Hugging Face's logo

HANI-LAB
/
Med-REFL-Huatuo-o1-8B-lora

Text Generation
Safetensors
English
medical
medical-reasoning
lora
dpo
reflection
Model card Files
xet
Community
1
CityU-Zongxian commited on
Commit
49751cd
·
verified ·
1 Parent(s): a672d3f

Upload 13 files

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. huatuo-o1-Med-REFL-LoraAdapter/README.md +62 -0
  3. huatuo-o1-Med-REFL-LoraAdapter/adapter_config.json +39 -0
  4. huatuo-o1-Med-REFL-LoraAdapter/adapter_model.safetensors +3 -0
  5. huatuo-o1-Med-REFL-LoraAdapter/all_results.json +9 -0
  6. huatuo-o1-Med-REFL-LoraAdapter/special_tokens_map.json +39 -0
  7. huatuo-o1-Med-REFL-LoraAdapter/tokenizer.json +3 -0
  8. huatuo-o1-Med-REFL-LoraAdapter/tokenizer_config.json +2070 -0
  9. huatuo-o1-Med-REFL-LoraAdapter/train_results.json +9 -0
  10. huatuo-o1-Med-REFL-LoraAdapter/trainer_log.jsonl +262 -0
  11. huatuo-o1-Med-REFL-LoraAdapter/trainer_state.json +0 -0
  12. huatuo-o1-Med-REFL-LoraAdapter/training_args.bin +3 -0
  13. huatuo-o1-Med-REFL-LoraAdapter/training_loss.png +0 -0
  14. huatuo-o1-Med-REFL-LoraAdapter/training_rewards_accuracies.png +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ huatuo-o1-Med-REFL-LoraAdapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
huatuo-o1-Med-REFL-LoraAdapter/README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: /home/yangzongxian/zongxian/Models/huatuo-o1
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Huatuo_Stage2_allPart
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Huatuo_Stage2_allPart
18
+
19
+ This model is a fine-tuned version of [/home/yangzongxian/zongxian/Models/huatuo-o1](https://huggingface.co//home/yangzongxian/zongxian/Models/huatuo-o1) on the DPO_merged_Stage2_Part1+2 dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 2
44
+ - gradient_accumulation_steps: 16
45
+ - total_train_batch_size: 128
46
+ - total_eval_batch_size: 16
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_steps: 10
50
+ - num_epochs: 1.0
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - PEFT 0.15.0
59
+ - Transformers 4.50.0
60
+ - Pytorch 2.6.0+cu124
61
+ - Datasets 3.1.0
62
+ - Tokenizers 0.21.0
huatuo-o1-Med-REFL-LoraAdapter/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/yangzongxian/zongxian/Models/huatuo-o1",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "o_proj",
29
+ "v_proj",
30
+ "up_proj",
31
+ "gate_proj",
32
+ "down_proj",
33
+ "k_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
huatuo-o1-Med-REFL-LoraAdapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:803941cc8bda379835131d4bb59bc094d2ac552490f947aec81f5f0a367713c6
3
+ size 671149168
huatuo-o1-Med-REFL-LoraAdapter/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997605937275557,
3
+ "num_input_tokens_seen": 93801152,
4
+ "total_flos": 4.318246812239528e+18,
5
+ "train_loss": 0.2454147177009747,
6
+ "train_runtime": 22841.5151,
7
+ "train_samples_per_second": 1.463,
8
+ "train_steps_per_second": 0.011
9
+ }
huatuo-o1-Med-REFL-LoraAdapter/special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eot_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|eom_id|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<|begin_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|eot_id|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "<|end_of_text|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
huatuo-o1-Med-REFL-LoraAdapter/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
huatuo-o1-Med-REFL-LoraAdapter/tokenizer_config.json ADDED
@@ -0,0 +1,2070 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "additional_special_tokens": [
2053
+ "<|eot_id|>",
2054
+ "<|eom_id|>"
2055
+ ],
2056
+ "bos_token": "<|begin_of_text|>",
2057
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2058
+ "clean_up_tokenization_spaces": true,
2059
+ "eos_token": "<|eot_id|>",
2060
+ "extra_special_tokens": {},
2061
+ "model_input_names": [
2062
+ "input_ids",
2063
+ "attention_mask"
2064
+ ],
2065
+ "model_max_length": 131072,
2066
+ "pad_token": "<|end_of_text|>",
2067
+ "padding_side": "right",
2068
+ "split_special_tokens": false,
2069
+ "tokenizer_class": "PreTrainedTokenizer"
2070
+ }
huatuo-o1-Med-REFL-LoraAdapter/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997605937275557,
3
+ "num_input_tokens_seen": 93801152,
4
+ "total_flos": 4.318246812239528e+18,
5
+ "train_loss": 0.2454147177009747,
6
+ "train_runtime": 22841.5151,
7
+ "train_samples_per_second": 1.463,
8
+ "train_steps_per_second": 0.011
9
+ }
huatuo-o1-Med-REFL-LoraAdapter/trainer_log.jsonl ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 261, "loss": 0.6931, "accuracy": 0.0, "lr": 1.0000000000000002e-06, "epoch": 0.0038305003591094086, "percentage": 0.38, "elapsed_time": "0:01:31", "remaining_time": "6:36:49", "throughput": 3958.44, "total_tokens": 362496}
2
+ {"current_steps": 2, "total_steps": 261, "loss": 0.6931, "accuracy": 0.0, "lr": 2.0000000000000003e-06, "epoch": 0.007661000718218817, "percentage": 0.77, "elapsed_time": "0:02:59", "remaining_time": "6:26:46", "throughput": 4007.56, "total_tokens": 718144}
3
+ {"current_steps": 3, "total_steps": 261, "loss": 0.7036, "accuracy": 0.4375, "lr": 3e-06, "epoch": 0.011491501077328227, "percentage": 1.15, "elapsed_time": "0:04:26", "remaining_time": "6:21:19", "throughput": 4042.19, "total_tokens": 1075392}
4
+ {"current_steps": 4, "total_steps": 261, "loss": 0.6913, "accuracy": 0.5390625, "lr": 4.000000000000001e-06, "epoch": 0.015322001436437634, "percentage": 1.53, "elapsed_time": "0:05:53", "remaining_time": "6:18:56", "throughput": 4041.16, "total_tokens": 1430080}
5
+ {"current_steps": 5, "total_steps": 261, "loss": 0.6978, "accuracy": 0.5, "lr": 5e-06, "epoch": 0.019152501795547044, "percentage": 1.92, "elapsed_time": "0:07:20", "remaining_time": "6:15:32", "throughput": 4059.0, "total_tokens": 1786304}
6
+ {"current_steps": 6, "total_steps": 261, "loss": 0.6808, "accuracy": 0.6015625, "lr": 6e-06, "epoch": 0.022983002154656453, "percentage": 2.3, "elapsed_time": "0:08:45", "remaining_time": "6:12:22", "throughput": 4056.45, "total_tokens": 2132544}
7
+ {"current_steps": 7, "total_steps": 261, "loss": 0.6866, "accuracy": 0.546875, "lr": 7e-06, "epoch": 0.02681350251376586, "percentage": 2.68, "elapsed_time": "0:10:12", "remaining_time": "6:10:27", "throughput": 4062.86, "total_tokens": 2488832}
8
+ {"current_steps": 8, "total_steps": 261, "loss": 0.6897, "accuracy": 0.515625, "lr": 8.000000000000001e-06, "epoch": 0.03064400287287527, "percentage": 3.07, "elapsed_time": "0:11:42", "remaining_time": "6:10:29", "throughput": 4058.27, "total_tokens": 2852544}
9
+ {"current_steps": 9, "total_steps": 261, "loss": 0.6901, "accuracy": 0.5546875, "lr": 9e-06, "epoch": 0.03447450323198468, "percentage": 3.45, "elapsed_time": "0:13:11", "remaining_time": "6:09:21", "throughput": 4069.02, "total_tokens": 3220608}
10
+ {"current_steps": 10, "total_steps": 261, "loss": 0.691, "accuracy": 0.53125, "lr": 1e-05, "epoch": 0.03830500359109409, "percentage": 3.83, "elapsed_time": "0:14:42", "remaining_time": "6:09:01", "throughput": 4072.11, "total_tokens": 3592128}
11
+ {"current_steps": 11, "total_steps": 261, "loss": 0.6915, "accuracy": 0.5, "lr": 9.999608360361114e-06, "epoch": 0.0421355039502035, "percentage": 4.21, "elapsed_time": "0:16:11", "remaining_time": "6:08:05", "throughput": 4086.82, "total_tokens": 3971392}
12
+ {"current_steps": 12, "total_steps": 261, "loss": 0.691, "accuracy": 0.515625, "lr": 9.998433502797097e-06, "epoch": 0.045966004309312906, "percentage": 4.6, "elapsed_time": "0:17:39", "remaining_time": "6:06:20", "throughput": 4085.34, "total_tokens": 4327552}
13
+ {"current_steps": 13, "total_steps": 261, "loss": 0.6828, "accuracy": 0.59375, "lr": 9.996475611356265e-06, "epoch": 0.049796504668422316, "percentage": 4.98, "elapsed_time": "0:19:10", "remaining_time": "6:05:48", "throughput": 4086.45, "total_tokens": 4701568}
14
+ {"current_steps": 14, "total_steps": 261, "loss": 0.6787, "accuracy": 0.6640625, "lr": 9.993734992753777e-06, "epoch": 0.05362700502753172, "percentage": 5.36, "elapsed_time": "0:20:37", "remaining_time": "6:03:49", "throughput": 4086.74, "total_tokens": 5056448}
15
+ {"current_steps": 15, "total_steps": 261, "loss": 0.6765, "accuracy": 0.6015625, "lr": 9.990212076323587e-06, "epoch": 0.05745750538664113, "percentage": 5.75, "elapsed_time": "0:22:00", "remaining_time": "6:00:58", "throughput": 4092.81, "total_tokens": 5405056}
16
+ {"current_steps": 16, "total_steps": 261, "loss": 0.6792, "accuracy": 0.6015625, "lr": 9.98590741395118e-06, "epoch": 0.06128800574575054, "percentage": 6.13, "elapsed_time": "0:23:28", "remaining_time": "5:59:21", "throughput": 4089.47, "total_tokens": 5758464}
17
+ {"current_steps": 17, "total_steps": 261, "loss": 0.6786, "accuracy": 0.59375, "lr": 9.980821679987125e-06, "epoch": 0.06511850610485995, "percentage": 6.51, "elapsed_time": "0:24:53", "remaining_time": "5:57:16", "throughput": 4095.4, "total_tokens": 6116480}
18
+ {"current_steps": 18, "total_steps": 261, "loss": 0.6739, "accuracy": 0.5703125, "lr": 9.974955671141425e-06, "epoch": 0.06894900646396936, "percentage": 6.9, "elapsed_time": "0:26:23", "remaining_time": "5:56:13", "throughput": 4094.55, "total_tokens": 6482624}
19
+ {"current_steps": 19, "total_steps": 261, "loss": 0.66, "accuracy": 0.6640625, "lr": 9.968310306358715e-06, "epoch": 0.07277950682307877, "percentage": 7.28, "elapsed_time": "0:27:49", "remaining_time": "5:54:27", "throughput": 4093.83, "total_tokens": 6835712}
20
+ {"current_steps": 20, "total_steps": 261, "loss": 0.6575, "accuracy": 0.6484375, "lr": 9.960886626674302e-06, "epoch": 0.07661000718218818, "percentage": 7.66, "elapsed_time": "0:29:17", "remaining_time": "5:53:02", "throughput": 4086.25, "total_tokens": 7183040}
21
+ {"current_steps": 21, "total_steps": 261, "loss": 0.6635, "accuracy": 0.6484375, "lr": 9.952685795051078e-06, "epoch": 0.08044050754129758, "percentage": 8.05, "elapsed_time": "0:30:49", "remaining_time": "5:52:15", "throughput": 4083.65, "total_tokens": 7552000}
22
+ {"current_steps": 22, "total_steps": 261, "loss": 0.6437, "accuracy": 0.7109375, "lr": 9.943709096197334e-06, "epoch": 0.084271007900407, "percentage": 8.43, "elapsed_time": "0:32:19", "remaining_time": "5:51:14", "throughput": 4082.07, "total_tokens": 7918784}
23
+ {"current_steps": 23, "total_steps": 261, "loss": 0.6572, "accuracy": 0.6953125, "lr": 9.933957936365515e-06, "epoch": 0.0881015082595164, "percentage": 8.81, "elapsed_time": "0:33:45", "remaining_time": "5:49:24", "throughput": 4084.71, "total_tokens": 8275392}
24
+ {"current_steps": 24, "total_steps": 261, "loss": 0.6214, "accuracy": 0.734375, "lr": 9.9234338431319e-06, "epoch": 0.09193200861862581, "percentage": 9.2, "elapsed_time": "0:35:11", "remaining_time": "5:47:31", "throughput": 4087.57, "total_tokens": 8630976}
25
+ {"current_steps": 25, "total_steps": 261, "loss": 0.6145, "accuracy": 0.75, "lr": 9.912138465157325e-06, "epoch": 0.09576250897773522, "percentage": 9.58, "elapsed_time": "0:36:40", "remaining_time": "5:46:15", "throughput": 4086.95, "total_tokens": 8994496}
26
+ {"current_steps": 26, "total_steps": 261, "loss": 0.6296, "accuracy": 0.75, "lr": 9.900073571928887e-06, "epoch": 0.09959300933684463, "percentage": 9.96, "elapsed_time": "0:38:11", "remaining_time": "5:45:10", "throughput": 4086.41, "total_tokens": 9363648}
27
+ {"current_steps": 27, "total_steps": 261, "loss": 0.6069, "accuracy": 0.7578125, "lr": 9.887241053482756e-06, "epoch": 0.10342350969595403, "percentage": 10.34, "elapsed_time": "0:39:38", "remaining_time": "5:43:30", "throughput": 4085.85, "total_tokens": 9716544}
28
+ {"current_steps": 28, "total_steps": 261, "loss": 0.5903, "accuracy": 0.8046875, "lr": 9.87364292010809e-06, "epoch": 0.10725401005506344, "percentage": 10.73, "elapsed_time": "0:41:01", "remaining_time": "5:41:26", "throughput": 4087.31, "total_tokens": 10062592}
29
+ {"current_steps": 29, "total_steps": 261, "loss": 0.5922, "accuracy": 0.8203125, "lr": 9.859281302032107e-06, "epoch": 0.11108451041417285, "percentage": 11.11, "elapsed_time": "0:42:27", "remaining_time": "5:39:43", "throughput": 4088.1, "total_tokens": 10416320}
30
+ {"current_steps": 30, "total_steps": 261, "loss": 0.5985, "accuracy": 0.796875, "lr": 9.844158449086372e-06, "epoch": 0.11491501077328226, "percentage": 11.49, "elapsed_time": "0:43:59", "remaining_time": "5:38:42", "throughput": 4086.59, "total_tokens": 10785856}
31
+ {"current_steps": 31, "total_steps": 261, "loss": 0.5576, "accuracy": 0.859375, "lr": 9.828276730354353e-06, "epoch": 0.11874551113239167, "percentage": 11.88, "elapsed_time": "0:45:28", "remaining_time": "5:37:20", "throughput": 4087.41, "total_tokens": 11150656}
32
+ {"current_steps": 32, "total_steps": 261, "loss": 0.5511, "accuracy": 0.84375, "lr": 9.811638633800287e-06, "epoch": 0.12257601149150107, "percentage": 12.26, "elapsed_time": "0:46:51", "remaining_time": "5:35:21", "throughput": 4087.77, "total_tokens": 11493568}
33
+ {"current_steps": 33, "total_steps": 261, "loss": 0.5723, "accuracy": 0.828125, "lr": 9.794246765879421e-06, "epoch": 0.1264065118506105, "percentage": 12.64, "elapsed_time": "0:48:20", "remaining_time": "5:34:00", "throughput": 4089.44, "total_tokens": 11861824}
34
+ {"current_steps": 34, "total_steps": 261, "loss": 0.5751, "accuracy": 0.828125, "lr": 9.776103851129706e-06, "epoch": 0.1302370122097199, "percentage": 13.03, "elapsed_time": "0:49:50", "remaining_time": "5:32:47", "throughput": 4089.28, "total_tokens": 12229824}
35
+ {"current_steps": 35, "total_steps": 261, "loss": 0.5121, "accuracy": 0.8984375, "lr": 9.757212731744973e-06, "epoch": 0.13406751256882932, "percentage": 13.41, "elapsed_time": "0:51:25", "remaining_time": "5:32:03", "throughput": 4087.14, "total_tokens": 12610880}
36
+ {"current_steps": 36, "total_steps": 261, "loss": 0.536, "accuracy": 0.796875, "lr": 9.737576367129694e-06, "epoch": 0.1378980129279387, "percentage": 13.79, "elapsed_time": "0:52:51", "remaining_time": "5:30:20", "throughput": 4086.3, "total_tokens": 12958592}
37
+ {"current_steps": 37, "total_steps": 261, "loss": 0.5294, "accuracy": 0.8203125, "lr": 9.717197833435367e-06, "epoch": 0.1417285132870481, "percentage": 14.18, "elapsed_time": "0:54:16", "remaining_time": "5:28:36", "throughput": 4087.02, "total_tokens": 13310336}
38
+ {"current_steps": 38, "total_steps": 261, "loss": 0.5191, "accuracy": 0.8046875, "lr": 9.696080323078621e-06, "epoch": 0.14555901364615753, "percentage": 14.56, "elapsed_time": "0:55:49", "remaining_time": "5:27:36", "throughput": 4084.64, "total_tokens": 13681920}
39
+ {"current_steps": 39, "total_steps": 261, "loss": 0.5371, "accuracy": 0.8515625, "lr": 9.67422714424111e-06, "epoch": 0.14938951400526693, "percentage": 14.94, "elapsed_time": "0:57:15", "remaining_time": "5:25:58", "throughput": 4084.4, "total_tokens": 14033792}
40
+ {"current_steps": 40, "total_steps": 261, "loss": 0.49, "accuracy": 0.8828125, "lr": 9.651641720351262e-06, "epoch": 0.15322001436437635, "percentage": 15.33, "elapsed_time": "0:58:41", "remaining_time": "5:24:14", "throughput": 4087.33, "total_tokens": 14392064}
41
+ {"current_steps": 41, "total_steps": 261, "loss": 0.4843, "accuracy": 0.8828125, "lr": 9.628327589547977e-06, "epoch": 0.15705051472348575, "percentage": 15.71, "elapsed_time": "1:00:08", "remaining_time": "5:22:41", "throughput": 4087.89, "total_tokens": 14750144}
42
+ {"current_steps": 42, "total_steps": 261, "loss": 0.4864, "accuracy": 0.9140625, "lr": 9.604288404126362e-06, "epoch": 0.16088101508259517, "percentage": 16.09, "elapsed_time": "1:01:35", "remaining_time": "5:21:11", "throughput": 4089.86, "total_tokens": 15115648}
43
+ {"current_steps": 43, "total_steps": 261, "loss": 0.4906, "accuracy": 0.890625, "lr": 9.579527929965581e-06, "epoch": 0.16471151544170456, "percentage": 16.48, "elapsed_time": "1:03:00", "remaining_time": "5:19:26", "throughput": 4093.04, "total_tokens": 15473984}
44
+ {"current_steps": 44, "total_steps": 261, "loss": 0.4451, "accuracy": 0.8671875, "lr": 9.554050045938893e-06, "epoch": 0.168542015800814, "percentage": 16.86, "elapsed_time": "1:04:26", "remaining_time": "5:17:50", "throughput": 4090.67, "total_tokens": 15818304}
45
+ {"current_steps": 45, "total_steps": 261, "loss": 0.448, "accuracy": 0.875, "lr": 9.52785874330602e-06, "epoch": 0.17237251615992338, "percentage": 17.24, "elapsed_time": "1:05:52", "remaining_time": "5:16:13", "throughput": 4091.57, "total_tokens": 16173312}
46
+ {"current_steps": 46, "total_steps": 261, "loss": 0.4443, "accuracy": 0.8671875, "lr": 9.500958125087882e-06, "epoch": 0.1762030165190328, "percentage": 17.62, "elapsed_time": "1:07:24", "remaining_time": "5:15:01", "throughput": 4090.57, "total_tokens": 16542400}
47
+ {"current_steps": 47, "total_steps": 261, "loss": 0.4219, "accuracy": 0.921875, "lr": 9.473352405423845e-06, "epoch": 0.1800335168781422, "percentage": 18.01, "elapsed_time": "1:08:55", "remaining_time": "5:13:49", "throughput": 4088.1, "total_tokens": 16906368}
48
+ {"current_steps": 48, "total_steps": 261, "loss": 0.4229, "accuracy": 0.8828125, "lr": 9.445045908911536e-06, "epoch": 0.18386401723725163, "percentage": 18.39, "elapsed_time": "1:10:18", "remaining_time": "5:11:58", "throughput": 4088.01, "total_tokens": 17244160}
49
+ {"current_steps": 49, "total_steps": 261, "loss": 0.421, "accuracy": 0.8828125, "lr": 9.416043069929389e-06, "epoch": 0.18769451759636102, "percentage": 18.77, "elapsed_time": "1:11:45", "remaining_time": "5:10:27", "throughput": 4089.12, "total_tokens": 17605632}
50
+ {"current_steps": 50, "total_steps": 261, "loss": 0.4248, "accuracy": 0.890625, "lr": 9.386348431941953e-06, "epoch": 0.19152501795547044, "percentage": 19.16, "elapsed_time": "1:13:13", "remaining_time": "5:09:02", "throughput": 4088.97, "total_tokens": 17966784}
51
+ {"current_steps": 51, "total_steps": 261, "loss": 0.3664, "accuracy": 0.8984375, "lr": 9.355966646788152e-06, "epoch": 0.19535551831457984, "percentage": 19.54, "elapsed_time": "1:14:41", "remaining_time": "5:07:33", "throughput": 4089.76, "total_tokens": 18328768}
52
+ {"current_steps": 52, "total_steps": 261, "loss": 0.427, "accuracy": 0.859375, "lr": 9.324902473952529e-06, "epoch": 0.19918601867368926, "percentage": 19.92, "elapsed_time": "1:16:08", "remaining_time": "5:06:02", "throughput": 4089.13, "total_tokens": 18682304}
53
+ {"current_steps": 53, "total_steps": 261, "loss": 0.3614, "accuracy": 0.890625, "lr": 9.293160779819658e-06, "epoch": 0.20301651903279866, "percentage": 20.31, "elapsed_time": "1:17:36", "remaining_time": "5:04:32", "throughput": 4088.82, "total_tokens": 19037760}
54
+ {"current_steps": 54, "total_steps": 261, "loss": 0.3549, "accuracy": 0.9140625, "lr": 9.260746536911792e-06, "epoch": 0.20684701939190805, "percentage": 20.69, "elapsed_time": "1:19:02", "remaining_time": "5:02:58", "throughput": 4089.83, "total_tokens": 19394688}
55
+ {"current_steps": 55, "total_steps": 261, "loss": 0.3531, "accuracy": 0.890625, "lr": 9.227664823109884e-06, "epoch": 0.21067751975101748, "percentage": 21.07, "elapsed_time": "1:20:33", "remaining_time": "5:01:43", "throughput": 4088.29, "total_tokens": 19760704}
56
+ {"current_steps": 56, "total_steps": 261, "loss": 0.3455, "accuracy": 0.9140625, "lr": 9.193920820858113e-06, "epoch": 0.21450802011012687, "percentage": 21.46, "elapsed_time": "1:22:01", "remaining_time": "5:00:17", "throughput": 4088.16, "total_tokens": 20121856}
57
+ {"current_steps": 57, "total_steps": 261, "loss": 0.3191, "accuracy": 0.9296875, "lr": 9.159519816352021e-06, "epoch": 0.2183385204692363, "percentage": 21.84, "elapsed_time": "1:23:30", "remaining_time": "4:58:51", "throughput": 4088.01, "total_tokens": 20482304}
58
+ {"current_steps": 58, "total_steps": 261, "loss": 0.3171, "accuracy": 0.9296875, "lr": 9.124467198710401e-06, "epoch": 0.2221690208283457, "percentage": 22.22, "elapsed_time": "1:24:53", "remaining_time": "4:57:07", "throughput": 4088.0, "total_tokens": 20822656}
59
+ {"current_steps": 59, "total_steps": 261, "loss": 0.3078, "accuracy": 0.9609375, "lr": 9.08876845913106e-06, "epoch": 0.22599952118745512, "percentage": 22.61, "elapsed_time": "1:26:21", "remaining_time": "4:55:41", "throughput": 4088.8, "total_tokens": 21187392}
60
+ {"current_steps": 60, "total_steps": 261, "loss": 0.3253, "accuracy": 0.90625, "lr": 9.052429190030589e-06, "epoch": 0.2298300215465645, "percentage": 22.99, "elapsed_time": "1:27:49", "remaining_time": "4:54:13", "throughput": 4088.61, "total_tokens": 21545600}
61
+ {"current_steps": 61, "total_steps": 261, "loss": 0.3212, "accuracy": 0.9140625, "lr": 9.015455084168279e-06, "epoch": 0.23366052190567393, "percentage": 23.37, "elapsed_time": "1:29:13", "remaining_time": "4:52:31", "throughput": 4088.75, "total_tokens": 21887936}
62
+ {"current_steps": 62, "total_steps": 261, "loss": 0.3188, "accuracy": 0.9609375, "lr": 8.977851933754317e-06, "epoch": 0.23749102226478333, "percentage": 23.75, "elapsed_time": "1:30:36", "remaining_time": "4:50:48", "throughput": 4089.71, "total_tokens": 22233024}
63
+ {"current_steps": 63, "total_steps": 261, "loss": 0.2957, "accuracy": 0.9140625, "lr": 8.939625629542401e-06, "epoch": 0.24132152262389275, "percentage": 24.14, "elapsed_time": "1:32:02", "remaining_time": "4:49:15", "throughput": 4090.04, "total_tokens": 22585472}
64
+ {"current_steps": 64, "total_steps": 261, "loss": 0.2977, "accuracy": 0.890625, "lr": 8.900782159906927e-06, "epoch": 0.24515202298300215, "percentage": 24.52, "elapsed_time": "1:33:31", "remaining_time": "4:47:54", "throughput": 4088.91, "total_tokens": 22946880}
65
+ {"current_steps": 65, "total_steps": 261, "loss": 0.2786, "accuracy": 0.921875, "lr": 8.861327609904859e-06, "epoch": 0.24898252334211157, "percentage": 24.9, "elapsed_time": "1:34:59", "remaining_time": "4:46:26", "throughput": 4088.82, "total_tokens": 23304320}
66
+ {"current_steps": 66, "total_steps": 261, "loss": 0.2977, "accuracy": 0.859375, "lr": 8.821268160322482e-06, "epoch": 0.252813023701221, "percentage": 25.29, "elapsed_time": "1:36:25", "remaining_time": "4:44:52", "throughput": 4090.71, "total_tokens": 23665536}
67
+ {"current_steps": 67, "total_steps": 261, "loss": 0.2613, "accuracy": 0.9296875, "lr": 8.780610086707149e-06, "epoch": 0.25664352406033036, "percentage": 25.67, "elapsed_time": "1:37:50", "remaining_time": "4:43:18", "throughput": 4091.77, "total_tokens": 24021376}
68
+ {"current_steps": 68, "total_steps": 261, "loss": 0.2722, "accuracy": 0.9296875, "lr": 8.739359758384162e-06, "epoch": 0.2604740244194398, "percentage": 26.05, "elapsed_time": "1:39:19", "remaining_time": "4:41:54", "throughput": 4091.81, "total_tokens": 24385216}
69
+ {"current_steps": 69, "total_steps": 261, "loss": 0.2872, "accuracy": 0.90625, "lr": 8.697523637458997e-06, "epoch": 0.2643045247785492, "percentage": 26.44, "elapsed_time": "1:40:50", "remaining_time": "4:40:36", "throughput": 4090.43, "total_tokens": 24750080}
70
+ {"current_steps": 70, "total_steps": 261, "loss": 0.272, "accuracy": 0.9140625, "lr": 8.655108277804975e-06, "epoch": 0.26813502513765863, "percentage": 26.82, "elapsed_time": "1:42:18", "remaining_time": "4:39:09", "throughput": 4091.52, "total_tokens": 25116480}
71
+ {"current_steps": 71, "total_steps": 261, "loss": 0.2075, "accuracy": 0.9609375, "lr": 8.612120324036548e-06, "epoch": 0.271965525496768, "percentage": 27.2, "elapsed_time": "1:43:43", "remaining_time": "4:37:34", "throughput": 4091.74, "total_tokens": 25465536}
72
+ {"current_steps": 72, "total_steps": 261, "loss": 0.2464, "accuracy": 0.9375, "lr": 8.568566510468392e-06, "epoch": 0.2757960258558774, "percentage": 27.59, "elapsed_time": "1:45:12", "remaining_time": "4:36:09", "throughput": 4092.6, "total_tokens": 25833344}
73
+ {"current_steps": 73, "total_steps": 261, "loss": 0.2724, "accuracy": 0.921875, "lr": 8.524453660060434e-06, "epoch": 0.27962652621498685, "percentage": 27.97, "elapsed_time": "1:46:36", "remaining_time": "4:34:32", "throughput": 4093.55, "total_tokens": 26183872}
74
+ {"current_steps": 74, "total_steps": 261, "loss": 0.2695, "accuracy": 0.8984375, "lr": 8.479788683348996e-06, "epoch": 0.2834570265740962, "percentage": 28.35, "elapsed_time": "1:48:04", "remaining_time": "4:33:06", "throughput": 4092.71, "total_tokens": 26539904}
75
+ {"current_steps": 75, "total_steps": 261, "loss": 0.266, "accuracy": 0.9140625, "lr": 8.434578577364218e-06, "epoch": 0.28728752693320564, "percentage": 28.74, "elapsed_time": "1:49:30", "remaining_time": "4:31:35", "throughput": 4094.22, "total_tokens": 26902464}
76
+ {"current_steps": 76, "total_steps": 261, "loss": 0.2346, "accuracy": 0.9296875, "lr": 8.388830424533935e-06, "epoch": 0.29111802729231506, "percentage": 29.12, "elapsed_time": "1:51:02", "remaining_time": "4:30:18", "throughput": 4092.74, "total_tokens": 27269504}
77
+ {"current_steps": 77, "total_steps": 261, "loss": 0.263, "accuracy": 0.9296875, "lr": 8.342551391574165e-06, "epoch": 0.2949485276514245, "percentage": 29.5, "elapsed_time": "1:52:30", "remaining_time": "4:28:52", "throughput": 4092.63, "total_tokens": 27629248}
78
+ {"current_steps": 78, "total_steps": 261, "loss": 0.2319, "accuracy": 0.921875, "lr": 8.295748728366414e-06, "epoch": 0.29877902801053385, "percentage": 29.89, "elapsed_time": "1:53:56", "remaining_time": "4:27:19", "throughput": 4094.02, "total_tokens": 27988096}
79
+ {"current_steps": 79, "total_steps": 261, "loss": 0.2636, "accuracy": 0.9296875, "lr": 8.248429766821925e-06, "epoch": 0.3026095283696433, "percentage": 30.27, "elapsed_time": "1:55:22", "remaining_time": "4:25:48", "throughput": 4094.65, "total_tokens": 28346432}
80
+ {"current_steps": 80, "total_steps": 261, "loss": 0.2616, "accuracy": 0.8984375, "lr": 8.200601919733106e-06, "epoch": 0.3064400287287527, "percentage": 30.65, "elapsed_time": "1:56:54", "remaining_time": "4:24:31", "throughput": 4093.47, "total_tokens": 28715200}
81
+ {"current_steps": 81, "total_steps": 261, "loss": 0.2285, "accuracy": 0.921875, "lr": 8.15227267961226e-06, "epoch": 0.3102705290878621, "percentage": 31.03, "elapsed_time": "1:58:19", "remaining_time": "4:22:57", "throughput": 4094.39, "total_tokens": 29068800}
82
+ {"current_steps": 82, "total_steps": 261, "loss": 0.257, "accuracy": 0.875, "lr": 8.10344961751785e-06, "epoch": 0.3141010294469715, "percentage": 31.42, "elapsed_time": "1:59:44", "remaining_time": "4:21:23", "throughput": 4094.2, "total_tokens": 29416000}
83
+ {"current_steps": 83, "total_steps": 261, "loss": 0.2235, "accuracy": 0.9453125, "lr": 8.054140381868435e-06, "epoch": 0.3179315298060809, "percentage": 31.8, "elapsed_time": "2:01:08", "remaining_time": "4:19:48", "throughput": 4095.4, "total_tokens": 29768704}
84
+ {"current_steps": 84, "total_steps": 261, "loss": 0.2401, "accuracy": 0.9296875, "lr": 8.004352697244516e-06, "epoch": 0.32176203016519034, "percentage": 32.18, "elapsed_time": "2:02:37", "remaining_time": "4:18:23", "throughput": 4097.01, "total_tokens": 30143360}
85
+ {"current_steps": 85, "total_steps": 261, "loss": 0.2107, "accuracy": 0.9453125, "lr": 7.954094363178421e-06, "epoch": 0.32559253052429976, "percentage": 32.57, "elapsed_time": "2:04:02", "remaining_time": "4:16:51", "throughput": 4097.44, "total_tokens": 30496832}
86
+ {"current_steps": 86, "total_steps": 261, "loss": 0.2237, "accuracy": 0.90625, "lr": 7.903373252932474e-06, "epoch": 0.32942303088340913, "percentage": 32.95, "elapsed_time": "2:05:30", "remaining_time": "4:15:23", "throughput": 4097.41, "total_tokens": 30854400}
87
+ {"current_steps": 87, "total_steps": 261, "loss": 0.2435, "accuracy": 0.9140625, "lr": 7.852197312265592e-06, "epoch": 0.33325353124251855, "percentage": 33.33, "elapsed_time": "2:06:55", "remaining_time": "4:13:51", "throughput": 4098.47, "total_tokens": 31212288}
88
+ {"current_steps": 88, "total_steps": 261, "loss": 0.2273, "accuracy": 0.921875, "lr": 7.800574558188548e-06, "epoch": 0.337084031601628, "percentage": 33.72, "elapsed_time": "2:08:25", "remaining_time": "4:12:27", "throughput": 4098.08, "total_tokens": 31576000}
89
+ {"current_steps": 89, "total_steps": 261, "loss": 0.2568, "accuracy": 0.90625, "lr": 7.748513077708044e-06, "epoch": 0.34091453196073734, "percentage": 34.1, "elapsed_time": "2:09:51", "remaining_time": "4:10:58", "throughput": 4098.02, "total_tokens": 31930560}
90
+ {"current_steps": 90, "total_steps": 261, "loss": 0.1811, "accuracy": 0.9453125, "lr": 7.69602102655985e-06, "epoch": 0.34474503231984677, "percentage": 34.48, "elapsed_time": "2:11:20", "remaining_time": "4:09:33", "throughput": 4098.03, "total_tokens": 32295488}
91
+ {"current_steps": 91, "total_steps": 261, "loss": 0.1776, "accuracy": 0.9609375, "lr": 7.643106627931148e-06, "epoch": 0.3485755326789562, "percentage": 34.87, "elapsed_time": "2:12:52", "remaining_time": "4:08:13", "throughput": 4098.46, "total_tokens": 32673984}
92
+ {"current_steps": 92, "total_steps": 261, "loss": 0.2421, "accuracy": 0.9140625, "lr": 7.5897781711723215e-06, "epoch": 0.3524060330380656, "percentage": 35.25, "elapsed_time": "2:14:19", "remaining_time": "4:06:45", "throughput": 4098.94, "total_tokens": 33035968}
93
+ {"current_steps": 93, "total_steps": 261, "loss": 0.2218, "accuracy": 0.921875, "lr": 7.536044010498396e-06, "epoch": 0.356236533397175, "percentage": 35.63, "elapsed_time": "2:15:47", "remaining_time": "4:05:17", "throughput": 4098.65, "total_tokens": 33392192}
94
+ {"current_steps": 94, "total_steps": 261, "loss": 0.1707, "accuracy": 0.9375, "lr": 7.48191256368028e-06, "epoch": 0.3600670337562844, "percentage": 36.02, "elapsed_time": "2:17:13", "remaining_time": "4:03:46", "throughput": 4100.39, "total_tokens": 33758976}
95
+ {"current_steps": 95, "total_steps": 261, "loss": 0.2029, "accuracy": 0.9140625, "lr": 7.427392310726088e-06, "epoch": 0.36389753411539383, "percentage": 36.4, "elapsed_time": "2:18:40", "remaining_time": "4:02:19", "throughput": 4101.05, "total_tokens": 34123840}
96
+ {"current_steps": 96, "total_steps": 261, "loss": 0.1596, "accuracy": 0.9765625, "lr": 7.372491792552694e-06, "epoch": 0.36772803447450325, "percentage": 36.78, "elapsed_time": "2:20:10", "remaining_time": "4:00:55", "throughput": 4099.51, "total_tokens": 34479552}
97
+ {"current_steps": 97, "total_steps": 261, "loss": 0.1881, "accuracy": 0.9453125, "lr": 7.31721960964774e-06, "epoch": 0.3715585348336126, "percentage": 37.16, "elapsed_time": "2:21:37", "remaining_time": "3:59:27", "throughput": 4099.45, "total_tokens": 34835840}
98
+ {"current_steps": 98, "total_steps": 261, "loss": 0.2405, "accuracy": 0.9296875, "lr": 7.261584420722328e-06, "epoch": 0.37538903519272204, "percentage": 37.55, "elapsed_time": "2:23:08", "remaining_time": "3:58:04", "throughput": 4099.72, "total_tokens": 35210176}
99
+ {"current_steps": 99, "total_steps": 261, "loss": 0.195, "accuracy": 0.953125, "lr": 7.20559494135458e-06, "epoch": 0.37921953555183147, "percentage": 37.93, "elapsed_time": "2:24:34", "remaining_time": "3:56:35", "throughput": 4100.18, "total_tokens": 35568576}
100
+ {"current_steps": 100, "total_steps": 261, "loss": 0.186, "accuracy": 0.9375, "lr": 7.149259942624287e-06, "epoch": 0.3830500359109409, "percentage": 38.31, "elapsed_time": "2:26:02", "remaining_time": "3:55:07", "throughput": 4100.38, "total_tokens": 35929024}
101
+ {"current_steps": 101, "total_steps": 261, "loss": 0.1837, "accuracy": 0.9453125, "lr": 7.092588249738871e-06, "epoch": 0.38688053627005026, "percentage": 38.7, "elapsed_time": "2:27:31", "remaining_time": "3:53:42", "throughput": 4100.13, "total_tokens": 36292032}
102
+ {"current_steps": 102, "total_steps": 261, "loss": 0.181, "accuracy": 0.9375, "lr": 7.03558874065087e-06, "epoch": 0.3907110366291597, "percentage": 39.08, "elapsed_time": "2:28:57", "remaining_time": "3:52:11", "throughput": 4100.56, "total_tokens": 36647104}
103
+ {"current_steps": 103, "total_steps": 261, "loss": 0.1815, "accuracy": 0.9453125, "lr": 6.978270344667143e-06, "epoch": 0.3945415369882691, "percentage": 39.46, "elapsed_time": "2:30:21", "remaining_time": "3:50:38", "throughput": 4101.06, "total_tokens": 36996736}
104
+ {"current_steps": 104, "total_steps": 261, "loss": 0.2464, "accuracy": 0.8828125, "lr": 6.920642041050055e-06, "epoch": 0.3983720373473785, "percentage": 39.85, "elapsed_time": "2:31:45", "remaining_time": "3:49:06", "throughput": 4101.87, "total_tokens": 37351296}
105
+ {"current_steps": 105, "total_steps": 261, "loss": 0.128, "accuracy": 0.96875, "lr": 6.862712857610812e-06, "epoch": 0.4022025377064879, "percentage": 40.23, "elapsed_time": "2:33:14", "remaining_time": "3:47:39", "throughput": 4101.58, "total_tokens": 37710464}
106
+ {"current_steps": 106, "total_steps": 261, "loss": 0.1922, "accuracy": 0.953125, "lr": 6.804491869295207e-06, "epoch": 0.4060330380655973, "percentage": 40.61, "elapsed_time": "2:34:42", "remaining_time": "3:46:14", "throughput": 4101.66, "total_tokens": 38075136}
107
+ {"current_steps": 107, "total_steps": 261, "loss": 0.1652, "accuracy": 0.953125, "lr": 6.745988196761976e-06, "epoch": 0.40986353842470674, "percentage": 41.0, "elapsed_time": "2:36:10", "remaining_time": "3:44:46", "throughput": 4102.1, "total_tokens": 38438464}
108
+ {"current_steps": 108, "total_steps": 261, "loss": 0.1384, "accuracy": 0.96875, "lr": 6.687211004953992e-06, "epoch": 0.4136940387838161, "percentage": 41.38, "elapsed_time": "2:37:38", "remaining_time": "3:43:18", "throughput": 4100.87, "total_tokens": 38786112}
109
+ {"current_steps": 109, "total_steps": 261, "loss": 0.1425, "accuracy": 0.9609375, "lr": 6.628169501662527e-06, "epoch": 0.41752453914292553, "percentage": 41.76, "elapsed_time": "2:39:02", "remaining_time": "3:41:47", "throughput": 4101.33, "total_tokens": 39137920}
110
+ {"current_steps": 110, "total_steps": 261, "loss": 0.2094, "accuracy": 0.9296875, "lr": 6.568872936084789e-06, "epoch": 0.42135503950203496, "percentage": 42.15, "elapsed_time": "2:40:31", "remaining_time": "3:40:21", "throughput": 4100.65, "total_tokens": 39496896}
111
+ {"current_steps": 111, "total_steps": 261, "loss": 0.1983, "accuracy": 0.9140625, "lr": 6.509330597374993e-06, "epoch": 0.4251855398611444, "percentage": 42.53, "elapsed_time": "2:41:59", "remaining_time": "3:38:54", "throughput": 4101.22, "total_tokens": 39862784}
112
+ {"current_steps": 112, "total_steps": 261, "loss": 0.2063, "accuracy": 0.90625, "lr": 6.44955181318915e-06, "epoch": 0.42901604022025375, "percentage": 42.91, "elapsed_time": "2:43:29", "remaining_time": "3:37:29", "throughput": 4101.16, "total_tokens": 40229504}
113
+ {"current_steps": 113, "total_steps": 261, "loss": 0.2079, "accuracy": 0.9296875, "lr": 6.389545948223841e-06, "epoch": 0.43284654057936317, "percentage": 43.3, "elapsed_time": "2:44:54", "remaining_time": "3:35:59", "throughput": 4101.1, "total_tokens": 40578304}
114
+ {"current_steps": 114, "total_steps": 261, "loss": 0.1346, "accuracy": 0.96875, "lr": 6.329322402749181e-06, "epoch": 0.4366770409384726, "percentage": 43.68, "elapsed_time": "2:46:19", "remaining_time": "3:34:28", "throughput": 4100.98, "total_tokens": 40926400}
115
+ {"current_steps": 115, "total_steps": 261, "loss": 0.1798, "accuracy": 0.953125, "lr": 6.2688906111362115e-06, "epoch": 0.440507541297582, "percentage": 44.06, "elapsed_time": "2:47:45", "remaining_time": "3:32:59", "throughput": 4101.3, "total_tokens": 41283008}
116
+ {"current_steps": 116, "total_steps": 261, "loss": 0.1762, "accuracy": 0.9296875, "lr": 6.208260040378946e-06, "epoch": 0.4443380416566914, "percentage": 44.44, "elapsed_time": "2:49:08", "remaining_time": "3:31:26", "throughput": 4100.92, "total_tokens": 41619520}
117
+ {"current_steps": 117, "total_steps": 261, "loss": 0.1582, "accuracy": 0.953125, "lr": 6.147440188611324e-06, "epoch": 0.4481685420158008, "percentage": 44.83, "elapsed_time": "2:50:39", "remaining_time": "3:30:02", "throughput": 4100.42, "total_tokens": 41986368}
118
+ {"current_steps": 118, "total_steps": 261, "loss": 0.1576, "accuracy": 0.9453125, "lr": 6.0864405836192575e-06, "epoch": 0.45199904237491023, "percentage": 45.21, "elapsed_time": "2:52:07", "remaining_time": "3:28:35", "throughput": 4100.32, "total_tokens": 42347008}
119
+ {"current_steps": 119, "total_steps": 261, "loss": 0.1499, "accuracy": 0.953125, "lr": 6.025270781348055e-06, "epoch": 0.45582954273401965, "percentage": 45.59, "elapsed_time": "2:53:34", "remaining_time": "3:27:06", "throughput": 4100.05, "total_tokens": 42698240}
120
+ {"current_steps": 120, "total_steps": 261, "loss": 0.1678, "accuracy": 0.9375, "lr": 5.963940364405425e-06, "epoch": 0.459660043093129, "percentage": 45.98, "elapsed_time": "2:54:58", "remaining_time": "3:25:36", "throughput": 4100.5, "total_tokens": 43050688}
121
+ {"current_steps": 121, "total_steps": 261, "loss": 0.1805, "accuracy": 0.921875, "lr": 5.902458940560304e-06, "epoch": 0.46349054345223845, "percentage": 46.36, "elapsed_time": "2:56:26", "remaining_time": "3:24:09", "throughput": 4100.89, "total_tokens": 43415744}
122
+ {"current_steps": 122, "total_steps": 261, "loss": 0.1412, "accuracy": 0.953125, "lr": 5.8408361412377475e-06, "epoch": 0.46732104381134787, "percentage": 46.74, "elapsed_time": "2:57:53", "remaining_time": "3:22:41", "throughput": 4100.71, "total_tokens": 43769984}
123
+ {"current_steps": 123, "total_steps": 261, "loss": 0.1359, "accuracy": 0.9765625, "lr": 5.779081620010104e-06, "epoch": 0.4711515441704573, "percentage": 47.13, "elapsed_time": "2:59:18", "remaining_time": "3:21:10", "throughput": 4101.56, "total_tokens": 44125376}
124
+ {"current_steps": 124, "total_steps": 261, "loss": 0.159, "accuracy": 0.9609375, "lr": 5.717205051084731e-06, "epoch": 0.47498204452956666, "percentage": 47.51, "elapsed_time": "3:00:46", "remaining_time": "3:19:43", "throughput": 4102.36, "total_tokens": 44496896}
125
+ {"current_steps": 125, "total_steps": 261, "loss": 0.1569, "accuracy": 0.9609375, "lr": 5.655216127788472e-06, "epoch": 0.4788125448886761, "percentage": 47.89, "elapsed_time": "3:02:15", "remaining_time": "3:18:17", "throughput": 4102.08, "total_tokens": 44858496}
126
+ {"current_steps": 126, "total_steps": 261, "loss": 0.1527, "accuracy": 0.9609375, "lr": 5.593124561049141e-06, "epoch": 0.4826430452477855, "percentage": 48.28, "elapsed_time": "3:03:41", "remaining_time": "3:16:49", "throughput": 4102.35, "total_tokens": 45215680}
127
+ {"current_steps": 127, "total_steps": 261, "loss": 0.1848, "accuracy": 0.9296875, "lr": 5.530940077874248e-06, "epoch": 0.4864735456068949, "percentage": 48.66, "elapsed_time": "3:05:09", "remaining_time": "3:15:21", "throughput": 4102.52, "total_tokens": 45575872}
128
+ {"current_steps": 128, "total_steps": 261, "loss": 0.1428, "accuracy": 0.9375, "lr": 5.468672419827208e-06, "epoch": 0.4903040459660043, "percentage": 49.04, "elapsed_time": "3:06:39", "remaining_time": "3:13:57", "throughput": 4102.97, "total_tokens": 45951488}
129
+ {"current_steps": 129, "total_steps": 261, "loss": 0.1905, "accuracy": 0.9296875, "lr": 5.406331341501264e-06, "epoch": 0.4941345463251137, "percentage": 49.43, "elapsed_time": "3:08:10", "remaining_time": "3:12:33", "throughput": 4101.9, "total_tokens": 46313472}
130
+ {"current_steps": 130, "total_steps": 261, "loss": 0.1683, "accuracy": 0.953125, "lr": 5.34392660899138e-06, "epoch": 0.49796504668422314, "percentage": 49.81, "elapsed_time": "3:09:42", "remaining_time": "3:11:09", "throughput": 4101.42, "total_tokens": 46683136}
131
+ {"current_steps": 131, "total_steps": 261, "loss": 0.1818, "accuracy": 0.921875, "lr": 5.281467998364314e-06, "epoch": 0.5017955470433325, "percentage": 50.19, "elapsed_time": "3:11:06", "remaining_time": "3:09:38", "throughput": 4101.81, "total_tokens": 47033152}
132
+ {"current_steps": 132, "total_steps": 261, "loss": 0.1355, "accuracy": 0.96875, "lr": 5.218965294127155e-06, "epoch": 0.505626047402442, "percentage": 50.57, "elapsed_time": "3:12:37", "remaining_time": "3:08:15", "throughput": 4101.8, "total_tokens": 47407552}
133
+ {"current_steps": 133, "total_steps": 261, "loss": 0.1517, "accuracy": 0.9609375, "lr": 5.156428287694508e-06, "epoch": 0.5094565477615514, "percentage": 50.96, "elapsed_time": "3:14:10", "remaining_time": "3:06:52", "throughput": 4100.87, "total_tokens": 47777088}
134
+ {"current_steps": 134, "total_steps": 261, "loss": 0.1486, "accuracy": 0.9453125, "lr": 5.093866775854618e-06, "epoch": 0.5132870481206607, "percentage": 51.34, "elapsed_time": "3:15:40", "remaining_time": "3:05:26", "throughput": 4101.0, "total_tokens": 48146176}
135
+ {"current_steps": 135, "total_steps": 261, "loss": 0.1411, "accuracy": 0.9609375, "lr": 5.03129055923465e-06, "epoch": 0.5171175484797702, "percentage": 51.72, "elapsed_time": "3:17:05", "remaining_time": "3:03:57", "throughput": 4102.23, "total_tokens": 48511488}
136
+ {"current_steps": 136, "total_steps": 261, "loss": 0.1288, "accuracy": 0.953125, "lr": 4.968709440765352e-06, "epoch": 0.5209480488388796, "percentage": 52.11, "elapsed_time": "3:18:28", "remaining_time": "3:02:24", "throughput": 4103.3, "total_tokens": 48862336}
137
+ {"current_steps": 137, "total_steps": 261, "loss": 0.1461, "accuracy": 0.96875, "lr": 4.906133224145384e-06, "epoch": 0.5247785491979889, "percentage": 52.49, "elapsed_time": "3:19:56", "remaining_time": "3:00:58", "throughput": 4103.41, "total_tokens": 49226048}
138
+ {"current_steps": 138, "total_steps": 261, "loss": 0.1788, "accuracy": 0.9453125, "lr": 4.843571712305493e-06, "epoch": 0.5286090495570984, "percentage": 52.87, "elapsed_time": "3:21:23", "remaining_time": "2:59:29", "throughput": 4103.32, "total_tokens": 49581888}
139
+ {"current_steps": 139, "total_steps": 261, "loss": 0.1061, "accuracy": 0.9921875, "lr": 4.781034705872846e-06, "epoch": 0.5324395499162078, "percentage": 53.26, "elapsed_time": "3:22:49", "remaining_time": "2:58:01", "throughput": 4103.42, "total_tokens": 49936512}
140
+ {"current_steps": 140, "total_steps": 261, "loss": 0.1376, "accuracy": 0.9609375, "lr": 4.7185320016356865e-06, "epoch": 0.5362700502753173, "percentage": 53.64, "elapsed_time": "3:24:18", "remaining_time": "2:56:35", "throughput": 4103.95, "total_tokens": 50309824}
141
+ {"current_steps": 141, "total_steps": 261, "loss": 0.1519, "accuracy": 0.9453125, "lr": 4.656073391008622e-06, "epoch": 0.5401005506344266, "percentage": 54.02, "elapsed_time": "3:25:41", "remaining_time": "2:55:03", "throughput": 4104.79, "total_tokens": 50659712}
142
+ {"current_steps": 142, "total_steps": 261, "loss": 0.1491, "accuracy": 0.9375, "lr": 4.593668658498737e-06, "epoch": 0.543931050993536, "percentage": 54.41, "elapsed_time": "3:27:06", "remaining_time": "2:53:34", "throughput": 4105.7, "total_tokens": 51020992}
143
+ {"current_steps": 143, "total_steps": 261, "loss": 0.1244, "accuracy": 0.9609375, "lr": 4.531327580172794e-06, "epoch": 0.5477615513526455, "percentage": 54.79, "elapsed_time": "3:28:34", "remaining_time": "2:52:06", "throughput": 4105.68, "total_tokens": 51378624}
144
+ {"current_steps": 144, "total_steps": 261, "loss": 0.1593, "accuracy": 0.9453125, "lr": 4.469059922125753e-06, "epoch": 0.5515920517117548, "percentage": 55.17, "elapsed_time": "3:30:05", "remaining_time": "2:50:41", "throughput": 4106.18, "total_tokens": 51760384}
145
+ {"current_steps": 145, "total_steps": 261, "loss": 0.1374, "accuracy": 0.9453125, "lr": 4.4068754389508616e-06, "epoch": 0.5554225520708642, "percentage": 55.56, "elapsed_time": "3:31:29", "remaining_time": "2:49:11", "throughput": 4106.93, "total_tokens": 52114304}
146
+ {"current_steps": 146, "total_steps": 261, "loss": 0.1643, "accuracy": 0.9296875, "lr": 4.34478387221153e-06, "epoch": 0.5592530524299737, "percentage": 55.94, "elapsed_time": "3:32:59", "remaining_time": "2:47:46", "throughput": 4107.03, "total_tokens": 52486784}
147
+ {"current_steps": 147, "total_steps": 261, "loss": 0.0999, "accuracy": 0.9765625, "lr": 4.282794948915271e-06, "epoch": 0.5630835527890831, "percentage": 56.32, "elapsed_time": "3:34:23", "remaining_time": "2:46:15", "throughput": 4107.12, "total_tokens": 52831680}
148
+ {"current_steps": 148, "total_steps": 261, "loss": 0.1095, "accuracy": 0.9609375, "lr": 4.220918379989898e-06, "epoch": 0.5669140531481924, "percentage": 56.7, "elapsed_time": "3:35:45", "remaining_time": "2:44:44", "throughput": 4107.58, "total_tokens": 53175680}
149
+ {"current_steps": 149, "total_steps": 261, "loss": 0.1384, "accuracy": 0.953125, "lr": 4.159163858762255e-06, "epoch": 0.5707445535073019, "percentage": 57.09, "elapsed_time": "3:37:13", "remaining_time": "2:43:17", "throughput": 4107.57, "total_tokens": 53537024}
150
+ {"current_steps": 150, "total_steps": 261, "loss": 0.1174, "accuracy": 0.96875, "lr": 4.097541059439698e-06, "epoch": 0.5745750538664113, "percentage": 57.47, "elapsed_time": "3:38:38", "remaining_time": "2:41:47", "throughput": 4108.2, "total_tokens": 53894528}
151
+ {"current_steps": 151, "total_steps": 261, "loss": 0.1603, "accuracy": 0.9609375, "lr": 4.036059635594578e-06, "epoch": 0.5784055542255208, "percentage": 57.85, "elapsed_time": "3:40:07", "remaining_time": "2:40:21", "throughput": 4108.47, "total_tokens": 54262848}
152
+ {"current_steps": 152, "total_steps": 261, "loss": 0.1102, "accuracy": 0.96875, "lr": 3.974729218651946e-06, "epoch": 0.5822360545846301, "percentage": 58.24, "elapsed_time": "3:41:38", "remaining_time": "2:38:56", "throughput": 4108.42, "total_tokens": 54635776}
153
+ {"current_steps": 153, "total_steps": 261, "loss": 0.1277, "accuracy": 0.9609375, "lr": 3.913559416380743e-06, "epoch": 0.5860665549437395, "percentage": 58.62, "elapsed_time": "3:43:08", "remaining_time": "2:37:30", "throughput": 4107.96, "total_tokens": 54999744}
154
+ {"current_steps": 154, "total_steps": 261, "loss": 0.0814, "accuracy": 0.96875, "lr": 3.852559811388676e-06, "epoch": 0.589897055302849, "percentage": 59.0, "elapsed_time": "3:44:31", "remaining_time": "2:35:59", "throughput": 4107.82, "total_tokens": 55337280}
155
+ {"current_steps": 155, "total_steps": 261, "loss": 0.1583, "accuracy": 0.96875, "lr": 3.791739959621054e-06, "epoch": 0.5937275556619583, "percentage": 59.39, "elapsed_time": "3:46:03", "remaining_time": "2:34:35", "throughput": 4106.66, "total_tokens": 55702336}
156
+ {"current_steps": 156, "total_steps": 261, "loss": 0.1345, "accuracy": 0.9453125, "lr": 3.7311093888637906e-06, "epoch": 0.5975580560210677, "percentage": 59.77, "elapsed_time": "3:47:35", "remaining_time": "2:33:11", "throughput": 4106.07, "total_tokens": 56070336}
157
+ {"current_steps": 157, "total_steps": 261, "loss": 0.1229, "accuracy": 0.953125, "lr": 3.670677597250819e-06, "epoch": 0.6013885563801772, "percentage": 60.15, "elapsed_time": "3:49:04", "remaining_time": "2:31:44", "throughput": 4105.6, "total_tokens": 56428800}
158
+ {"current_steps": 158, "total_steps": 261, "loss": 0.1324, "accuracy": 0.9375, "lr": 3.6104540517761594e-06, "epoch": 0.6052190567392866, "percentage": 60.54, "elapsed_time": "3:50:29", "remaining_time": "2:30:15", "throughput": 4105.85, "total_tokens": 56783040}
159
+ {"current_steps": 159, "total_steps": 261, "loss": 0.0872, "accuracy": 0.9765625, "lr": 3.55044818681085e-06, "epoch": 0.609049557098396, "percentage": 60.92, "elapsed_time": "3:51:57", "remaining_time": "2:28:47", "throughput": 4106.16, "total_tokens": 57145920}
160
+ {"current_steps": 160, "total_steps": 261, "loss": 0.1244, "accuracy": 0.9609375, "lr": 3.4906694026250075e-06, "epoch": 0.6128800574575054, "percentage": 61.3, "elapsed_time": "3:53:23", "remaining_time": "2:27:19", "throughput": 4106.31, "total_tokens": 57502528}
161
+ {"current_steps": 161, "total_steps": 261, "loss": 0.1404, "accuracy": 0.9453125, "lr": 3.431127063915213e-06, "epoch": 0.6167105578166148, "percentage": 61.69, "elapsed_time": "3:54:49", "remaining_time": "2:25:51", "throughput": 4106.85, "total_tokens": 57864896}
162
+ {"current_steps": 162, "total_steps": 261, "loss": 0.0902, "accuracy": 0.9765625, "lr": 3.371830498337475e-06, "epoch": 0.6205410581757242, "percentage": 62.07, "elapsed_time": "3:56:18", "remaining_time": "2:24:24", "throughput": 4106.03, "total_tokens": 58218496}
163
+ {"current_steps": 163, "total_steps": 261, "loss": 0.1118, "accuracy": 0.9609375, "lr": 3.3127889950460094e-06, "epoch": 0.6243715585348336, "percentage": 62.45, "elapsed_time": "3:57:41", "remaining_time": "2:22:54", "throughput": 4106.27, "total_tokens": 58561152}
164
+ {"current_steps": 164, "total_steps": 261, "loss": 0.154, "accuracy": 0.9453125, "lr": 3.254011803238026e-06, "epoch": 0.628202058893943, "percentage": 62.84, "elapsed_time": "3:59:10", "remaining_time": "2:21:27", "throughput": 4106.26, "total_tokens": 58925504}
165
+ {"current_steps": 165, "total_steps": 261, "loss": 0.1232, "accuracy": 0.96875, "lr": 3.195508130704795e-06, "epoch": 0.6320325592530525, "percentage": 63.22, "elapsed_time": "4:00:33", "remaining_time": "2:19:57", "throughput": 4106.45, "total_tokens": 59269120}
166
+ {"current_steps": 166, "total_steps": 261, "loss": 0.1412, "accuracy": 0.9609375, "lr": 3.1372871423891894e-06, "epoch": 0.6358630596121618, "percentage": 63.6, "elapsed_time": "4:01:58", "remaining_time": "2:18:28", "throughput": 4106.69, "total_tokens": 59620928}
167
+ {"current_steps": 167, "total_steps": 261, "loss": 0.0887, "accuracy": 0.9765625, "lr": 3.079357958949946e-06, "epoch": 0.6396935599712712, "percentage": 63.98, "elapsed_time": "4:03:21", "remaining_time": "2:16:58", "throughput": 4107.34, "total_tokens": 59974656}
168
+ {"current_steps": 168, "total_steps": 261, "loss": 0.1555, "accuracy": 0.953125, "lr": 3.021729655332858e-06, "epoch": 0.6435240603303807, "percentage": 64.37, "elapsed_time": "4:04:46", "remaining_time": "2:15:29", "throughput": 4107.93, "total_tokens": 60329216}
169
+ {"current_steps": 169, "total_steps": 261, "loss": 0.086, "accuracy": 0.9765625, "lr": 2.9644112593491315e-06, "epoch": 0.64735456068949, "percentage": 64.75, "elapsed_time": "4:06:13", "remaining_time": "2:14:02", "throughput": 4107.67, "total_tokens": 60686464}
170
+ {"current_steps": 170, "total_steps": 261, "loss": 0.134, "accuracy": 0.9375, "lr": 2.90741175026113e-06, "epoch": 0.6511850610485995, "percentage": 65.13, "elapsed_time": "4:07:41", "remaining_time": "2:12:35", "throughput": 4107.75, "total_tokens": 61046144}
171
+ {"current_steps": 171, "total_steps": 261, "loss": 0.1397, "accuracy": 0.953125, "lr": 2.850740057375716e-06, "epoch": 0.6550155614077089, "percentage": 65.52, "elapsed_time": "4:09:07", "remaining_time": "2:11:06", "throughput": 4107.49, "total_tokens": 61395776}
172
+ {"current_steps": 172, "total_steps": 261, "loss": 0.1393, "accuracy": 0.9296875, "lr": 2.7944050586454215e-06, "epoch": 0.6588460617668183, "percentage": 65.9, "elapsed_time": "4:10:31", "remaining_time": "2:09:38", "throughput": 4107.22, "total_tokens": 61739072}
173
+ {"current_steps": 173, "total_steps": 261, "loss": 0.107, "accuracy": 0.9609375, "lr": 2.7384155792776724e-06, "epoch": 0.6626765621259277, "percentage": 66.28, "elapsed_time": "4:11:56", "remaining_time": "2:08:09", "throughput": 4107.67, "total_tokens": 62091840}
174
+ {"current_steps": 174, "total_steps": 261, "loss": 0.1178, "accuracy": 0.9609375, "lr": 2.682780390352262e-06, "epoch": 0.6665070624850371, "percentage": 66.67, "elapsed_time": "4:13:24", "remaining_time": "2:06:42", "throughput": 4107.51, "total_tokens": 62452416}
175
+ {"current_steps": 175, "total_steps": 261, "loss": 0.1382, "accuracy": 0.9453125, "lr": 2.627508207447308e-06, "epoch": 0.6703375628441465, "percentage": 67.05, "elapsed_time": "4:14:55", "remaining_time": "2:05:16", "throughput": 4107.5, "total_tokens": 62826432}
176
+ {"current_steps": 176, "total_steps": 261, "loss": 0.1451, "accuracy": 0.9453125, "lr": 2.5726076892739127e-06, "epoch": 0.674168063203256, "percentage": 67.43, "elapsed_time": "4:16:22", "remaining_time": "2:03:49", "throughput": 4107.81, "total_tokens": 63188736}
177
+ {"current_steps": 177, "total_steps": 261, "loss": 0.1113, "accuracy": 0.9765625, "lr": 2.5180874363197217e-06, "epoch": 0.6779985635623653, "percentage": 67.82, "elapsed_time": "4:17:51", "remaining_time": "2:02:22", "throughput": 4108.19, "total_tokens": 63559040}
178
+ {"current_steps": 178, "total_steps": 261, "loss": 0.1304, "accuracy": 0.9609375, "lr": 2.463955989501607e-06, "epoch": 0.6818290639214747, "percentage": 68.2, "elapsed_time": "4:19:18", "remaining_time": "2:00:54", "throughput": 4108.19, "total_tokens": 63918080}
179
+ {"current_steps": 179, "total_steps": 261, "loss": 0.1064, "accuracy": 0.9765625, "lr": 2.41022182882768e-06, "epoch": 0.6856595642805842, "percentage": 68.58, "elapsed_time": "4:20:41", "remaining_time": "1:59:25", "throughput": 4108.51, "total_tokens": 64264384}
180
+ {"current_steps": 180, "total_steps": 261, "loss": 0.1286, "accuracy": 0.9453125, "lr": 2.356893372068855e-06, "epoch": 0.6894900646396935, "percentage": 68.97, "elapsed_time": "4:22:08", "remaining_time": "1:57:57", "throughput": 4108.91, "total_tokens": 64627520}
181
+ {"current_steps": 181, "total_steps": 261, "loss": 0.1146, "accuracy": 0.96875, "lr": 2.3039789734401524e-06, "epoch": 0.693320564998803, "percentage": 69.35, "elapsed_time": "4:23:35", "remaining_time": "1:56:30", "throughput": 4108.91, "total_tokens": 64985472}
182
+ {"current_steps": 182, "total_steps": 261, "loss": 0.1146, "accuracy": 0.96875, "lr": 2.251486922291957e-06, "epoch": 0.6971510653579124, "percentage": 69.73, "elapsed_time": "4:24:59", "remaining_time": "1:55:01", "throughput": 4109.14, "total_tokens": 65333056}
183
+ {"current_steps": 183, "total_steps": 261, "loss": 0.1325, "accuracy": 0.9453125, "lr": 2.1994254418114524e-06, "epoch": 0.7009815657170217, "percentage": 70.11, "elapsed_time": "4:26:29", "remaining_time": "1:53:35", "throughput": 4108.96, "total_tokens": 65701376}
184
+ {"current_steps": 184, "total_steps": 261, "loss": 0.1278, "accuracy": 0.953125, "lr": 2.147802687734409e-06, "epoch": 0.7048120660761312, "percentage": 70.5, "elapsed_time": "4:27:57", "remaining_time": "1:52:08", "throughput": 4108.72, "total_tokens": 66057152}
185
+ {"current_steps": 185, "total_steps": 261, "loss": 0.1137, "accuracy": 0.9609375, "lr": 2.0966267470675273e-06, "epoch": 0.7086425664352406, "percentage": 70.88, "elapsed_time": "4:29:24", "remaining_time": "1:50:40", "throughput": 4108.71, "total_tokens": 66413248}
186
+ {"current_steps": 186, "total_steps": 261, "loss": 0.1468, "accuracy": 0.921875, "lr": 2.0459056368215786e-06, "epoch": 0.71247306679435, "percentage": 71.26, "elapsed_time": "4:30:51", "remaining_time": "1:49:12", "throughput": 4109.05, "total_tokens": 66777600}
187
+ {"current_steps": 187, "total_steps": 261, "loss": 0.1509, "accuracy": 0.953125, "lr": 1.9956473027554846e-06, "epoch": 0.7163035671534594, "percentage": 71.65, "elapsed_time": "4:32:18", "remaining_time": "1:47:45", "throughput": 4108.46, "total_tokens": 67126784}
188
+ {"current_steps": 188, "total_steps": 261, "loss": 0.1212, "accuracy": 0.96875, "lr": 1.9458596181315643e-06, "epoch": 0.7201340675125688, "percentage": 72.03, "elapsed_time": "4:33:45", "remaining_time": "1:46:17", "throughput": 4108.67, "total_tokens": 67486848}
189
+ {"current_steps": 189, "total_steps": 261, "loss": 0.1096, "accuracy": 0.9609375, "lr": 1.8965503824821496e-06, "epoch": 0.7239645678716783, "percentage": 72.41, "elapsed_time": "4:35:10", "remaining_time": "1:44:49", "throughput": 4108.35, "total_tokens": 67830400}
190
+ {"current_steps": 190, "total_steps": 261, "loss": 0.156, "accuracy": 0.9453125, "lr": 1.84772732038774e-06, "epoch": 0.7277950682307877, "percentage": 72.8, "elapsed_time": "4:36:35", "remaining_time": "1:43:21", "throughput": 4108.7, "total_tokens": 68184448}
191
+ {"current_steps": 191, "total_steps": 261, "loss": 0.105, "accuracy": 0.96875, "lr": 1.7993980802668947e-06, "epoch": 0.731625568589897, "percentage": 73.18, "elapsed_time": "4:38:02", "remaining_time": "1:41:54", "throughput": 4108.25, "total_tokens": 68536640}
192
+ {"current_steps": 192, "total_steps": 261, "loss": 0.124, "accuracy": 0.9765625, "lr": 1.7515702331780753e-06, "epoch": 0.7354560689490065, "percentage": 73.56, "elapsed_time": "4:39:26", "remaining_time": "1:40:25", "throughput": 4108.35, "total_tokens": 68881216}
193
+ {"current_steps": 193, "total_steps": 261, "loss": 0.1209, "accuracy": 0.96875, "lr": 1.7042512716335873e-06, "epoch": 0.7392865693081159, "percentage": 73.95, "elapsed_time": "4:40:56", "remaining_time": "1:38:59", "throughput": 4108.62, "total_tokens": 69258368}
194
+ {"current_steps": 194, "total_steps": 261, "loss": 0.1065, "accuracy": 0.9609375, "lr": 1.6574486084258369e-06, "epoch": 0.7431170696672252, "percentage": 74.33, "elapsed_time": "4:42:25", "remaining_time": "1:37:32", "throughput": 4108.27, "total_tokens": 69617152}
195
+ {"current_steps": 195, "total_steps": 261, "loss": 0.1183, "accuracy": 0.9609375, "lr": 1.6111695754660667e-06, "epoch": 0.7469475700263347, "percentage": 74.71, "elapsed_time": "4:43:54", "remaining_time": "1:36:05", "throughput": 4107.99, "total_tokens": 69979072}
196
+ {"current_steps": 196, "total_steps": 261, "loss": 0.0792, "accuracy": 0.9921875, "lr": 1.5654214226357822e-06, "epoch": 0.7507780703854441, "percentage": 75.1, "elapsed_time": "4:45:21", "remaining_time": "1:34:38", "throughput": 4108.54, "total_tokens": 70344768}
197
+ {"current_steps": 197, "total_steps": 261, "loss": 0.1402, "accuracy": 0.9453125, "lr": 1.5202113166510058e-06, "epoch": 0.7546085707445535, "percentage": 75.48, "elapsed_time": "4:46:53", "remaining_time": "1:33:12", "throughput": 4108.56, "total_tokens": 70721984}
198
+ {"current_steps": 198, "total_steps": 261, "loss": 0.0939, "accuracy": 0.9765625, "lr": 1.475546339939568e-06, "epoch": 0.7584390711036629, "percentage": 75.86, "elapsed_time": "4:48:21", "remaining_time": "1:31:44", "throughput": 4108.5, "total_tokens": 71082368}
199
+ {"current_steps": 199, "total_steps": 261, "loss": 0.1234, "accuracy": 0.96875, "lr": 1.4314334895316095e-06, "epoch": 0.7622695714627723, "percentage": 76.25, "elapsed_time": "4:49:49", "remaining_time": "1:30:17", "throughput": 4108.13, "total_tokens": 71436928}
200
+ {"current_steps": 200, "total_steps": 261, "loss": 0.1007, "accuracy": 0.984375, "lr": 1.3878796759634544e-06, "epoch": 0.7661000718218818, "percentage": 76.63, "elapsed_time": "4:51:20", "remaining_time": "1:28:51", "throughput": 4107.49, "total_tokens": 71801024}
201
+ {"current_steps": 201, "total_steps": 261, "loss": 0.1182, "accuracy": 0.96875, "lr": 1.3448917221950264e-06, "epoch": 0.7699305721809911, "percentage": 77.01, "elapsed_time": "4:52:50", "remaining_time": "1:27:24", "throughput": 4107.64, "total_tokens": 72172800}
202
+ {"current_steps": 202, "total_steps": 261, "loss": 0.0918, "accuracy": 0.9765625, "lr": 1.3024763625410025e-06, "epoch": 0.7737610725401005, "percentage": 77.39, "elapsed_time": "4:54:18", "remaining_time": "1:25:57", "throughput": 4107.65, "total_tokens": 72536000}
203
+ {"current_steps": 203, "total_steps": 261, "loss": 0.1069, "accuracy": 0.984375, "lr": 1.2606402416158391e-06, "epoch": 0.77759157289921, "percentage": 77.78, "elapsed_time": "4:55:48", "remaining_time": "1:24:30", "throughput": 4107.51, "total_tokens": 72900672}
204
+ {"current_steps": 204, "total_steps": 261, "loss": 0.1164, "accuracy": 0.96875, "lr": 1.2193899132928539e-06, "epoch": 0.7814220732583194, "percentage": 78.16, "elapsed_time": "4:57:11", "remaining_time": "1:23:02", "throughput": 4107.43, "total_tokens": 73242240}
205
+ {"current_steps": 205, "total_steps": 261, "loss": 0.1268, "accuracy": 0.953125, "lr": 1.1787318396775188e-06, "epoch": 0.7852525736174287, "percentage": 78.54, "elapsed_time": "4:58:39", "remaining_time": "1:21:35", "throughput": 4107.39, "total_tokens": 73604288}
206
+ {"current_steps": 206, "total_steps": 261, "loss": 0.1272, "accuracy": 0.9453125, "lr": 1.138672390095143e-06, "epoch": 0.7890830739765382, "percentage": 78.93, "elapsed_time": "5:00:04", "remaining_time": "1:20:06", "throughput": 4107.6, "total_tokens": 73953984}
207
+ {"current_steps": 207, "total_steps": 261, "loss": 0.1464, "accuracy": 0.9609375, "lr": 1.0992178400930753e-06, "epoch": 0.7929135743356476, "percentage": 79.31, "elapsed_time": "5:01:33", "remaining_time": "1:18:40", "throughput": 4107.63, "total_tokens": 74322752}
208
+ {"current_steps": 208, "total_steps": 261, "loss": 0.0975, "accuracy": 0.96875, "lr": 1.0603743704575992e-06, "epoch": 0.796744074694757, "percentage": 79.69, "elapsed_time": "5:03:04", "remaining_time": "1:17:13", "throughput": 4107.5, "total_tokens": 74692672}
209
+ {"current_steps": 209, "total_steps": 261, "loss": 0.1429, "accuracy": 0.96875, "lr": 1.0221480662456845e-06, "epoch": 0.8005745750538664, "percentage": 80.08, "elapsed_time": "5:04:30", "remaining_time": "1:15:45", "throughput": 4107.48, "total_tokens": 75043648}
210
+ {"current_steps": 210, "total_steps": 261, "loss": 0.1222, "accuracy": 0.96875, "lr": 9.845449158317216e-07, "epoch": 0.8044050754129758, "percentage": 80.46, "elapsed_time": "5:05:58", "remaining_time": "1:14:18", "throughput": 4107.58, "total_tokens": 75408832}
211
+ {"current_steps": 211, "total_steps": 261, "loss": 0.09, "accuracy": 0.984375, "lr": 9.475708099694125e-07, "epoch": 0.8082355757720853, "percentage": 80.84, "elapsed_time": "5:07:28", "remaining_time": "1:12:51", "throughput": 4106.95, "total_tokens": 75767744}
212
+ {"current_steps": 212, "total_steps": 261, "loss": 0.151, "accuracy": 0.9453125, "lr": 9.112315408689415e-07, "epoch": 0.8120660761311946, "percentage": 81.23, "elapsed_time": "5:08:58", "remaining_time": "1:11:24", "throughput": 4107.26, "total_tokens": 76143744}
213
+ {"current_steps": 213, "total_steps": 261, "loss": 0.1176, "accuracy": 0.9609375, "lr": 8.755328012896002e-07, "epoch": 0.815896576490304, "percentage": 81.61, "elapsed_time": "5:10:24", "remaining_time": "1:09:57", "throughput": 4107.0, "total_tokens": 76490112}
214
+ {"current_steps": 214, "total_steps": 261, "loss": 0.1373, "accuracy": 0.9609375, "lr": 8.404801836479809e-07, "epoch": 0.8197270768494135, "percentage": 81.99, "elapsed_time": "5:11:54", "remaining_time": "1:08:30", "throughput": 4107.32, "total_tokens": 76866048}
215
+ {"current_steps": 215, "total_steps": 261, "loss": 0.1295, "accuracy": 0.9453125, "lr": 8.060791791418887e-07, "epoch": 0.8235575772085229, "percentage": 82.38, "elapsed_time": "5:13:26", "remaining_time": "1:07:03", "throughput": 4106.8, "total_tokens": 77235840}
216
+ {"current_steps": 216, "total_steps": 261, "loss": 0.1176, "accuracy": 0.9765625, "lr": 7.723351768901172e-07, "epoch": 0.8273880775676322, "percentage": 82.76, "elapsed_time": "5:14:53", "remaining_time": "1:05:36", "throughput": 4106.77, "total_tokens": 77590592}
217
+ {"current_steps": 217, "total_steps": 261, "loss": 0.1177, "accuracy": 0.9609375, "lr": 7.392534630882092e-07, "epoch": 0.8312185779267417, "percentage": 83.14, "elapsed_time": "5:16:20", "remaining_time": "1:04:08", "throughput": 4106.76, "total_tokens": 77947072}
218
+ {"current_steps": 218, "total_steps": 261, "loss": 0.1055, "accuracy": 0.953125, "lr": 7.06839220180342e-07, "epoch": 0.8350490782858511, "percentage": 83.52, "elapsed_time": "5:17:45", "remaining_time": "1:02:40", "throughput": 4106.77, "total_tokens": 78299264}
219
+ {"current_steps": 219, "total_steps": 261, "loss": 0.1392, "accuracy": 0.9609375, "lr": 6.750975260474718e-07, "epoch": 0.8388795786449605, "percentage": 83.91, "elapsed_time": "5:19:11", "remaining_time": "1:01:12", "throughput": 4107.21, "total_tokens": 78658112}
220
+ {"current_steps": 220, "total_steps": 261, "loss": 0.1061, "accuracy": 0.9765625, "lr": 6.440333532118503e-07, "epoch": 0.8427100790040699, "percentage": 84.29, "elapsed_time": "5:20:41", "remaining_time": "0:59:45", "throughput": 4106.81, "total_tokens": 79021824}
221
+ {"current_steps": 221, "total_steps": 261, "loss": 0.0769, "accuracy": 0.984375, "lr": 6.136515680580479e-07, "epoch": 0.8465405793631793, "percentage": 84.67, "elapsed_time": "5:22:08", "remaining_time": "0:58:18", "throughput": 4106.74, "total_tokens": 79377856}
222
+ {"current_steps": 222, "total_steps": 261, "loss": 0.0993, "accuracy": 0.9609375, "lr": 5.839569300706127e-07, "epoch": 0.8503710797222888, "percentage": 85.06, "elapsed_time": "5:23:35", "remaining_time": "0:56:50", "throughput": 4106.74, "total_tokens": 79735616}
223
+ {"current_steps": 223, "total_steps": 261, "loss": 0.0954, "accuracy": 0.96875, "lr": 5.549540910884649e-07, "epoch": 0.8542015800813981, "percentage": 85.44, "elapsed_time": "5:25:06", "remaining_time": "0:55:24", "throughput": 4106.46, "total_tokens": 80104704}
224
+ {"current_steps": 224, "total_steps": 261, "loss": 0.0731, "accuracy": 0.9921875, "lr": 5.266475945761562e-07, "epoch": 0.8580320804405075, "percentage": 85.82, "elapsed_time": "5:26:29", "remaining_time": "0:53:55", "throughput": 4106.86, "total_tokens": 80450752}
225
+ {"current_steps": 225, "total_steps": 261, "loss": 0.1237, "accuracy": 0.96875, "lr": 4.990418749121179e-07, "epoch": 0.861862580799617, "percentage": 86.21, "elapsed_time": "5:27:57", "remaining_time": "0:52:28", "throughput": 4107.09, "total_tokens": 80818432}
226
+ {"current_steps": 226, "total_steps": 261, "loss": 0.0816, "accuracy": 0.9765625, "lr": 4.721412566939804e-07, "epoch": 0.8656930811587263, "percentage": 86.59, "elapsed_time": "5:29:24", "remaining_time": "0:51:00", "throughput": 4107.05, "total_tokens": 81175296}
227
+ {"current_steps": 227, "total_steps": 261, "loss": 0.1063, "accuracy": 0.9609375, "lr": 4.4594995406110785e-07, "epoch": 0.8695235815178358, "percentage": 86.97, "elapsed_time": "5:30:53", "remaining_time": "0:49:33", "throughput": 4106.61, "total_tokens": 81528576}
228
+ {"current_steps": 228, "total_steps": 261, "loss": 0.1303, "accuracy": 0.9609375, "lr": 4.2047207003442003e-07, "epoch": 0.8733540818769452, "percentage": 87.36, "elapsed_time": "5:32:22", "remaining_time": "0:48:06", "throughput": 4106.4, "total_tokens": 81893888}
229
+ {"current_steps": 229, "total_steps": 261, "loss": 0.1263, "accuracy": 0.9453125, "lr": 3.957115958736374e-07, "epoch": 0.8771845822360546, "percentage": 87.74, "elapsed_time": "5:33:41", "remaining_time": "0:46:37", "throughput": 4106.6, "total_tokens": 82220416}
230
+ {"current_steps": 230, "total_steps": 261, "loss": 0.1151, "accuracy": 0.9609375, "lr": 3.7167241045202474e-07, "epoch": 0.881015082595164, "percentage": 88.12, "elapsed_time": "5:35:08", "remaining_time": "0:45:10", "throughput": 4106.82, "total_tokens": 82582784}
231
+ {"current_steps": 231, "total_steps": 261, "loss": 0.0953, "accuracy": 0.9765625, "lr": 3.483582796487395e-07, "epoch": 0.8848455829542734, "percentage": 88.51, "elapsed_time": "5:36:38", "remaining_time": "0:43:43", "throughput": 4106.55, "total_tokens": 82945856}
232
+ {"current_steps": 232, "total_steps": 261, "loss": 0.1001, "accuracy": 0.9765625, "lr": 3.257728557588902e-07, "epoch": 0.8886760833133828, "percentage": 88.89, "elapsed_time": "5:38:09", "remaining_time": "0:42:16", "throughput": 4106.76, "total_tokens": 83325760}
233
+ {"current_steps": 233, "total_steps": 261, "loss": 0.0911, "accuracy": 0.984375, "lr": 3.039196769213787e-07, "epoch": 0.8925065836724922, "percentage": 89.27, "elapsed_time": "5:39:35", "remaining_time": "0:40:48", "throughput": 4107.17, "total_tokens": 83684032}
234
+ {"current_steps": 234, "total_steps": 261, "loss": 0.1165, "accuracy": 0.96875, "lr": 2.828021665646341e-07, "epoch": 0.8963370840316016, "percentage": 89.66, "elapsed_time": "5:41:04", "remaining_time": "0:39:21", "throughput": 4107.55, "total_tokens": 84058624}
235
+ {"current_steps": 235, "total_steps": 261, "loss": 0.1757, "accuracy": 0.9296875, "lr": 2.6242363287030617e-07, "epoch": 0.900167584390711, "percentage": 90.04, "elapsed_time": "5:42:31", "remaining_time": "0:37:53", "throughput": 4107.73, "total_tokens": 84418816}
236
+ {"current_steps": 236, "total_steps": 261, "loss": 0.1672, "accuracy": 0.9296875, "lr": 2.4278726825502696e-07, "epoch": 0.9039980847498205, "percentage": 90.42, "elapsed_time": "5:44:02", "remaining_time": "0:36:26", "throughput": 4107.7, "total_tokens": 84791232}
237
+ {"current_steps": 237, "total_steps": 261, "loss": 0.1262, "accuracy": 0.96875, "lr": 2.2389614887029564e-07, "epoch": 0.9078285851089298, "percentage": 90.8, "elapsed_time": "5:45:28", "remaining_time": "0:34:59", "throughput": 4107.78, "total_tokens": 85148544}
238
+ {"current_steps": 238, "total_steps": 261, "loss": 0.1671, "accuracy": 0.9453125, "lr": 2.0575323412058036e-07, "epoch": 0.9116590854680393, "percentage": 91.19, "elapsed_time": "5:46:55", "remaining_time": "0:33:31", "throughput": 4108.28, "total_tokens": 85514624}
239
+ {"current_steps": 239, "total_steps": 261, "loss": 0.1018, "accuracy": 0.9765625, "lr": 1.8836136619971468e-07, "epoch": 0.9154895858271487, "percentage": 91.57, "elapsed_time": "5:48:18", "remaining_time": "0:32:03", "throughput": 4108.7, "total_tokens": 85866560}
240
+ {"current_steps": 240, "total_steps": 261, "loss": 0.1222, "accuracy": 0.96875, "lr": 1.7172326964564777e-07, "epoch": 0.919320086186258, "percentage": 91.95, "elapsed_time": "5:49:47", "remaining_time": "0:30:36", "throughput": 4108.53, "total_tokens": 86227584}
241
+ {"current_steps": 241, "total_steps": 261, "loss": 0.1439, "accuracy": 0.9609375, "lr": 1.5584155091362907e-07, "epoch": 0.9231505865453675, "percentage": 92.34, "elapsed_time": "5:51:16", "remaining_time": "0:29:09", "throughput": 4108.87, "total_tokens": 86599360}
242
+ {"current_steps": 242, "total_steps": 261, "loss": 0.1047, "accuracy": 0.9765625, "lr": 1.4071869796789427e-07, "epoch": 0.9269810869044769, "percentage": 92.72, "elapsed_time": "5:52:45", "remaining_time": "0:27:41", "throughput": 4108.77, "total_tokens": 86962112}
243
+ {"current_steps": 243, "total_steps": 261, "loss": 0.0951, "accuracy": 0.9609375, "lr": 1.263570798919106e-07, "epoch": 0.9308115872635863, "percentage": 93.1, "elapsed_time": "5:54:10", "remaining_time": "0:26:14", "throughput": 4109.06, "total_tokens": 87320064}
244
+ {"current_steps": 244, "total_steps": 261, "loss": 0.111, "accuracy": 0.9765625, "lr": 1.1275894651724517e-07, "epoch": 0.9346420876226957, "percentage": 93.49, "elapsed_time": "5:55:37", "remaining_time": "0:24:46", "throughput": 4108.78, "total_tokens": 87670976}
245
+ {"current_steps": 245, "total_steps": 261, "loss": 0.0918, "accuracy": 0.984375, "lr": 9.992642807111486e-08, "epoch": 0.9384725879818051, "percentage": 93.87, "elapsed_time": "5:56:57", "remaining_time": "0:23:18", "throughput": 4108.86, "total_tokens": 88002176}
246
+ {"current_steps": 246, "total_steps": 261, "loss": 0.0682, "accuracy": 0.9921875, "lr": 8.78615348426759e-08, "epoch": 0.9423030883409146, "percentage": 94.25, "elapsed_time": "5:58:22", "remaining_time": "0:21:51", "throughput": 4108.79, "total_tokens": 88350976}
247
+ {"current_steps": 247, "total_steps": 261, "loss": 0.0867, "accuracy": 0.984375, "lr": 7.656615686809976e-08, "epoch": 0.946133588700024, "percentage": 94.64, "elapsed_time": "5:59:52", "remaining_time": "0:20:23", "throughput": 4108.56, "total_tokens": 88715456}
248
+ {"current_steps": 248, "total_steps": 261, "loss": 0.0874, "accuracy": 0.984375, "lr": 6.604206363448662e-08, "epoch": 0.9499640890591333, "percentage": 95.02, "elapsed_time": "6:01:21", "remaining_time": "0:18:56", "throughput": 4108.95, "total_tokens": 89086656}
249
+ {"current_steps": 249, "total_steps": 261, "loss": 0.0937, "accuracy": 0.9765625, "lr": 5.6290903802665444e-08, "epoch": 0.9537945894182428, "percentage": 95.4, "elapsed_time": "6:02:54", "remaining_time": "0:17:29", "throughput": 4108.84, "total_tokens": 89469120}
250
+ {"current_steps": 250, "total_steps": 261, "loss": 0.1485, "accuracy": 0.953125, "lr": 4.7314204948923356e-08, "epoch": 0.9576250897773522, "percentage": 95.79, "elapsed_time": "6:04:23", "remaining_time": "0:16:01", "throughput": 4108.85, "total_tokens": 89832832}
251
+ {"current_steps": 251, "total_steps": 261, "loss": 0.143, "accuracy": 0.953125, "lr": 3.911337332569876e-08, "epoch": 0.9614555901364615, "percentage": 96.17, "elapsed_time": "6:05:49", "remaining_time": "0:14:34", "throughput": 4108.79, "total_tokens": 90184960}
252
+ {"current_steps": 252, "total_steps": 261, "loss": 0.1005, "accuracy": 0.9609375, "lr": 3.168969364128527e-08, "epoch": 0.965286090495571, "percentage": 96.55, "elapsed_time": "6:07:17", "remaining_time": "0:13:07", "throughput": 4108.39, "total_tokens": 90540608}
253
+ {"current_steps": 253, "total_steps": 261, "loss": 0.1082, "accuracy": 0.96875, "lr": 2.5044328858576105e-08, "epoch": 0.9691165908546804, "percentage": 96.93, "elapsed_time": "6:08:45", "remaining_time": "0:11:39", "throughput": 4108.53, "total_tokens": 90903552}
254
+ {"current_steps": 254, "total_steps": 261, "loss": 0.1193, "accuracy": 0.9453125, "lr": 1.917832001287645e-08, "epoch": 0.9729470912137897, "percentage": 97.32, "elapsed_time": "6:10:23", "remaining_time": "0:10:12", "throughput": 4107.27, "total_tokens": 91277824}
255
+ {"current_steps": 255, "total_steps": 261, "loss": 0.1073, "accuracy": 0.96875, "lr": 1.4092586048820578e-08, "epoch": 0.9767775915728992, "percentage": 97.7, "elapsed_time": "6:11:50", "remaining_time": "0:08:44", "throughput": 4107.44, "total_tokens": 91637568}
256
+ {"current_steps": 256, "total_steps": 261, "loss": 0.1165, "accuracy": 0.9765625, "lr": 9.787923676414235e-09, "epoch": 0.9806080919320086, "percentage": 98.08, "elapsed_time": "6:13:15", "remaining_time": "0:07:17", "throughput": 4107.35, "total_tokens": 91986624}
257
+ {"current_steps": 257, "total_steps": 261, "loss": 0.1232, "accuracy": 0.9765625, "lr": 6.265007246223365e-09, "epoch": 0.9844385922911181, "percentage": 98.47, "elapsed_time": "6:14:46", "remaining_time": "0:05:49", "throughput": 4107.29, "total_tokens": 92359232}
258
+ {"current_steps": 258, "total_steps": 261, "loss": 0.1287, "accuracy": 0.9609375, "lr": 3.524388643736387e-09, "epoch": 0.9882690926502274, "percentage": 98.85, "elapsed_time": "6:16:16", "remaining_time": "0:04:22", "throughput": 4107.16, "total_tokens": 92725888}
259
+ {"current_steps": 259, "total_steps": 261, "loss": 0.1515, "accuracy": 0.9375, "lr": 1.566497202904471e-09, "epoch": 0.9920995930093368, "percentage": 99.23, "elapsed_time": "6:17:46", "remaining_time": "0:02:55", "throughput": 4107.02, "total_tokens": 93092224}
260
+ {"current_steps": 260, "total_steps": 261, "loss": 0.1015, "accuracy": 0.9765625, "lr": 3.916396388869981e-10, "epoch": 0.9959300933684463, "percentage": 99.62, "elapsed_time": "6:19:12", "remaining_time": "0:01:27", "throughput": 4107.3, "total_tokens": 93450688}
261
+ {"current_steps": 261, "total_steps": 261, "loss": 0.1225, "accuracy": 0.9453125, "lr": 0.0, "epoch": 0.9997605937275557, "percentage": 100.0, "elapsed_time": "6:20:38", "remaining_time": "0:00:00", "throughput": 4107.23, "total_tokens": 93801152}
262
+ {"current_steps": 261, "total_steps": 261, "epoch": 0.9997605937275557, "percentage": 100.0, "elapsed_time": "6:20:41", "remaining_time": "0:00:00", "throughput": 4106.61, "total_tokens": 93801152}
huatuo-o1-Med-REFL-LoraAdapter/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
huatuo-o1-Med-REFL-LoraAdapter/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6def9b9db806518266832e691d4e104bde84b17f602a7256c4abee2923ec02
3
+ size 5688
huatuo-o1-Med-REFL-LoraAdapter/training_loss.png ADDED
huatuo-o1-Med-REFL-LoraAdapter/training_rewards_accuracies.png ADDED