, "tokens": 145213286400, "tok_s": 157900.4}
|
| 232 |
+
{"step": 138540, "epoch": 0.88, "loss": 1.73789, "ppl": 5.685, "lr": 0.003, "grad": 0.0702, "tokens": 145234252800, "tok_s": 158745.9}
|
| 233 |
+
{"step": 138560, "epoch": 0.88, "loss": 1.80834, "ppl": 6.1, "lr": 0.003, "grad": 0.1513, "tokens": 145255219200, "tok_s": 158201.4}
|
| 234 |
+
{"step": 138580, "epoch": 0.88, "loss": 1.71827, "ppl": 5.575, "lr": 0.003, "grad": 0.1518, "tokens": 145276185600, "tok_s": 158267.9}
|
| 235 |
+
{"step": 138600, "epoch": 0.881, "loss": 1.7521, "ppl": 5.767, "lr": 0.003, "grad": 0.1253, "tokens": 145297152000, "tok_s": 158227.8}
|
| 236 |
+
{"step": 138620, "epoch": 0.881, "loss": 1.76864, "ppl": 5.863, "lr": 0.003, "grad": 0.107, "tokens": 145318118400, "tok_s": 158385.3}
|
| 237 |
+
{"step": 138640, "epoch": 0.881, "loss": 1.73934, "ppl": 5.694, "lr": 0.003, "grad": 0.186, "tokens": 145339084800, "tok_s": 158692.7}
|
| 238 |
+
{"step": 138660, "epoch": 0.881, "loss": 1.71111, "ppl": 5.535, "lr": 0.003, "grad": 0.0888, "tokens": 145360051200, "tok_s": 158584.9}
|
| 239 |
+
{"step": 138680, "epoch": 0.881, "loss": 1.79492, "ppl": 6.019, "lr": 0.003, "grad": 0.1115, "tokens": 145381017600, "tok_s": 158327.3}
|
| 240 |
+
{"step": 138700, "epoch": 0.881, "loss": 1.70846, "ppl": 5.52, "lr": 0.003, "grad": 0.206, "tokens": 145401984000, "tok_s": 158368.8}
|
| 241 |
+
{"step": 138720, "epoch": 0.881, "loss": 1.73845, "ppl": 5.689, "lr": 0.003, "grad": 0.1735, "tokens": 145422950400, "tok_s": 158355.4}
|
| 242 |
+
{"step": 138740, "epoch": 0.882, "loss": 1.76436, "ppl": 5.838, "lr": 0.003, "grad": 0.21, "tokens": 145443916800, "tok_s": 158526.0}
|
| 243 |
+
{"step": 138760, "epoch": 0.882, "loss": 1.77963, "ppl": 5.928, "lr": 0.003, "grad": 0.1336, "tokens": 145464883200, "tok_s": 158460.9}
|
| 244 |
+
{"step": 138780, "epoch": 0.882, "loss": 1.73439, "ppl": 5.665, "lr": 0.003, "grad": 0.1404, "tokens": 145485849600, "tok_s": 158566.1}
|
| 245 |
+
{"step": 138800, "epoch": 0.882, "loss": 1.76871, "ppl": 5.863, "lr": 0.003, "grad": 0.102, "tokens": 145506816000, "tok_s": 158235.0}
|
| 246 |
+
{"step": 138820, "epoch": 0.882, "loss": 1.70429, "ppl": 5.497, "lr": 0.003, "grad": 0.1543, "tokens": 145527782400, "tok_s": 158354.2}
|
| 247 |
+
{"step": 138840, "epoch": 0.882, "loss": 1.74885, "ppl": 5.748, "lr": 0.003, "grad": 0.1406, "tokens": 145548748800, "tok_s": 158365.7}
|
| 248 |
+
{"step": 138860, "epoch": 0.882, "loss": 1.75637, "ppl": 5.791, "lr": 0.003, "grad": 0.1099, "tokens": 145569715200, "tok_s": 158465.0}
|
| 249 |
+
{"step": 138880, "epoch": 0.882, "loss": 1.66724, "ppl": 5.298, "lr": 0.003, "grad": 0.0623, "tokens": 145590681600, "tok_s": 158503.1}
|
| 250 |
+
{"step": 138900, "epoch": 0.883, "loss": 1.7521, "ppl": 5.767, "lr": 0.003, "grad": 0.1257, "tokens": 145611648000, "tok_s": 158586.8}
|
| 251 |
+
{"step": 138920, "epoch": 0.883, "loss": 1.73698, "ppl": 5.68, "lr": 0.003, "grad": 0.1244, "tokens": 145632614400, "tok_s": 158283.6}
|
| 252 |
+
{"step": 138940, "epoch": 0.883, "loss": 1.72563, "ppl": 5.616, "lr": 0.003, "grad": 0.1412, "tokens": 145653580800, "tok_s": 158672.7}
|
| 253 |
+
{"step": 138960, "epoch": 0.883, "loss": 1.69748, "ppl": 5.46, "lr": 0.003, "grad": 0.1304, "tokens": 145674547200, "tok_s": 158239.5}
|
| 254 |
+
{"step": 138980, "epoch": 0.883, "loss": 1.76463, "ppl": 5.839, "lr": 0.003, "grad": 0.1115, "tokens": 145695513600, "tok_s": 158276.4}
|
| 255 |
+
{"step": 139000, "epoch": 0.883, "loss": 1.78175, "ppl": 5.94, "lr": 0.003, "grad": 0.1805, "tokens": 145716480000, "tok_s": 158571.1}
|
| 256 |
+
{"step": 139000, "val_loss": 1.75062, "val_ppl": 5.758, "is_best": false}
|