Instructions to use benchflow/benchflow-qwen35-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use benchflow/benchflow-qwen35-9b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B") model = PeftModel.from_pretrained(base_model, "benchflow/benchflow-qwen35-9b") - Notebooks
- Google Colab
- Kaggle
Replace with general-agent Qwen3.5 step-200 LoRA adapter
Browse filesClean replacement from benchflow/general-agent-qwen35-9b-sft-seq2048-fresh-20260624T131847Z-lora. Removed prior env0 task-lite adapter/results artifacts and uploaded the current general-agent Qwen3.5 step-200 LoRA adapter files.
- README.md +8 -39
- TRAINING_MANIFEST.json +0 -43
- adapter_config.json +10 -42
- adapter_model.safetensors +2 -2
- all_results.json +0 -12
- eval_results.json +0 -7
- generation_config.json +6 -0
- processor_config.json +0 -60
- tokenizer_config.json +1 -3
- train_results.json +0 -8
- trainer_log.jsonl +0 -307
- trainer_state.json +0 -2191
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -1,39 +1,8 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
-
|
| 7 |
-
-
|
| 8 |
-
-
|
| 9 |
-
- env-0
|
| 10 |
-
- task-lite
|
| 11 |
-
---
|
| 12 |
-
|
| 13 |
-
# Qwen3.5-9B env-0 task-lite QLoRA adapter
|
| 14 |
-
|
| 15 |
-
PEFT LoRA adapter trained from `Qwen/Qwen3.5-9B` for the env-0 task-lite/OpenHands experiment.
|
| 16 |
-
|
| 17 |
-
## Provenance
|
| 18 |
-
|
| 19 |
-
- Base model: `Qwen/Qwen3.5-9B`
|
| 20 |
-
- Trainer: LLaMAFactory QLoRA
|
| 21 |
-
- Dataset: `env0_task_lite_gpt55_qwen_sft_reward1_exchanges`
|
| 22 |
-
- Training rows loaded: 1,087; train examples after validation split/filtering: 1,076
|
| 23 |
-
- Validation examples: 11 (`val_size: 0.01`)
|
| 24 |
-
- LoRA rank: 64
|
| 25 |
-
- LoRA alpha: 128
|
| 26 |
-
- Target modules: `['k_proj', 'in_proj_z', 'gate_proj', 'in_proj_b', 'o_proj', 'v_proj', 'in_proj_qkv', 'down_proj', 'q_proj', 'in_proj_a', 'out_proj', 'up_proj']`
|
| 27 |
-
- Train loss: 0.36306977348348785
|
| 28 |
-
- Eval loss: 0.0005094278603792191
|
| 29 |
-
- Train runtime seconds: 18396.5429
|
| 30 |
-
|
| 31 |
-
## Evaluation context
|
| 32 |
-
|
| 33 |
-
Baseline `Qwen/Qwen3.5-9B + OpenHands + SGLang + Daytona` on env-0 task-lite was 3 / 100 pass after 128k-context serving and infra refill. Post-SFT pass-rate evaluation is run separately; do not interpret training loss as task pass rate.
|
| 34 |
-
|
| 35 |
-
## Serving note
|
| 36 |
-
|
| 37 |
-
This adapter uses `lora_target: all`, including Qwen3.5 linear-attention modules such as `in_proj_qkv`, `in_proj_a`, `in_proj_b`, `in_proj_z`, and `out_proj`. Serving stacks that only support standard attention/MLP LoRA modules may need Qwen3.5-specific LoRA support.
|
| 38 |
-
|
| 39 |
-
Generated at: 2026-06-23T06:18:25Z
|
|
|
|
| 1 |
+
# general-agent-qwen35-9b-sft-seq2048-fresh-20260624T131847Z LoRA Adapter
|
| 2 |
+
|
| 3 |
+
- Base model: Qwen/Qwen3.5-9B
|
| 4 |
+
- Dataset: benchflow/general-agent-qwen35-9b-azure-gpt54mini-sft
|
| 5 |
+
- Rows: 4414
|
| 6 |
+
- Training: Prime-RL SFT, LoRA r=16 alpha=32, data.seq_len=2048, 200 steps
|
| 7 |
+
- W&B project: general-agent-qwen35-9b-sft-seq2048-fresh-20260624T131847Z
|
| 8 |
+
- Raw artifacts: benchflow/env0-experiment-trajectories/experiments/general-agent/general-agent-qwen35-9b-sft-seq2048-fresh-20260624T131847Z
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
TRAINING_MANIFEST.json
DELETED
|
@@ -1,43 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"adapter_config_subset": {
|
| 3 |
-
"base_model_name_or_path": "Qwen/Qwen3.5-9B",
|
| 4 |
-
"lora_alpha": 128,
|
| 5 |
-
"lora_dropout": 0.05,
|
| 6 |
-
"peft_type": "LORA",
|
| 7 |
-
"r": 64,
|
| 8 |
-
"target_modules": [
|
| 9 |
-
"k_proj",
|
| 10 |
-
"in_proj_z",
|
| 11 |
-
"gate_proj",
|
| 12 |
-
"in_proj_b",
|
| 13 |
-
"o_proj",
|
| 14 |
-
"v_proj",
|
| 15 |
-
"in_proj_qkv",
|
| 16 |
-
"down_proj",
|
| 17 |
-
"q_proj",
|
| 18 |
-
"in_proj_a",
|
| 19 |
-
"out_proj",
|
| 20 |
-
"up_proj"
|
| 21 |
-
],
|
| 22 |
-
"task_type": "CAUSAL_LM"
|
| 23 |
-
},
|
| 24 |
-
"artifact_type": "peft_lora_adapter",
|
| 25 |
-
"base_model": "Qwen/Qwen3.5-9B",
|
| 26 |
-
"created_at": "2026-06-23T06:18:25Z",
|
| 27 |
-
"eval_results": {
|
| 28 |
-
"epoch": 2.2230483271375463,
|
| 29 |
-
"eval_loss": 0.0005094278603792191,
|
| 30 |
-
"eval_runtime": 25.4345,
|
| 31 |
-
"eval_samples_per_second": 0.432,
|
| 32 |
-
"eval_steps_per_second": 0.432
|
| 33 |
-
},
|
| 34 |
-
"repo_id": "benchflow/qwen35-9b-env0-task-lite-qlora",
|
| 35 |
-
"train_results": {
|
| 36 |
-
"epoch": 2.2230483271375463,
|
| 37 |
-
"total_flos": 9.267981213438605e+17,
|
| 38 |
-
"train_loss": 0.36306977348348785,
|
| 39 |
-
"train_runtime": 18396.5429,
|
| 40 |
-
"train_samples_per_second": 0.13,
|
| 41 |
-
"train_steps_per_second": 0.016
|
| 42 |
-
}
|
| 43 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter_config.json
CHANGED
|
@@ -1,51 +1,19 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"arrow_config": null,
|
| 5 |
-
"auto_mapping": null,
|
| 6 |
"base_model_name_or_path": "Qwen/Qwen3.5-9B",
|
|
|
|
|
|
|
|
|
|
| 7 |
"bias": "none",
|
| 8 |
-
"corda_config": null,
|
| 9 |
-
"ensure_weight_tying": false,
|
| 10 |
-
"eva_config": null,
|
| 11 |
-
"exclude_modules": null,
|
| 12 |
-
"fan_in_fan_out": false,
|
| 13 |
-
"inference_mode": true,
|
| 14 |
-
"init_lora_weights": true,
|
| 15 |
-
"layer_replication": null,
|
| 16 |
-
"layers_pattern": null,
|
| 17 |
-
"layers_to_transform": null,
|
| 18 |
-
"loftq_config": {},
|
| 19 |
-
"lora_alpha": 128,
|
| 20 |
-
"lora_bias": false,
|
| 21 |
-
"lora_dropout": 0.05,
|
| 22 |
-
"megatron_config": null,
|
| 23 |
-
"megatron_core": "megatron.core",
|
| 24 |
-
"modules_to_save": null,
|
| 25 |
-
"peft_type": "LORA",
|
| 26 |
-
"peft_version": "0.18.1",
|
| 27 |
-
"qalora_group_size": 16,
|
| 28 |
-
"r": 64,
|
| 29 |
-
"rank_pattern": {},
|
| 30 |
-
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"
|
| 33 |
-
"in_proj_z",
|
| 34 |
"gate_proj",
|
| 35 |
-
"
|
| 36 |
"o_proj",
|
| 37 |
-
"v_proj",
|
| 38 |
-
"in_proj_qkv",
|
| 39 |
-
"down_proj",
|
| 40 |
"q_proj",
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
"up_proj"
|
| 44 |
],
|
| 45 |
-
"
|
| 46 |
-
"task_type": "CAUSAL_LM",
|
| 47 |
-
"trainable_token_indices": null,
|
| 48 |
-
"use_dora": false,
|
| 49 |
-
"use_qalora": false,
|
| 50 |
-
"use_rslora": false
|
| 51 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"peft_type": "LORA",
|
| 3 |
+
"task_type": "CAUSAL_LM",
|
|
|
|
|
|
|
| 4 |
"base_model_name_or_path": "Qwen/Qwen3.5-9B",
|
| 5 |
+
"r": 16,
|
| 6 |
+
"lora_alpha": 32.0,
|
| 7 |
+
"lora_dropout": 0.0,
|
| 8 |
"bias": "none",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"target_modules": [
|
| 10 |
+
"down_proj",
|
|
|
|
| 11 |
"gate_proj",
|
| 12 |
+
"k_proj",
|
| 13 |
"o_proj",
|
|
|
|
|
|
|
|
|
|
| 14 |
"q_proj",
|
| 15 |
+
"up_proj",
|
| 16 |
+
"v_proj"
|
|
|
|
| 17 |
],
|
| 18 |
+
"modules_to_save": null
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa60aae6e769faad42c7bb6c11a4685c7713da24e60175603e2926c943eaa7cd
|
| 3 |
+
size 58233888
|
all_results.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.2230483271375463,
|
| 3 |
-
"eval_loss": 0.0005094278603792191,
|
| 4 |
-
"eval_runtime": 25.4345,
|
| 5 |
-
"eval_samples_per_second": 0.432,
|
| 6 |
-
"eval_steps_per_second": 0.432,
|
| 7 |
-
"total_flos": 9.267981213438605e+17,
|
| 8 |
-
"train_loss": 0.36306977348348785,
|
| 9 |
-
"train_runtime": 18396.5429,
|
| 10 |
-
"train_samples_per_second": 0.13,
|
| 11 |
-
"train_steps_per_second": 0.016
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
eval_results.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.2230483271375463,
|
| 3 |
-
"eval_loss": 0.0005094278603792191,
|
| 4 |
-
"eval_runtime": 25.4345,
|
| 5 |
-
"eval_samples_per_second": 0.432,
|
| 6 |
-
"eval_steps_per_second": 0.432
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 248044,
|
| 4 |
+
"transformers_version": "5.6.2",
|
| 5 |
+
"use_cache": true
|
| 6 |
+
}
|
processor_config.json
DELETED
|
@@ -1,60 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"image_processor": {
|
| 3 |
-
"do_convert_rgb": true,
|
| 4 |
-
"do_normalize": true,
|
| 5 |
-
"do_rescale": true,
|
| 6 |
-
"do_resize": true,
|
| 7 |
-
"image_mean": [
|
| 8 |
-
0.5,
|
| 9 |
-
0.5,
|
| 10 |
-
0.5
|
| 11 |
-
],
|
| 12 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
-
"image_std": [
|
| 14 |
-
0.5,
|
| 15 |
-
0.5,
|
| 16 |
-
0.5
|
| 17 |
-
],
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"patch_size": 16,
|
| 20 |
-
"resample": 3,
|
| 21 |
-
"rescale_factor": 0.00392156862745098,
|
| 22 |
-
"size": {
|
| 23 |
-
"longest_edge": 16777216,
|
| 24 |
-
"shortest_edge": 65536
|
| 25 |
-
},
|
| 26 |
-
"temporal_patch_size": 2
|
| 27 |
-
},
|
| 28 |
-
"processor_class": "Qwen3VLProcessor",
|
| 29 |
-
"video_processor": {
|
| 30 |
-
"do_convert_rgb": true,
|
| 31 |
-
"do_normalize": true,
|
| 32 |
-
"do_rescale": true,
|
| 33 |
-
"do_resize": true,
|
| 34 |
-
"do_sample_frames": true,
|
| 35 |
-
"fps": 2,
|
| 36 |
-
"image_mean": [
|
| 37 |
-
0.5,
|
| 38 |
-
0.5,
|
| 39 |
-
0.5
|
| 40 |
-
],
|
| 41 |
-
"image_std": [
|
| 42 |
-
0.5,
|
| 43 |
-
0.5,
|
| 44 |
-
0.5
|
| 45 |
-
],
|
| 46 |
-
"max_frames": 768,
|
| 47 |
-
"merge_size": 2,
|
| 48 |
-
"min_frames": 4,
|
| 49 |
-
"patch_size": 16,
|
| 50 |
-
"resample": 3,
|
| 51 |
-
"rescale_factor": 0.00392156862745098,
|
| 52 |
-
"return_metadata": false,
|
| 53 |
-
"size": {
|
| 54 |
-
"longest_edge": 25165824,
|
| 55 |
-
"shortest_edge": 4096
|
| 56 |
-
},
|
| 57 |
-
"temporal_patch_size": 2,
|
| 58 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
-
}
|
| 60 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer_config.json
CHANGED
|
@@ -21,10 +21,8 @@
|
|
| 21 |
"vision_bos_token": "<|vision_start|>",
|
| 22 |
"vision_eos_token": "<|vision_end|>"
|
| 23 |
},
|
| 24 |
-
"pad_token": "<|
|
| 25 |
-
"padding_side": "right",
|
| 26 |
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 27 |
-
"processor_class": "Qwen3VLProcessor",
|
| 28 |
"split_special_tokens": false,
|
| 29 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 30 |
"unk_token": null,
|
|
|
|
| 21 |
"vision_bos_token": "<|vision_start|>",
|
| 22 |
"vision_eos_token": "<|vision_end|>"
|
| 23 |
},
|
| 24 |
+
"pad_token": "<|im_end|>",
|
|
|
|
| 25 |
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
|
|
|
| 26 |
"split_special_tokens": false,
|
| 27 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
"unk_token": null,
|
train_results.json
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.2230483271375463,
|
| 3 |
-
"total_flos": 9.267981213438605e+17,
|
| 4 |
-
"train_loss": 0.36306977348348785,
|
| 5 |
-
"train_runtime": 18396.5429,
|
| 6 |
-
"train_samples_per_second": 0.13,
|
| 7 |
-
"train_steps_per_second": 0.016
|
| 8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
trainer_log.jsonl
DELETED
|
@@ -1,307 +0,0 @@
|
|
| 1 |
-
{"current_steps": 1, "total_steps": 300, "loss": 3.987701892852783, "lr": 0.0, "epoch": 0.007434944237918215, "percentage": 0.33, "elapsed_time": "0:01:02", "remaining_time": "5:09:43"}
|
| 2 |
-
{"current_steps": 2, "total_steps": 300, "loss": 4.61507511138916, "lr": 2.222222222222222e-06, "epoch": 0.01486988847583643, "percentage": 0.67, "elapsed_time": "0:01:59", "remaining_time": "4:56:41"}
|
| 3 |
-
{"current_steps": 3, "total_steps": 300, "loss": 4.111183166503906, "lr": 4.444444444444444e-06, "epoch": 0.022304832713754646, "percentage": 1.0, "elapsed_time": "0:02:55", "remaining_time": "4:48:55"}
|
| 4 |
-
{"current_steps": 4, "total_steps": 300, "loss": 3.9212229251861572, "lr": 6.666666666666667e-06, "epoch": 0.02973977695167286, "percentage": 1.33, "elapsed_time": "0:04:02", "remaining_time": "4:59:00"}
|
| 5 |
-
{"current_steps": 5, "total_steps": 300, "loss": 4.2523193359375, "lr": 8.888888888888888e-06, "epoch": 0.03717472118959108, "percentage": 1.67, "elapsed_time": "0:05:04", "remaining_time": "4:59:09"}
|
| 6 |
-
{"current_steps": 6, "total_steps": 300, "loss": 3.648789167404175, "lr": 1.1111111111111113e-05, "epoch": 0.04460966542750929, "percentage": 2.0, "elapsed_time": "0:06:06", "remaining_time": "4:59:15"}
|
| 7 |
-
{"current_steps": 7, "total_steps": 300, "loss": 3.7300028800964355, "lr": 1.3333333333333333e-05, "epoch": 0.05204460966542751, "percentage": 2.33, "elapsed_time": "0:07:10", "remaining_time": "5:00:39"}
|
| 8 |
-
{"current_steps": 8, "total_steps": 300, "loss": 2.775282621383667, "lr": 1.555555555555556e-05, "epoch": 0.05947955390334572, "percentage": 2.67, "elapsed_time": "0:08:13", "remaining_time": "5:00:03"}
|
| 9 |
-
{"current_steps": 9, "total_steps": 300, "loss": 2.708098888397217, "lr": 1.7777777777777777e-05, "epoch": 0.06691449814126393, "percentage": 3.0, "elapsed_time": "0:09:17", "remaining_time": "5:00:23"}
|
| 10 |
-
{"current_steps": 10, "total_steps": 300, "loss": 2.5016918182373047, "lr": 2e-05, "epoch": 0.07434944237918216, "percentage": 3.33, "elapsed_time": "0:10:19", "remaining_time": "4:59:35"}
|
| 11 |
-
{"current_steps": 11, "total_steps": 300, "loss": 2.194194793701172, "lr": 1.9999417253661235e-05, "epoch": 0.08178438661710037, "percentage": 3.67, "elapsed_time": "0:11:26", "remaining_time": "5:00:36"}
|
| 12 |
-
{"current_steps": 12, "total_steps": 300, "loss": 2.1397340297698975, "lr": 1.9997669082563597e-05, "epoch": 0.08921933085501858, "percentage": 4.0, "elapsed_time": "0:12:30", "remaining_time": "5:00:05"}
|
| 13 |
-
{"current_steps": 13, "total_steps": 300, "loss": 2.126490354537964, "lr": 1.9994755690455154e-05, "epoch": 0.09665427509293681, "percentage": 4.33, "elapsed_time": "0:13:37", "remaining_time": "5:00:56"}
|
| 14 |
-
{"current_steps": 14, "total_steps": 300, "loss": 2.0997183322906494, "lr": 1.999067741688961e-05, "epoch": 0.10408921933085502, "percentage": 4.67, "elapsed_time": "0:14:40", "remaining_time": "4:59:47"}
|
| 15 |
-
{"current_steps": 15, "total_steps": 300, "loss": 1.8205538988113403, "lr": 1.998543473718677e-05, "epoch": 0.11152416356877323, "percentage": 5.0, "elapsed_time": "0:15:44", "remaining_time": "4:59:06"}
|
| 16 |
-
{"current_steps": 16, "total_steps": 300, "loss": 1.888378620147705, "lr": 1.997902826237712e-05, "epoch": 0.11895910780669144, "percentage": 5.33, "elapsed_time": "0:16:40", "remaining_time": "4:55:56"}
|
| 17 |
-
{"current_steps": 17, "total_steps": 300, "loss": 1.8607885837554932, "lr": 1.9971458739130598e-05, "epoch": 0.12639405204460966, "percentage": 5.67, "elapsed_time": "0:17:44", "remaining_time": "4:55:21"}
|
| 18 |
-
{"current_steps": 18, "total_steps": 300, "loss": 1.6387686729431152, "lr": 1.99627270496696e-05, "epoch": 0.13382899628252787, "percentage": 6.0, "elapsed_time": "0:18:43", "remaining_time": "4:53:17"}
|
| 19 |
-
{"current_steps": 19, "total_steps": 300, "loss": 1.459620714187622, "lr": 1.995283421166614e-05, "epoch": 0.1412639405204461, "percentage": 6.33, "elapsed_time": "0:19:42", "remaining_time": "4:51:31"}
|
| 20 |
-
{"current_steps": 20, "total_steps": 300, "loss": 1.5848277807235718, "lr": 1.9941781378123244e-05, "epoch": 0.14869888475836432, "percentage": 6.67, "elapsed_time": "0:20:41", "remaining_time": "4:49:38"}
|
| 21 |
-
{"current_steps": 21, "total_steps": 300, "loss": 1.549344778060913, "lr": 1.9929569837240567e-05, "epoch": 0.15613382899628253, "percentage": 7.0, "elapsed_time": "0:21:45", "remaining_time": "4:49:08"}
|
| 22 |
-
{"current_steps": 22, "total_steps": 300, "loss": 1.3735941648483276, "lr": 1.9916201012264255e-05, "epoch": 0.16356877323420074, "percentage": 7.33, "elapsed_time": "0:22:43", "remaining_time": "4:47:09"}
|
| 23 |
-
{"current_steps": 23, "total_steps": 300, "loss": 1.315460443496704, "lr": 1.990167646132107e-05, "epoch": 0.17100371747211895, "percentage": 7.67, "elapsed_time": "0:23:47", "remaining_time": "4:46:34"}
|
| 24 |
-
{"current_steps": 24, "total_steps": 300, "loss": 1.169264793395996, "lr": 1.9885997877236788e-05, "epoch": 0.17843866171003717, "percentage": 8.0, "elapsed_time": "0:24:45", "remaining_time": "4:44:48"}
|
| 25 |
-
{"current_steps": 25, "total_steps": 300, "loss": 1.4500298500061035, "lr": 1.9869167087338908e-05, "epoch": 0.18587360594795538, "percentage": 8.33, "elapsed_time": "0:25:45", "remaining_time": "4:43:24"}
|
| 26 |
-
{"current_steps": 26, "total_steps": 300, "loss": 0.9683340787887573, "lr": 1.9851186053243667e-05, "epoch": 0.19330855018587362, "percentage": 8.67, "elapsed_time": "0:26:41", "remaining_time": "4:41:17"}
|
| 27 |
-
{"current_steps": 27, "total_steps": 300, "loss": 1.2549272775650024, "lr": 1.983205687062742e-05, "epoch": 0.20074349442379183, "percentage": 9.0, "elapsed_time": "0:27:45", "remaining_time": "4:40:45"}
|
| 28 |
-
{"current_steps": 28, "total_steps": 300, "loss": 1.299641728401184, "lr": 1.9811781768982392e-05, "epoch": 0.20817843866171004, "percentage": 9.33, "elapsed_time": "0:28:42", "remaining_time": "4:38:50"}
|
| 29 |
-
{"current_steps": 29, "total_steps": 300, "loss": 1.1472691297531128, "lr": 1.9790363111356838e-05, "epoch": 0.21561338289962825, "percentage": 9.67, "elapsed_time": "0:29:46", "remaining_time": "4:38:14"}
|
| 30 |
-
{"current_steps": 30, "total_steps": 300, "loss": 1.0264108180999756, "lr": 1.9767803394079618e-05, "epoch": 0.22304832713754646, "percentage": 10.0, "elapsed_time": "0:30:43", "remaining_time": "4:36:29"}
|
| 31 |
-
{"current_steps": 31, "total_steps": 300, "loss": 0.9291560053825378, "lr": 1.9744105246469264e-05, "epoch": 0.23048327137546468, "percentage": 10.33, "elapsed_time": "0:31:42", "remaining_time": "4:35:12"}
|
| 32 |
-
{"current_steps": 32, "total_steps": 300, "loss": 1.0158250331878662, "lr": 1.971927143052752e-05, "epoch": 0.2379182156133829, "percentage": 10.67, "elapsed_time": "0:32:43", "remaining_time": "4:34:02"}
|
| 33 |
-
{"current_steps": 33, "total_steps": 300, "loss": 1.0452557802200317, "lr": 1.9693304840617456e-05, "epoch": 0.24535315985130113, "percentage": 11.0, "elapsed_time": "0:33:43", "remaining_time": "4:32:53"}
|
| 34 |
-
{"current_steps": 34, "total_steps": 300, "loss": 1.0367774963378906, "lr": 1.9666208503126115e-05, "epoch": 0.2527881040892193, "percentage": 11.33, "elapsed_time": "0:34:44", "remaining_time": "4:31:50"}
|
| 35 |
-
{"current_steps": 35, "total_steps": 300, "loss": 0.986078679561615, "lr": 1.963798557611178e-05, "epoch": 0.26022304832713755, "percentage": 11.67, "elapsed_time": "0:35:39", "remaining_time": "4:29:57"}
|
| 36 |
-
{"current_steps": 36, "total_steps": 300, "loss": 1.1179544925689697, "lr": 1.9608639348935938e-05, "epoch": 0.26765799256505574, "percentage": 12.0, "elapsed_time": "0:36:37", "remaining_time": "4:28:38"}
|
| 37 |
-
{"current_steps": 37, "total_steps": 300, "loss": 0.859326958656311, "lr": 1.957817324187987e-05, "epoch": 0.275092936802974, "percentage": 12.33, "elapsed_time": "0:37:41", "remaining_time": "4:27:55"}
|
| 38 |
-
{"current_steps": 38, "total_steps": 300, "loss": 1.0027873516082764, "lr": 1.9546590805746054e-05, "epoch": 0.2825278810408922, "percentage": 12.67, "elapsed_time": "0:38:45", "remaining_time": "4:27:15"}
|
| 39 |
-
{"current_steps": 39, "total_steps": 300, "loss": 1.0196456909179688, "lr": 1.9513895721444286e-05, "epoch": 0.2899628252788104, "percentage": 13.0, "elapsed_time": "0:39:50", "remaining_time": "4:26:36"}
|
| 40 |
-
{"current_steps": 40, "total_steps": 300, "loss": 0.7273167967796326, "lr": 1.9480091799562706e-05, "epoch": 0.29739776951672864, "percentage": 13.33, "elapsed_time": "0:40:50", "remaining_time": "4:25:31"}
|
| 41 |
-
{"current_steps": 41, "total_steps": 300, "loss": 0.7274726033210754, "lr": 1.9445182979923657e-05, "epoch": 0.3048327137546468, "percentage": 13.67, "elapsed_time": "0:41:56", "remaining_time": "4:24:53"}
|
| 42 |
-
{"current_steps": 42, "total_steps": 300, "loss": 1.0878797769546509, "lr": 1.94091733311245e-05, "epoch": 0.31226765799256506, "percentage": 14.0, "elapsed_time": "0:43:03", "remaining_time": "4:24:27"}
|
| 43 |
-
{"current_steps": 43, "total_steps": 300, "loss": 1.0284857749938965, "lr": 1.937206705006344e-05, "epoch": 0.31970260223048325, "percentage": 14.33, "elapsed_time": "0:44:03", "remaining_time": "4:23:19"}
|
| 44 |
-
{"current_steps": 44, "total_steps": 300, "loss": 0.8737478852272034, "lr": 1.933386846145036e-05, "epoch": 0.3271375464684015, "percentage": 14.67, "elapsed_time": "0:45:01", "remaining_time": "4:21:55"}
|
| 45 |
-
{"current_steps": 45, "total_steps": 300, "loss": 0.8448168039321899, "lr": 1.9294582017302797e-05, "epoch": 0.3345724907063197, "percentage": 15.0, "elapsed_time": "0:46:02", "remaining_time": "4:20:53"}
|
| 46 |
-
{"current_steps": 46, "total_steps": 300, "loss": 0.7004423141479492, "lr": 1.9254212296427043e-05, "epoch": 0.3420074349442379, "percentage": 15.33, "elapsed_time": "0:47:01", "remaining_time": "4:19:40"}
|
| 47 |
-
{"current_steps": 47, "total_steps": 300, "loss": 0.6901130676269531, "lr": 1.921276400388451e-05, "epoch": 0.34944237918215615, "percentage": 15.67, "elapsed_time": "0:48:02", "remaining_time": "4:18:37"}
|
| 48 |
-
{"current_steps": 48, "total_steps": 300, "loss": 0.8856571316719055, "lr": 1.9170241970443344e-05, "epoch": 0.35687732342007433, "percentage": 16.0, "elapsed_time": "0:49:09", "remaining_time": "4:18:03"}
|
| 49 |
-
{"current_steps": 49, "total_steps": 300, "loss": 0.8404887914657593, "lr": 1.9126651152015404e-05, "epoch": 0.3643122676579926, "percentage": 16.33, "elapsed_time": "0:50:12", "remaining_time": "4:17:11"}
|
| 50 |
-
{"current_steps": 50, "total_steps": 300, "loss": 0.719481348991394, "lr": 1.9081996629078655e-05, "epoch": 0.37174721189591076, "percentage": 16.67, "elapsed_time": "0:51:17", "remaining_time": "4:16:27"}
|
| 51 |
-
{"current_steps": 50, "total_steps": 300, "eval_loss": 0.6215242147445679, "epoch": 0.37174721189591076, "percentage": 16.67, "elapsed_time": "0:51:42", "remaining_time": "4:18:34"}
|
| 52 |
-
{"current_steps": 51, "total_steps": 300, "loss": 0.7017593383789062, "lr": 1.9036283606085057e-05, "epoch": 0.379182156133829, "percentage": 17.0, "elapsed_time": "0:52:39", "remaining_time": "4:17:03"}
|
| 53 |
-
{"current_steps": 52, "total_steps": 300, "loss": 0.729701578617096, "lr": 1.8989517410853956e-05, "epoch": 0.38661710037174724, "percentage": 17.33, "elapsed_time": "0:53:36", "remaining_time": "4:15:38"}
|
| 54 |
-
{"current_steps": 53, "total_steps": 300, "loss": 0.6863357424736023, "lr": 1.8941703493951163e-05, "epoch": 0.3940520446096654, "percentage": 17.67, "elapsed_time": "0:54:34", "remaining_time": "4:14:19"}
|
| 55 |
-
{"current_steps": 54, "total_steps": 300, "loss": 0.5587253570556641, "lr": 1.8892847428053692e-05, "epoch": 0.40148698884758366, "percentage": 18.0, "elapsed_time": "0:55:31", "remaining_time": "4:12:56"}
|
| 56 |
-
{"current_steps": 55, "total_steps": 300, "loss": 0.5541514158248901, "lr": 1.8842954907300236e-05, "epoch": 0.40892193308550184, "percentage": 18.33, "elapsed_time": "0:56:30", "remaining_time": "4:11:42"}
|
| 57 |
-
{"current_steps": 56, "total_steps": 300, "loss": 0.492585688829422, "lr": 1.8792031746627563e-05, "epoch": 0.4163568773234201, "percentage": 18.67, "elapsed_time": "0:57:33", "remaining_time": "4:10:47"}
|
| 58 |
-
{"current_steps": 57, "total_steps": 300, "loss": 0.5921511054039001, "lr": 1.874008388109276e-05, "epoch": 0.42379182156133827, "percentage": 19.0, "elapsed_time": "0:58:40", "remaining_time": "4:10:10"}
|
| 59 |
-
{"current_steps": 58, "total_steps": 300, "loss": 0.630439043045044, "lr": 1.8687117365181514e-05, "epoch": 0.4312267657992565, "percentage": 19.33, "elapsed_time": "0:59:43", "remaining_time": "4:09:12"}
|
| 60 |
-
{"current_steps": 59, "total_steps": 300, "loss": 0.33777663111686707, "lr": 1.863313837210247e-05, "epoch": 0.43866171003717475, "percentage": 19.67, "elapsed_time": "1:00:44", "remaining_time": "4:08:06"}
|
| 61 |
-
{"current_steps": 60, "total_steps": 300, "loss": 0.6077542304992676, "lr": 1.8578153193067746e-05, "epoch": 0.44609665427509293, "percentage": 20.0, "elapsed_time": "1:01:48", "remaining_time": "4:07:14"}
|
| 62 |
-
{"current_steps": 61, "total_steps": 300, "loss": 0.3710643947124481, "lr": 1.8522168236559693e-05, "epoch": 0.45353159851301117, "percentage": 20.33, "elapsed_time": "1:02:47", "remaining_time": "4:06:01"}
|
| 63 |
-
{"current_steps": 62, "total_steps": 300, "loss": 0.6277018785476685, "lr": 1.8465190027584007e-05, "epoch": 0.46096654275092935, "percentage": 20.67, "elapsed_time": "1:03:46", "remaining_time": "4:04:49"}
|
| 64 |
-
{"current_steps": 63, "total_steps": 300, "loss": 0.3125975430011749, "lr": 1.840722520690921e-05, "epoch": 0.4684014869888476, "percentage": 21.0, "elapsed_time": "1:04:45", "remaining_time": "4:03:35"}
|
| 65 |
-
{"current_steps": 64, "total_steps": 300, "loss": 0.6476871371269226, "lr": 1.8348280530292712e-05, "epoch": 0.4758364312267658, "percentage": 21.33, "elapsed_time": "1:05:42", "remaining_time": "4:02:19"}
|
| 66 |
-
{"current_steps": 65, "total_steps": 300, "loss": 0.3975735008716583, "lr": 1.8288362867693414e-05, "epoch": 0.483271375464684, "percentage": 21.67, "elapsed_time": "1:06:50", "remaining_time": "4:01:39"}
|
| 67 |
-
{"current_steps": 66, "total_steps": 300, "loss": 0.5023108720779419, "lr": 1.8227479202471016e-05, "epoch": 0.49070631970260226, "percentage": 22.0, "elapsed_time": "1:07:51", "remaining_time": "4:00:35"}
|
| 68 |
-
{"current_steps": 67, "total_steps": 300, "loss": 0.6572962403297424, "lr": 1.816563663057211e-05, "epoch": 0.49814126394052044, "percentage": 22.33, "elapsed_time": "1:08:52", "remaining_time": "3:59:29"}
|
| 69 |
-
{"current_steps": 68, "total_steps": 300, "loss": 0.48458513617515564, "lr": 1.8102842359703177e-05, "epoch": 0.5055762081784386, "percentage": 22.67, "elapsed_time": "1:09:54", "remaining_time": "3:58:32"}
|
| 70 |
-
{"current_steps": 69, "total_steps": 300, "loss": 0.4269074499607086, "lr": 1.8039103708490503e-05, "epoch": 0.5130111524163569, "percentage": 23.0, "elapsed_time": "1:10:56", "remaining_time": "3:57:29"}
|
| 71 |
-
{"current_steps": 70, "total_steps": 300, "loss": 0.22324775159358978, "lr": 1.797442810562721e-05, "epoch": 0.5204460966542751, "percentage": 23.33, "elapsed_time": "1:11:56", "remaining_time": "3:56:24"}
|
| 72 |
-
{"current_steps": 71, "total_steps": 300, "loss": 0.40716752409935, "lr": 1.790882308900746e-05, "epoch": 0.5278810408921933, "percentage": 23.67, "elapsed_time": "1:12:57", "remaining_time": "3:55:18"}
|
| 73 |
-
{"current_steps": 72, "total_steps": 300, "loss": 0.4579300880432129, "lr": 1.7842296304847892e-05, "epoch": 0.5353159851301115, "percentage": 24.0, "elapsed_time": "1:14:03", "remaining_time": "3:54:29"}
|
| 74 |
-
{"current_steps": 73, "total_steps": 300, "loss": 0.4471757113933563, "lr": 1.7774855506796497e-05, "epoch": 0.5427509293680297, "percentage": 24.33, "elapsed_time": "1:15:00", "remaining_time": "3:53:15"}
|
| 75 |
-
{"current_steps": 74, "total_steps": 300, "loss": 0.32918351888656616, "lr": 1.7706508555028895e-05, "epoch": 0.550185873605948, "percentage": 24.67, "elapsed_time": "1:16:05", "remaining_time": "3:52:24"}
|
| 76 |
-
{"current_steps": 75, "total_steps": 300, "loss": 0.5008412599563599, "lr": 1.7637263415332272e-05, "epoch": 0.5576208178438662, "percentage": 25.0, "elapsed_time": "1:17:10", "remaining_time": "3:51:30"}
|
| 77 |
-
{"current_steps": 76, "total_steps": 300, "loss": 0.4642640948295593, "lr": 1.7567128158176955e-05, "epoch": 0.5650557620817844, "percentage": 25.33, "elapsed_time": "1:18:08", "remaining_time": "3:50:17"}
|
| 78 |
-
{"current_steps": 77, "total_steps": 300, "loss": 0.37716782093048096, "lr": 1.749611095777581e-05, "epoch": 0.5724907063197026, "percentage": 25.67, "elapsed_time": "1:19:03", "remaining_time": "3:48:57"}
|
| 79 |
-
{"current_steps": 78, "total_steps": 300, "loss": 0.3629510998725891, "lr": 1.7424220091131536e-05, "epoch": 0.5799256505576208, "percentage": 26.0, "elapsed_time": "1:20:05", "remaining_time": "3:47:56"}
|
| 80 |
-
{"current_steps": 79, "total_steps": 300, "loss": 0.4114101529121399, "lr": 1.7351463937072008e-05, "epoch": 0.587360594795539, "percentage": 26.33, "elapsed_time": "1:21:05", "remaining_time": "3:46:50"}
|
| 81 |
-
{"current_steps": 80, "total_steps": 300, "loss": 0.2293665111064911, "lr": 1.7277850975273694e-05, "epoch": 0.5947955390334573, "percentage": 26.67, "elapsed_time": "1:21:54", "remaining_time": "3:45:14"}
|
| 82 |
-
{"current_steps": 81, "total_steps": 300, "loss": 0.27701911330223083, "lr": 1.7203389785273402e-05, "epoch": 0.6022304832713755, "percentage": 27.0, "elapsed_time": "1:22:50", "remaining_time": "3:43:57"}
|
| 83 |
-
{"current_steps": 82, "total_steps": 300, "loss": 0.2363108992576599, "lr": 1.7128089045468294e-05, "epoch": 0.6096654275092936, "percentage": 27.33, "elapsed_time": "1:23:45", "remaining_time": "3:42:41"}
|
| 84 |
-
{"current_steps": 83, "total_steps": 300, "loss": 0.236406609416008, "lr": 1.705195753210446e-05, "epoch": 0.6171003717472119, "percentage": 27.67, "elapsed_time": "1:24:47", "remaining_time": "3:41:41"}
|
| 85 |
-
{"current_steps": 84, "total_steps": 300, "loss": 0.23633553087711334, "lr": 1.697500411825403e-05, "epoch": 0.6245353159851301, "percentage": 28.0, "elapsed_time": "1:25:54", "remaining_time": "3:40:53"}
|
| 86 |
-
{"current_steps": 85, "total_steps": 300, "loss": 0.29998382925987244, "lr": 1.6897237772781046e-05, "epoch": 0.6319702602230484, "percentage": 28.33, "elapsed_time": "1:26:57", "remaining_time": "3:39:58"}
|
| 87 |
-
{"current_steps": 86, "total_steps": 300, "loss": 0.11270587891340256, "lr": 1.681866755929612e-05, "epoch": 0.6394052044609665, "percentage": 28.67, "elapsed_time": "1:27:57", "remaining_time": "3:38:53"}
|
| 88 |
-
{"current_steps": 87, "total_steps": 300, "loss": 0.15540620684623718, "lr": 1.673930263510011e-05, "epoch": 0.6468401486988847, "percentage": 29.0, "elapsed_time": "1:29:00", "remaining_time": "3:37:54"}
|
| 89 |
-
{"current_steps": 88, "total_steps": 300, "loss": 0.15637709200382233, "lr": 1.665915225011681e-05, "epoch": 0.654275092936803, "percentage": 29.33, "elapsed_time": "1:29:58", "remaining_time": "3:36:45"}
|
| 90 |
-
{"current_steps": 89, "total_steps": 300, "loss": 0.2768555283546448, "lr": 1.6578225745814907e-05, "epoch": 0.6617100371747212, "percentage": 29.67, "elapsed_time": "1:30:56", "remaining_time": "3:35:35"}
|
| 91 |
-
{"current_steps": 90, "total_steps": 300, "loss": 0.20483152568340302, "lr": 1.6496532554119214e-05, "epoch": 0.6691449814126395, "percentage": 30.0, "elapsed_time": "1:31:57", "remaining_time": "3:34:34"}
|
| 92 |
-
{"current_steps": 91, "total_steps": 300, "loss": 0.1862092763185501, "lr": 1.6414082196311402e-05, "epoch": 0.6765799256505576, "percentage": 30.33, "elapsed_time": "1:33:00", "remaining_time": "3:33:36"}
|
| 93 |
-
{"current_steps": 92, "total_steps": 300, "loss": 0.2161349058151245, "lr": 1.63308842819203e-05, "epoch": 0.6840148698884758, "percentage": 30.67, "elapsed_time": "1:34:04", "remaining_time": "3:32:41"}
|
| 94 |
-
{"current_steps": 93, "total_steps": 300, "loss": 0.16542889177799225, "lr": 1.6246948507601915e-05, "epoch": 0.6914498141263941, "percentage": 31.0, "elapsed_time": "1:35:02", "remaining_time": "3:31:32"}
|
| 95 |
-
{"current_steps": 94, "total_steps": 300, "loss": 0.20036524534225464, "lr": 1.6162284656009276e-05, "epoch": 0.6988847583643123, "percentage": 31.33, "elapsed_time": "1:36:04", "remaining_time": "3:30:33"}
|
| 96 |
-
{"current_steps": 95, "total_steps": 300, "loss": 0.1164686307311058, "lr": 1.607690259465229e-05, "epoch": 0.7063197026022305, "percentage": 31.67, "elapsed_time": "1:37:04", "remaining_time": "3:29:28"}
|
| 97 |
-
{"current_steps": 96, "total_steps": 300, "loss": 0.31526434421539307, "lr": 1.5990812274747695e-05, "epoch": 0.7137546468401487, "percentage": 32.0, "elapsed_time": "1:37:57", "remaining_time": "3:28:09"}
|
| 98 |
-
{"current_steps": 97, "total_steps": 300, "loss": 0.2151976376771927, "lr": 1.5904023730059227e-05, "epoch": 0.7211895910780669, "percentage": 32.33, "elapsed_time": "1:39:03", "remaining_time": "3:27:17"}
|
| 99 |
-
{"current_steps": 98, "total_steps": 300, "loss": 0.16460475325584412, "lr": 1.5816547075728227e-05, "epoch": 0.7286245353159851, "percentage": 32.67, "elapsed_time": "1:39:58", "remaining_time": "3:26:03"}
|
| 100 |
-
{"current_steps": 99, "total_steps": 300, "loss": 0.1308743804693222, "lr": 1.57283925070947e-05, "epoch": 0.7360594795539034, "percentage": 33.0, "elapsed_time": "1:41:05", "remaining_time": "3:25:15"}
|
| 101 |
-
{"current_steps": 100, "total_steps": 300, "loss": 0.10017991811037064, "lr": 1.5639570298509067e-05, "epoch": 0.7434944237918215, "percentage": 33.33, "elapsed_time": "1:42:07", "remaining_time": "3:24:14"}
|
| 102 |
-
{"current_steps": 100, "total_steps": 300, "eval_loss": 0.07931093126535416, "epoch": 0.7434944237918215, "percentage": 33.33, "elapsed_time": "1:42:32", "remaining_time": "3:25:04"}
|
| 103 |
-
{"current_steps": 101, "total_steps": 300, "loss": 0.14433185756206512, "lr": 1.55500908021347e-05, "epoch": 0.7509293680297398, "percentage": 33.67, "elapsed_time": "1:43:37", "remaining_time": "3:24:11"}
|
| 104 |
-
{"current_steps": 102, "total_steps": 300, "loss": 0.1454196274280548, "lr": 1.545996444674138e-05, "epoch": 0.758364312267658, "percentage": 34.0, "elapsed_time": "1:44:44", "remaining_time": "3:23:18"}
|
| 105 |
-
{"current_steps": 103, "total_steps": 300, "loss": 0.13363991677761078, "lr": 1.536920173648984e-05, "epoch": 0.7657992565055762, "percentage": 34.33, "elapsed_time": "1:45:47", "remaining_time": "3:22:19"}
|
| 106 |
-
{"current_steps": 104, "total_steps": 300, "loss": 0.164640873670578, "lr": 1.5277813249707488e-05, "epoch": 0.7732342007434945, "percentage": 34.67, "elapsed_time": "1:46:48", "remaining_time": "3:21:16"}
|
| 107 |
-
{"current_steps": 105, "total_steps": 300, "loss": 0.11201221495866776, "lr": 1.5185809637655548e-05, "epoch": 0.7806691449814126, "percentage": 35.0, "elapsed_time": "1:47:44", "remaining_time": "3:20:04"}
|
| 108 |
-
{"current_steps": 106, "total_steps": 300, "loss": 0.06443426012992859, "lr": 1.5093201623287631e-05, "epoch": 0.7881040892193308, "percentage": 35.33, "elapsed_time": "1:48:45", "remaining_time": "3:19:02"}
|
| 109 |
-
{"current_steps": 107, "total_steps": 300, "loss": 0.17740455269813538, "lr": 1.5000000000000002e-05, "epoch": 0.7955390334572491, "percentage": 35.67, "elapsed_time": "1:49:44", "remaining_time": "3:17:57"}
|
| 110 |
-
{"current_steps": 108, "total_steps": 300, "loss": 0.15067075192928314, "lr": 1.4906215630373606e-05, "epoch": 0.8029739776951673, "percentage": 36.0, "elapsed_time": "1:50:48", "remaining_time": "3:17:00"}
|
| 111 |
-
{"current_steps": 109, "total_steps": 300, "loss": 0.0934559628367424, "lr": 1.4811859444908053e-05, "epoch": 0.8104089219330854, "percentage": 36.33, "elapsed_time": "1:51:40", "remaining_time": "3:15:40"}
|
| 112 |
-
{"current_steps": 110, "total_steps": 300, "loss": 0.1534709483385086, "lr": 1.4716942440747663e-05, "epoch": 0.8178438661710037, "percentage": 36.67, "elapsed_time": "1:52:43", "remaining_time": "3:14:41"}
|
| 113 |
-
{"current_steps": 111, "total_steps": 300, "loss": 0.040919575840234756, "lr": 1.4621475680399771e-05, "epoch": 0.8252788104089219, "percentage": 37.0, "elapsed_time": "1:53:47", "remaining_time": "3:13:45"}
|
| 114 |
-
{"current_steps": 112, "total_steps": 300, "loss": 0.0943223163485527, "lr": 1.4525470290445392e-05, "epoch": 0.8327137546468402, "percentage": 37.33, "elapsed_time": "1:54:45", "remaining_time": "3:12:38"}
|
| 115 |
-
{"current_steps": 113, "total_steps": 300, "loss": 0.09913193434476852, "lr": 1.4428937460242417e-05, "epoch": 0.8401486988847584, "percentage": 37.67, "elapsed_time": "1:55:45", "remaining_time": "3:11:33"}
|
| 116 |
-
{"current_steps": 114, "total_steps": 300, "loss": 0.08492155373096466, "lr": 1.4331888440621533e-05, "epoch": 0.8475836431226765, "percentage": 38.0, "elapsed_time": "1:56:49", "remaining_time": "3:10:36"}
|
| 117 |
-
{"current_steps": 115, "total_steps": 300, "loss": 0.0402367040514946, "lr": 1.4234334542574906e-05, "epoch": 0.8550185873605948, "percentage": 38.33, "elapsed_time": "1:57:51", "remaining_time": "3:09:36"}
|
| 118 |
-
{"current_steps": 116, "total_steps": 300, "loss": 0.046510517597198486, "lr": 1.4136287135937915e-05, "epoch": 0.862453531598513, "percentage": 38.67, "elapsed_time": "1:58:53", "remaining_time": "3:08:35"}
|
| 119 |
-
{"current_steps": 117, "total_steps": 300, "loss": 0.12098722159862518, "lr": 1.4037757648064019e-05, "epoch": 0.8698884758364313, "percentage": 39.0, "elapsed_time": "1:59:58", "remaining_time": "3:07:38"}
|
| 120 |
-
{"current_steps": 118, "total_steps": 300, "loss": 0.22321803867816925, "lr": 1.3938757562492873e-05, "epoch": 0.8773234200743495, "percentage": 39.33, "elapsed_time": "2:01:03", "remaining_time": "3:06:43"}
|
| 121 |
-
{"current_steps": 119, "total_steps": 300, "loss": 0.09593161195516586, "lr": 1.3839298417611964e-05, "epoch": 0.8847583643122676, "percentage": 39.67, "elapsed_time": "2:01:57", "remaining_time": "3:05:30"}
|
| 122 |
-
{"current_steps": 120, "total_steps": 300, "loss": 0.024490350857377052, "lr": 1.3739391805311795e-05, "epoch": 0.8921933085501859, "percentage": 40.0, "elapsed_time": "2:02:59", "remaining_time": "3:04:28"}
|
| 123 |
-
{"current_steps": 121, "total_steps": 300, "loss": 0.07902126759290695, "lr": 1.3639049369634878e-05, "epoch": 0.8996282527881041, "percentage": 40.33, "elapsed_time": "2:04:00", "remaining_time": "3:03:26"}
|
| 124 |
-
{"current_steps": 122, "total_steps": 300, "loss": 0.14102190732955933, "lr": 1.353828280541861e-05, "epoch": 0.9070631970260223, "percentage": 40.67, "elapsed_time": "2:04:59", "remaining_time": "3:02:21"}
|
| 125 |
-
{"current_steps": 123, "total_steps": 300, "loss": 0.05054217204451561, "lr": 1.3437103856932266e-05, "epoch": 0.9144981412639405, "percentage": 41.0, "elapsed_time": "2:06:03", "remaining_time": "3:01:23"}
|
| 126 |
-
{"current_steps": 124, "total_steps": 300, "loss": 0.03348986431956291, "lr": 1.3335524316508208e-05, "epoch": 0.9219330855018587, "percentage": 41.33, "elapsed_time": "2:07:04", "remaining_time": "3:00:22"}
|
| 127 |
-
{"current_steps": 125, "total_steps": 300, "loss": 0.053330615162849426, "lr": 1.3233556023167487e-05, "epoch": 0.929368029739777, "percentage": 41.67, "elapsed_time": "2:08:01", "remaining_time": "2:59:14"}
|
| 128 |
-
{"current_steps": 126, "total_steps": 300, "loss": 0.05251903086900711, "lr": 1.3131210861240027e-05, "epoch": 0.9368029739776952, "percentage": 42.0, "elapsed_time": "2:09:03", "remaining_time": "2:58:13"}
|
| 129 |
-
{"current_steps": 127, "total_steps": 300, "loss": 0.09079591929912567, "lr": 1.3028500758979507e-05, "epoch": 0.9442379182156134, "percentage": 42.33, "elapsed_time": "2:10:03", "remaining_time": "2:57:10"}
|
| 130 |
-
{"current_steps": 128, "total_steps": 300, "loss": 0.04166308045387268, "lr": 1.2925437687173144e-05, "epoch": 0.9516728624535316, "percentage": 42.67, "elapsed_time": "2:11:04", "remaining_time": "2:56:08"}
|
| 131 |
-
{"current_steps": 129, "total_steps": 300, "loss": 0.04305100068449974, "lr": 1.2822033657746478e-05, "epoch": 0.9591078066914498, "percentage": 43.0, "elapsed_time": "2:12:06", "remaining_time": "2:55:07"}
|
| 132 |
-
{"current_steps": 130, "total_steps": 300, "loss": 0.020988037809729576, "lr": 1.2718300722363431e-05, "epoch": 0.966542750929368, "percentage": 43.33, "elapsed_time": "2:13:09", "remaining_time": "2:54:08"}
|
| 133 |
-
{"current_steps": 131, "total_steps": 300, "loss": 0.01916791871190071, "lr": 1.2614250971021658e-05, "epoch": 0.9739776951672863, "percentage": 43.67, "elapsed_time": "2:14:11", "remaining_time": "2:53:06"}
|
| 134 |
-
{"current_steps": 132, "total_steps": 300, "loss": 0.02789604477584362, "lr": 1.2509896530643488e-05, "epoch": 0.9814126394052045, "percentage": 44.0, "elapsed_time": "2:15:11", "remaining_time": "2:52:03"}
|
| 135 |
-
{"current_steps": 133, "total_steps": 300, "loss": 0.0284620001912117, "lr": 1.2405249563662539e-05, "epoch": 0.9888475836431226, "percentage": 44.33, "elapsed_time": "2:16:14", "remaining_time": "2:51:03"}
|
| 136 |
-
{"current_steps": 134, "total_steps": 300, "loss": 0.07058233767747879, "lr": 1.2300322266606176e-05, "epoch": 0.9962825278810409, "percentage": 44.67, "elapsed_time": "2:17:12", "remaining_time": "2:49:58"}
|
| 137 |
-
{"current_steps": 135, "total_steps": 300, "loss": 0.10080776363611221, "lr": 1.2195126868674052e-05, "epoch": 1.0, "percentage": 45.0, "elapsed_time": "2:17:38", "remaining_time": "2:48:14"}
|
| 138 |
-
{"current_steps": 136, "total_steps": 300, "loss": 0.012475713156163692, "lr": 1.2089675630312755e-05, "epoch": 1.0074349442379182, "percentage": 45.33, "elapsed_time": "2:18:38", "remaining_time": "2:47:11"}
|
| 139 |
-
{"current_steps": 137, "total_steps": 300, "loss": 0.02550521492958069, "lr": 1.1983980841786899e-05, "epoch": 1.0148698884758365, "percentage": 45.67, "elapsed_time": "2:19:40", "remaining_time": "2:46:11"}
|
| 140 |
-
{"current_steps": 138, "total_steps": 300, "loss": 0.03438372164964676, "lr": 1.1878054821746703e-05, "epoch": 1.0223048327137547, "percentage": 46.0, "elapsed_time": "2:20:38", "remaining_time": "2:45:05"}
|
| 141 |
-
{"current_steps": 139, "total_steps": 300, "loss": 0.012718814425170422, "lr": 1.177190991579223e-05, "epoch": 1.029739776951673, "percentage": 46.33, "elapsed_time": "2:21:36", "remaining_time": "2:44:01"}
|
| 142 |
-
{"current_steps": 140, "total_steps": 300, "loss": 0.010748831555247307, "lr": 1.1665558495034546e-05, "epoch": 1.037174721189591, "percentage": 46.67, "elapsed_time": "2:22:39", "remaining_time": "2:43:02"}
|
| 143 |
-
{"current_steps": 141, "total_steps": 300, "loss": 0.03220899775624275, "lr": 1.1559012954653865e-05, "epoch": 1.0446096654275092, "percentage": 47.0, "elapsed_time": "2:23:42", "remaining_time": "2:42:03"}
|
| 144 |
-
{"current_steps": 142, "total_steps": 300, "loss": 0.012064998038113117, "lr": 1.1452285712454905e-05, "epoch": 1.0520446096654275, "percentage": 47.33, "elapsed_time": "2:24:37", "remaining_time": "2:40:55"}
|
| 145 |
-
{"current_steps": 143, "total_steps": 300, "loss": 0.022306285798549652, "lr": 1.1345389207419588e-05, "epoch": 1.0594795539033457, "percentage": 47.67, "elapsed_time": "2:25:39", "remaining_time": "2:39:55"}
|
| 146 |
-
{"current_steps": 144, "total_steps": 300, "loss": 0.04725006967782974, "lr": 1.1238335898257305e-05, "epoch": 1.066914498141264, "percentage": 48.0, "elapsed_time": "2:26:43", "remaining_time": "2:38:57"}
|
| 147 |
-
{"current_steps": 145, "total_steps": 300, "loss": 0.024585356935858727, "lr": 1.1131138261952845e-05, "epoch": 1.0743494423791822, "percentage": 48.33, "elapsed_time": "2:27:39", "remaining_time": "2:37:50"}
|
| 148 |
-
{"current_steps": 146, "total_steps": 300, "loss": 0.02972128801047802, "lr": 1.1023808792312226e-05, "epoch": 1.0817843866171004, "percentage": 48.67, "elapsed_time": "2:28:36", "remaining_time": "2:36:45"}
|
| 149 |
-
{"current_steps": 147, "total_steps": 300, "loss": 0.03628234192728996, "lr": 1.0916359998506549e-05, "epoch": 1.0892193308550187, "percentage": 49.0, "elapsed_time": "2:29:36", "remaining_time": "2:35:42"}
|
| 150 |
-
{"current_steps": 148, "total_steps": 300, "loss": 0.02200871706008911, "lr": 1.0808804403614044e-05, "epoch": 1.096654275092937, "percentage": 49.33, "elapsed_time": "2:30:33", "remaining_time": "2:34:37"}
|
| 151 |
-
{"current_steps": 149, "total_steps": 300, "loss": 0.012756682932376862, "lr": 1.070115454316054e-05, "epoch": 1.104089219330855, "percentage": 49.67, "elapsed_time": "2:31:36", "remaining_time": "2:33:38"}
|
| 152 |
-
{"current_steps": 150, "total_steps": 300, "loss": 0.021982628852128983, "lr": 1.0593422963658453e-05, "epoch": 1.1115241635687731, "percentage": 50.0, "elapsed_time": "2:32:42", "remaining_time": "2:32:42"}
|
| 153 |
-
{"current_steps": 150, "total_steps": 300, "eval_loss": 0.037792377173900604, "epoch": 1.1115241635687731, "percentage": 50.0, "elapsed_time": "2:33:08", "remaining_time": "2:33:08"}
|
| 154 |
-
{"current_steps": 151, "total_steps": 300, "loss": 0.006427440792322159, "lr": 1.0485622221144485e-05, "epoch": 1.1189591078066914, "percentage": 50.33, "elapsed_time": "2:34:04", "remaining_time": "2:32:02"}
|
| 155 |
-
{"current_steps": 152, "total_steps": 300, "loss": 0.019488757476210594, "lr": 1.0377764879716234e-05, "epoch": 1.1263940520446096, "percentage": 50.67, "elapsed_time": "2:35:12", "remaining_time": "2:31:07"}
|
| 156 |
-
{"current_steps": 153, "total_steps": 300, "loss": 0.006268701050430536, "lr": 1.0269863510067872e-05, "epoch": 1.1338289962825279, "percentage": 51.0, "elapsed_time": "2:36:15", "remaining_time": "2:30:08"}
|
| 157 |
-
{"current_steps": 154, "total_steps": 300, "loss": 0.027911271899938583, "lr": 1.0161930688025018e-05, "epoch": 1.141263940520446, "percentage": 51.33, "elapsed_time": "2:37:13", "remaining_time": "2:29:03"}
|
| 158 |
-
{"current_steps": 155, "total_steps": 300, "loss": 0.034651659429073334, "lr": 1.0053978993079046e-05, "epoch": 1.1486988847583643, "percentage": 51.67, "elapsed_time": "2:38:13", "remaining_time": "2:28:01"}
|
| 159 |
-
{"current_steps": 156, "total_steps": 300, "loss": 0.024138193577528, "lr": 9.946021006920959e-06, "epoch": 1.1561338289962826, "percentage": 52.0, "elapsed_time": "2:39:12", "remaining_time": "2:26:57"}
|
| 160 |
-
{"current_steps": 157, "total_steps": 300, "loss": 0.05596349760890007, "lr": 9.838069311974986e-06, "epoch": 1.1635687732342008, "percentage": 52.33, "elapsed_time": "2:40:13", "remaining_time": "2:25:55"}
|
| 161 |
-
{"current_steps": 158, "total_steps": 300, "loss": 0.04488427937030792, "lr": 9.730136489932133e-06, "epoch": 1.1710037174721188, "percentage": 52.67, "elapsed_time": "2:41:12", "remaining_time": "2:24:52"}
|
| 162 |
-
{"current_steps": 159, "total_steps": 300, "loss": 0.009759537875652313, "lr": 9.622235120283769e-06, "epoch": 1.178438661710037, "percentage": 53.0, "elapsed_time": "2:42:13", "remaining_time": "2:23:51"}
|
| 163 |
-
{"current_steps": 160, "total_steps": 300, "loss": 0.013831784948706627, "lr": 9.514377778855521e-06, "epoch": 1.1858736059479553, "percentage": 53.33, "elapsed_time": "2:43:15", "remaining_time": "2:22:51"}
|
| 164 |
-
{"current_steps": 161, "total_steps": 300, "loss": 0.02133704535663128, "lr": 9.406577036341548e-06, "epoch": 1.1933085501858736, "percentage": 53.67, "elapsed_time": "2:44:19", "remaining_time": "2:21:52"}
|
| 165 |
-
{"current_steps": 162, "total_steps": 300, "loss": 0.02591024711728096, "lr": 9.298845456839459e-06, "epoch": 1.2007434944237918, "percentage": 54.0, "elapsed_time": "2:45:12", "remaining_time": "2:20:44"}
|
| 166 |
-
{"current_steps": 163, "total_steps": 300, "loss": 0.017063425853848457, "lr": 9.19119559638596e-06, "epoch": 1.20817843866171, "percentage": 54.33, "elapsed_time": "2:46:13", "remaining_time": "2:19:42"}
|
| 167 |
-
{"current_steps": 164, "total_steps": 300, "loss": 0.011678601615130901, "lr": 9.083640001493455e-06, "epoch": 1.2156133828996283, "percentage": 54.67, "elapsed_time": "2:47:11", "remaining_time": "2:18:38"}
|
| 168 |
-
{"current_steps": 165, "total_steps": 300, "loss": 0.02969130128622055, "lr": 8.976191207687775e-06, "epoch": 1.2230483271375465, "percentage": 55.0, "elapsed_time": "2:48:18", "remaining_time": "2:17:42"}
|
| 169 |
-
{"current_steps": 166, "total_steps": 300, "loss": 0.04694490134716034, "lr": 8.868861738047158e-06, "epoch": 1.2304832713754648, "percentage": 55.33, "elapsed_time": "2:49:16", "remaining_time": "2:16:38"}
|
| 170 |
-
{"current_steps": 167, "total_steps": 300, "loss": 0.013061350211501122, "lr": 8.7616641017427e-06, "epoch": 1.2379182156133828, "percentage": 55.67, "elapsed_time": "2:50:13", "remaining_time": "2:15:34"}
|
| 171 |
-
{"current_steps": 168, "total_steps": 300, "loss": 0.06219532713294029, "lr": 8.654610792580415e-06, "epoch": 1.2453531598513012, "percentage": 56.0, "elapsed_time": "2:51:07", "remaining_time": "2:14:27"}
|
| 172 |
-
{"current_steps": 169, "total_steps": 300, "loss": 0.04001167416572571, "lr": 8.5477142875451e-06, "epoch": 1.2527881040892193, "percentage": 56.33, "elapsed_time": "2:52:09", "remaining_time": "2:13:26"}
|
| 173 |
-
{"current_steps": 170, "total_steps": 300, "loss": 0.0347297228872776, "lr": 8.440987045346135e-06, "epoch": 1.2602230483271375, "percentage": 56.67, "elapsed_time": "2:53:11", "remaining_time": "2:12:26"}
|
| 174 |
-
{"current_steps": 171, "total_steps": 300, "loss": 0.005336158908903599, "lr": 8.334441504965456e-06, "epoch": 1.2676579925650557, "percentage": 57.0, "elapsed_time": "2:54:12", "remaining_time": "2:11:25"}
|
| 175 |
-
{"current_steps": 172, "total_steps": 300, "loss": 0.009373579174280167, "lr": 8.228090084207773e-06, "epoch": 1.275092936802974, "percentage": 57.33, "elapsed_time": "2:55:09", "remaining_time": "2:10:20"}
|
| 176 |
-
{"current_steps": 173, "total_steps": 300, "loss": 0.006868388969451189, "lr": 8.1219451782533e-06, "epoch": 1.2825278810408922, "percentage": 57.67, "elapsed_time": "2:56:10", "remaining_time": "2:09:19"}
|
| 177 |
-
{"current_steps": 174, "total_steps": 300, "loss": 0.0061888257041573524, "lr": 8.016019158213103e-06, "epoch": 1.2899628252788105, "percentage": 58.0, "elapsed_time": "2:57:13", "remaining_time": "2:08:20"}
|
| 178 |
-
{"current_steps": 175, "total_steps": 300, "loss": 0.03539920598268509, "lr": 7.91032436968725e-06, "epoch": 1.2973977695167287, "percentage": 58.33, "elapsed_time": "2:58:15", "remaining_time": "2:07:19"}
|
| 179 |
-
{"current_steps": 176, "total_steps": 300, "loss": 0.005195024888962507, "lr": 7.804873131325955e-06, "epoch": 1.3048327137546467, "percentage": 58.67, "elapsed_time": "2:59:19", "remaining_time": "2:06:20"}
|
| 180 |
-
{"current_steps": 177, "total_steps": 300, "loss": 0.053930528461933136, "lr": 7.699677733393827e-06, "epoch": 1.3122676579925652, "percentage": 59.0, "elapsed_time": "3:00:24", "remaining_time": "2:05:21"}
|
| 181 |
-
{"current_steps": 178, "total_steps": 300, "loss": 0.11866368353366852, "lr": 7.594750436337467e-06, "epoch": 1.3197026022304832, "percentage": 59.33, "elapsed_time": "3:01:25", "remaining_time": "2:04:20"}
|
| 182 |
-
{"current_steps": 179, "total_steps": 300, "loss": 0.009668141603469849, "lr": 7.490103469356513e-06, "epoch": 1.3271375464684014, "percentage": 59.67, "elapsed_time": "3:02:29", "remaining_time": "2:03:21"}
|
| 183 |
-
{"current_steps": 180, "total_steps": 300, "loss": 0.05012731999158859, "lr": 7.385749028978347e-06, "epoch": 1.3345724907063197, "percentage": 60.0, "elapsed_time": "3:03:32", "remaining_time": "2:02:21"}
|
| 184 |
-
{"current_steps": 181, "total_steps": 300, "loss": 0.030221598222851753, "lr": 7.2816992776365714e-06, "epoch": 1.342007434944238, "percentage": 60.33, "elapsed_time": "3:04:31", "remaining_time": "2:01:18"}
|
| 185 |
-
{"current_steps": 182, "total_steps": 300, "loss": 0.006099697668105364, "lr": 7.1779663422535235e-06, "epoch": 1.3494423791821561, "percentage": 60.67, "elapsed_time": "3:05:32", "remaining_time": "2:00:18"}
|
| 186 |
-
{"current_steps": 183, "total_steps": 300, "loss": 0.007234757766127586, "lr": 7.0745623128268605e-06, "epoch": 1.3568773234200744, "percentage": 61.0, "elapsed_time": "3:06:35", "remaining_time": "1:59:17"}
|
| 187 |
-
{"current_steps": 184, "total_steps": 300, "loss": 0.03112523816525936, "lr": 6.971499241020495e-06, "epoch": 1.3643122676579926, "percentage": 61.33, "elapsed_time": "3:07:40", "remaining_time": "1:58:19"}
|
| 188 |
-
{"current_steps": 185, "total_steps": 300, "loss": 0.0031025242060422897, "lr": 6.868789138759977e-06, "epoch": 1.3717472118959106, "percentage": 61.67, "elapsed_time": "3:08:40", "remaining_time": "1:57:16"}
|
| 189 |
-
{"current_steps": 186, "total_steps": 300, "loss": 0.00931456033140421, "lr": 6.766443976832518e-06, "epoch": 1.379182156133829, "percentage": 62.0, "elapsed_time": "3:09:42", "remaining_time": "1:56:16"}
|
| 190 |
-
{"current_steps": 187, "total_steps": 300, "loss": 0.006034584250301123, "lr": 6.664475683491797e-06, "epoch": 1.3866171003717471, "percentage": 62.33, "elapsed_time": "3:10:43", "remaining_time": "1:55:15"}
|
| 191 |
-
{"current_steps": 188, "total_steps": 300, "loss": 0.011754708364605904, "lr": 6.562896143067734e-06, "epoch": 1.3940520446096654, "percentage": 62.67, "elapsed_time": "3:11:48", "remaining_time": "1:54:15"}
|
| 192 |
-
{"current_steps": 189, "total_steps": 300, "loss": 0.0026434683240950108, "lr": 6.461717194581394e-06, "epoch": 1.4014869888475836, "percentage": 63.0, "elapsed_time": "3:12:48", "remaining_time": "1:53:13"}
|
| 193 |
-
{"current_steps": 190, "total_steps": 300, "loss": 0.00918147899210453, "lr": 6.360950630365126e-06, "epoch": 1.4089219330855018, "percentage": 63.33, "elapsed_time": "3:13:46", "remaining_time": "1:52:11"}
|
| 194 |
-
{"current_steps": 191, "total_steps": 300, "loss": 0.005454449914395809, "lr": 6.260608194688207e-06, "epoch": 1.41635687732342, "percentage": 63.67, "elapsed_time": "3:14:47", "remaining_time": "1:51:09"}
|
| 195 |
-
{"current_steps": 192, "total_steps": 300, "loss": 0.019059546291828156, "lr": 6.160701582388039e-06, "epoch": 1.4237918215613383, "percentage": 64.0, "elapsed_time": "3:15:54", "remaining_time": "1:50:11"}
|
| 196 |
-
{"current_steps": 193, "total_steps": 300, "loss": 0.004893932491540909, "lr": 6.061242437507131e-06, "epoch": 1.4312267657992566, "percentage": 64.33, "elapsed_time": "3:16:54", "remaining_time": "1:49:09"}
|
| 197 |
-
{"current_steps": 194, "total_steps": 300, "loss": 0.0030322109814733267, "lr": 5.962242351935985e-06, "epoch": 1.4386617100371748, "percentage": 64.67, "elapsed_time": "3:17:50", "remaining_time": "1:48:05"}
|
| 198 |
-
{"current_steps": 195, "total_steps": 300, "loss": 0.0014967583119869232, "lr": 5.863712864062089e-06, "epoch": 1.446096654275093, "percentage": 65.0, "elapsed_time": "3:18:50", "remaining_time": "1:47:03"}
|
| 199 |
-
{"current_steps": 196, "total_steps": 300, "loss": 0.0014030743623152375, "lr": 5.765665457425102e-06, "epoch": 1.453531598513011, "percentage": 65.33, "elapsed_time": "3:19:51", "remaining_time": "1:46:02"}
|
| 200 |
-
{"current_steps": 197, "total_steps": 300, "loss": 0.0031558023765683174, "lr": 5.6681115593784705e-06, "epoch": 1.4609665427509293, "percentage": 65.67, "elapsed_time": "3:20:50", "remaining_time": "1:45:00"}
|
| 201 |
-
{"current_steps": 198, "total_steps": 300, "loss": 0.0015127082588151097, "lr": 5.571062539757582e-06, "epoch": 1.4684014869888475, "percentage": 66.0, "elapsed_time": "3:21:52", "remaining_time": "1:44:00"}
|
| 202 |
-
{"current_steps": 199, "total_steps": 300, "loss": 0.0025897377636283636, "lr": 5.4745297095546125e-06, "epoch": 1.4758364312267658, "percentage": 66.33, "elapsed_time": "3:22:57", "remaining_time": "1:43:00"}
|
| 203 |
-
{"current_steps": 200, "total_steps": 300, "loss": 0.05572836101055145, "lr": 5.378524319600231e-06, "epoch": 1.483271375464684, "percentage": 66.67, "elapsed_time": "3:24:01", "remaining_time": "1:42:00"}
|
| 204 |
-
{"current_steps": 200, "total_steps": 300, "eval_loss": 0.00345331197604537, "epoch": 1.483271375464684, "percentage": 66.67, "elapsed_time": "3:24:27", "remaining_time": "1:42:13"}
|
| 205 |
-
{"current_steps": 201, "total_steps": 300, "loss": 0.008380255661904812, "lr": 5.2830575592523415e-06, "epoch": 1.4907063197026023, "percentage": 67.0, "elapsed_time": "3:25:32", "remaining_time": "1:41:14"}
|
| 206 |
-
{"current_steps": 202, "total_steps": 300, "loss": 0.00754923652857542, "lr": 5.18814055509195e-06, "epoch": 1.4981412639405205, "percentage": 67.33, "elapsed_time": "3:26:36", "remaining_time": "1:40:14"}
|
| 207 |
-
{"current_steps": 203, "total_steps": 300, "loss": 0.0010725234169512987, "lr": 5.093784369626397e-06, "epoch": 1.5055762081784385, "percentage": 67.67, "elapsed_time": "3:27:34", "remaining_time": "1:39:11"}
|
| 208 |
-
{"current_steps": 204, "total_steps": 300, "loss": 0.004665295593440533, "lr": 5.000000000000003e-06, "epoch": 1.513011152416357, "percentage": 68.0, "elapsed_time": "3:28:38", "remaining_time": "1:38:11"}
|
| 209 |
-
{"current_steps": 205, "total_steps": 300, "loss": 0.0016852637054398656, "lr": 4.9067983767123736e-06, "epoch": 1.520446096654275, "percentage": 68.33, "elapsed_time": "3:29:42", "remaining_time": "1:37:10"}
|
| 210 |
-
{"current_steps": 206, "total_steps": 300, "loss": 0.025673305615782738, "lr": 4.814190362344454e-06, "epoch": 1.5278810408921935, "percentage": 68.67, "elapsed_time": "3:30:41", "remaining_time": "1:36:08"}
|
| 211 |
-
{"current_steps": 207, "total_steps": 300, "loss": 0.0010814513079822063, "lr": 4.722186750292511e-06, "epoch": 1.5353159851301115, "percentage": 69.0, "elapsed_time": "3:31:48", "remaining_time": "1:35:09"}
|
| 212 |
-
{"current_steps": 208, "total_steps": 300, "loss": 0.002239473396912217, "lr": 4.630798263510162e-06, "epoch": 1.5427509293680297, "percentage": 69.33, "elapsed_time": "3:32:45", "remaining_time": "1:34:06"}
|
| 213 |
-
{"current_steps": 209, "total_steps": 300, "loss": 0.005386807024478912, "lr": 4.54003555325862e-06, "epoch": 1.550185873605948, "percentage": 69.67, "elapsed_time": "3:33:39", "remaining_time": "1:33:01"}
|
| 214 |
-
{"current_steps": 210, "total_steps": 300, "loss": 0.004140175879001617, "lr": 4.449909197865303e-06, "epoch": 1.5576208178438662, "percentage": 70.0, "elapsed_time": "3:34:41", "remaining_time": "1:32:00"}
|
| 215 |
-
{"current_steps": 211, "total_steps": 300, "loss": 0.004319075495004654, "lr": 4.360429701490935e-06, "epoch": 1.5650557620817844, "percentage": 70.33, "elapsed_time": "3:35:45", "remaining_time": "1:31:00"}
|
| 216 |
-
{"current_steps": 212, "total_steps": 300, "loss": 0.0016975726466625929, "lr": 4.271607492905303e-06, "epoch": 1.5724907063197024, "percentage": 70.67, "elapsed_time": "3:36:46", "remaining_time": "1:29:58"}
|
| 217 |
-
{"current_steps": 213, "total_steps": 300, "loss": 0.0005350559949874878, "lr": 4.183452924271776e-06, "epoch": 1.579925650557621, "percentage": 71.0, "elapsed_time": "3:37:47", "remaining_time": "1:28:57"}
|
| 218 |
-
{"current_steps": 214, "total_steps": 300, "loss": 0.002190855098888278, "lr": 4.095976269940777e-06, "epoch": 1.587360594795539, "percentage": 71.33, "elapsed_time": "3:38:51", "remaining_time": "1:27:57"}
|
| 219 |
-
{"current_steps": 215, "total_steps": 300, "loss": 0.0012900492874905467, "lr": 4.009187725252309e-06, "epoch": 1.5947955390334574, "percentage": 71.67, "elapsed_time": "3:39:51", "remaining_time": "1:26:55"}
|
| 220 |
-
{"current_steps": 216, "total_steps": 300, "loss": 0.0025745758321136236, "lr": 3.923097405347709e-06, "epoch": 1.6022304832713754, "percentage": 72.0, "elapsed_time": "3:40:52", "remaining_time": "1:25:53"}
|
| 221 |
-
{"current_steps": 217, "total_steps": 300, "loss": 0.0015018703415989876, "lr": 3.837715343990727e-06, "epoch": 1.6096654275092936, "percentage": 72.33, "elapsed_time": "3:41:48", "remaining_time": "1:24:50"}
|
| 222 |
-
{"current_steps": 218, "total_steps": 300, "loss": 0.001234126859344542, "lr": 3.753051492398089e-06, "epoch": 1.6171003717472119, "percentage": 72.67, "elapsed_time": "3:42:49", "remaining_time": "1:23:48"}
|
| 223 |
-
{"current_steps": 219, "total_steps": 300, "loss": 0.0005210964009165764, "lr": 3.669115718079702e-06, "epoch": 1.6245353159851301, "percentage": 73.0, "elapsed_time": "3:43:51", "remaining_time": "1:22:47"}
|
| 224 |
-
{"current_steps": 220, "total_steps": 300, "loss": 0.002871165983378887, "lr": 3.585917803688603e-06, "epoch": 1.6319702602230484, "percentage": 73.33, "elapsed_time": "3:44:50", "remaining_time": "1:21:45"}
|
| 225 |
-
{"current_steps": 221, "total_steps": 300, "loss": 0.007808375637978315, "lr": 3.5034674458807893e-06, "epoch": 1.6394052044609664, "percentage": 73.67, "elapsed_time": "3:45:52", "remaining_time": "1:20:44"}
|
| 226 |
-
{"current_steps": 222, "total_steps": 300, "loss": 0.0021337075158953667, "lr": 3.421774254185096e-06, "epoch": 1.6468401486988848, "percentage": 74.0, "elapsed_time": "3:46:57", "remaining_time": "1:19:44"}
|
| 227 |
-
{"current_steps": 223, "total_steps": 300, "loss": 0.00113480887375772, "lr": 3.3408477498831917e-06, "epoch": 1.6542750929368029, "percentage": 74.33, "elapsed_time": "3:47:57", "remaining_time": "1:18:42"}
|
| 228 |
-
{"current_steps": 224, "total_steps": 300, "loss": 0.0014634067192673683, "lr": 3.2606973648998918e-06, "epoch": 1.6617100371747213, "percentage": 74.67, "elapsed_time": "3:48:54", "remaining_time": "1:17:39"}
|
| 229 |
-
{"current_steps": 225, "total_steps": 300, "loss": 0.0005495938239619136, "lr": 3.1813324407038826e-06, "epoch": 1.6691449814126393, "percentage": 75.0, "elapsed_time": "3:49:47", "remaining_time": "1:16:35"}
|
| 230 |
-
{"current_steps": 226, "total_steps": 300, "loss": 0.0010474955197423697, "lr": 3.1027622272189572e-06, "epoch": 1.6765799256505576, "percentage": 75.33, "elapsed_time": "3:50:48", "remaining_time": "1:15:34"}
|
| 231 |
-
{"current_steps": 227, "total_steps": 300, "loss": 0.0005706051597371697, "lr": 3.024995881745972e-06, "epoch": 1.6840148698884758, "percentage": 75.67, "elapsed_time": "3:51:47", "remaining_time": "1:14:32"}
|
| 232 |
-
{"current_steps": 228, "total_steps": 300, "loss": 0.0005536235403269529, "lr": 2.948042467895544e-06, "epoch": 1.691449814126394, "percentage": 76.0, "elapsed_time": "3:52:44", "remaining_time": "1:13:29"}
|
| 233 |
-
{"current_steps": 229, "total_steps": 300, "loss": 0.0010236221132799983, "lr": 2.8719109545317102e-06, "epoch": 1.6988847583643123, "percentage": 76.33, "elapsed_time": "3:53:43", "remaining_time": "1:12:27"}
|
| 234 |
-
{"current_steps": 230, "total_steps": 300, "loss": 0.0007985785487107933, "lr": 2.7966102147265993e-06, "epoch": 1.7063197026022305, "percentage": 76.67, "elapsed_time": "3:54:42", "remaining_time": "1:11:26"}
|
| 235 |
-
{"current_steps": 231, "total_steps": 300, "loss": 0.0009809861658141017, "lr": 2.722149024726307e-06, "epoch": 1.7137546468401488, "percentage": 77.0, "elapsed_time": "3:55:36", "remaining_time": "1:10:22"}
|
| 236 |
-
{"current_steps": 232, "total_steps": 300, "loss": 0.001332507818005979, "lr": 2.648536062927999e-06, "epoch": 1.7211895910780668, "percentage": 77.33, "elapsed_time": "3:56:36", "remaining_time": "1:09:20"}
|
| 237 |
-
{"current_steps": 233, "total_steps": 300, "loss": 0.0014440901577472687, "lr": 2.5757799088684654e-06, "epoch": 1.7286245353159853, "percentage": 77.67, "elapsed_time": "3:57:41", "remaining_time": "1:08:20"}
|
| 238 |
-
{"current_steps": 234, "total_steps": 300, "loss": 0.0013162668328732252, "lr": 2.5038890422241958e-06, "epoch": 1.7360594795539033, "percentage": 78.0, "elapsed_time": "3:58:41", "remaining_time": "1:07:19"}
|
| 239 |
-
{"current_steps": 235, "total_steps": 300, "loss": 0.0006657422054558992, "lr": 2.432871841823047e-06, "epoch": 1.7434944237918215, "percentage": 78.33, "elapsed_time": "3:59:41", "remaining_time": "1:06:17"}
|
| 240 |
-
{"current_steps": 236, "total_steps": 300, "loss": 0.0005915165529586375, "lr": 2.362736584667731e-06, "epoch": 1.7509293680297398, "percentage": 78.67, "elapsed_time": "4:00:40", "remaining_time": "1:05:16"}
|
| 241 |
-
{"current_steps": 237, "total_steps": 300, "loss": 0.0014591675717383623, "lr": 2.293491444971109e-06, "epoch": 1.758364312267658, "percentage": 79.0, "elapsed_time": "4:01:48", "remaining_time": "1:04:16"}
|
| 242 |
-
{"current_steps": 238, "total_steps": 300, "loss": 0.001061687944456935, "lr": 2.2251444932035094e-06, "epoch": 1.7657992565055762, "percentage": 79.33, "elapsed_time": "4:02:52", "remaining_time": "1:03:16"}
|
| 243 |
-
{"current_steps": 239, "total_steps": 300, "loss": 0.001086688251234591, "lr": 2.157703695152109e-06, "epoch": 1.7732342007434945, "percentage": 79.67, "elapsed_time": "4:04:00", "remaining_time": "1:02:16"}
|
| 244 |
-
{"current_steps": 240, "total_steps": 300, "loss": 0.0005726361414417624, "lr": 2.091176910992545e-06, "epoch": 1.7806691449814127, "percentage": 80.0, "elapsed_time": "4:05:03", "remaining_time": "1:01:15"}
|
| 245 |
-
{"current_steps": 241, "total_steps": 300, "loss": 0.0005661951145157218, "lr": 2.025571894372794e-06, "epoch": 1.7881040892193307, "percentage": 80.33, "elapsed_time": "4:06:04", "remaining_time": "1:00:14"}
|
| 246 |
-
{"current_steps": 242, "total_steps": 300, "loss": 0.00041253669769503176, "lr": 1.9608962915095e-06, "epoch": 1.7955390334572492, "percentage": 80.67, "elapsed_time": "4:07:01", "remaining_time": "0:59:12"}
|
| 247 |
-
{"current_steps": 243, "total_steps": 300, "loss": 0.0005594079266302288, "lr": 1.897157640296825e-06, "epoch": 1.8029739776951672, "percentage": 81.0, "elapsed_time": "4:08:01", "remaining_time": "0:58:10"}
|
| 248 |
-
{"current_steps": 244, "total_steps": 300, "loss": 0.0004925344837829471, "lr": 1.8343633694278895e-06, "epoch": 1.8104089219330854, "percentage": 81.33, "elapsed_time": "4:09:05", "remaining_time": "0:57:10"}
|
| 249 |
-
{"current_steps": 245, "total_steps": 300, "loss": 0.0007212568307295442, "lr": 1.7725207975289883e-06, "epoch": 1.8178438661710037, "percentage": 81.67, "elapsed_time": "4:10:03", "remaining_time": "0:56:08"}
|
| 250 |
-
{"current_steps": 246, "total_steps": 300, "loss": 0.0008221275638788939, "lr": 1.7116371323065883e-06, "epoch": 1.825278810408922, "percentage": 82.0, "elapsed_time": "4:11:07", "remaining_time": "0:55:07"}
|
| 251 |
-
{"current_steps": 247, "total_steps": 300, "loss": 0.0011635192204266787, "lr": 1.6517194697072903e-06, "epoch": 1.8327137546468402, "percentage": 82.33, "elapsed_time": "4:12:12", "remaining_time": "0:54:07"}
|
| 252 |
-
{"current_steps": 248, "total_steps": 300, "loss": 0.0005840228404849768, "lr": 1.5927747930907921e-06, "epoch": 1.8401486988847584, "percentage": 82.67, "elapsed_time": "4:13:09", "remaining_time": "0:53:04"}
|
| 253 |
-
{"current_steps": 249, "total_steps": 300, "loss": 0.0008757053292356431, "lr": 1.534809972415998e-06, "epoch": 1.8475836431226766, "percentage": 83.0, "elapsed_time": "4:14:07", "remaining_time": "0:52:02"}
|
| 254 |
-
{"current_steps": 250, "total_steps": 300, "loss": 0.0006142967031337321, "lr": 1.4778317634403082e-06, "epoch": 1.8550185873605947, "percentage": 83.33, "elapsed_time": "4:15:01", "remaining_time": "0:51:00"}
|
| 255 |
-
{"current_steps": 250, "total_steps": 300, "eval_loss": 0.0005828889552503824, "epoch": 1.8550185873605947, "percentage": 83.33, "elapsed_time": "4:15:27", "remaining_time": "0:51:05"}
|
| 256 |
-
{"current_steps": 251, "total_steps": 300, "loss": 0.0005684165516868234, "lr": 1.4218468069322576e-06, "epoch": 1.8624535315985131, "percentage": 83.67, "elapsed_time": "4:16:22", "remaining_time": "0:50:02"}
|
| 257 |
-
{"current_steps": 252, "total_steps": 300, "loss": 0.0006938453880138695, "lr": 1.3668616278975343e-06, "epoch": 1.8698884758364311, "percentage": 84.0, "elapsed_time": "4:17:26", "remaining_time": "0:49:02"}
|
| 258 |
-
{"current_steps": 253, "total_steps": 300, "loss": 0.0008722958737052977, "lr": 1.3128826348184886e-06, "epoch": 1.8773234200743496, "percentage": 84.33, "elapsed_time": "4:18:31", "remaining_time": "0:48:01"}
|
| 259 |
-
{"current_steps": 254, "total_steps": 300, "loss": 0.0004048564878758043, "lr": 1.2599161189072428e-06, "epoch": 1.8847583643122676, "percentage": 84.67, "elapsed_time": "4:19:38", "remaining_time": "0:47:01"}
|
| 260 |
-
{"current_steps": 255, "total_steps": 300, "loss": 0.0004900405765511096, "lr": 1.207968253372438e-06, "epoch": 1.8921933085501859, "percentage": 85.0, "elapsed_time": "4:20:41", "remaining_time": "0:46:00"}
|
| 261 |
-
{"current_steps": 256, "total_steps": 300, "loss": 0.00596074853092432, "lr": 1.1570450926997657e-06, "epoch": 1.899628252788104, "percentage": 85.33, "elapsed_time": "4:21:47", "remaining_time": "0:44:59"}
|
| 262 |
-
{"current_steps": 257, "total_steps": 300, "loss": 0.003298816503956914, "lr": 1.1071525719463094e-06, "epoch": 1.9070631970260223, "percentage": 85.67, "elapsed_time": "4:22:54", "remaining_time": "0:43:59"}
|
| 263 |
-
{"current_steps": 258, "total_steps": 300, "loss": 0.0005693072453141212, "lr": 1.058296506048836e-06, "epoch": 1.9144981412639406, "percentage": 86.0, "elapsed_time": "4:23:55", "remaining_time": "0:42:57"}
|
| 264 |
-
{"current_steps": 259, "total_steps": 300, "loss": 0.0003265823470428586, "lr": 1.010482589146048e-06, "epoch": 1.9219330855018586, "percentage": 86.33, "elapsed_time": "4:25:02", "remaining_time": "0:41:57"}
|
| 265 |
-
{"current_steps": 260, "total_steps": 300, "loss": 0.00038790475809946656, "lr": 9.637163939149485e-07, "epoch": 1.929368029739777, "percentage": 86.67, "elapsed_time": "4:26:07", "remaining_time": "0:40:56"}
|
| 266 |
-
{"current_steps": 261, "total_steps": 300, "loss": 0.000698139367159456, "lr": 9.180033709213454e-07, "epoch": 1.936802973977695, "percentage": 87.0, "elapsed_time": "4:27:08", "remaining_time": "0:39:55"}
|
| 267 |
-
{"current_steps": 262, "total_steps": 300, "loss": 0.00024097770801745355, "lr": 8.733488479845997e-07, "epoch": 1.9442379182156135, "percentage": 87.33, "elapsed_time": "4:28:05", "remaining_time": "0:38:53"}
|
| 268 |
-
{"current_steps": 263, "total_steps": 300, "loss": 0.0003770535986404866, "lr": 8.297580295566576e-07, "epoch": 1.9516728624535316, "percentage": 87.67, "elapsed_time": "4:29:08", "remaining_time": "0:37:51"}
|
| 269 |
-
{"current_steps": 264, "total_steps": 300, "loss": 0.0005116399261169136, "lr": 7.872359961154907e-07, "epoch": 1.9591078066914498, "percentage": 88.0, "elapsed_time": "4:30:03", "remaining_time": "0:36:49"}
|
| 270 |
-
{"current_steps": 265, "total_steps": 300, "loss": 0.00033355015330016613, "lr": 7.457877035729588e-07, "epoch": 1.966542750929368, "percentage": 88.33, "elapsed_time": "4:31:01", "remaining_time": "0:35:47"}
|
| 271 |
-
{"current_steps": 266, "total_steps": 300, "loss": 0.0005097900284454226, "lr": 7.054179826972074e-07, "epoch": 1.9739776951672863, "percentage": 88.67, "elapsed_time": "4:32:07", "remaining_time": "0:34:47"}
|
| 272 |
-
{"current_steps": 267, "total_steps": 300, "loss": 0.0005295310402289033, "lr": 6.661315385496426e-07, "epoch": 1.9814126394052045, "percentage": 89.0, "elapsed_time": "4:33:12", "remaining_time": "0:33:46"}
|
| 273 |
-
{"current_steps": 268, "total_steps": 300, "loss": 0.000684445898514241, "lr": 6.279329499365649e-07, "epoch": 1.9888475836431225, "percentage": 89.33, "elapsed_time": "4:34:04", "remaining_time": "0:32:43"}
|
| 274 |
-
{"current_steps": 269, "total_steps": 300, "loss": 0.0006487981881946325, "lr": 5.908266688755049e-07, "epoch": 1.996282527881041, "percentage": 89.67, "elapsed_time": "4:35:05", "remaining_time": "0:31:42"}
|
| 275 |
-
{"current_steps": 270, "total_steps": 300, "loss": 0.0005617543356493115, "lr": 5.54817020076347e-07, "epoch": 2.0, "percentage": 90.0, "elapsed_time": "4:35:36", "remaining_time": "0:30:37"}
|
| 276 |
-
{"current_steps": 271, "total_steps": 300, "loss": 0.0002831058227457106, "lr": 5.199082004372958e-07, "epoch": 2.007434944237918, "percentage": 90.33, "elapsed_time": "4:36:33", "remaining_time": "0:29:35"}
|
| 277 |
-
{"current_steps": 272, "total_steps": 300, "loss": 0.00032035651383921504, "lr": 4.861042785557147e-07, "epoch": 2.0148698884758365, "percentage": 90.67, "elapsed_time": "4:37:36", "remaining_time": "0:28:34"}
|
| 278 |
-
{"current_steps": 273, "total_steps": 300, "loss": 0.0003928366641048342, "lr": 4.534091942539476e-07, "epoch": 2.0223048327137545, "percentage": 91.0, "elapsed_time": "4:38:38", "remaining_time": "0:27:33"}
|
| 279 |
-
{"current_steps": 274, "total_steps": 300, "loss": 0.00045185262570157647, "lr": 4.218267581201296e-07, "epoch": 2.029739776951673, "percentage": 91.33, "elapsed_time": "4:39:44", "remaining_time": "0:26:32"}
|
| 280 |
-
{"current_steps": 275, "total_steps": 300, "loss": 0.0003131507837679237, "lr": 3.913606510640644e-07, "epoch": 2.037174721189591, "percentage": 91.67, "elapsed_time": "4:40:43", "remaining_time": "0:25:31"}
|
| 281 |
-
{"current_steps": 276, "total_steps": 300, "loss": 0.0007142139365896583, "lr": 3.620144238882206e-07, "epoch": 2.0446096654275094, "percentage": 92.0, "elapsed_time": "4:41:48", "remaining_time": "0:24:30"}
|
| 282 |
-
{"current_steps": 277, "total_steps": 300, "loss": 0.0004891973803751171, "lr": 3.3379149687388866e-07, "epoch": 2.0520446096654275, "percentage": 92.33, "elapsed_time": "4:42:49", "remaining_time": "0:23:29"}
|
| 283 |
-
{"current_steps": 278, "total_steps": 300, "loss": 0.00264157191850245, "lr": 3.0669515938254404e-07, "epoch": 2.059479553903346, "percentage": 92.67, "elapsed_time": "4:43:50", "remaining_time": "0:22:27"}
|
| 284 |
-
{"current_steps": 279, "total_steps": 300, "loss": 0.0003561996854841709, "lr": 2.807285694724804e-07, "epoch": 2.066914498141264, "percentage": 93.0, "elapsed_time": "4:44:48", "remaining_time": "0:21:26"}
|
| 285 |
-
{"current_steps": 280, "total_steps": 300, "loss": 0.0004683621518779546, "lr": 2.5589475353073987e-07, "epoch": 2.074349442379182, "percentage": 93.33, "elapsed_time": "4:45:47", "remaining_time": "0:20:24"}
|
| 286 |
-
{"current_steps": 281, "total_steps": 300, "loss": 0.00034518816391937435, "lr": 2.3219660592038285e-07, "epoch": 2.0817843866171004, "percentage": 93.67, "elapsed_time": "4:46:52", "remaining_time": "0:19:23"}
|
| 287 |
-
{"current_steps": 282, "total_steps": 300, "loss": 0.00025010405806824565, "lr": 2.0963688864316324e-07, "epoch": 2.0892193308550184, "percentage": 94.0, "elapsed_time": "4:47:54", "remaining_time": "0:18:22"}
|
| 288 |
-
{"current_steps": 283, "total_steps": 300, "loss": 0.0003774496726691723, "lr": 1.8821823101760949e-07, "epoch": 2.096654275092937, "percentage": 94.33, "elapsed_time": "4:48:53", "remaining_time": "0:17:21"}
|
| 289 |
-
{"current_steps": 284, "total_steps": 300, "loss": 0.00038810307160019875, "lr": 1.6794312937258417e-07, "epoch": 2.104089219330855, "percentage": 94.67, "elapsed_time": "4:49:51", "remaining_time": "0:16:19"}
|
| 290 |
-
{"current_steps": 285, "total_steps": 300, "loss": 0.00043630838626995683, "lr": 1.4881394675633543e-07, "epoch": 2.1115241635687734, "percentage": 95.0, "elapsed_time": "4:50:54", "remaining_time": "0:15:18"}
|
| 291 |
-
{"current_steps": 286, "total_steps": 300, "loss": 0.0002762812946457416, "lr": 1.30832912661093e-07, "epoch": 2.1189591078066914, "percentage": 95.33, "elapsed_time": "4:52:01", "remaining_time": "0:14:17"}
|
| 292 |
-
{"current_steps": 287, "total_steps": 300, "loss": 0.0004420560726430267, "lr": 1.1400212276321377e-07, "epoch": 2.12639405204461, "percentage": 95.67, "elapsed_time": "4:52:59", "remaining_time": "0:13:16"}
|
| 293 |
-
{"current_steps": 288, "total_steps": 300, "loss": 0.00048654654528945684, "lr": 9.832353867893385e-08, "epoch": 2.133828996282528, "percentage": 96.0, "elapsed_time": "4:53:58", "remaining_time": "0:12:14"}
|
| 294 |
-
{"current_steps": 289, "total_steps": 300, "loss": 0.0005200268933549523, "lr": 8.379898773574924e-08, "epoch": 2.141263940520446, "percentage": 96.33, "elapsed_time": "4:55:03", "remaining_time": "0:11:13"}
|
| 295 |
-
{"current_steps": 290, "total_steps": 300, "loss": 0.0003803567960858345, "lr": 7.043016275943614e-08, "epoch": 2.1486988847583643, "percentage": 96.67, "elapsed_time": "4:56:09", "remaining_time": "0:10:12"}
|
| 296 |
-
{"current_steps": 291, "total_steps": 300, "loss": 0.0005831126472912729, "lr": 5.821862187675775e-08, "epoch": 2.1561338289962824, "percentage": 97.0, "elapsed_time": "4:57:02", "remaining_time": "0:09:11"}
|
| 297 |
-
{"current_steps": 292, "total_steps": 300, "loss": 0.00043936495785601437, "lr": 4.716578833386054e-08, "epoch": 2.163568773234201, "percentage": 97.33, "elapsed_time": "4:58:03", "remaining_time": "0:08:09"}
|
| 298 |
-
{"current_steps": 293, "total_steps": 300, "loss": 0.000401977333240211, "lr": 3.727295033040035e-08, "epoch": 2.171003717472119, "percentage": 97.67, "elapsed_time": "4:59:07", "remaining_time": "0:07:08"}
|
| 299 |
-
{"current_steps": 294, "total_steps": 300, "loss": 0.0002383627142990008, "lr": 2.8541260869403565e-08, "epoch": 2.1784386617100373, "percentage": 98.0, "elapsed_time": "5:00:05", "remaining_time": "0:06:07"}
|
| 300 |
-
{"current_steps": 295, "total_steps": 300, "loss": 0.000635640521068126, "lr": 2.0971737622883515e-08, "epoch": 2.1858736059479553, "percentage": 98.33, "elapsed_time": "5:01:05", "remaining_time": "0:05:06"}
|
| 301 |
-
{"current_steps": 296, "total_steps": 300, "loss": 0.00035777079756371677, "lr": 1.4565262813230896e-08, "epoch": 2.193308550185874, "percentage": 98.67, "elapsed_time": "5:02:00", "remaining_time": "0:04:04"}
|
| 302 |
-
{"current_steps": 297, "total_steps": 300, "loss": 0.0003764816792681813, "lr": 9.322583110392692e-09, "epoch": 2.200743494423792, "percentage": 99.0, "elapsed_time": "5:03:04", "remaining_time": "0:03:03"}
|
| 303 |
-
{"current_steps": 298, "total_steps": 300, "loss": 0.0005360089126043022, "lr": 5.2443095448506674e-09, "epoch": 2.20817843866171, "percentage": 99.33, "elapsed_time": "5:04:08", "remaining_time": "0:02:02"}
|
| 304 |
-
{"current_steps": 299, "total_steps": 300, "loss": 0.000445480109192431, "lr": 2.330917436402791e-09, "epoch": 2.2156133828996283, "percentage": 99.67, "elapsed_time": "5:05:04", "remaining_time": "0:01:01"}
|
| 305 |
-
{"current_steps": 300, "total_steps": 300, "loss": 0.0004715001559816301, "lr": 5.827463387653165e-10, "epoch": 2.2230483271375463, "percentage": 100.0, "elapsed_time": "5:06:08", "remaining_time": "0:00:00"}
|
| 306 |
-
{"current_steps": 300, "total_steps": 300, "eval_loss": 0.0005094278603792191, "epoch": 2.2230483271375463, "percentage": 100.0, "elapsed_time": "5:06:33", "remaining_time": "0:00:00"}
|
| 307 |
-
{"current_steps": 300, "total_steps": 300, "epoch": 2.2230483271375463, "percentage": 100.0, "elapsed_time": "5:06:36", "remaining_time": "0:00:00"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
trainer_state.json
DELETED
|
@@ -1,2191 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 2.2230483271375463,
|
| 6 |
-
"eval_steps": 50,
|
| 7 |
-
"global_step": 300,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.007434944237918215,
|
| 14 |
-
"grad_norm": 25.154041290283203,
|
| 15 |
-
"learning_rate": 0.0,
|
| 16 |
-
"loss": 3.987701892852783,
|
| 17 |
-
"step": 1
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.01486988847583643,
|
| 21 |
-
"grad_norm": 32.74612808227539,
|
| 22 |
-
"learning_rate": 2.222222222222222e-06,
|
| 23 |
-
"loss": 4.61507511138916,
|
| 24 |
-
"step": 2
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.022304832713754646,
|
| 28 |
-
"grad_norm": 27.67908477783203,
|
| 29 |
-
"learning_rate": 4.444444444444444e-06,
|
| 30 |
-
"loss": 4.111183166503906,
|
| 31 |
-
"step": 3
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.02973977695167286,
|
| 35 |
-
"grad_norm": 33.00176239013672,
|
| 36 |
-
"learning_rate": 6.666666666666667e-06,
|
| 37 |
-
"loss": 3.9212229251861572,
|
| 38 |
-
"step": 4
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.03717472118959108,
|
| 42 |
-
"grad_norm": 32.0166015625,
|
| 43 |
-
"learning_rate": 8.888888888888888e-06,
|
| 44 |
-
"loss": 4.2523193359375,
|
| 45 |
-
"step": 5
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.04460966542750929,
|
| 49 |
-
"grad_norm": 22.236347198486328,
|
| 50 |
-
"learning_rate": 1.1111111111111113e-05,
|
| 51 |
-
"loss": 3.648789167404175,
|
| 52 |
-
"step": 6
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.05204460966542751,
|
| 56 |
-
"grad_norm": 19.99039077758789,
|
| 57 |
-
"learning_rate": 1.3333333333333333e-05,
|
| 58 |
-
"loss": 3.7300028800964355,
|
| 59 |
-
"step": 7
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 0.05947955390334572,
|
| 63 |
-
"grad_norm": 10.491039276123047,
|
| 64 |
-
"learning_rate": 1.555555555555556e-05,
|
| 65 |
-
"loss": 2.775282621383667,
|
| 66 |
-
"step": 8
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 0.06691449814126393,
|
| 70 |
-
"grad_norm": 11.603081703186035,
|
| 71 |
-
"learning_rate": 1.7777777777777777e-05,
|
| 72 |
-
"loss": 2.708098888397217,
|
| 73 |
-
"step": 9
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 0.07434944237918216,
|
| 77 |
-
"grad_norm": 7.7384562492370605,
|
| 78 |
-
"learning_rate": 2e-05,
|
| 79 |
-
"loss": 2.5016918182373047,
|
| 80 |
-
"step": 10
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.08178438661710037,
|
| 84 |
-
"grad_norm": 6.404298305511475,
|
| 85 |
-
"learning_rate": 1.9999417253661235e-05,
|
| 86 |
-
"loss": 2.194194793701172,
|
| 87 |
-
"step": 11
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.08921933085501858,
|
| 91 |
-
"grad_norm": 6.126753330230713,
|
| 92 |
-
"learning_rate": 1.9997669082563597e-05,
|
| 93 |
-
"loss": 2.1397340297698975,
|
| 94 |
-
"step": 12
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 0.09665427509293681,
|
| 98 |
-
"grad_norm": 6.815288066864014,
|
| 99 |
-
"learning_rate": 1.9994755690455154e-05,
|
| 100 |
-
"loss": 2.126490354537964,
|
| 101 |
-
"step": 13
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 0.10408921933085502,
|
| 105 |
-
"grad_norm": 6.371899604797363,
|
| 106 |
-
"learning_rate": 1.999067741688961e-05,
|
| 107 |
-
"loss": 2.0997183322906494,
|
| 108 |
-
"step": 14
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 0.11152416356877323,
|
| 112 |
-
"grad_norm": 5.765743255615234,
|
| 113 |
-
"learning_rate": 1.998543473718677e-05,
|
| 114 |
-
"loss": 1.8205538988113403,
|
| 115 |
-
"step": 15
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 0.11895910780669144,
|
| 119 |
-
"grad_norm": 7.067747592926025,
|
| 120 |
-
"learning_rate": 1.997902826237712e-05,
|
| 121 |
-
"loss": 1.888378620147705,
|
| 122 |
-
"step": 16
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.12639405204460966,
|
| 126 |
-
"grad_norm": 7.431400775909424,
|
| 127 |
-
"learning_rate": 1.9971458739130598e-05,
|
| 128 |
-
"loss": 1.8607885837554932,
|
| 129 |
-
"step": 17
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.13382899628252787,
|
| 133 |
-
"grad_norm": 10.6022310256958,
|
| 134 |
-
"learning_rate": 1.99627270496696e-05,
|
| 135 |
-
"loss": 1.6387686729431152,
|
| 136 |
-
"step": 18
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 0.1412639405204461,
|
| 140 |
-
"grad_norm": 5.877020835876465,
|
| 141 |
-
"learning_rate": 1.995283421166614e-05,
|
| 142 |
-
"loss": 1.459620714187622,
|
| 143 |
-
"step": 19
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 0.14869888475836432,
|
| 147 |
-
"grad_norm": 5.877013683319092,
|
| 148 |
-
"learning_rate": 1.9941781378123244e-05,
|
| 149 |
-
"loss": 1.5848277807235718,
|
| 150 |
-
"step": 20
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 0.15613382899628253,
|
| 154 |
-
"grad_norm": 6.430077075958252,
|
| 155 |
-
"learning_rate": 1.9929569837240567e-05,
|
| 156 |
-
"loss": 1.549344778060913,
|
| 157 |
-
"step": 21
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 0.16356877323420074,
|
| 161 |
-
"grad_norm": 5.693595886230469,
|
| 162 |
-
"learning_rate": 1.9916201012264255e-05,
|
| 163 |
-
"loss": 1.3735941648483276,
|
| 164 |
-
"step": 22
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 0.17100371747211895,
|
| 168 |
-
"grad_norm": 5.920788764953613,
|
| 169 |
-
"learning_rate": 1.990167646132107e-05,
|
| 170 |
-
"loss": 1.315460443496704,
|
| 171 |
-
"step": 23
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 0.17843866171003717,
|
| 175 |
-
"grad_norm": 5.601658344268799,
|
| 176 |
-
"learning_rate": 1.9885997877236788e-05,
|
| 177 |
-
"loss": 1.169264793395996,
|
| 178 |
-
"step": 24
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 0.18587360594795538,
|
| 182 |
-
"grad_norm": 6.948248386383057,
|
| 183 |
-
"learning_rate": 1.9869167087338908e-05,
|
| 184 |
-
"loss": 1.4500298500061035,
|
| 185 |
-
"step": 25
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 0.19330855018587362,
|
| 189 |
-
"grad_norm": 10.766579627990723,
|
| 190 |
-
"learning_rate": 1.9851186053243667e-05,
|
| 191 |
-
"loss": 0.9683340787887573,
|
| 192 |
-
"step": 26
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 0.20074349442379183,
|
| 196 |
-
"grad_norm": 5.798827648162842,
|
| 197 |
-
"learning_rate": 1.983205687062742e-05,
|
| 198 |
-
"loss": 1.2549272775650024,
|
| 199 |
-
"step": 27
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 0.20817843866171004,
|
| 203 |
-
"grad_norm": 7.144542694091797,
|
| 204 |
-
"learning_rate": 1.9811781768982392e-05,
|
| 205 |
-
"loss": 1.299641728401184,
|
| 206 |
-
"step": 28
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.21561338289962825,
|
| 210 |
-
"grad_norm": 5.873534679412842,
|
| 211 |
-
"learning_rate": 1.9790363111356838e-05,
|
| 212 |
-
"loss": 1.1472691297531128,
|
| 213 |
-
"step": 29
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.22304832713754646,
|
| 217 |
-
"grad_norm": 6.155928611755371,
|
| 218 |
-
"learning_rate": 1.9767803394079618e-05,
|
| 219 |
-
"loss": 1.0264108180999756,
|
| 220 |
-
"step": 30
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 0.23048327137546468,
|
| 224 |
-
"grad_norm": 5.134888172149658,
|
| 225 |
-
"learning_rate": 1.9744105246469264e-05,
|
| 226 |
-
"loss": 0.9291560053825378,
|
| 227 |
-
"step": 31
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 0.2379182156133829,
|
| 231 |
-
"grad_norm": 7.357876777648926,
|
| 232 |
-
"learning_rate": 1.971927143052752e-05,
|
| 233 |
-
"loss": 1.0158250331878662,
|
| 234 |
-
"step": 32
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 0.24535315985130113,
|
| 238 |
-
"grad_norm": 6.1326117515563965,
|
| 239 |
-
"learning_rate": 1.9693304840617456e-05,
|
| 240 |
-
"loss": 1.0452557802200317,
|
| 241 |
-
"step": 33
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 0.2527881040892193,
|
| 245 |
-
"grad_norm": 5.832793712615967,
|
| 246 |
-
"learning_rate": 1.9666208503126115e-05,
|
| 247 |
-
"loss": 1.0367774963378906,
|
| 248 |
-
"step": 34
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 0.26022304832713755,
|
| 252 |
-
"grad_norm": 7.788253307342529,
|
| 253 |
-
"learning_rate": 1.963798557611178e-05,
|
| 254 |
-
"loss": 0.986078679561615,
|
| 255 |
-
"step": 35
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 0.26765799256505574,
|
| 259 |
-
"grad_norm": 6.585196495056152,
|
| 260 |
-
"learning_rate": 1.9608639348935938e-05,
|
| 261 |
-
"loss": 1.1179544925689697,
|
| 262 |
-
"step": 36
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 0.275092936802974,
|
| 266 |
-
"grad_norm": 6.1796956062316895,
|
| 267 |
-
"learning_rate": 1.957817324187987e-05,
|
| 268 |
-
"loss": 0.859326958656311,
|
| 269 |
-
"step": 37
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 0.2825278810408922,
|
| 273 |
-
"grad_norm": 5.778043746948242,
|
| 274 |
-
"learning_rate": 1.9546590805746054e-05,
|
| 275 |
-
"loss": 1.0027873516082764,
|
| 276 |
-
"step": 38
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 0.2899628252788104,
|
| 280 |
-
"grad_norm": 5.684733867645264,
|
| 281 |
-
"learning_rate": 1.9513895721444286e-05,
|
| 282 |
-
"loss": 1.0196456909179688,
|
| 283 |
-
"step": 39
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 0.29739776951672864,
|
| 287 |
-
"grad_norm": 6.871935844421387,
|
| 288 |
-
"learning_rate": 1.9480091799562706e-05,
|
| 289 |
-
"loss": 0.7273167967796326,
|
| 290 |
-
"step": 40
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 0.3048327137546468,
|
| 294 |
-
"grad_norm": 6.154053211212158,
|
| 295 |
-
"learning_rate": 1.9445182979923657e-05,
|
| 296 |
-
"loss": 0.7274726033210754,
|
| 297 |
-
"step": 41
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 0.31226765799256506,
|
| 301 |
-
"grad_norm": 7.8968682289123535,
|
| 302 |
-
"learning_rate": 1.94091733311245e-05,
|
| 303 |
-
"loss": 1.0878797769546509,
|
| 304 |
-
"step": 42
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"epoch": 0.31970260223048325,
|
| 308 |
-
"grad_norm": 7.9655046463012695,
|
| 309 |
-
"learning_rate": 1.937206705006344e-05,
|
| 310 |
-
"loss": 1.0284857749938965,
|
| 311 |
-
"step": 43
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 0.3271375464684015,
|
| 315 |
-
"grad_norm": 9.110565185546875,
|
| 316 |
-
"learning_rate": 1.933386846145036e-05,
|
| 317 |
-
"loss": 0.8737478852272034,
|
| 318 |
-
"step": 44
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 0.3345724907063197,
|
| 322 |
-
"grad_norm": 8.593986511230469,
|
| 323 |
-
"learning_rate": 1.9294582017302797e-05,
|
| 324 |
-
"loss": 0.8448168039321899,
|
| 325 |
-
"step": 45
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 0.3420074349442379,
|
| 329 |
-
"grad_norm": 6.716855525970459,
|
| 330 |
-
"learning_rate": 1.9254212296427043e-05,
|
| 331 |
-
"loss": 0.7004423141479492,
|
| 332 |
-
"step": 46
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 0.34944237918215615,
|
| 336 |
-
"grad_norm": 6.527238368988037,
|
| 337 |
-
"learning_rate": 1.921276400388451e-05,
|
| 338 |
-
"loss": 0.6901130676269531,
|
| 339 |
-
"step": 47
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.35687732342007433,
|
| 343 |
-
"grad_norm": 8.95169734954834,
|
| 344 |
-
"learning_rate": 1.9170241970443344e-05,
|
| 345 |
-
"loss": 0.8856571316719055,
|
| 346 |
-
"step": 48
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 0.3643122676579926,
|
| 350 |
-
"grad_norm": 7.18155574798584,
|
| 351 |
-
"learning_rate": 1.9126651152015404e-05,
|
| 352 |
-
"loss": 0.8404887914657593,
|
| 353 |
-
"step": 49
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 0.37174721189591076,
|
| 357 |
-
"grad_norm": 6.580371856689453,
|
| 358 |
-
"learning_rate": 1.9081996629078655e-05,
|
| 359 |
-
"loss": 0.719481348991394,
|
| 360 |
-
"step": 50
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 0.37174721189591076,
|
| 364 |
-
"eval_loss": 0.6215242147445679,
|
| 365 |
-
"eval_runtime": 25.3502,
|
| 366 |
-
"eval_samples_per_second": 0.434,
|
| 367 |
-
"eval_steps_per_second": 0.434,
|
| 368 |
-
"step": 50
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 0.379182156133829,
|
| 372 |
-
"grad_norm": 13.19458293914795,
|
| 373 |
-
"learning_rate": 1.9036283606085057e-05,
|
| 374 |
-
"loss": 0.7017593383789062,
|
| 375 |
-
"step": 51
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 0.38661710037174724,
|
| 379 |
-
"grad_norm": 6.939234256744385,
|
| 380 |
-
"learning_rate": 1.8989517410853956e-05,
|
| 381 |
-
"loss": 0.729701578617096,
|
| 382 |
-
"step": 52
|
| 383 |
-
},
|
| 384 |
-
{
|
| 385 |
-
"epoch": 0.3940520446096654,
|
| 386 |
-
"grad_norm": 6.942519664764404,
|
| 387 |
-
"learning_rate": 1.8941703493951163e-05,
|
| 388 |
-
"loss": 0.6863357424736023,
|
| 389 |
-
"step": 53
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 0.40148698884758366,
|
| 393 |
-
"grad_norm": 6.991189956665039,
|
| 394 |
-
"learning_rate": 1.8892847428053692e-05,
|
| 395 |
-
"loss": 0.5587253570556641,
|
| 396 |
-
"step": 54
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"epoch": 0.40892193308550184,
|
| 400 |
-
"grad_norm": 6.602214813232422,
|
| 401 |
-
"learning_rate": 1.8842954907300236e-05,
|
| 402 |
-
"loss": 0.5541514158248901,
|
| 403 |
-
"step": 55
|
| 404 |
-
},
|
| 405 |
-
{
|
| 406 |
-
"epoch": 0.4163568773234201,
|
| 407 |
-
"grad_norm": 7.6546478271484375,
|
| 408 |
-
"learning_rate": 1.8792031746627563e-05,
|
| 409 |
-
"loss": 0.492585688829422,
|
| 410 |
-
"step": 56
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 0.42379182156133827,
|
| 414 |
-
"grad_norm": 10.151951789855957,
|
| 415 |
-
"learning_rate": 1.874008388109276e-05,
|
| 416 |
-
"loss": 0.5921511054039001,
|
| 417 |
-
"step": 57
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 0.4312267657992565,
|
| 421 |
-
"grad_norm": 11.066969871520996,
|
| 422 |
-
"learning_rate": 1.8687117365181514e-05,
|
| 423 |
-
"loss": 0.630439043045044,
|
| 424 |
-
"step": 58
|
| 425 |
-
},
|
| 426 |
-
{
|
| 427 |
-
"epoch": 0.43866171003717475,
|
| 428 |
-
"grad_norm": 7.973349571228027,
|
| 429 |
-
"learning_rate": 1.863313837210247e-05,
|
| 430 |
-
"loss": 0.33777663111686707,
|
| 431 |
-
"step": 59
|
| 432 |
-
},
|
| 433 |
-
{
|
| 434 |
-
"epoch": 0.44609665427509293,
|
| 435 |
-
"grad_norm": 10.419097900390625,
|
| 436 |
-
"learning_rate": 1.8578153193067746e-05,
|
| 437 |
-
"loss": 0.6077542304992676,
|
| 438 |
-
"step": 60
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 0.45353159851301117,
|
| 442 |
-
"grad_norm": 8.547870635986328,
|
| 443 |
-
"learning_rate": 1.8522168236559693e-05,
|
| 444 |
-
"loss": 0.3710643947124481,
|
| 445 |
-
"step": 61
|
| 446 |
-
},
|
| 447 |
-
{
|
| 448 |
-
"epoch": 0.46096654275092935,
|
| 449 |
-
"grad_norm": 9.719517707824707,
|
| 450 |
-
"learning_rate": 1.8465190027584007e-05,
|
| 451 |
-
"loss": 0.6277018785476685,
|
| 452 |
-
"step": 62
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 0.4684014869888476,
|
| 456 |
-
"grad_norm": 7.974103927612305,
|
| 457 |
-
"learning_rate": 1.840722520690921e-05,
|
| 458 |
-
"loss": 0.3125975430011749,
|
| 459 |
-
"step": 63
|
| 460 |
-
},
|
| 461 |
-
{
|
| 462 |
-
"epoch": 0.4758364312267658,
|
| 463 |
-
"grad_norm": 9.939184188842773,
|
| 464 |
-
"learning_rate": 1.8348280530292712e-05,
|
| 465 |
-
"loss": 0.6476871371269226,
|
| 466 |
-
"step": 64
|
| 467 |
-
},
|
| 468 |
-
{
|
| 469 |
-
"epoch": 0.483271375464684,
|
| 470 |
-
"grad_norm": 6.947506904602051,
|
| 471 |
-
"learning_rate": 1.8288362867693414e-05,
|
| 472 |
-
"loss": 0.3975735008716583,
|
| 473 |
-
"step": 65
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 0.49070631970260226,
|
| 477 |
-
"grad_norm": 7.688926696777344,
|
| 478 |
-
"learning_rate": 1.8227479202471016e-05,
|
| 479 |
-
"loss": 0.5023108720779419,
|
| 480 |
-
"step": 66
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"epoch": 0.49814126394052044,
|
| 484 |
-
"grad_norm": 9.634269714355469,
|
| 485 |
-
"learning_rate": 1.816563663057211e-05,
|
| 486 |
-
"loss": 0.6572962403297424,
|
| 487 |
-
"step": 67
|
| 488 |
-
},
|
| 489 |
-
{
|
| 490 |
-
"epoch": 0.5055762081784386,
|
| 491 |
-
"grad_norm": 6.918145656585693,
|
| 492 |
-
"learning_rate": 1.8102842359703177e-05,
|
| 493 |
-
"loss": 0.48458513617515564,
|
| 494 |
-
"step": 68
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 0.5130111524163569,
|
| 498 |
-
"grad_norm": 6.915331840515137,
|
| 499 |
-
"learning_rate": 1.8039103708490503e-05,
|
| 500 |
-
"loss": 0.4269074499607086,
|
| 501 |
-
"step": 69
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 0.5204460966542751,
|
| 505 |
-
"grad_norm": 5.478643894195557,
|
| 506 |
-
"learning_rate": 1.797442810562721e-05,
|
| 507 |
-
"loss": 0.22324775159358978,
|
| 508 |
-
"step": 70
|
| 509 |
-
},
|
| 510 |
-
{
|
| 511 |
-
"epoch": 0.5278810408921933,
|
| 512 |
-
"grad_norm": 7.473972797393799,
|
| 513 |
-
"learning_rate": 1.790882308900746e-05,
|
| 514 |
-
"loss": 0.40716752409935,
|
| 515 |
-
"step": 71
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 0.5353159851301115,
|
| 519 |
-
"grad_norm": 7.293805122375488,
|
| 520 |
-
"learning_rate": 1.7842296304847892e-05,
|
| 521 |
-
"loss": 0.4579300880432129,
|
| 522 |
-
"step": 72
|
| 523 |
-
},
|
| 524 |
-
{
|
| 525 |
-
"epoch": 0.5427509293680297,
|
| 526 |
-
"grad_norm": 10.298800468444824,
|
| 527 |
-
"learning_rate": 1.7774855506796497e-05,
|
| 528 |
-
"loss": 0.4471757113933563,
|
| 529 |
-
"step": 73
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 0.550185873605948,
|
| 533 |
-
"grad_norm": 7.985231399536133,
|
| 534 |
-
"learning_rate": 1.7706508555028895e-05,
|
| 535 |
-
"loss": 0.32918351888656616,
|
| 536 |
-
"step": 74
|
| 537 |
-
},
|
| 538 |
-
{
|
| 539 |
-
"epoch": 0.5576208178438662,
|
| 540 |
-
"grad_norm": 10.254871368408203,
|
| 541 |
-
"learning_rate": 1.7637263415332272e-05,
|
| 542 |
-
"loss": 0.5008412599563599,
|
| 543 |
-
"step": 75
|
| 544 |
-
},
|
| 545 |
-
{
|
| 546 |
-
"epoch": 0.5650557620817844,
|
| 547 |
-
"grad_norm": 8.151082038879395,
|
| 548 |
-
"learning_rate": 1.7567128158176955e-05,
|
| 549 |
-
"loss": 0.4642640948295593,
|
| 550 |
-
"step": 76
|
| 551 |
-
},
|
| 552 |
-
{
|
| 553 |
-
"epoch": 0.5724907063197026,
|
| 554 |
-
"grad_norm": 7.846113681793213,
|
| 555 |
-
"learning_rate": 1.749611095777581e-05,
|
| 556 |
-
"loss": 0.37716782093048096,
|
| 557 |
-
"step": 77
|
| 558 |
-
},
|
| 559 |
-
{
|
| 560 |
-
"epoch": 0.5799256505576208,
|
| 561 |
-
"grad_norm": 8.735235214233398,
|
| 562 |
-
"learning_rate": 1.7424220091131536e-05,
|
| 563 |
-
"loss": 0.3629510998725891,
|
| 564 |
-
"step": 78
|
| 565 |
-
},
|
| 566 |
-
{
|
| 567 |
-
"epoch": 0.587360594795539,
|
| 568 |
-
"grad_norm": 6.430633068084717,
|
| 569 |
-
"learning_rate": 1.7351463937072008e-05,
|
| 570 |
-
"loss": 0.4114101529121399,
|
| 571 |
-
"step": 79
|
| 572 |
-
},
|
| 573 |
-
{
|
| 574 |
-
"epoch": 0.5947955390334573,
|
| 575 |
-
"grad_norm": 7.204378128051758,
|
| 576 |
-
"learning_rate": 1.7277850975273694e-05,
|
| 577 |
-
"loss": 0.2293665111064911,
|
| 578 |
-
"step": 80
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"epoch": 0.6022304832713755,
|
| 582 |
-
"grad_norm": 8.465530395507812,
|
| 583 |
-
"learning_rate": 1.7203389785273402e-05,
|
| 584 |
-
"loss": 0.27701911330223083,
|
| 585 |
-
"step": 81
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 0.6096654275092936,
|
| 589 |
-
"grad_norm": 7.8714165687561035,
|
| 590 |
-
"learning_rate": 1.7128089045468294e-05,
|
| 591 |
-
"loss": 0.2363108992576599,
|
| 592 |
-
"step": 82
|
| 593 |
-
},
|
| 594 |
-
{
|
| 595 |
-
"epoch": 0.6171003717472119,
|
| 596 |
-
"grad_norm": 12.45476245880127,
|
| 597 |
-
"learning_rate": 1.705195753210446e-05,
|
| 598 |
-
"loss": 0.236406609416008,
|
| 599 |
-
"step": 83
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 0.6245353159851301,
|
| 603 |
-
"grad_norm": 10.298430442810059,
|
| 604 |
-
"learning_rate": 1.697500411825403e-05,
|
| 605 |
-
"loss": 0.23633553087711334,
|
| 606 |
-
"step": 84
|
| 607 |
-
},
|
| 608 |
-
{
|
| 609 |
-
"epoch": 0.6319702602230484,
|
| 610 |
-
"grad_norm": 9.498958587646484,
|
| 611 |
-
"learning_rate": 1.6897237772781046e-05,
|
| 612 |
-
"loss": 0.29998382925987244,
|
| 613 |
-
"step": 85
|
| 614 |
-
},
|
| 615 |
-
{
|
| 616 |
-
"epoch": 0.6394052044609665,
|
| 617 |
-
"grad_norm": 8.283910751342773,
|
| 618 |
-
"learning_rate": 1.681866755929612e-05,
|
| 619 |
-
"loss": 0.11270587891340256,
|
| 620 |
-
"step": 86
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 0.6468401486988847,
|
| 624 |
-
"grad_norm": 8.229190826416016,
|
| 625 |
-
"learning_rate": 1.673930263510011e-05,
|
| 626 |
-
"loss": 0.15540620684623718,
|
| 627 |
-
"step": 87
|
| 628 |
-
},
|
| 629 |
-
{
|
| 630 |
-
"epoch": 0.654275092936803,
|
| 631 |
-
"grad_norm": 11.606176376342773,
|
| 632 |
-
"learning_rate": 1.665915225011681e-05,
|
| 633 |
-
"loss": 0.15637709200382233,
|
| 634 |
-
"step": 88
|
| 635 |
-
},
|
| 636 |
-
{
|
| 637 |
-
"epoch": 0.6617100371747212,
|
| 638 |
-
"grad_norm": 12.170763969421387,
|
| 639 |
-
"learning_rate": 1.6578225745814907e-05,
|
| 640 |
-
"loss": 0.2768555283546448,
|
| 641 |
-
"step": 89
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 0.6691449814126395,
|
| 645 |
-
"grad_norm": 13.229410171508789,
|
| 646 |
-
"learning_rate": 1.6496532554119214e-05,
|
| 647 |
-
"loss": 0.20483152568340302,
|
| 648 |
-
"step": 90
|
| 649 |
-
},
|
| 650 |
-
{
|
| 651 |
-
"epoch": 0.6765799256505576,
|
| 652 |
-
"grad_norm": 10.10963249206543,
|
| 653 |
-
"learning_rate": 1.6414082196311402e-05,
|
| 654 |
-
"loss": 0.1862092763185501,
|
| 655 |
-
"step": 91
|
| 656 |
-
},
|
| 657 |
-
{
|
| 658 |
-
"epoch": 0.6840148698884758,
|
| 659 |
-
"grad_norm": 12.798712730407715,
|
| 660 |
-
"learning_rate": 1.63308842819203e-05,
|
| 661 |
-
"loss": 0.2161349058151245,
|
| 662 |
-
"step": 92
|
| 663 |
-
},
|
| 664 |
-
{
|
| 665 |
-
"epoch": 0.6914498141263941,
|
| 666 |
-
"grad_norm": 9.150581359863281,
|
| 667 |
-
"learning_rate": 1.6246948507601915e-05,
|
| 668 |
-
"loss": 0.16542889177799225,
|
| 669 |
-
"step": 93
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 0.6988847583643123,
|
| 673 |
-
"grad_norm": 7.667386054992676,
|
| 674 |
-
"learning_rate": 1.6162284656009276e-05,
|
| 675 |
-
"loss": 0.20036524534225464,
|
| 676 |
-
"step": 94
|
| 677 |
-
},
|
| 678 |
-
{
|
| 679 |
-
"epoch": 0.7063197026022305,
|
| 680 |
-
"grad_norm": 6.500722885131836,
|
| 681 |
-
"learning_rate": 1.607690259465229e-05,
|
| 682 |
-
"loss": 0.1164686307311058,
|
| 683 |
-
"step": 95
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 0.7137546468401487,
|
| 687 |
-
"grad_norm": 14.25678539276123,
|
| 688 |
-
"learning_rate": 1.5990812274747695e-05,
|
| 689 |
-
"loss": 0.31526434421539307,
|
| 690 |
-
"step": 96
|
| 691 |
-
},
|
| 692 |
-
{
|
| 693 |
-
"epoch": 0.7211895910780669,
|
| 694 |
-
"grad_norm": 10.335010528564453,
|
| 695 |
-
"learning_rate": 1.5904023730059227e-05,
|
| 696 |
-
"loss": 0.2151976376771927,
|
| 697 |
-
"step": 97
|
| 698 |
-
},
|
| 699 |
-
{
|
| 700 |
-
"epoch": 0.7286245353159851,
|
| 701 |
-
"grad_norm": 8.368386268615723,
|
| 702 |
-
"learning_rate": 1.5816547075728227e-05,
|
| 703 |
-
"loss": 0.16460475325584412,
|
| 704 |
-
"step": 98
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 0.7360594795539034,
|
| 708 |
-
"grad_norm": 10.102240562438965,
|
| 709 |
-
"learning_rate": 1.57283925070947e-05,
|
| 710 |
-
"loss": 0.1308743804693222,
|
| 711 |
-
"step": 99
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 0.7434944237918215,
|
| 715 |
-
"grad_norm": 8.150355339050293,
|
| 716 |
-
"learning_rate": 1.5639570298509067e-05,
|
| 717 |
-
"loss": 0.10017991811037064,
|
| 718 |
-
"step": 100
|
| 719 |
-
},
|
| 720 |
-
{
|
| 721 |
-
"epoch": 0.7434944237918215,
|
| 722 |
-
"eval_loss": 0.07931093126535416,
|
| 723 |
-
"eval_runtime": 25.3325,
|
| 724 |
-
"eval_samples_per_second": 0.434,
|
| 725 |
-
"eval_steps_per_second": 0.434,
|
| 726 |
-
"step": 100
|
| 727 |
-
},
|
| 728 |
-
{
|
| 729 |
-
"epoch": 0.7509293680297398,
|
| 730 |
-
"grad_norm": 7.901605129241943,
|
| 731 |
-
"learning_rate": 1.55500908021347e-05,
|
| 732 |
-
"loss": 0.14433185756206512,
|
| 733 |
-
"step": 101
|
| 734 |
-
},
|
| 735 |
-
{
|
| 736 |
-
"epoch": 0.758364312267658,
|
| 737 |
-
"grad_norm": 7.710682392120361,
|
| 738 |
-
"learning_rate": 1.545996444674138e-05,
|
| 739 |
-
"loss": 0.1454196274280548,
|
| 740 |
-
"step": 102
|
| 741 |
-
},
|
| 742 |
-
{
|
| 743 |
-
"epoch": 0.7657992565055762,
|
| 744 |
-
"grad_norm": 5.5696635246276855,
|
| 745 |
-
"learning_rate": 1.536920173648984e-05,
|
| 746 |
-
"loss": 0.13363991677761078,
|
| 747 |
-
"step": 103
|
| 748 |
-
},
|
| 749 |
-
{
|
| 750 |
-
"epoch": 0.7732342007434945,
|
| 751 |
-
"grad_norm": 16.91303253173828,
|
| 752 |
-
"learning_rate": 1.5277813249707488e-05,
|
| 753 |
-
"loss": 0.164640873670578,
|
| 754 |
-
"step": 104
|
| 755 |
-
},
|
| 756 |
-
{
|
| 757 |
-
"epoch": 0.7806691449814126,
|
| 758 |
-
"grad_norm": 7.379611015319824,
|
| 759 |
-
"learning_rate": 1.5185809637655548e-05,
|
| 760 |
-
"loss": 0.11201221495866776,
|
| 761 |
-
"step": 105
|
| 762 |
-
},
|
| 763 |
-
{
|
| 764 |
-
"epoch": 0.7881040892193308,
|
| 765 |
-
"grad_norm": 8.399946212768555,
|
| 766 |
-
"learning_rate": 1.5093201623287631e-05,
|
| 767 |
-
"loss": 0.06443426012992859,
|
| 768 |
-
"step": 106
|
| 769 |
-
},
|
| 770 |
-
{
|
| 771 |
-
"epoch": 0.7955390334572491,
|
| 772 |
-
"grad_norm": 11.232651710510254,
|
| 773 |
-
"learning_rate": 1.5000000000000002e-05,
|
| 774 |
-
"loss": 0.17740455269813538,
|
| 775 |
-
"step": 107
|
| 776 |
-
},
|
| 777 |
-
{
|
| 778 |
-
"epoch": 0.8029739776951673,
|
| 779 |
-
"grad_norm": 10.214211463928223,
|
| 780 |
-
"learning_rate": 1.4906215630373606e-05,
|
| 781 |
-
"loss": 0.15067075192928314,
|
| 782 |
-
"step": 108
|
| 783 |
-
},
|
| 784 |
-
{
|
| 785 |
-
"epoch": 0.8104089219330854,
|
| 786 |
-
"grad_norm": 9.358437538146973,
|
| 787 |
-
"learning_rate": 1.4811859444908053e-05,
|
| 788 |
-
"loss": 0.0934559628367424,
|
| 789 |
-
"step": 109
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 0.8178438661710037,
|
| 793 |
-
"grad_norm": 11.665548324584961,
|
| 794 |
-
"learning_rate": 1.4716942440747663e-05,
|
| 795 |
-
"loss": 0.1534709483385086,
|
| 796 |
-
"step": 110
|
| 797 |
-
},
|
| 798 |
-
{
|
| 799 |
-
"epoch": 0.8252788104089219,
|
| 800 |
-
"grad_norm": 6.228277683258057,
|
| 801 |
-
"learning_rate": 1.4621475680399771e-05,
|
| 802 |
-
"loss": 0.040919575840234756,
|
| 803 |
-
"step": 111
|
| 804 |
-
},
|
| 805 |
-
{
|
| 806 |
-
"epoch": 0.8327137546468402,
|
| 807 |
-
"grad_norm": 8.82528018951416,
|
| 808 |
-
"learning_rate": 1.4525470290445392e-05,
|
| 809 |
-
"loss": 0.0943223163485527,
|
| 810 |
-
"step": 112
|
| 811 |
-
},
|
| 812 |
-
{
|
| 813 |
-
"epoch": 0.8401486988847584,
|
| 814 |
-
"grad_norm": 7.472390174865723,
|
| 815 |
-
"learning_rate": 1.4428937460242417e-05,
|
| 816 |
-
"loss": 0.09913193434476852,
|
| 817 |
-
"step": 113
|
| 818 |
-
},
|
| 819 |
-
{
|
| 820 |
-
"epoch": 0.8475836431226765,
|
| 821 |
-
"grad_norm": 5.956215858459473,
|
| 822 |
-
"learning_rate": 1.4331888440621533e-05,
|
| 823 |
-
"loss": 0.08492155373096466,
|
| 824 |
-
"step": 114
|
| 825 |
-
},
|
| 826 |
-
{
|
| 827 |
-
"epoch": 0.8550185873605948,
|
| 828 |
-
"grad_norm": 4.825902938842773,
|
| 829 |
-
"learning_rate": 1.4234334542574906e-05,
|
| 830 |
-
"loss": 0.0402367040514946,
|
| 831 |
-
"step": 115
|
| 832 |
-
},
|
| 833 |
-
{
|
| 834 |
-
"epoch": 0.862453531598513,
|
| 835 |
-
"grad_norm": 5.286779403686523,
|
| 836 |
-
"learning_rate": 1.4136287135937915e-05,
|
| 837 |
-
"loss": 0.046510517597198486,
|
| 838 |
-
"step": 116
|
| 839 |
-
},
|
| 840 |
-
{
|
| 841 |
-
"epoch": 0.8698884758364313,
|
| 842 |
-
"grad_norm": 9.62835693359375,
|
| 843 |
-
"learning_rate": 1.4037757648064019e-05,
|
| 844 |
-
"loss": 0.12098722159862518,
|
| 845 |
-
"step": 117
|
| 846 |
-
},
|
| 847 |
-
{
|
| 848 |
-
"epoch": 0.8773234200743495,
|
| 849 |
-
"grad_norm": 12.230518341064453,
|
| 850 |
-
"learning_rate": 1.3938757562492873e-05,
|
| 851 |
-
"loss": 0.22321803867816925,
|
| 852 |
-
"step": 118
|
| 853 |
-
},
|
| 854 |
-
{
|
| 855 |
-
"epoch": 0.8847583643122676,
|
| 856 |
-
"grad_norm": 9.319808959960938,
|
| 857 |
-
"learning_rate": 1.3839298417611964e-05,
|
| 858 |
-
"loss": 0.09593161195516586,
|
| 859 |
-
"step": 119
|
| 860 |
-
},
|
| 861 |
-
{
|
| 862 |
-
"epoch": 0.8921933085501859,
|
| 863 |
-
"grad_norm": 5.922304630279541,
|
| 864 |
-
"learning_rate": 1.3739391805311795e-05,
|
| 865 |
-
"loss": 0.024490350857377052,
|
| 866 |
-
"step": 120
|
| 867 |
-
},
|
| 868 |
-
{
|
| 869 |
-
"epoch": 0.8996282527881041,
|
| 870 |
-
"grad_norm": 9.537947654724121,
|
| 871 |
-
"learning_rate": 1.3639049369634878e-05,
|
| 872 |
-
"loss": 0.07902126759290695,
|
| 873 |
-
"step": 121
|
| 874 |
-
},
|
| 875 |
-
{
|
| 876 |
-
"epoch": 0.9070631970260223,
|
| 877 |
-
"grad_norm": 8.033231735229492,
|
| 878 |
-
"learning_rate": 1.353828280541861e-05,
|
| 879 |
-
"loss": 0.14102190732955933,
|
| 880 |
-
"step": 122
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"epoch": 0.9144981412639405,
|
| 884 |
-
"grad_norm": 4.262823581695557,
|
| 885 |
-
"learning_rate": 1.3437103856932266e-05,
|
| 886 |
-
"loss": 0.05054217204451561,
|
| 887 |
-
"step": 123
|
| 888 |
-
},
|
| 889 |
-
{
|
| 890 |
-
"epoch": 0.9219330855018587,
|
| 891 |
-
"grad_norm": 5.425140857696533,
|
| 892 |
-
"learning_rate": 1.3335524316508208e-05,
|
| 893 |
-
"loss": 0.03348986431956291,
|
| 894 |
-
"step": 124
|
| 895 |
-
},
|
| 896 |
-
{
|
| 897 |
-
"epoch": 0.929368029739777,
|
| 898 |
-
"grad_norm": 9.413047790527344,
|
| 899 |
-
"learning_rate": 1.3233556023167487e-05,
|
| 900 |
-
"loss": 0.053330615162849426,
|
| 901 |
-
"step": 125
|
| 902 |
-
},
|
| 903 |
-
{
|
| 904 |
-
"epoch": 0.9368029739776952,
|
| 905 |
-
"grad_norm": 7.04603910446167,
|
| 906 |
-
"learning_rate": 1.3131210861240027e-05,
|
| 907 |
-
"loss": 0.05251903086900711,
|
| 908 |
-
"step": 126
|
| 909 |
-
},
|
| 910 |
-
{
|
| 911 |
-
"epoch": 0.9442379182156134,
|
| 912 |
-
"grad_norm": 8.633530616760254,
|
| 913 |
-
"learning_rate": 1.3028500758979507e-05,
|
| 914 |
-
"loss": 0.09079591929912567,
|
| 915 |
-
"step": 127
|
| 916 |
-
},
|
| 917 |
-
{
|
| 918 |
-
"epoch": 0.9516728624535316,
|
| 919 |
-
"grad_norm": 8.762675285339355,
|
| 920 |
-
"learning_rate": 1.2925437687173144e-05,
|
| 921 |
-
"loss": 0.04166308045387268,
|
| 922 |
-
"step": 128
|
| 923 |
-
},
|
| 924 |
-
{
|
| 925 |
-
"epoch": 0.9591078066914498,
|
| 926 |
-
"grad_norm": 5.175497531890869,
|
| 927 |
-
"learning_rate": 1.2822033657746478e-05,
|
| 928 |
-
"loss": 0.04305100068449974,
|
| 929 |
-
"step": 129
|
| 930 |
-
},
|
| 931 |
-
{
|
| 932 |
-
"epoch": 0.966542750929368,
|
| 933 |
-
"grad_norm": 4.320688247680664,
|
| 934 |
-
"learning_rate": 1.2718300722363431e-05,
|
| 935 |
-
"loss": 0.020988037809729576,
|
| 936 |
-
"step": 130
|
| 937 |
-
},
|
| 938 |
-
{
|
| 939 |
-
"epoch": 0.9739776951672863,
|
| 940 |
-
"grad_norm": 7.2845139503479,
|
| 941 |
-
"learning_rate": 1.2614250971021658e-05,
|
| 942 |
-
"loss": 0.01916791871190071,
|
| 943 |
-
"step": 131
|
| 944 |
-
},
|
| 945 |
-
{
|
| 946 |
-
"epoch": 0.9814126394052045,
|
| 947 |
-
"grad_norm": 4.949283123016357,
|
| 948 |
-
"learning_rate": 1.2509896530643488e-05,
|
| 949 |
-
"loss": 0.02789604477584362,
|
| 950 |
-
"step": 132
|
| 951 |
-
},
|
| 952 |
-
{
|
| 953 |
-
"epoch": 0.9888475836431226,
|
| 954 |
-
"grad_norm": 5.301331520080566,
|
| 955 |
-
"learning_rate": 1.2405249563662539e-05,
|
| 956 |
-
"loss": 0.0284620001912117,
|
| 957 |
-
"step": 133
|
| 958 |
-
},
|
| 959 |
-
{
|
| 960 |
-
"epoch": 0.9962825278810409,
|
| 961 |
-
"grad_norm": 7.240689754486084,
|
| 962 |
-
"learning_rate": 1.2300322266606176e-05,
|
| 963 |
-
"loss": 0.07058233767747879,
|
| 964 |
-
"step": 134
|
| 965 |
-
},
|
| 966 |
-
{
|
| 967 |
-
"epoch": 1.0,
|
| 968 |
-
"grad_norm": 23.66366958618164,
|
| 969 |
-
"learning_rate": 1.2195126868674052e-05,
|
| 970 |
-
"loss": 0.10080776363611221,
|
| 971 |
-
"step": 135
|
| 972 |
-
},
|
| 973 |
-
{
|
| 974 |
-
"epoch": 1.0074349442379182,
|
| 975 |
-
"grad_norm": 8.742890357971191,
|
| 976 |
-
"learning_rate": 1.2089675630312755e-05,
|
| 977 |
-
"loss": 0.012475713156163692,
|
| 978 |
-
"step": 136
|
| 979 |
-
},
|
| 980 |
-
{
|
| 981 |
-
"epoch": 1.0148698884758365,
|
| 982 |
-
"grad_norm": 7.660653591156006,
|
| 983 |
-
"learning_rate": 1.1983980841786899e-05,
|
| 984 |
-
"loss": 0.02550521492958069,
|
| 985 |
-
"step": 137
|
| 986 |
-
},
|
| 987 |
-
{
|
| 988 |
-
"epoch": 1.0223048327137547,
|
| 989 |
-
"grad_norm": 8.254356384277344,
|
| 990 |
-
"learning_rate": 1.1878054821746703e-05,
|
| 991 |
-
"loss": 0.03438372164964676,
|
| 992 |
-
"step": 138
|
| 993 |
-
},
|
| 994 |
-
{
|
| 995 |
-
"epoch": 1.029739776951673,
|
| 996 |
-
"grad_norm": 7.544351577758789,
|
| 997 |
-
"learning_rate": 1.177190991579223e-05,
|
| 998 |
-
"loss": 0.012718814425170422,
|
| 999 |
-
"step": 139
|
| 1000 |
-
},
|
| 1001 |
-
{
|
| 1002 |
-
"epoch": 1.037174721189591,
|
| 1003 |
-
"grad_norm": 4.3011579513549805,
|
| 1004 |
-
"learning_rate": 1.1665558495034546e-05,
|
| 1005 |
-
"loss": 0.010748831555247307,
|
| 1006 |
-
"step": 140
|
| 1007 |
-
},
|
| 1008 |
-
{
|
| 1009 |
-
"epoch": 1.0446096654275092,
|
| 1010 |
-
"grad_norm": 5.313868045806885,
|
| 1011 |
-
"learning_rate": 1.1559012954653865e-05,
|
| 1012 |
-
"loss": 0.03220899775624275,
|
| 1013 |
-
"step": 141
|
| 1014 |
-
},
|
| 1015 |
-
{
|
| 1016 |
-
"epoch": 1.0520446096654275,
|
| 1017 |
-
"grad_norm": 3.8190832138061523,
|
| 1018 |
-
"learning_rate": 1.1452285712454905e-05,
|
| 1019 |
-
"loss": 0.012064998038113117,
|
| 1020 |
-
"step": 142
|
| 1021 |
-
},
|
| 1022 |
-
{
|
| 1023 |
-
"epoch": 1.0594795539033457,
|
| 1024 |
-
"grad_norm": 3.9894635677337646,
|
| 1025 |
-
"learning_rate": 1.1345389207419588e-05,
|
| 1026 |
-
"loss": 0.022306285798549652,
|
| 1027 |
-
"step": 143
|
| 1028 |
-
},
|
| 1029 |
-
{
|
| 1030 |
-
"epoch": 1.066914498141264,
|
| 1031 |
-
"grad_norm": 8.896062850952148,
|
| 1032 |
-
"learning_rate": 1.1238335898257305e-05,
|
| 1033 |
-
"loss": 0.04725006967782974,
|
| 1034 |
-
"step": 144
|
| 1035 |
-
},
|
| 1036 |
-
{
|
| 1037 |
-
"epoch": 1.0743494423791822,
|
| 1038 |
-
"grad_norm": 6.4355387687683105,
|
| 1039 |
-
"learning_rate": 1.1131138261952845e-05,
|
| 1040 |
-
"loss": 0.024585356935858727,
|
| 1041 |
-
"step": 145
|
| 1042 |
-
},
|
| 1043 |
-
{
|
| 1044 |
-
"epoch": 1.0817843866171004,
|
| 1045 |
-
"grad_norm": 4.504736423492432,
|
| 1046 |
-
"learning_rate": 1.1023808792312226e-05,
|
| 1047 |
-
"loss": 0.02972128801047802,
|
| 1048 |
-
"step": 146
|
| 1049 |
-
},
|
| 1050 |
-
{
|
| 1051 |
-
"epoch": 1.0892193308550187,
|
| 1052 |
-
"grad_norm": 6.781092643737793,
|
| 1053 |
-
"learning_rate": 1.0916359998506549e-05,
|
| 1054 |
-
"loss": 0.03628234192728996,
|
| 1055 |
-
"step": 147
|
| 1056 |
-
},
|
| 1057 |
-
{
|
| 1058 |
-
"epoch": 1.096654275092937,
|
| 1059 |
-
"grad_norm": 7.668790340423584,
|
| 1060 |
-
"learning_rate": 1.0808804403614044e-05,
|
| 1061 |
-
"loss": 0.02200871706008911,
|
| 1062 |
-
"step": 148
|
| 1063 |
-
},
|
| 1064 |
-
{
|
| 1065 |
-
"epoch": 1.104089219330855,
|
| 1066 |
-
"grad_norm": 3.6971218585968018,
|
| 1067 |
-
"learning_rate": 1.070115454316054e-05,
|
| 1068 |
-
"loss": 0.012756682932376862,
|
| 1069 |
-
"step": 149
|
| 1070 |
-
},
|
| 1071 |
-
{
|
| 1072 |
-
"epoch": 1.1115241635687731,
|
| 1073 |
-
"grad_norm": 6.258151531219482,
|
| 1074 |
-
"learning_rate": 1.0593422963658453e-05,
|
| 1075 |
-
"loss": 0.021982628852128983,
|
| 1076 |
-
"step": 150
|
| 1077 |
-
},
|
| 1078 |
-
{
|
| 1079 |
-
"epoch": 1.1115241635687731,
|
| 1080 |
-
"eval_loss": 0.037792377173900604,
|
| 1081 |
-
"eval_runtime": 25.4019,
|
| 1082 |
-
"eval_samples_per_second": 0.433,
|
| 1083 |
-
"eval_steps_per_second": 0.433,
|
| 1084 |
-
"step": 150
|
| 1085 |
-
},
|
| 1086 |
-
{
|
| 1087 |
-
"epoch": 1.1189591078066914,
|
| 1088 |
-
"grad_norm": 4.057281017303467,
|
| 1089 |
-
"learning_rate": 1.0485622221144485e-05,
|
| 1090 |
-
"loss": 0.006427440792322159,
|
| 1091 |
-
"step": 151
|
| 1092 |
-
},
|
| 1093 |
-
{
|
| 1094 |
-
"epoch": 1.1263940520446096,
|
| 1095 |
-
"grad_norm": 6.9714274406433105,
|
| 1096 |
-
"learning_rate": 1.0377764879716234e-05,
|
| 1097 |
-
"loss": 0.019488757476210594,
|
| 1098 |
-
"step": 152
|
| 1099 |
-
},
|
| 1100 |
-
{
|
| 1101 |
-
"epoch": 1.1338289962825279,
|
| 1102 |
-
"grad_norm": 2.0719211101531982,
|
| 1103 |
-
"learning_rate": 1.0269863510067872e-05,
|
| 1104 |
-
"loss": 0.006268701050430536,
|
| 1105 |
-
"step": 153
|
| 1106 |
-
},
|
| 1107 |
-
{
|
| 1108 |
-
"epoch": 1.141263940520446,
|
| 1109 |
-
"grad_norm": 8.397356986999512,
|
| 1110 |
-
"learning_rate": 1.0161930688025018e-05,
|
| 1111 |
-
"loss": 0.027911271899938583,
|
| 1112 |
-
"step": 154
|
| 1113 |
-
},
|
| 1114 |
-
{
|
| 1115 |
-
"epoch": 1.1486988847583643,
|
| 1116 |
-
"grad_norm": 6.956691741943359,
|
| 1117 |
-
"learning_rate": 1.0053978993079046e-05,
|
| 1118 |
-
"loss": 0.034651659429073334,
|
| 1119 |
-
"step": 155
|
| 1120 |
-
},
|
| 1121 |
-
{
|
| 1122 |
-
"epoch": 1.1561338289962826,
|
| 1123 |
-
"grad_norm": 10.412235260009766,
|
| 1124 |
-
"learning_rate": 9.946021006920959e-06,
|
| 1125 |
-
"loss": 0.024138193577528,
|
| 1126 |
-
"step": 156
|
| 1127 |
-
},
|
| 1128 |
-
{
|
| 1129 |
-
"epoch": 1.1635687732342008,
|
| 1130 |
-
"grad_norm": 8.673863410949707,
|
| 1131 |
-
"learning_rate": 9.838069311974986e-06,
|
| 1132 |
-
"loss": 0.05596349760890007,
|
| 1133 |
-
"step": 157
|
| 1134 |
-
},
|
| 1135 |
-
{
|
| 1136 |
-
"epoch": 1.1710037174721188,
|
| 1137 |
-
"grad_norm": 13.151246070861816,
|
| 1138 |
-
"learning_rate": 9.730136489932133e-06,
|
| 1139 |
-
"loss": 0.04488427937030792,
|
| 1140 |
-
"step": 158
|
| 1141 |
-
},
|
| 1142 |
-
{
|
| 1143 |
-
"epoch": 1.178438661710037,
|
| 1144 |
-
"grad_norm": 2.4643819332122803,
|
| 1145 |
-
"learning_rate": 9.622235120283769e-06,
|
| 1146 |
-
"loss": 0.009759537875652313,
|
| 1147 |
-
"step": 159
|
| 1148 |
-
},
|
| 1149 |
-
{
|
| 1150 |
-
"epoch": 1.1858736059479553,
|
| 1151 |
-
"grad_norm": 4.208892345428467,
|
| 1152 |
-
"learning_rate": 9.514377778855521e-06,
|
| 1153 |
-
"loss": 0.013831784948706627,
|
| 1154 |
-
"step": 160
|
| 1155 |
-
},
|
| 1156 |
-
{
|
| 1157 |
-
"epoch": 1.1933085501858736,
|
| 1158 |
-
"grad_norm": 4.5636396408081055,
|
| 1159 |
-
"learning_rate": 9.406577036341548e-06,
|
| 1160 |
-
"loss": 0.02133704535663128,
|
| 1161 |
-
"step": 161
|
| 1162 |
-
},
|
| 1163 |
-
{
|
| 1164 |
-
"epoch": 1.2007434944237918,
|
| 1165 |
-
"grad_norm": 11.264151573181152,
|
| 1166 |
-
"learning_rate": 9.298845456839459e-06,
|
| 1167 |
-
"loss": 0.02591024711728096,
|
| 1168 |
-
"step": 162
|
| 1169 |
-
},
|
| 1170 |
-
{
|
| 1171 |
-
"epoch": 1.20817843866171,
|
| 1172 |
-
"grad_norm": 7.221699237823486,
|
| 1173 |
-
"learning_rate": 9.19119559638596e-06,
|
| 1174 |
-
"loss": 0.017063425853848457,
|
| 1175 |
-
"step": 163
|
| 1176 |
-
},
|
| 1177 |
-
{
|
| 1178 |
-
"epoch": 1.2156133828996283,
|
| 1179 |
-
"grad_norm": 2.1452982425689697,
|
| 1180 |
-
"learning_rate": 9.083640001493455e-06,
|
| 1181 |
-
"loss": 0.011678601615130901,
|
| 1182 |
-
"step": 164
|
| 1183 |
-
},
|
| 1184 |
-
{
|
| 1185 |
-
"epoch": 1.2230483271375465,
|
| 1186 |
-
"grad_norm": 7.512999534606934,
|
| 1187 |
-
"learning_rate": 8.976191207687775e-06,
|
| 1188 |
-
"loss": 0.02969130128622055,
|
| 1189 |
-
"step": 165
|
| 1190 |
-
},
|
| 1191 |
-
{
|
| 1192 |
-
"epoch": 1.2304832713754648,
|
| 1193 |
-
"grad_norm": 7.162579536437988,
|
| 1194 |
-
"learning_rate": 8.868861738047158e-06,
|
| 1195 |
-
"loss": 0.04694490134716034,
|
| 1196 |
-
"step": 166
|
| 1197 |
-
},
|
| 1198 |
-
{
|
| 1199 |
-
"epoch": 1.2379182156133828,
|
| 1200 |
-
"grad_norm": 4.975037097930908,
|
| 1201 |
-
"learning_rate": 8.7616641017427e-06,
|
| 1202 |
-
"loss": 0.013061350211501122,
|
| 1203 |
-
"step": 167
|
| 1204 |
-
},
|
| 1205 |
-
{
|
| 1206 |
-
"epoch": 1.2453531598513012,
|
| 1207 |
-
"grad_norm": 10.431370735168457,
|
| 1208 |
-
"learning_rate": 8.654610792580415e-06,
|
| 1209 |
-
"loss": 0.06219532713294029,
|
| 1210 |
-
"step": 168
|
| 1211 |
-
},
|
| 1212 |
-
{
|
| 1213 |
-
"epoch": 1.2527881040892193,
|
| 1214 |
-
"grad_norm": 13.840130805969238,
|
| 1215 |
-
"learning_rate": 8.5477142875451e-06,
|
| 1216 |
-
"loss": 0.04001167416572571,
|
| 1217 |
-
"step": 169
|
| 1218 |
-
},
|
| 1219 |
-
{
|
| 1220 |
-
"epoch": 1.2602230483271375,
|
| 1221 |
-
"grad_norm": 8.468676567077637,
|
| 1222 |
-
"learning_rate": 8.440987045346135e-06,
|
| 1223 |
-
"loss": 0.0347297228872776,
|
| 1224 |
-
"step": 170
|
| 1225 |
-
},
|
| 1226 |
-
{
|
| 1227 |
-
"epoch": 1.2676579925650557,
|
| 1228 |
-
"grad_norm": 1.6266356706619263,
|
| 1229 |
-
"learning_rate": 8.334441504965456e-06,
|
| 1230 |
-
"loss": 0.005336158908903599,
|
| 1231 |
-
"step": 171
|
| 1232 |
-
},
|
| 1233 |
-
{
|
| 1234 |
-
"epoch": 1.275092936802974,
|
| 1235 |
-
"grad_norm": 3.5108299255371094,
|
| 1236 |
-
"learning_rate": 8.228090084207773e-06,
|
| 1237 |
-
"loss": 0.009373579174280167,
|
| 1238 |
-
"step": 172
|
| 1239 |
-
},
|
| 1240 |
-
{
|
| 1241 |
-
"epoch": 1.2825278810408922,
|
| 1242 |
-
"grad_norm": 1.94013249874115,
|
| 1243 |
-
"learning_rate": 8.1219451782533e-06,
|
| 1244 |
-
"loss": 0.006868388969451189,
|
| 1245 |
-
"step": 173
|
| 1246 |
-
},
|
| 1247 |
-
{
|
| 1248 |
-
"epoch": 1.2899628252788105,
|
| 1249 |
-
"grad_norm": 1.9547545909881592,
|
| 1250 |
-
"learning_rate": 8.016019158213103e-06,
|
| 1251 |
-
"loss": 0.0061888257041573524,
|
| 1252 |
-
"step": 174
|
| 1253 |
-
},
|
| 1254 |
-
{
|
| 1255 |
-
"epoch": 1.2973977695167287,
|
| 1256 |
-
"grad_norm": 8.551900863647461,
|
| 1257 |
-
"learning_rate": 7.91032436968725e-06,
|
| 1258 |
-
"loss": 0.03539920598268509,
|
| 1259 |
-
"step": 175
|
| 1260 |
-
},
|
| 1261 |
-
{
|
| 1262 |
-
"epoch": 1.3048327137546467,
|
| 1263 |
-
"grad_norm": 1.8512156009674072,
|
| 1264 |
-
"learning_rate": 7.804873131325955e-06,
|
| 1265 |
-
"loss": 0.005195024888962507,
|
| 1266 |
-
"step": 176
|
| 1267 |
-
},
|
| 1268 |
-
{
|
| 1269 |
-
"epoch": 1.3122676579925652,
|
| 1270 |
-
"grad_norm": 4.592437744140625,
|
| 1271 |
-
"learning_rate": 7.699677733393827e-06,
|
| 1272 |
-
"loss": 0.053930528461933136,
|
| 1273 |
-
"step": 177
|
| 1274 |
-
},
|
| 1275 |
-
{
|
| 1276 |
-
"epoch": 1.3197026022304832,
|
| 1277 |
-
"grad_norm": 20.684314727783203,
|
| 1278 |
-
"learning_rate": 7.594750436337467e-06,
|
| 1279 |
-
"loss": 0.11866368353366852,
|
| 1280 |
-
"step": 178
|
| 1281 |
-
},
|
| 1282 |
-
{
|
| 1283 |
-
"epoch": 1.3271375464684014,
|
| 1284 |
-
"grad_norm": 3.084477663040161,
|
| 1285 |
-
"learning_rate": 7.490103469356513e-06,
|
| 1286 |
-
"loss": 0.009668141603469849,
|
| 1287 |
-
"step": 179
|
| 1288 |
-
},
|
| 1289 |
-
{
|
| 1290 |
-
"epoch": 1.3345724907063197,
|
| 1291 |
-
"grad_norm": 6.361363410949707,
|
| 1292 |
-
"learning_rate": 7.385749028978347e-06,
|
| 1293 |
-
"loss": 0.05012731999158859,
|
| 1294 |
-
"step": 180
|
| 1295 |
-
},
|
| 1296 |
-
{
|
| 1297 |
-
"epoch": 1.342007434944238,
|
| 1298 |
-
"grad_norm": 6.477831840515137,
|
| 1299 |
-
"learning_rate": 7.2816992776365714e-06,
|
| 1300 |
-
"loss": 0.030221598222851753,
|
| 1301 |
-
"step": 181
|
| 1302 |
-
},
|
| 1303 |
-
{
|
| 1304 |
-
"epoch": 1.3494423791821561,
|
| 1305 |
-
"grad_norm": 3.268894672393799,
|
| 1306 |
-
"learning_rate": 7.1779663422535235e-06,
|
| 1307 |
-
"loss": 0.006099697668105364,
|
| 1308 |
-
"step": 182
|
| 1309 |
-
},
|
| 1310 |
-
{
|
| 1311 |
-
"epoch": 1.3568773234200744,
|
| 1312 |
-
"grad_norm": 1.827690601348877,
|
| 1313 |
-
"learning_rate": 7.0745623128268605e-06,
|
| 1314 |
-
"loss": 0.007234757766127586,
|
| 1315 |
-
"step": 183
|
| 1316 |
-
},
|
| 1317 |
-
{
|
| 1318 |
-
"epoch": 1.3643122676579926,
|
| 1319 |
-
"grad_norm": 3.0039429664611816,
|
| 1320 |
-
"learning_rate": 6.971499241020495e-06,
|
| 1321 |
-
"loss": 0.03112523816525936,
|
| 1322 |
-
"step": 184
|
| 1323 |
-
},
|
| 1324 |
-
{
|
| 1325 |
-
"epoch": 1.3717472118959106,
|
| 1326 |
-
"grad_norm": 3.156479597091675,
|
| 1327 |
-
"learning_rate": 6.868789138759977e-06,
|
| 1328 |
-
"loss": 0.0031025242060422897,
|
| 1329 |
-
"step": 185
|
| 1330 |
-
},
|
| 1331 |
-
{
|
| 1332 |
-
"epoch": 1.379182156133829,
|
| 1333 |
-
"grad_norm": 3.8309895992279053,
|
| 1334 |
-
"learning_rate": 6.766443976832518e-06,
|
| 1335 |
-
"loss": 0.00931456033140421,
|
| 1336 |
-
"step": 186
|
| 1337 |
-
},
|
| 1338 |
-
{
|
| 1339 |
-
"epoch": 1.3866171003717471,
|
| 1340 |
-
"grad_norm": 1.5250825881958008,
|
| 1341 |
-
"learning_rate": 6.664475683491797e-06,
|
| 1342 |
-
"loss": 0.006034584250301123,
|
| 1343 |
-
"step": 187
|
| 1344 |
-
},
|
| 1345 |
-
{
|
| 1346 |
-
"epoch": 1.3940520446096654,
|
| 1347 |
-
"grad_norm": 3.9715824127197266,
|
| 1348 |
-
"learning_rate": 6.562896143067734e-06,
|
| 1349 |
-
"loss": 0.011754708364605904,
|
| 1350 |
-
"step": 188
|
| 1351 |
-
},
|
| 1352 |
-
{
|
| 1353 |
-
"epoch": 1.4014869888475836,
|
| 1354 |
-
"grad_norm": 0.8444815874099731,
|
| 1355 |
-
"learning_rate": 6.461717194581394e-06,
|
| 1356 |
-
"loss": 0.0026434683240950108,
|
| 1357 |
-
"step": 189
|
| 1358 |
-
},
|
| 1359 |
-
{
|
| 1360 |
-
"epoch": 1.4089219330855018,
|
| 1361 |
-
"grad_norm": 4.460427761077881,
|
| 1362 |
-
"learning_rate": 6.360950630365126e-06,
|
| 1363 |
-
"loss": 0.00918147899210453,
|
| 1364 |
-
"step": 190
|
| 1365 |
-
},
|
| 1366 |
-
{
|
| 1367 |
-
"epoch": 1.41635687732342,
|
| 1368 |
-
"grad_norm": 1.743480920791626,
|
| 1369 |
-
"learning_rate": 6.260608194688207e-06,
|
| 1370 |
-
"loss": 0.005454449914395809,
|
| 1371 |
-
"step": 191
|
| 1372 |
-
},
|
| 1373 |
-
{
|
| 1374 |
-
"epoch": 1.4237918215613383,
|
| 1375 |
-
"grad_norm": 3.6512022018432617,
|
| 1376 |
-
"learning_rate": 6.160701582388039e-06,
|
| 1377 |
-
"loss": 0.019059546291828156,
|
| 1378 |
-
"step": 192
|
| 1379 |
-
},
|
| 1380 |
-
{
|
| 1381 |
-
"epoch": 1.4312267657992566,
|
| 1382 |
-
"grad_norm": 2.2396457195281982,
|
| 1383 |
-
"learning_rate": 6.061242437507131e-06,
|
| 1384 |
-
"loss": 0.004893932491540909,
|
| 1385 |
-
"step": 193
|
| 1386 |
-
},
|
| 1387 |
-
{
|
| 1388 |
-
"epoch": 1.4386617100371748,
|
| 1389 |
-
"grad_norm": 1.3282725811004639,
|
| 1390 |
-
"learning_rate": 5.962242351935985e-06,
|
| 1391 |
-
"loss": 0.0030322109814733267,
|
| 1392 |
-
"step": 194
|
| 1393 |
-
},
|
| 1394 |
-
{
|
| 1395 |
-
"epoch": 1.446096654275093,
|
| 1396 |
-
"grad_norm": 0.45283815264701843,
|
| 1397 |
-
"learning_rate": 5.863712864062089e-06,
|
| 1398 |
-
"loss": 0.0014967583119869232,
|
| 1399 |
-
"step": 195
|
| 1400 |
-
},
|
| 1401 |
-
{
|
| 1402 |
-
"epoch": 1.453531598513011,
|
| 1403 |
-
"grad_norm": 0.2984156310558319,
|
| 1404 |
-
"learning_rate": 5.765665457425102e-06,
|
| 1405 |
-
"loss": 0.0014030743623152375,
|
| 1406 |
-
"step": 196
|
| 1407 |
-
},
|
| 1408 |
-
{
|
| 1409 |
-
"epoch": 1.4609665427509293,
|
| 1410 |
-
"grad_norm": 2.0028910636901855,
|
| 1411 |
-
"learning_rate": 5.6681115593784705e-06,
|
| 1412 |
-
"loss": 0.0031558023765683174,
|
| 1413 |
-
"step": 197
|
| 1414 |
-
},
|
| 1415 |
-
{
|
| 1416 |
-
"epoch": 1.4684014869888475,
|
| 1417 |
-
"grad_norm": 0.3523065149784088,
|
| 1418 |
-
"learning_rate": 5.571062539757582e-06,
|
| 1419 |
-
"loss": 0.0015127082588151097,
|
| 1420 |
-
"step": 198
|
| 1421 |
-
},
|
| 1422 |
-
{
|
| 1423 |
-
"epoch": 1.4758364312267658,
|
| 1424 |
-
"grad_norm": 1.5797808170318604,
|
| 1425 |
-
"learning_rate": 5.4745297095546125e-06,
|
| 1426 |
-
"loss": 0.0025897377636283636,
|
| 1427 |
-
"step": 199
|
| 1428 |
-
},
|
| 1429 |
-
{
|
| 1430 |
-
"epoch": 1.483271375464684,
|
| 1431 |
-
"grad_norm": 8.218883514404297,
|
| 1432 |
-
"learning_rate": 5.378524319600231e-06,
|
| 1433 |
-
"loss": 0.05572836101055145,
|
| 1434 |
-
"step": 200
|
| 1435 |
-
},
|
| 1436 |
-
{
|
| 1437 |
-
"epoch": 1.483271375464684,
|
| 1438 |
-
"eval_loss": 0.00345331197604537,
|
| 1439 |
-
"eval_runtime": 25.372,
|
| 1440 |
-
"eval_samples_per_second": 0.434,
|
| 1441 |
-
"eval_steps_per_second": 0.434,
|
| 1442 |
-
"step": 200
|
| 1443 |
-
},
|
| 1444 |
-
{
|
| 1445 |
-
"epoch": 1.4907063197026023,
|
| 1446 |
-
"grad_norm": 4.23383092880249,
|
| 1447 |
-
"learning_rate": 5.2830575592523415e-06,
|
| 1448 |
-
"loss": 0.008380255661904812,
|
| 1449 |
-
"step": 201
|
| 1450 |
-
},
|
| 1451 |
-
{
|
| 1452 |
-
"epoch": 1.4981412639405205,
|
| 1453 |
-
"grad_norm": 3.009281635284424,
|
| 1454 |
-
"learning_rate": 5.18814055509195e-06,
|
| 1455 |
-
"loss": 0.00754923652857542,
|
| 1456 |
-
"step": 202
|
| 1457 |
-
},
|
| 1458 |
-
{
|
| 1459 |
-
"epoch": 1.5055762081784385,
|
| 1460 |
-
"grad_norm": 0.5061541795730591,
|
| 1461 |
-
"learning_rate": 5.093784369626397e-06,
|
| 1462 |
-
"loss": 0.0010725234169512987,
|
| 1463 |
-
"step": 203
|
| 1464 |
-
},
|
| 1465 |
-
{
|
| 1466 |
-
"epoch": 1.513011152416357,
|
| 1467 |
-
"grad_norm": 2.566987991333008,
|
| 1468 |
-
"learning_rate": 5.000000000000003e-06,
|
| 1469 |
-
"loss": 0.004665295593440533,
|
| 1470 |
-
"step": 204
|
| 1471 |
-
},
|
| 1472 |
-
{
|
| 1473 |
-
"epoch": 1.520446096654275,
|
| 1474 |
-
"grad_norm": 0.5442692041397095,
|
| 1475 |
-
"learning_rate": 4.9067983767123736e-06,
|
| 1476 |
-
"loss": 0.0016852637054398656,
|
| 1477 |
-
"step": 205
|
| 1478 |
-
},
|
| 1479 |
-
{
|
| 1480 |
-
"epoch": 1.5278810408921935,
|
| 1481 |
-
"grad_norm": 7.433818340301514,
|
| 1482 |
-
"learning_rate": 4.814190362344454e-06,
|
| 1483 |
-
"loss": 0.025673305615782738,
|
| 1484 |
-
"step": 206
|
| 1485 |
-
},
|
| 1486 |
-
{
|
| 1487 |
-
"epoch": 1.5353159851301115,
|
| 1488 |
-
"grad_norm": 0.4558600187301636,
|
| 1489 |
-
"learning_rate": 4.722186750292511e-06,
|
| 1490 |
-
"loss": 0.0010814513079822063,
|
| 1491 |
-
"step": 207
|
| 1492 |
-
},
|
| 1493 |
-
{
|
| 1494 |
-
"epoch": 1.5427509293680297,
|
| 1495 |
-
"grad_norm": 1.2294921875,
|
| 1496 |
-
"learning_rate": 4.630798263510162e-06,
|
| 1497 |
-
"loss": 0.002239473396912217,
|
| 1498 |
-
"step": 208
|
| 1499 |
-
},
|
| 1500 |
-
{
|
| 1501 |
-
"epoch": 1.550185873605948,
|
| 1502 |
-
"grad_norm": 1.7435331344604492,
|
| 1503 |
-
"learning_rate": 4.54003555325862e-06,
|
| 1504 |
-
"loss": 0.005386807024478912,
|
| 1505 |
-
"step": 209
|
| 1506 |
-
},
|
| 1507 |
-
{
|
| 1508 |
-
"epoch": 1.5576208178438662,
|
| 1509 |
-
"grad_norm": 2.6051065921783447,
|
| 1510 |
-
"learning_rate": 4.449909197865303e-06,
|
| 1511 |
-
"loss": 0.004140175879001617,
|
| 1512 |
-
"step": 210
|
| 1513 |
-
},
|
| 1514 |
-
{
|
| 1515 |
-
"epoch": 1.5650557620817844,
|
| 1516 |
-
"grad_norm": 2.899318218231201,
|
| 1517 |
-
"learning_rate": 4.360429701490935e-06,
|
| 1518 |
-
"loss": 0.004319075495004654,
|
| 1519 |
-
"step": 211
|
| 1520 |
-
},
|
| 1521 |
-
{
|
| 1522 |
-
"epoch": 1.5724907063197024,
|
| 1523 |
-
"grad_norm": 1.0033962726593018,
|
| 1524 |
-
"learning_rate": 4.271607492905303e-06,
|
| 1525 |
-
"loss": 0.0016975726466625929,
|
| 1526 |
-
"step": 212
|
| 1527 |
-
},
|
| 1528 |
-
{
|
| 1529 |
-
"epoch": 1.579925650557621,
|
| 1530 |
-
"grad_norm": 0.11318615823984146,
|
| 1531 |
-
"learning_rate": 4.183452924271776e-06,
|
| 1532 |
-
"loss": 0.0005350559949874878,
|
| 1533 |
-
"step": 213
|
| 1534 |
-
},
|
| 1535 |
-
{
|
| 1536 |
-
"epoch": 1.587360594795539,
|
| 1537 |
-
"grad_norm": 0.6640377640724182,
|
| 1538 |
-
"learning_rate": 4.095976269940777e-06,
|
| 1539 |
-
"loss": 0.002190855098888278,
|
| 1540 |
-
"step": 214
|
| 1541 |
-
},
|
| 1542 |
-
{
|
| 1543 |
-
"epoch": 1.5947955390334574,
|
| 1544 |
-
"grad_norm": 0.9191398024559021,
|
| 1545 |
-
"learning_rate": 4.009187725252309e-06,
|
| 1546 |
-
"loss": 0.0012900492874905467,
|
| 1547 |
-
"step": 215
|
| 1548 |
-
},
|
| 1549 |
-
{
|
| 1550 |
-
"epoch": 1.6022304832713754,
|
| 1551 |
-
"grad_norm": 1.209619402885437,
|
| 1552 |
-
"learning_rate": 3.923097405347709e-06,
|
| 1553 |
-
"loss": 0.0025745758321136236,
|
| 1554 |
-
"step": 216
|
| 1555 |
-
},
|
| 1556 |
-
{
|
| 1557 |
-
"epoch": 1.6096654275092936,
|
| 1558 |
-
"grad_norm": 1.8463724851608276,
|
| 1559 |
-
"learning_rate": 3.837715343990727e-06,
|
| 1560 |
-
"loss": 0.0015018703415989876,
|
| 1561 |
-
"step": 217
|
| 1562 |
-
},
|
| 1563 |
-
{
|
| 1564 |
-
"epoch": 1.6171003717472119,
|
| 1565 |
-
"grad_norm": 0.3702464699745178,
|
| 1566 |
-
"learning_rate": 3.753051492398089e-06,
|
| 1567 |
-
"loss": 0.001234126859344542,
|
| 1568 |
-
"step": 218
|
| 1569 |
-
},
|
| 1570 |
-
{
|
| 1571 |
-
"epoch": 1.6245353159851301,
|
| 1572 |
-
"grad_norm": 0.07822796702384949,
|
| 1573 |
-
"learning_rate": 3.669115718079702e-06,
|
| 1574 |
-
"loss": 0.0005210964009165764,
|
| 1575 |
-
"step": 219
|
| 1576 |
-
},
|
| 1577 |
-
{
|
| 1578 |
-
"epoch": 1.6319702602230484,
|
| 1579 |
-
"grad_norm": 1.3892689943313599,
|
| 1580 |
-
"learning_rate": 3.585917803688603e-06,
|
| 1581 |
-
"loss": 0.002871165983378887,
|
| 1582 |
-
"step": 220
|
| 1583 |
-
},
|
| 1584 |
-
{
|
| 1585 |
-
"epoch": 1.6394052044609664,
|
| 1586 |
-
"grad_norm": 2.2215311527252197,
|
| 1587 |
-
"learning_rate": 3.5034674458807893e-06,
|
| 1588 |
-
"loss": 0.007808375637978315,
|
| 1589 |
-
"step": 221
|
| 1590 |
-
},
|
| 1591 |
-
{
|
| 1592 |
-
"epoch": 1.6468401486988848,
|
| 1593 |
-
"grad_norm": 1.4664288759231567,
|
| 1594 |
-
"learning_rate": 3.421774254185096e-06,
|
| 1595 |
-
"loss": 0.0021337075158953667,
|
| 1596 |
-
"step": 222
|
| 1597 |
-
},
|
| 1598 |
-
{
|
| 1599 |
-
"epoch": 1.6542750929368029,
|
| 1600 |
-
"grad_norm": 0.2864939868450165,
|
| 1601 |
-
"learning_rate": 3.3408477498831917e-06,
|
| 1602 |
-
"loss": 0.00113480887375772,
|
| 1603 |
-
"step": 223
|
| 1604 |
-
},
|
| 1605 |
-
{
|
| 1606 |
-
"epoch": 1.6617100371747213,
|
| 1607 |
-
"grad_norm": 0.3169388473033905,
|
| 1608 |
-
"learning_rate": 3.2606973648998918e-06,
|
| 1609 |
-
"loss": 0.0014634067192673683,
|
| 1610 |
-
"step": 224
|
| 1611 |
-
},
|
| 1612 |
-
{
|
| 1613 |
-
"epoch": 1.6691449814126393,
|
| 1614 |
-
"grad_norm": 0.11810390651226044,
|
| 1615 |
-
"learning_rate": 3.1813324407038826e-06,
|
| 1616 |
-
"loss": 0.0005495938239619136,
|
| 1617 |
-
"step": 225
|
| 1618 |
-
},
|
| 1619 |
-
{
|
| 1620 |
-
"epoch": 1.6765799256505576,
|
| 1621 |
-
"grad_norm": 0.2937239110469818,
|
| 1622 |
-
"learning_rate": 3.1027622272189572e-06,
|
| 1623 |
-
"loss": 0.0010474955197423697,
|
| 1624 |
-
"step": 226
|
| 1625 |
-
},
|
| 1626 |
-
{
|
| 1627 |
-
"epoch": 1.6840148698884758,
|
| 1628 |
-
"grad_norm": 0.2832512855529785,
|
| 1629 |
-
"learning_rate": 3.024995881745972e-06,
|
| 1630 |
-
"loss": 0.0005706051597371697,
|
| 1631 |
-
"step": 227
|
| 1632 |
-
},
|
| 1633 |
-
{
|
| 1634 |
-
"epoch": 1.691449814126394,
|
| 1635 |
-
"grad_norm": 0.12802739441394806,
|
| 1636 |
-
"learning_rate": 2.948042467895544e-06,
|
| 1637 |
-
"loss": 0.0005536235403269529,
|
| 1638 |
-
"step": 228
|
| 1639 |
-
},
|
| 1640 |
-
{
|
| 1641 |
-
"epoch": 1.6988847583643123,
|
| 1642 |
-
"grad_norm": 1.1371771097183228,
|
| 1643 |
-
"learning_rate": 2.8719109545317102e-06,
|
| 1644 |
-
"loss": 0.0010236221132799983,
|
| 1645 |
-
"step": 229
|
| 1646 |
-
},
|
| 1647 |
-
{
|
| 1648 |
-
"epoch": 1.7063197026022305,
|
| 1649 |
-
"grad_norm": 0.2581642270088196,
|
| 1650 |
-
"learning_rate": 2.7966102147265993e-06,
|
| 1651 |
-
"loss": 0.0007985785487107933,
|
| 1652 |
-
"step": 230
|
| 1653 |
-
},
|
| 1654 |
-
{
|
| 1655 |
-
"epoch": 1.7137546468401488,
|
| 1656 |
-
"grad_norm": 0.24933426082134247,
|
| 1657 |
-
"learning_rate": 2.722149024726307e-06,
|
| 1658 |
-
"loss": 0.0009809861658141017,
|
| 1659 |
-
"step": 231
|
| 1660 |
-
},
|
| 1661 |
-
{
|
| 1662 |
-
"epoch": 1.7211895910780668,
|
| 1663 |
-
"grad_norm": 0.4896416664123535,
|
| 1664 |
-
"learning_rate": 2.648536062927999e-06,
|
| 1665 |
-
"loss": 0.001332507818005979,
|
| 1666 |
-
"step": 232
|
| 1667 |
-
},
|
| 1668 |
-
{
|
| 1669 |
-
"epoch": 1.7286245353159853,
|
| 1670 |
-
"grad_norm": 1.2645158767700195,
|
| 1671 |
-
"learning_rate": 2.5757799088684654e-06,
|
| 1672 |
-
"loss": 0.0014440901577472687,
|
| 1673 |
-
"step": 233
|
| 1674 |
-
},
|
| 1675 |
-
{
|
| 1676 |
-
"epoch": 1.7360594795539033,
|
| 1677 |
-
"grad_norm": 1.4792110919952393,
|
| 1678 |
-
"learning_rate": 2.5038890422241958e-06,
|
| 1679 |
-
"loss": 0.0013162668328732252,
|
| 1680 |
-
"step": 234
|
| 1681 |
-
},
|
| 1682 |
-
{
|
| 1683 |
-
"epoch": 1.7434944237918215,
|
| 1684 |
-
"grad_norm": 0.18054908514022827,
|
| 1685 |
-
"learning_rate": 2.432871841823047e-06,
|
| 1686 |
-
"loss": 0.0006657422054558992,
|
| 1687 |
-
"step": 235
|
| 1688 |
-
},
|
| 1689 |
-
{
|
| 1690 |
-
"epoch": 1.7509293680297398,
|
| 1691 |
-
"grad_norm": 0.13751235604286194,
|
| 1692 |
-
"learning_rate": 2.362736584667731e-06,
|
| 1693 |
-
"loss": 0.0005915165529586375,
|
| 1694 |
-
"step": 236
|
| 1695 |
-
},
|
| 1696 |
-
{
|
| 1697 |
-
"epoch": 1.758364312267658,
|
| 1698 |
-
"grad_norm": 0.7317216992378235,
|
| 1699 |
-
"learning_rate": 2.293491444971109e-06,
|
| 1700 |
-
"loss": 0.0014591675717383623,
|
| 1701 |
-
"step": 237
|
| 1702 |
-
},
|
| 1703 |
-
{
|
| 1704 |
-
"epoch": 1.7657992565055762,
|
| 1705 |
-
"grad_norm": 0.21496990323066711,
|
| 1706 |
-
"learning_rate": 2.2251444932035094e-06,
|
| 1707 |
-
"loss": 0.001061687944456935,
|
| 1708 |
-
"step": 238
|
| 1709 |
-
},
|
| 1710 |
-
{
|
| 1711 |
-
"epoch": 1.7732342007434945,
|
| 1712 |
-
"grad_norm": 0.2875332832336426,
|
| 1713 |
-
"learning_rate": 2.157703695152109e-06,
|
| 1714 |
-
"loss": 0.001086688251234591,
|
| 1715 |
-
"step": 239
|
| 1716 |
-
},
|
| 1717 |
-
{
|
| 1718 |
-
"epoch": 1.7806691449814127,
|
| 1719 |
-
"grad_norm": 0.09178756922483444,
|
| 1720 |
-
"learning_rate": 2.091176910992545e-06,
|
| 1721 |
-
"loss": 0.0005726361414417624,
|
| 1722 |
-
"step": 240
|
| 1723 |
-
},
|
| 1724 |
-
{
|
| 1725 |
-
"epoch": 1.7881040892193307,
|
| 1726 |
-
"grad_norm": 0.1605064868927002,
|
| 1727 |
-
"learning_rate": 2.025571894372794e-06,
|
| 1728 |
-
"loss": 0.0005661951145157218,
|
| 1729 |
-
"step": 241
|
| 1730 |
-
},
|
| 1731 |
-
{
|
| 1732 |
-
"epoch": 1.7955390334572492,
|
| 1733 |
-
"grad_norm": 0.10298097133636475,
|
| 1734 |
-
"learning_rate": 1.9608962915095e-06,
|
| 1735 |
-
"loss": 0.00041253669769503176,
|
| 1736 |
-
"step": 242
|
| 1737 |
-
},
|
| 1738 |
-
{
|
| 1739 |
-
"epoch": 1.8029739776951672,
|
| 1740 |
-
"grad_norm": 0.10088713467121124,
|
| 1741 |
-
"learning_rate": 1.897157640296825e-06,
|
| 1742 |
-
"loss": 0.0005594079266302288,
|
| 1743 |
-
"step": 243
|
| 1744 |
-
},
|
| 1745 |
-
{
|
| 1746 |
-
"epoch": 1.8104089219330854,
|
| 1747 |
-
"grad_norm": 0.08347094804048538,
|
| 1748 |
-
"learning_rate": 1.8343633694278895e-06,
|
| 1749 |
-
"loss": 0.0004925344837829471,
|
| 1750 |
-
"step": 244
|
| 1751 |
-
},
|
| 1752 |
-
{
|
| 1753 |
-
"epoch": 1.8178438661710037,
|
| 1754 |
-
"grad_norm": 0.1905243843793869,
|
| 1755 |
-
"learning_rate": 1.7725207975289883e-06,
|
| 1756 |
-
"loss": 0.0007212568307295442,
|
| 1757 |
-
"step": 245
|
| 1758 |
-
},
|
| 1759 |
-
{
|
| 1760 |
-
"epoch": 1.825278810408922,
|
| 1761 |
-
"grad_norm": 0.38704320788383484,
|
| 1762 |
-
"learning_rate": 1.7116371323065883e-06,
|
| 1763 |
-
"loss": 0.0008221275638788939,
|
| 1764 |
-
"step": 246
|
| 1765 |
-
},
|
| 1766 |
-
{
|
| 1767 |
-
"epoch": 1.8327137546468402,
|
| 1768 |
-
"grad_norm": 0.4447123110294342,
|
| 1769 |
-
"learning_rate": 1.6517194697072903e-06,
|
| 1770 |
-
"loss": 0.0011635192204266787,
|
| 1771 |
-
"step": 247
|
| 1772 |
-
},
|
| 1773 |
-
{
|
| 1774 |
-
"epoch": 1.8401486988847584,
|
| 1775 |
-
"grad_norm": 0.1510232537984848,
|
| 1776 |
-
"learning_rate": 1.5927747930907921e-06,
|
| 1777 |
-
"loss": 0.0005840228404849768,
|
| 1778 |
-
"step": 248
|
| 1779 |
-
},
|
| 1780 |
-
{
|
| 1781 |
-
"epoch": 1.8475836431226766,
|
| 1782 |
-
"grad_norm": 0.37208065390586853,
|
| 1783 |
-
"learning_rate": 1.534809972415998e-06,
|
| 1784 |
-
"loss": 0.0008757053292356431,
|
| 1785 |
-
"step": 249
|
| 1786 |
-
},
|
| 1787 |
-
{
|
| 1788 |
-
"epoch": 1.8550185873605947,
|
| 1789 |
-
"grad_norm": 0.11863338202238083,
|
| 1790 |
-
"learning_rate": 1.4778317634403082e-06,
|
| 1791 |
-
"loss": 0.0006142967031337321,
|
| 1792 |
-
"step": 250
|
| 1793 |
-
},
|
| 1794 |
-
{
|
| 1795 |
-
"epoch": 1.8550185873605947,
|
| 1796 |
-
"eval_loss": 0.0005828889552503824,
|
| 1797 |
-
"eval_runtime": 25.3796,
|
| 1798 |
-
"eval_samples_per_second": 0.433,
|
| 1799 |
-
"eval_steps_per_second": 0.433,
|
| 1800 |
-
"step": 250
|
| 1801 |
-
},
|
| 1802 |
-
{
|
| 1803 |
-
"epoch": 1.8624535315985131,
|
| 1804 |
-
"grad_norm": 0.4753115475177765,
|
| 1805 |
-
"learning_rate": 1.4218468069322576e-06,
|
| 1806 |
-
"loss": 0.0005684165516868234,
|
| 1807 |
-
"step": 251
|
| 1808 |
-
},
|
| 1809 |
-
{
|
| 1810 |
-
"epoch": 1.8698884758364311,
|
| 1811 |
-
"grad_norm": 0.6209020614624023,
|
| 1812 |
-
"learning_rate": 1.3668616278975343e-06,
|
| 1813 |
-
"loss": 0.0006938453880138695,
|
| 1814 |
-
"step": 252
|
| 1815 |
-
},
|
| 1816 |
-
{
|
| 1817 |
-
"epoch": 1.8773234200743496,
|
| 1818 |
-
"grad_norm": 0.13119417428970337,
|
| 1819 |
-
"learning_rate": 1.3128826348184886e-06,
|
| 1820 |
-
"loss": 0.0008722958737052977,
|
| 1821 |
-
"step": 253
|
| 1822 |
-
},
|
| 1823 |
-
{
|
| 1824 |
-
"epoch": 1.8847583643122676,
|
| 1825 |
-
"grad_norm": 0.05212293937802315,
|
| 1826 |
-
"learning_rate": 1.2599161189072428e-06,
|
| 1827 |
-
"loss": 0.0004048564878758043,
|
| 1828 |
-
"step": 254
|
| 1829 |
-
},
|
| 1830 |
-
{
|
| 1831 |
-
"epoch": 1.8921933085501859,
|
| 1832 |
-
"grad_norm": 0.09230067580938339,
|
| 1833 |
-
"learning_rate": 1.207968253372438e-06,
|
| 1834 |
-
"loss": 0.0004900405765511096,
|
| 1835 |
-
"step": 255
|
| 1836 |
-
},
|
| 1837 |
-
{
|
| 1838 |
-
"epoch": 1.899628252788104,
|
| 1839 |
-
"grad_norm": 2.7577662467956543,
|
| 1840 |
-
"learning_rate": 1.1570450926997657e-06,
|
| 1841 |
-
"loss": 0.00596074853092432,
|
| 1842 |
-
"step": 256
|
| 1843 |
-
},
|
| 1844 |
-
{
|
| 1845 |
-
"epoch": 1.9070631970260223,
|
| 1846 |
-
"grad_norm": 1.3561674356460571,
|
| 1847 |
-
"learning_rate": 1.1071525719463094e-06,
|
| 1848 |
-
"loss": 0.003298816503956914,
|
| 1849 |
-
"step": 257
|
| 1850 |
-
},
|
| 1851 |
-
{
|
| 1852 |
-
"epoch": 1.9144981412639406,
|
| 1853 |
-
"grad_norm": 0.10489499568939209,
|
| 1854 |
-
"learning_rate": 1.058296506048836e-06,
|
| 1855 |
-
"loss": 0.0005693072453141212,
|
| 1856 |
-
"step": 258
|
| 1857 |
-
},
|
| 1858 |
-
{
|
| 1859 |
-
"epoch": 1.9219330855018586,
|
| 1860 |
-
"grad_norm": 0.03541704639792442,
|
| 1861 |
-
"learning_rate": 1.010482589146048e-06,
|
| 1862 |
-
"loss": 0.0003265823470428586,
|
| 1863 |
-
"step": 259
|
| 1864 |
-
},
|
| 1865 |
-
{
|
| 1866 |
-
"epoch": 1.929368029739777,
|
| 1867 |
-
"grad_norm": 0.04660625010728836,
|
| 1868 |
-
"learning_rate": 9.637163939149485e-07,
|
| 1869 |
-
"loss": 0.00038790475809946656,
|
| 1870 |
-
"step": 260
|
| 1871 |
-
},
|
| 1872 |
-
{
|
| 1873 |
-
"epoch": 1.936802973977695,
|
| 1874 |
-
"grad_norm": 0.12105000764131546,
|
| 1875 |
-
"learning_rate": 9.180033709213454e-07,
|
| 1876 |
-
"loss": 0.000698139367159456,
|
| 1877 |
-
"step": 261
|
| 1878 |
-
},
|
| 1879 |
-
{
|
| 1880 |
-
"epoch": 1.9442379182156135,
|
| 1881 |
-
"grad_norm": 0.06474104523658752,
|
| 1882 |
-
"learning_rate": 8.733488479845997e-07,
|
| 1883 |
-
"loss": 0.00024097770801745355,
|
| 1884 |
-
"step": 262
|
| 1885 |
-
},
|
| 1886 |
-
{
|
| 1887 |
-
"epoch": 1.9516728624535316,
|
| 1888 |
-
"grad_norm": 0.0482507087290287,
|
| 1889 |
-
"learning_rate": 8.297580295566576e-07,
|
| 1890 |
-
"loss": 0.0003770535986404866,
|
| 1891 |
-
"step": 263
|
| 1892 |
-
},
|
| 1893 |
-
{
|
| 1894 |
-
"epoch": 1.9591078066914498,
|
| 1895 |
-
"grad_norm": 0.08156494051218033,
|
| 1896 |
-
"learning_rate": 7.872359961154907e-07,
|
| 1897 |
-
"loss": 0.0005116399261169136,
|
| 1898 |
-
"step": 264
|
| 1899 |
-
},
|
| 1900 |
-
{
|
| 1901 |
-
"epoch": 1.966542750929368,
|
| 1902 |
-
"grad_norm": 0.04401222988963127,
|
| 1903 |
-
"learning_rate": 7.457877035729588e-07,
|
| 1904 |
-
"loss": 0.00033355015330016613,
|
| 1905 |
-
"step": 265
|
| 1906 |
-
},
|
| 1907 |
-
{
|
| 1908 |
-
"epoch": 1.9739776951672863,
|
| 1909 |
-
"grad_norm": 0.05555126443505287,
|
| 1910 |
-
"learning_rate": 7.054179826972074e-07,
|
| 1911 |
-
"loss": 0.0005097900284454226,
|
| 1912 |
-
"step": 266
|
| 1913 |
-
},
|
| 1914 |
-
{
|
| 1915 |
-
"epoch": 1.9814126394052045,
|
| 1916 |
-
"grad_norm": 0.06824725866317749,
|
| 1917 |
-
"learning_rate": 6.661315385496426e-07,
|
| 1918 |
-
"loss": 0.0005295310402289033,
|
| 1919 |
-
"step": 267
|
| 1920 |
-
},
|
| 1921 |
-
{
|
| 1922 |
-
"epoch": 1.9888475836431225,
|
| 1923 |
-
"grad_norm": 0.1338755488395691,
|
| 1924 |
-
"learning_rate": 6.279329499365649e-07,
|
| 1925 |
-
"loss": 0.000684445898514241,
|
| 1926 |
-
"step": 268
|
| 1927 |
-
},
|
| 1928 |
-
{
|
| 1929 |
-
"epoch": 1.996282527881041,
|
| 1930 |
-
"grad_norm": 0.10122767835855484,
|
| 1931 |
-
"learning_rate": 5.908266688755049e-07,
|
| 1932 |
-
"loss": 0.0006487981881946325,
|
| 1933 |
-
"step": 269
|
| 1934 |
-
},
|
| 1935 |
-
{
|
| 1936 |
-
"epoch": 2.0,
|
| 1937 |
-
"grad_norm": 0.22046668827533722,
|
| 1938 |
-
"learning_rate": 5.54817020076347e-07,
|
| 1939 |
-
"loss": 0.0005617543356493115,
|
| 1940 |
-
"step": 270
|
| 1941 |
-
},
|
| 1942 |
-
{
|
| 1943 |
-
"epoch": 2.007434944237918,
|
| 1944 |
-
"grad_norm": 0.049495428800582886,
|
| 1945 |
-
"learning_rate": 5.199082004372958e-07,
|
| 1946 |
-
"loss": 0.0002831058227457106,
|
| 1947 |
-
"step": 271
|
| 1948 |
-
},
|
| 1949 |
-
{
|
| 1950 |
-
"epoch": 2.0148698884758365,
|
| 1951 |
-
"grad_norm": 0.051289305090904236,
|
| 1952 |
-
"learning_rate": 4.861042785557147e-07,
|
| 1953 |
-
"loss": 0.00032035651383921504,
|
| 1954 |
-
"step": 272
|
| 1955 |
-
},
|
| 1956 |
-
{
|
| 1957 |
-
"epoch": 2.0223048327137545,
|
| 1958 |
-
"grad_norm": 0.04580337926745415,
|
| 1959 |
-
"learning_rate": 4.534091942539476e-07,
|
| 1960 |
-
"loss": 0.0003928366641048342,
|
| 1961 |
-
"step": 273
|
| 1962 |
-
},
|
| 1963 |
-
{
|
| 1964 |
-
"epoch": 2.029739776951673,
|
| 1965 |
-
"grad_norm": 0.057850733399391174,
|
| 1966 |
-
"learning_rate": 4.218267581201296e-07,
|
| 1967 |
-
"loss": 0.00045185262570157647,
|
| 1968 |
-
"step": 274
|
| 1969 |
-
},
|
| 1970 |
-
{
|
| 1971 |
-
"epoch": 2.037174721189591,
|
| 1972 |
-
"grad_norm": 0.05098224803805351,
|
| 1973 |
-
"learning_rate": 3.913606510640644e-07,
|
| 1974 |
-
"loss": 0.0003131507837679237,
|
| 1975 |
-
"step": 275
|
| 1976 |
-
},
|
| 1977 |
-
{
|
| 1978 |
-
"epoch": 2.0446096654275094,
|
| 1979 |
-
"grad_norm": 0.1178661659359932,
|
| 1980 |
-
"learning_rate": 3.620144238882206e-07,
|
| 1981 |
-
"loss": 0.0007142139365896583,
|
| 1982 |
-
"step": 276
|
| 1983 |
-
},
|
| 1984 |
-
{
|
| 1985 |
-
"epoch": 2.0520446096654275,
|
| 1986 |
-
"grad_norm": 0.3379584550857544,
|
| 1987 |
-
"learning_rate": 3.3379149687388866e-07,
|
| 1988 |
-
"loss": 0.0004891973803751171,
|
| 1989 |
-
"step": 277
|
| 1990 |
-
},
|
| 1991 |
-
{
|
| 1992 |
-
"epoch": 2.059479553903346,
|
| 1993 |
-
"grad_norm": 0.957190215587616,
|
| 1994 |
-
"learning_rate": 3.0669515938254404e-07,
|
| 1995 |
-
"loss": 0.00264157191850245,
|
| 1996 |
-
"step": 278
|
| 1997 |
-
},
|
| 1998 |
-
{
|
| 1999 |
-
"epoch": 2.066914498141264,
|
| 2000 |
-
"grad_norm": 0.05272980034351349,
|
| 2001 |
-
"learning_rate": 2.807285694724804e-07,
|
| 2002 |
-
"loss": 0.0003561996854841709,
|
| 2003 |
-
"step": 279
|
| 2004 |
-
},
|
| 2005 |
-
{
|
| 2006 |
-
"epoch": 2.074349442379182,
|
| 2007 |
-
"grad_norm": 0.05989179015159607,
|
| 2008 |
-
"learning_rate": 2.5589475353073987e-07,
|
| 2009 |
-
"loss": 0.0004683621518779546,
|
| 2010 |
-
"step": 280
|
| 2011 |
-
},
|
| 2012 |
-
{
|
| 2013 |
-
"epoch": 2.0817843866171004,
|
| 2014 |
-
"grad_norm": 0.05498693510890007,
|
| 2015 |
-
"learning_rate": 2.3219660592038285e-07,
|
| 2016 |
-
"loss": 0.00034518816391937435,
|
| 2017 |
-
"step": 281
|
| 2018 |
-
},
|
| 2019 |
-
{
|
| 2020 |
-
"epoch": 2.0892193308550184,
|
| 2021 |
-
"grad_norm": 0.04088941216468811,
|
| 2022 |
-
"learning_rate": 2.0963688864316324e-07,
|
| 2023 |
-
"loss": 0.00025010405806824565,
|
| 2024 |
-
"step": 282
|
| 2025 |
-
},
|
| 2026 |
-
{
|
| 2027 |
-
"epoch": 2.096654275092937,
|
| 2028 |
-
"grad_norm": 0.0437583401799202,
|
| 2029 |
-
"learning_rate": 1.8821823101760949e-07,
|
| 2030 |
-
"loss": 0.0003774496726691723,
|
| 2031 |
-
"step": 283
|
| 2032 |
-
},
|
| 2033 |
-
{
|
| 2034 |
-
"epoch": 2.104089219330855,
|
| 2035 |
-
"grad_norm": 0.40435388684272766,
|
| 2036 |
-
"learning_rate": 1.6794312937258417e-07,
|
| 2037 |
-
"loss": 0.00038810307160019875,
|
| 2038 |
-
"step": 284
|
| 2039 |
-
},
|
| 2040 |
-
{
|
| 2041 |
-
"epoch": 2.1115241635687734,
|
| 2042 |
-
"grad_norm": 0.08561220020055771,
|
| 2043 |
-
"learning_rate": 1.4881394675633543e-07,
|
| 2044 |
-
"loss": 0.00043630838626995683,
|
| 2045 |
-
"step": 285
|
| 2046 |
-
},
|
| 2047 |
-
{
|
| 2048 |
-
"epoch": 2.1189591078066914,
|
| 2049 |
-
"grad_norm": 0.05500214546918869,
|
| 2050 |
-
"learning_rate": 1.30832912661093e-07,
|
| 2051 |
-
"loss": 0.0002762812946457416,
|
| 2052 |
-
"step": 286
|
| 2053 |
-
},
|
| 2054 |
-
{
|
| 2055 |
-
"epoch": 2.12639405204461,
|
| 2056 |
-
"grad_norm": 0.055472973734140396,
|
| 2057 |
-
"learning_rate": 1.1400212276321377e-07,
|
| 2058 |
-
"loss": 0.0004420560726430267,
|
| 2059 |
-
"step": 287
|
| 2060 |
-
},
|
| 2061 |
-
{
|
| 2062 |
-
"epoch": 2.133828996282528,
|
| 2063 |
-
"grad_norm": 0.07219704985618591,
|
| 2064 |
-
"learning_rate": 9.832353867893385e-08,
|
| 2065 |
-
"loss": 0.00048654654528945684,
|
| 2066 |
-
"step": 288
|
| 2067 |
-
},
|
| 2068 |
-
{
|
| 2069 |
-
"epoch": 2.141263940520446,
|
| 2070 |
-
"grad_norm": 0.07219995558261871,
|
| 2071 |
-
"learning_rate": 8.379898773574924e-08,
|
| 2072 |
-
"loss": 0.0005200268933549523,
|
| 2073 |
-
"step": 289
|
| 2074 |
-
},
|
| 2075 |
-
{
|
| 2076 |
-
"epoch": 2.1486988847583643,
|
| 2077 |
-
"grad_norm": 0.045199330896139145,
|
| 2078 |
-
"learning_rate": 7.043016275943614e-08,
|
| 2079 |
-
"loss": 0.0003803567960858345,
|
| 2080 |
-
"step": 290
|
| 2081 |
-
},
|
| 2082 |
-
{
|
| 2083 |
-
"epoch": 2.1561338289962824,
|
| 2084 |
-
"grad_norm": 0.5883752703666687,
|
| 2085 |
-
"learning_rate": 5.821862187675775e-08,
|
| 2086 |
-
"loss": 0.0005831126472912729,
|
| 2087 |
-
"step": 291
|
| 2088 |
-
},
|
| 2089 |
-
{
|
| 2090 |
-
"epoch": 2.163568773234201,
|
| 2091 |
-
"grad_norm": 0.08384323120117188,
|
| 2092 |
-
"learning_rate": 4.716578833386054e-08,
|
| 2093 |
-
"loss": 0.00043936495785601437,
|
| 2094 |
-
"step": 292
|
| 2095 |
-
},
|
| 2096 |
-
{
|
| 2097 |
-
"epoch": 2.171003717472119,
|
| 2098 |
-
"grad_norm": 0.04956158995628357,
|
| 2099 |
-
"learning_rate": 3.727295033040035e-08,
|
| 2100 |
-
"loss": 0.000401977333240211,
|
| 2101 |
-
"step": 293
|
| 2102 |
-
},
|
| 2103 |
-
{
|
| 2104 |
-
"epoch": 2.1784386617100373,
|
| 2105 |
-
"grad_norm": 0.03216640651226044,
|
| 2106 |
-
"learning_rate": 2.8541260869403565e-08,
|
| 2107 |
-
"loss": 0.0002383627142990008,
|
| 2108 |
-
"step": 294
|
| 2109 |
-
},
|
| 2110 |
-
{
|
| 2111 |
-
"epoch": 2.1858736059479553,
|
| 2112 |
-
"grad_norm": 0.21096163988113403,
|
| 2113 |
-
"learning_rate": 2.0971737622883515e-08,
|
| 2114 |
-
"loss": 0.000635640521068126,
|
| 2115 |
-
"step": 295
|
| 2116 |
-
},
|
| 2117 |
-
{
|
| 2118 |
-
"epoch": 2.193308550185874,
|
| 2119 |
-
"grad_norm": 0.06296732276678085,
|
| 2120 |
-
"learning_rate": 1.4565262813230896e-08,
|
| 2121 |
-
"loss": 0.00035777079756371677,
|
| 2122 |
-
"step": 296
|
| 2123 |
-
},
|
| 2124 |
-
{
|
| 2125 |
-
"epoch": 2.200743494423792,
|
| 2126 |
-
"grad_norm": 0.07209618389606476,
|
| 2127 |
-
"learning_rate": 9.322583110392692e-09,
|
| 2128 |
-
"loss": 0.0003764816792681813,
|
| 2129 |
-
"step": 297
|
| 2130 |
-
},
|
| 2131 |
-
{
|
| 2132 |
-
"epoch": 2.20817843866171,
|
| 2133 |
-
"grad_norm": 0.08437097072601318,
|
| 2134 |
-
"learning_rate": 5.2443095448506674e-09,
|
| 2135 |
-
"loss": 0.0005360089126043022,
|
| 2136 |
-
"step": 298
|
| 2137 |
-
},
|
| 2138 |
-
{
|
| 2139 |
-
"epoch": 2.2156133828996283,
|
| 2140 |
-
"grad_norm": 0.049833204597234726,
|
| 2141 |
-
"learning_rate": 2.330917436402791e-09,
|
| 2142 |
-
"loss": 0.000445480109192431,
|
| 2143 |
-
"step": 299
|
| 2144 |
-
},
|
| 2145 |
-
{
|
| 2146 |
-
"epoch": 2.2230483271375463,
|
| 2147 |
-
"grad_norm": 0.1327083259820938,
|
| 2148 |
-
"learning_rate": 5.827463387653165e-10,
|
| 2149 |
-
"loss": 0.0004715001559816301,
|
| 2150 |
-
"step": 300
|
| 2151 |
-
},
|
| 2152 |
-
{
|
| 2153 |
-
"epoch": 2.2230483271375463,
|
| 2154 |
-
"eval_loss": 0.0005094278603792191,
|
| 2155 |
-
"eval_runtime": 25.4287,
|
| 2156 |
-
"eval_samples_per_second": 0.433,
|
| 2157 |
-
"eval_steps_per_second": 0.433,
|
| 2158 |
-
"step": 300
|
| 2159 |
-
},
|
| 2160 |
-
{
|
| 2161 |
-
"epoch": 2.2230483271375463,
|
| 2162 |
-
"step": 300,
|
| 2163 |
-
"total_flos": 9.267981213438605e+17,
|
| 2164 |
-
"train_loss": 0.36306977348348785,
|
| 2165 |
-
"train_runtime": 18396.5429,
|
| 2166 |
-
"train_samples_per_second": 0.13,
|
| 2167 |
-
"train_steps_per_second": 0.016
|
| 2168 |
-
}
|
| 2169 |
-
],
|
| 2170 |
-
"logging_steps": 1,
|
| 2171 |
-
"max_steps": 300,
|
| 2172 |
-
"num_input_tokens_seen": 0,
|
| 2173 |
-
"num_train_epochs": 3,
|
| 2174 |
-
"save_steps": 100,
|
| 2175 |
-
"stateful_callbacks": {
|
| 2176 |
-
"TrainerControl": {
|
| 2177 |
-
"args": {
|
| 2178 |
-
"should_epoch_stop": false,
|
| 2179 |
-
"should_evaluate": false,
|
| 2180 |
-
"should_log": false,
|
| 2181 |
-
"should_save": true,
|
| 2182 |
-
"should_training_stop": true
|
| 2183 |
-
},
|
| 2184 |
-
"attributes": {}
|
| 2185 |
-
}
|
| 2186 |
-
},
|
| 2187 |
-
"total_flos": 9.267981213438605e+17,
|
| 2188 |
-
"train_batch_size": 1,
|
| 2189 |
-
"trial_name": null,
|
| 2190 |
-
"trial_params": null
|
| 2191 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_eval_loss.png
DELETED
|
Binary file (35.6 kB)
|
|
|
training_loss.png
DELETED
|
Binary file (35.7 kB)
|
|
|