xdotli commited on
Commit
04f8298
·
verified ·
1 Parent(s): 5b02f4d

Replace with general-agent Qwen3.5 step-200 LoRA adapter

Browse files

Clean 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 CHANGED
@@ -1,39 +1,8 @@
1
- ---
2
- base_model: Qwen/Qwen3.5-9B
3
- library_name: peft
4
- pipeline_tag: text-generation
5
- tags:
6
- - peft
7
- - lora
8
- - qwen3.5
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
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
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
- "k_proj",
33
- "in_proj_z",
34
  "gate_proj",
35
- "in_proj_b",
36
  "o_proj",
37
- "v_proj",
38
- "in_proj_qkv",
39
- "down_proj",
40
  "q_proj",
41
- "in_proj_a",
42
- "out_proj",
43
- "up_proj"
44
  ],
45
- "target_parameters": null,
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 sha256:6b92737832847b9966babd7d250107090a6641db8dcd7d6ed8d0ad52fa9f5ef9
3
- size 692529024
 
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": "<|endoftext|>",
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)