JW17 commited on
Commit
abfe084
·
verified ·
1 Parent(s): f7e206e

Add files using upload-large-folder tool

Browse files
Files changed (43) hide show
  1. .gitattributes +5 -0
  2. README.md +55 -0
  3. checkpoint-160/config.json +47 -0
  4. checkpoint-160/model.safetensors +3 -0
  5. checkpoint-160/special_tokens_map.json +23 -0
  6. checkpoint-160/tokenizer.json +3 -0
  7. checkpoint-160/tokenizer_config.json +2064 -0
  8. checkpoint-160/trainer_state.json +2113 -0
  9. checkpoint-160/training_args.bin +3 -0
  10. checkpoint-240/config.json +47 -0
  11. checkpoint-240/model.safetensors +3 -0
  12. checkpoint-240/special_tokens_map.json +23 -0
  13. checkpoint-240/tokenizer.json +3 -0
  14. checkpoint-240/tokenizer_config.json +2064 -0
  15. checkpoint-240/trainer_state.json +3153 -0
  16. checkpoint-240/training_args.bin +3 -0
  17. checkpoint-320/config.json +47 -0
  18. checkpoint-320/model.safetensors +3 -0
  19. checkpoint-320/special_tokens_map.json +23 -0
  20. checkpoint-320/tokenizer.json +3 -0
  21. checkpoint-320/tokenizer_config.json +2064 -0
  22. checkpoint-320/trainer_state.json +4193 -0
  23. checkpoint-320/training_args.bin +3 -0
  24. checkpoint-400/config.json +47 -0
  25. checkpoint-400/model.safetensors +3 -0
  26. checkpoint-400/special_tokens_map.json +23 -0
  27. checkpoint-400/tokenizer.json +3 -0
  28. checkpoint-400/tokenizer_config.json +2064 -0
  29. checkpoint-400/trainer_state.json +0 -0
  30. checkpoint-400/training_args.bin +3 -0
  31. checkpoint-80/config.json +47 -0
  32. checkpoint-80/model.safetensors +3 -0
  33. checkpoint-80/special_tokens_map.json +23 -0
  34. checkpoint-80/tokenizer.json +3 -0
  35. checkpoint-80/tokenizer_config.json +2064 -0
  36. checkpoint-80/trainer_state.json +1073 -0
  37. checkpoint-80/training_args.bin +3 -0
  38. config.json +47 -0
  39. model.safetensors +3 -0
  40. special_tokens_map.json +23 -0
  41. tokenizer.json +3 -0
  42. tokenizer_config.json +2064 -0
  43. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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
+ checkpoint-80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: tlrm/L32-1B-UC
3
+ library_name: transformers
4
+ tags:
5
+ - generated_from_trainer
6
+ licence: license
7
+ ---
8
+
9
+ # Model Card for None
10
+
11
+ This model is a fine-tuned version of [tlrm/L32-1B-UC](https://huggingface.co/tlrm/L32-1B-UC).
12
+ It has been trained using [TRL](https://github.com/huggingface/trl).
13
+
14
+ ## Quick start
15
+
16
+ ```python
17
+ from transformers import pipeline
18
+
19
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
20
+ generator = pipeline("text-generation", model="None", device="cuda")
21
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
22
+ print(output["generated_text"])
23
+ ```
24
+
25
+ ## Training procedure
26
+
27
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jiwooya1000/RMVar-Submission/runs/nj58ft7v)
28
+
29
+
30
+ This model was trained with Reward.
31
+
32
+ ### Framework versions
33
+
34
+ - TRL: 0.13.0
35
+ - Transformers: 4.48.0
36
+ - Pytorch: 2.4.1+cu124
37
+ - Datasets: 3.2.0
38
+ - Tokenizers: 0.21.0
39
+
40
+ ## Citations
41
+
42
+
43
+
44
+ Cite TRL as:
45
+
46
+ ```bibtex
47
+ @misc{vonwerra2022trl,
48
+ title = {{TRL: Transformer Reinforcement Learning}},
49
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
50
+ year = 2020,
51
+ journal = {GitHub repository},
52
+ publisher = {GitHub},
53
+ howpublished = {\url{https://github.com/huggingface/trl}}
54
+ }
55
+ ```
checkpoint-160/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-1B-UC",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "max_position_embeddings": 131072,
26
+ "mlp_bias": false,
27
+ "model_type": "llama",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 16,
30
+ "num_key_value_heads": 8,
31
+ "pad_token_id": 128001,
32
+ "pretraining_tp": 1,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "factor": 32.0,
36
+ "high_freq_factor": 4.0,
37
+ "low_freq_factor": 1.0,
38
+ "original_max_position_embeddings": 8192,
39
+ "rope_type": "llama3"
40
+ },
41
+ "rope_theta": 500000.0,
42
+ "tie_word_embeddings": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.48.0",
45
+ "use_cache": false,
46
+ "vocab_size": 128256
47
+ }
checkpoint-160/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73e5a347c23d1c85061fbb41ac580f214955281f05ba9b1b3d7b0dd07817659
3
+ size 4943282608
checkpoint-160/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-160/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-160/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,2113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.4,
5
+ "eval_steps": 500,
6
+ "global_step": 160,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "Batch Mean": 2.64666748046875,
13
+ "accuracy": 0.484375,
14
+ "epoch": 0,
15
+ "step": 0
16
+ },
17
+ {
18
+ "epoch": 0.0025,
19
+ "grad_norm": 9.6364107131958,
20
+ "learning_rate": 2.5000000000000004e-07,
21
+ "loss": 0.723,
22
+ "step": 1
23
+ },
24
+ {
25
+ "Batch Mean": 2.6478805541992188,
26
+ "accuracy": 0.46875,
27
+ "epoch": 0.0025,
28
+ "step": 1
29
+ },
30
+ {
31
+ "epoch": 0.005,
32
+ "grad_norm": 7.393254280090332,
33
+ "learning_rate": 5.000000000000001e-07,
34
+ "loss": 0.7006,
35
+ "step": 2
36
+ },
37
+ {
38
+ "Batch Mean": 2.62982177734375,
39
+ "accuracy": 0.4453125,
40
+ "epoch": 0.005,
41
+ "step": 2
42
+ },
43
+ {
44
+ "epoch": 0.0075,
45
+ "grad_norm": 8.464498519897461,
46
+ "learning_rate": 7.5e-07,
47
+ "loss": 0.7093,
48
+ "step": 3
49
+ },
50
+ {
51
+ "Batch Mean": 2.6655197143554688,
52
+ "accuracy": 0.5,
53
+ "epoch": 0.0075,
54
+ "step": 3
55
+ },
56
+ {
57
+ "epoch": 0.01,
58
+ "grad_norm": 7.2742462158203125,
59
+ "learning_rate": 1.0000000000000002e-06,
60
+ "loss": 0.7101,
61
+ "step": 4
62
+ },
63
+ {
64
+ "Batch Mean": 2.616424560546875,
65
+ "accuracy": 0.4296875,
66
+ "epoch": 0.01,
67
+ "step": 4
68
+ },
69
+ {
70
+ "epoch": 0.0125,
71
+ "grad_norm": 8.216493606567383,
72
+ "learning_rate": 1.25e-06,
73
+ "loss": 0.7145,
74
+ "step": 5
75
+ },
76
+ {
77
+ "Batch Mean": 2.6591033935546875,
78
+ "accuracy": 0.546875,
79
+ "epoch": 0.0125,
80
+ "step": 5
81
+ },
82
+ {
83
+ "epoch": 0.015,
84
+ "grad_norm": 8.033185958862305,
85
+ "learning_rate": 1.5e-06,
86
+ "loss": 0.6821,
87
+ "step": 6
88
+ },
89
+ {
90
+ "Batch Mean": 2.6329345703125,
91
+ "accuracy": 0.640625,
92
+ "epoch": 0.015,
93
+ "step": 6
94
+ },
95
+ {
96
+ "epoch": 0.0175,
97
+ "grad_norm": 10.476421356201172,
98
+ "learning_rate": 1.75e-06,
99
+ "loss": 0.6911,
100
+ "step": 7
101
+ },
102
+ {
103
+ "Batch Mean": 2.680908203125,
104
+ "accuracy": 0.5859375,
105
+ "epoch": 0.0175,
106
+ "step": 7
107
+ },
108
+ {
109
+ "epoch": 0.02,
110
+ "grad_norm": 9.513436317443848,
111
+ "learning_rate": 2.0000000000000003e-06,
112
+ "loss": 0.6859,
113
+ "step": 8
114
+ },
115
+ {
116
+ "Batch Mean": 2.658843994140625,
117
+ "accuracy": 0.53125,
118
+ "epoch": 0.02,
119
+ "step": 8
120
+ },
121
+ {
122
+ "epoch": 0.0225,
123
+ "grad_norm": 7.415161609649658,
124
+ "learning_rate": 2.25e-06,
125
+ "loss": 0.6839,
126
+ "step": 9
127
+ },
128
+ {
129
+ "Batch Mean": 2.74237060546875,
130
+ "accuracy": 0.6328125,
131
+ "epoch": 0.0225,
132
+ "step": 9
133
+ },
134
+ {
135
+ "epoch": 0.025,
136
+ "grad_norm": 6.572882175445557,
137
+ "learning_rate": 2.5e-06,
138
+ "loss": 0.6557,
139
+ "step": 10
140
+ },
141
+ {
142
+ "Batch Mean": 2.9183349609375,
143
+ "accuracy": 0.65625,
144
+ "epoch": 0.025,
145
+ "step": 10
146
+ },
147
+ {
148
+ "epoch": 0.0275,
149
+ "grad_norm": 6.594631671905518,
150
+ "learning_rate": 2.7500000000000004e-06,
151
+ "loss": 0.6336,
152
+ "step": 11
153
+ },
154
+ {
155
+ "Batch Mean": 2.929656982421875,
156
+ "accuracy": 0.546875,
157
+ "epoch": 0.0275,
158
+ "step": 11
159
+ },
160
+ {
161
+ "epoch": 0.03,
162
+ "grad_norm": 6.199557304382324,
163
+ "learning_rate": 3e-06,
164
+ "loss": 0.6784,
165
+ "step": 12
166
+ },
167
+ {
168
+ "Batch Mean": 2.938323974609375,
169
+ "accuracy": 0.59375,
170
+ "epoch": 0.03,
171
+ "step": 12
172
+ },
173
+ {
174
+ "epoch": 0.0325,
175
+ "grad_norm": 8.091628074645996,
176
+ "learning_rate": 3.2500000000000002e-06,
177
+ "loss": 0.6887,
178
+ "step": 13
179
+ },
180
+ {
181
+ "Batch Mean": 3.0481414794921875,
182
+ "accuracy": 0.6171875,
183
+ "epoch": 0.0325,
184
+ "step": 13
185
+ },
186
+ {
187
+ "epoch": 0.035,
188
+ "grad_norm": 8.876925468444824,
189
+ "learning_rate": 3.5e-06,
190
+ "loss": 0.6421,
191
+ "step": 14
192
+ },
193
+ {
194
+ "Batch Mean": 3.2818450927734375,
195
+ "accuracy": 0.703125,
196
+ "epoch": 0.035,
197
+ "step": 14
198
+ },
199
+ {
200
+ "epoch": 0.0375,
201
+ "grad_norm": 10.33357048034668,
202
+ "learning_rate": 3.7500000000000005e-06,
203
+ "loss": 0.5853,
204
+ "step": 15
205
+ },
206
+ {
207
+ "Batch Mean": 3.2837677001953125,
208
+ "accuracy": 0.625,
209
+ "epoch": 0.0375,
210
+ "step": 15
211
+ },
212
+ {
213
+ "epoch": 0.04,
214
+ "grad_norm": 11.141650199890137,
215
+ "learning_rate": 4.000000000000001e-06,
216
+ "loss": 0.6495,
217
+ "step": 16
218
+ },
219
+ {
220
+ "Batch Mean": 3.2836532592773438,
221
+ "accuracy": 0.6015625,
222
+ "epoch": 0.04,
223
+ "step": 16
224
+ },
225
+ {
226
+ "epoch": 0.0425,
227
+ "grad_norm": 8.093420028686523,
228
+ "learning_rate": 4.25e-06,
229
+ "loss": 0.6607,
230
+ "step": 17
231
+ },
232
+ {
233
+ "Batch Mean": 3.3738174438476562,
234
+ "accuracy": 0.65625,
235
+ "epoch": 0.0425,
236
+ "step": 17
237
+ },
238
+ {
239
+ "epoch": 0.045,
240
+ "grad_norm": 8.171963691711426,
241
+ "learning_rate": 4.5e-06,
242
+ "loss": 0.5946,
243
+ "step": 18
244
+ },
245
+ {
246
+ "Batch Mean": 3.8035507202148438,
247
+ "accuracy": 0.6015625,
248
+ "epoch": 0.045,
249
+ "step": 18
250
+ },
251
+ {
252
+ "epoch": 0.0475,
253
+ "grad_norm": 10.379010200500488,
254
+ "learning_rate": 4.75e-06,
255
+ "loss": 0.62,
256
+ "step": 19
257
+ },
258
+ {
259
+ "Batch Mean": 4.241037845611572,
260
+ "accuracy": 0.7421875,
261
+ "epoch": 0.0475,
262
+ "step": 19
263
+ },
264
+ {
265
+ "epoch": 0.05,
266
+ "grad_norm": 8.072366714477539,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6094,
269
+ "step": 20
270
+ },
271
+ {
272
+ "Batch Mean": 4.397010803222656,
273
+ "accuracy": 0.65625,
274
+ "epoch": 0.05,
275
+ "step": 20
276
+ },
277
+ {
278
+ "epoch": 0.0525,
279
+ "grad_norm": 7.2537384033203125,
280
+ "learning_rate": 4.986842105263158e-06,
281
+ "loss": 0.5916,
282
+ "step": 21
283
+ },
284
+ {
285
+ "Batch Mean": 4.36688232421875,
286
+ "accuracy": 0.671875,
287
+ "epoch": 0.0525,
288
+ "step": 21
289
+ },
290
+ {
291
+ "epoch": 0.055,
292
+ "grad_norm": 8.559549331665039,
293
+ "learning_rate": 4.973684210526316e-06,
294
+ "loss": 0.5884,
295
+ "step": 22
296
+ },
297
+ {
298
+ "Batch Mean": 4.482940673828125,
299
+ "accuracy": 0.6640625,
300
+ "epoch": 0.055,
301
+ "step": 22
302
+ },
303
+ {
304
+ "epoch": 0.0575,
305
+ "grad_norm": 8.731099128723145,
306
+ "learning_rate": 4.960526315789474e-06,
307
+ "loss": 0.6106,
308
+ "step": 23
309
+ },
310
+ {
311
+ "Batch Mean": 4.41278076171875,
312
+ "accuracy": 0.7109375,
313
+ "epoch": 0.0575,
314
+ "step": 23
315
+ },
316
+ {
317
+ "epoch": 0.06,
318
+ "grad_norm": 6.149895191192627,
319
+ "learning_rate": 4.947368421052632e-06,
320
+ "loss": 0.5569,
321
+ "step": 24
322
+ },
323
+ {
324
+ "Batch Mean": 4.1328277587890625,
325
+ "accuracy": 0.6484375,
326
+ "epoch": 0.06,
327
+ "step": 24
328
+ },
329
+ {
330
+ "epoch": 0.0625,
331
+ "grad_norm": 6.8678879737854,
332
+ "learning_rate": 4.9342105263157895e-06,
333
+ "loss": 0.5729,
334
+ "step": 25
335
+ },
336
+ {
337
+ "Batch Mean": 3.8360061645507812,
338
+ "accuracy": 0.6484375,
339
+ "epoch": 0.0625,
340
+ "step": 25
341
+ },
342
+ {
343
+ "epoch": 0.065,
344
+ "grad_norm": 6.591639041900635,
345
+ "learning_rate": 4.921052631578948e-06,
346
+ "loss": 0.5902,
347
+ "step": 26
348
+ },
349
+ {
350
+ "Batch Mean": 3.9048538208007812,
351
+ "accuracy": 0.6953125,
352
+ "epoch": 0.065,
353
+ "step": 26
354
+ },
355
+ {
356
+ "epoch": 0.0675,
357
+ "grad_norm": 5.855933666229248,
358
+ "learning_rate": 4.907894736842106e-06,
359
+ "loss": 0.5666,
360
+ "step": 27
361
+ },
362
+ {
363
+ "Batch Mean": 3.7672348022460938,
364
+ "accuracy": 0.6953125,
365
+ "epoch": 0.0675,
366
+ "step": 27
367
+ },
368
+ {
369
+ "epoch": 0.07,
370
+ "grad_norm": 5.393594264984131,
371
+ "learning_rate": 4.894736842105264e-06,
372
+ "loss": 0.5508,
373
+ "step": 28
374
+ },
375
+ {
376
+ "Batch Mean": 3.723773956298828,
377
+ "accuracy": 0.65625,
378
+ "epoch": 0.07,
379
+ "step": 28
380
+ },
381
+ {
382
+ "epoch": 0.0725,
383
+ "grad_norm": 5.428353786468506,
384
+ "learning_rate": 4.881578947368422e-06,
385
+ "loss": 0.5694,
386
+ "step": 29
387
+ },
388
+ {
389
+ "Batch Mean": 3.7498779296875,
390
+ "accuracy": 0.6953125,
391
+ "epoch": 0.0725,
392
+ "step": 29
393
+ },
394
+ {
395
+ "epoch": 0.075,
396
+ "grad_norm": 5.005551338195801,
397
+ "learning_rate": 4.8684210526315795e-06,
398
+ "loss": 0.5905,
399
+ "step": 30
400
+ },
401
+ {
402
+ "Batch Mean": 3.564330577850342,
403
+ "accuracy": 0.671875,
404
+ "epoch": 0.075,
405
+ "step": 30
406
+ },
407
+ {
408
+ "epoch": 0.0775,
409
+ "grad_norm": 6.4090681076049805,
410
+ "learning_rate": 4.855263157894737e-06,
411
+ "loss": 0.5901,
412
+ "step": 31
413
+ },
414
+ {
415
+ "Batch Mean": 3.5886306762695312,
416
+ "accuracy": 0.7421875,
417
+ "epoch": 0.0775,
418
+ "step": 31
419
+ },
420
+ {
421
+ "epoch": 0.08,
422
+ "grad_norm": 6.025192737579346,
423
+ "learning_rate": 4.842105263157895e-06,
424
+ "loss": 0.5265,
425
+ "step": 32
426
+ },
427
+ {
428
+ "Batch Mean": 3.64593505859375,
429
+ "accuracy": 0.6953125,
430
+ "epoch": 0.08,
431
+ "step": 32
432
+ },
433
+ {
434
+ "epoch": 0.0825,
435
+ "grad_norm": 6.129398345947266,
436
+ "learning_rate": 4.828947368421053e-06,
437
+ "loss": 0.5083,
438
+ "step": 33
439
+ },
440
+ {
441
+ "Batch Mean": 3.5973358154296875,
442
+ "accuracy": 0.6875,
443
+ "epoch": 0.0825,
444
+ "step": 33
445
+ },
446
+ {
447
+ "epoch": 0.085,
448
+ "grad_norm": 6.91660737991333,
449
+ "learning_rate": 4.815789473684211e-06,
450
+ "loss": 0.5365,
451
+ "step": 34
452
+ },
453
+ {
454
+ "Batch Mean": 3.6286163330078125,
455
+ "accuracy": 0.7109375,
456
+ "epoch": 0.085,
457
+ "step": 34
458
+ },
459
+ {
460
+ "epoch": 0.0875,
461
+ "grad_norm": 7.553361892700195,
462
+ "learning_rate": 4.802631578947369e-06,
463
+ "loss": 0.5196,
464
+ "step": 35
465
+ },
466
+ {
467
+ "Batch Mean": 3.5937328338623047,
468
+ "accuracy": 0.7109375,
469
+ "epoch": 0.0875,
470
+ "step": 35
471
+ },
472
+ {
473
+ "epoch": 0.09,
474
+ "grad_norm": 7.884591579437256,
475
+ "learning_rate": 4.789473684210527e-06,
476
+ "loss": 0.5533,
477
+ "step": 36
478
+ },
479
+ {
480
+ "Batch Mean": 3.28558349609375,
481
+ "accuracy": 0.6796875,
482
+ "epoch": 0.09,
483
+ "step": 36
484
+ },
485
+ {
486
+ "epoch": 0.0925,
487
+ "grad_norm": 8.118135452270508,
488
+ "learning_rate": 4.7763157894736844e-06,
489
+ "loss": 0.5145,
490
+ "step": 37
491
+ },
492
+ {
493
+ "Batch Mean": 3.079477310180664,
494
+ "accuracy": 0.7421875,
495
+ "epoch": 0.0925,
496
+ "step": 37
497
+ },
498
+ {
499
+ "epoch": 0.095,
500
+ "grad_norm": 10.431463241577148,
501
+ "learning_rate": 4.763157894736842e-06,
502
+ "loss": 0.6,
503
+ "step": 38
504
+ },
505
+ {
506
+ "Batch Mean": 2.9296703338623047,
507
+ "accuracy": 0.7578125,
508
+ "epoch": 0.095,
509
+ "step": 38
510
+ },
511
+ {
512
+ "epoch": 0.0975,
513
+ "grad_norm": 8.055816650390625,
514
+ "learning_rate": 4.75e-06,
515
+ "loss": 0.445,
516
+ "step": 39
517
+ },
518
+ {
519
+ "Batch Mean": 2.9282093048095703,
520
+ "accuracy": 0.7109375,
521
+ "epoch": 0.0975,
522
+ "step": 39
523
+ },
524
+ {
525
+ "epoch": 0.1,
526
+ "grad_norm": 9.155073165893555,
527
+ "learning_rate": 4.736842105263158e-06,
528
+ "loss": 0.5568,
529
+ "step": 40
530
+ },
531
+ {
532
+ "Batch Mean": 2.4473862648010254,
533
+ "accuracy": 0.6171875,
534
+ "epoch": 0.1,
535
+ "step": 40
536
+ },
537
+ {
538
+ "epoch": 0.1025,
539
+ "grad_norm": 8.89163589477539,
540
+ "learning_rate": 4.723684210526316e-06,
541
+ "loss": 0.5934,
542
+ "step": 41
543
+ },
544
+ {
545
+ "Batch Mean": 2.4439845085144043,
546
+ "accuracy": 0.6953125,
547
+ "epoch": 0.1025,
548
+ "step": 41
549
+ },
550
+ {
551
+ "epoch": 0.105,
552
+ "grad_norm": 7.411705017089844,
553
+ "learning_rate": 4.710526315789474e-06,
554
+ "loss": 0.5522,
555
+ "step": 42
556
+ },
557
+ {
558
+ "Batch Mean": 1.7335999011993408,
559
+ "accuracy": 0.734375,
560
+ "epoch": 0.105,
561
+ "step": 42
562
+ },
563
+ {
564
+ "epoch": 0.1075,
565
+ "grad_norm": 7.0730109214782715,
566
+ "learning_rate": 4.697368421052632e-06,
567
+ "loss": 0.5157,
568
+ "step": 43
569
+ },
570
+ {
571
+ "Batch Mean": 1.7379779815673828,
572
+ "accuracy": 0.71875,
573
+ "epoch": 0.1075,
574
+ "step": 43
575
+ },
576
+ {
577
+ "epoch": 0.11,
578
+ "grad_norm": 7.879677772521973,
579
+ "learning_rate": 4.68421052631579e-06,
580
+ "loss": 0.5405,
581
+ "step": 44
582
+ },
583
+ {
584
+ "Batch Mean": 1.7085151672363281,
585
+ "accuracy": 0.6796875,
586
+ "epoch": 0.11,
587
+ "step": 44
588
+ },
589
+ {
590
+ "epoch": 0.1125,
591
+ "grad_norm": 6.630401611328125,
592
+ "learning_rate": 4.671052631578948e-06,
593
+ "loss": 0.564,
594
+ "step": 45
595
+ },
596
+ {
597
+ "Batch Mean": 1.7431907653808594,
598
+ "accuracy": 0.734375,
599
+ "epoch": 0.1125,
600
+ "step": 45
601
+ },
602
+ {
603
+ "epoch": 0.115,
604
+ "grad_norm": 6.569342136383057,
605
+ "learning_rate": 4.657894736842106e-06,
606
+ "loss": 0.4969,
607
+ "step": 46
608
+ },
609
+ {
610
+ "Batch Mean": 2.4792041778564453,
611
+ "accuracy": 0.6953125,
612
+ "epoch": 0.115,
613
+ "step": 46
614
+ },
615
+ {
616
+ "epoch": 0.1175,
617
+ "grad_norm": 6.198298931121826,
618
+ "learning_rate": 4.6447368421052635e-06,
619
+ "loss": 0.5501,
620
+ "step": 47
621
+ },
622
+ {
623
+ "Batch Mean": 2.4960689544677734,
624
+ "accuracy": 0.7578125,
625
+ "epoch": 0.1175,
626
+ "step": 47
627
+ },
628
+ {
629
+ "epoch": 0.12,
630
+ "grad_norm": 5.984739780426025,
631
+ "learning_rate": 4.631578947368421e-06,
632
+ "loss": 0.4513,
633
+ "step": 48
634
+ },
635
+ {
636
+ "Batch Mean": 2.7437705993652344,
637
+ "accuracy": 0.71875,
638
+ "epoch": 0.12,
639
+ "step": 48
640
+ },
641
+ {
642
+ "epoch": 0.1225,
643
+ "grad_norm": 6.669623374938965,
644
+ "learning_rate": 4.618421052631579e-06,
645
+ "loss": 0.5404,
646
+ "step": 49
647
+ },
648
+ {
649
+ "Batch Mean": 2.672210693359375,
650
+ "accuracy": 0.75,
651
+ "epoch": 0.1225,
652
+ "step": 49
653
+ },
654
+ {
655
+ "epoch": 0.125,
656
+ "grad_norm": 6.217676639556885,
657
+ "learning_rate": 4.605263157894737e-06,
658
+ "loss": 0.4668,
659
+ "step": 50
660
+ },
661
+ {
662
+ "Batch Mean": 2.7935009002685547,
663
+ "accuracy": 0.75,
664
+ "epoch": 0.125,
665
+ "step": 50
666
+ },
667
+ {
668
+ "epoch": 0.1275,
669
+ "grad_norm": 7.666802883148193,
670
+ "learning_rate": 4.592105263157895e-06,
671
+ "loss": 0.5491,
672
+ "step": 51
673
+ },
674
+ {
675
+ "Batch Mean": 2.651923179626465,
676
+ "accuracy": 0.734375,
677
+ "epoch": 0.1275,
678
+ "step": 51
679
+ },
680
+ {
681
+ "epoch": 0.13,
682
+ "grad_norm": 9.799866676330566,
683
+ "learning_rate": 4.578947368421053e-06,
684
+ "loss": 0.5173,
685
+ "step": 52
686
+ },
687
+ {
688
+ "Batch Mean": 2.9287376403808594,
689
+ "accuracy": 0.734375,
690
+ "epoch": 0.13,
691
+ "step": 52
692
+ },
693
+ {
694
+ "epoch": 0.1325,
695
+ "grad_norm": 8.577540397644043,
696
+ "learning_rate": 4.565789473684211e-06,
697
+ "loss": 0.5279,
698
+ "step": 53
699
+ },
700
+ {
701
+ "Batch Mean": 3.0377674102783203,
702
+ "accuracy": 0.7265625,
703
+ "epoch": 0.1325,
704
+ "step": 53
705
+ },
706
+ {
707
+ "epoch": 0.135,
708
+ "grad_norm": 8.099453926086426,
709
+ "learning_rate": 4.552631578947369e-06,
710
+ "loss": 0.5122,
711
+ "step": 54
712
+ },
713
+ {
714
+ "Batch Mean": 3.3550057411193848,
715
+ "accuracy": 0.6953125,
716
+ "epoch": 0.135,
717
+ "step": 54
718
+ },
719
+ {
720
+ "epoch": 0.1375,
721
+ "grad_norm": 9.597841262817383,
722
+ "learning_rate": 4.539473684210527e-06,
723
+ "loss": 0.5034,
724
+ "step": 55
725
+ },
726
+ {
727
+ "Batch Mean": 3.3833670616149902,
728
+ "accuracy": 0.7578125,
729
+ "epoch": 0.1375,
730
+ "step": 55
731
+ },
732
+ {
733
+ "epoch": 0.14,
734
+ "grad_norm": 9.208806037902832,
735
+ "learning_rate": 4.526315789473685e-06,
736
+ "loss": 0.53,
737
+ "step": 56
738
+ },
739
+ {
740
+ "Batch Mean": 3.255979537963867,
741
+ "accuracy": 0.7890625,
742
+ "epoch": 0.14,
743
+ "step": 56
744
+ },
745
+ {
746
+ "epoch": 0.1425,
747
+ "grad_norm": 7.923739910125732,
748
+ "learning_rate": 4.513157894736843e-06,
749
+ "loss": 0.4315,
750
+ "step": 57
751
+ },
752
+ {
753
+ "Batch Mean": 3.003221273422241,
754
+ "accuracy": 0.7265625,
755
+ "epoch": 0.1425,
756
+ "step": 57
757
+ },
758
+ {
759
+ "epoch": 0.145,
760
+ "grad_norm": 8.64991569519043,
761
+ "learning_rate": 4.5e-06,
762
+ "loss": 0.5038,
763
+ "step": 58
764
+ },
765
+ {
766
+ "Batch Mean": 3.122058868408203,
767
+ "accuracy": 0.78125,
768
+ "epoch": 0.145,
769
+ "step": 58
770
+ },
771
+ {
772
+ "epoch": 0.1475,
773
+ "grad_norm": 8.633460998535156,
774
+ "learning_rate": 4.4868421052631584e-06,
775
+ "loss": 0.4886,
776
+ "step": 59
777
+ },
778
+ {
779
+ "Batch Mean": 2.8752236366271973,
780
+ "accuracy": 0.7109375,
781
+ "epoch": 0.1475,
782
+ "step": 59
783
+ },
784
+ {
785
+ "epoch": 0.15,
786
+ "grad_norm": 8.399279594421387,
787
+ "learning_rate": 4.473684210526316e-06,
788
+ "loss": 0.5239,
789
+ "step": 60
790
+ },
791
+ {
792
+ "Batch Mean": 2.694100856781006,
793
+ "accuracy": 0.7578125,
794
+ "epoch": 0.15,
795
+ "step": 60
796
+ },
797
+ {
798
+ "epoch": 0.1525,
799
+ "grad_norm": 7.846778869628906,
800
+ "learning_rate": 4.460526315789474e-06,
801
+ "loss": 0.4538,
802
+ "step": 61
803
+ },
804
+ {
805
+ "Batch Mean": 2.59914493560791,
806
+ "accuracy": 0.8046875,
807
+ "epoch": 0.1525,
808
+ "step": 61
809
+ },
810
+ {
811
+ "epoch": 0.155,
812
+ "grad_norm": 7.844125270843506,
813
+ "learning_rate": 4.447368421052632e-06,
814
+ "loss": 0.4234,
815
+ "step": 62
816
+ },
817
+ {
818
+ "Batch Mean": 2.431262493133545,
819
+ "accuracy": 0.75,
820
+ "epoch": 0.155,
821
+ "step": 62
822
+ },
823
+ {
824
+ "epoch": 0.1575,
825
+ "grad_norm": 8.15548038482666,
826
+ "learning_rate": 4.43421052631579e-06,
827
+ "loss": 0.4695,
828
+ "step": 63
829
+ },
830
+ {
831
+ "Batch Mean": 2.162135124206543,
832
+ "accuracy": 0.7421875,
833
+ "epoch": 0.1575,
834
+ "step": 63
835
+ },
836
+ {
837
+ "epoch": 0.16,
838
+ "grad_norm": 9.166322708129883,
839
+ "learning_rate": 4.4210526315789476e-06,
840
+ "loss": 0.4898,
841
+ "step": 64
842
+ },
843
+ {
844
+ "Batch Mean": 1.8282737731933594,
845
+ "accuracy": 0.75,
846
+ "epoch": 0.16,
847
+ "step": 64
848
+ },
849
+ {
850
+ "epoch": 0.1625,
851
+ "grad_norm": 9.52655029296875,
852
+ "learning_rate": 4.407894736842105e-06,
853
+ "loss": 0.4651,
854
+ "step": 65
855
+ },
856
+ {
857
+ "Batch Mean": 1.9480819702148438,
858
+ "accuracy": 0.7890625,
859
+ "epoch": 0.1625,
860
+ "step": 65
861
+ },
862
+ {
863
+ "epoch": 0.165,
864
+ "grad_norm": 8.491720199584961,
865
+ "learning_rate": 4.394736842105263e-06,
866
+ "loss": 0.4578,
867
+ "step": 66
868
+ },
869
+ {
870
+ "Batch Mean": 1.8442394733428955,
871
+ "accuracy": 0.7734375,
872
+ "epoch": 0.165,
873
+ "step": 66
874
+ },
875
+ {
876
+ "epoch": 0.1675,
877
+ "grad_norm": 9.01707649230957,
878
+ "learning_rate": 4.381578947368421e-06,
879
+ "loss": 0.4858,
880
+ "step": 67
881
+ },
882
+ {
883
+ "Batch Mean": 1.2759554386138916,
884
+ "accuracy": 0.6953125,
885
+ "epoch": 0.1675,
886
+ "step": 67
887
+ },
888
+ {
889
+ "epoch": 0.17,
890
+ "grad_norm": 10.790990829467773,
891
+ "learning_rate": 4.368421052631579e-06,
892
+ "loss": 0.5368,
893
+ "step": 68
894
+ },
895
+ {
896
+ "Batch Mean": 0.916658878326416,
897
+ "accuracy": 0.7109375,
898
+ "epoch": 0.17,
899
+ "step": 68
900
+ },
901
+ {
902
+ "epoch": 0.1725,
903
+ "grad_norm": 10.27574634552002,
904
+ "learning_rate": 4.3552631578947375e-06,
905
+ "loss": 0.5475,
906
+ "step": 69
907
+ },
908
+ {
909
+ "Batch Mean": 0.9389474391937256,
910
+ "accuracy": 0.6875,
911
+ "epoch": 0.1725,
912
+ "step": 69
913
+ },
914
+ {
915
+ "epoch": 0.175,
916
+ "grad_norm": 9.463624954223633,
917
+ "learning_rate": 4.342105263157895e-06,
918
+ "loss": 0.5295,
919
+ "step": 70
920
+ },
921
+ {
922
+ "Batch Mean": 0.6801865100860596,
923
+ "accuracy": 0.78125,
924
+ "epoch": 0.175,
925
+ "step": 70
926
+ },
927
+ {
928
+ "epoch": 0.1775,
929
+ "grad_norm": 7.813968658447266,
930
+ "learning_rate": 4.328947368421053e-06,
931
+ "loss": 0.4602,
932
+ "step": 71
933
+ },
934
+ {
935
+ "Batch Mean": 0.6634016036987305,
936
+ "accuracy": 0.78125,
937
+ "epoch": 0.1775,
938
+ "step": 71
939
+ },
940
+ {
941
+ "epoch": 0.18,
942
+ "grad_norm": 7.322629928588867,
943
+ "learning_rate": 4.315789473684211e-06,
944
+ "loss": 0.4328,
945
+ "step": 72
946
+ },
947
+ {
948
+ "Batch Mean": 0.518225908279419,
949
+ "accuracy": 0.8359375,
950
+ "epoch": 0.18,
951
+ "step": 72
952
+ },
953
+ {
954
+ "epoch": 0.1825,
955
+ "grad_norm": 7.121971130371094,
956
+ "learning_rate": 4.302631578947369e-06,
957
+ "loss": 0.3997,
958
+ "step": 73
959
+ },
960
+ {
961
+ "Batch Mean": 0.6286078691482544,
962
+ "accuracy": 0.75,
963
+ "epoch": 0.1825,
964
+ "step": 73
965
+ },
966
+ {
967
+ "epoch": 0.185,
968
+ "grad_norm": 8.812067031860352,
969
+ "learning_rate": 4.289473684210527e-06,
970
+ "loss": 0.5345,
971
+ "step": 74
972
+ },
973
+ {
974
+ "Batch Mean": 0.4055500030517578,
975
+ "accuracy": 0.78125,
976
+ "epoch": 0.185,
977
+ "step": 74
978
+ },
979
+ {
980
+ "epoch": 0.1875,
981
+ "grad_norm": 8.031818389892578,
982
+ "learning_rate": 4.276315789473684e-06,
983
+ "loss": 0.4436,
984
+ "step": 75
985
+ },
986
+ {
987
+ "Batch Mean": 0.6844688057899475,
988
+ "accuracy": 0.6640625,
989
+ "epoch": 0.1875,
990
+ "step": 75
991
+ },
992
+ {
993
+ "epoch": 0.19,
994
+ "grad_norm": 9.14492130279541,
995
+ "learning_rate": 4.2631578947368425e-06,
996
+ "loss": 0.5727,
997
+ "step": 76
998
+ },
999
+ {
1000
+ "Batch Mean": 0.549891471862793,
1001
+ "accuracy": 0.7578125,
1002
+ "epoch": 0.19,
1003
+ "step": 76
1004
+ },
1005
+ {
1006
+ "epoch": 0.1925,
1007
+ "grad_norm": 8.721407890319824,
1008
+ "learning_rate": 4.25e-06,
1009
+ "loss": 0.4997,
1010
+ "step": 77
1011
+ },
1012
+ {
1013
+ "Batch Mean": 0.3632768988609314,
1014
+ "accuracy": 0.703125,
1015
+ "epoch": 0.1925,
1016
+ "step": 77
1017
+ },
1018
+ {
1019
+ "epoch": 0.195,
1020
+ "grad_norm": 8.776328086853027,
1021
+ "learning_rate": 4.236842105263158e-06,
1022
+ "loss": 0.5442,
1023
+ "step": 78
1024
+ },
1025
+ {
1026
+ "Batch Mean": 0.4604153633117676,
1027
+ "accuracy": 0.7421875,
1028
+ "epoch": 0.195,
1029
+ "step": 78
1030
+ },
1031
+ {
1032
+ "epoch": 0.1975,
1033
+ "grad_norm": 7.281062126159668,
1034
+ "learning_rate": 4.223684210526316e-06,
1035
+ "loss": 0.4793,
1036
+ "step": 79
1037
+ },
1038
+ {
1039
+ "Batch Mean": 0.605268120765686,
1040
+ "accuracy": 0.765625,
1041
+ "epoch": 0.1975,
1042
+ "step": 79
1043
+ },
1044
+ {
1045
+ "epoch": 0.2,
1046
+ "grad_norm": 7.533178329467773,
1047
+ "learning_rate": 4.210526315789474e-06,
1048
+ "loss": 0.4338,
1049
+ "step": 80
1050
+ },
1051
+ {
1052
+ "Batch Mean": 0.9789919257164001,
1053
+ "accuracy": 0.75,
1054
+ "epoch": 0.2,
1055
+ "step": 80
1056
+ },
1057
+ {
1058
+ "epoch": 0.2025,
1059
+ "grad_norm": 7.2433671951293945,
1060
+ "learning_rate": 4.197368421052632e-06,
1061
+ "loss": 0.4785,
1062
+ "step": 81
1063
+ },
1064
+ {
1065
+ "Batch Mean": 1.114579200744629,
1066
+ "accuracy": 0.71875,
1067
+ "epoch": 0.2025,
1068
+ "step": 81
1069
+ },
1070
+ {
1071
+ "epoch": 0.205,
1072
+ "grad_norm": 7.2934064865112305,
1073
+ "learning_rate": 4.18421052631579e-06,
1074
+ "loss": 0.4836,
1075
+ "step": 82
1076
+ },
1077
+ {
1078
+ "Batch Mean": 1.0528812408447266,
1079
+ "accuracy": 0.7578125,
1080
+ "epoch": 0.205,
1081
+ "step": 82
1082
+ },
1083
+ {
1084
+ "epoch": 0.2075,
1085
+ "grad_norm": 7.544822692871094,
1086
+ "learning_rate": 4.171052631578948e-06,
1087
+ "loss": 0.5077,
1088
+ "step": 83
1089
+ },
1090
+ {
1091
+ "Batch Mean": 1.1365894079208374,
1092
+ "accuracy": 0.671875,
1093
+ "epoch": 0.2075,
1094
+ "step": 83
1095
+ },
1096
+ {
1097
+ "epoch": 0.21,
1098
+ "grad_norm": 8.340349197387695,
1099
+ "learning_rate": 4.157894736842106e-06,
1100
+ "loss": 0.579,
1101
+ "step": 84
1102
+ },
1103
+ {
1104
+ "Batch Mean": 1.7320103645324707,
1105
+ "accuracy": 0.8125,
1106
+ "epoch": 0.21,
1107
+ "step": 84
1108
+ },
1109
+ {
1110
+ "epoch": 0.2125,
1111
+ "grad_norm": 6.645724296569824,
1112
+ "learning_rate": 4.144736842105263e-06,
1113
+ "loss": 0.4114,
1114
+ "step": 85
1115
+ },
1116
+ {
1117
+ "Batch Mean": 1.443530559539795,
1118
+ "accuracy": 0.7578125,
1119
+ "epoch": 0.2125,
1120
+ "step": 85
1121
+ },
1122
+ {
1123
+ "epoch": 0.215,
1124
+ "grad_norm": 6.647582530975342,
1125
+ "learning_rate": 4.1315789473684216e-06,
1126
+ "loss": 0.4369,
1127
+ "step": 86
1128
+ },
1129
+ {
1130
+ "Batch Mean": 1.5358202457427979,
1131
+ "accuracy": 0.7578125,
1132
+ "epoch": 0.215,
1133
+ "step": 86
1134
+ },
1135
+ {
1136
+ "epoch": 0.2175,
1137
+ "grad_norm": 7.315903186798096,
1138
+ "learning_rate": 4.118421052631579e-06,
1139
+ "loss": 0.4895,
1140
+ "step": 87
1141
+ },
1142
+ {
1143
+ "Batch Mean": 1.7256877422332764,
1144
+ "accuracy": 0.7734375,
1145
+ "epoch": 0.2175,
1146
+ "step": 87
1147
+ },
1148
+ {
1149
+ "epoch": 0.22,
1150
+ "grad_norm": 8.285420417785645,
1151
+ "learning_rate": 4.105263157894737e-06,
1152
+ "loss": 0.5035,
1153
+ "step": 88
1154
+ },
1155
+ {
1156
+ "Batch Mean": 1.5997413396835327,
1157
+ "accuracy": 0.75,
1158
+ "epoch": 0.22,
1159
+ "step": 88
1160
+ },
1161
+ {
1162
+ "epoch": 0.2225,
1163
+ "grad_norm": 7.990715026855469,
1164
+ "learning_rate": 4.092105263157895e-06,
1165
+ "loss": 0.51,
1166
+ "step": 89
1167
+ },
1168
+ {
1169
+ "Batch Mean": 1.6425485610961914,
1170
+ "accuracy": 0.734375,
1171
+ "epoch": 0.2225,
1172
+ "step": 89
1173
+ },
1174
+ {
1175
+ "epoch": 0.225,
1176
+ "grad_norm": 8.72641658782959,
1177
+ "learning_rate": 4.078947368421053e-06,
1178
+ "loss": 0.4908,
1179
+ "step": 90
1180
+ },
1181
+ {
1182
+ "Batch Mean": 1.9212679862976074,
1183
+ "accuracy": 0.84375,
1184
+ "epoch": 0.225,
1185
+ "step": 90
1186
+ },
1187
+ {
1188
+ "epoch": 0.2275,
1189
+ "grad_norm": 7.567220211029053,
1190
+ "learning_rate": 4.065789473684211e-06,
1191
+ "loss": 0.4152,
1192
+ "step": 91
1193
+ },
1194
+ {
1195
+ "Batch Mean": 1.6822540760040283,
1196
+ "accuracy": 0.8046875,
1197
+ "epoch": 0.2275,
1198
+ "step": 91
1199
+ },
1200
+ {
1201
+ "epoch": 0.23,
1202
+ "grad_norm": 7.402642726898193,
1203
+ "learning_rate": 4.052631578947368e-06,
1204
+ "loss": 0.4054,
1205
+ "step": 92
1206
+ },
1207
+ {
1208
+ "Batch Mean": 1.5377750396728516,
1209
+ "accuracy": 0.75,
1210
+ "epoch": 0.23,
1211
+ "step": 92
1212
+ },
1213
+ {
1214
+ "epoch": 0.2325,
1215
+ "grad_norm": 8.574016571044922,
1216
+ "learning_rate": 4.0394736842105265e-06,
1217
+ "loss": 0.4739,
1218
+ "step": 93
1219
+ },
1220
+ {
1221
+ "Batch Mean": 1.332385540008545,
1222
+ "accuracy": 0.734375,
1223
+ "epoch": 0.2325,
1224
+ "step": 93
1225
+ },
1226
+ {
1227
+ "epoch": 0.235,
1228
+ "grad_norm": 8.827500343322754,
1229
+ "learning_rate": 4.026315789473684e-06,
1230
+ "loss": 0.4983,
1231
+ "step": 94
1232
+ },
1233
+ {
1234
+ "Batch Mean": 1.0707147121429443,
1235
+ "accuracy": 0.8046875,
1236
+ "epoch": 0.235,
1237
+ "step": 94
1238
+ },
1239
+ {
1240
+ "epoch": 0.2375,
1241
+ "grad_norm": 7.975078105926514,
1242
+ "learning_rate": 4.013157894736842e-06,
1243
+ "loss": 0.4709,
1244
+ "step": 95
1245
+ },
1246
+ {
1247
+ "Batch Mean": 1.1354491710662842,
1248
+ "accuracy": 0.75,
1249
+ "epoch": 0.2375,
1250
+ "step": 95
1251
+ },
1252
+ {
1253
+ "epoch": 0.24,
1254
+ "grad_norm": 7.764720916748047,
1255
+ "learning_rate": 4.000000000000001e-06,
1256
+ "loss": 0.4697,
1257
+ "step": 96
1258
+ },
1259
+ {
1260
+ "Batch Mean": 0.7834959030151367,
1261
+ "accuracy": 0.765625,
1262
+ "epoch": 0.24,
1263
+ "step": 96
1264
+ },
1265
+ {
1266
+ "epoch": 0.2425,
1267
+ "grad_norm": 8.38682746887207,
1268
+ "learning_rate": 3.986842105263158e-06,
1269
+ "loss": 0.46,
1270
+ "step": 97
1271
+ },
1272
+ {
1273
+ "Batch Mean": 0.9441508650779724,
1274
+ "accuracy": 0.8359375,
1275
+ "epoch": 0.2425,
1276
+ "step": 97
1277
+ },
1278
+ {
1279
+ "epoch": 0.245,
1280
+ "grad_norm": 8.565149307250977,
1281
+ "learning_rate": 3.9736842105263165e-06,
1282
+ "loss": 0.4071,
1283
+ "step": 98
1284
+ },
1285
+ {
1286
+ "Batch Mean": 0.8886473178863525,
1287
+ "accuracy": 0.8203125,
1288
+ "epoch": 0.245,
1289
+ "step": 98
1290
+ },
1291
+ {
1292
+ "epoch": 0.2475,
1293
+ "grad_norm": 7.316027641296387,
1294
+ "learning_rate": 3.960526315789474e-06,
1295
+ "loss": 0.413,
1296
+ "step": 99
1297
+ },
1298
+ {
1299
+ "Batch Mean": 1.3381073474884033,
1300
+ "accuracy": 0.765625,
1301
+ "epoch": 0.2475,
1302
+ "step": 99
1303
+ },
1304
+ {
1305
+ "epoch": 0.25,
1306
+ "grad_norm": 7.380762577056885,
1307
+ "learning_rate": 3.947368421052632e-06,
1308
+ "loss": 0.4639,
1309
+ "step": 100
1310
+ },
1311
+ {
1312
+ "Batch Mean": 1.8181347846984863,
1313
+ "accuracy": 0.78125,
1314
+ "epoch": 0.25,
1315
+ "step": 100
1316
+ },
1317
+ {
1318
+ "epoch": 0.2525,
1319
+ "grad_norm": 8.348108291625977,
1320
+ "learning_rate": 3.93421052631579e-06,
1321
+ "loss": 0.4568,
1322
+ "step": 101
1323
+ },
1324
+ {
1325
+ "Batch Mean": 1.850348711013794,
1326
+ "accuracy": 0.828125,
1327
+ "epoch": 0.2525,
1328
+ "step": 101
1329
+ },
1330
+ {
1331
+ "epoch": 0.255,
1332
+ "grad_norm": 7.533435821533203,
1333
+ "learning_rate": 3.921052631578947e-06,
1334
+ "loss": 0.4471,
1335
+ "step": 102
1336
+ },
1337
+ {
1338
+ "Batch Mean": 1.8302688598632812,
1339
+ "accuracy": 0.7265625,
1340
+ "epoch": 0.255,
1341
+ "step": 102
1342
+ },
1343
+ {
1344
+ "epoch": 0.2575,
1345
+ "grad_norm": 7.560754776000977,
1346
+ "learning_rate": 3.907894736842106e-06,
1347
+ "loss": 0.4922,
1348
+ "step": 103
1349
+ },
1350
+ {
1351
+ "Batch Mean": 1.832013487815857,
1352
+ "accuracy": 0.7734375,
1353
+ "epoch": 0.2575,
1354
+ "step": 103
1355
+ },
1356
+ {
1357
+ "epoch": 0.26,
1358
+ "grad_norm": 8.4998197555542,
1359
+ "learning_rate": 3.894736842105263e-06,
1360
+ "loss": 0.4636,
1361
+ "step": 104
1362
+ },
1363
+ {
1364
+ "Batch Mean": 1.9380416870117188,
1365
+ "accuracy": 0.7421875,
1366
+ "epoch": 0.26,
1367
+ "step": 104
1368
+ },
1369
+ {
1370
+ "epoch": 0.2625,
1371
+ "grad_norm": 8.759364128112793,
1372
+ "learning_rate": 3.8815789473684214e-06,
1373
+ "loss": 0.5117,
1374
+ "step": 105
1375
+ },
1376
+ {
1377
+ "Batch Mean": 2.0537302494049072,
1378
+ "accuracy": 0.78125,
1379
+ "epoch": 0.2625,
1380
+ "step": 105
1381
+ },
1382
+ {
1383
+ "epoch": 0.265,
1384
+ "grad_norm": 7.300965785980225,
1385
+ "learning_rate": 3.868421052631579e-06,
1386
+ "loss": 0.3956,
1387
+ "step": 106
1388
+ },
1389
+ {
1390
+ "Batch Mean": 2.236231803894043,
1391
+ "accuracy": 0.7890625,
1392
+ "epoch": 0.265,
1393
+ "step": 106
1394
+ },
1395
+ {
1396
+ "epoch": 0.2675,
1397
+ "grad_norm": 7.826519012451172,
1398
+ "learning_rate": 3.855263157894737e-06,
1399
+ "loss": 0.462,
1400
+ "step": 107
1401
+ },
1402
+ {
1403
+ "Batch Mean": 2.2571160793304443,
1404
+ "accuracy": 0.78125,
1405
+ "epoch": 0.2675,
1406
+ "step": 107
1407
+ },
1408
+ {
1409
+ "epoch": 0.27,
1410
+ "grad_norm": 7.177440643310547,
1411
+ "learning_rate": 3.842105263157895e-06,
1412
+ "loss": 0.4264,
1413
+ "step": 108
1414
+ },
1415
+ {
1416
+ "Batch Mean": 2.3395166397094727,
1417
+ "accuracy": 0.8359375,
1418
+ "epoch": 0.27,
1419
+ "step": 108
1420
+ },
1421
+ {
1422
+ "epoch": 0.2725,
1423
+ "grad_norm": 7.556861877441406,
1424
+ "learning_rate": 3.828947368421053e-06,
1425
+ "loss": 0.3825,
1426
+ "step": 109
1427
+ },
1428
+ {
1429
+ "Batch Mean": 2.5364012718200684,
1430
+ "accuracy": 0.7890625,
1431
+ "epoch": 0.2725,
1432
+ "step": 109
1433
+ },
1434
+ {
1435
+ "epoch": 0.275,
1436
+ "grad_norm": 8.785236358642578,
1437
+ "learning_rate": 3.815789473684211e-06,
1438
+ "loss": 0.4915,
1439
+ "step": 110
1440
+ },
1441
+ {
1442
+ "Batch Mean": 2.545170783996582,
1443
+ "accuracy": 0.71875,
1444
+ "epoch": 0.275,
1445
+ "step": 110
1446
+ },
1447
+ {
1448
+ "epoch": 0.2775,
1449
+ "grad_norm": 8.062837600708008,
1450
+ "learning_rate": 3.802631578947369e-06,
1451
+ "loss": 0.5025,
1452
+ "step": 111
1453
+ },
1454
+ {
1455
+ "Batch Mean": 2.6232008934020996,
1456
+ "accuracy": 0.7734375,
1457
+ "epoch": 0.2775,
1458
+ "step": 111
1459
+ },
1460
+ {
1461
+ "epoch": 0.28,
1462
+ "grad_norm": 7.3966498374938965,
1463
+ "learning_rate": 3.789473684210527e-06,
1464
+ "loss": 0.4145,
1465
+ "step": 112
1466
+ },
1467
+ {
1468
+ "Batch Mean": 2.351048469543457,
1469
+ "accuracy": 0.6953125,
1470
+ "epoch": 0.28,
1471
+ "step": 112
1472
+ },
1473
+ {
1474
+ "epoch": 0.2825,
1475
+ "grad_norm": 7.810081958770752,
1476
+ "learning_rate": 3.7763157894736847e-06,
1477
+ "loss": 0.5147,
1478
+ "step": 113
1479
+ },
1480
+ {
1481
+ "Batch Mean": 1.6083295345306396,
1482
+ "accuracy": 0.796875,
1483
+ "epoch": 0.2825,
1484
+ "step": 113
1485
+ },
1486
+ {
1487
+ "epoch": 0.285,
1488
+ "grad_norm": 6.8766703605651855,
1489
+ "learning_rate": 3.7631578947368426e-06,
1490
+ "loss": 0.4275,
1491
+ "step": 114
1492
+ },
1493
+ {
1494
+ "Batch Mean": 1.594513177871704,
1495
+ "accuracy": 0.8046875,
1496
+ "epoch": 0.285,
1497
+ "step": 114
1498
+ },
1499
+ {
1500
+ "epoch": 0.2875,
1501
+ "grad_norm": 7.07267427444458,
1502
+ "learning_rate": 3.7500000000000005e-06,
1503
+ "loss": 0.4197,
1504
+ "step": 115
1505
+ },
1506
+ {
1507
+ "Batch Mean": 1.6583623886108398,
1508
+ "accuracy": 0.7421875,
1509
+ "epoch": 0.2875,
1510
+ "step": 115
1511
+ },
1512
+ {
1513
+ "epoch": 0.29,
1514
+ "grad_norm": 8.415107727050781,
1515
+ "learning_rate": 3.736842105263158e-06,
1516
+ "loss": 0.4723,
1517
+ "step": 116
1518
+ },
1519
+ {
1520
+ "Batch Mean": 1.6947704553604126,
1521
+ "accuracy": 0.8203125,
1522
+ "epoch": 0.29,
1523
+ "step": 116
1524
+ },
1525
+ {
1526
+ "epoch": 0.2925,
1527
+ "grad_norm": 7.132028102874756,
1528
+ "learning_rate": 3.723684210526316e-06,
1529
+ "loss": 0.4039,
1530
+ "step": 117
1531
+ },
1532
+ {
1533
+ "Batch Mean": 1.7144229412078857,
1534
+ "accuracy": 0.8046875,
1535
+ "epoch": 0.2925,
1536
+ "step": 117
1537
+ },
1538
+ {
1539
+ "epoch": 0.295,
1540
+ "grad_norm": 6.850518703460693,
1541
+ "learning_rate": 3.710526315789474e-06,
1542
+ "loss": 0.4148,
1543
+ "step": 118
1544
+ },
1545
+ {
1546
+ "Batch Mean": 1.4002912044525146,
1547
+ "accuracy": 0.828125,
1548
+ "epoch": 0.295,
1549
+ "step": 118
1550
+ },
1551
+ {
1552
+ "epoch": 0.2975,
1553
+ "grad_norm": 7.008551120758057,
1554
+ "learning_rate": 3.6973684210526317e-06,
1555
+ "loss": 0.3972,
1556
+ "step": 119
1557
+ },
1558
+ {
1559
+ "Batch Mean": 1.1955918073654175,
1560
+ "accuracy": 0.7890625,
1561
+ "epoch": 0.2975,
1562
+ "step": 119
1563
+ },
1564
+ {
1565
+ "epoch": 0.3,
1566
+ "grad_norm": 8.176568984985352,
1567
+ "learning_rate": 3.6842105263157896e-06,
1568
+ "loss": 0.4894,
1569
+ "step": 120
1570
+ },
1571
+ {
1572
+ "Batch Mean": 1.4260971546173096,
1573
+ "accuracy": 0.765625,
1574
+ "epoch": 0.3,
1575
+ "step": 120
1576
+ },
1577
+ {
1578
+ "epoch": 0.3025,
1579
+ "grad_norm": 7.905389308929443,
1580
+ "learning_rate": 3.6710526315789476e-06,
1581
+ "loss": 0.4796,
1582
+ "step": 121
1583
+ },
1584
+ {
1585
+ "Batch Mean": 1.1381725072860718,
1586
+ "accuracy": 0.84375,
1587
+ "epoch": 0.3025,
1588
+ "step": 121
1589
+ },
1590
+ {
1591
+ "epoch": 0.305,
1592
+ "grad_norm": 7.464083194732666,
1593
+ "learning_rate": 3.657894736842106e-06,
1594
+ "loss": 0.387,
1595
+ "step": 122
1596
+ },
1597
+ {
1598
+ "Batch Mean": 1.064018726348877,
1599
+ "accuracy": 0.8125,
1600
+ "epoch": 0.305,
1601
+ "step": 122
1602
+ },
1603
+ {
1604
+ "epoch": 0.3075,
1605
+ "grad_norm": 8.280699729919434,
1606
+ "learning_rate": 3.644736842105264e-06,
1607
+ "loss": 0.4154,
1608
+ "step": 123
1609
+ },
1610
+ {
1611
+ "Batch Mean": 1.3708758354187012,
1612
+ "accuracy": 0.765625,
1613
+ "epoch": 0.3075,
1614
+ "step": 123
1615
+ },
1616
+ {
1617
+ "epoch": 0.31,
1618
+ "grad_norm": 9.830754280090332,
1619
+ "learning_rate": 3.6315789473684217e-06,
1620
+ "loss": 0.5003,
1621
+ "step": 124
1622
+ },
1623
+ {
1624
+ "Batch Mean": 1.162580132484436,
1625
+ "accuracy": 0.828125,
1626
+ "epoch": 0.31,
1627
+ "step": 124
1628
+ },
1629
+ {
1630
+ "epoch": 0.3125,
1631
+ "grad_norm": 8.671696662902832,
1632
+ "learning_rate": 3.618421052631579e-06,
1633
+ "loss": 0.4389,
1634
+ "step": 125
1635
+ },
1636
+ {
1637
+ "Batch Mean": 0.671147346496582,
1638
+ "accuracy": 0.8125,
1639
+ "epoch": 0.3125,
1640
+ "step": 125
1641
+ },
1642
+ {
1643
+ "epoch": 0.315,
1644
+ "grad_norm": 8.493339538574219,
1645
+ "learning_rate": 3.605263157894737e-06,
1646
+ "loss": 0.4434,
1647
+ "step": 126
1648
+ },
1649
+ {
1650
+ "Batch Mean": 0.8207384347915649,
1651
+ "accuracy": 0.8203125,
1652
+ "epoch": 0.315,
1653
+ "step": 126
1654
+ },
1655
+ {
1656
+ "epoch": 0.3175,
1657
+ "grad_norm": 8.274676322937012,
1658
+ "learning_rate": 3.592105263157895e-06,
1659
+ "loss": 0.4057,
1660
+ "step": 127
1661
+ },
1662
+ {
1663
+ "Batch Mean": 0.5156043767929077,
1664
+ "accuracy": 0.75,
1665
+ "epoch": 0.3175,
1666
+ "step": 127
1667
+ },
1668
+ {
1669
+ "epoch": 0.32,
1670
+ "grad_norm": 9.094855308532715,
1671
+ "learning_rate": 3.578947368421053e-06,
1672
+ "loss": 0.4661,
1673
+ "step": 128
1674
+ },
1675
+ {
1676
+ "Batch Mean": 0.43193674087524414,
1677
+ "accuracy": 0.8203125,
1678
+ "epoch": 0.32,
1679
+ "step": 128
1680
+ },
1681
+ {
1682
+ "epoch": 0.3225,
1683
+ "grad_norm": 8.729266166687012,
1684
+ "learning_rate": 3.565789473684211e-06,
1685
+ "loss": 0.4586,
1686
+ "step": 129
1687
+ },
1688
+ {
1689
+ "Batch Mean": 0.30504658818244934,
1690
+ "accuracy": 0.7421875,
1691
+ "epoch": 0.3225,
1692
+ "step": 129
1693
+ },
1694
+ {
1695
+ "epoch": 0.325,
1696
+ "grad_norm": 11.113021850585938,
1697
+ "learning_rate": 3.5526315789473687e-06,
1698
+ "loss": 0.4894,
1699
+ "step": 130
1700
+ },
1701
+ {
1702
+ "Batch Mean": 0.3271394371986389,
1703
+ "accuracy": 0.7734375,
1704
+ "epoch": 0.325,
1705
+ "step": 130
1706
+ },
1707
+ {
1708
+ "epoch": 0.3275,
1709
+ "grad_norm": 8.692556381225586,
1710
+ "learning_rate": 3.5394736842105266e-06,
1711
+ "loss": 0.4227,
1712
+ "step": 131
1713
+ },
1714
+ {
1715
+ "Batch Mean": 0.6269352436065674,
1716
+ "accuracy": 0.7734375,
1717
+ "epoch": 0.3275,
1718
+ "step": 131
1719
+ },
1720
+ {
1721
+ "epoch": 0.33,
1722
+ "grad_norm": 8.046867370605469,
1723
+ "learning_rate": 3.5263157894736846e-06,
1724
+ "loss": 0.496,
1725
+ "step": 132
1726
+ },
1727
+ {
1728
+ "Batch Mean": 0.6559182405471802,
1729
+ "accuracy": 0.765625,
1730
+ "epoch": 0.33,
1731
+ "step": 132
1732
+ },
1733
+ {
1734
+ "epoch": 0.3325,
1735
+ "grad_norm": 7.385076999664307,
1736
+ "learning_rate": 3.513157894736842e-06,
1737
+ "loss": 0.4459,
1738
+ "step": 133
1739
+ },
1740
+ {
1741
+ "Batch Mean": 0.5328922271728516,
1742
+ "accuracy": 0.7578125,
1743
+ "epoch": 0.3325,
1744
+ "step": 133
1745
+ },
1746
+ {
1747
+ "epoch": 0.335,
1748
+ "grad_norm": 7.108922481536865,
1749
+ "learning_rate": 3.5e-06,
1750
+ "loss": 0.428,
1751
+ "step": 134
1752
+ },
1753
+ {
1754
+ "Batch Mean": 1.1600193977355957,
1755
+ "accuracy": 0.828125,
1756
+ "epoch": 0.335,
1757
+ "step": 134
1758
+ },
1759
+ {
1760
+ "epoch": 0.3375,
1761
+ "grad_norm": 6.962152004241943,
1762
+ "learning_rate": 3.486842105263158e-06,
1763
+ "loss": 0.4237,
1764
+ "step": 135
1765
+ },
1766
+ {
1767
+ "Batch Mean": 1.1642009019851685,
1768
+ "accuracy": 0.6953125,
1769
+ "epoch": 0.3375,
1770
+ "step": 135
1771
+ },
1772
+ {
1773
+ "epoch": 0.34,
1774
+ "grad_norm": 7.879281520843506,
1775
+ "learning_rate": 3.473684210526316e-06,
1776
+ "loss": 0.528,
1777
+ "step": 136
1778
+ },
1779
+ {
1780
+ "Batch Mean": 1.0588830709457397,
1781
+ "accuracy": 0.6953125,
1782
+ "epoch": 0.34,
1783
+ "step": 136
1784
+ },
1785
+ {
1786
+ "epoch": 0.3425,
1787
+ "grad_norm": 9.492472648620605,
1788
+ "learning_rate": 3.460526315789474e-06,
1789
+ "loss": 0.5365,
1790
+ "step": 137
1791
+ },
1792
+ {
1793
+ "Batch Mean": 1.3413481712341309,
1794
+ "accuracy": 0.8046875,
1795
+ "epoch": 0.3425,
1796
+ "step": 137
1797
+ },
1798
+ {
1799
+ "epoch": 0.345,
1800
+ "grad_norm": 6.448349952697754,
1801
+ "learning_rate": 3.447368421052632e-06,
1802
+ "loss": 0.4449,
1803
+ "step": 138
1804
+ },
1805
+ {
1806
+ "Batch Mean": 1.3028790950775146,
1807
+ "accuracy": 0.7578125,
1808
+ "epoch": 0.345,
1809
+ "step": 138
1810
+ },
1811
+ {
1812
+ "epoch": 0.3475,
1813
+ "grad_norm": 6.54162073135376,
1814
+ "learning_rate": 3.43421052631579e-06,
1815
+ "loss": 0.4109,
1816
+ "step": 139
1817
+ },
1818
+ {
1819
+ "Batch Mean": 1.206446886062622,
1820
+ "accuracy": 0.7734375,
1821
+ "epoch": 0.3475,
1822
+ "step": 139
1823
+ },
1824
+ {
1825
+ "epoch": 0.35,
1826
+ "grad_norm": 7.594364166259766,
1827
+ "learning_rate": 3.421052631578948e-06,
1828
+ "loss": 0.4771,
1829
+ "step": 140
1830
+ },
1831
+ {
1832
+ "Batch Mean": 1.425430417060852,
1833
+ "accuracy": 0.7734375,
1834
+ "epoch": 0.35,
1835
+ "step": 140
1836
+ },
1837
+ {
1838
+ "epoch": 0.3525,
1839
+ "grad_norm": 6.744152069091797,
1840
+ "learning_rate": 3.4078947368421057e-06,
1841
+ "loss": 0.4458,
1842
+ "step": 141
1843
+ },
1844
+ {
1845
+ "Batch Mean": 1.4311294555664062,
1846
+ "accuracy": 0.765625,
1847
+ "epoch": 0.3525,
1848
+ "step": 141
1849
+ },
1850
+ {
1851
+ "epoch": 0.355,
1852
+ "grad_norm": 6.789750576019287,
1853
+ "learning_rate": 3.3947368421052636e-06,
1854
+ "loss": 0.4798,
1855
+ "step": 142
1856
+ },
1857
+ {
1858
+ "Batch Mean": 1.6251521110534668,
1859
+ "accuracy": 0.765625,
1860
+ "epoch": 0.355,
1861
+ "step": 142
1862
+ },
1863
+ {
1864
+ "epoch": 0.3575,
1865
+ "grad_norm": 7.658289909362793,
1866
+ "learning_rate": 3.381578947368421e-06,
1867
+ "loss": 0.5209,
1868
+ "step": 143
1869
+ },
1870
+ {
1871
+ "Batch Mean": 1.5901494026184082,
1872
+ "accuracy": 0.7890625,
1873
+ "epoch": 0.3575,
1874
+ "step": 143
1875
+ },
1876
+ {
1877
+ "epoch": 0.36,
1878
+ "grad_norm": 7.741049289703369,
1879
+ "learning_rate": 3.368421052631579e-06,
1880
+ "loss": 0.448,
1881
+ "step": 144
1882
+ },
1883
+ {
1884
+ "Batch Mean": 1.7485175132751465,
1885
+ "accuracy": 0.71875,
1886
+ "epoch": 0.36,
1887
+ "step": 144
1888
+ },
1889
+ {
1890
+ "epoch": 0.3625,
1891
+ "grad_norm": 7.933503150939941,
1892
+ "learning_rate": 3.355263157894737e-06,
1893
+ "loss": 0.4745,
1894
+ "step": 145
1895
+ },
1896
+ {
1897
+ "Batch Mean": 1.8909566402435303,
1898
+ "accuracy": 0.796875,
1899
+ "epoch": 0.3625,
1900
+ "step": 145
1901
+ },
1902
+ {
1903
+ "epoch": 0.365,
1904
+ "grad_norm": 7.310222148895264,
1905
+ "learning_rate": 3.342105263157895e-06,
1906
+ "loss": 0.4671,
1907
+ "step": 146
1908
+ },
1909
+ {
1910
+ "Batch Mean": 2.035611152648926,
1911
+ "accuracy": 0.75,
1912
+ "epoch": 0.365,
1913
+ "step": 146
1914
+ },
1915
+ {
1916
+ "epoch": 0.3675,
1917
+ "grad_norm": 7.8623809814453125,
1918
+ "learning_rate": 3.3289473684210528e-06,
1919
+ "loss": 0.5079,
1920
+ "step": 147
1921
+ },
1922
+ {
1923
+ "Batch Mean": 2.0848422050476074,
1924
+ "accuracy": 0.8203125,
1925
+ "epoch": 0.3675,
1926
+ "step": 147
1927
+ },
1928
+ {
1929
+ "epoch": 0.37,
1930
+ "grad_norm": 7.38020133972168,
1931
+ "learning_rate": 3.3157894736842107e-06,
1932
+ "loss": 0.5131,
1933
+ "step": 148
1934
+ },
1935
+ {
1936
+ "Batch Mean": 1.9938535690307617,
1937
+ "accuracy": 0.7734375,
1938
+ "epoch": 0.37,
1939
+ "step": 148
1940
+ },
1941
+ {
1942
+ "epoch": 0.3725,
1943
+ "grad_norm": 7.401918411254883,
1944
+ "learning_rate": 3.302631578947369e-06,
1945
+ "loss": 0.4059,
1946
+ "step": 149
1947
+ },
1948
+ {
1949
+ "Batch Mean": 1.9994306564331055,
1950
+ "accuracy": 0.8515625,
1951
+ "epoch": 0.3725,
1952
+ "step": 149
1953
+ },
1954
+ {
1955
+ "epoch": 0.375,
1956
+ "grad_norm": 7.515151500701904,
1957
+ "learning_rate": 3.289473684210527e-06,
1958
+ "loss": 0.4198,
1959
+ "step": 150
1960
+ },
1961
+ {
1962
+ "Batch Mean": 1.9627342224121094,
1963
+ "accuracy": 0.78125,
1964
+ "epoch": 0.375,
1965
+ "step": 150
1966
+ },
1967
+ {
1968
+ "epoch": 0.3775,
1969
+ "grad_norm": 9.086411476135254,
1970
+ "learning_rate": 3.276315789473685e-06,
1971
+ "loss": 0.407,
1972
+ "step": 151
1973
+ },
1974
+ {
1975
+ "Batch Mean": 2.247910499572754,
1976
+ "accuracy": 0.75,
1977
+ "epoch": 0.3775,
1978
+ "step": 151
1979
+ },
1980
+ {
1981
+ "epoch": 0.38,
1982
+ "grad_norm": 8.9763765335083,
1983
+ "learning_rate": 3.2631578947368423e-06,
1984
+ "loss": 0.5274,
1985
+ "step": 152
1986
+ },
1987
+ {
1988
+ "Batch Mean": 2.261256694793701,
1989
+ "accuracy": 0.8125,
1990
+ "epoch": 0.38,
1991
+ "step": 152
1992
+ },
1993
+ {
1994
+ "epoch": 0.3825,
1995
+ "grad_norm": 6.913736820220947,
1996
+ "learning_rate": 3.2500000000000002e-06,
1997
+ "loss": 0.4049,
1998
+ "step": 153
1999
+ },
2000
+ {
2001
+ "Batch Mean": 2.136556386947632,
2002
+ "accuracy": 0.78125,
2003
+ "epoch": 0.3825,
2004
+ "step": 153
2005
+ },
2006
+ {
2007
+ "epoch": 0.385,
2008
+ "grad_norm": 7.755904674530029,
2009
+ "learning_rate": 3.236842105263158e-06,
2010
+ "loss": 0.449,
2011
+ "step": 154
2012
+ },
2013
+ {
2014
+ "Batch Mean": 2.088193416595459,
2015
+ "accuracy": 0.8046875,
2016
+ "epoch": 0.385,
2017
+ "step": 154
2018
+ },
2019
+ {
2020
+ "epoch": 0.3875,
2021
+ "grad_norm": 7.1718316078186035,
2022
+ "learning_rate": 3.223684210526316e-06,
2023
+ "loss": 0.4129,
2024
+ "step": 155
2025
+ },
2026
+ {
2027
+ "Batch Mean": 2.5068817138671875,
2028
+ "accuracy": 0.796875,
2029
+ "epoch": 0.3875,
2030
+ "step": 155
2031
+ },
2032
+ {
2033
+ "epoch": 0.39,
2034
+ "grad_norm": 9.461467742919922,
2035
+ "learning_rate": 3.210526315789474e-06,
2036
+ "loss": 0.4147,
2037
+ "step": 156
2038
+ },
2039
+ {
2040
+ "Batch Mean": 2.0449132919311523,
2041
+ "accuracy": 0.7578125,
2042
+ "epoch": 0.39,
2043
+ "step": 156
2044
+ },
2045
+ {
2046
+ "epoch": 0.3925,
2047
+ "grad_norm": 8.785501480102539,
2048
+ "learning_rate": 3.197368421052632e-06,
2049
+ "loss": 0.478,
2050
+ "step": 157
2051
+ },
2052
+ {
2053
+ "Batch Mean": 2.2665648460388184,
2054
+ "accuracy": 0.8203125,
2055
+ "epoch": 0.3925,
2056
+ "step": 157
2057
+ },
2058
+ {
2059
+ "epoch": 0.395,
2060
+ "grad_norm": 7.906212329864502,
2061
+ "learning_rate": 3.1842105263157898e-06,
2062
+ "loss": 0.4083,
2063
+ "step": 158
2064
+ },
2065
+ {
2066
+ "Batch Mean": 1.8799333572387695,
2067
+ "accuracy": 0.734375,
2068
+ "epoch": 0.395,
2069
+ "step": 158
2070
+ },
2071
+ {
2072
+ "epoch": 0.3975,
2073
+ "grad_norm": 9.25344467163086,
2074
+ "learning_rate": 3.1710526315789477e-06,
2075
+ "loss": 0.5007,
2076
+ "step": 159
2077
+ },
2078
+ {
2079
+ "Batch Mean": 2.178339719772339,
2080
+ "accuracy": 0.828125,
2081
+ "epoch": 0.3975,
2082
+ "step": 159
2083
+ },
2084
+ {
2085
+ "epoch": 0.4,
2086
+ "grad_norm": 8.476263046264648,
2087
+ "learning_rate": 3.157894736842105e-06,
2088
+ "loss": 0.4184,
2089
+ "step": 160
2090
+ }
2091
+ ],
2092
+ "logging_steps": 1,
2093
+ "max_steps": 400,
2094
+ "num_input_tokens_seen": 0,
2095
+ "num_train_epochs": 1,
2096
+ "save_steps": 80,
2097
+ "stateful_callbacks": {
2098
+ "TrainerControl": {
2099
+ "args": {
2100
+ "should_epoch_stop": false,
2101
+ "should_evaluate": false,
2102
+ "should_log": false,
2103
+ "should_save": true,
2104
+ "should_training_stop": false
2105
+ },
2106
+ "attributes": {}
2107
+ }
2108
+ },
2109
+ "total_flos": 0.0,
2110
+ "train_batch_size": 64,
2111
+ "trial_name": null,
2112
+ "trial_params": null
2113
+ }
checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130b9bda9b58e60760405321a76b9b11a12c69620b1886f49451f28ec3960f24
3
+ size 5752
checkpoint-240/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-1B-UC",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "max_position_embeddings": 131072,
26
+ "mlp_bias": false,
27
+ "model_type": "llama",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 16,
30
+ "num_key_value_heads": 8,
31
+ "pad_token_id": 128001,
32
+ "pretraining_tp": 1,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "factor": 32.0,
36
+ "high_freq_factor": 4.0,
37
+ "low_freq_factor": 1.0,
38
+ "original_max_position_embeddings": 8192,
39
+ "rope_type": "llama3"
40
+ },
41
+ "rope_theta": 500000.0,
42
+ "tie_word_embeddings": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.48.0",
45
+ "use_cache": false,
46
+ "vocab_size": 128256
47
+ }
checkpoint-240/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1273524da594c58cbc9ec41b23c8b5f249402e4f9cf93f2e3116eae10afe6317
3
+ size 4943282608
checkpoint-240/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-240/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-240/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
checkpoint-240/trainer_state.json ADDED
@@ -0,0 +1,3153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6,
5
+ "eval_steps": 500,
6
+ "global_step": 240,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "Batch Mean": 2.64666748046875,
13
+ "accuracy": 0.484375,
14
+ "epoch": 0,
15
+ "step": 0
16
+ },
17
+ {
18
+ "epoch": 0.0025,
19
+ "grad_norm": 9.6364107131958,
20
+ "learning_rate": 2.5000000000000004e-07,
21
+ "loss": 0.723,
22
+ "step": 1
23
+ },
24
+ {
25
+ "Batch Mean": 2.6478805541992188,
26
+ "accuracy": 0.46875,
27
+ "epoch": 0.0025,
28
+ "step": 1
29
+ },
30
+ {
31
+ "epoch": 0.005,
32
+ "grad_norm": 7.393254280090332,
33
+ "learning_rate": 5.000000000000001e-07,
34
+ "loss": 0.7006,
35
+ "step": 2
36
+ },
37
+ {
38
+ "Batch Mean": 2.62982177734375,
39
+ "accuracy": 0.4453125,
40
+ "epoch": 0.005,
41
+ "step": 2
42
+ },
43
+ {
44
+ "epoch": 0.0075,
45
+ "grad_norm": 8.464498519897461,
46
+ "learning_rate": 7.5e-07,
47
+ "loss": 0.7093,
48
+ "step": 3
49
+ },
50
+ {
51
+ "Batch Mean": 2.6655197143554688,
52
+ "accuracy": 0.5,
53
+ "epoch": 0.0075,
54
+ "step": 3
55
+ },
56
+ {
57
+ "epoch": 0.01,
58
+ "grad_norm": 7.2742462158203125,
59
+ "learning_rate": 1.0000000000000002e-06,
60
+ "loss": 0.7101,
61
+ "step": 4
62
+ },
63
+ {
64
+ "Batch Mean": 2.616424560546875,
65
+ "accuracy": 0.4296875,
66
+ "epoch": 0.01,
67
+ "step": 4
68
+ },
69
+ {
70
+ "epoch": 0.0125,
71
+ "grad_norm": 8.216493606567383,
72
+ "learning_rate": 1.25e-06,
73
+ "loss": 0.7145,
74
+ "step": 5
75
+ },
76
+ {
77
+ "Batch Mean": 2.6591033935546875,
78
+ "accuracy": 0.546875,
79
+ "epoch": 0.0125,
80
+ "step": 5
81
+ },
82
+ {
83
+ "epoch": 0.015,
84
+ "grad_norm": 8.033185958862305,
85
+ "learning_rate": 1.5e-06,
86
+ "loss": 0.6821,
87
+ "step": 6
88
+ },
89
+ {
90
+ "Batch Mean": 2.6329345703125,
91
+ "accuracy": 0.640625,
92
+ "epoch": 0.015,
93
+ "step": 6
94
+ },
95
+ {
96
+ "epoch": 0.0175,
97
+ "grad_norm": 10.476421356201172,
98
+ "learning_rate": 1.75e-06,
99
+ "loss": 0.6911,
100
+ "step": 7
101
+ },
102
+ {
103
+ "Batch Mean": 2.680908203125,
104
+ "accuracy": 0.5859375,
105
+ "epoch": 0.0175,
106
+ "step": 7
107
+ },
108
+ {
109
+ "epoch": 0.02,
110
+ "grad_norm": 9.513436317443848,
111
+ "learning_rate": 2.0000000000000003e-06,
112
+ "loss": 0.6859,
113
+ "step": 8
114
+ },
115
+ {
116
+ "Batch Mean": 2.658843994140625,
117
+ "accuracy": 0.53125,
118
+ "epoch": 0.02,
119
+ "step": 8
120
+ },
121
+ {
122
+ "epoch": 0.0225,
123
+ "grad_norm": 7.415161609649658,
124
+ "learning_rate": 2.25e-06,
125
+ "loss": 0.6839,
126
+ "step": 9
127
+ },
128
+ {
129
+ "Batch Mean": 2.74237060546875,
130
+ "accuracy": 0.6328125,
131
+ "epoch": 0.0225,
132
+ "step": 9
133
+ },
134
+ {
135
+ "epoch": 0.025,
136
+ "grad_norm": 6.572882175445557,
137
+ "learning_rate": 2.5e-06,
138
+ "loss": 0.6557,
139
+ "step": 10
140
+ },
141
+ {
142
+ "Batch Mean": 2.9183349609375,
143
+ "accuracy": 0.65625,
144
+ "epoch": 0.025,
145
+ "step": 10
146
+ },
147
+ {
148
+ "epoch": 0.0275,
149
+ "grad_norm": 6.594631671905518,
150
+ "learning_rate": 2.7500000000000004e-06,
151
+ "loss": 0.6336,
152
+ "step": 11
153
+ },
154
+ {
155
+ "Batch Mean": 2.929656982421875,
156
+ "accuracy": 0.546875,
157
+ "epoch": 0.0275,
158
+ "step": 11
159
+ },
160
+ {
161
+ "epoch": 0.03,
162
+ "grad_norm": 6.199557304382324,
163
+ "learning_rate": 3e-06,
164
+ "loss": 0.6784,
165
+ "step": 12
166
+ },
167
+ {
168
+ "Batch Mean": 2.938323974609375,
169
+ "accuracy": 0.59375,
170
+ "epoch": 0.03,
171
+ "step": 12
172
+ },
173
+ {
174
+ "epoch": 0.0325,
175
+ "grad_norm": 8.091628074645996,
176
+ "learning_rate": 3.2500000000000002e-06,
177
+ "loss": 0.6887,
178
+ "step": 13
179
+ },
180
+ {
181
+ "Batch Mean": 3.0481414794921875,
182
+ "accuracy": 0.6171875,
183
+ "epoch": 0.0325,
184
+ "step": 13
185
+ },
186
+ {
187
+ "epoch": 0.035,
188
+ "grad_norm": 8.876925468444824,
189
+ "learning_rate": 3.5e-06,
190
+ "loss": 0.6421,
191
+ "step": 14
192
+ },
193
+ {
194
+ "Batch Mean": 3.2818450927734375,
195
+ "accuracy": 0.703125,
196
+ "epoch": 0.035,
197
+ "step": 14
198
+ },
199
+ {
200
+ "epoch": 0.0375,
201
+ "grad_norm": 10.33357048034668,
202
+ "learning_rate": 3.7500000000000005e-06,
203
+ "loss": 0.5853,
204
+ "step": 15
205
+ },
206
+ {
207
+ "Batch Mean": 3.2837677001953125,
208
+ "accuracy": 0.625,
209
+ "epoch": 0.0375,
210
+ "step": 15
211
+ },
212
+ {
213
+ "epoch": 0.04,
214
+ "grad_norm": 11.141650199890137,
215
+ "learning_rate": 4.000000000000001e-06,
216
+ "loss": 0.6495,
217
+ "step": 16
218
+ },
219
+ {
220
+ "Batch Mean": 3.2836532592773438,
221
+ "accuracy": 0.6015625,
222
+ "epoch": 0.04,
223
+ "step": 16
224
+ },
225
+ {
226
+ "epoch": 0.0425,
227
+ "grad_norm": 8.093420028686523,
228
+ "learning_rate": 4.25e-06,
229
+ "loss": 0.6607,
230
+ "step": 17
231
+ },
232
+ {
233
+ "Batch Mean": 3.3738174438476562,
234
+ "accuracy": 0.65625,
235
+ "epoch": 0.0425,
236
+ "step": 17
237
+ },
238
+ {
239
+ "epoch": 0.045,
240
+ "grad_norm": 8.171963691711426,
241
+ "learning_rate": 4.5e-06,
242
+ "loss": 0.5946,
243
+ "step": 18
244
+ },
245
+ {
246
+ "Batch Mean": 3.8035507202148438,
247
+ "accuracy": 0.6015625,
248
+ "epoch": 0.045,
249
+ "step": 18
250
+ },
251
+ {
252
+ "epoch": 0.0475,
253
+ "grad_norm": 10.379010200500488,
254
+ "learning_rate": 4.75e-06,
255
+ "loss": 0.62,
256
+ "step": 19
257
+ },
258
+ {
259
+ "Batch Mean": 4.241037845611572,
260
+ "accuracy": 0.7421875,
261
+ "epoch": 0.0475,
262
+ "step": 19
263
+ },
264
+ {
265
+ "epoch": 0.05,
266
+ "grad_norm": 8.072366714477539,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6094,
269
+ "step": 20
270
+ },
271
+ {
272
+ "Batch Mean": 4.397010803222656,
273
+ "accuracy": 0.65625,
274
+ "epoch": 0.05,
275
+ "step": 20
276
+ },
277
+ {
278
+ "epoch": 0.0525,
279
+ "grad_norm": 7.2537384033203125,
280
+ "learning_rate": 4.986842105263158e-06,
281
+ "loss": 0.5916,
282
+ "step": 21
283
+ },
284
+ {
285
+ "Batch Mean": 4.36688232421875,
286
+ "accuracy": 0.671875,
287
+ "epoch": 0.0525,
288
+ "step": 21
289
+ },
290
+ {
291
+ "epoch": 0.055,
292
+ "grad_norm": 8.559549331665039,
293
+ "learning_rate": 4.973684210526316e-06,
294
+ "loss": 0.5884,
295
+ "step": 22
296
+ },
297
+ {
298
+ "Batch Mean": 4.482940673828125,
299
+ "accuracy": 0.6640625,
300
+ "epoch": 0.055,
301
+ "step": 22
302
+ },
303
+ {
304
+ "epoch": 0.0575,
305
+ "grad_norm": 8.731099128723145,
306
+ "learning_rate": 4.960526315789474e-06,
307
+ "loss": 0.6106,
308
+ "step": 23
309
+ },
310
+ {
311
+ "Batch Mean": 4.41278076171875,
312
+ "accuracy": 0.7109375,
313
+ "epoch": 0.0575,
314
+ "step": 23
315
+ },
316
+ {
317
+ "epoch": 0.06,
318
+ "grad_norm": 6.149895191192627,
319
+ "learning_rate": 4.947368421052632e-06,
320
+ "loss": 0.5569,
321
+ "step": 24
322
+ },
323
+ {
324
+ "Batch Mean": 4.1328277587890625,
325
+ "accuracy": 0.6484375,
326
+ "epoch": 0.06,
327
+ "step": 24
328
+ },
329
+ {
330
+ "epoch": 0.0625,
331
+ "grad_norm": 6.8678879737854,
332
+ "learning_rate": 4.9342105263157895e-06,
333
+ "loss": 0.5729,
334
+ "step": 25
335
+ },
336
+ {
337
+ "Batch Mean": 3.8360061645507812,
338
+ "accuracy": 0.6484375,
339
+ "epoch": 0.0625,
340
+ "step": 25
341
+ },
342
+ {
343
+ "epoch": 0.065,
344
+ "grad_norm": 6.591639041900635,
345
+ "learning_rate": 4.921052631578948e-06,
346
+ "loss": 0.5902,
347
+ "step": 26
348
+ },
349
+ {
350
+ "Batch Mean": 3.9048538208007812,
351
+ "accuracy": 0.6953125,
352
+ "epoch": 0.065,
353
+ "step": 26
354
+ },
355
+ {
356
+ "epoch": 0.0675,
357
+ "grad_norm": 5.855933666229248,
358
+ "learning_rate": 4.907894736842106e-06,
359
+ "loss": 0.5666,
360
+ "step": 27
361
+ },
362
+ {
363
+ "Batch Mean": 3.7672348022460938,
364
+ "accuracy": 0.6953125,
365
+ "epoch": 0.0675,
366
+ "step": 27
367
+ },
368
+ {
369
+ "epoch": 0.07,
370
+ "grad_norm": 5.393594264984131,
371
+ "learning_rate": 4.894736842105264e-06,
372
+ "loss": 0.5508,
373
+ "step": 28
374
+ },
375
+ {
376
+ "Batch Mean": 3.723773956298828,
377
+ "accuracy": 0.65625,
378
+ "epoch": 0.07,
379
+ "step": 28
380
+ },
381
+ {
382
+ "epoch": 0.0725,
383
+ "grad_norm": 5.428353786468506,
384
+ "learning_rate": 4.881578947368422e-06,
385
+ "loss": 0.5694,
386
+ "step": 29
387
+ },
388
+ {
389
+ "Batch Mean": 3.7498779296875,
390
+ "accuracy": 0.6953125,
391
+ "epoch": 0.0725,
392
+ "step": 29
393
+ },
394
+ {
395
+ "epoch": 0.075,
396
+ "grad_norm": 5.005551338195801,
397
+ "learning_rate": 4.8684210526315795e-06,
398
+ "loss": 0.5905,
399
+ "step": 30
400
+ },
401
+ {
402
+ "Batch Mean": 3.564330577850342,
403
+ "accuracy": 0.671875,
404
+ "epoch": 0.075,
405
+ "step": 30
406
+ },
407
+ {
408
+ "epoch": 0.0775,
409
+ "grad_norm": 6.4090681076049805,
410
+ "learning_rate": 4.855263157894737e-06,
411
+ "loss": 0.5901,
412
+ "step": 31
413
+ },
414
+ {
415
+ "Batch Mean": 3.5886306762695312,
416
+ "accuracy": 0.7421875,
417
+ "epoch": 0.0775,
418
+ "step": 31
419
+ },
420
+ {
421
+ "epoch": 0.08,
422
+ "grad_norm": 6.025192737579346,
423
+ "learning_rate": 4.842105263157895e-06,
424
+ "loss": 0.5265,
425
+ "step": 32
426
+ },
427
+ {
428
+ "Batch Mean": 3.64593505859375,
429
+ "accuracy": 0.6953125,
430
+ "epoch": 0.08,
431
+ "step": 32
432
+ },
433
+ {
434
+ "epoch": 0.0825,
435
+ "grad_norm": 6.129398345947266,
436
+ "learning_rate": 4.828947368421053e-06,
437
+ "loss": 0.5083,
438
+ "step": 33
439
+ },
440
+ {
441
+ "Batch Mean": 3.5973358154296875,
442
+ "accuracy": 0.6875,
443
+ "epoch": 0.0825,
444
+ "step": 33
445
+ },
446
+ {
447
+ "epoch": 0.085,
448
+ "grad_norm": 6.91660737991333,
449
+ "learning_rate": 4.815789473684211e-06,
450
+ "loss": 0.5365,
451
+ "step": 34
452
+ },
453
+ {
454
+ "Batch Mean": 3.6286163330078125,
455
+ "accuracy": 0.7109375,
456
+ "epoch": 0.085,
457
+ "step": 34
458
+ },
459
+ {
460
+ "epoch": 0.0875,
461
+ "grad_norm": 7.553361892700195,
462
+ "learning_rate": 4.802631578947369e-06,
463
+ "loss": 0.5196,
464
+ "step": 35
465
+ },
466
+ {
467
+ "Batch Mean": 3.5937328338623047,
468
+ "accuracy": 0.7109375,
469
+ "epoch": 0.0875,
470
+ "step": 35
471
+ },
472
+ {
473
+ "epoch": 0.09,
474
+ "grad_norm": 7.884591579437256,
475
+ "learning_rate": 4.789473684210527e-06,
476
+ "loss": 0.5533,
477
+ "step": 36
478
+ },
479
+ {
480
+ "Batch Mean": 3.28558349609375,
481
+ "accuracy": 0.6796875,
482
+ "epoch": 0.09,
483
+ "step": 36
484
+ },
485
+ {
486
+ "epoch": 0.0925,
487
+ "grad_norm": 8.118135452270508,
488
+ "learning_rate": 4.7763157894736844e-06,
489
+ "loss": 0.5145,
490
+ "step": 37
491
+ },
492
+ {
493
+ "Batch Mean": 3.079477310180664,
494
+ "accuracy": 0.7421875,
495
+ "epoch": 0.0925,
496
+ "step": 37
497
+ },
498
+ {
499
+ "epoch": 0.095,
500
+ "grad_norm": 10.431463241577148,
501
+ "learning_rate": 4.763157894736842e-06,
502
+ "loss": 0.6,
503
+ "step": 38
504
+ },
505
+ {
506
+ "Batch Mean": 2.9296703338623047,
507
+ "accuracy": 0.7578125,
508
+ "epoch": 0.095,
509
+ "step": 38
510
+ },
511
+ {
512
+ "epoch": 0.0975,
513
+ "grad_norm": 8.055816650390625,
514
+ "learning_rate": 4.75e-06,
515
+ "loss": 0.445,
516
+ "step": 39
517
+ },
518
+ {
519
+ "Batch Mean": 2.9282093048095703,
520
+ "accuracy": 0.7109375,
521
+ "epoch": 0.0975,
522
+ "step": 39
523
+ },
524
+ {
525
+ "epoch": 0.1,
526
+ "grad_norm": 9.155073165893555,
527
+ "learning_rate": 4.736842105263158e-06,
528
+ "loss": 0.5568,
529
+ "step": 40
530
+ },
531
+ {
532
+ "Batch Mean": 2.4473862648010254,
533
+ "accuracy": 0.6171875,
534
+ "epoch": 0.1,
535
+ "step": 40
536
+ },
537
+ {
538
+ "epoch": 0.1025,
539
+ "grad_norm": 8.89163589477539,
540
+ "learning_rate": 4.723684210526316e-06,
541
+ "loss": 0.5934,
542
+ "step": 41
543
+ },
544
+ {
545
+ "Batch Mean": 2.4439845085144043,
546
+ "accuracy": 0.6953125,
547
+ "epoch": 0.1025,
548
+ "step": 41
549
+ },
550
+ {
551
+ "epoch": 0.105,
552
+ "grad_norm": 7.411705017089844,
553
+ "learning_rate": 4.710526315789474e-06,
554
+ "loss": 0.5522,
555
+ "step": 42
556
+ },
557
+ {
558
+ "Batch Mean": 1.7335999011993408,
559
+ "accuracy": 0.734375,
560
+ "epoch": 0.105,
561
+ "step": 42
562
+ },
563
+ {
564
+ "epoch": 0.1075,
565
+ "grad_norm": 7.0730109214782715,
566
+ "learning_rate": 4.697368421052632e-06,
567
+ "loss": 0.5157,
568
+ "step": 43
569
+ },
570
+ {
571
+ "Batch Mean": 1.7379779815673828,
572
+ "accuracy": 0.71875,
573
+ "epoch": 0.1075,
574
+ "step": 43
575
+ },
576
+ {
577
+ "epoch": 0.11,
578
+ "grad_norm": 7.879677772521973,
579
+ "learning_rate": 4.68421052631579e-06,
580
+ "loss": 0.5405,
581
+ "step": 44
582
+ },
583
+ {
584
+ "Batch Mean": 1.7085151672363281,
585
+ "accuracy": 0.6796875,
586
+ "epoch": 0.11,
587
+ "step": 44
588
+ },
589
+ {
590
+ "epoch": 0.1125,
591
+ "grad_norm": 6.630401611328125,
592
+ "learning_rate": 4.671052631578948e-06,
593
+ "loss": 0.564,
594
+ "step": 45
595
+ },
596
+ {
597
+ "Batch Mean": 1.7431907653808594,
598
+ "accuracy": 0.734375,
599
+ "epoch": 0.1125,
600
+ "step": 45
601
+ },
602
+ {
603
+ "epoch": 0.115,
604
+ "grad_norm": 6.569342136383057,
605
+ "learning_rate": 4.657894736842106e-06,
606
+ "loss": 0.4969,
607
+ "step": 46
608
+ },
609
+ {
610
+ "Batch Mean": 2.4792041778564453,
611
+ "accuracy": 0.6953125,
612
+ "epoch": 0.115,
613
+ "step": 46
614
+ },
615
+ {
616
+ "epoch": 0.1175,
617
+ "grad_norm": 6.198298931121826,
618
+ "learning_rate": 4.6447368421052635e-06,
619
+ "loss": 0.5501,
620
+ "step": 47
621
+ },
622
+ {
623
+ "Batch Mean": 2.4960689544677734,
624
+ "accuracy": 0.7578125,
625
+ "epoch": 0.1175,
626
+ "step": 47
627
+ },
628
+ {
629
+ "epoch": 0.12,
630
+ "grad_norm": 5.984739780426025,
631
+ "learning_rate": 4.631578947368421e-06,
632
+ "loss": 0.4513,
633
+ "step": 48
634
+ },
635
+ {
636
+ "Batch Mean": 2.7437705993652344,
637
+ "accuracy": 0.71875,
638
+ "epoch": 0.12,
639
+ "step": 48
640
+ },
641
+ {
642
+ "epoch": 0.1225,
643
+ "grad_norm": 6.669623374938965,
644
+ "learning_rate": 4.618421052631579e-06,
645
+ "loss": 0.5404,
646
+ "step": 49
647
+ },
648
+ {
649
+ "Batch Mean": 2.672210693359375,
650
+ "accuracy": 0.75,
651
+ "epoch": 0.1225,
652
+ "step": 49
653
+ },
654
+ {
655
+ "epoch": 0.125,
656
+ "grad_norm": 6.217676639556885,
657
+ "learning_rate": 4.605263157894737e-06,
658
+ "loss": 0.4668,
659
+ "step": 50
660
+ },
661
+ {
662
+ "Batch Mean": 2.7935009002685547,
663
+ "accuracy": 0.75,
664
+ "epoch": 0.125,
665
+ "step": 50
666
+ },
667
+ {
668
+ "epoch": 0.1275,
669
+ "grad_norm": 7.666802883148193,
670
+ "learning_rate": 4.592105263157895e-06,
671
+ "loss": 0.5491,
672
+ "step": 51
673
+ },
674
+ {
675
+ "Batch Mean": 2.651923179626465,
676
+ "accuracy": 0.734375,
677
+ "epoch": 0.1275,
678
+ "step": 51
679
+ },
680
+ {
681
+ "epoch": 0.13,
682
+ "grad_norm": 9.799866676330566,
683
+ "learning_rate": 4.578947368421053e-06,
684
+ "loss": 0.5173,
685
+ "step": 52
686
+ },
687
+ {
688
+ "Batch Mean": 2.9287376403808594,
689
+ "accuracy": 0.734375,
690
+ "epoch": 0.13,
691
+ "step": 52
692
+ },
693
+ {
694
+ "epoch": 0.1325,
695
+ "grad_norm": 8.577540397644043,
696
+ "learning_rate": 4.565789473684211e-06,
697
+ "loss": 0.5279,
698
+ "step": 53
699
+ },
700
+ {
701
+ "Batch Mean": 3.0377674102783203,
702
+ "accuracy": 0.7265625,
703
+ "epoch": 0.1325,
704
+ "step": 53
705
+ },
706
+ {
707
+ "epoch": 0.135,
708
+ "grad_norm": 8.099453926086426,
709
+ "learning_rate": 4.552631578947369e-06,
710
+ "loss": 0.5122,
711
+ "step": 54
712
+ },
713
+ {
714
+ "Batch Mean": 3.3550057411193848,
715
+ "accuracy": 0.6953125,
716
+ "epoch": 0.135,
717
+ "step": 54
718
+ },
719
+ {
720
+ "epoch": 0.1375,
721
+ "grad_norm": 9.597841262817383,
722
+ "learning_rate": 4.539473684210527e-06,
723
+ "loss": 0.5034,
724
+ "step": 55
725
+ },
726
+ {
727
+ "Batch Mean": 3.3833670616149902,
728
+ "accuracy": 0.7578125,
729
+ "epoch": 0.1375,
730
+ "step": 55
731
+ },
732
+ {
733
+ "epoch": 0.14,
734
+ "grad_norm": 9.208806037902832,
735
+ "learning_rate": 4.526315789473685e-06,
736
+ "loss": 0.53,
737
+ "step": 56
738
+ },
739
+ {
740
+ "Batch Mean": 3.255979537963867,
741
+ "accuracy": 0.7890625,
742
+ "epoch": 0.14,
743
+ "step": 56
744
+ },
745
+ {
746
+ "epoch": 0.1425,
747
+ "grad_norm": 7.923739910125732,
748
+ "learning_rate": 4.513157894736843e-06,
749
+ "loss": 0.4315,
750
+ "step": 57
751
+ },
752
+ {
753
+ "Batch Mean": 3.003221273422241,
754
+ "accuracy": 0.7265625,
755
+ "epoch": 0.1425,
756
+ "step": 57
757
+ },
758
+ {
759
+ "epoch": 0.145,
760
+ "grad_norm": 8.64991569519043,
761
+ "learning_rate": 4.5e-06,
762
+ "loss": 0.5038,
763
+ "step": 58
764
+ },
765
+ {
766
+ "Batch Mean": 3.122058868408203,
767
+ "accuracy": 0.78125,
768
+ "epoch": 0.145,
769
+ "step": 58
770
+ },
771
+ {
772
+ "epoch": 0.1475,
773
+ "grad_norm": 8.633460998535156,
774
+ "learning_rate": 4.4868421052631584e-06,
775
+ "loss": 0.4886,
776
+ "step": 59
777
+ },
778
+ {
779
+ "Batch Mean": 2.8752236366271973,
780
+ "accuracy": 0.7109375,
781
+ "epoch": 0.1475,
782
+ "step": 59
783
+ },
784
+ {
785
+ "epoch": 0.15,
786
+ "grad_norm": 8.399279594421387,
787
+ "learning_rate": 4.473684210526316e-06,
788
+ "loss": 0.5239,
789
+ "step": 60
790
+ },
791
+ {
792
+ "Batch Mean": 2.694100856781006,
793
+ "accuracy": 0.7578125,
794
+ "epoch": 0.15,
795
+ "step": 60
796
+ },
797
+ {
798
+ "epoch": 0.1525,
799
+ "grad_norm": 7.846778869628906,
800
+ "learning_rate": 4.460526315789474e-06,
801
+ "loss": 0.4538,
802
+ "step": 61
803
+ },
804
+ {
805
+ "Batch Mean": 2.59914493560791,
806
+ "accuracy": 0.8046875,
807
+ "epoch": 0.1525,
808
+ "step": 61
809
+ },
810
+ {
811
+ "epoch": 0.155,
812
+ "grad_norm": 7.844125270843506,
813
+ "learning_rate": 4.447368421052632e-06,
814
+ "loss": 0.4234,
815
+ "step": 62
816
+ },
817
+ {
818
+ "Batch Mean": 2.431262493133545,
819
+ "accuracy": 0.75,
820
+ "epoch": 0.155,
821
+ "step": 62
822
+ },
823
+ {
824
+ "epoch": 0.1575,
825
+ "grad_norm": 8.15548038482666,
826
+ "learning_rate": 4.43421052631579e-06,
827
+ "loss": 0.4695,
828
+ "step": 63
829
+ },
830
+ {
831
+ "Batch Mean": 2.162135124206543,
832
+ "accuracy": 0.7421875,
833
+ "epoch": 0.1575,
834
+ "step": 63
835
+ },
836
+ {
837
+ "epoch": 0.16,
838
+ "grad_norm": 9.166322708129883,
839
+ "learning_rate": 4.4210526315789476e-06,
840
+ "loss": 0.4898,
841
+ "step": 64
842
+ },
843
+ {
844
+ "Batch Mean": 1.8282737731933594,
845
+ "accuracy": 0.75,
846
+ "epoch": 0.16,
847
+ "step": 64
848
+ },
849
+ {
850
+ "epoch": 0.1625,
851
+ "grad_norm": 9.52655029296875,
852
+ "learning_rate": 4.407894736842105e-06,
853
+ "loss": 0.4651,
854
+ "step": 65
855
+ },
856
+ {
857
+ "Batch Mean": 1.9480819702148438,
858
+ "accuracy": 0.7890625,
859
+ "epoch": 0.1625,
860
+ "step": 65
861
+ },
862
+ {
863
+ "epoch": 0.165,
864
+ "grad_norm": 8.491720199584961,
865
+ "learning_rate": 4.394736842105263e-06,
866
+ "loss": 0.4578,
867
+ "step": 66
868
+ },
869
+ {
870
+ "Batch Mean": 1.8442394733428955,
871
+ "accuracy": 0.7734375,
872
+ "epoch": 0.165,
873
+ "step": 66
874
+ },
875
+ {
876
+ "epoch": 0.1675,
877
+ "grad_norm": 9.01707649230957,
878
+ "learning_rate": 4.381578947368421e-06,
879
+ "loss": 0.4858,
880
+ "step": 67
881
+ },
882
+ {
883
+ "Batch Mean": 1.2759554386138916,
884
+ "accuracy": 0.6953125,
885
+ "epoch": 0.1675,
886
+ "step": 67
887
+ },
888
+ {
889
+ "epoch": 0.17,
890
+ "grad_norm": 10.790990829467773,
891
+ "learning_rate": 4.368421052631579e-06,
892
+ "loss": 0.5368,
893
+ "step": 68
894
+ },
895
+ {
896
+ "Batch Mean": 0.916658878326416,
897
+ "accuracy": 0.7109375,
898
+ "epoch": 0.17,
899
+ "step": 68
900
+ },
901
+ {
902
+ "epoch": 0.1725,
903
+ "grad_norm": 10.27574634552002,
904
+ "learning_rate": 4.3552631578947375e-06,
905
+ "loss": 0.5475,
906
+ "step": 69
907
+ },
908
+ {
909
+ "Batch Mean": 0.9389474391937256,
910
+ "accuracy": 0.6875,
911
+ "epoch": 0.1725,
912
+ "step": 69
913
+ },
914
+ {
915
+ "epoch": 0.175,
916
+ "grad_norm": 9.463624954223633,
917
+ "learning_rate": 4.342105263157895e-06,
918
+ "loss": 0.5295,
919
+ "step": 70
920
+ },
921
+ {
922
+ "Batch Mean": 0.6801865100860596,
923
+ "accuracy": 0.78125,
924
+ "epoch": 0.175,
925
+ "step": 70
926
+ },
927
+ {
928
+ "epoch": 0.1775,
929
+ "grad_norm": 7.813968658447266,
930
+ "learning_rate": 4.328947368421053e-06,
931
+ "loss": 0.4602,
932
+ "step": 71
933
+ },
934
+ {
935
+ "Batch Mean": 0.6634016036987305,
936
+ "accuracy": 0.78125,
937
+ "epoch": 0.1775,
938
+ "step": 71
939
+ },
940
+ {
941
+ "epoch": 0.18,
942
+ "grad_norm": 7.322629928588867,
943
+ "learning_rate": 4.315789473684211e-06,
944
+ "loss": 0.4328,
945
+ "step": 72
946
+ },
947
+ {
948
+ "Batch Mean": 0.518225908279419,
949
+ "accuracy": 0.8359375,
950
+ "epoch": 0.18,
951
+ "step": 72
952
+ },
953
+ {
954
+ "epoch": 0.1825,
955
+ "grad_norm": 7.121971130371094,
956
+ "learning_rate": 4.302631578947369e-06,
957
+ "loss": 0.3997,
958
+ "step": 73
959
+ },
960
+ {
961
+ "Batch Mean": 0.6286078691482544,
962
+ "accuracy": 0.75,
963
+ "epoch": 0.1825,
964
+ "step": 73
965
+ },
966
+ {
967
+ "epoch": 0.185,
968
+ "grad_norm": 8.812067031860352,
969
+ "learning_rate": 4.289473684210527e-06,
970
+ "loss": 0.5345,
971
+ "step": 74
972
+ },
973
+ {
974
+ "Batch Mean": 0.4055500030517578,
975
+ "accuracy": 0.78125,
976
+ "epoch": 0.185,
977
+ "step": 74
978
+ },
979
+ {
980
+ "epoch": 0.1875,
981
+ "grad_norm": 8.031818389892578,
982
+ "learning_rate": 4.276315789473684e-06,
983
+ "loss": 0.4436,
984
+ "step": 75
985
+ },
986
+ {
987
+ "Batch Mean": 0.6844688057899475,
988
+ "accuracy": 0.6640625,
989
+ "epoch": 0.1875,
990
+ "step": 75
991
+ },
992
+ {
993
+ "epoch": 0.19,
994
+ "grad_norm": 9.14492130279541,
995
+ "learning_rate": 4.2631578947368425e-06,
996
+ "loss": 0.5727,
997
+ "step": 76
998
+ },
999
+ {
1000
+ "Batch Mean": 0.549891471862793,
1001
+ "accuracy": 0.7578125,
1002
+ "epoch": 0.19,
1003
+ "step": 76
1004
+ },
1005
+ {
1006
+ "epoch": 0.1925,
1007
+ "grad_norm": 8.721407890319824,
1008
+ "learning_rate": 4.25e-06,
1009
+ "loss": 0.4997,
1010
+ "step": 77
1011
+ },
1012
+ {
1013
+ "Batch Mean": 0.3632768988609314,
1014
+ "accuracy": 0.703125,
1015
+ "epoch": 0.1925,
1016
+ "step": 77
1017
+ },
1018
+ {
1019
+ "epoch": 0.195,
1020
+ "grad_norm": 8.776328086853027,
1021
+ "learning_rate": 4.236842105263158e-06,
1022
+ "loss": 0.5442,
1023
+ "step": 78
1024
+ },
1025
+ {
1026
+ "Batch Mean": 0.4604153633117676,
1027
+ "accuracy": 0.7421875,
1028
+ "epoch": 0.195,
1029
+ "step": 78
1030
+ },
1031
+ {
1032
+ "epoch": 0.1975,
1033
+ "grad_norm": 7.281062126159668,
1034
+ "learning_rate": 4.223684210526316e-06,
1035
+ "loss": 0.4793,
1036
+ "step": 79
1037
+ },
1038
+ {
1039
+ "Batch Mean": 0.605268120765686,
1040
+ "accuracy": 0.765625,
1041
+ "epoch": 0.1975,
1042
+ "step": 79
1043
+ },
1044
+ {
1045
+ "epoch": 0.2,
1046
+ "grad_norm": 7.533178329467773,
1047
+ "learning_rate": 4.210526315789474e-06,
1048
+ "loss": 0.4338,
1049
+ "step": 80
1050
+ },
1051
+ {
1052
+ "Batch Mean": 0.9789919257164001,
1053
+ "accuracy": 0.75,
1054
+ "epoch": 0.2,
1055
+ "step": 80
1056
+ },
1057
+ {
1058
+ "epoch": 0.2025,
1059
+ "grad_norm": 7.2433671951293945,
1060
+ "learning_rate": 4.197368421052632e-06,
1061
+ "loss": 0.4785,
1062
+ "step": 81
1063
+ },
1064
+ {
1065
+ "Batch Mean": 1.114579200744629,
1066
+ "accuracy": 0.71875,
1067
+ "epoch": 0.2025,
1068
+ "step": 81
1069
+ },
1070
+ {
1071
+ "epoch": 0.205,
1072
+ "grad_norm": 7.2934064865112305,
1073
+ "learning_rate": 4.18421052631579e-06,
1074
+ "loss": 0.4836,
1075
+ "step": 82
1076
+ },
1077
+ {
1078
+ "Batch Mean": 1.0528812408447266,
1079
+ "accuracy": 0.7578125,
1080
+ "epoch": 0.205,
1081
+ "step": 82
1082
+ },
1083
+ {
1084
+ "epoch": 0.2075,
1085
+ "grad_norm": 7.544822692871094,
1086
+ "learning_rate": 4.171052631578948e-06,
1087
+ "loss": 0.5077,
1088
+ "step": 83
1089
+ },
1090
+ {
1091
+ "Batch Mean": 1.1365894079208374,
1092
+ "accuracy": 0.671875,
1093
+ "epoch": 0.2075,
1094
+ "step": 83
1095
+ },
1096
+ {
1097
+ "epoch": 0.21,
1098
+ "grad_norm": 8.340349197387695,
1099
+ "learning_rate": 4.157894736842106e-06,
1100
+ "loss": 0.579,
1101
+ "step": 84
1102
+ },
1103
+ {
1104
+ "Batch Mean": 1.7320103645324707,
1105
+ "accuracy": 0.8125,
1106
+ "epoch": 0.21,
1107
+ "step": 84
1108
+ },
1109
+ {
1110
+ "epoch": 0.2125,
1111
+ "grad_norm": 6.645724296569824,
1112
+ "learning_rate": 4.144736842105263e-06,
1113
+ "loss": 0.4114,
1114
+ "step": 85
1115
+ },
1116
+ {
1117
+ "Batch Mean": 1.443530559539795,
1118
+ "accuracy": 0.7578125,
1119
+ "epoch": 0.2125,
1120
+ "step": 85
1121
+ },
1122
+ {
1123
+ "epoch": 0.215,
1124
+ "grad_norm": 6.647582530975342,
1125
+ "learning_rate": 4.1315789473684216e-06,
1126
+ "loss": 0.4369,
1127
+ "step": 86
1128
+ },
1129
+ {
1130
+ "Batch Mean": 1.5358202457427979,
1131
+ "accuracy": 0.7578125,
1132
+ "epoch": 0.215,
1133
+ "step": 86
1134
+ },
1135
+ {
1136
+ "epoch": 0.2175,
1137
+ "grad_norm": 7.315903186798096,
1138
+ "learning_rate": 4.118421052631579e-06,
1139
+ "loss": 0.4895,
1140
+ "step": 87
1141
+ },
1142
+ {
1143
+ "Batch Mean": 1.7256877422332764,
1144
+ "accuracy": 0.7734375,
1145
+ "epoch": 0.2175,
1146
+ "step": 87
1147
+ },
1148
+ {
1149
+ "epoch": 0.22,
1150
+ "grad_norm": 8.285420417785645,
1151
+ "learning_rate": 4.105263157894737e-06,
1152
+ "loss": 0.5035,
1153
+ "step": 88
1154
+ },
1155
+ {
1156
+ "Batch Mean": 1.5997413396835327,
1157
+ "accuracy": 0.75,
1158
+ "epoch": 0.22,
1159
+ "step": 88
1160
+ },
1161
+ {
1162
+ "epoch": 0.2225,
1163
+ "grad_norm": 7.990715026855469,
1164
+ "learning_rate": 4.092105263157895e-06,
1165
+ "loss": 0.51,
1166
+ "step": 89
1167
+ },
1168
+ {
1169
+ "Batch Mean": 1.6425485610961914,
1170
+ "accuracy": 0.734375,
1171
+ "epoch": 0.2225,
1172
+ "step": 89
1173
+ },
1174
+ {
1175
+ "epoch": 0.225,
1176
+ "grad_norm": 8.72641658782959,
1177
+ "learning_rate": 4.078947368421053e-06,
1178
+ "loss": 0.4908,
1179
+ "step": 90
1180
+ },
1181
+ {
1182
+ "Batch Mean": 1.9212679862976074,
1183
+ "accuracy": 0.84375,
1184
+ "epoch": 0.225,
1185
+ "step": 90
1186
+ },
1187
+ {
1188
+ "epoch": 0.2275,
1189
+ "grad_norm": 7.567220211029053,
1190
+ "learning_rate": 4.065789473684211e-06,
1191
+ "loss": 0.4152,
1192
+ "step": 91
1193
+ },
1194
+ {
1195
+ "Batch Mean": 1.6822540760040283,
1196
+ "accuracy": 0.8046875,
1197
+ "epoch": 0.2275,
1198
+ "step": 91
1199
+ },
1200
+ {
1201
+ "epoch": 0.23,
1202
+ "grad_norm": 7.402642726898193,
1203
+ "learning_rate": 4.052631578947368e-06,
1204
+ "loss": 0.4054,
1205
+ "step": 92
1206
+ },
1207
+ {
1208
+ "Batch Mean": 1.5377750396728516,
1209
+ "accuracy": 0.75,
1210
+ "epoch": 0.23,
1211
+ "step": 92
1212
+ },
1213
+ {
1214
+ "epoch": 0.2325,
1215
+ "grad_norm": 8.574016571044922,
1216
+ "learning_rate": 4.0394736842105265e-06,
1217
+ "loss": 0.4739,
1218
+ "step": 93
1219
+ },
1220
+ {
1221
+ "Batch Mean": 1.332385540008545,
1222
+ "accuracy": 0.734375,
1223
+ "epoch": 0.2325,
1224
+ "step": 93
1225
+ },
1226
+ {
1227
+ "epoch": 0.235,
1228
+ "grad_norm": 8.827500343322754,
1229
+ "learning_rate": 4.026315789473684e-06,
1230
+ "loss": 0.4983,
1231
+ "step": 94
1232
+ },
1233
+ {
1234
+ "Batch Mean": 1.0707147121429443,
1235
+ "accuracy": 0.8046875,
1236
+ "epoch": 0.235,
1237
+ "step": 94
1238
+ },
1239
+ {
1240
+ "epoch": 0.2375,
1241
+ "grad_norm": 7.975078105926514,
1242
+ "learning_rate": 4.013157894736842e-06,
1243
+ "loss": 0.4709,
1244
+ "step": 95
1245
+ },
1246
+ {
1247
+ "Batch Mean": 1.1354491710662842,
1248
+ "accuracy": 0.75,
1249
+ "epoch": 0.2375,
1250
+ "step": 95
1251
+ },
1252
+ {
1253
+ "epoch": 0.24,
1254
+ "grad_norm": 7.764720916748047,
1255
+ "learning_rate": 4.000000000000001e-06,
1256
+ "loss": 0.4697,
1257
+ "step": 96
1258
+ },
1259
+ {
1260
+ "Batch Mean": 0.7834959030151367,
1261
+ "accuracy": 0.765625,
1262
+ "epoch": 0.24,
1263
+ "step": 96
1264
+ },
1265
+ {
1266
+ "epoch": 0.2425,
1267
+ "grad_norm": 8.38682746887207,
1268
+ "learning_rate": 3.986842105263158e-06,
1269
+ "loss": 0.46,
1270
+ "step": 97
1271
+ },
1272
+ {
1273
+ "Batch Mean": 0.9441508650779724,
1274
+ "accuracy": 0.8359375,
1275
+ "epoch": 0.2425,
1276
+ "step": 97
1277
+ },
1278
+ {
1279
+ "epoch": 0.245,
1280
+ "grad_norm": 8.565149307250977,
1281
+ "learning_rate": 3.9736842105263165e-06,
1282
+ "loss": 0.4071,
1283
+ "step": 98
1284
+ },
1285
+ {
1286
+ "Batch Mean": 0.8886473178863525,
1287
+ "accuracy": 0.8203125,
1288
+ "epoch": 0.245,
1289
+ "step": 98
1290
+ },
1291
+ {
1292
+ "epoch": 0.2475,
1293
+ "grad_norm": 7.316027641296387,
1294
+ "learning_rate": 3.960526315789474e-06,
1295
+ "loss": 0.413,
1296
+ "step": 99
1297
+ },
1298
+ {
1299
+ "Batch Mean": 1.3381073474884033,
1300
+ "accuracy": 0.765625,
1301
+ "epoch": 0.2475,
1302
+ "step": 99
1303
+ },
1304
+ {
1305
+ "epoch": 0.25,
1306
+ "grad_norm": 7.380762577056885,
1307
+ "learning_rate": 3.947368421052632e-06,
1308
+ "loss": 0.4639,
1309
+ "step": 100
1310
+ },
1311
+ {
1312
+ "Batch Mean": 1.8181347846984863,
1313
+ "accuracy": 0.78125,
1314
+ "epoch": 0.25,
1315
+ "step": 100
1316
+ },
1317
+ {
1318
+ "epoch": 0.2525,
1319
+ "grad_norm": 8.348108291625977,
1320
+ "learning_rate": 3.93421052631579e-06,
1321
+ "loss": 0.4568,
1322
+ "step": 101
1323
+ },
1324
+ {
1325
+ "Batch Mean": 1.850348711013794,
1326
+ "accuracy": 0.828125,
1327
+ "epoch": 0.2525,
1328
+ "step": 101
1329
+ },
1330
+ {
1331
+ "epoch": 0.255,
1332
+ "grad_norm": 7.533435821533203,
1333
+ "learning_rate": 3.921052631578947e-06,
1334
+ "loss": 0.4471,
1335
+ "step": 102
1336
+ },
1337
+ {
1338
+ "Batch Mean": 1.8302688598632812,
1339
+ "accuracy": 0.7265625,
1340
+ "epoch": 0.255,
1341
+ "step": 102
1342
+ },
1343
+ {
1344
+ "epoch": 0.2575,
1345
+ "grad_norm": 7.560754776000977,
1346
+ "learning_rate": 3.907894736842106e-06,
1347
+ "loss": 0.4922,
1348
+ "step": 103
1349
+ },
1350
+ {
1351
+ "Batch Mean": 1.832013487815857,
1352
+ "accuracy": 0.7734375,
1353
+ "epoch": 0.2575,
1354
+ "step": 103
1355
+ },
1356
+ {
1357
+ "epoch": 0.26,
1358
+ "grad_norm": 8.4998197555542,
1359
+ "learning_rate": 3.894736842105263e-06,
1360
+ "loss": 0.4636,
1361
+ "step": 104
1362
+ },
1363
+ {
1364
+ "Batch Mean": 1.9380416870117188,
1365
+ "accuracy": 0.7421875,
1366
+ "epoch": 0.26,
1367
+ "step": 104
1368
+ },
1369
+ {
1370
+ "epoch": 0.2625,
1371
+ "grad_norm": 8.759364128112793,
1372
+ "learning_rate": 3.8815789473684214e-06,
1373
+ "loss": 0.5117,
1374
+ "step": 105
1375
+ },
1376
+ {
1377
+ "Batch Mean": 2.0537302494049072,
1378
+ "accuracy": 0.78125,
1379
+ "epoch": 0.2625,
1380
+ "step": 105
1381
+ },
1382
+ {
1383
+ "epoch": 0.265,
1384
+ "grad_norm": 7.300965785980225,
1385
+ "learning_rate": 3.868421052631579e-06,
1386
+ "loss": 0.3956,
1387
+ "step": 106
1388
+ },
1389
+ {
1390
+ "Batch Mean": 2.236231803894043,
1391
+ "accuracy": 0.7890625,
1392
+ "epoch": 0.265,
1393
+ "step": 106
1394
+ },
1395
+ {
1396
+ "epoch": 0.2675,
1397
+ "grad_norm": 7.826519012451172,
1398
+ "learning_rate": 3.855263157894737e-06,
1399
+ "loss": 0.462,
1400
+ "step": 107
1401
+ },
1402
+ {
1403
+ "Batch Mean": 2.2571160793304443,
1404
+ "accuracy": 0.78125,
1405
+ "epoch": 0.2675,
1406
+ "step": 107
1407
+ },
1408
+ {
1409
+ "epoch": 0.27,
1410
+ "grad_norm": 7.177440643310547,
1411
+ "learning_rate": 3.842105263157895e-06,
1412
+ "loss": 0.4264,
1413
+ "step": 108
1414
+ },
1415
+ {
1416
+ "Batch Mean": 2.3395166397094727,
1417
+ "accuracy": 0.8359375,
1418
+ "epoch": 0.27,
1419
+ "step": 108
1420
+ },
1421
+ {
1422
+ "epoch": 0.2725,
1423
+ "grad_norm": 7.556861877441406,
1424
+ "learning_rate": 3.828947368421053e-06,
1425
+ "loss": 0.3825,
1426
+ "step": 109
1427
+ },
1428
+ {
1429
+ "Batch Mean": 2.5364012718200684,
1430
+ "accuracy": 0.7890625,
1431
+ "epoch": 0.2725,
1432
+ "step": 109
1433
+ },
1434
+ {
1435
+ "epoch": 0.275,
1436
+ "grad_norm": 8.785236358642578,
1437
+ "learning_rate": 3.815789473684211e-06,
1438
+ "loss": 0.4915,
1439
+ "step": 110
1440
+ },
1441
+ {
1442
+ "Batch Mean": 2.545170783996582,
1443
+ "accuracy": 0.71875,
1444
+ "epoch": 0.275,
1445
+ "step": 110
1446
+ },
1447
+ {
1448
+ "epoch": 0.2775,
1449
+ "grad_norm": 8.062837600708008,
1450
+ "learning_rate": 3.802631578947369e-06,
1451
+ "loss": 0.5025,
1452
+ "step": 111
1453
+ },
1454
+ {
1455
+ "Batch Mean": 2.6232008934020996,
1456
+ "accuracy": 0.7734375,
1457
+ "epoch": 0.2775,
1458
+ "step": 111
1459
+ },
1460
+ {
1461
+ "epoch": 0.28,
1462
+ "grad_norm": 7.3966498374938965,
1463
+ "learning_rate": 3.789473684210527e-06,
1464
+ "loss": 0.4145,
1465
+ "step": 112
1466
+ },
1467
+ {
1468
+ "Batch Mean": 2.351048469543457,
1469
+ "accuracy": 0.6953125,
1470
+ "epoch": 0.28,
1471
+ "step": 112
1472
+ },
1473
+ {
1474
+ "epoch": 0.2825,
1475
+ "grad_norm": 7.810081958770752,
1476
+ "learning_rate": 3.7763157894736847e-06,
1477
+ "loss": 0.5147,
1478
+ "step": 113
1479
+ },
1480
+ {
1481
+ "Batch Mean": 1.6083295345306396,
1482
+ "accuracy": 0.796875,
1483
+ "epoch": 0.2825,
1484
+ "step": 113
1485
+ },
1486
+ {
1487
+ "epoch": 0.285,
1488
+ "grad_norm": 6.8766703605651855,
1489
+ "learning_rate": 3.7631578947368426e-06,
1490
+ "loss": 0.4275,
1491
+ "step": 114
1492
+ },
1493
+ {
1494
+ "Batch Mean": 1.594513177871704,
1495
+ "accuracy": 0.8046875,
1496
+ "epoch": 0.285,
1497
+ "step": 114
1498
+ },
1499
+ {
1500
+ "epoch": 0.2875,
1501
+ "grad_norm": 7.07267427444458,
1502
+ "learning_rate": 3.7500000000000005e-06,
1503
+ "loss": 0.4197,
1504
+ "step": 115
1505
+ },
1506
+ {
1507
+ "Batch Mean": 1.6583623886108398,
1508
+ "accuracy": 0.7421875,
1509
+ "epoch": 0.2875,
1510
+ "step": 115
1511
+ },
1512
+ {
1513
+ "epoch": 0.29,
1514
+ "grad_norm": 8.415107727050781,
1515
+ "learning_rate": 3.736842105263158e-06,
1516
+ "loss": 0.4723,
1517
+ "step": 116
1518
+ },
1519
+ {
1520
+ "Batch Mean": 1.6947704553604126,
1521
+ "accuracy": 0.8203125,
1522
+ "epoch": 0.29,
1523
+ "step": 116
1524
+ },
1525
+ {
1526
+ "epoch": 0.2925,
1527
+ "grad_norm": 7.132028102874756,
1528
+ "learning_rate": 3.723684210526316e-06,
1529
+ "loss": 0.4039,
1530
+ "step": 117
1531
+ },
1532
+ {
1533
+ "Batch Mean": 1.7144229412078857,
1534
+ "accuracy": 0.8046875,
1535
+ "epoch": 0.2925,
1536
+ "step": 117
1537
+ },
1538
+ {
1539
+ "epoch": 0.295,
1540
+ "grad_norm": 6.850518703460693,
1541
+ "learning_rate": 3.710526315789474e-06,
1542
+ "loss": 0.4148,
1543
+ "step": 118
1544
+ },
1545
+ {
1546
+ "Batch Mean": 1.4002912044525146,
1547
+ "accuracy": 0.828125,
1548
+ "epoch": 0.295,
1549
+ "step": 118
1550
+ },
1551
+ {
1552
+ "epoch": 0.2975,
1553
+ "grad_norm": 7.008551120758057,
1554
+ "learning_rate": 3.6973684210526317e-06,
1555
+ "loss": 0.3972,
1556
+ "step": 119
1557
+ },
1558
+ {
1559
+ "Batch Mean": 1.1955918073654175,
1560
+ "accuracy": 0.7890625,
1561
+ "epoch": 0.2975,
1562
+ "step": 119
1563
+ },
1564
+ {
1565
+ "epoch": 0.3,
1566
+ "grad_norm": 8.176568984985352,
1567
+ "learning_rate": 3.6842105263157896e-06,
1568
+ "loss": 0.4894,
1569
+ "step": 120
1570
+ },
1571
+ {
1572
+ "Batch Mean": 1.4260971546173096,
1573
+ "accuracy": 0.765625,
1574
+ "epoch": 0.3,
1575
+ "step": 120
1576
+ },
1577
+ {
1578
+ "epoch": 0.3025,
1579
+ "grad_norm": 7.905389308929443,
1580
+ "learning_rate": 3.6710526315789476e-06,
1581
+ "loss": 0.4796,
1582
+ "step": 121
1583
+ },
1584
+ {
1585
+ "Batch Mean": 1.1381725072860718,
1586
+ "accuracy": 0.84375,
1587
+ "epoch": 0.3025,
1588
+ "step": 121
1589
+ },
1590
+ {
1591
+ "epoch": 0.305,
1592
+ "grad_norm": 7.464083194732666,
1593
+ "learning_rate": 3.657894736842106e-06,
1594
+ "loss": 0.387,
1595
+ "step": 122
1596
+ },
1597
+ {
1598
+ "Batch Mean": 1.064018726348877,
1599
+ "accuracy": 0.8125,
1600
+ "epoch": 0.305,
1601
+ "step": 122
1602
+ },
1603
+ {
1604
+ "epoch": 0.3075,
1605
+ "grad_norm": 8.280699729919434,
1606
+ "learning_rate": 3.644736842105264e-06,
1607
+ "loss": 0.4154,
1608
+ "step": 123
1609
+ },
1610
+ {
1611
+ "Batch Mean": 1.3708758354187012,
1612
+ "accuracy": 0.765625,
1613
+ "epoch": 0.3075,
1614
+ "step": 123
1615
+ },
1616
+ {
1617
+ "epoch": 0.31,
1618
+ "grad_norm": 9.830754280090332,
1619
+ "learning_rate": 3.6315789473684217e-06,
1620
+ "loss": 0.5003,
1621
+ "step": 124
1622
+ },
1623
+ {
1624
+ "Batch Mean": 1.162580132484436,
1625
+ "accuracy": 0.828125,
1626
+ "epoch": 0.31,
1627
+ "step": 124
1628
+ },
1629
+ {
1630
+ "epoch": 0.3125,
1631
+ "grad_norm": 8.671696662902832,
1632
+ "learning_rate": 3.618421052631579e-06,
1633
+ "loss": 0.4389,
1634
+ "step": 125
1635
+ },
1636
+ {
1637
+ "Batch Mean": 0.671147346496582,
1638
+ "accuracy": 0.8125,
1639
+ "epoch": 0.3125,
1640
+ "step": 125
1641
+ },
1642
+ {
1643
+ "epoch": 0.315,
1644
+ "grad_norm": 8.493339538574219,
1645
+ "learning_rate": 3.605263157894737e-06,
1646
+ "loss": 0.4434,
1647
+ "step": 126
1648
+ },
1649
+ {
1650
+ "Batch Mean": 0.8207384347915649,
1651
+ "accuracy": 0.8203125,
1652
+ "epoch": 0.315,
1653
+ "step": 126
1654
+ },
1655
+ {
1656
+ "epoch": 0.3175,
1657
+ "grad_norm": 8.274676322937012,
1658
+ "learning_rate": 3.592105263157895e-06,
1659
+ "loss": 0.4057,
1660
+ "step": 127
1661
+ },
1662
+ {
1663
+ "Batch Mean": 0.5156043767929077,
1664
+ "accuracy": 0.75,
1665
+ "epoch": 0.3175,
1666
+ "step": 127
1667
+ },
1668
+ {
1669
+ "epoch": 0.32,
1670
+ "grad_norm": 9.094855308532715,
1671
+ "learning_rate": 3.578947368421053e-06,
1672
+ "loss": 0.4661,
1673
+ "step": 128
1674
+ },
1675
+ {
1676
+ "Batch Mean": 0.43193674087524414,
1677
+ "accuracy": 0.8203125,
1678
+ "epoch": 0.32,
1679
+ "step": 128
1680
+ },
1681
+ {
1682
+ "epoch": 0.3225,
1683
+ "grad_norm": 8.729266166687012,
1684
+ "learning_rate": 3.565789473684211e-06,
1685
+ "loss": 0.4586,
1686
+ "step": 129
1687
+ },
1688
+ {
1689
+ "Batch Mean": 0.30504658818244934,
1690
+ "accuracy": 0.7421875,
1691
+ "epoch": 0.3225,
1692
+ "step": 129
1693
+ },
1694
+ {
1695
+ "epoch": 0.325,
1696
+ "grad_norm": 11.113021850585938,
1697
+ "learning_rate": 3.5526315789473687e-06,
1698
+ "loss": 0.4894,
1699
+ "step": 130
1700
+ },
1701
+ {
1702
+ "Batch Mean": 0.3271394371986389,
1703
+ "accuracy": 0.7734375,
1704
+ "epoch": 0.325,
1705
+ "step": 130
1706
+ },
1707
+ {
1708
+ "epoch": 0.3275,
1709
+ "grad_norm": 8.692556381225586,
1710
+ "learning_rate": 3.5394736842105266e-06,
1711
+ "loss": 0.4227,
1712
+ "step": 131
1713
+ },
1714
+ {
1715
+ "Batch Mean": 0.6269352436065674,
1716
+ "accuracy": 0.7734375,
1717
+ "epoch": 0.3275,
1718
+ "step": 131
1719
+ },
1720
+ {
1721
+ "epoch": 0.33,
1722
+ "grad_norm": 8.046867370605469,
1723
+ "learning_rate": 3.5263157894736846e-06,
1724
+ "loss": 0.496,
1725
+ "step": 132
1726
+ },
1727
+ {
1728
+ "Batch Mean": 0.6559182405471802,
1729
+ "accuracy": 0.765625,
1730
+ "epoch": 0.33,
1731
+ "step": 132
1732
+ },
1733
+ {
1734
+ "epoch": 0.3325,
1735
+ "grad_norm": 7.385076999664307,
1736
+ "learning_rate": 3.513157894736842e-06,
1737
+ "loss": 0.4459,
1738
+ "step": 133
1739
+ },
1740
+ {
1741
+ "Batch Mean": 0.5328922271728516,
1742
+ "accuracy": 0.7578125,
1743
+ "epoch": 0.3325,
1744
+ "step": 133
1745
+ },
1746
+ {
1747
+ "epoch": 0.335,
1748
+ "grad_norm": 7.108922481536865,
1749
+ "learning_rate": 3.5e-06,
1750
+ "loss": 0.428,
1751
+ "step": 134
1752
+ },
1753
+ {
1754
+ "Batch Mean": 1.1600193977355957,
1755
+ "accuracy": 0.828125,
1756
+ "epoch": 0.335,
1757
+ "step": 134
1758
+ },
1759
+ {
1760
+ "epoch": 0.3375,
1761
+ "grad_norm": 6.962152004241943,
1762
+ "learning_rate": 3.486842105263158e-06,
1763
+ "loss": 0.4237,
1764
+ "step": 135
1765
+ },
1766
+ {
1767
+ "Batch Mean": 1.1642009019851685,
1768
+ "accuracy": 0.6953125,
1769
+ "epoch": 0.3375,
1770
+ "step": 135
1771
+ },
1772
+ {
1773
+ "epoch": 0.34,
1774
+ "grad_norm": 7.879281520843506,
1775
+ "learning_rate": 3.473684210526316e-06,
1776
+ "loss": 0.528,
1777
+ "step": 136
1778
+ },
1779
+ {
1780
+ "Batch Mean": 1.0588830709457397,
1781
+ "accuracy": 0.6953125,
1782
+ "epoch": 0.34,
1783
+ "step": 136
1784
+ },
1785
+ {
1786
+ "epoch": 0.3425,
1787
+ "grad_norm": 9.492472648620605,
1788
+ "learning_rate": 3.460526315789474e-06,
1789
+ "loss": 0.5365,
1790
+ "step": 137
1791
+ },
1792
+ {
1793
+ "Batch Mean": 1.3413481712341309,
1794
+ "accuracy": 0.8046875,
1795
+ "epoch": 0.3425,
1796
+ "step": 137
1797
+ },
1798
+ {
1799
+ "epoch": 0.345,
1800
+ "grad_norm": 6.448349952697754,
1801
+ "learning_rate": 3.447368421052632e-06,
1802
+ "loss": 0.4449,
1803
+ "step": 138
1804
+ },
1805
+ {
1806
+ "Batch Mean": 1.3028790950775146,
1807
+ "accuracy": 0.7578125,
1808
+ "epoch": 0.345,
1809
+ "step": 138
1810
+ },
1811
+ {
1812
+ "epoch": 0.3475,
1813
+ "grad_norm": 6.54162073135376,
1814
+ "learning_rate": 3.43421052631579e-06,
1815
+ "loss": 0.4109,
1816
+ "step": 139
1817
+ },
1818
+ {
1819
+ "Batch Mean": 1.206446886062622,
1820
+ "accuracy": 0.7734375,
1821
+ "epoch": 0.3475,
1822
+ "step": 139
1823
+ },
1824
+ {
1825
+ "epoch": 0.35,
1826
+ "grad_norm": 7.594364166259766,
1827
+ "learning_rate": 3.421052631578948e-06,
1828
+ "loss": 0.4771,
1829
+ "step": 140
1830
+ },
1831
+ {
1832
+ "Batch Mean": 1.425430417060852,
1833
+ "accuracy": 0.7734375,
1834
+ "epoch": 0.35,
1835
+ "step": 140
1836
+ },
1837
+ {
1838
+ "epoch": 0.3525,
1839
+ "grad_norm": 6.744152069091797,
1840
+ "learning_rate": 3.4078947368421057e-06,
1841
+ "loss": 0.4458,
1842
+ "step": 141
1843
+ },
1844
+ {
1845
+ "Batch Mean": 1.4311294555664062,
1846
+ "accuracy": 0.765625,
1847
+ "epoch": 0.3525,
1848
+ "step": 141
1849
+ },
1850
+ {
1851
+ "epoch": 0.355,
1852
+ "grad_norm": 6.789750576019287,
1853
+ "learning_rate": 3.3947368421052636e-06,
1854
+ "loss": 0.4798,
1855
+ "step": 142
1856
+ },
1857
+ {
1858
+ "Batch Mean": 1.6251521110534668,
1859
+ "accuracy": 0.765625,
1860
+ "epoch": 0.355,
1861
+ "step": 142
1862
+ },
1863
+ {
1864
+ "epoch": 0.3575,
1865
+ "grad_norm": 7.658289909362793,
1866
+ "learning_rate": 3.381578947368421e-06,
1867
+ "loss": 0.5209,
1868
+ "step": 143
1869
+ },
1870
+ {
1871
+ "Batch Mean": 1.5901494026184082,
1872
+ "accuracy": 0.7890625,
1873
+ "epoch": 0.3575,
1874
+ "step": 143
1875
+ },
1876
+ {
1877
+ "epoch": 0.36,
1878
+ "grad_norm": 7.741049289703369,
1879
+ "learning_rate": 3.368421052631579e-06,
1880
+ "loss": 0.448,
1881
+ "step": 144
1882
+ },
1883
+ {
1884
+ "Batch Mean": 1.7485175132751465,
1885
+ "accuracy": 0.71875,
1886
+ "epoch": 0.36,
1887
+ "step": 144
1888
+ },
1889
+ {
1890
+ "epoch": 0.3625,
1891
+ "grad_norm": 7.933503150939941,
1892
+ "learning_rate": 3.355263157894737e-06,
1893
+ "loss": 0.4745,
1894
+ "step": 145
1895
+ },
1896
+ {
1897
+ "Batch Mean": 1.8909566402435303,
1898
+ "accuracy": 0.796875,
1899
+ "epoch": 0.3625,
1900
+ "step": 145
1901
+ },
1902
+ {
1903
+ "epoch": 0.365,
1904
+ "grad_norm": 7.310222148895264,
1905
+ "learning_rate": 3.342105263157895e-06,
1906
+ "loss": 0.4671,
1907
+ "step": 146
1908
+ },
1909
+ {
1910
+ "Batch Mean": 2.035611152648926,
1911
+ "accuracy": 0.75,
1912
+ "epoch": 0.365,
1913
+ "step": 146
1914
+ },
1915
+ {
1916
+ "epoch": 0.3675,
1917
+ "grad_norm": 7.8623809814453125,
1918
+ "learning_rate": 3.3289473684210528e-06,
1919
+ "loss": 0.5079,
1920
+ "step": 147
1921
+ },
1922
+ {
1923
+ "Batch Mean": 2.0848422050476074,
1924
+ "accuracy": 0.8203125,
1925
+ "epoch": 0.3675,
1926
+ "step": 147
1927
+ },
1928
+ {
1929
+ "epoch": 0.37,
1930
+ "grad_norm": 7.38020133972168,
1931
+ "learning_rate": 3.3157894736842107e-06,
1932
+ "loss": 0.5131,
1933
+ "step": 148
1934
+ },
1935
+ {
1936
+ "Batch Mean": 1.9938535690307617,
1937
+ "accuracy": 0.7734375,
1938
+ "epoch": 0.37,
1939
+ "step": 148
1940
+ },
1941
+ {
1942
+ "epoch": 0.3725,
1943
+ "grad_norm": 7.401918411254883,
1944
+ "learning_rate": 3.302631578947369e-06,
1945
+ "loss": 0.4059,
1946
+ "step": 149
1947
+ },
1948
+ {
1949
+ "Batch Mean": 1.9994306564331055,
1950
+ "accuracy": 0.8515625,
1951
+ "epoch": 0.3725,
1952
+ "step": 149
1953
+ },
1954
+ {
1955
+ "epoch": 0.375,
1956
+ "grad_norm": 7.515151500701904,
1957
+ "learning_rate": 3.289473684210527e-06,
1958
+ "loss": 0.4198,
1959
+ "step": 150
1960
+ },
1961
+ {
1962
+ "Batch Mean": 1.9627342224121094,
1963
+ "accuracy": 0.78125,
1964
+ "epoch": 0.375,
1965
+ "step": 150
1966
+ },
1967
+ {
1968
+ "epoch": 0.3775,
1969
+ "grad_norm": 9.086411476135254,
1970
+ "learning_rate": 3.276315789473685e-06,
1971
+ "loss": 0.407,
1972
+ "step": 151
1973
+ },
1974
+ {
1975
+ "Batch Mean": 2.247910499572754,
1976
+ "accuracy": 0.75,
1977
+ "epoch": 0.3775,
1978
+ "step": 151
1979
+ },
1980
+ {
1981
+ "epoch": 0.38,
1982
+ "grad_norm": 8.9763765335083,
1983
+ "learning_rate": 3.2631578947368423e-06,
1984
+ "loss": 0.5274,
1985
+ "step": 152
1986
+ },
1987
+ {
1988
+ "Batch Mean": 2.261256694793701,
1989
+ "accuracy": 0.8125,
1990
+ "epoch": 0.38,
1991
+ "step": 152
1992
+ },
1993
+ {
1994
+ "epoch": 0.3825,
1995
+ "grad_norm": 6.913736820220947,
1996
+ "learning_rate": 3.2500000000000002e-06,
1997
+ "loss": 0.4049,
1998
+ "step": 153
1999
+ },
2000
+ {
2001
+ "Batch Mean": 2.136556386947632,
2002
+ "accuracy": 0.78125,
2003
+ "epoch": 0.3825,
2004
+ "step": 153
2005
+ },
2006
+ {
2007
+ "epoch": 0.385,
2008
+ "grad_norm": 7.755904674530029,
2009
+ "learning_rate": 3.236842105263158e-06,
2010
+ "loss": 0.449,
2011
+ "step": 154
2012
+ },
2013
+ {
2014
+ "Batch Mean": 2.088193416595459,
2015
+ "accuracy": 0.8046875,
2016
+ "epoch": 0.385,
2017
+ "step": 154
2018
+ },
2019
+ {
2020
+ "epoch": 0.3875,
2021
+ "grad_norm": 7.1718316078186035,
2022
+ "learning_rate": 3.223684210526316e-06,
2023
+ "loss": 0.4129,
2024
+ "step": 155
2025
+ },
2026
+ {
2027
+ "Batch Mean": 2.5068817138671875,
2028
+ "accuracy": 0.796875,
2029
+ "epoch": 0.3875,
2030
+ "step": 155
2031
+ },
2032
+ {
2033
+ "epoch": 0.39,
2034
+ "grad_norm": 9.461467742919922,
2035
+ "learning_rate": 3.210526315789474e-06,
2036
+ "loss": 0.4147,
2037
+ "step": 156
2038
+ },
2039
+ {
2040
+ "Batch Mean": 2.0449132919311523,
2041
+ "accuracy": 0.7578125,
2042
+ "epoch": 0.39,
2043
+ "step": 156
2044
+ },
2045
+ {
2046
+ "epoch": 0.3925,
2047
+ "grad_norm": 8.785501480102539,
2048
+ "learning_rate": 3.197368421052632e-06,
2049
+ "loss": 0.478,
2050
+ "step": 157
2051
+ },
2052
+ {
2053
+ "Batch Mean": 2.2665648460388184,
2054
+ "accuracy": 0.8203125,
2055
+ "epoch": 0.3925,
2056
+ "step": 157
2057
+ },
2058
+ {
2059
+ "epoch": 0.395,
2060
+ "grad_norm": 7.906212329864502,
2061
+ "learning_rate": 3.1842105263157898e-06,
2062
+ "loss": 0.4083,
2063
+ "step": 158
2064
+ },
2065
+ {
2066
+ "Batch Mean": 1.8799333572387695,
2067
+ "accuracy": 0.734375,
2068
+ "epoch": 0.395,
2069
+ "step": 158
2070
+ },
2071
+ {
2072
+ "epoch": 0.3975,
2073
+ "grad_norm": 9.25344467163086,
2074
+ "learning_rate": 3.1710526315789477e-06,
2075
+ "loss": 0.5007,
2076
+ "step": 159
2077
+ },
2078
+ {
2079
+ "Batch Mean": 2.178339719772339,
2080
+ "accuracy": 0.828125,
2081
+ "epoch": 0.3975,
2082
+ "step": 159
2083
+ },
2084
+ {
2085
+ "epoch": 0.4,
2086
+ "grad_norm": 8.476263046264648,
2087
+ "learning_rate": 3.157894736842105e-06,
2088
+ "loss": 0.4184,
2089
+ "step": 160
2090
+ },
2091
+ {
2092
+ "Batch Mean": 1.9270563125610352,
2093
+ "accuracy": 0.7421875,
2094
+ "epoch": 0.4,
2095
+ "step": 160
2096
+ },
2097
+ {
2098
+ "epoch": 0.4025,
2099
+ "grad_norm": 10.214958190917969,
2100
+ "learning_rate": 3.144736842105263e-06,
2101
+ "loss": 0.5542,
2102
+ "step": 161
2103
+ },
2104
+ {
2105
+ "Batch Mean": 1.8700056076049805,
2106
+ "accuracy": 0.796875,
2107
+ "epoch": 0.4025,
2108
+ "step": 161
2109
+ },
2110
+ {
2111
+ "epoch": 0.405,
2112
+ "grad_norm": 8.01285171508789,
2113
+ "learning_rate": 3.131578947368421e-06,
2114
+ "loss": 0.4171,
2115
+ "step": 162
2116
+ },
2117
+ {
2118
+ "Batch Mean": 1.8484151363372803,
2119
+ "accuracy": 0.765625,
2120
+ "epoch": 0.405,
2121
+ "step": 162
2122
+ },
2123
+ {
2124
+ "epoch": 0.4075,
2125
+ "grad_norm": 8.116409301757812,
2126
+ "learning_rate": 3.1184210526315793e-06,
2127
+ "loss": 0.4576,
2128
+ "step": 163
2129
+ },
2130
+ {
2131
+ "Batch Mean": 1.7719857692718506,
2132
+ "accuracy": 0.78125,
2133
+ "epoch": 0.4075,
2134
+ "step": 163
2135
+ },
2136
+ {
2137
+ "epoch": 0.41,
2138
+ "grad_norm": 7.865448951721191,
2139
+ "learning_rate": 3.1052631578947372e-06,
2140
+ "loss": 0.4393,
2141
+ "step": 164
2142
+ },
2143
+ {
2144
+ "Batch Mean": 1.7638423442840576,
2145
+ "accuracy": 0.78125,
2146
+ "epoch": 0.41,
2147
+ "step": 164
2148
+ },
2149
+ {
2150
+ "epoch": 0.4125,
2151
+ "grad_norm": 7.379011631011963,
2152
+ "learning_rate": 3.092105263157895e-06,
2153
+ "loss": 0.4278,
2154
+ "step": 165
2155
+ },
2156
+ {
2157
+ "Batch Mean": 1.7345421314239502,
2158
+ "accuracy": 0.671875,
2159
+ "epoch": 0.4125,
2160
+ "step": 165
2161
+ },
2162
+ {
2163
+ "epoch": 0.415,
2164
+ "grad_norm": 8.332331657409668,
2165
+ "learning_rate": 3.078947368421053e-06,
2166
+ "loss": 0.5219,
2167
+ "step": 166
2168
+ },
2169
+ {
2170
+ "Batch Mean": 1.5037906169891357,
2171
+ "accuracy": 0.8203125,
2172
+ "epoch": 0.415,
2173
+ "step": 166
2174
+ },
2175
+ {
2176
+ "epoch": 0.4175,
2177
+ "grad_norm": 7.413763523101807,
2178
+ "learning_rate": 3.065789473684211e-06,
2179
+ "loss": 0.4208,
2180
+ "step": 167
2181
+ },
2182
+ {
2183
+ "Batch Mean": 1.7763586044311523,
2184
+ "accuracy": 0.84375,
2185
+ "epoch": 0.4175,
2186
+ "step": 167
2187
+ },
2188
+ {
2189
+ "epoch": 0.42,
2190
+ "grad_norm": 6.86100435256958,
2191
+ "learning_rate": 3.052631578947369e-06,
2192
+ "loss": 0.3848,
2193
+ "step": 168
2194
+ },
2195
+ {
2196
+ "Batch Mean": 1.7984695434570312,
2197
+ "accuracy": 0.7421875,
2198
+ "epoch": 0.42,
2199
+ "step": 168
2200
+ },
2201
+ {
2202
+ "epoch": 0.4225,
2203
+ "grad_norm": 8.179668426513672,
2204
+ "learning_rate": 3.0394736842105268e-06,
2205
+ "loss": 0.4362,
2206
+ "step": 169
2207
+ },
2208
+ {
2209
+ "Batch Mean": 2.192814588546753,
2210
+ "accuracy": 0.8046875,
2211
+ "epoch": 0.4225,
2212
+ "step": 169
2213
+ },
2214
+ {
2215
+ "epoch": 0.425,
2216
+ "grad_norm": 7.526256561279297,
2217
+ "learning_rate": 3.0263157894736843e-06,
2218
+ "loss": 0.4229,
2219
+ "step": 170
2220
+ },
2221
+ {
2222
+ "Batch Mean": 2.0280096530914307,
2223
+ "accuracy": 0.75,
2224
+ "epoch": 0.425,
2225
+ "step": 170
2226
+ },
2227
+ {
2228
+ "epoch": 0.4275,
2229
+ "grad_norm": 9.94598388671875,
2230
+ "learning_rate": 3.013157894736842e-06,
2231
+ "loss": 0.4399,
2232
+ "step": 171
2233
+ },
2234
+ {
2235
+ "Batch Mean": 2.0560245513916016,
2236
+ "accuracy": 0.7890625,
2237
+ "epoch": 0.4275,
2238
+ "step": 171
2239
+ },
2240
+ {
2241
+ "epoch": 0.43,
2242
+ "grad_norm": 8.51555347442627,
2243
+ "learning_rate": 3e-06,
2244
+ "loss": 0.4532,
2245
+ "step": 172
2246
+ },
2247
+ {
2248
+ "Batch Mean": 2.4426515102386475,
2249
+ "accuracy": 0.796875,
2250
+ "epoch": 0.43,
2251
+ "step": 172
2252
+ },
2253
+ {
2254
+ "epoch": 0.4325,
2255
+ "grad_norm": 10.147135734558105,
2256
+ "learning_rate": 2.986842105263158e-06,
2257
+ "loss": 0.415,
2258
+ "step": 173
2259
+ },
2260
+ {
2261
+ "Batch Mean": 2.6248912811279297,
2262
+ "accuracy": 0.765625,
2263
+ "epoch": 0.4325,
2264
+ "step": 173
2265
+ },
2266
+ {
2267
+ "epoch": 0.435,
2268
+ "grad_norm": 8.979937553405762,
2269
+ "learning_rate": 2.973684210526316e-06,
2270
+ "loss": 0.4281,
2271
+ "step": 174
2272
+ },
2273
+ {
2274
+ "Batch Mean": 2.5382537841796875,
2275
+ "accuracy": 0.75,
2276
+ "epoch": 0.435,
2277
+ "step": 174
2278
+ },
2279
+ {
2280
+ "epoch": 0.4375,
2281
+ "grad_norm": 9.164665222167969,
2282
+ "learning_rate": 2.960526315789474e-06,
2283
+ "loss": 0.5332,
2284
+ "step": 175
2285
+ },
2286
+ {
2287
+ "Batch Mean": 2.4894802570343018,
2288
+ "accuracy": 0.8515625,
2289
+ "epoch": 0.4375,
2290
+ "step": 175
2291
+ },
2292
+ {
2293
+ "epoch": 0.44,
2294
+ "grad_norm": 8.5990571975708,
2295
+ "learning_rate": 2.9473684210526317e-06,
2296
+ "loss": 0.3928,
2297
+ "step": 176
2298
+ },
2299
+ {
2300
+ "Batch Mean": 2.163804054260254,
2301
+ "accuracy": 0.8359375,
2302
+ "epoch": 0.44,
2303
+ "step": 176
2304
+ },
2305
+ {
2306
+ "epoch": 0.4425,
2307
+ "grad_norm": 7.983039855957031,
2308
+ "learning_rate": 2.93421052631579e-06,
2309
+ "loss": 0.3724,
2310
+ "step": 177
2311
+ },
2312
+ {
2313
+ "Batch Mean": 2.3338851928710938,
2314
+ "accuracy": 0.71875,
2315
+ "epoch": 0.4425,
2316
+ "step": 177
2317
+ },
2318
+ {
2319
+ "epoch": 0.445,
2320
+ "grad_norm": 11.577138900756836,
2321
+ "learning_rate": 2.921052631578948e-06,
2322
+ "loss": 0.5237,
2323
+ "step": 178
2324
+ },
2325
+ {
2326
+ "Batch Mean": 2.19907808303833,
2327
+ "accuracy": 0.78125,
2328
+ "epoch": 0.445,
2329
+ "step": 178
2330
+ },
2331
+ {
2332
+ "epoch": 0.4475,
2333
+ "grad_norm": 9.622861862182617,
2334
+ "learning_rate": 2.907894736842106e-06,
2335
+ "loss": 0.4411,
2336
+ "step": 179
2337
+ },
2338
+ {
2339
+ "Batch Mean": 2.456371307373047,
2340
+ "accuracy": 0.8203125,
2341
+ "epoch": 0.4475,
2342
+ "step": 179
2343
+ },
2344
+ {
2345
+ "epoch": 0.45,
2346
+ "grad_norm": 8.121110916137695,
2347
+ "learning_rate": 2.8947368421052634e-06,
2348
+ "loss": 0.3666,
2349
+ "step": 180
2350
+ },
2351
+ {
2352
+ "Batch Mean": 2.4925358295440674,
2353
+ "accuracy": 0.8046875,
2354
+ "epoch": 0.45,
2355
+ "step": 180
2356
+ },
2357
+ {
2358
+ "epoch": 0.4525,
2359
+ "grad_norm": 10.249773025512695,
2360
+ "learning_rate": 2.8815789473684213e-06,
2361
+ "loss": 0.4987,
2362
+ "step": 181
2363
+ },
2364
+ {
2365
+ "Batch Mean": 2.46488094329834,
2366
+ "accuracy": 0.84375,
2367
+ "epoch": 0.4525,
2368
+ "step": 181
2369
+ },
2370
+ {
2371
+ "epoch": 0.455,
2372
+ "grad_norm": 7.278886318206787,
2373
+ "learning_rate": 2.868421052631579e-06,
2374
+ "loss": 0.3417,
2375
+ "step": 182
2376
+ },
2377
+ {
2378
+ "Batch Mean": 2.4173011779785156,
2379
+ "accuracy": 0.8125,
2380
+ "epoch": 0.455,
2381
+ "step": 182
2382
+ },
2383
+ {
2384
+ "epoch": 0.4575,
2385
+ "grad_norm": 8.626398086547852,
2386
+ "learning_rate": 2.855263157894737e-06,
2387
+ "loss": 0.4077,
2388
+ "step": 183
2389
+ },
2390
+ {
2391
+ "Batch Mean": 1.8599066734313965,
2392
+ "accuracy": 0.7421875,
2393
+ "epoch": 0.4575,
2394
+ "step": 183
2395
+ },
2396
+ {
2397
+ "epoch": 0.46,
2398
+ "grad_norm": 9.768396377563477,
2399
+ "learning_rate": 2.842105263157895e-06,
2400
+ "loss": 0.4882,
2401
+ "step": 184
2402
+ },
2403
+ {
2404
+ "Batch Mean": 2.145785331726074,
2405
+ "accuracy": 0.78125,
2406
+ "epoch": 0.46,
2407
+ "step": 184
2408
+ },
2409
+ {
2410
+ "epoch": 0.4625,
2411
+ "grad_norm": 8.507255554199219,
2412
+ "learning_rate": 2.828947368421053e-06,
2413
+ "loss": 0.4024,
2414
+ "step": 185
2415
+ },
2416
+ {
2417
+ "Batch Mean": 1.7814726829528809,
2418
+ "accuracy": 0.7578125,
2419
+ "epoch": 0.4625,
2420
+ "step": 185
2421
+ },
2422
+ {
2423
+ "epoch": 0.465,
2424
+ "grad_norm": 10.355148315429688,
2425
+ "learning_rate": 2.815789473684211e-06,
2426
+ "loss": 0.5292,
2427
+ "step": 186
2428
+ },
2429
+ {
2430
+ "Batch Mean": 1.888627529144287,
2431
+ "accuracy": 0.828125,
2432
+ "epoch": 0.465,
2433
+ "step": 186
2434
+ },
2435
+ {
2436
+ "epoch": 0.4675,
2437
+ "grad_norm": 8.215280532836914,
2438
+ "learning_rate": 2.8026315789473683e-06,
2439
+ "loss": 0.3985,
2440
+ "step": 187
2441
+ },
2442
+ {
2443
+ "Batch Mean": 1.8559679985046387,
2444
+ "accuracy": 0.828125,
2445
+ "epoch": 0.4675,
2446
+ "step": 187
2447
+ },
2448
+ {
2449
+ "epoch": 0.47,
2450
+ "grad_norm": 7.013787269592285,
2451
+ "learning_rate": 2.789473684210526e-06,
2452
+ "loss": 0.3815,
2453
+ "step": 188
2454
+ },
2455
+ {
2456
+ "Batch Mean": 1.7180118560791016,
2457
+ "accuracy": 0.7578125,
2458
+ "epoch": 0.47,
2459
+ "step": 188
2460
+ },
2461
+ {
2462
+ "epoch": 0.4725,
2463
+ "grad_norm": 7.246432781219482,
2464
+ "learning_rate": 2.776315789473684e-06,
2465
+ "loss": 0.4432,
2466
+ "step": 189
2467
+ },
2468
+ {
2469
+ "Batch Mean": 1.5764282941818237,
2470
+ "accuracy": 0.8046875,
2471
+ "epoch": 0.4725,
2472
+ "step": 189
2473
+ },
2474
+ {
2475
+ "epoch": 0.475,
2476
+ "grad_norm": 7.489908218383789,
2477
+ "learning_rate": 2.7631578947368424e-06,
2478
+ "loss": 0.4256,
2479
+ "step": 190
2480
+ },
2481
+ {
2482
+ "Batch Mean": 1.2490241527557373,
2483
+ "accuracy": 0.796875,
2484
+ "epoch": 0.475,
2485
+ "step": 190
2486
+ },
2487
+ {
2488
+ "epoch": 0.4775,
2489
+ "grad_norm": 7.128645420074463,
2490
+ "learning_rate": 2.7500000000000004e-06,
2491
+ "loss": 0.4488,
2492
+ "step": 191
2493
+ },
2494
+ {
2495
+ "Batch Mean": 1.0759793519973755,
2496
+ "accuracy": 0.828125,
2497
+ "epoch": 0.4775,
2498
+ "step": 191
2499
+ },
2500
+ {
2501
+ "epoch": 0.48,
2502
+ "grad_norm": 7.570965766906738,
2503
+ "learning_rate": 2.7368421052631583e-06,
2504
+ "loss": 0.4073,
2505
+ "step": 192
2506
+ },
2507
+ {
2508
+ "Batch Mean": 0.8960497379302979,
2509
+ "accuracy": 0.84375,
2510
+ "epoch": 0.48,
2511
+ "step": 192
2512
+ },
2513
+ {
2514
+ "epoch": 0.4825,
2515
+ "grad_norm": 7.548012733459473,
2516
+ "learning_rate": 2.723684210526316e-06,
2517
+ "loss": 0.3733,
2518
+ "step": 193
2519
+ },
2520
+ {
2521
+ "Batch Mean": 0.9645734429359436,
2522
+ "accuracy": 0.765625,
2523
+ "epoch": 0.4825,
2524
+ "step": 193
2525
+ },
2526
+ {
2527
+ "epoch": 0.485,
2528
+ "grad_norm": 7.658840656280518,
2529
+ "learning_rate": 2.710526315789474e-06,
2530
+ "loss": 0.4456,
2531
+ "step": 194
2532
+ },
2533
+ {
2534
+ "Batch Mean": 0.9235124588012695,
2535
+ "accuracy": 0.8515625,
2536
+ "epoch": 0.485,
2537
+ "step": 194
2538
+ },
2539
+ {
2540
+ "epoch": 0.4875,
2541
+ "grad_norm": 7.451051235198975,
2542
+ "learning_rate": 2.697368421052632e-06,
2543
+ "loss": 0.3823,
2544
+ "step": 195
2545
+ },
2546
+ {
2547
+ "Batch Mean": 1.27029550075531,
2548
+ "accuracy": 0.84375,
2549
+ "epoch": 0.4875,
2550
+ "step": 195
2551
+ },
2552
+ {
2553
+ "epoch": 0.49,
2554
+ "grad_norm": 7.330119609832764,
2555
+ "learning_rate": 2.68421052631579e-06,
2556
+ "loss": 0.3983,
2557
+ "step": 196
2558
+ },
2559
+ {
2560
+ "Batch Mean": 1.3359482288360596,
2561
+ "accuracy": 0.7578125,
2562
+ "epoch": 0.49,
2563
+ "step": 196
2564
+ },
2565
+ {
2566
+ "epoch": 0.4925,
2567
+ "grad_norm": 7.700873374938965,
2568
+ "learning_rate": 2.6710526315789474e-06,
2569
+ "loss": 0.4517,
2570
+ "step": 197
2571
+ },
2572
+ {
2573
+ "Batch Mean": 1.4910411834716797,
2574
+ "accuracy": 0.7265625,
2575
+ "epoch": 0.4925,
2576
+ "step": 197
2577
+ },
2578
+ {
2579
+ "epoch": 0.495,
2580
+ "grad_norm": 8.952484130859375,
2581
+ "learning_rate": 2.6578947368421053e-06,
2582
+ "loss": 0.4592,
2583
+ "step": 198
2584
+ },
2585
+ {
2586
+ "Batch Mean": 1.6832847595214844,
2587
+ "accuracy": 0.8359375,
2588
+ "epoch": 0.495,
2589
+ "step": 198
2590
+ },
2591
+ {
2592
+ "epoch": 0.4975,
2593
+ "grad_norm": 8.010570526123047,
2594
+ "learning_rate": 2.644736842105263e-06,
2595
+ "loss": 0.4087,
2596
+ "step": 199
2597
+ },
2598
+ {
2599
+ "Batch Mean": 1.5343718528747559,
2600
+ "accuracy": 0.796875,
2601
+ "epoch": 0.4975,
2602
+ "step": 199
2603
+ },
2604
+ {
2605
+ "epoch": 0.5,
2606
+ "grad_norm": 8.992362976074219,
2607
+ "learning_rate": 2.631578947368421e-06,
2608
+ "loss": 0.4823,
2609
+ "step": 200
2610
+ },
2611
+ {
2612
+ "Batch Mean": 1.6328332424163818,
2613
+ "accuracy": 0.7734375,
2614
+ "epoch": 0.5,
2615
+ "step": 200
2616
+ },
2617
+ {
2618
+ "epoch": 0.5025,
2619
+ "grad_norm": 9.035256385803223,
2620
+ "learning_rate": 2.618421052631579e-06,
2621
+ "loss": 0.4471,
2622
+ "step": 201
2623
+ },
2624
+ {
2625
+ "Batch Mean": 1.5844993591308594,
2626
+ "accuracy": 0.78125,
2627
+ "epoch": 0.5025,
2628
+ "step": 201
2629
+ },
2630
+ {
2631
+ "epoch": 0.505,
2632
+ "grad_norm": 7.833075046539307,
2633
+ "learning_rate": 2.605263157894737e-06,
2634
+ "loss": 0.4245,
2635
+ "step": 202
2636
+ },
2637
+ {
2638
+ "Batch Mean": 1.411280632019043,
2639
+ "accuracy": 0.7734375,
2640
+ "epoch": 0.505,
2641
+ "step": 202
2642
+ },
2643
+ {
2644
+ "epoch": 0.5075,
2645
+ "grad_norm": 9.432007789611816,
2646
+ "learning_rate": 2.592105263157895e-06,
2647
+ "loss": 0.4416,
2648
+ "step": 203
2649
+ },
2650
+ {
2651
+ "Batch Mean": 1.6097602844238281,
2652
+ "accuracy": 0.7421875,
2653
+ "epoch": 0.5075,
2654
+ "step": 203
2655
+ },
2656
+ {
2657
+ "epoch": 0.51,
2658
+ "grad_norm": 8.289928436279297,
2659
+ "learning_rate": 2.578947368421053e-06,
2660
+ "loss": 0.4749,
2661
+ "step": 204
2662
+ },
2663
+ {
2664
+ "Batch Mean": 1.1805787086486816,
2665
+ "accuracy": 0.734375,
2666
+ "epoch": 0.51,
2667
+ "step": 204
2668
+ },
2669
+ {
2670
+ "epoch": 0.5125,
2671
+ "grad_norm": 9.437891960144043,
2672
+ "learning_rate": 2.565789473684211e-06,
2673
+ "loss": 0.4626,
2674
+ "step": 205
2675
+ },
2676
+ {
2677
+ "Batch Mean": 1.347944736480713,
2678
+ "accuracy": 0.7265625,
2679
+ "epoch": 0.5125,
2680
+ "step": 205
2681
+ },
2682
+ {
2683
+ "epoch": 0.515,
2684
+ "grad_norm": 8.658241271972656,
2685
+ "learning_rate": 2.552631578947369e-06,
2686
+ "loss": 0.4763,
2687
+ "step": 206
2688
+ },
2689
+ {
2690
+ "Batch Mean": 1.2932205200195312,
2691
+ "accuracy": 0.7890625,
2692
+ "epoch": 0.515,
2693
+ "step": 206
2694
+ },
2695
+ {
2696
+ "epoch": 0.5175,
2697
+ "grad_norm": 8.141422271728516,
2698
+ "learning_rate": 2.5394736842105265e-06,
2699
+ "loss": 0.4264,
2700
+ "step": 207
2701
+ },
2702
+ {
2703
+ "Batch Mean": 1.2558472156524658,
2704
+ "accuracy": 0.8046875,
2705
+ "epoch": 0.5175,
2706
+ "step": 207
2707
+ },
2708
+ {
2709
+ "epoch": 0.52,
2710
+ "grad_norm": 7.476047515869141,
2711
+ "learning_rate": 2.5263157894736844e-06,
2712
+ "loss": 0.4308,
2713
+ "step": 208
2714
+ },
2715
+ {
2716
+ "Batch Mean": 0.9620341062545776,
2717
+ "accuracy": 0.7421875,
2718
+ "epoch": 0.52,
2719
+ "step": 208
2720
+ },
2721
+ {
2722
+ "epoch": 0.5225,
2723
+ "grad_norm": 7.889948844909668,
2724
+ "learning_rate": 2.5131578947368423e-06,
2725
+ "loss": 0.4499,
2726
+ "step": 209
2727
+ },
2728
+ {
2729
+ "Batch Mean": 0.7413516640663147,
2730
+ "accuracy": 0.7265625,
2731
+ "epoch": 0.5225,
2732
+ "step": 209
2733
+ },
2734
+ {
2735
+ "epoch": 0.525,
2736
+ "grad_norm": 9.15515422821045,
2737
+ "learning_rate": 2.5e-06,
2738
+ "loss": 0.5032,
2739
+ "step": 210
2740
+ },
2741
+ {
2742
+ "Batch Mean": 0.9634220600128174,
2743
+ "accuracy": 0.8515625,
2744
+ "epoch": 0.525,
2745
+ "step": 210
2746
+ },
2747
+ {
2748
+ "epoch": 0.5275,
2749
+ "grad_norm": 6.711307048797607,
2750
+ "learning_rate": 2.486842105263158e-06,
2751
+ "loss": 0.3679,
2752
+ "step": 211
2753
+ },
2754
+ {
2755
+ "Batch Mean": 1.191461205482483,
2756
+ "accuracy": 0.734375,
2757
+ "epoch": 0.5275,
2758
+ "step": 211
2759
+ },
2760
+ {
2761
+ "epoch": 0.53,
2762
+ "grad_norm": 7.998767375946045,
2763
+ "learning_rate": 2.473684210526316e-06,
2764
+ "loss": 0.4737,
2765
+ "step": 212
2766
+ },
2767
+ {
2768
+ "Batch Mean": 0.9631187915802002,
2769
+ "accuracy": 0.828125,
2770
+ "epoch": 0.53,
2771
+ "step": 212
2772
+ },
2773
+ {
2774
+ "epoch": 0.5325,
2775
+ "grad_norm": 5.967334747314453,
2776
+ "learning_rate": 2.460526315789474e-06,
2777
+ "loss": 0.3451,
2778
+ "step": 213
2779
+ },
2780
+ {
2781
+ "Batch Mean": 0.8651614189147949,
2782
+ "accuracy": 0.7734375,
2783
+ "epoch": 0.5325,
2784
+ "step": 213
2785
+ },
2786
+ {
2787
+ "epoch": 0.535,
2788
+ "grad_norm": 7.710539817810059,
2789
+ "learning_rate": 2.447368421052632e-06,
2790
+ "loss": 0.4404,
2791
+ "step": 214
2792
+ },
2793
+ {
2794
+ "Batch Mean": 0.9871734380722046,
2795
+ "accuracy": 0.8515625,
2796
+ "epoch": 0.535,
2797
+ "step": 214
2798
+ },
2799
+ {
2800
+ "epoch": 0.5375,
2801
+ "grad_norm": 7.020612716674805,
2802
+ "learning_rate": 2.4342105263157898e-06,
2803
+ "loss": 0.3469,
2804
+ "step": 215
2805
+ },
2806
+ {
2807
+ "Batch Mean": 0.9098066091537476,
2808
+ "accuracy": 0.765625,
2809
+ "epoch": 0.5375,
2810
+ "step": 215
2811
+ },
2812
+ {
2813
+ "epoch": 0.54,
2814
+ "grad_norm": 8.405688285827637,
2815
+ "learning_rate": 2.4210526315789477e-06,
2816
+ "loss": 0.5086,
2817
+ "step": 216
2818
+ },
2819
+ {
2820
+ "Batch Mean": 0.9320878982543945,
2821
+ "accuracy": 0.7734375,
2822
+ "epoch": 0.54,
2823
+ "step": 216
2824
+ },
2825
+ {
2826
+ "epoch": 0.5425,
2827
+ "grad_norm": 7.488485336303711,
2828
+ "learning_rate": 2.4078947368421056e-06,
2829
+ "loss": 0.4145,
2830
+ "step": 217
2831
+ },
2832
+ {
2833
+ "Batch Mean": 1.1252110004425049,
2834
+ "accuracy": 0.7734375,
2835
+ "epoch": 0.5425,
2836
+ "step": 217
2837
+ },
2838
+ {
2839
+ "epoch": 0.545,
2840
+ "grad_norm": 8.458834648132324,
2841
+ "learning_rate": 2.3947368421052635e-06,
2842
+ "loss": 0.4336,
2843
+ "step": 218
2844
+ },
2845
+ {
2846
+ "Batch Mean": 1.0384407043457031,
2847
+ "accuracy": 0.828125,
2848
+ "epoch": 0.545,
2849
+ "step": 218
2850
+ },
2851
+ {
2852
+ "epoch": 0.5475,
2853
+ "grad_norm": 8.343704223632812,
2854
+ "learning_rate": 2.381578947368421e-06,
2855
+ "loss": 0.3845,
2856
+ "step": 219
2857
+ },
2858
+ {
2859
+ "Batch Mean": 1.3833621740341187,
2860
+ "accuracy": 0.7734375,
2861
+ "epoch": 0.5475,
2862
+ "step": 219
2863
+ },
2864
+ {
2865
+ "epoch": 0.55,
2866
+ "grad_norm": 9.676087379455566,
2867
+ "learning_rate": 2.368421052631579e-06,
2868
+ "loss": 0.4359,
2869
+ "step": 220
2870
+ },
2871
+ {
2872
+ "Batch Mean": 0.9786429405212402,
2873
+ "accuracy": 0.7890625,
2874
+ "epoch": 0.55,
2875
+ "step": 220
2876
+ },
2877
+ {
2878
+ "epoch": 0.5525,
2879
+ "grad_norm": 8.946784019470215,
2880
+ "learning_rate": 2.355263157894737e-06,
2881
+ "loss": 0.4391,
2882
+ "step": 221
2883
+ },
2884
+ {
2885
+ "Batch Mean": 1.0276886224746704,
2886
+ "accuracy": 0.796875,
2887
+ "epoch": 0.5525,
2888
+ "step": 221
2889
+ },
2890
+ {
2891
+ "epoch": 0.555,
2892
+ "grad_norm": 9.185587882995605,
2893
+ "learning_rate": 2.342105263157895e-06,
2894
+ "loss": 0.4326,
2895
+ "step": 222
2896
+ },
2897
+ {
2898
+ "Batch Mean": 1.312666416168213,
2899
+ "accuracy": 0.765625,
2900
+ "epoch": 0.555,
2901
+ "step": 222
2902
+ },
2903
+ {
2904
+ "epoch": 0.5575,
2905
+ "grad_norm": 9.896113395690918,
2906
+ "learning_rate": 2.328947368421053e-06,
2907
+ "loss": 0.4861,
2908
+ "step": 223
2909
+ },
2910
+ {
2911
+ "Batch Mean": 1.1942353248596191,
2912
+ "accuracy": 0.828125,
2913
+ "epoch": 0.5575,
2914
+ "step": 223
2915
+ },
2916
+ {
2917
+ "epoch": 0.56,
2918
+ "grad_norm": 7.770511150360107,
2919
+ "learning_rate": 2.3157894736842105e-06,
2920
+ "loss": 0.3452,
2921
+ "step": 224
2922
+ },
2923
+ {
2924
+ "Batch Mean": 0.8957247734069824,
2925
+ "accuracy": 0.765625,
2926
+ "epoch": 0.56,
2927
+ "step": 224
2928
+ },
2929
+ {
2930
+ "epoch": 0.5625,
2931
+ "grad_norm": 10.309408187866211,
2932
+ "learning_rate": 2.3026315789473684e-06,
2933
+ "loss": 0.459,
2934
+ "step": 225
2935
+ },
2936
+ {
2937
+ "Batch Mean": 0.9890605807304382,
2938
+ "accuracy": 0.7734375,
2939
+ "epoch": 0.5625,
2940
+ "step": 225
2941
+ },
2942
+ {
2943
+ "epoch": 0.565,
2944
+ "grad_norm": 10.081012725830078,
2945
+ "learning_rate": 2.2894736842105263e-06,
2946
+ "loss": 0.433,
2947
+ "step": 226
2948
+ },
2949
+ {
2950
+ "Batch Mean": 0.37744632363319397,
2951
+ "accuracy": 0.7734375,
2952
+ "epoch": 0.565,
2953
+ "step": 226
2954
+ },
2955
+ {
2956
+ "epoch": 0.5675,
2957
+ "grad_norm": 10.793180465698242,
2958
+ "learning_rate": 2.2763157894736847e-06,
2959
+ "loss": 0.4462,
2960
+ "step": 227
2961
+ },
2962
+ {
2963
+ "Batch Mean": 0.5035256147384644,
2964
+ "accuracy": 0.796875,
2965
+ "epoch": 0.5675,
2966
+ "step": 227
2967
+ },
2968
+ {
2969
+ "epoch": 0.57,
2970
+ "grad_norm": 10.840557098388672,
2971
+ "learning_rate": 2.2631578947368426e-06,
2972
+ "loss": 0.4301,
2973
+ "step": 228
2974
+ },
2975
+ {
2976
+ "Batch Mean": 0.3500272035598755,
2977
+ "accuracy": 0.828125,
2978
+ "epoch": 0.57,
2979
+ "step": 228
2980
+ },
2981
+ {
2982
+ "epoch": 0.5725,
2983
+ "grad_norm": 7.773880958557129,
2984
+ "learning_rate": 2.25e-06,
2985
+ "loss": 0.3467,
2986
+ "step": 229
2987
+ },
2988
+ {
2989
+ "Batch Mean": 0.548717737197876,
2990
+ "accuracy": 0.8125,
2991
+ "epoch": 0.5725,
2992
+ "step": 229
2993
+ },
2994
+ {
2995
+ "epoch": 0.575,
2996
+ "grad_norm": 9.137742042541504,
2997
+ "learning_rate": 2.236842105263158e-06,
2998
+ "loss": 0.4347,
2999
+ "step": 230
3000
+ },
3001
+ {
3002
+ "Batch Mean": 0.3661317825317383,
3003
+ "accuracy": 0.84375,
3004
+ "epoch": 0.575,
3005
+ "step": 230
3006
+ },
3007
+ {
3008
+ "epoch": 0.5775,
3009
+ "grad_norm": 7.887228012084961,
3010
+ "learning_rate": 2.223684210526316e-06,
3011
+ "loss": 0.3833,
3012
+ "step": 231
3013
+ },
3014
+ {
3015
+ "Batch Mean": 0.12111562490463257,
3016
+ "accuracy": 0.7890625,
3017
+ "epoch": 0.5775,
3018
+ "step": 231
3019
+ },
3020
+ {
3021
+ "epoch": 0.58,
3022
+ "grad_norm": 7.976273536682129,
3023
+ "learning_rate": 2.2105263157894738e-06,
3024
+ "loss": 0.4134,
3025
+ "step": 232
3026
+ },
3027
+ {
3028
+ "Batch Mean": 0.4660627841949463,
3029
+ "accuracy": 0.78125,
3030
+ "epoch": 0.58,
3031
+ "step": 232
3032
+ },
3033
+ {
3034
+ "epoch": 0.5825,
3035
+ "grad_norm": 9.632377624511719,
3036
+ "learning_rate": 2.1973684210526317e-06,
3037
+ "loss": 0.4059,
3038
+ "step": 233
3039
+ },
3040
+ {
3041
+ "Batch Mean": 0.21030330657958984,
3042
+ "accuracy": 0.78125,
3043
+ "epoch": 0.5825,
3044
+ "step": 233
3045
+ },
3046
+ {
3047
+ "epoch": 0.585,
3048
+ "grad_norm": 8.921050071716309,
3049
+ "learning_rate": 2.1842105263157896e-06,
3050
+ "loss": 0.4555,
3051
+ "step": 234
3052
+ },
3053
+ {
3054
+ "Batch Mean": 0.2276170253753662,
3055
+ "accuracy": 0.890625,
3056
+ "epoch": 0.585,
3057
+ "step": 234
3058
+ },
3059
+ {
3060
+ "epoch": 0.5875,
3061
+ "grad_norm": 7.977242469787598,
3062
+ "learning_rate": 2.1710526315789475e-06,
3063
+ "loss": 0.3518,
3064
+ "step": 235
3065
+ },
3066
+ {
3067
+ "Batch Mean": 0.11401081085205078,
3068
+ "accuracy": 0.828125,
3069
+ "epoch": 0.5875,
3070
+ "step": 235
3071
+ },
3072
+ {
3073
+ "epoch": 0.59,
3074
+ "grad_norm": 8.604510307312012,
3075
+ "learning_rate": 2.1578947368421054e-06,
3076
+ "loss": 0.3273,
3077
+ "step": 236
3078
+ },
3079
+ {
3080
+ "Batch Mean": 0.21731328964233398,
3081
+ "accuracy": 0.7578125,
3082
+ "epoch": 0.59,
3083
+ "step": 236
3084
+ },
3085
+ {
3086
+ "epoch": 0.5925,
3087
+ "grad_norm": 11.264445304870605,
3088
+ "learning_rate": 2.1447368421052633e-06,
3089
+ "loss": 0.5015,
3090
+ "step": 237
3091
+ },
3092
+ {
3093
+ "Batch Mean": 0.24432829022407532,
3094
+ "accuracy": 0.8125,
3095
+ "epoch": 0.5925,
3096
+ "step": 237
3097
+ },
3098
+ {
3099
+ "epoch": 0.595,
3100
+ "grad_norm": 11.254815101623535,
3101
+ "learning_rate": 2.1315789473684212e-06,
3102
+ "loss": 0.4282,
3103
+ "step": 238
3104
+ },
3105
+ {
3106
+ "Batch Mean": 0.29278555512428284,
3107
+ "accuracy": 0.7734375,
3108
+ "epoch": 0.595,
3109
+ "step": 238
3110
+ },
3111
+ {
3112
+ "epoch": 0.5975,
3113
+ "grad_norm": 9.741961479187012,
3114
+ "learning_rate": 2.118421052631579e-06,
3115
+ "loss": 0.4351,
3116
+ "step": 239
3117
+ },
3118
+ {
3119
+ "Batch Mean": 0.41886043548583984,
3120
+ "accuracy": 0.8046875,
3121
+ "epoch": 0.5975,
3122
+ "step": 239
3123
+ },
3124
+ {
3125
+ "epoch": 0.6,
3126
+ "grad_norm": 9.94571590423584,
3127
+ "learning_rate": 2.105263157894737e-06,
3128
+ "loss": 0.4331,
3129
+ "step": 240
3130
+ }
3131
+ ],
3132
+ "logging_steps": 1,
3133
+ "max_steps": 400,
3134
+ "num_input_tokens_seen": 0,
3135
+ "num_train_epochs": 1,
3136
+ "save_steps": 80,
3137
+ "stateful_callbacks": {
3138
+ "TrainerControl": {
3139
+ "args": {
3140
+ "should_epoch_stop": false,
3141
+ "should_evaluate": false,
3142
+ "should_log": false,
3143
+ "should_save": true,
3144
+ "should_training_stop": false
3145
+ },
3146
+ "attributes": {}
3147
+ }
3148
+ },
3149
+ "total_flos": 0.0,
3150
+ "train_batch_size": 64,
3151
+ "trial_name": null,
3152
+ "trial_params": null
3153
+ }
checkpoint-240/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130b9bda9b58e60760405321a76b9b11a12c69620b1886f49451f28ec3960f24
3
+ size 5752
checkpoint-320/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-1B-UC",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "max_position_embeddings": 131072,
26
+ "mlp_bias": false,
27
+ "model_type": "llama",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 16,
30
+ "num_key_value_heads": 8,
31
+ "pad_token_id": 128001,
32
+ "pretraining_tp": 1,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "factor": 32.0,
36
+ "high_freq_factor": 4.0,
37
+ "low_freq_factor": 1.0,
38
+ "original_max_position_embeddings": 8192,
39
+ "rope_type": "llama3"
40
+ },
41
+ "rope_theta": 500000.0,
42
+ "tie_word_embeddings": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.48.0",
45
+ "use_cache": false,
46
+ "vocab_size": 128256
47
+ }
checkpoint-320/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49990aa7753ca5b5657f2497f617ee632a50b3f8c7a01505c7e1f99fa400f8e4
3
+ size 4943282608
checkpoint-320/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-320/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-320/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
checkpoint-320/trainer_state.json ADDED
@@ -0,0 +1,4193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8,
5
+ "eval_steps": 500,
6
+ "global_step": 320,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "Batch Mean": 2.64666748046875,
13
+ "accuracy": 0.484375,
14
+ "epoch": 0,
15
+ "step": 0
16
+ },
17
+ {
18
+ "epoch": 0.0025,
19
+ "grad_norm": 9.6364107131958,
20
+ "learning_rate": 2.5000000000000004e-07,
21
+ "loss": 0.723,
22
+ "step": 1
23
+ },
24
+ {
25
+ "Batch Mean": 2.6478805541992188,
26
+ "accuracy": 0.46875,
27
+ "epoch": 0.0025,
28
+ "step": 1
29
+ },
30
+ {
31
+ "epoch": 0.005,
32
+ "grad_norm": 7.393254280090332,
33
+ "learning_rate": 5.000000000000001e-07,
34
+ "loss": 0.7006,
35
+ "step": 2
36
+ },
37
+ {
38
+ "Batch Mean": 2.62982177734375,
39
+ "accuracy": 0.4453125,
40
+ "epoch": 0.005,
41
+ "step": 2
42
+ },
43
+ {
44
+ "epoch": 0.0075,
45
+ "grad_norm": 8.464498519897461,
46
+ "learning_rate": 7.5e-07,
47
+ "loss": 0.7093,
48
+ "step": 3
49
+ },
50
+ {
51
+ "Batch Mean": 2.6655197143554688,
52
+ "accuracy": 0.5,
53
+ "epoch": 0.0075,
54
+ "step": 3
55
+ },
56
+ {
57
+ "epoch": 0.01,
58
+ "grad_norm": 7.2742462158203125,
59
+ "learning_rate": 1.0000000000000002e-06,
60
+ "loss": 0.7101,
61
+ "step": 4
62
+ },
63
+ {
64
+ "Batch Mean": 2.616424560546875,
65
+ "accuracy": 0.4296875,
66
+ "epoch": 0.01,
67
+ "step": 4
68
+ },
69
+ {
70
+ "epoch": 0.0125,
71
+ "grad_norm": 8.216493606567383,
72
+ "learning_rate": 1.25e-06,
73
+ "loss": 0.7145,
74
+ "step": 5
75
+ },
76
+ {
77
+ "Batch Mean": 2.6591033935546875,
78
+ "accuracy": 0.546875,
79
+ "epoch": 0.0125,
80
+ "step": 5
81
+ },
82
+ {
83
+ "epoch": 0.015,
84
+ "grad_norm": 8.033185958862305,
85
+ "learning_rate": 1.5e-06,
86
+ "loss": 0.6821,
87
+ "step": 6
88
+ },
89
+ {
90
+ "Batch Mean": 2.6329345703125,
91
+ "accuracy": 0.640625,
92
+ "epoch": 0.015,
93
+ "step": 6
94
+ },
95
+ {
96
+ "epoch": 0.0175,
97
+ "grad_norm": 10.476421356201172,
98
+ "learning_rate": 1.75e-06,
99
+ "loss": 0.6911,
100
+ "step": 7
101
+ },
102
+ {
103
+ "Batch Mean": 2.680908203125,
104
+ "accuracy": 0.5859375,
105
+ "epoch": 0.0175,
106
+ "step": 7
107
+ },
108
+ {
109
+ "epoch": 0.02,
110
+ "grad_norm": 9.513436317443848,
111
+ "learning_rate": 2.0000000000000003e-06,
112
+ "loss": 0.6859,
113
+ "step": 8
114
+ },
115
+ {
116
+ "Batch Mean": 2.658843994140625,
117
+ "accuracy": 0.53125,
118
+ "epoch": 0.02,
119
+ "step": 8
120
+ },
121
+ {
122
+ "epoch": 0.0225,
123
+ "grad_norm": 7.415161609649658,
124
+ "learning_rate": 2.25e-06,
125
+ "loss": 0.6839,
126
+ "step": 9
127
+ },
128
+ {
129
+ "Batch Mean": 2.74237060546875,
130
+ "accuracy": 0.6328125,
131
+ "epoch": 0.0225,
132
+ "step": 9
133
+ },
134
+ {
135
+ "epoch": 0.025,
136
+ "grad_norm": 6.572882175445557,
137
+ "learning_rate": 2.5e-06,
138
+ "loss": 0.6557,
139
+ "step": 10
140
+ },
141
+ {
142
+ "Batch Mean": 2.9183349609375,
143
+ "accuracy": 0.65625,
144
+ "epoch": 0.025,
145
+ "step": 10
146
+ },
147
+ {
148
+ "epoch": 0.0275,
149
+ "grad_norm": 6.594631671905518,
150
+ "learning_rate": 2.7500000000000004e-06,
151
+ "loss": 0.6336,
152
+ "step": 11
153
+ },
154
+ {
155
+ "Batch Mean": 2.929656982421875,
156
+ "accuracy": 0.546875,
157
+ "epoch": 0.0275,
158
+ "step": 11
159
+ },
160
+ {
161
+ "epoch": 0.03,
162
+ "grad_norm": 6.199557304382324,
163
+ "learning_rate": 3e-06,
164
+ "loss": 0.6784,
165
+ "step": 12
166
+ },
167
+ {
168
+ "Batch Mean": 2.938323974609375,
169
+ "accuracy": 0.59375,
170
+ "epoch": 0.03,
171
+ "step": 12
172
+ },
173
+ {
174
+ "epoch": 0.0325,
175
+ "grad_norm": 8.091628074645996,
176
+ "learning_rate": 3.2500000000000002e-06,
177
+ "loss": 0.6887,
178
+ "step": 13
179
+ },
180
+ {
181
+ "Batch Mean": 3.0481414794921875,
182
+ "accuracy": 0.6171875,
183
+ "epoch": 0.0325,
184
+ "step": 13
185
+ },
186
+ {
187
+ "epoch": 0.035,
188
+ "grad_norm": 8.876925468444824,
189
+ "learning_rate": 3.5e-06,
190
+ "loss": 0.6421,
191
+ "step": 14
192
+ },
193
+ {
194
+ "Batch Mean": 3.2818450927734375,
195
+ "accuracy": 0.703125,
196
+ "epoch": 0.035,
197
+ "step": 14
198
+ },
199
+ {
200
+ "epoch": 0.0375,
201
+ "grad_norm": 10.33357048034668,
202
+ "learning_rate": 3.7500000000000005e-06,
203
+ "loss": 0.5853,
204
+ "step": 15
205
+ },
206
+ {
207
+ "Batch Mean": 3.2837677001953125,
208
+ "accuracy": 0.625,
209
+ "epoch": 0.0375,
210
+ "step": 15
211
+ },
212
+ {
213
+ "epoch": 0.04,
214
+ "grad_norm": 11.141650199890137,
215
+ "learning_rate": 4.000000000000001e-06,
216
+ "loss": 0.6495,
217
+ "step": 16
218
+ },
219
+ {
220
+ "Batch Mean": 3.2836532592773438,
221
+ "accuracy": 0.6015625,
222
+ "epoch": 0.04,
223
+ "step": 16
224
+ },
225
+ {
226
+ "epoch": 0.0425,
227
+ "grad_norm": 8.093420028686523,
228
+ "learning_rate": 4.25e-06,
229
+ "loss": 0.6607,
230
+ "step": 17
231
+ },
232
+ {
233
+ "Batch Mean": 3.3738174438476562,
234
+ "accuracy": 0.65625,
235
+ "epoch": 0.0425,
236
+ "step": 17
237
+ },
238
+ {
239
+ "epoch": 0.045,
240
+ "grad_norm": 8.171963691711426,
241
+ "learning_rate": 4.5e-06,
242
+ "loss": 0.5946,
243
+ "step": 18
244
+ },
245
+ {
246
+ "Batch Mean": 3.8035507202148438,
247
+ "accuracy": 0.6015625,
248
+ "epoch": 0.045,
249
+ "step": 18
250
+ },
251
+ {
252
+ "epoch": 0.0475,
253
+ "grad_norm": 10.379010200500488,
254
+ "learning_rate": 4.75e-06,
255
+ "loss": 0.62,
256
+ "step": 19
257
+ },
258
+ {
259
+ "Batch Mean": 4.241037845611572,
260
+ "accuracy": 0.7421875,
261
+ "epoch": 0.0475,
262
+ "step": 19
263
+ },
264
+ {
265
+ "epoch": 0.05,
266
+ "grad_norm": 8.072366714477539,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6094,
269
+ "step": 20
270
+ },
271
+ {
272
+ "Batch Mean": 4.397010803222656,
273
+ "accuracy": 0.65625,
274
+ "epoch": 0.05,
275
+ "step": 20
276
+ },
277
+ {
278
+ "epoch": 0.0525,
279
+ "grad_norm": 7.2537384033203125,
280
+ "learning_rate": 4.986842105263158e-06,
281
+ "loss": 0.5916,
282
+ "step": 21
283
+ },
284
+ {
285
+ "Batch Mean": 4.36688232421875,
286
+ "accuracy": 0.671875,
287
+ "epoch": 0.0525,
288
+ "step": 21
289
+ },
290
+ {
291
+ "epoch": 0.055,
292
+ "grad_norm": 8.559549331665039,
293
+ "learning_rate": 4.973684210526316e-06,
294
+ "loss": 0.5884,
295
+ "step": 22
296
+ },
297
+ {
298
+ "Batch Mean": 4.482940673828125,
299
+ "accuracy": 0.6640625,
300
+ "epoch": 0.055,
301
+ "step": 22
302
+ },
303
+ {
304
+ "epoch": 0.0575,
305
+ "grad_norm": 8.731099128723145,
306
+ "learning_rate": 4.960526315789474e-06,
307
+ "loss": 0.6106,
308
+ "step": 23
309
+ },
310
+ {
311
+ "Batch Mean": 4.41278076171875,
312
+ "accuracy": 0.7109375,
313
+ "epoch": 0.0575,
314
+ "step": 23
315
+ },
316
+ {
317
+ "epoch": 0.06,
318
+ "grad_norm": 6.149895191192627,
319
+ "learning_rate": 4.947368421052632e-06,
320
+ "loss": 0.5569,
321
+ "step": 24
322
+ },
323
+ {
324
+ "Batch Mean": 4.1328277587890625,
325
+ "accuracy": 0.6484375,
326
+ "epoch": 0.06,
327
+ "step": 24
328
+ },
329
+ {
330
+ "epoch": 0.0625,
331
+ "grad_norm": 6.8678879737854,
332
+ "learning_rate": 4.9342105263157895e-06,
333
+ "loss": 0.5729,
334
+ "step": 25
335
+ },
336
+ {
337
+ "Batch Mean": 3.8360061645507812,
338
+ "accuracy": 0.6484375,
339
+ "epoch": 0.0625,
340
+ "step": 25
341
+ },
342
+ {
343
+ "epoch": 0.065,
344
+ "grad_norm": 6.591639041900635,
345
+ "learning_rate": 4.921052631578948e-06,
346
+ "loss": 0.5902,
347
+ "step": 26
348
+ },
349
+ {
350
+ "Batch Mean": 3.9048538208007812,
351
+ "accuracy": 0.6953125,
352
+ "epoch": 0.065,
353
+ "step": 26
354
+ },
355
+ {
356
+ "epoch": 0.0675,
357
+ "grad_norm": 5.855933666229248,
358
+ "learning_rate": 4.907894736842106e-06,
359
+ "loss": 0.5666,
360
+ "step": 27
361
+ },
362
+ {
363
+ "Batch Mean": 3.7672348022460938,
364
+ "accuracy": 0.6953125,
365
+ "epoch": 0.0675,
366
+ "step": 27
367
+ },
368
+ {
369
+ "epoch": 0.07,
370
+ "grad_norm": 5.393594264984131,
371
+ "learning_rate": 4.894736842105264e-06,
372
+ "loss": 0.5508,
373
+ "step": 28
374
+ },
375
+ {
376
+ "Batch Mean": 3.723773956298828,
377
+ "accuracy": 0.65625,
378
+ "epoch": 0.07,
379
+ "step": 28
380
+ },
381
+ {
382
+ "epoch": 0.0725,
383
+ "grad_norm": 5.428353786468506,
384
+ "learning_rate": 4.881578947368422e-06,
385
+ "loss": 0.5694,
386
+ "step": 29
387
+ },
388
+ {
389
+ "Batch Mean": 3.7498779296875,
390
+ "accuracy": 0.6953125,
391
+ "epoch": 0.0725,
392
+ "step": 29
393
+ },
394
+ {
395
+ "epoch": 0.075,
396
+ "grad_norm": 5.005551338195801,
397
+ "learning_rate": 4.8684210526315795e-06,
398
+ "loss": 0.5905,
399
+ "step": 30
400
+ },
401
+ {
402
+ "Batch Mean": 3.564330577850342,
403
+ "accuracy": 0.671875,
404
+ "epoch": 0.075,
405
+ "step": 30
406
+ },
407
+ {
408
+ "epoch": 0.0775,
409
+ "grad_norm": 6.4090681076049805,
410
+ "learning_rate": 4.855263157894737e-06,
411
+ "loss": 0.5901,
412
+ "step": 31
413
+ },
414
+ {
415
+ "Batch Mean": 3.5886306762695312,
416
+ "accuracy": 0.7421875,
417
+ "epoch": 0.0775,
418
+ "step": 31
419
+ },
420
+ {
421
+ "epoch": 0.08,
422
+ "grad_norm": 6.025192737579346,
423
+ "learning_rate": 4.842105263157895e-06,
424
+ "loss": 0.5265,
425
+ "step": 32
426
+ },
427
+ {
428
+ "Batch Mean": 3.64593505859375,
429
+ "accuracy": 0.6953125,
430
+ "epoch": 0.08,
431
+ "step": 32
432
+ },
433
+ {
434
+ "epoch": 0.0825,
435
+ "grad_norm": 6.129398345947266,
436
+ "learning_rate": 4.828947368421053e-06,
437
+ "loss": 0.5083,
438
+ "step": 33
439
+ },
440
+ {
441
+ "Batch Mean": 3.5973358154296875,
442
+ "accuracy": 0.6875,
443
+ "epoch": 0.0825,
444
+ "step": 33
445
+ },
446
+ {
447
+ "epoch": 0.085,
448
+ "grad_norm": 6.91660737991333,
449
+ "learning_rate": 4.815789473684211e-06,
450
+ "loss": 0.5365,
451
+ "step": 34
452
+ },
453
+ {
454
+ "Batch Mean": 3.6286163330078125,
455
+ "accuracy": 0.7109375,
456
+ "epoch": 0.085,
457
+ "step": 34
458
+ },
459
+ {
460
+ "epoch": 0.0875,
461
+ "grad_norm": 7.553361892700195,
462
+ "learning_rate": 4.802631578947369e-06,
463
+ "loss": 0.5196,
464
+ "step": 35
465
+ },
466
+ {
467
+ "Batch Mean": 3.5937328338623047,
468
+ "accuracy": 0.7109375,
469
+ "epoch": 0.0875,
470
+ "step": 35
471
+ },
472
+ {
473
+ "epoch": 0.09,
474
+ "grad_norm": 7.884591579437256,
475
+ "learning_rate": 4.789473684210527e-06,
476
+ "loss": 0.5533,
477
+ "step": 36
478
+ },
479
+ {
480
+ "Batch Mean": 3.28558349609375,
481
+ "accuracy": 0.6796875,
482
+ "epoch": 0.09,
483
+ "step": 36
484
+ },
485
+ {
486
+ "epoch": 0.0925,
487
+ "grad_norm": 8.118135452270508,
488
+ "learning_rate": 4.7763157894736844e-06,
489
+ "loss": 0.5145,
490
+ "step": 37
491
+ },
492
+ {
493
+ "Batch Mean": 3.079477310180664,
494
+ "accuracy": 0.7421875,
495
+ "epoch": 0.0925,
496
+ "step": 37
497
+ },
498
+ {
499
+ "epoch": 0.095,
500
+ "grad_norm": 10.431463241577148,
501
+ "learning_rate": 4.763157894736842e-06,
502
+ "loss": 0.6,
503
+ "step": 38
504
+ },
505
+ {
506
+ "Batch Mean": 2.9296703338623047,
507
+ "accuracy": 0.7578125,
508
+ "epoch": 0.095,
509
+ "step": 38
510
+ },
511
+ {
512
+ "epoch": 0.0975,
513
+ "grad_norm": 8.055816650390625,
514
+ "learning_rate": 4.75e-06,
515
+ "loss": 0.445,
516
+ "step": 39
517
+ },
518
+ {
519
+ "Batch Mean": 2.9282093048095703,
520
+ "accuracy": 0.7109375,
521
+ "epoch": 0.0975,
522
+ "step": 39
523
+ },
524
+ {
525
+ "epoch": 0.1,
526
+ "grad_norm": 9.155073165893555,
527
+ "learning_rate": 4.736842105263158e-06,
528
+ "loss": 0.5568,
529
+ "step": 40
530
+ },
531
+ {
532
+ "Batch Mean": 2.4473862648010254,
533
+ "accuracy": 0.6171875,
534
+ "epoch": 0.1,
535
+ "step": 40
536
+ },
537
+ {
538
+ "epoch": 0.1025,
539
+ "grad_norm": 8.89163589477539,
540
+ "learning_rate": 4.723684210526316e-06,
541
+ "loss": 0.5934,
542
+ "step": 41
543
+ },
544
+ {
545
+ "Batch Mean": 2.4439845085144043,
546
+ "accuracy": 0.6953125,
547
+ "epoch": 0.1025,
548
+ "step": 41
549
+ },
550
+ {
551
+ "epoch": 0.105,
552
+ "grad_norm": 7.411705017089844,
553
+ "learning_rate": 4.710526315789474e-06,
554
+ "loss": 0.5522,
555
+ "step": 42
556
+ },
557
+ {
558
+ "Batch Mean": 1.7335999011993408,
559
+ "accuracy": 0.734375,
560
+ "epoch": 0.105,
561
+ "step": 42
562
+ },
563
+ {
564
+ "epoch": 0.1075,
565
+ "grad_norm": 7.0730109214782715,
566
+ "learning_rate": 4.697368421052632e-06,
567
+ "loss": 0.5157,
568
+ "step": 43
569
+ },
570
+ {
571
+ "Batch Mean": 1.7379779815673828,
572
+ "accuracy": 0.71875,
573
+ "epoch": 0.1075,
574
+ "step": 43
575
+ },
576
+ {
577
+ "epoch": 0.11,
578
+ "grad_norm": 7.879677772521973,
579
+ "learning_rate": 4.68421052631579e-06,
580
+ "loss": 0.5405,
581
+ "step": 44
582
+ },
583
+ {
584
+ "Batch Mean": 1.7085151672363281,
585
+ "accuracy": 0.6796875,
586
+ "epoch": 0.11,
587
+ "step": 44
588
+ },
589
+ {
590
+ "epoch": 0.1125,
591
+ "grad_norm": 6.630401611328125,
592
+ "learning_rate": 4.671052631578948e-06,
593
+ "loss": 0.564,
594
+ "step": 45
595
+ },
596
+ {
597
+ "Batch Mean": 1.7431907653808594,
598
+ "accuracy": 0.734375,
599
+ "epoch": 0.1125,
600
+ "step": 45
601
+ },
602
+ {
603
+ "epoch": 0.115,
604
+ "grad_norm": 6.569342136383057,
605
+ "learning_rate": 4.657894736842106e-06,
606
+ "loss": 0.4969,
607
+ "step": 46
608
+ },
609
+ {
610
+ "Batch Mean": 2.4792041778564453,
611
+ "accuracy": 0.6953125,
612
+ "epoch": 0.115,
613
+ "step": 46
614
+ },
615
+ {
616
+ "epoch": 0.1175,
617
+ "grad_norm": 6.198298931121826,
618
+ "learning_rate": 4.6447368421052635e-06,
619
+ "loss": 0.5501,
620
+ "step": 47
621
+ },
622
+ {
623
+ "Batch Mean": 2.4960689544677734,
624
+ "accuracy": 0.7578125,
625
+ "epoch": 0.1175,
626
+ "step": 47
627
+ },
628
+ {
629
+ "epoch": 0.12,
630
+ "grad_norm": 5.984739780426025,
631
+ "learning_rate": 4.631578947368421e-06,
632
+ "loss": 0.4513,
633
+ "step": 48
634
+ },
635
+ {
636
+ "Batch Mean": 2.7437705993652344,
637
+ "accuracy": 0.71875,
638
+ "epoch": 0.12,
639
+ "step": 48
640
+ },
641
+ {
642
+ "epoch": 0.1225,
643
+ "grad_norm": 6.669623374938965,
644
+ "learning_rate": 4.618421052631579e-06,
645
+ "loss": 0.5404,
646
+ "step": 49
647
+ },
648
+ {
649
+ "Batch Mean": 2.672210693359375,
650
+ "accuracy": 0.75,
651
+ "epoch": 0.1225,
652
+ "step": 49
653
+ },
654
+ {
655
+ "epoch": 0.125,
656
+ "grad_norm": 6.217676639556885,
657
+ "learning_rate": 4.605263157894737e-06,
658
+ "loss": 0.4668,
659
+ "step": 50
660
+ },
661
+ {
662
+ "Batch Mean": 2.7935009002685547,
663
+ "accuracy": 0.75,
664
+ "epoch": 0.125,
665
+ "step": 50
666
+ },
667
+ {
668
+ "epoch": 0.1275,
669
+ "grad_norm": 7.666802883148193,
670
+ "learning_rate": 4.592105263157895e-06,
671
+ "loss": 0.5491,
672
+ "step": 51
673
+ },
674
+ {
675
+ "Batch Mean": 2.651923179626465,
676
+ "accuracy": 0.734375,
677
+ "epoch": 0.1275,
678
+ "step": 51
679
+ },
680
+ {
681
+ "epoch": 0.13,
682
+ "grad_norm": 9.799866676330566,
683
+ "learning_rate": 4.578947368421053e-06,
684
+ "loss": 0.5173,
685
+ "step": 52
686
+ },
687
+ {
688
+ "Batch Mean": 2.9287376403808594,
689
+ "accuracy": 0.734375,
690
+ "epoch": 0.13,
691
+ "step": 52
692
+ },
693
+ {
694
+ "epoch": 0.1325,
695
+ "grad_norm": 8.577540397644043,
696
+ "learning_rate": 4.565789473684211e-06,
697
+ "loss": 0.5279,
698
+ "step": 53
699
+ },
700
+ {
701
+ "Batch Mean": 3.0377674102783203,
702
+ "accuracy": 0.7265625,
703
+ "epoch": 0.1325,
704
+ "step": 53
705
+ },
706
+ {
707
+ "epoch": 0.135,
708
+ "grad_norm": 8.099453926086426,
709
+ "learning_rate": 4.552631578947369e-06,
710
+ "loss": 0.5122,
711
+ "step": 54
712
+ },
713
+ {
714
+ "Batch Mean": 3.3550057411193848,
715
+ "accuracy": 0.6953125,
716
+ "epoch": 0.135,
717
+ "step": 54
718
+ },
719
+ {
720
+ "epoch": 0.1375,
721
+ "grad_norm": 9.597841262817383,
722
+ "learning_rate": 4.539473684210527e-06,
723
+ "loss": 0.5034,
724
+ "step": 55
725
+ },
726
+ {
727
+ "Batch Mean": 3.3833670616149902,
728
+ "accuracy": 0.7578125,
729
+ "epoch": 0.1375,
730
+ "step": 55
731
+ },
732
+ {
733
+ "epoch": 0.14,
734
+ "grad_norm": 9.208806037902832,
735
+ "learning_rate": 4.526315789473685e-06,
736
+ "loss": 0.53,
737
+ "step": 56
738
+ },
739
+ {
740
+ "Batch Mean": 3.255979537963867,
741
+ "accuracy": 0.7890625,
742
+ "epoch": 0.14,
743
+ "step": 56
744
+ },
745
+ {
746
+ "epoch": 0.1425,
747
+ "grad_norm": 7.923739910125732,
748
+ "learning_rate": 4.513157894736843e-06,
749
+ "loss": 0.4315,
750
+ "step": 57
751
+ },
752
+ {
753
+ "Batch Mean": 3.003221273422241,
754
+ "accuracy": 0.7265625,
755
+ "epoch": 0.1425,
756
+ "step": 57
757
+ },
758
+ {
759
+ "epoch": 0.145,
760
+ "grad_norm": 8.64991569519043,
761
+ "learning_rate": 4.5e-06,
762
+ "loss": 0.5038,
763
+ "step": 58
764
+ },
765
+ {
766
+ "Batch Mean": 3.122058868408203,
767
+ "accuracy": 0.78125,
768
+ "epoch": 0.145,
769
+ "step": 58
770
+ },
771
+ {
772
+ "epoch": 0.1475,
773
+ "grad_norm": 8.633460998535156,
774
+ "learning_rate": 4.4868421052631584e-06,
775
+ "loss": 0.4886,
776
+ "step": 59
777
+ },
778
+ {
779
+ "Batch Mean": 2.8752236366271973,
780
+ "accuracy": 0.7109375,
781
+ "epoch": 0.1475,
782
+ "step": 59
783
+ },
784
+ {
785
+ "epoch": 0.15,
786
+ "grad_norm": 8.399279594421387,
787
+ "learning_rate": 4.473684210526316e-06,
788
+ "loss": 0.5239,
789
+ "step": 60
790
+ },
791
+ {
792
+ "Batch Mean": 2.694100856781006,
793
+ "accuracy": 0.7578125,
794
+ "epoch": 0.15,
795
+ "step": 60
796
+ },
797
+ {
798
+ "epoch": 0.1525,
799
+ "grad_norm": 7.846778869628906,
800
+ "learning_rate": 4.460526315789474e-06,
801
+ "loss": 0.4538,
802
+ "step": 61
803
+ },
804
+ {
805
+ "Batch Mean": 2.59914493560791,
806
+ "accuracy": 0.8046875,
807
+ "epoch": 0.1525,
808
+ "step": 61
809
+ },
810
+ {
811
+ "epoch": 0.155,
812
+ "grad_norm": 7.844125270843506,
813
+ "learning_rate": 4.447368421052632e-06,
814
+ "loss": 0.4234,
815
+ "step": 62
816
+ },
817
+ {
818
+ "Batch Mean": 2.431262493133545,
819
+ "accuracy": 0.75,
820
+ "epoch": 0.155,
821
+ "step": 62
822
+ },
823
+ {
824
+ "epoch": 0.1575,
825
+ "grad_norm": 8.15548038482666,
826
+ "learning_rate": 4.43421052631579e-06,
827
+ "loss": 0.4695,
828
+ "step": 63
829
+ },
830
+ {
831
+ "Batch Mean": 2.162135124206543,
832
+ "accuracy": 0.7421875,
833
+ "epoch": 0.1575,
834
+ "step": 63
835
+ },
836
+ {
837
+ "epoch": 0.16,
838
+ "grad_norm": 9.166322708129883,
839
+ "learning_rate": 4.4210526315789476e-06,
840
+ "loss": 0.4898,
841
+ "step": 64
842
+ },
843
+ {
844
+ "Batch Mean": 1.8282737731933594,
845
+ "accuracy": 0.75,
846
+ "epoch": 0.16,
847
+ "step": 64
848
+ },
849
+ {
850
+ "epoch": 0.1625,
851
+ "grad_norm": 9.52655029296875,
852
+ "learning_rate": 4.407894736842105e-06,
853
+ "loss": 0.4651,
854
+ "step": 65
855
+ },
856
+ {
857
+ "Batch Mean": 1.9480819702148438,
858
+ "accuracy": 0.7890625,
859
+ "epoch": 0.1625,
860
+ "step": 65
861
+ },
862
+ {
863
+ "epoch": 0.165,
864
+ "grad_norm": 8.491720199584961,
865
+ "learning_rate": 4.394736842105263e-06,
866
+ "loss": 0.4578,
867
+ "step": 66
868
+ },
869
+ {
870
+ "Batch Mean": 1.8442394733428955,
871
+ "accuracy": 0.7734375,
872
+ "epoch": 0.165,
873
+ "step": 66
874
+ },
875
+ {
876
+ "epoch": 0.1675,
877
+ "grad_norm": 9.01707649230957,
878
+ "learning_rate": 4.381578947368421e-06,
879
+ "loss": 0.4858,
880
+ "step": 67
881
+ },
882
+ {
883
+ "Batch Mean": 1.2759554386138916,
884
+ "accuracy": 0.6953125,
885
+ "epoch": 0.1675,
886
+ "step": 67
887
+ },
888
+ {
889
+ "epoch": 0.17,
890
+ "grad_norm": 10.790990829467773,
891
+ "learning_rate": 4.368421052631579e-06,
892
+ "loss": 0.5368,
893
+ "step": 68
894
+ },
895
+ {
896
+ "Batch Mean": 0.916658878326416,
897
+ "accuracy": 0.7109375,
898
+ "epoch": 0.17,
899
+ "step": 68
900
+ },
901
+ {
902
+ "epoch": 0.1725,
903
+ "grad_norm": 10.27574634552002,
904
+ "learning_rate": 4.3552631578947375e-06,
905
+ "loss": 0.5475,
906
+ "step": 69
907
+ },
908
+ {
909
+ "Batch Mean": 0.9389474391937256,
910
+ "accuracy": 0.6875,
911
+ "epoch": 0.1725,
912
+ "step": 69
913
+ },
914
+ {
915
+ "epoch": 0.175,
916
+ "grad_norm": 9.463624954223633,
917
+ "learning_rate": 4.342105263157895e-06,
918
+ "loss": 0.5295,
919
+ "step": 70
920
+ },
921
+ {
922
+ "Batch Mean": 0.6801865100860596,
923
+ "accuracy": 0.78125,
924
+ "epoch": 0.175,
925
+ "step": 70
926
+ },
927
+ {
928
+ "epoch": 0.1775,
929
+ "grad_norm": 7.813968658447266,
930
+ "learning_rate": 4.328947368421053e-06,
931
+ "loss": 0.4602,
932
+ "step": 71
933
+ },
934
+ {
935
+ "Batch Mean": 0.6634016036987305,
936
+ "accuracy": 0.78125,
937
+ "epoch": 0.1775,
938
+ "step": 71
939
+ },
940
+ {
941
+ "epoch": 0.18,
942
+ "grad_norm": 7.322629928588867,
943
+ "learning_rate": 4.315789473684211e-06,
944
+ "loss": 0.4328,
945
+ "step": 72
946
+ },
947
+ {
948
+ "Batch Mean": 0.518225908279419,
949
+ "accuracy": 0.8359375,
950
+ "epoch": 0.18,
951
+ "step": 72
952
+ },
953
+ {
954
+ "epoch": 0.1825,
955
+ "grad_norm": 7.121971130371094,
956
+ "learning_rate": 4.302631578947369e-06,
957
+ "loss": 0.3997,
958
+ "step": 73
959
+ },
960
+ {
961
+ "Batch Mean": 0.6286078691482544,
962
+ "accuracy": 0.75,
963
+ "epoch": 0.1825,
964
+ "step": 73
965
+ },
966
+ {
967
+ "epoch": 0.185,
968
+ "grad_norm": 8.812067031860352,
969
+ "learning_rate": 4.289473684210527e-06,
970
+ "loss": 0.5345,
971
+ "step": 74
972
+ },
973
+ {
974
+ "Batch Mean": 0.4055500030517578,
975
+ "accuracy": 0.78125,
976
+ "epoch": 0.185,
977
+ "step": 74
978
+ },
979
+ {
980
+ "epoch": 0.1875,
981
+ "grad_norm": 8.031818389892578,
982
+ "learning_rate": 4.276315789473684e-06,
983
+ "loss": 0.4436,
984
+ "step": 75
985
+ },
986
+ {
987
+ "Batch Mean": 0.6844688057899475,
988
+ "accuracy": 0.6640625,
989
+ "epoch": 0.1875,
990
+ "step": 75
991
+ },
992
+ {
993
+ "epoch": 0.19,
994
+ "grad_norm": 9.14492130279541,
995
+ "learning_rate": 4.2631578947368425e-06,
996
+ "loss": 0.5727,
997
+ "step": 76
998
+ },
999
+ {
1000
+ "Batch Mean": 0.549891471862793,
1001
+ "accuracy": 0.7578125,
1002
+ "epoch": 0.19,
1003
+ "step": 76
1004
+ },
1005
+ {
1006
+ "epoch": 0.1925,
1007
+ "grad_norm": 8.721407890319824,
1008
+ "learning_rate": 4.25e-06,
1009
+ "loss": 0.4997,
1010
+ "step": 77
1011
+ },
1012
+ {
1013
+ "Batch Mean": 0.3632768988609314,
1014
+ "accuracy": 0.703125,
1015
+ "epoch": 0.1925,
1016
+ "step": 77
1017
+ },
1018
+ {
1019
+ "epoch": 0.195,
1020
+ "grad_norm": 8.776328086853027,
1021
+ "learning_rate": 4.236842105263158e-06,
1022
+ "loss": 0.5442,
1023
+ "step": 78
1024
+ },
1025
+ {
1026
+ "Batch Mean": 0.4604153633117676,
1027
+ "accuracy": 0.7421875,
1028
+ "epoch": 0.195,
1029
+ "step": 78
1030
+ },
1031
+ {
1032
+ "epoch": 0.1975,
1033
+ "grad_norm": 7.281062126159668,
1034
+ "learning_rate": 4.223684210526316e-06,
1035
+ "loss": 0.4793,
1036
+ "step": 79
1037
+ },
1038
+ {
1039
+ "Batch Mean": 0.605268120765686,
1040
+ "accuracy": 0.765625,
1041
+ "epoch": 0.1975,
1042
+ "step": 79
1043
+ },
1044
+ {
1045
+ "epoch": 0.2,
1046
+ "grad_norm": 7.533178329467773,
1047
+ "learning_rate": 4.210526315789474e-06,
1048
+ "loss": 0.4338,
1049
+ "step": 80
1050
+ },
1051
+ {
1052
+ "Batch Mean": 0.9789919257164001,
1053
+ "accuracy": 0.75,
1054
+ "epoch": 0.2,
1055
+ "step": 80
1056
+ },
1057
+ {
1058
+ "epoch": 0.2025,
1059
+ "grad_norm": 7.2433671951293945,
1060
+ "learning_rate": 4.197368421052632e-06,
1061
+ "loss": 0.4785,
1062
+ "step": 81
1063
+ },
1064
+ {
1065
+ "Batch Mean": 1.114579200744629,
1066
+ "accuracy": 0.71875,
1067
+ "epoch": 0.2025,
1068
+ "step": 81
1069
+ },
1070
+ {
1071
+ "epoch": 0.205,
1072
+ "grad_norm": 7.2934064865112305,
1073
+ "learning_rate": 4.18421052631579e-06,
1074
+ "loss": 0.4836,
1075
+ "step": 82
1076
+ },
1077
+ {
1078
+ "Batch Mean": 1.0528812408447266,
1079
+ "accuracy": 0.7578125,
1080
+ "epoch": 0.205,
1081
+ "step": 82
1082
+ },
1083
+ {
1084
+ "epoch": 0.2075,
1085
+ "grad_norm": 7.544822692871094,
1086
+ "learning_rate": 4.171052631578948e-06,
1087
+ "loss": 0.5077,
1088
+ "step": 83
1089
+ },
1090
+ {
1091
+ "Batch Mean": 1.1365894079208374,
1092
+ "accuracy": 0.671875,
1093
+ "epoch": 0.2075,
1094
+ "step": 83
1095
+ },
1096
+ {
1097
+ "epoch": 0.21,
1098
+ "grad_norm": 8.340349197387695,
1099
+ "learning_rate": 4.157894736842106e-06,
1100
+ "loss": 0.579,
1101
+ "step": 84
1102
+ },
1103
+ {
1104
+ "Batch Mean": 1.7320103645324707,
1105
+ "accuracy": 0.8125,
1106
+ "epoch": 0.21,
1107
+ "step": 84
1108
+ },
1109
+ {
1110
+ "epoch": 0.2125,
1111
+ "grad_norm": 6.645724296569824,
1112
+ "learning_rate": 4.144736842105263e-06,
1113
+ "loss": 0.4114,
1114
+ "step": 85
1115
+ },
1116
+ {
1117
+ "Batch Mean": 1.443530559539795,
1118
+ "accuracy": 0.7578125,
1119
+ "epoch": 0.2125,
1120
+ "step": 85
1121
+ },
1122
+ {
1123
+ "epoch": 0.215,
1124
+ "grad_norm": 6.647582530975342,
1125
+ "learning_rate": 4.1315789473684216e-06,
1126
+ "loss": 0.4369,
1127
+ "step": 86
1128
+ },
1129
+ {
1130
+ "Batch Mean": 1.5358202457427979,
1131
+ "accuracy": 0.7578125,
1132
+ "epoch": 0.215,
1133
+ "step": 86
1134
+ },
1135
+ {
1136
+ "epoch": 0.2175,
1137
+ "grad_norm": 7.315903186798096,
1138
+ "learning_rate": 4.118421052631579e-06,
1139
+ "loss": 0.4895,
1140
+ "step": 87
1141
+ },
1142
+ {
1143
+ "Batch Mean": 1.7256877422332764,
1144
+ "accuracy": 0.7734375,
1145
+ "epoch": 0.2175,
1146
+ "step": 87
1147
+ },
1148
+ {
1149
+ "epoch": 0.22,
1150
+ "grad_norm": 8.285420417785645,
1151
+ "learning_rate": 4.105263157894737e-06,
1152
+ "loss": 0.5035,
1153
+ "step": 88
1154
+ },
1155
+ {
1156
+ "Batch Mean": 1.5997413396835327,
1157
+ "accuracy": 0.75,
1158
+ "epoch": 0.22,
1159
+ "step": 88
1160
+ },
1161
+ {
1162
+ "epoch": 0.2225,
1163
+ "grad_norm": 7.990715026855469,
1164
+ "learning_rate": 4.092105263157895e-06,
1165
+ "loss": 0.51,
1166
+ "step": 89
1167
+ },
1168
+ {
1169
+ "Batch Mean": 1.6425485610961914,
1170
+ "accuracy": 0.734375,
1171
+ "epoch": 0.2225,
1172
+ "step": 89
1173
+ },
1174
+ {
1175
+ "epoch": 0.225,
1176
+ "grad_norm": 8.72641658782959,
1177
+ "learning_rate": 4.078947368421053e-06,
1178
+ "loss": 0.4908,
1179
+ "step": 90
1180
+ },
1181
+ {
1182
+ "Batch Mean": 1.9212679862976074,
1183
+ "accuracy": 0.84375,
1184
+ "epoch": 0.225,
1185
+ "step": 90
1186
+ },
1187
+ {
1188
+ "epoch": 0.2275,
1189
+ "grad_norm": 7.567220211029053,
1190
+ "learning_rate": 4.065789473684211e-06,
1191
+ "loss": 0.4152,
1192
+ "step": 91
1193
+ },
1194
+ {
1195
+ "Batch Mean": 1.6822540760040283,
1196
+ "accuracy": 0.8046875,
1197
+ "epoch": 0.2275,
1198
+ "step": 91
1199
+ },
1200
+ {
1201
+ "epoch": 0.23,
1202
+ "grad_norm": 7.402642726898193,
1203
+ "learning_rate": 4.052631578947368e-06,
1204
+ "loss": 0.4054,
1205
+ "step": 92
1206
+ },
1207
+ {
1208
+ "Batch Mean": 1.5377750396728516,
1209
+ "accuracy": 0.75,
1210
+ "epoch": 0.23,
1211
+ "step": 92
1212
+ },
1213
+ {
1214
+ "epoch": 0.2325,
1215
+ "grad_norm": 8.574016571044922,
1216
+ "learning_rate": 4.0394736842105265e-06,
1217
+ "loss": 0.4739,
1218
+ "step": 93
1219
+ },
1220
+ {
1221
+ "Batch Mean": 1.332385540008545,
1222
+ "accuracy": 0.734375,
1223
+ "epoch": 0.2325,
1224
+ "step": 93
1225
+ },
1226
+ {
1227
+ "epoch": 0.235,
1228
+ "grad_norm": 8.827500343322754,
1229
+ "learning_rate": 4.026315789473684e-06,
1230
+ "loss": 0.4983,
1231
+ "step": 94
1232
+ },
1233
+ {
1234
+ "Batch Mean": 1.0707147121429443,
1235
+ "accuracy": 0.8046875,
1236
+ "epoch": 0.235,
1237
+ "step": 94
1238
+ },
1239
+ {
1240
+ "epoch": 0.2375,
1241
+ "grad_norm": 7.975078105926514,
1242
+ "learning_rate": 4.013157894736842e-06,
1243
+ "loss": 0.4709,
1244
+ "step": 95
1245
+ },
1246
+ {
1247
+ "Batch Mean": 1.1354491710662842,
1248
+ "accuracy": 0.75,
1249
+ "epoch": 0.2375,
1250
+ "step": 95
1251
+ },
1252
+ {
1253
+ "epoch": 0.24,
1254
+ "grad_norm": 7.764720916748047,
1255
+ "learning_rate": 4.000000000000001e-06,
1256
+ "loss": 0.4697,
1257
+ "step": 96
1258
+ },
1259
+ {
1260
+ "Batch Mean": 0.7834959030151367,
1261
+ "accuracy": 0.765625,
1262
+ "epoch": 0.24,
1263
+ "step": 96
1264
+ },
1265
+ {
1266
+ "epoch": 0.2425,
1267
+ "grad_norm": 8.38682746887207,
1268
+ "learning_rate": 3.986842105263158e-06,
1269
+ "loss": 0.46,
1270
+ "step": 97
1271
+ },
1272
+ {
1273
+ "Batch Mean": 0.9441508650779724,
1274
+ "accuracy": 0.8359375,
1275
+ "epoch": 0.2425,
1276
+ "step": 97
1277
+ },
1278
+ {
1279
+ "epoch": 0.245,
1280
+ "grad_norm": 8.565149307250977,
1281
+ "learning_rate": 3.9736842105263165e-06,
1282
+ "loss": 0.4071,
1283
+ "step": 98
1284
+ },
1285
+ {
1286
+ "Batch Mean": 0.8886473178863525,
1287
+ "accuracy": 0.8203125,
1288
+ "epoch": 0.245,
1289
+ "step": 98
1290
+ },
1291
+ {
1292
+ "epoch": 0.2475,
1293
+ "grad_norm": 7.316027641296387,
1294
+ "learning_rate": 3.960526315789474e-06,
1295
+ "loss": 0.413,
1296
+ "step": 99
1297
+ },
1298
+ {
1299
+ "Batch Mean": 1.3381073474884033,
1300
+ "accuracy": 0.765625,
1301
+ "epoch": 0.2475,
1302
+ "step": 99
1303
+ },
1304
+ {
1305
+ "epoch": 0.25,
1306
+ "grad_norm": 7.380762577056885,
1307
+ "learning_rate": 3.947368421052632e-06,
1308
+ "loss": 0.4639,
1309
+ "step": 100
1310
+ },
1311
+ {
1312
+ "Batch Mean": 1.8181347846984863,
1313
+ "accuracy": 0.78125,
1314
+ "epoch": 0.25,
1315
+ "step": 100
1316
+ },
1317
+ {
1318
+ "epoch": 0.2525,
1319
+ "grad_norm": 8.348108291625977,
1320
+ "learning_rate": 3.93421052631579e-06,
1321
+ "loss": 0.4568,
1322
+ "step": 101
1323
+ },
1324
+ {
1325
+ "Batch Mean": 1.850348711013794,
1326
+ "accuracy": 0.828125,
1327
+ "epoch": 0.2525,
1328
+ "step": 101
1329
+ },
1330
+ {
1331
+ "epoch": 0.255,
1332
+ "grad_norm": 7.533435821533203,
1333
+ "learning_rate": 3.921052631578947e-06,
1334
+ "loss": 0.4471,
1335
+ "step": 102
1336
+ },
1337
+ {
1338
+ "Batch Mean": 1.8302688598632812,
1339
+ "accuracy": 0.7265625,
1340
+ "epoch": 0.255,
1341
+ "step": 102
1342
+ },
1343
+ {
1344
+ "epoch": 0.2575,
1345
+ "grad_norm": 7.560754776000977,
1346
+ "learning_rate": 3.907894736842106e-06,
1347
+ "loss": 0.4922,
1348
+ "step": 103
1349
+ },
1350
+ {
1351
+ "Batch Mean": 1.832013487815857,
1352
+ "accuracy": 0.7734375,
1353
+ "epoch": 0.2575,
1354
+ "step": 103
1355
+ },
1356
+ {
1357
+ "epoch": 0.26,
1358
+ "grad_norm": 8.4998197555542,
1359
+ "learning_rate": 3.894736842105263e-06,
1360
+ "loss": 0.4636,
1361
+ "step": 104
1362
+ },
1363
+ {
1364
+ "Batch Mean": 1.9380416870117188,
1365
+ "accuracy": 0.7421875,
1366
+ "epoch": 0.26,
1367
+ "step": 104
1368
+ },
1369
+ {
1370
+ "epoch": 0.2625,
1371
+ "grad_norm": 8.759364128112793,
1372
+ "learning_rate": 3.8815789473684214e-06,
1373
+ "loss": 0.5117,
1374
+ "step": 105
1375
+ },
1376
+ {
1377
+ "Batch Mean": 2.0537302494049072,
1378
+ "accuracy": 0.78125,
1379
+ "epoch": 0.2625,
1380
+ "step": 105
1381
+ },
1382
+ {
1383
+ "epoch": 0.265,
1384
+ "grad_norm": 7.300965785980225,
1385
+ "learning_rate": 3.868421052631579e-06,
1386
+ "loss": 0.3956,
1387
+ "step": 106
1388
+ },
1389
+ {
1390
+ "Batch Mean": 2.236231803894043,
1391
+ "accuracy": 0.7890625,
1392
+ "epoch": 0.265,
1393
+ "step": 106
1394
+ },
1395
+ {
1396
+ "epoch": 0.2675,
1397
+ "grad_norm": 7.826519012451172,
1398
+ "learning_rate": 3.855263157894737e-06,
1399
+ "loss": 0.462,
1400
+ "step": 107
1401
+ },
1402
+ {
1403
+ "Batch Mean": 2.2571160793304443,
1404
+ "accuracy": 0.78125,
1405
+ "epoch": 0.2675,
1406
+ "step": 107
1407
+ },
1408
+ {
1409
+ "epoch": 0.27,
1410
+ "grad_norm": 7.177440643310547,
1411
+ "learning_rate": 3.842105263157895e-06,
1412
+ "loss": 0.4264,
1413
+ "step": 108
1414
+ },
1415
+ {
1416
+ "Batch Mean": 2.3395166397094727,
1417
+ "accuracy": 0.8359375,
1418
+ "epoch": 0.27,
1419
+ "step": 108
1420
+ },
1421
+ {
1422
+ "epoch": 0.2725,
1423
+ "grad_norm": 7.556861877441406,
1424
+ "learning_rate": 3.828947368421053e-06,
1425
+ "loss": 0.3825,
1426
+ "step": 109
1427
+ },
1428
+ {
1429
+ "Batch Mean": 2.5364012718200684,
1430
+ "accuracy": 0.7890625,
1431
+ "epoch": 0.2725,
1432
+ "step": 109
1433
+ },
1434
+ {
1435
+ "epoch": 0.275,
1436
+ "grad_norm": 8.785236358642578,
1437
+ "learning_rate": 3.815789473684211e-06,
1438
+ "loss": 0.4915,
1439
+ "step": 110
1440
+ },
1441
+ {
1442
+ "Batch Mean": 2.545170783996582,
1443
+ "accuracy": 0.71875,
1444
+ "epoch": 0.275,
1445
+ "step": 110
1446
+ },
1447
+ {
1448
+ "epoch": 0.2775,
1449
+ "grad_norm": 8.062837600708008,
1450
+ "learning_rate": 3.802631578947369e-06,
1451
+ "loss": 0.5025,
1452
+ "step": 111
1453
+ },
1454
+ {
1455
+ "Batch Mean": 2.6232008934020996,
1456
+ "accuracy": 0.7734375,
1457
+ "epoch": 0.2775,
1458
+ "step": 111
1459
+ },
1460
+ {
1461
+ "epoch": 0.28,
1462
+ "grad_norm": 7.3966498374938965,
1463
+ "learning_rate": 3.789473684210527e-06,
1464
+ "loss": 0.4145,
1465
+ "step": 112
1466
+ },
1467
+ {
1468
+ "Batch Mean": 2.351048469543457,
1469
+ "accuracy": 0.6953125,
1470
+ "epoch": 0.28,
1471
+ "step": 112
1472
+ },
1473
+ {
1474
+ "epoch": 0.2825,
1475
+ "grad_norm": 7.810081958770752,
1476
+ "learning_rate": 3.7763157894736847e-06,
1477
+ "loss": 0.5147,
1478
+ "step": 113
1479
+ },
1480
+ {
1481
+ "Batch Mean": 1.6083295345306396,
1482
+ "accuracy": 0.796875,
1483
+ "epoch": 0.2825,
1484
+ "step": 113
1485
+ },
1486
+ {
1487
+ "epoch": 0.285,
1488
+ "grad_norm": 6.8766703605651855,
1489
+ "learning_rate": 3.7631578947368426e-06,
1490
+ "loss": 0.4275,
1491
+ "step": 114
1492
+ },
1493
+ {
1494
+ "Batch Mean": 1.594513177871704,
1495
+ "accuracy": 0.8046875,
1496
+ "epoch": 0.285,
1497
+ "step": 114
1498
+ },
1499
+ {
1500
+ "epoch": 0.2875,
1501
+ "grad_norm": 7.07267427444458,
1502
+ "learning_rate": 3.7500000000000005e-06,
1503
+ "loss": 0.4197,
1504
+ "step": 115
1505
+ },
1506
+ {
1507
+ "Batch Mean": 1.6583623886108398,
1508
+ "accuracy": 0.7421875,
1509
+ "epoch": 0.2875,
1510
+ "step": 115
1511
+ },
1512
+ {
1513
+ "epoch": 0.29,
1514
+ "grad_norm": 8.415107727050781,
1515
+ "learning_rate": 3.736842105263158e-06,
1516
+ "loss": 0.4723,
1517
+ "step": 116
1518
+ },
1519
+ {
1520
+ "Batch Mean": 1.6947704553604126,
1521
+ "accuracy": 0.8203125,
1522
+ "epoch": 0.29,
1523
+ "step": 116
1524
+ },
1525
+ {
1526
+ "epoch": 0.2925,
1527
+ "grad_norm": 7.132028102874756,
1528
+ "learning_rate": 3.723684210526316e-06,
1529
+ "loss": 0.4039,
1530
+ "step": 117
1531
+ },
1532
+ {
1533
+ "Batch Mean": 1.7144229412078857,
1534
+ "accuracy": 0.8046875,
1535
+ "epoch": 0.2925,
1536
+ "step": 117
1537
+ },
1538
+ {
1539
+ "epoch": 0.295,
1540
+ "grad_norm": 6.850518703460693,
1541
+ "learning_rate": 3.710526315789474e-06,
1542
+ "loss": 0.4148,
1543
+ "step": 118
1544
+ },
1545
+ {
1546
+ "Batch Mean": 1.4002912044525146,
1547
+ "accuracy": 0.828125,
1548
+ "epoch": 0.295,
1549
+ "step": 118
1550
+ },
1551
+ {
1552
+ "epoch": 0.2975,
1553
+ "grad_norm": 7.008551120758057,
1554
+ "learning_rate": 3.6973684210526317e-06,
1555
+ "loss": 0.3972,
1556
+ "step": 119
1557
+ },
1558
+ {
1559
+ "Batch Mean": 1.1955918073654175,
1560
+ "accuracy": 0.7890625,
1561
+ "epoch": 0.2975,
1562
+ "step": 119
1563
+ },
1564
+ {
1565
+ "epoch": 0.3,
1566
+ "grad_norm": 8.176568984985352,
1567
+ "learning_rate": 3.6842105263157896e-06,
1568
+ "loss": 0.4894,
1569
+ "step": 120
1570
+ },
1571
+ {
1572
+ "Batch Mean": 1.4260971546173096,
1573
+ "accuracy": 0.765625,
1574
+ "epoch": 0.3,
1575
+ "step": 120
1576
+ },
1577
+ {
1578
+ "epoch": 0.3025,
1579
+ "grad_norm": 7.905389308929443,
1580
+ "learning_rate": 3.6710526315789476e-06,
1581
+ "loss": 0.4796,
1582
+ "step": 121
1583
+ },
1584
+ {
1585
+ "Batch Mean": 1.1381725072860718,
1586
+ "accuracy": 0.84375,
1587
+ "epoch": 0.3025,
1588
+ "step": 121
1589
+ },
1590
+ {
1591
+ "epoch": 0.305,
1592
+ "grad_norm": 7.464083194732666,
1593
+ "learning_rate": 3.657894736842106e-06,
1594
+ "loss": 0.387,
1595
+ "step": 122
1596
+ },
1597
+ {
1598
+ "Batch Mean": 1.064018726348877,
1599
+ "accuracy": 0.8125,
1600
+ "epoch": 0.305,
1601
+ "step": 122
1602
+ },
1603
+ {
1604
+ "epoch": 0.3075,
1605
+ "grad_norm": 8.280699729919434,
1606
+ "learning_rate": 3.644736842105264e-06,
1607
+ "loss": 0.4154,
1608
+ "step": 123
1609
+ },
1610
+ {
1611
+ "Batch Mean": 1.3708758354187012,
1612
+ "accuracy": 0.765625,
1613
+ "epoch": 0.3075,
1614
+ "step": 123
1615
+ },
1616
+ {
1617
+ "epoch": 0.31,
1618
+ "grad_norm": 9.830754280090332,
1619
+ "learning_rate": 3.6315789473684217e-06,
1620
+ "loss": 0.5003,
1621
+ "step": 124
1622
+ },
1623
+ {
1624
+ "Batch Mean": 1.162580132484436,
1625
+ "accuracy": 0.828125,
1626
+ "epoch": 0.31,
1627
+ "step": 124
1628
+ },
1629
+ {
1630
+ "epoch": 0.3125,
1631
+ "grad_norm": 8.671696662902832,
1632
+ "learning_rate": 3.618421052631579e-06,
1633
+ "loss": 0.4389,
1634
+ "step": 125
1635
+ },
1636
+ {
1637
+ "Batch Mean": 0.671147346496582,
1638
+ "accuracy": 0.8125,
1639
+ "epoch": 0.3125,
1640
+ "step": 125
1641
+ },
1642
+ {
1643
+ "epoch": 0.315,
1644
+ "grad_norm": 8.493339538574219,
1645
+ "learning_rate": 3.605263157894737e-06,
1646
+ "loss": 0.4434,
1647
+ "step": 126
1648
+ },
1649
+ {
1650
+ "Batch Mean": 0.8207384347915649,
1651
+ "accuracy": 0.8203125,
1652
+ "epoch": 0.315,
1653
+ "step": 126
1654
+ },
1655
+ {
1656
+ "epoch": 0.3175,
1657
+ "grad_norm": 8.274676322937012,
1658
+ "learning_rate": 3.592105263157895e-06,
1659
+ "loss": 0.4057,
1660
+ "step": 127
1661
+ },
1662
+ {
1663
+ "Batch Mean": 0.5156043767929077,
1664
+ "accuracy": 0.75,
1665
+ "epoch": 0.3175,
1666
+ "step": 127
1667
+ },
1668
+ {
1669
+ "epoch": 0.32,
1670
+ "grad_norm": 9.094855308532715,
1671
+ "learning_rate": 3.578947368421053e-06,
1672
+ "loss": 0.4661,
1673
+ "step": 128
1674
+ },
1675
+ {
1676
+ "Batch Mean": 0.43193674087524414,
1677
+ "accuracy": 0.8203125,
1678
+ "epoch": 0.32,
1679
+ "step": 128
1680
+ },
1681
+ {
1682
+ "epoch": 0.3225,
1683
+ "grad_norm": 8.729266166687012,
1684
+ "learning_rate": 3.565789473684211e-06,
1685
+ "loss": 0.4586,
1686
+ "step": 129
1687
+ },
1688
+ {
1689
+ "Batch Mean": 0.30504658818244934,
1690
+ "accuracy": 0.7421875,
1691
+ "epoch": 0.3225,
1692
+ "step": 129
1693
+ },
1694
+ {
1695
+ "epoch": 0.325,
1696
+ "grad_norm": 11.113021850585938,
1697
+ "learning_rate": 3.5526315789473687e-06,
1698
+ "loss": 0.4894,
1699
+ "step": 130
1700
+ },
1701
+ {
1702
+ "Batch Mean": 0.3271394371986389,
1703
+ "accuracy": 0.7734375,
1704
+ "epoch": 0.325,
1705
+ "step": 130
1706
+ },
1707
+ {
1708
+ "epoch": 0.3275,
1709
+ "grad_norm": 8.692556381225586,
1710
+ "learning_rate": 3.5394736842105266e-06,
1711
+ "loss": 0.4227,
1712
+ "step": 131
1713
+ },
1714
+ {
1715
+ "Batch Mean": 0.6269352436065674,
1716
+ "accuracy": 0.7734375,
1717
+ "epoch": 0.3275,
1718
+ "step": 131
1719
+ },
1720
+ {
1721
+ "epoch": 0.33,
1722
+ "grad_norm": 8.046867370605469,
1723
+ "learning_rate": 3.5263157894736846e-06,
1724
+ "loss": 0.496,
1725
+ "step": 132
1726
+ },
1727
+ {
1728
+ "Batch Mean": 0.6559182405471802,
1729
+ "accuracy": 0.765625,
1730
+ "epoch": 0.33,
1731
+ "step": 132
1732
+ },
1733
+ {
1734
+ "epoch": 0.3325,
1735
+ "grad_norm": 7.385076999664307,
1736
+ "learning_rate": 3.513157894736842e-06,
1737
+ "loss": 0.4459,
1738
+ "step": 133
1739
+ },
1740
+ {
1741
+ "Batch Mean": 0.5328922271728516,
1742
+ "accuracy": 0.7578125,
1743
+ "epoch": 0.3325,
1744
+ "step": 133
1745
+ },
1746
+ {
1747
+ "epoch": 0.335,
1748
+ "grad_norm": 7.108922481536865,
1749
+ "learning_rate": 3.5e-06,
1750
+ "loss": 0.428,
1751
+ "step": 134
1752
+ },
1753
+ {
1754
+ "Batch Mean": 1.1600193977355957,
1755
+ "accuracy": 0.828125,
1756
+ "epoch": 0.335,
1757
+ "step": 134
1758
+ },
1759
+ {
1760
+ "epoch": 0.3375,
1761
+ "grad_norm": 6.962152004241943,
1762
+ "learning_rate": 3.486842105263158e-06,
1763
+ "loss": 0.4237,
1764
+ "step": 135
1765
+ },
1766
+ {
1767
+ "Batch Mean": 1.1642009019851685,
1768
+ "accuracy": 0.6953125,
1769
+ "epoch": 0.3375,
1770
+ "step": 135
1771
+ },
1772
+ {
1773
+ "epoch": 0.34,
1774
+ "grad_norm": 7.879281520843506,
1775
+ "learning_rate": 3.473684210526316e-06,
1776
+ "loss": 0.528,
1777
+ "step": 136
1778
+ },
1779
+ {
1780
+ "Batch Mean": 1.0588830709457397,
1781
+ "accuracy": 0.6953125,
1782
+ "epoch": 0.34,
1783
+ "step": 136
1784
+ },
1785
+ {
1786
+ "epoch": 0.3425,
1787
+ "grad_norm": 9.492472648620605,
1788
+ "learning_rate": 3.460526315789474e-06,
1789
+ "loss": 0.5365,
1790
+ "step": 137
1791
+ },
1792
+ {
1793
+ "Batch Mean": 1.3413481712341309,
1794
+ "accuracy": 0.8046875,
1795
+ "epoch": 0.3425,
1796
+ "step": 137
1797
+ },
1798
+ {
1799
+ "epoch": 0.345,
1800
+ "grad_norm": 6.448349952697754,
1801
+ "learning_rate": 3.447368421052632e-06,
1802
+ "loss": 0.4449,
1803
+ "step": 138
1804
+ },
1805
+ {
1806
+ "Batch Mean": 1.3028790950775146,
1807
+ "accuracy": 0.7578125,
1808
+ "epoch": 0.345,
1809
+ "step": 138
1810
+ },
1811
+ {
1812
+ "epoch": 0.3475,
1813
+ "grad_norm": 6.54162073135376,
1814
+ "learning_rate": 3.43421052631579e-06,
1815
+ "loss": 0.4109,
1816
+ "step": 139
1817
+ },
1818
+ {
1819
+ "Batch Mean": 1.206446886062622,
1820
+ "accuracy": 0.7734375,
1821
+ "epoch": 0.3475,
1822
+ "step": 139
1823
+ },
1824
+ {
1825
+ "epoch": 0.35,
1826
+ "grad_norm": 7.594364166259766,
1827
+ "learning_rate": 3.421052631578948e-06,
1828
+ "loss": 0.4771,
1829
+ "step": 140
1830
+ },
1831
+ {
1832
+ "Batch Mean": 1.425430417060852,
1833
+ "accuracy": 0.7734375,
1834
+ "epoch": 0.35,
1835
+ "step": 140
1836
+ },
1837
+ {
1838
+ "epoch": 0.3525,
1839
+ "grad_norm": 6.744152069091797,
1840
+ "learning_rate": 3.4078947368421057e-06,
1841
+ "loss": 0.4458,
1842
+ "step": 141
1843
+ },
1844
+ {
1845
+ "Batch Mean": 1.4311294555664062,
1846
+ "accuracy": 0.765625,
1847
+ "epoch": 0.3525,
1848
+ "step": 141
1849
+ },
1850
+ {
1851
+ "epoch": 0.355,
1852
+ "grad_norm": 6.789750576019287,
1853
+ "learning_rate": 3.3947368421052636e-06,
1854
+ "loss": 0.4798,
1855
+ "step": 142
1856
+ },
1857
+ {
1858
+ "Batch Mean": 1.6251521110534668,
1859
+ "accuracy": 0.765625,
1860
+ "epoch": 0.355,
1861
+ "step": 142
1862
+ },
1863
+ {
1864
+ "epoch": 0.3575,
1865
+ "grad_norm": 7.658289909362793,
1866
+ "learning_rate": 3.381578947368421e-06,
1867
+ "loss": 0.5209,
1868
+ "step": 143
1869
+ },
1870
+ {
1871
+ "Batch Mean": 1.5901494026184082,
1872
+ "accuracy": 0.7890625,
1873
+ "epoch": 0.3575,
1874
+ "step": 143
1875
+ },
1876
+ {
1877
+ "epoch": 0.36,
1878
+ "grad_norm": 7.741049289703369,
1879
+ "learning_rate": 3.368421052631579e-06,
1880
+ "loss": 0.448,
1881
+ "step": 144
1882
+ },
1883
+ {
1884
+ "Batch Mean": 1.7485175132751465,
1885
+ "accuracy": 0.71875,
1886
+ "epoch": 0.36,
1887
+ "step": 144
1888
+ },
1889
+ {
1890
+ "epoch": 0.3625,
1891
+ "grad_norm": 7.933503150939941,
1892
+ "learning_rate": 3.355263157894737e-06,
1893
+ "loss": 0.4745,
1894
+ "step": 145
1895
+ },
1896
+ {
1897
+ "Batch Mean": 1.8909566402435303,
1898
+ "accuracy": 0.796875,
1899
+ "epoch": 0.3625,
1900
+ "step": 145
1901
+ },
1902
+ {
1903
+ "epoch": 0.365,
1904
+ "grad_norm": 7.310222148895264,
1905
+ "learning_rate": 3.342105263157895e-06,
1906
+ "loss": 0.4671,
1907
+ "step": 146
1908
+ },
1909
+ {
1910
+ "Batch Mean": 2.035611152648926,
1911
+ "accuracy": 0.75,
1912
+ "epoch": 0.365,
1913
+ "step": 146
1914
+ },
1915
+ {
1916
+ "epoch": 0.3675,
1917
+ "grad_norm": 7.8623809814453125,
1918
+ "learning_rate": 3.3289473684210528e-06,
1919
+ "loss": 0.5079,
1920
+ "step": 147
1921
+ },
1922
+ {
1923
+ "Batch Mean": 2.0848422050476074,
1924
+ "accuracy": 0.8203125,
1925
+ "epoch": 0.3675,
1926
+ "step": 147
1927
+ },
1928
+ {
1929
+ "epoch": 0.37,
1930
+ "grad_norm": 7.38020133972168,
1931
+ "learning_rate": 3.3157894736842107e-06,
1932
+ "loss": 0.5131,
1933
+ "step": 148
1934
+ },
1935
+ {
1936
+ "Batch Mean": 1.9938535690307617,
1937
+ "accuracy": 0.7734375,
1938
+ "epoch": 0.37,
1939
+ "step": 148
1940
+ },
1941
+ {
1942
+ "epoch": 0.3725,
1943
+ "grad_norm": 7.401918411254883,
1944
+ "learning_rate": 3.302631578947369e-06,
1945
+ "loss": 0.4059,
1946
+ "step": 149
1947
+ },
1948
+ {
1949
+ "Batch Mean": 1.9994306564331055,
1950
+ "accuracy": 0.8515625,
1951
+ "epoch": 0.3725,
1952
+ "step": 149
1953
+ },
1954
+ {
1955
+ "epoch": 0.375,
1956
+ "grad_norm": 7.515151500701904,
1957
+ "learning_rate": 3.289473684210527e-06,
1958
+ "loss": 0.4198,
1959
+ "step": 150
1960
+ },
1961
+ {
1962
+ "Batch Mean": 1.9627342224121094,
1963
+ "accuracy": 0.78125,
1964
+ "epoch": 0.375,
1965
+ "step": 150
1966
+ },
1967
+ {
1968
+ "epoch": 0.3775,
1969
+ "grad_norm": 9.086411476135254,
1970
+ "learning_rate": 3.276315789473685e-06,
1971
+ "loss": 0.407,
1972
+ "step": 151
1973
+ },
1974
+ {
1975
+ "Batch Mean": 2.247910499572754,
1976
+ "accuracy": 0.75,
1977
+ "epoch": 0.3775,
1978
+ "step": 151
1979
+ },
1980
+ {
1981
+ "epoch": 0.38,
1982
+ "grad_norm": 8.9763765335083,
1983
+ "learning_rate": 3.2631578947368423e-06,
1984
+ "loss": 0.5274,
1985
+ "step": 152
1986
+ },
1987
+ {
1988
+ "Batch Mean": 2.261256694793701,
1989
+ "accuracy": 0.8125,
1990
+ "epoch": 0.38,
1991
+ "step": 152
1992
+ },
1993
+ {
1994
+ "epoch": 0.3825,
1995
+ "grad_norm": 6.913736820220947,
1996
+ "learning_rate": 3.2500000000000002e-06,
1997
+ "loss": 0.4049,
1998
+ "step": 153
1999
+ },
2000
+ {
2001
+ "Batch Mean": 2.136556386947632,
2002
+ "accuracy": 0.78125,
2003
+ "epoch": 0.3825,
2004
+ "step": 153
2005
+ },
2006
+ {
2007
+ "epoch": 0.385,
2008
+ "grad_norm": 7.755904674530029,
2009
+ "learning_rate": 3.236842105263158e-06,
2010
+ "loss": 0.449,
2011
+ "step": 154
2012
+ },
2013
+ {
2014
+ "Batch Mean": 2.088193416595459,
2015
+ "accuracy": 0.8046875,
2016
+ "epoch": 0.385,
2017
+ "step": 154
2018
+ },
2019
+ {
2020
+ "epoch": 0.3875,
2021
+ "grad_norm": 7.1718316078186035,
2022
+ "learning_rate": 3.223684210526316e-06,
2023
+ "loss": 0.4129,
2024
+ "step": 155
2025
+ },
2026
+ {
2027
+ "Batch Mean": 2.5068817138671875,
2028
+ "accuracy": 0.796875,
2029
+ "epoch": 0.3875,
2030
+ "step": 155
2031
+ },
2032
+ {
2033
+ "epoch": 0.39,
2034
+ "grad_norm": 9.461467742919922,
2035
+ "learning_rate": 3.210526315789474e-06,
2036
+ "loss": 0.4147,
2037
+ "step": 156
2038
+ },
2039
+ {
2040
+ "Batch Mean": 2.0449132919311523,
2041
+ "accuracy": 0.7578125,
2042
+ "epoch": 0.39,
2043
+ "step": 156
2044
+ },
2045
+ {
2046
+ "epoch": 0.3925,
2047
+ "grad_norm": 8.785501480102539,
2048
+ "learning_rate": 3.197368421052632e-06,
2049
+ "loss": 0.478,
2050
+ "step": 157
2051
+ },
2052
+ {
2053
+ "Batch Mean": 2.2665648460388184,
2054
+ "accuracy": 0.8203125,
2055
+ "epoch": 0.3925,
2056
+ "step": 157
2057
+ },
2058
+ {
2059
+ "epoch": 0.395,
2060
+ "grad_norm": 7.906212329864502,
2061
+ "learning_rate": 3.1842105263157898e-06,
2062
+ "loss": 0.4083,
2063
+ "step": 158
2064
+ },
2065
+ {
2066
+ "Batch Mean": 1.8799333572387695,
2067
+ "accuracy": 0.734375,
2068
+ "epoch": 0.395,
2069
+ "step": 158
2070
+ },
2071
+ {
2072
+ "epoch": 0.3975,
2073
+ "grad_norm": 9.25344467163086,
2074
+ "learning_rate": 3.1710526315789477e-06,
2075
+ "loss": 0.5007,
2076
+ "step": 159
2077
+ },
2078
+ {
2079
+ "Batch Mean": 2.178339719772339,
2080
+ "accuracy": 0.828125,
2081
+ "epoch": 0.3975,
2082
+ "step": 159
2083
+ },
2084
+ {
2085
+ "epoch": 0.4,
2086
+ "grad_norm": 8.476263046264648,
2087
+ "learning_rate": 3.157894736842105e-06,
2088
+ "loss": 0.4184,
2089
+ "step": 160
2090
+ },
2091
+ {
2092
+ "Batch Mean": 1.9270563125610352,
2093
+ "accuracy": 0.7421875,
2094
+ "epoch": 0.4,
2095
+ "step": 160
2096
+ },
2097
+ {
2098
+ "epoch": 0.4025,
2099
+ "grad_norm": 10.214958190917969,
2100
+ "learning_rate": 3.144736842105263e-06,
2101
+ "loss": 0.5542,
2102
+ "step": 161
2103
+ },
2104
+ {
2105
+ "Batch Mean": 1.8700056076049805,
2106
+ "accuracy": 0.796875,
2107
+ "epoch": 0.4025,
2108
+ "step": 161
2109
+ },
2110
+ {
2111
+ "epoch": 0.405,
2112
+ "grad_norm": 8.01285171508789,
2113
+ "learning_rate": 3.131578947368421e-06,
2114
+ "loss": 0.4171,
2115
+ "step": 162
2116
+ },
2117
+ {
2118
+ "Batch Mean": 1.8484151363372803,
2119
+ "accuracy": 0.765625,
2120
+ "epoch": 0.405,
2121
+ "step": 162
2122
+ },
2123
+ {
2124
+ "epoch": 0.4075,
2125
+ "grad_norm": 8.116409301757812,
2126
+ "learning_rate": 3.1184210526315793e-06,
2127
+ "loss": 0.4576,
2128
+ "step": 163
2129
+ },
2130
+ {
2131
+ "Batch Mean": 1.7719857692718506,
2132
+ "accuracy": 0.78125,
2133
+ "epoch": 0.4075,
2134
+ "step": 163
2135
+ },
2136
+ {
2137
+ "epoch": 0.41,
2138
+ "grad_norm": 7.865448951721191,
2139
+ "learning_rate": 3.1052631578947372e-06,
2140
+ "loss": 0.4393,
2141
+ "step": 164
2142
+ },
2143
+ {
2144
+ "Batch Mean": 1.7638423442840576,
2145
+ "accuracy": 0.78125,
2146
+ "epoch": 0.41,
2147
+ "step": 164
2148
+ },
2149
+ {
2150
+ "epoch": 0.4125,
2151
+ "grad_norm": 7.379011631011963,
2152
+ "learning_rate": 3.092105263157895e-06,
2153
+ "loss": 0.4278,
2154
+ "step": 165
2155
+ },
2156
+ {
2157
+ "Batch Mean": 1.7345421314239502,
2158
+ "accuracy": 0.671875,
2159
+ "epoch": 0.4125,
2160
+ "step": 165
2161
+ },
2162
+ {
2163
+ "epoch": 0.415,
2164
+ "grad_norm": 8.332331657409668,
2165
+ "learning_rate": 3.078947368421053e-06,
2166
+ "loss": 0.5219,
2167
+ "step": 166
2168
+ },
2169
+ {
2170
+ "Batch Mean": 1.5037906169891357,
2171
+ "accuracy": 0.8203125,
2172
+ "epoch": 0.415,
2173
+ "step": 166
2174
+ },
2175
+ {
2176
+ "epoch": 0.4175,
2177
+ "grad_norm": 7.413763523101807,
2178
+ "learning_rate": 3.065789473684211e-06,
2179
+ "loss": 0.4208,
2180
+ "step": 167
2181
+ },
2182
+ {
2183
+ "Batch Mean": 1.7763586044311523,
2184
+ "accuracy": 0.84375,
2185
+ "epoch": 0.4175,
2186
+ "step": 167
2187
+ },
2188
+ {
2189
+ "epoch": 0.42,
2190
+ "grad_norm": 6.86100435256958,
2191
+ "learning_rate": 3.052631578947369e-06,
2192
+ "loss": 0.3848,
2193
+ "step": 168
2194
+ },
2195
+ {
2196
+ "Batch Mean": 1.7984695434570312,
2197
+ "accuracy": 0.7421875,
2198
+ "epoch": 0.42,
2199
+ "step": 168
2200
+ },
2201
+ {
2202
+ "epoch": 0.4225,
2203
+ "grad_norm": 8.179668426513672,
2204
+ "learning_rate": 3.0394736842105268e-06,
2205
+ "loss": 0.4362,
2206
+ "step": 169
2207
+ },
2208
+ {
2209
+ "Batch Mean": 2.192814588546753,
2210
+ "accuracy": 0.8046875,
2211
+ "epoch": 0.4225,
2212
+ "step": 169
2213
+ },
2214
+ {
2215
+ "epoch": 0.425,
2216
+ "grad_norm": 7.526256561279297,
2217
+ "learning_rate": 3.0263157894736843e-06,
2218
+ "loss": 0.4229,
2219
+ "step": 170
2220
+ },
2221
+ {
2222
+ "Batch Mean": 2.0280096530914307,
2223
+ "accuracy": 0.75,
2224
+ "epoch": 0.425,
2225
+ "step": 170
2226
+ },
2227
+ {
2228
+ "epoch": 0.4275,
2229
+ "grad_norm": 9.94598388671875,
2230
+ "learning_rate": 3.013157894736842e-06,
2231
+ "loss": 0.4399,
2232
+ "step": 171
2233
+ },
2234
+ {
2235
+ "Batch Mean": 2.0560245513916016,
2236
+ "accuracy": 0.7890625,
2237
+ "epoch": 0.4275,
2238
+ "step": 171
2239
+ },
2240
+ {
2241
+ "epoch": 0.43,
2242
+ "grad_norm": 8.51555347442627,
2243
+ "learning_rate": 3e-06,
2244
+ "loss": 0.4532,
2245
+ "step": 172
2246
+ },
2247
+ {
2248
+ "Batch Mean": 2.4426515102386475,
2249
+ "accuracy": 0.796875,
2250
+ "epoch": 0.43,
2251
+ "step": 172
2252
+ },
2253
+ {
2254
+ "epoch": 0.4325,
2255
+ "grad_norm": 10.147135734558105,
2256
+ "learning_rate": 2.986842105263158e-06,
2257
+ "loss": 0.415,
2258
+ "step": 173
2259
+ },
2260
+ {
2261
+ "Batch Mean": 2.6248912811279297,
2262
+ "accuracy": 0.765625,
2263
+ "epoch": 0.4325,
2264
+ "step": 173
2265
+ },
2266
+ {
2267
+ "epoch": 0.435,
2268
+ "grad_norm": 8.979937553405762,
2269
+ "learning_rate": 2.973684210526316e-06,
2270
+ "loss": 0.4281,
2271
+ "step": 174
2272
+ },
2273
+ {
2274
+ "Batch Mean": 2.5382537841796875,
2275
+ "accuracy": 0.75,
2276
+ "epoch": 0.435,
2277
+ "step": 174
2278
+ },
2279
+ {
2280
+ "epoch": 0.4375,
2281
+ "grad_norm": 9.164665222167969,
2282
+ "learning_rate": 2.960526315789474e-06,
2283
+ "loss": 0.5332,
2284
+ "step": 175
2285
+ },
2286
+ {
2287
+ "Batch Mean": 2.4894802570343018,
2288
+ "accuracy": 0.8515625,
2289
+ "epoch": 0.4375,
2290
+ "step": 175
2291
+ },
2292
+ {
2293
+ "epoch": 0.44,
2294
+ "grad_norm": 8.5990571975708,
2295
+ "learning_rate": 2.9473684210526317e-06,
2296
+ "loss": 0.3928,
2297
+ "step": 176
2298
+ },
2299
+ {
2300
+ "Batch Mean": 2.163804054260254,
2301
+ "accuracy": 0.8359375,
2302
+ "epoch": 0.44,
2303
+ "step": 176
2304
+ },
2305
+ {
2306
+ "epoch": 0.4425,
2307
+ "grad_norm": 7.983039855957031,
2308
+ "learning_rate": 2.93421052631579e-06,
2309
+ "loss": 0.3724,
2310
+ "step": 177
2311
+ },
2312
+ {
2313
+ "Batch Mean": 2.3338851928710938,
2314
+ "accuracy": 0.71875,
2315
+ "epoch": 0.4425,
2316
+ "step": 177
2317
+ },
2318
+ {
2319
+ "epoch": 0.445,
2320
+ "grad_norm": 11.577138900756836,
2321
+ "learning_rate": 2.921052631578948e-06,
2322
+ "loss": 0.5237,
2323
+ "step": 178
2324
+ },
2325
+ {
2326
+ "Batch Mean": 2.19907808303833,
2327
+ "accuracy": 0.78125,
2328
+ "epoch": 0.445,
2329
+ "step": 178
2330
+ },
2331
+ {
2332
+ "epoch": 0.4475,
2333
+ "grad_norm": 9.622861862182617,
2334
+ "learning_rate": 2.907894736842106e-06,
2335
+ "loss": 0.4411,
2336
+ "step": 179
2337
+ },
2338
+ {
2339
+ "Batch Mean": 2.456371307373047,
2340
+ "accuracy": 0.8203125,
2341
+ "epoch": 0.4475,
2342
+ "step": 179
2343
+ },
2344
+ {
2345
+ "epoch": 0.45,
2346
+ "grad_norm": 8.121110916137695,
2347
+ "learning_rate": 2.8947368421052634e-06,
2348
+ "loss": 0.3666,
2349
+ "step": 180
2350
+ },
2351
+ {
2352
+ "Batch Mean": 2.4925358295440674,
2353
+ "accuracy": 0.8046875,
2354
+ "epoch": 0.45,
2355
+ "step": 180
2356
+ },
2357
+ {
2358
+ "epoch": 0.4525,
2359
+ "grad_norm": 10.249773025512695,
2360
+ "learning_rate": 2.8815789473684213e-06,
2361
+ "loss": 0.4987,
2362
+ "step": 181
2363
+ },
2364
+ {
2365
+ "Batch Mean": 2.46488094329834,
2366
+ "accuracy": 0.84375,
2367
+ "epoch": 0.4525,
2368
+ "step": 181
2369
+ },
2370
+ {
2371
+ "epoch": 0.455,
2372
+ "grad_norm": 7.278886318206787,
2373
+ "learning_rate": 2.868421052631579e-06,
2374
+ "loss": 0.3417,
2375
+ "step": 182
2376
+ },
2377
+ {
2378
+ "Batch Mean": 2.4173011779785156,
2379
+ "accuracy": 0.8125,
2380
+ "epoch": 0.455,
2381
+ "step": 182
2382
+ },
2383
+ {
2384
+ "epoch": 0.4575,
2385
+ "grad_norm": 8.626398086547852,
2386
+ "learning_rate": 2.855263157894737e-06,
2387
+ "loss": 0.4077,
2388
+ "step": 183
2389
+ },
2390
+ {
2391
+ "Batch Mean": 1.8599066734313965,
2392
+ "accuracy": 0.7421875,
2393
+ "epoch": 0.4575,
2394
+ "step": 183
2395
+ },
2396
+ {
2397
+ "epoch": 0.46,
2398
+ "grad_norm": 9.768396377563477,
2399
+ "learning_rate": 2.842105263157895e-06,
2400
+ "loss": 0.4882,
2401
+ "step": 184
2402
+ },
2403
+ {
2404
+ "Batch Mean": 2.145785331726074,
2405
+ "accuracy": 0.78125,
2406
+ "epoch": 0.46,
2407
+ "step": 184
2408
+ },
2409
+ {
2410
+ "epoch": 0.4625,
2411
+ "grad_norm": 8.507255554199219,
2412
+ "learning_rate": 2.828947368421053e-06,
2413
+ "loss": 0.4024,
2414
+ "step": 185
2415
+ },
2416
+ {
2417
+ "Batch Mean": 1.7814726829528809,
2418
+ "accuracy": 0.7578125,
2419
+ "epoch": 0.4625,
2420
+ "step": 185
2421
+ },
2422
+ {
2423
+ "epoch": 0.465,
2424
+ "grad_norm": 10.355148315429688,
2425
+ "learning_rate": 2.815789473684211e-06,
2426
+ "loss": 0.5292,
2427
+ "step": 186
2428
+ },
2429
+ {
2430
+ "Batch Mean": 1.888627529144287,
2431
+ "accuracy": 0.828125,
2432
+ "epoch": 0.465,
2433
+ "step": 186
2434
+ },
2435
+ {
2436
+ "epoch": 0.4675,
2437
+ "grad_norm": 8.215280532836914,
2438
+ "learning_rate": 2.8026315789473683e-06,
2439
+ "loss": 0.3985,
2440
+ "step": 187
2441
+ },
2442
+ {
2443
+ "Batch Mean": 1.8559679985046387,
2444
+ "accuracy": 0.828125,
2445
+ "epoch": 0.4675,
2446
+ "step": 187
2447
+ },
2448
+ {
2449
+ "epoch": 0.47,
2450
+ "grad_norm": 7.013787269592285,
2451
+ "learning_rate": 2.789473684210526e-06,
2452
+ "loss": 0.3815,
2453
+ "step": 188
2454
+ },
2455
+ {
2456
+ "Batch Mean": 1.7180118560791016,
2457
+ "accuracy": 0.7578125,
2458
+ "epoch": 0.47,
2459
+ "step": 188
2460
+ },
2461
+ {
2462
+ "epoch": 0.4725,
2463
+ "grad_norm": 7.246432781219482,
2464
+ "learning_rate": 2.776315789473684e-06,
2465
+ "loss": 0.4432,
2466
+ "step": 189
2467
+ },
2468
+ {
2469
+ "Batch Mean": 1.5764282941818237,
2470
+ "accuracy": 0.8046875,
2471
+ "epoch": 0.4725,
2472
+ "step": 189
2473
+ },
2474
+ {
2475
+ "epoch": 0.475,
2476
+ "grad_norm": 7.489908218383789,
2477
+ "learning_rate": 2.7631578947368424e-06,
2478
+ "loss": 0.4256,
2479
+ "step": 190
2480
+ },
2481
+ {
2482
+ "Batch Mean": 1.2490241527557373,
2483
+ "accuracy": 0.796875,
2484
+ "epoch": 0.475,
2485
+ "step": 190
2486
+ },
2487
+ {
2488
+ "epoch": 0.4775,
2489
+ "grad_norm": 7.128645420074463,
2490
+ "learning_rate": 2.7500000000000004e-06,
2491
+ "loss": 0.4488,
2492
+ "step": 191
2493
+ },
2494
+ {
2495
+ "Batch Mean": 1.0759793519973755,
2496
+ "accuracy": 0.828125,
2497
+ "epoch": 0.4775,
2498
+ "step": 191
2499
+ },
2500
+ {
2501
+ "epoch": 0.48,
2502
+ "grad_norm": 7.570965766906738,
2503
+ "learning_rate": 2.7368421052631583e-06,
2504
+ "loss": 0.4073,
2505
+ "step": 192
2506
+ },
2507
+ {
2508
+ "Batch Mean": 0.8960497379302979,
2509
+ "accuracy": 0.84375,
2510
+ "epoch": 0.48,
2511
+ "step": 192
2512
+ },
2513
+ {
2514
+ "epoch": 0.4825,
2515
+ "grad_norm": 7.548012733459473,
2516
+ "learning_rate": 2.723684210526316e-06,
2517
+ "loss": 0.3733,
2518
+ "step": 193
2519
+ },
2520
+ {
2521
+ "Batch Mean": 0.9645734429359436,
2522
+ "accuracy": 0.765625,
2523
+ "epoch": 0.4825,
2524
+ "step": 193
2525
+ },
2526
+ {
2527
+ "epoch": 0.485,
2528
+ "grad_norm": 7.658840656280518,
2529
+ "learning_rate": 2.710526315789474e-06,
2530
+ "loss": 0.4456,
2531
+ "step": 194
2532
+ },
2533
+ {
2534
+ "Batch Mean": 0.9235124588012695,
2535
+ "accuracy": 0.8515625,
2536
+ "epoch": 0.485,
2537
+ "step": 194
2538
+ },
2539
+ {
2540
+ "epoch": 0.4875,
2541
+ "grad_norm": 7.451051235198975,
2542
+ "learning_rate": 2.697368421052632e-06,
2543
+ "loss": 0.3823,
2544
+ "step": 195
2545
+ },
2546
+ {
2547
+ "Batch Mean": 1.27029550075531,
2548
+ "accuracy": 0.84375,
2549
+ "epoch": 0.4875,
2550
+ "step": 195
2551
+ },
2552
+ {
2553
+ "epoch": 0.49,
2554
+ "grad_norm": 7.330119609832764,
2555
+ "learning_rate": 2.68421052631579e-06,
2556
+ "loss": 0.3983,
2557
+ "step": 196
2558
+ },
2559
+ {
2560
+ "Batch Mean": 1.3359482288360596,
2561
+ "accuracy": 0.7578125,
2562
+ "epoch": 0.49,
2563
+ "step": 196
2564
+ },
2565
+ {
2566
+ "epoch": 0.4925,
2567
+ "grad_norm": 7.700873374938965,
2568
+ "learning_rate": 2.6710526315789474e-06,
2569
+ "loss": 0.4517,
2570
+ "step": 197
2571
+ },
2572
+ {
2573
+ "Batch Mean": 1.4910411834716797,
2574
+ "accuracy": 0.7265625,
2575
+ "epoch": 0.4925,
2576
+ "step": 197
2577
+ },
2578
+ {
2579
+ "epoch": 0.495,
2580
+ "grad_norm": 8.952484130859375,
2581
+ "learning_rate": 2.6578947368421053e-06,
2582
+ "loss": 0.4592,
2583
+ "step": 198
2584
+ },
2585
+ {
2586
+ "Batch Mean": 1.6832847595214844,
2587
+ "accuracy": 0.8359375,
2588
+ "epoch": 0.495,
2589
+ "step": 198
2590
+ },
2591
+ {
2592
+ "epoch": 0.4975,
2593
+ "grad_norm": 8.010570526123047,
2594
+ "learning_rate": 2.644736842105263e-06,
2595
+ "loss": 0.4087,
2596
+ "step": 199
2597
+ },
2598
+ {
2599
+ "Batch Mean": 1.5343718528747559,
2600
+ "accuracy": 0.796875,
2601
+ "epoch": 0.4975,
2602
+ "step": 199
2603
+ },
2604
+ {
2605
+ "epoch": 0.5,
2606
+ "grad_norm": 8.992362976074219,
2607
+ "learning_rate": 2.631578947368421e-06,
2608
+ "loss": 0.4823,
2609
+ "step": 200
2610
+ },
2611
+ {
2612
+ "Batch Mean": 1.6328332424163818,
2613
+ "accuracy": 0.7734375,
2614
+ "epoch": 0.5,
2615
+ "step": 200
2616
+ },
2617
+ {
2618
+ "epoch": 0.5025,
2619
+ "grad_norm": 9.035256385803223,
2620
+ "learning_rate": 2.618421052631579e-06,
2621
+ "loss": 0.4471,
2622
+ "step": 201
2623
+ },
2624
+ {
2625
+ "Batch Mean": 1.5844993591308594,
2626
+ "accuracy": 0.78125,
2627
+ "epoch": 0.5025,
2628
+ "step": 201
2629
+ },
2630
+ {
2631
+ "epoch": 0.505,
2632
+ "grad_norm": 7.833075046539307,
2633
+ "learning_rate": 2.605263157894737e-06,
2634
+ "loss": 0.4245,
2635
+ "step": 202
2636
+ },
2637
+ {
2638
+ "Batch Mean": 1.411280632019043,
2639
+ "accuracy": 0.7734375,
2640
+ "epoch": 0.505,
2641
+ "step": 202
2642
+ },
2643
+ {
2644
+ "epoch": 0.5075,
2645
+ "grad_norm": 9.432007789611816,
2646
+ "learning_rate": 2.592105263157895e-06,
2647
+ "loss": 0.4416,
2648
+ "step": 203
2649
+ },
2650
+ {
2651
+ "Batch Mean": 1.6097602844238281,
2652
+ "accuracy": 0.7421875,
2653
+ "epoch": 0.5075,
2654
+ "step": 203
2655
+ },
2656
+ {
2657
+ "epoch": 0.51,
2658
+ "grad_norm": 8.289928436279297,
2659
+ "learning_rate": 2.578947368421053e-06,
2660
+ "loss": 0.4749,
2661
+ "step": 204
2662
+ },
2663
+ {
2664
+ "Batch Mean": 1.1805787086486816,
2665
+ "accuracy": 0.734375,
2666
+ "epoch": 0.51,
2667
+ "step": 204
2668
+ },
2669
+ {
2670
+ "epoch": 0.5125,
2671
+ "grad_norm": 9.437891960144043,
2672
+ "learning_rate": 2.565789473684211e-06,
2673
+ "loss": 0.4626,
2674
+ "step": 205
2675
+ },
2676
+ {
2677
+ "Batch Mean": 1.347944736480713,
2678
+ "accuracy": 0.7265625,
2679
+ "epoch": 0.5125,
2680
+ "step": 205
2681
+ },
2682
+ {
2683
+ "epoch": 0.515,
2684
+ "grad_norm": 8.658241271972656,
2685
+ "learning_rate": 2.552631578947369e-06,
2686
+ "loss": 0.4763,
2687
+ "step": 206
2688
+ },
2689
+ {
2690
+ "Batch Mean": 1.2932205200195312,
2691
+ "accuracy": 0.7890625,
2692
+ "epoch": 0.515,
2693
+ "step": 206
2694
+ },
2695
+ {
2696
+ "epoch": 0.5175,
2697
+ "grad_norm": 8.141422271728516,
2698
+ "learning_rate": 2.5394736842105265e-06,
2699
+ "loss": 0.4264,
2700
+ "step": 207
2701
+ },
2702
+ {
2703
+ "Batch Mean": 1.2558472156524658,
2704
+ "accuracy": 0.8046875,
2705
+ "epoch": 0.5175,
2706
+ "step": 207
2707
+ },
2708
+ {
2709
+ "epoch": 0.52,
2710
+ "grad_norm": 7.476047515869141,
2711
+ "learning_rate": 2.5263157894736844e-06,
2712
+ "loss": 0.4308,
2713
+ "step": 208
2714
+ },
2715
+ {
2716
+ "Batch Mean": 0.9620341062545776,
2717
+ "accuracy": 0.7421875,
2718
+ "epoch": 0.52,
2719
+ "step": 208
2720
+ },
2721
+ {
2722
+ "epoch": 0.5225,
2723
+ "grad_norm": 7.889948844909668,
2724
+ "learning_rate": 2.5131578947368423e-06,
2725
+ "loss": 0.4499,
2726
+ "step": 209
2727
+ },
2728
+ {
2729
+ "Batch Mean": 0.7413516640663147,
2730
+ "accuracy": 0.7265625,
2731
+ "epoch": 0.5225,
2732
+ "step": 209
2733
+ },
2734
+ {
2735
+ "epoch": 0.525,
2736
+ "grad_norm": 9.15515422821045,
2737
+ "learning_rate": 2.5e-06,
2738
+ "loss": 0.5032,
2739
+ "step": 210
2740
+ },
2741
+ {
2742
+ "Batch Mean": 0.9634220600128174,
2743
+ "accuracy": 0.8515625,
2744
+ "epoch": 0.525,
2745
+ "step": 210
2746
+ },
2747
+ {
2748
+ "epoch": 0.5275,
2749
+ "grad_norm": 6.711307048797607,
2750
+ "learning_rate": 2.486842105263158e-06,
2751
+ "loss": 0.3679,
2752
+ "step": 211
2753
+ },
2754
+ {
2755
+ "Batch Mean": 1.191461205482483,
2756
+ "accuracy": 0.734375,
2757
+ "epoch": 0.5275,
2758
+ "step": 211
2759
+ },
2760
+ {
2761
+ "epoch": 0.53,
2762
+ "grad_norm": 7.998767375946045,
2763
+ "learning_rate": 2.473684210526316e-06,
2764
+ "loss": 0.4737,
2765
+ "step": 212
2766
+ },
2767
+ {
2768
+ "Batch Mean": 0.9631187915802002,
2769
+ "accuracy": 0.828125,
2770
+ "epoch": 0.53,
2771
+ "step": 212
2772
+ },
2773
+ {
2774
+ "epoch": 0.5325,
2775
+ "grad_norm": 5.967334747314453,
2776
+ "learning_rate": 2.460526315789474e-06,
2777
+ "loss": 0.3451,
2778
+ "step": 213
2779
+ },
2780
+ {
2781
+ "Batch Mean": 0.8651614189147949,
2782
+ "accuracy": 0.7734375,
2783
+ "epoch": 0.5325,
2784
+ "step": 213
2785
+ },
2786
+ {
2787
+ "epoch": 0.535,
2788
+ "grad_norm": 7.710539817810059,
2789
+ "learning_rate": 2.447368421052632e-06,
2790
+ "loss": 0.4404,
2791
+ "step": 214
2792
+ },
2793
+ {
2794
+ "Batch Mean": 0.9871734380722046,
2795
+ "accuracy": 0.8515625,
2796
+ "epoch": 0.535,
2797
+ "step": 214
2798
+ },
2799
+ {
2800
+ "epoch": 0.5375,
2801
+ "grad_norm": 7.020612716674805,
2802
+ "learning_rate": 2.4342105263157898e-06,
2803
+ "loss": 0.3469,
2804
+ "step": 215
2805
+ },
2806
+ {
2807
+ "Batch Mean": 0.9098066091537476,
2808
+ "accuracy": 0.765625,
2809
+ "epoch": 0.5375,
2810
+ "step": 215
2811
+ },
2812
+ {
2813
+ "epoch": 0.54,
2814
+ "grad_norm": 8.405688285827637,
2815
+ "learning_rate": 2.4210526315789477e-06,
2816
+ "loss": 0.5086,
2817
+ "step": 216
2818
+ },
2819
+ {
2820
+ "Batch Mean": 0.9320878982543945,
2821
+ "accuracy": 0.7734375,
2822
+ "epoch": 0.54,
2823
+ "step": 216
2824
+ },
2825
+ {
2826
+ "epoch": 0.5425,
2827
+ "grad_norm": 7.488485336303711,
2828
+ "learning_rate": 2.4078947368421056e-06,
2829
+ "loss": 0.4145,
2830
+ "step": 217
2831
+ },
2832
+ {
2833
+ "Batch Mean": 1.1252110004425049,
2834
+ "accuracy": 0.7734375,
2835
+ "epoch": 0.5425,
2836
+ "step": 217
2837
+ },
2838
+ {
2839
+ "epoch": 0.545,
2840
+ "grad_norm": 8.458834648132324,
2841
+ "learning_rate": 2.3947368421052635e-06,
2842
+ "loss": 0.4336,
2843
+ "step": 218
2844
+ },
2845
+ {
2846
+ "Batch Mean": 1.0384407043457031,
2847
+ "accuracy": 0.828125,
2848
+ "epoch": 0.545,
2849
+ "step": 218
2850
+ },
2851
+ {
2852
+ "epoch": 0.5475,
2853
+ "grad_norm": 8.343704223632812,
2854
+ "learning_rate": 2.381578947368421e-06,
2855
+ "loss": 0.3845,
2856
+ "step": 219
2857
+ },
2858
+ {
2859
+ "Batch Mean": 1.3833621740341187,
2860
+ "accuracy": 0.7734375,
2861
+ "epoch": 0.5475,
2862
+ "step": 219
2863
+ },
2864
+ {
2865
+ "epoch": 0.55,
2866
+ "grad_norm": 9.676087379455566,
2867
+ "learning_rate": 2.368421052631579e-06,
2868
+ "loss": 0.4359,
2869
+ "step": 220
2870
+ },
2871
+ {
2872
+ "Batch Mean": 0.9786429405212402,
2873
+ "accuracy": 0.7890625,
2874
+ "epoch": 0.55,
2875
+ "step": 220
2876
+ },
2877
+ {
2878
+ "epoch": 0.5525,
2879
+ "grad_norm": 8.946784019470215,
2880
+ "learning_rate": 2.355263157894737e-06,
2881
+ "loss": 0.4391,
2882
+ "step": 221
2883
+ },
2884
+ {
2885
+ "Batch Mean": 1.0276886224746704,
2886
+ "accuracy": 0.796875,
2887
+ "epoch": 0.5525,
2888
+ "step": 221
2889
+ },
2890
+ {
2891
+ "epoch": 0.555,
2892
+ "grad_norm": 9.185587882995605,
2893
+ "learning_rate": 2.342105263157895e-06,
2894
+ "loss": 0.4326,
2895
+ "step": 222
2896
+ },
2897
+ {
2898
+ "Batch Mean": 1.312666416168213,
2899
+ "accuracy": 0.765625,
2900
+ "epoch": 0.555,
2901
+ "step": 222
2902
+ },
2903
+ {
2904
+ "epoch": 0.5575,
2905
+ "grad_norm": 9.896113395690918,
2906
+ "learning_rate": 2.328947368421053e-06,
2907
+ "loss": 0.4861,
2908
+ "step": 223
2909
+ },
2910
+ {
2911
+ "Batch Mean": 1.1942353248596191,
2912
+ "accuracy": 0.828125,
2913
+ "epoch": 0.5575,
2914
+ "step": 223
2915
+ },
2916
+ {
2917
+ "epoch": 0.56,
2918
+ "grad_norm": 7.770511150360107,
2919
+ "learning_rate": 2.3157894736842105e-06,
2920
+ "loss": 0.3452,
2921
+ "step": 224
2922
+ },
2923
+ {
2924
+ "Batch Mean": 0.8957247734069824,
2925
+ "accuracy": 0.765625,
2926
+ "epoch": 0.56,
2927
+ "step": 224
2928
+ },
2929
+ {
2930
+ "epoch": 0.5625,
2931
+ "grad_norm": 10.309408187866211,
2932
+ "learning_rate": 2.3026315789473684e-06,
2933
+ "loss": 0.459,
2934
+ "step": 225
2935
+ },
2936
+ {
2937
+ "Batch Mean": 0.9890605807304382,
2938
+ "accuracy": 0.7734375,
2939
+ "epoch": 0.5625,
2940
+ "step": 225
2941
+ },
2942
+ {
2943
+ "epoch": 0.565,
2944
+ "grad_norm": 10.081012725830078,
2945
+ "learning_rate": 2.2894736842105263e-06,
2946
+ "loss": 0.433,
2947
+ "step": 226
2948
+ },
2949
+ {
2950
+ "Batch Mean": 0.37744632363319397,
2951
+ "accuracy": 0.7734375,
2952
+ "epoch": 0.565,
2953
+ "step": 226
2954
+ },
2955
+ {
2956
+ "epoch": 0.5675,
2957
+ "grad_norm": 10.793180465698242,
2958
+ "learning_rate": 2.2763157894736847e-06,
2959
+ "loss": 0.4462,
2960
+ "step": 227
2961
+ },
2962
+ {
2963
+ "Batch Mean": 0.5035256147384644,
2964
+ "accuracy": 0.796875,
2965
+ "epoch": 0.5675,
2966
+ "step": 227
2967
+ },
2968
+ {
2969
+ "epoch": 0.57,
2970
+ "grad_norm": 10.840557098388672,
2971
+ "learning_rate": 2.2631578947368426e-06,
2972
+ "loss": 0.4301,
2973
+ "step": 228
2974
+ },
2975
+ {
2976
+ "Batch Mean": 0.3500272035598755,
2977
+ "accuracy": 0.828125,
2978
+ "epoch": 0.57,
2979
+ "step": 228
2980
+ },
2981
+ {
2982
+ "epoch": 0.5725,
2983
+ "grad_norm": 7.773880958557129,
2984
+ "learning_rate": 2.25e-06,
2985
+ "loss": 0.3467,
2986
+ "step": 229
2987
+ },
2988
+ {
2989
+ "Batch Mean": 0.548717737197876,
2990
+ "accuracy": 0.8125,
2991
+ "epoch": 0.5725,
2992
+ "step": 229
2993
+ },
2994
+ {
2995
+ "epoch": 0.575,
2996
+ "grad_norm": 9.137742042541504,
2997
+ "learning_rate": 2.236842105263158e-06,
2998
+ "loss": 0.4347,
2999
+ "step": 230
3000
+ },
3001
+ {
3002
+ "Batch Mean": 0.3661317825317383,
3003
+ "accuracy": 0.84375,
3004
+ "epoch": 0.575,
3005
+ "step": 230
3006
+ },
3007
+ {
3008
+ "epoch": 0.5775,
3009
+ "grad_norm": 7.887228012084961,
3010
+ "learning_rate": 2.223684210526316e-06,
3011
+ "loss": 0.3833,
3012
+ "step": 231
3013
+ },
3014
+ {
3015
+ "Batch Mean": 0.12111562490463257,
3016
+ "accuracy": 0.7890625,
3017
+ "epoch": 0.5775,
3018
+ "step": 231
3019
+ },
3020
+ {
3021
+ "epoch": 0.58,
3022
+ "grad_norm": 7.976273536682129,
3023
+ "learning_rate": 2.2105263157894738e-06,
3024
+ "loss": 0.4134,
3025
+ "step": 232
3026
+ },
3027
+ {
3028
+ "Batch Mean": 0.4660627841949463,
3029
+ "accuracy": 0.78125,
3030
+ "epoch": 0.58,
3031
+ "step": 232
3032
+ },
3033
+ {
3034
+ "epoch": 0.5825,
3035
+ "grad_norm": 9.632377624511719,
3036
+ "learning_rate": 2.1973684210526317e-06,
3037
+ "loss": 0.4059,
3038
+ "step": 233
3039
+ },
3040
+ {
3041
+ "Batch Mean": 0.21030330657958984,
3042
+ "accuracy": 0.78125,
3043
+ "epoch": 0.5825,
3044
+ "step": 233
3045
+ },
3046
+ {
3047
+ "epoch": 0.585,
3048
+ "grad_norm": 8.921050071716309,
3049
+ "learning_rate": 2.1842105263157896e-06,
3050
+ "loss": 0.4555,
3051
+ "step": 234
3052
+ },
3053
+ {
3054
+ "Batch Mean": 0.2276170253753662,
3055
+ "accuracy": 0.890625,
3056
+ "epoch": 0.585,
3057
+ "step": 234
3058
+ },
3059
+ {
3060
+ "epoch": 0.5875,
3061
+ "grad_norm": 7.977242469787598,
3062
+ "learning_rate": 2.1710526315789475e-06,
3063
+ "loss": 0.3518,
3064
+ "step": 235
3065
+ },
3066
+ {
3067
+ "Batch Mean": 0.11401081085205078,
3068
+ "accuracy": 0.828125,
3069
+ "epoch": 0.5875,
3070
+ "step": 235
3071
+ },
3072
+ {
3073
+ "epoch": 0.59,
3074
+ "grad_norm": 8.604510307312012,
3075
+ "learning_rate": 2.1578947368421054e-06,
3076
+ "loss": 0.3273,
3077
+ "step": 236
3078
+ },
3079
+ {
3080
+ "Batch Mean": 0.21731328964233398,
3081
+ "accuracy": 0.7578125,
3082
+ "epoch": 0.59,
3083
+ "step": 236
3084
+ },
3085
+ {
3086
+ "epoch": 0.5925,
3087
+ "grad_norm": 11.264445304870605,
3088
+ "learning_rate": 2.1447368421052633e-06,
3089
+ "loss": 0.5015,
3090
+ "step": 237
3091
+ },
3092
+ {
3093
+ "Batch Mean": 0.24432829022407532,
3094
+ "accuracy": 0.8125,
3095
+ "epoch": 0.5925,
3096
+ "step": 237
3097
+ },
3098
+ {
3099
+ "epoch": 0.595,
3100
+ "grad_norm": 11.254815101623535,
3101
+ "learning_rate": 2.1315789473684212e-06,
3102
+ "loss": 0.4282,
3103
+ "step": 238
3104
+ },
3105
+ {
3106
+ "Batch Mean": 0.29278555512428284,
3107
+ "accuracy": 0.7734375,
3108
+ "epoch": 0.595,
3109
+ "step": 238
3110
+ },
3111
+ {
3112
+ "epoch": 0.5975,
3113
+ "grad_norm": 9.741961479187012,
3114
+ "learning_rate": 2.118421052631579e-06,
3115
+ "loss": 0.4351,
3116
+ "step": 239
3117
+ },
3118
+ {
3119
+ "Batch Mean": 0.41886043548583984,
3120
+ "accuracy": 0.8046875,
3121
+ "epoch": 0.5975,
3122
+ "step": 239
3123
+ },
3124
+ {
3125
+ "epoch": 0.6,
3126
+ "grad_norm": 9.94571590423584,
3127
+ "learning_rate": 2.105263157894737e-06,
3128
+ "loss": 0.4331,
3129
+ "step": 240
3130
+ },
3131
+ {
3132
+ "Batch Mean": 0.3082854747772217,
3133
+ "accuracy": 0.78125,
3134
+ "epoch": 0.6,
3135
+ "step": 240
3136
+ },
3137
+ {
3138
+ "epoch": 0.6025,
3139
+ "grad_norm": 10.888338088989258,
3140
+ "learning_rate": 2.092105263157895e-06,
3141
+ "loss": 0.4521,
3142
+ "step": 241
3143
+ },
3144
+ {
3145
+ "Batch Mean": 0.2888784408569336,
3146
+ "accuracy": 0.8203125,
3147
+ "epoch": 0.6025,
3148
+ "step": 241
3149
+ },
3150
+ {
3151
+ "epoch": 0.605,
3152
+ "grad_norm": 9.849271774291992,
3153
+ "learning_rate": 2.078947368421053e-06,
3154
+ "loss": 0.4457,
3155
+ "step": 242
3156
+ },
3157
+ {
3158
+ "Batch Mean": 0.33397483825683594,
3159
+ "accuracy": 0.8125,
3160
+ "epoch": 0.605,
3161
+ "step": 242
3162
+ },
3163
+ {
3164
+ "epoch": 0.6075,
3165
+ "grad_norm": 7.735013484954834,
3166
+ "learning_rate": 2.0657894736842108e-06,
3167
+ "loss": 0.3658,
3168
+ "step": 243
3169
+ },
3170
+ {
3171
+ "Batch Mean": 0.4756225347518921,
3172
+ "accuracy": 0.78125,
3173
+ "epoch": 0.6075,
3174
+ "step": 243
3175
+ },
3176
+ {
3177
+ "epoch": 0.61,
3178
+ "grad_norm": 10.216158866882324,
3179
+ "learning_rate": 2.0526315789473687e-06,
3180
+ "loss": 0.4212,
3181
+ "step": 244
3182
+ },
3183
+ {
3184
+ "Batch Mean": -0.44994914531707764,
3185
+ "accuracy": 0.8203125,
3186
+ "epoch": 0.61,
3187
+ "step": 244
3188
+ },
3189
+ {
3190
+ "epoch": 0.6125,
3191
+ "grad_norm": 10.403032302856445,
3192
+ "learning_rate": 2.0394736842105266e-06,
3193
+ "loss": 0.4733,
3194
+ "step": 245
3195
+ },
3196
+ {
3197
+ "Batch Mean": 0.5498628616333008,
3198
+ "accuracy": 0.7890625,
3199
+ "epoch": 0.6125,
3200
+ "step": 245
3201
+ },
3202
+ {
3203
+ "epoch": 0.615,
3204
+ "grad_norm": 10.038982391357422,
3205
+ "learning_rate": 2.026315789473684e-06,
3206
+ "loss": 0.4919,
3207
+ "step": 246
3208
+ },
3209
+ {
3210
+ "Batch Mean": 0.31244945526123047,
3211
+ "accuracy": 0.7421875,
3212
+ "epoch": 0.615,
3213
+ "step": 246
3214
+ },
3215
+ {
3216
+ "epoch": 0.6175,
3217
+ "grad_norm": 9.569629669189453,
3218
+ "learning_rate": 2.013157894736842e-06,
3219
+ "loss": 0.4326,
3220
+ "step": 247
3221
+ },
3222
+ {
3223
+ "Batch Mean": 0.19263625144958496,
3224
+ "accuracy": 0.828125,
3225
+ "epoch": 0.6175,
3226
+ "step": 247
3227
+ },
3228
+ {
3229
+ "epoch": 0.62,
3230
+ "grad_norm": 8.492071151733398,
3231
+ "learning_rate": 2.0000000000000003e-06,
3232
+ "loss": 0.3753,
3233
+ "step": 248
3234
+ },
3235
+ {
3236
+ "Batch Mean": -0.19965410232543945,
3237
+ "accuracy": 0.796875,
3238
+ "epoch": 0.62,
3239
+ "step": 248
3240
+ },
3241
+ {
3242
+ "epoch": 0.6225,
3243
+ "grad_norm": 7.891626358032227,
3244
+ "learning_rate": 1.9868421052631582e-06,
3245
+ "loss": 0.3956,
3246
+ "step": 249
3247
+ },
3248
+ {
3249
+ "Batch Mean": -0.16769587993621826,
3250
+ "accuracy": 0.7890625,
3251
+ "epoch": 0.6225,
3252
+ "step": 249
3253
+ },
3254
+ {
3255
+ "epoch": 0.625,
3256
+ "grad_norm": 7.962087154388428,
3257
+ "learning_rate": 1.973684210526316e-06,
3258
+ "loss": 0.3986,
3259
+ "step": 250
3260
+ },
3261
+ {
3262
+ "Batch Mean": 0.14302682876586914,
3263
+ "accuracy": 0.7421875,
3264
+ "epoch": 0.625,
3265
+ "step": 250
3266
+ },
3267
+ {
3268
+ "epoch": 0.6275,
3269
+ "grad_norm": 8.172347068786621,
3270
+ "learning_rate": 1.9605263157894736e-06,
3271
+ "loss": 0.4544,
3272
+ "step": 251
3273
+ },
3274
+ {
3275
+ "Batch Mean": -0.0999612808227539,
3276
+ "accuracy": 0.8203125,
3277
+ "epoch": 0.6275,
3278
+ "step": 251
3279
+ },
3280
+ {
3281
+ "epoch": 0.63,
3282
+ "grad_norm": 7.999663352966309,
3283
+ "learning_rate": 1.9473684210526315e-06,
3284
+ "loss": 0.3684,
3285
+ "step": 252
3286
+ },
3287
+ {
3288
+ "Batch Mean": 0.26888561248779297,
3289
+ "accuracy": 0.8046875,
3290
+ "epoch": 0.63,
3291
+ "step": 252
3292
+ },
3293
+ {
3294
+ "epoch": 0.6325,
3295
+ "grad_norm": 7.38095235824585,
3296
+ "learning_rate": 1.9342105263157895e-06,
3297
+ "loss": 0.4204,
3298
+ "step": 253
3299
+ },
3300
+ {
3301
+ "Batch Mean": 0.32740533351898193,
3302
+ "accuracy": 0.8359375,
3303
+ "epoch": 0.6325,
3304
+ "step": 253
3305
+ },
3306
+ {
3307
+ "epoch": 0.635,
3308
+ "grad_norm": 7.9545111656188965,
3309
+ "learning_rate": 1.9210526315789474e-06,
3310
+ "loss": 0.3764,
3311
+ "step": 254
3312
+ },
3313
+ {
3314
+ "Batch Mean": 0.7168645858764648,
3315
+ "accuracy": 0.7265625,
3316
+ "epoch": 0.635,
3317
+ "step": 254
3318
+ },
3319
+ {
3320
+ "epoch": 0.6375,
3321
+ "grad_norm": 8.771035194396973,
3322
+ "learning_rate": 1.9078947368421057e-06,
3323
+ "loss": 0.4705,
3324
+ "step": 255
3325
+ },
3326
+ {
3327
+ "Batch Mean": 0.7449779510498047,
3328
+ "accuracy": 0.8125,
3329
+ "epoch": 0.6375,
3330
+ "step": 255
3331
+ },
3332
+ {
3333
+ "epoch": 0.64,
3334
+ "grad_norm": 7.6166157722473145,
3335
+ "learning_rate": 1.8947368421052634e-06,
3336
+ "loss": 0.4284,
3337
+ "step": 256
3338
+ },
3339
+ {
3340
+ "Batch Mean": 0.4443552494049072,
3341
+ "accuracy": 0.7890625,
3342
+ "epoch": 0.64,
3343
+ "step": 256
3344
+ },
3345
+ {
3346
+ "epoch": 0.6425,
3347
+ "grad_norm": 7.024027347564697,
3348
+ "learning_rate": 1.8815789473684213e-06,
3349
+ "loss": 0.3937,
3350
+ "step": 257
3351
+ },
3352
+ {
3353
+ "Batch Mean": 0.8168082237243652,
3354
+ "accuracy": 0.734375,
3355
+ "epoch": 0.6425,
3356
+ "step": 257
3357
+ },
3358
+ {
3359
+ "epoch": 0.645,
3360
+ "grad_norm": 9.206171035766602,
3361
+ "learning_rate": 1.868421052631579e-06,
3362
+ "loss": 0.5132,
3363
+ "step": 258
3364
+ },
3365
+ {
3366
+ "Batch Mean": 0.9836267232894897,
3367
+ "accuracy": 0.765625,
3368
+ "epoch": 0.645,
3369
+ "step": 258
3370
+ },
3371
+ {
3372
+ "epoch": 0.6475,
3373
+ "grad_norm": 8.63451862335205,
3374
+ "learning_rate": 1.855263157894737e-06,
3375
+ "loss": 0.4299,
3376
+ "step": 259
3377
+ },
3378
+ {
3379
+ "Batch Mean": 1.264570713043213,
3380
+ "accuracy": 0.796875,
3381
+ "epoch": 0.6475,
3382
+ "step": 259
3383
+ },
3384
+ {
3385
+ "epoch": 0.65,
3386
+ "grad_norm": 7.692586421966553,
3387
+ "learning_rate": 1.8421052631578948e-06,
3388
+ "loss": 0.4257,
3389
+ "step": 260
3390
+ },
3391
+ {
3392
+ "Batch Mean": 1.4181015491485596,
3393
+ "accuracy": 0.8125,
3394
+ "epoch": 0.65,
3395
+ "step": 260
3396
+ },
3397
+ {
3398
+ "epoch": 0.6525,
3399
+ "grad_norm": 8.58105182647705,
3400
+ "learning_rate": 1.828947368421053e-06,
3401
+ "loss": 0.4744,
3402
+ "step": 261
3403
+ },
3404
+ {
3405
+ "Batch Mean": 1.348689079284668,
3406
+ "accuracy": 0.828125,
3407
+ "epoch": 0.6525,
3408
+ "step": 261
3409
+ },
3410
+ {
3411
+ "epoch": 0.655,
3412
+ "grad_norm": 8.066439628601074,
3413
+ "learning_rate": 1.8157894736842109e-06,
3414
+ "loss": 0.4056,
3415
+ "step": 262
3416
+ },
3417
+ {
3418
+ "Batch Mean": 1.0410746335983276,
3419
+ "accuracy": 0.78125,
3420
+ "epoch": 0.655,
3421
+ "step": 262
3422
+ },
3423
+ {
3424
+ "epoch": 0.6575,
3425
+ "grad_norm": 7.489403247833252,
3426
+ "learning_rate": 1.8026315789473685e-06,
3427
+ "loss": 0.4268,
3428
+ "step": 263
3429
+ },
3430
+ {
3431
+ "Batch Mean": 1.3752142190933228,
3432
+ "accuracy": 0.8515625,
3433
+ "epoch": 0.6575,
3434
+ "step": 263
3435
+ },
3436
+ {
3437
+ "epoch": 0.66,
3438
+ "grad_norm": 7.725265026092529,
3439
+ "learning_rate": 1.7894736842105265e-06,
3440
+ "loss": 0.4003,
3441
+ "step": 264
3442
+ },
3443
+ {
3444
+ "Batch Mean": 1.4269516468048096,
3445
+ "accuracy": 0.8046875,
3446
+ "epoch": 0.66,
3447
+ "step": 264
3448
+ },
3449
+ {
3450
+ "epoch": 0.6625,
3451
+ "grad_norm": 8.406197547912598,
3452
+ "learning_rate": 1.7763157894736844e-06,
3453
+ "loss": 0.4057,
3454
+ "step": 265
3455
+ },
3456
+ {
3457
+ "Batch Mean": 1.553175926208496,
3458
+ "accuracy": 0.8359375,
3459
+ "epoch": 0.6625,
3460
+ "step": 265
3461
+ },
3462
+ {
3463
+ "epoch": 0.665,
3464
+ "grad_norm": 8.426583290100098,
3465
+ "learning_rate": 1.7631578947368423e-06,
3466
+ "loss": 0.3518,
3467
+ "step": 266
3468
+ },
3469
+ {
3470
+ "Batch Mean": 1.6486907005310059,
3471
+ "accuracy": 0.859375,
3472
+ "epoch": 0.665,
3473
+ "step": 266
3474
+ },
3475
+ {
3476
+ "epoch": 0.6675,
3477
+ "grad_norm": 8.128406524658203,
3478
+ "learning_rate": 1.75e-06,
3479
+ "loss": 0.3854,
3480
+ "step": 267
3481
+ },
3482
+ {
3483
+ "Batch Mean": 1.7819617986679077,
3484
+ "accuracy": 0.796875,
3485
+ "epoch": 0.6675,
3486
+ "step": 267
3487
+ },
3488
+ {
3489
+ "epoch": 0.67,
3490
+ "grad_norm": 8.426019668579102,
3491
+ "learning_rate": 1.736842105263158e-06,
3492
+ "loss": 0.4415,
3493
+ "step": 268
3494
+ },
3495
+ {
3496
+ "Batch Mean": 1.423553705215454,
3497
+ "accuracy": 0.8359375,
3498
+ "epoch": 0.67,
3499
+ "step": 268
3500
+ },
3501
+ {
3502
+ "epoch": 0.6725,
3503
+ "grad_norm": 7.446429252624512,
3504
+ "learning_rate": 1.723684210526316e-06,
3505
+ "loss": 0.3808,
3506
+ "step": 269
3507
+ },
3508
+ {
3509
+ "Batch Mean": 1.6426506042480469,
3510
+ "accuracy": 0.78125,
3511
+ "epoch": 0.6725,
3512
+ "step": 269
3513
+ },
3514
+ {
3515
+ "epoch": 0.675,
3516
+ "grad_norm": 7.678967475891113,
3517
+ "learning_rate": 1.710526315789474e-06,
3518
+ "loss": 0.4357,
3519
+ "step": 270
3520
+ },
3521
+ {
3522
+ "Batch Mean": 1.4175643920898438,
3523
+ "accuracy": 0.84375,
3524
+ "epoch": 0.675,
3525
+ "step": 270
3526
+ },
3527
+ {
3528
+ "epoch": 0.6775,
3529
+ "grad_norm": 8.308606147766113,
3530
+ "learning_rate": 1.6973684210526318e-06,
3531
+ "loss": 0.3834,
3532
+ "step": 271
3533
+ },
3534
+ {
3535
+ "Batch Mean": 1.5686655044555664,
3536
+ "accuracy": 0.8125,
3537
+ "epoch": 0.6775,
3538
+ "step": 271
3539
+ },
3540
+ {
3541
+ "epoch": 0.68,
3542
+ "grad_norm": 9.372905731201172,
3543
+ "learning_rate": 1.6842105263157895e-06,
3544
+ "loss": 0.4161,
3545
+ "step": 272
3546
+ },
3547
+ {
3548
+ "Batch Mean": 1.3371083736419678,
3549
+ "accuracy": 0.8046875,
3550
+ "epoch": 0.68,
3551
+ "step": 272
3552
+ },
3553
+ {
3554
+ "epoch": 0.6825,
3555
+ "grad_norm": 8.12229061126709,
3556
+ "learning_rate": 1.6710526315789474e-06,
3557
+ "loss": 0.4039,
3558
+ "step": 273
3559
+ },
3560
+ {
3561
+ "Batch Mean": 1.0551990270614624,
3562
+ "accuracy": 0.8046875,
3563
+ "epoch": 0.6825,
3564
+ "step": 273
3565
+ },
3566
+ {
3567
+ "epoch": 0.685,
3568
+ "grad_norm": 7.422252178192139,
3569
+ "learning_rate": 1.6578947368421053e-06,
3570
+ "loss": 0.3893,
3571
+ "step": 274
3572
+ },
3573
+ {
3574
+ "Batch Mean": 1.1766936779022217,
3575
+ "accuracy": 0.796875,
3576
+ "epoch": 0.685,
3577
+ "step": 274
3578
+ },
3579
+ {
3580
+ "epoch": 0.6875,
3581
+ "grad_norm": 8.245626449584961,
3582
+ "learning_rate": 1.6447368421052635e-06,
3583
+ "loss": 0.4395,
3584
+ "step": 275
3585
+ },
3586
+ {
3587
+ "Batch Mean": 1.4158720970153809,
3588
+ "accuracy": 0.8515625,
3589
+ "epoch": 0.6875,
3590
+ "step": 275
3591
+ },
3592
+ {
3593
+ "epoch": 0.69,
3594
+ "grad_norm": 7.877889633178711,
3595
+ "learning_rate": 1.6315789473684212e-06,
3596
+ "loss": 0.3947,
3597
+ "step": 276
3598
+ },
3599
+ {
3600
+ "Batch Mean": 1.196899652481079,
3601
+ "accuracy": 0.7890625,
3602
+ "epoch": 0.69,
3603
+ "step": 276
3604
+ },
3605
+ {
3606
+ "epoch": 0.6925,
3607
+ "grad_norm": 9.034087181091309,
3608
+ "learning_rate": 1.618421052631579e-06,
3609
+ "loss": 0.4123,
3610
+ "step": 277
3611
+ },
3612
+ {
3613
+ "Batch Mean": 1.1326861381530762,
3614
+ "accuracy": 0.828125,
3615
+ "epoch": 0.6925,
3616
+ "step": 277
3617
+ },
3618
+ {
3619
+ "epoch": 0.695,
3620
+ "grad_norm": 7.901162624359131,
3621
+ "learning_rate": 1.605263157894737e-06,
3622
+ "loss": 0.3597,
3623
+ "step": 278
3624
+ },
3625
+ {
3626
+ "Batch Mean": 0.9996824264526367,
3627
+ "accuracy": 0.8359375,
3628
+ "epoch": 0.695,
3629
+ "step": 278
3630
+ },
3631
+ {
3632
+ "epoch": 0.6975,
3633
+ "grad_norm": 8.420028686523438,
3634
+ "learning_rate": 1.5921052631578949e-06,
3635
+ "loss": 0.3625,
3636
+ "step": 279
3637
+ },
3638
+ {
3639
+ "Batch Mean": 1.1864922046661377,
3640
+ "accuracy": 0.8046875,
3641
+ "epoch": 0.6975,
3642
+ "step": 279
3643
+ },
3644
+ {
3645
+ "epoch": 0.7,
3646
+ "grad_norm": 8.587984085083008,
3647
+ "learning_rate": 1.5789473684210526e-06,
3648
+ "loss": 0.4278,
3649
+ "step": 280
3650
+ },
3651
+ {
3652
+ "Batch Mean": 1.194761037826538,
3653
+ "accuracy": 0.78125,
3654
+ "epoch": 0.7,
3655
+ "step": 280
3656
+ },
3657
+ {
3658
+ "epoch": 0.7025,
3659
+ "grad_norm": 9.341832160949707,
3660
+ "learning_rate": 1.5657894736842105e-06,
3661
+ "loss": 0.4657,
3662
+ "step": 281
3663
+ },
3664
+ {
3665
+ "Batch Mean": 1.2568970918655396,
3666
+ "accuracy": 0.8515625,
3667
+ "epoch": 0.7025,
3668
+ "step": 281
3669
+ },
3670
+ {
3671
+ "epoch": 0.705,
3672
+ "grad_norm": 8.656058311462402,
3673
+ "learning_rate": 1.5526315789473686e-06,
3674
+ "loss": 0.3952,
3675
+ "step": 282
3676
+ },
3677
+ {
3678
+ "Batch Mean": 0.6381912231445312,
3679
+ "accuracy": 0.78125,
3680
+ "epoch": 0.705,
3681
+ "step": 282
3682
+ },
3683
+ {
3684
+ "epoch": 0.7075,
3685
+ "grad_norm": 10.641399383544922,
3686
+ "learning_rate": 1.5394736842105265e-06,
3687
+ "loss": 0.4827,
3688
+ "step": 283
3689
+ },
3690
+ {
3691
+ "Batch Mean": 1.1566600799560547,
3692
+ "accuracy": 0.8203125,
3693
+ "epoch": 0.7075,
3694
+ "step": 283
3695
+ },
3696
+ {
3697
+ "epoch": 0.71,
3698
+ "grad_norm": 8.96735668182373,
3699
+ "learning_rate": 1.5263157894736844e-06,
3700
+ "loss": 0.3853,
3701
+ "step": 284
3702
+ },
3703
+ {
3704
+ "Batch Mean": 0.9634236693382263,
3705
+ "accuracy": 0.7734375,
3706
+ "epoch": 0.71,
3707
+ "step": 284
3708
+ },
3709
+ {
3710
+ "epoch": 0.7125,
3711
+ "grad_norm": 8.702007293701172,
3712
+ "learning_rate": 1.5131578947368421e-06,
3713
+ "loss": 0.3859,
3714
+ "step": 285
3715
+ },
3716
+ {
3717
+ "Batch Mean": 0.8360998630523682,
3718
+ "accuracy": 0.8125,
3719
+ "epoch": 0.7125,
3720
+ "step": 285
3721
+ },
3722
+ {
3723
+ "epoch": 0.715,
3724
+ "grad_norm": 10.517492294311523,
3725
+ "learning_rate": 1.5e-06,
3726
+ "loss": 0.4453,
3727
+ "step": 286
3728
+ },
3729
+ {
3730
+ "Batch Mean": 0.8578420877456665,
3731
+ "accuracy": 0.8125,
3732
+ "epoch": 0.715,
3733
+ "step": 286
3734
+ },
3735
+ {
3736
+ "epoch": 0.7175,
3737
+ "grad_norm": 10.013699531555176,
3738
+ "learning_rate": 1.486842105263158e-06,
3739
+ "loss": 0.4632,
3740
+ "step": 287
3741
+ },
3742
+ {
3743
+ "Batch Mean": 0.3317883014678955,
3744
+ "accuracy": 0.8203125,
3745
+ "epoch": 0.7175,
3746
+ "step": 287
3747
+ },
3748
+ {
3749
+ "epoch": 0.72,
3750
+ "grad_norm": 8.058357238769531,
3751
+ "learning_rate": 1.4736842105263159e-06,
3752
+ "loss": 0.3923,
3753
+ "step": 288
3754
+ },
3755
+ {
3756
+ "Batch Mean": 0.6622927188873291,
3757
+ "accuracy": 0.78125,
3758
+ "epoch": 0.72,
3759
+ "step": 288
3760
+ },
3761
+ {
3762
+ "epoch": 0.7225,
3763
+ "grad_norm": 8.682968139648438,
3764
+ "learning_rate": 1.460526315789474e-06,
3765
+ "loss": 0.456,
3766
+ "step": 289
3767
+ },
3768
+ {
3769
+ "Batch Mean": 0.6830942630767822,
3770
+ "accuracy": 0.78125,
3771
+ "epoch": 0.7225,
3772
+ "step": 289
3773
+ },
3774
+ {
3775
+ "epoch": 0.725,
3776
+ "grad_norm": 10.149425506591797,
3777
+ "learning_rate": 1.4473684210526317e-06,
3778
+ "loss": 0.4826,
3779
+ "step": 290
3780
+ },
3781
+ {
3782
+ "Batch Mean": 0.3039674758911133,
3783
+ "accuracy": 0.78125,
3784
+ "epoch": 0.725,
3785
+ "step": 290
3786
+ },
3787
+ {
3788
+ "epoch": 0.7275,
3789
+ "grad_norm": 8.727519035339355,
3790
+ "learning_rate": 1.4342105263157896e-06,
3791
+ "loss": 0.4374,
3792
+ "step": 291
3793
+ },
3794
+ {
3795
+ "Batch Mean": 0.27513647079467773,
3796
+ "accuracy": 0.84375,
3797
+ "epoch": 0.7275,
3798
+ "step": 291
3799
+ },
3800
+ {
3801
+ "epoch": 0.73,
3802
+ "grad_norm": 7.006710529327393,
3803
+ "learning_rate": 1.4210526315789475e-06,
3804
+ "loss": 0.3133,
3805
+ "step": 292
3806
+ },
3807
+ {
3808
+ "Batch Mean": 0.6557639837265015,
3809
+ "accuracy": 0.84375,
3810
+ "epoch": 0.73,
3811
+ "step": 292
3812
+ },
3813
+ {
3814
+ "epoch": 0.7325,
3815
+ "grad_norm": 8.32409954071045,
3816
+ "learning_rate": 1.4078947368421054e-06,
3817
+ "loss": 0.3789,
3818
+ "step": 293
3819
+ },
3820
+ {
3821
+ "Batch Mean": 0.34485912322998047,
3822
+ "accuracy": 0.78125,
3823
+ "epoch": 0.7325,
3824
+ "step": 293
3825
+ },
3826
+ {
3827
+ "epoch": 0.735,
3828
+ "grad_norm": 9.060379028320312,
3829
+ "learning_rate": 1.394736842105263e-06,
3830
+ "loss": 0.4696,
3831
+ "step": 294
3832
+ },
3833
+ {
3834
+ "Batch Mean": -0.03677475452423096,
3835
+ "accuracy": 0.796875,
3836
+ "epoch": 0.735,
3837
+ "step": 294
3838
+ },
3839
+ {
3840
+ "epoch": 0.7375,
3841
+ "grad_norm": 8.253447532653809,
3842
+ "learning_rate": 1.3815789473684212e-06,
3843
+ "loss": 0.4298,
3844
+ "step": 295
3845
+ },
3846
+ {
3847
+ "Batch Mean": 0.1854919195175171,
3848
+ "accuracy": 0.796875,
3849
+ "epoch": 0.7375,
3850
+ "step": 295
3851
+ },
3852
+ {
3853
+ "epoch": 0.74,
3854
+ "grad_norm": 7.977970123291016,
3855
+ "learning_rate": 1.3684210526315791e-06,
3856
+ "loss": 0.3875,
3857
+ "step": 296
3858
+ },
3859
+ {
3860
+ "Batch Mean": 0.2770446538925171,
3861
+ "accuracy": 0.7890625,
3862
+ "epoch": 0.74,
3863
+ "step": 296
3864
+ },
3865
+ {
3866
+ "epoch": 0.7425,
3867
+ "grad_norm": 9.434441566467285,
3868
+ "learning_rate": 1.355263157894737e-06,
3869
+ "loss": 0.4307,
3870
+ "step": 297
3871
+ },
3872
+ {
3873
+ "Batch Mean": 0.17018723487854004,
3874
+ "accuracy": 0.703125,
3875
+ "epoch": 0.7425,
3876
+ "step": 297
3877
+ },
3878
+ {
3879
+ "epoch": 0.745,
3880
+ "grad_norm": 9.74467945098877,
3881
+ "learning_rate": 1.342105263157895e-06,
3882
+ "loss": 0.4805,
3883
+ "step": 298
3884
+ },
3885
+ {
3886
+ "Batch Mean": 0.7385026216506958,
3887
+ "accuracy": 0.8359375,
3888
+ "epoch": 0.745,
3889
+ "step": 298
3890
+ },
3891
+ {
3892
+ "epoch": 0.7475,
3893
+ "grad_norm": 7.976377487182617,
3894
+ "learning_rate": 1.3289473684210526e-06,
3895
+ "loss": 0.3466,
3896
+ "step": 299
3897
+ },
3898
+ {
3899
+ "Batch Mean": 0.5781590938568115,
3900
+ "accuracy": 0.796875,
3901
+ "epoch": 0.7475,
3902
+ "step": 299
3903
+ },
3904
+ {
3905
+ "epoch": 0.75,
3906
+ "grad_norm": 8.911229133605957,
3907
+ "learning_rate": 1.3157894736842106e-06,
3908
+ "loss": 0.4001,
3909
+ "step": 300
3910
+ },
3911
+ {
3912
+ "Batch Mean": 0.5454775094985962,
3913
+ "accuracy": 0.7578125,
3914
+ "epoch": 0.75,
3915
+ "step": 300
3916
+ },
3917
+ {
3918
+ "epoch": 0.7525,
3919
+ "grad_norm": 9.226743698120117,
3920
+ "learning_rate": 1.3026315789473685e-06,
3921
+ "loss": 0.4997,
3922
+ "step": 301
3923
+ },
3924
+ {
3925
+ "Batch Mean": 0.7983531951904297,
3926
+ "accuracy": 0.7890625,
3927
+ "epoch": 0.7525,
3928
+ "step": 301
3929
+ },
3930
+ {
3931
+ "epoch": 0.755,
3932
+ "grad_norm": 8.112704277038574,
3933
+ "learning_rate": 1.2894736842105266e-06,
3934
+ "loss": 0.4428,
3935
+ "step": 302
3936
+ },
3937
+ {
3938
+ "Batch Mean": 0.6288890838623047,
3939
+ "accuracy": 0.8046875,
3940
+ "epoch": 0.755,
3941
+ "step": 302
3942
+ },
3943
+ {
3944
+ "epoch": 0.7575,
3945
+ "grad_norm": 8.986902236938477,
3946
+ "learning_rate": 1.2763157894736845e-06,
3947
+ "loss": 0.4304,
3948
+ "step": 303
3949
+ },
3950
+ {
3951
+ "Batch Mean": 0.42789459228515625,
3952
+ "accuracy": 0.75,
3953
+ "epoch": 0.7575,
3954
+ "step": 303
3955
+ },
3956
+ {
3957
+ "epoch": 0.76,
3958
+ "grad_norm": 9.686219215393066,
3959
+ "learning_rate": 1.2631578947368422e-06,
3960
+ "loss": 0.5235,
3961
+ "step": 304
3962
+ },
3963
+ {
3964
+ "Batch Mean": 0.6602230072021484,
3965
+ "accuracy": 0.890625,
3966
+ "epoch": 0.76,
3967
+ "step": 304
3968
+ },
3969
+ {
3970
+ "epoch": 0.7625,
3971
+ "grad_norm": 7.1107048988342285,
3972
+ "learning_rate": 1.25e-06,
3973
+ "loss": 0.3158,
3974
+ "step": 305
3975
+ },
3976
+ {
3977
+ "Batch Mean": 0.4711933135986328,
3978
+ "accuracy": 0.8828125,
3979
+ "epoch": 0.7625,
3980
+ "step": 305
3981
+ },
3982
+ {
3983
+ "epoch": 0.765,
3984
+ "grad_norm": 7.437671184539795,
3985
+ "learning_rate": 1.236842105263158e-06,
3986
+ "loss": 0.3386,
3987
+ "step": 306
3988
+ },
3989
+ {
3990
+ "Batch Mean": 0.9208922386169434,
3991
+ "accuracy": 0.796875,
3992
+ "epoch": 0.765,
3993
+ "step": 306
3994
+ },
3995
+ {
3996
+ "epoch": 0.7675,
3997
+ "grad_norm": 6.951391220092773,
3998
+ "learning_rate": 1.223684210526316e-06,
3999
+ "loss": 0.3802,
4000
+ "step": 307
4001
+ },
4002
+ {
4003
+ "Batch Mean": 0.4036996364593506,
4004
+ "accuracy": 0.75,
4005
+ "epoch": 0.7675,
4006
+ "step": 307
4007
+ },
4008
+ {
4009
+ "epoch": 0.77,
4010
+ "grad_norm": 9.149080276489258,
4011
+ "learning_rate": 1.2105263157894738e-06,
4012
+ "loss": 0.4636,
4013
+ "step": 308
4014
+ },
4015
+ {
4016
+ "Batch Mean": 0.6852213144302368,
4017
+ "accuracy": 0.765625,
4018
+ "epoch": 0.77,
4019
+ "step": 308
4020
+ },
4021
+ {
4022
+ "epoch": 0.7725,
4023
+ "grad_norm": 9.365516662597656,
4024
+ "learning_rate": 1.1973684210526317e-06,
4025
+ "loss": 0.4672,
4026
+ "step": 309
4027
+ },
4028
+ {
4029
+ "Batch Mean": 0.7226486802101135,
4030
+ "accuracy": 0.8125,
4031
+ "epoch": 0.7725,
4032
+ "step": 309
4033
+ },
4034
+ {
4035
+ "epoch": 0.775,
4036
+ "grad_norm": 8.166211128234863,
4037
+ "learning_rate": 1.1842105263157894e-06,
4038
+ "loss": 0.4039,
4039
+ "step": 310
4040
+ },
4041
+ {
4042
+ "Batch Mean": 0.8003917336463928,
4043
+ "accuracy": 0.7890625,
4044
+ "epoch": 0.775,
4045
+ "step": 310
4046
+ },
4047
+ {
4048
+ "epoch": 0.7775,
4049
+ "grad_norm": 8.930299758911133,
4050
+ "learning_rate": 1.1710526315789476e-06,
4051
+ "loss": 0.4418,
4052
+ "step": 311
4053
+ },
4054
+ {
4055
+ "Batch Mean": 0.909870982170105,
4056
+ "accuracy": 0.8046875,
4057
+ "epoch": 0.7775,
4058
+ "step": 311
4059
+ },
4060
+ {
4061
+ "epoch": 0.78,
4062
+ "grad_norm": 8.864906311035156,
4063
+ "learning_rate": 1.1578947368421053e-06,
4064
+ "loss": 0.4414,
4065
+ "step": 312
4066
+ },
4067
+ {
4068
+ "Batch Mean": 0.9025444984436035,
4069
+ "accuracy": 0.7578125,
4070
+ "epoch": 0.78,
4071
+ "step": 312
4072
+ },
4073
+ {
4074
+ "epoch": 0.7825,
4075
+ "grad_norm": 9.02528190612793,
4076
+ "learning_rate": 1.1447368421052632e-06,
4077
+ "loss": 0.4417,
4078
+ "step": 313
4079
+ },
4080
+ {
4081
+ "Batch Mean": 0.7603792548179626,
4082
+ "accuracy": 0.78125,
4083
+ "epoch": 0.7825,
4084
+ "step": 313
4085
+ },
4086
+ {
4087
+ "epoch": 0.785,
4088
+ "grad_norm": 10.754321098327637,
4089
+ "learning_rate": 1.1315789473684213e-06,
4090
+ "loss": 0.504,
4091
+ "step": 314
4092
+ },
4093
+ {
4094
+ "Batch Mean": 0.5785622000694275,
4095
+ "accuracy": 0.8125,
4096
+ "epoch": 0.785,
4097
+ "step": 314
4098
+ },
4099
+ {
4100
+ "epoch": 0.7875,
4101
+ "grad_norm": 7.807627201080322,
4102
+ "learning_rate": 1.118421052631579e-06,
4103
+ "loss": 0.3825,
4104
+ "step": 315
4105
+ },
4106
+ {
4107
+ "Batch Mean": 0.7554885149002075,
4108
+ "accuracy": 0.78125,
4109
+ "epoch": 0.7875,
4110
+ "step": 315
4111
+ },
4112
+ {
4113
+ "epoch": 0.79,
4114
+ "grad_norm": 8.794540405273438,
4115
+ "learning_rate": 1.1052631578947369e-06,
4116
+ "loss": 0.4374,
4117
+ "step": 316
4118
+ },
4119
+ {
4120
+ "Batch Mean": 0.3685053586959839,
4121
+ "accuracy": 0.7890625,
4122
+ "epoch": 0.79,
4123
+ "step": 316
4124
+ },
4125
+ {
4126
+ "epoch": 0.7925,
4127
+ "grad_norm": 7.32318639755249,
4128
+ "learning_rate": 1.0921052631578948e-06,
4129
+ "loss": 0.4272,
4130
+ "step": 317
4131
+ },
4132
+ {
4133
+ "Batch Mean": 0.6454563140869141,
4134
+ "accuracy": 0.7890625,
4135
+ "epoch": 0.7925,
4136
+ "step": 317
4137
+ },
4138
+ {
4139
+ "epoch": 0.795,
4140
+ "grad_norm": 7.675666332244873,
4141
+ "learning_rate": 1.0789473684210527e-06,
4142
+ "loss": 0.3687,
4143
+ "step": 318
4144
+ },
4145
+ {
4146
+ "Batch Mean": 0.39517223834991455,
4147
+ "accuracy": 0.8125,
4148
+ "epoch": 0.795,
4149
+ "step": 318
4150
+ },
4151
+ {
4152
+ "epoch": 0.7975,
4153
+ "grad_norm": 8.13251781463623,
4154
+ "learning_rate": 1.0657894736842106e-06,
4155
+ "loss": 0.4212,
4156
+ "step": 319
4157
+ },
4158
+ {
4159
+ "Batch Mean": 0.754143238067627,
4160
+ "accuracy": 0.8203125,
4161
+ "epoch": 0.7975,
4162
+ "step": 319
4163
+ },
4164
+ {
4165
+ "epoch": 0.8,
4166
+ "grad_norm": 8.40969467163086,
4167
+ "learning_rate": 1.0526315789473685e-06,
4168
+ "loss": 0.4132,
4169
+ "step": 320
4170
+ }
4171
+ ],
4172
+ "logging_steps": 1,
4173
+ "max_steps": 400,
4174
+ "num_input_tokens_seen": 0,
4175
+ "num_train_epochs": 1,
4176
+ "save_steps": 80,
4177
+ "stateful_callbacks": {
4178
+ "TrainerControl": {
4179
+ "args": {
4180
+ "should_epoch_stop": false,
4181
+ "should_evaluate": false,
4182
+ "should_log": false,
4183
+ "should_save": true,
4184
+ "should_training_stop": false
4185
+ },
4186
+ "attributes": {}
4187
+ }
4188
+ },
4189
+ "total_flos": 0.0,
4190
+ "train_batch_size": 64,
4191
+ "trial_name": null,
4192
+ "trial_params": null
4193
+ }
checkpoint-320/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130b9bda9b58e60760405321a76b9b11a12c69620b1886f49451f28ec3960f24
3
+ size 5752
checkpoint-400/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-1B-UC",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "max_position_embeddings": 131072,
26
+ "mlp_bias": false,
27
+ "model_type": "llama",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 16,
30
+ "num_key_value_heads": 8,
31
+ "pad_token_id": 128001,
32
+ "pretraining_tp": 1,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "factor": 32.0,
36
+ "high_freq_factor": 4.0,
37
+ "low_freq_factor": 1.0,
38
+ "original_max_position_embeddings": 8192,
39
+ "rope_type": "llama3"
40
+ },
41
+ "rope_theta": 500000.0,
42
+ "tie_word_embeddings": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.48.0",
45
+ "use_cache": false,
46
+ "vocab_size": 128256
47
+ }
checkpoint-400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e031fe59032f0d93a3d7ff05b080ca8a848a41fd886b7759ce5dede721263f
3
+ size 4943282608
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
checkpoint-400/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130b9bda9b58e60760405321a76b9b11a12c69620b1886f49451f28ec3960f24
3
+ size 5752
checkpoint-80/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-1B-UC",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "max_position_embeddings": 131072,
26
+ "mlp_bias": false,
27
+ "model_type": "llama",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 16,
30
+ "num_key_value_heads": 8,
31
+ "pad_token_id": 128001,
32
+ "pretraining_tp": 1,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "factor": 32.0,
36
+ "high_freq_factor": 4.0,
37
+ "low_freq_factor": 1.0,
38
+ "original_max_position_embeddings": 8192,
39
+ "rope_type": "llama3"
40
+ },
41
+ "rope_theta": 500000.0,
42
+ "tie_word_embeddings": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.48.0",
45
+ "use_cache": false,
46
+ "vocab_size": 128256
47
+ }
checkpoint-80/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c83b9cedd22f865f6b74170bb603039ac00e8a946e80aba70f079a6240ffad7d
3
+ size 4943282608
checkpoint-80/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-80/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-80/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
checkpoint-80/trainer_state.json ADDED
@@ -0,0 +1,1073 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2,
5
+ "eval_steps": 500,
6
+ "global_step": 80,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "Batch Mean": 2.64666748046875,
13
+ "accuracy": 0.484375,
14
+ "epoch": 0,
15
+ "step": 0
16
+ },
17
+ {
18
+ "epoch": 0.0025,
19
+ "grad_norm": 9.6364107131958,
20
+ "learning_rate": 2.5000000000000004e-07,
21
+ "loss": 0.723,
22
+ "step": 1
23
+ },
24
+ {
25
+ "Batch Mean": 2.6478805541992188,
26
+ "accuracy": 0.46875,
27
+ "epoch": 0.0025,
28
+ "step": 1
29
+ },
30
+ {
31
+ "epoch": 0.005,
32
+ "grad_norm": 7.393254280090332,
33
+ "learning_rate": 5.000000000000001e-07,
34
+ "loss": 0.7006,
35
+ "step": 2
36
+ },
37
+ {
38
+ "Batch Mean": 2.62982177734375,
39
+ "accuracy": 0.4453125,
40
+ "epoch": 0.005,
41
+ "step": 2
42
+ },
43
+ {
44
+ "epoch": 0.0075,
45
+ "grad_norm": 8.464498519897461,
46
+ "learning_rate": 7.5e-07,
47
+ "loss": 0.7093,
48
+ "step": 3
49
+ },
50
+ {
51
+ "Batch Mean": 2.6655197143554688,
52
+ "accuracy": 0.5,
53
+ "epoch": 0.0075,
54
+ "step": 3
55
+ },
56
+ {
57
+ "epoch": 0.01,
58
+ "grad_norm": 7.2742462158203125,
59
+ "learning_rate": 1.0000000000000002e-06,
60
+ "loss": 0.7101,
61
+ "step": 4
62
+ },
63
+ {
64
+ "Batch Mean": 2.616424560546875,
65
+ "accuracy": 0.4296875,
66
+ "epoch": 0.01,
67
+ "step": 4
68
+ },
69
+ {
70
+ "epoch": 0.0125,
71
+ "grad_norm": 8.216493606567383,
72
+ "learning_rate": 1.25e-06,
73
+ "loss": 0.7145,
74
+ "step": 5
75
+ },
76
+ {
77
+ "Batch Mean": 2.6591033935546875,
78
+ "accuracy": 0.546875,
79
+ "epoch": 0.0125,
80
+ "step": 5
81
+ },
82
+ {
83
+ "epoch": 0.015,
84
+ "grad_norm": 8.033185958862305,
85
+ "learning_rate": 1.5e-06,
86
+ "loss": 0.6821,
87
+ "step": 6
88
+ },
89
+ {
90
+ "Batch Mean": 2.6329345703125,
91
+ "accuracy": 0.640625,
92
+ "epoch": 0.015,
93
+ "step": 6
94
+ },
95
+ {
96
+ "epoch": 0.0175,
97
+ "grad_norm": 10.476421356201172,
98
+ "learning_rate": 1.75e-06,
99
+ "loss": 0.6911,
100
+ "step": 7
101
+ },
102
+ {
103
+ "Batch Mean": 2.680908203125,
104
+ "accuracy": 0.5859375,
105
+ "epoch": 0.0175,
106
+ "step": 7
107
+ },
108
+ {
109
+ "epoch": 0.02,
110
+ "grad_norm": 9.513436317443848,
111
+ "learning_rate": 2.0000000000000003e-06,
112
+ "loss": 0.6859,
113
+ "step": 8
114
+ },
115
+ {
116
+ "Batch Mean": 2.658843994140625,
117
+ "accuracy": 0.53125,
118
+ "epoch": 0.02,
119
+ "step": 8
120
+ },
121
+ {
122
+ "epoch": 0.0225,
123
+ "grad_norm": 7.415161609649658,
124
+ "learning_rate": 2.25e-06,
125
+ "loss": 0.6839,
126
+ "step": 9
127
+ },
128
+ {
129
+ "Batch Mean": 2.74237060546875,
130
+ "accuracy": 0.6328125,
131
+ "epoch": 0.0225,
132
+ "step": 9
133
+ },
134
+ {
135
+ "epoch": 0.025,
136
+ "grad_norm": 6.572882175445557,
137
+ "learning_rate": 2.5e-06,
138
+ "loss": 0.6557,
139
+ "step": 10
140
+ },
141
+ {
142
+ "Batch Mean": 2.9183349609375,
143
+ "accuracy": 0.65625,
144
+ "epoch": 0.025,
145
+ "step": 10
146
+ },
147
+ {
148
+ "epoch": 0.0275,
149
+ "grad_norm": 6.594631671905518,
150
+ "learning_rate": 2.7500000000000004e-06,
151
+ "loss": 0.6336,
152
+ "step": 11
153
+ },
154
+ {
155
+ "Batch Mean": 2.929656982421875,
156
+ "accuracy": 0.546875,
157
+ "epoch": 0.0275,
158
+ "step": 11
159
+ },
160
+ {
161
+ "epoch": 0.03,
162
+ "grad_norm": 6.199557304382324,
163
+ "learning_rate": 3e-06,
164
+ "loss": 0.6784,
165
+ "step": 12
166
+ },
167
+ {
168
+ "Batch Mean": 2.938323974609375,
169
+ "accuracy": 0.59375,
170
+ "epoch": 0.03,
171
+ "step": 12
172
+ },
173
+ {
174
+ "epoch": 0.0325,
175
+ "grad_norm": 8.091628074645996,
176
+ "learning_rate": 3.2500000000000002e-06,
177
+ "loss": 0.6887,
178
+ "step": 13
179
+ },
180
+ {
181
+ "Batch Mean": 3.0481414794921875,
182
+ "accuracy": 0.6171875,
183
+ "epoch": 0.0325,
184
+ "step": 13
185
+ },
186
+ {
187
+ "epoch": 0.035,
188
+ "grad_norm": 8.876925468444824,
189
+ "learning_rate": 3.5e-06,
190
+ "loss": 0.6421,
191
+ "step": 14
192
+ },
193
+ {
194
+ "Batch Mean": 3.2818450927734375,
195
+ "accuracy": 0.703125,
196
+ "epoch": 0.035,
197
+ "step": 14
198
+ },
199
+ {
200
+ "epoch": 0.0375,
201
+ "grad_norm": 10.33357048034668,
202
+ "learning_rate": 3.7500000000000005e-06,
203
+ "loss": 0.5853,
204
+ "step": 15
205
+ },
206
+ {
207
+ "Batch Mean": 3.2837677001953125,
208
+ "accuracy": 0.625,
209
+ "epoch": 0.0375,
210
+ "step": 15
211
+ },
212
+ {
213
+ "epoch": 0.04,
214
+ "grad_norm": 11.141650199890137,
215
+ "learning_rate": 4.000000000000001e-06,
216
+ "loss": 0.6495,
217
+ "step": 16
218
+ },
219
+ {
220
+ "Batch Mean": 3.2836532592773438,
221
+ "accuracy": 0.6015625,
222
+ "epoch": 0.04,
223
+ "step": 16
224
+ },
225
+ {
226
+ "epoch": 0.0425,
227
+ "grad_norm": 8.093420028686523,
228
+ "learning_rate": 4.25e-06,
229
+ "loss": 0.6607,
230
+ "step": 17
231
+ },
232
+ {
233
+ "Batch Mean": 3.3738174438476562,
234
+ "accuracy": 0.65625,
235
+ "epoch": 0.0425,
236
+ "step": 17
237
+ },
238
+ {
239
+ "epoch": 0.045,
240
+ "grad_norm": 8.171963691711426,
241
+ "learning_rate": 4.5e-06,
242
+ "loss": 0.5946,
243
+ "step": 18
244
+ },
245
+ {
246
+ "Batch Mean": 3.8035507202148438,
247
+ "accuracy": 0.6015625,
248
+ "epoch": 0.045,
249
+ "step": 18
250
+ },
251
+ {
252
+ "epoch": 0.0475,
253
+ "grad_norm": 10.379010200500488,
254
+ "learning_rate": 4.75e-06,
255
+ "loss": 0.62,
256
+ "step": 19
257
+ },
258
+ {
259
+ "Batch Mean": 4.241037845611572,
260
+ "accuracy": 0.7421875,
261
+ "epoch": 0.0475,
262
+ "step": 19
263
+ },
264
+ {
265
+ "epoch": 0.05,
266
+ "grad_norm": 8.072366714477539,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6094,
269
+ "step": 20
270
+ },
271
+ {
272
+ "Batch Mean": 4.397010803222656,
273
+ "accuracy": 0.65625,
274
+ "epoch": 0.05,
275
+ "step": 20
276
+ },
277
+ {
278
+ "epoch": 0.0525,
279
+ "grad_norm": 7.2537384033203125,
280
+ "learning_rate": 4.986842105263158e-06,
281
+ "loss": 0.5916,
282
+ "step": 21
283
+ },
284
+ {
285
+ "Batch Mean": 4.36688232421875,
286
+ "accuracy": 0.671875,
287
+ "epoch": 0.0525,
288
+ "step": 21
289
+ },
290
+ {
291
+ "epoch": 0.055,
292
+ "grad_norm": 8.559549331665039,
293
+ "learning_rate": 4.973684210526316e-06,
294
+ "loss": 0.5884,
295
+ "step": 22
296
+ },
297
+ {
298
+ "Batch Mean": 4.482940673828125,
299
+ "accuracy": 0.6640625,
300
+ "epoch": 0.055,
301
+ "step": 22
302
+ },
303
+ {
304
+ "epoch": 0.0575,
305
+ "grad_norm": 8.731099128723145,
306
+ "learning_rate": 4.960526315789474e-06,
307
+ "loss": 0.6106,
308
+ "step": 23
309
+ },
310
+ {
311
+ "Batch Mean": 4.41278076171875,
312
+ "accuracy": 0.7109375,
313
+ "epoch": 0.0575,
314
+ "step": 23
315
+ },
316
+ {
317
+ "epoch": 0.06,
318
+ "grad_norm": 6.149895191192627,
319
+ "learning_rate": 4.947368421052632e-06,
320
+ "loss": 0.5569,
321
+ "step": 24
322
+ },
323
+ {
324
+ "Batch Mean": 4.1328277587890625,
325
+ "accuracy": 0.6484375,
326
+ "epoch": 0.06,
327
+ "step": 24
328
+ },
329
+ {
330
+ "epoch": 0.0625,
331
+ "grad_norm": 6.8678879737854,
332
+ "learning_rate": 4.9342105263157895e-06,
333
+ "loss": 0.5729,
334
+ "step": 25
335
+ },
336
+ {
337
+ "Batch Mean": 3.8360061645507812,
338
+ "accuracy": 0.6484375,
339
+ "epoch": 0.0625,
340
+ "step": 25
341
+ },
342
+ {
343
+ "epoch": 0.065,
344
+ "grad_norm": 6.591639041900635,
345
+ "learning_rate": 4.921052631578948e-06,
346
+ "loss": 0.5902,
347
+ "step": 26
348
+ },
349
+ {
350
+ "Batch Mean": 3.9048538208007812,
351
+ "accuracy": 0.6953125,
352
+ "epoch": 0.065,
353
+ "step": 26
354
+ },
355
+ {
356
+ "epoch": 0.0675,
357
+ "grad_norm": 5.855933666229248,
358
+ "learning_rate": 4.907894736842106e-06,
359
+ "loss": 0.5666,
360
+ "step": 27
361
+ },
362
+ {
363
+ "Batch Mean": 3.7672348022460938,
364
+ "accuracy": 0.6953125,
365
+ "epoch": 0.0675,
366
+ "step": 27
367
+ },
368
+ {
369
+ "epoch": 0.07,
370
+ "grad_norm": 5.393594264984131,
371
+ "learning_rate": 4.894736842105264e-06,
372
+ "loss": 0.5508,
373
+ "step": 28
374
+ },
375
+ {
376
+ "Batch Mean": 3.723773956298828,
377
+ "accuracy": 0.65625,
378
+ "epoch": 0.07,
379
+ "step": 28
380
+ },
381
+ {
382
+ "epoch": 0.0725,
383
+ "grad_norm": 5.428353786468506,
384
+ "learning_rate": 4.881578947368422e-06,
385
+ "loss": 0.5694,
386
+ "step": 29
387
+ },
388
+ {
389
+ "Batch Mean": 3.7498779296875,
390
+ "accuracy": 0.6953125,
391
+ "epoch": 0.0725,
392
+ "step": 29
393
+ },
394
+ {
395
+ "epoch": 0.075,
396
+ "grad_norm": 5.005551338195801,
397
+ "learning_rate": 4.8684210526315795e-06,
398
+ "loss": 0.5905,
399
+ "step": 30
400
+ },
401
+ {
402
+ "Batch Mean": 3.564330577850342,
403
+ "accuracy": 0.671875,
404
+ "epoch": 0.075,
405
+ "step": 30
406
+ },
407
+ {
408
+ "epoch": 0.0775,
409
+ "grad_norm": 6.4090681076049805,
410
+ "learning_rate": 4.855263157894737e-06,
411
+ "loss": 0.5901,
412
+ "step": 31
413
+ },
414
+ {
415
+ "Batch Mean": 3.5886306762695312,
416
+ "accuracy": 0.7421875,
417
+ "epoch": 0.0775,
418
+ "step": 31
419
+ },
420
+ {
421
+ "epoch": 0.08,
422
+ "grad_norm": 6.025192737579346,
423
+ "learning_rate": 4.842105263157895e-06,
424
+ "loss": 0.5265,
425
+ "step": 32
426
+ },
427
+ {
428
+ "Batch Mean": 3.64593505859375,
429
+ "accuracy": 0.6953125,
430
+ "epoch": 0.08,
431
+ "step": 32
432
+ },
433
+ {
434
+ "epoch": 0.0825,
435
+ "grad_norm": 6.129398345947266,
436
+ "learning_rate": 4.828947368421053e-06,
437
+ "loss": 0.5083,
438
+ "step": 33
439
+ },
440
+ {
441
+ "Batch Mean": 3.5973358154296875,
442
+ "accuracy": 0.6875,
443
+ "epoch": 0.0825,
444
+ "step": 33
445
+ },
446
+ {
447
+ "epoch": 0.085,
448
+ "grad_norm": 6.91660737991333,
449
+ "learning_rate": 4.815789473684211e-06,
450
+ "loss": 0.5365,
451
+ "step": 34
452
+ },
453
+ {
454
+ "Batch Mean": 3.6286163330078125,
455
+ "accuracy": 0.7109375,
456
+ "epoch": 0.085,
457
+ "step": 34
458
+ },
459
+ {
460
+ "epoch": 0.0875,
461
+ "grad_norm": 7.553361892700195,
462
+ "learning_rate": 4.802631578947369e-06,
463
+ "loss": 0.5196,
464
+ "step": 35
465
+ },
466
+ {
467
+ "Batch Mean": 3.5937328338623047,
468
+ "accuracy": 0.7109375,
469
+ "epoch": 0.0875,
470
+ "step": 35
471
+ },
472
+ {
473
+ "epoch": 0.09,
474
+ "grad_norm": 7.884591579437256,
475
+ "learning_rate": 4.789473684210527e-06,
476
+ "loss": 0.5533,
477
+ "step": 36
478
+ },
479
+ {
480
+ "Batch Mean": 3.28558349609375,
481
+ "accuracy": 0.6796875,
482
+ "epoch": 0.09,
483
+ "step": 36
484
+ },
485
+ {
486
+ "epoch": 0.0925,
487
+ "grad_norm": 8.118135452270508,
488
+ "learning_rate": 4.7763157894736844e-06,
489
+ "loss": 0.5145,
490
+ "step": 37
491
+ },
492
+ {
493
+ "Batch Mean": 3.079477310180664,
494
+ "accuracy": 0.7421875,
495
+ "epoch": 0.0925,
496
+ "step": 37
497
+ },
498
+ {
499
+ "epoch": 0.095,
500
+ "grad_norm": 10.431463241577148,
501
+ "learning_rate": 4.763157894736842e-06,
502
+ "loss": 0.6,
503
+ "step": 38
504
+ },
505
+ {
506
+ "Batch Mean": 2.9296703338623047,
507
+ "accuracy": 0.7578125,
508
+ "epoch": 0.095,
509
+ "step": 38
510
+ },
511
+ {
512
+ "epoch": 0.0975,
513
+ "grad_norm": 8.055816650390625,
514
+ "learning_rate": 4.75e-06,
515
+ "loss": 0.445,
516
+ "step": 39
517
+ },
518
+ {
519
+ "Batch Mean": 2.9282093048095703,
520
+ "accuracy": 0.7109375,
521
+ "epoch": 0.0975,
522
+ "step": 39
523
+ },
524
+ {
525
+ "epoch": 0.1,
526
+ "grad_norm": 9.155073165893555,
527
+ "learning_rate": 4.736842105263158e-06,
528
+ "loss": 0.5568,
529
+ "step": 40
530
+ },
531
+ {
532
+ "Batch Mean": 2.4473862648010254,
533
+ "accuracy": 0.6171875,
534
+ "epoch": 0.1,
535
+ "step": 40
536
+ },
537
+ {
538
+ "epoch": 0.1025,
539
+ "grad_norm": 8.89163589477539,
540
+ "learning_rate": 4.723684210526316e-06,
541
+ "loss": 0.5934,
542
+ "step": 41
543
+ },
544
+ {
545
+ "Batch Mean": 2.4439845085144043,
546
+ "accuracy": 0.6953125,
547
+ "epoch": 0.1025,
548
+ "step": 41
549
+ },
550
+ {
551
+ "epoch": 0.105,
552
+ "grad_norm": 7.411705017089844,
553
+ "learning_rate": 4.710526315789474e-06,
554
+ "loss": 0.5522,
555
+ "step": 42
556
+ },
557
+ {
558
+ "Batch Mean": 1.7335999011993408,
559
+ "accuracy": 0.734375,
560
+ "epoch": 0.105,
561
+ "step": 42
562
+ },
563
+ {
564
+ "epoch": 0.1075,
565
+ "grad_norm": 7.0730109214782715,
566
+ "learning_rate": 4.697368421052632e-06,
567
+ "loss": 0.5157,
568
+ "step": 43
569
+ },
570
+ {
571
+ "Batch Mean": 1.7379779815673828,
572
+ "accuracy": 0.71875,
573
+ "epoch": 0.1075,
574
+ "step": 43
575
+ },
576
+ {
577
+ "epoch": 0.11,
578
+ "grad_norm": 7.879677772521973,
579
+ "learning_rate": 4.68421052631579e-06,
580
+ "loss": 0.5405,
581
+ "step": 44
582
+ },
583
+ {
584
+ "Batch Mean": 1.7085151672363281,
585
+ "accuracy": 0.6796875,
586
+ "epoch": 0.11,
587
+ "step": 44
588
+ },
589
+ {
590
+ "epoch": 0.1125,
591
+ "grad_norm": 6.630401611328125,
592
+ "learning_rate": 4.671052631578948e-06,
593
+ "loss": 0.564,
594
+ "step": 45
595
+ },
596
+ {
597
+ "Batch Mean": 1.7431907653808594,
598
+ "accuracy": 0.734375,
599
+ "epoch": 0.1125,
600
+ "step": 45
601
+ },
602
+ {
603
+ "epoch": 0.115,
604
+ "grad_norm": 6.569342136383057,
605
+ "learning_rate": 4.657894736842106e-06,
606
+ "loss": 0.4969,
607
+ "step": 46
608
+ },
609
+ {
610
+ "Batch Mean": 2.4792041778564453,
611
+ "accuracy": 0.6953125,
612
+ "epoch": 0.115,
613
+ "step": 46
614
+ },
615
+ {
616
+ "epoch": 0.1175,
617
+ "grad_norm": 6.198298931121826,
618
+ "learning_rate": 4.6447368421052635e-06,
619
+ "loss": 0.5501,
620
+ "step": 47
621
+ },
622
+ {
623
+ "Batch Mean": 2.4960689544677734,
624
+ "accuracy": 0.7578125,
625
+ "epoch": 0.1175,
626
+ "step": 47
627
+ },
628
+ {
629
+ "epoch": 0.12,
630
+ "grad_norm": 5.984739780426025,
631
+ "learning_rate": 4.631578947368421e-06,
632
+ "loss": 0.4513,
633
+ "step": 48
634
+ },
635
+ {
636
+ "Batch Mean": 2.7437705993652344,
637
+ "accuracy": 0.71875,
638
+ "epoch": 0.12,
639
+ "step": 48
640
+ },
641
+ {
642
+ "epoch": 0.1225,
643
+ "grad_norm": 6.669623374938965,
644
+ "learning_rate": 4.618421052631579e-06,
645
+ "loss": 0.5404,
646
+ "step": 49
647
+ },
648
+ {
649
+ "Batch Mean": 2.672210693359375,
650
+ "accuracy": 0.75,
651
+ "epoch": 0.1225,
652
+ "step": 49
653
+ },
654
+ {
655
+ "epoch": 0.125,
656
+ "grad_norm": 6.217676639556885,
657
+ "learning_rate": 4.605263157894737e-06,
658
+ "loss": 0.4668,
659
+ "step": 50
660
+ },
661
+ {
662
+ "Batch Mean": 2.7935009002685547,
663
+ "accuracy": 0.75,
664
+ "epoch": 0.125,
665
+ "step": 50
666
+ },
667
+ {
668
+ "epoch": 0.1275,
669
+ "grad_norm": 7.666802883148193,
670
+ "learning_rate": 4.592105263157895e-06,
671
+ "loss": 0.5491,
672
+ "step": 51
673
+ },
674
+ {
675
+ "Batch Mean": 2.651923179626465,
676
+ "accuracy": 0.734375,
677
+ "epoch": 0.1275,
678
+ "step": 51
679
+ },
680
+ {
681
+ "epoch": 0.13,
682
+ "grad_norm": 9.799866676330566,
683
+ "learning_rate": 4.578947368421053e-06,
684
+ "loss": 0.5173,
685
+ "step": 52
686
+ },
687
+ {
688
+ "Batch Mean": 2.9287376403808594,
689
+ "accuracy": 0.734375,
690
+ "epoch": 0.13,
691
+ "step": 52
692
+ },
693
+ {
694
+ "epoch": 0.1325,
695
+ "grad_norm": 8.577540397644043,
696
+ "learning_rate": 4.565789473684211e-06,
697
+ "loss": 0.5279,
698
+ "step": 53
699
+ },
700
+ {
701
+ "Batch Mean": 3.0377674102783203,
702
+ "accuracy": 0.7265625,
703
+ "epoch": 0.1325,
704
+ "step": 53
705
+ },
706
+ {
707
+ "epoch": 0.135,
708
+ "grad_norm": 8.099453926086426,
709
+ "learning_rate": 4.552631578947369e-06,
710
+ "loss": 0.5122,
711
+ "step": 54
712
+ },
713
+ {
714
+ "Batch Mean": 3.3550057411193848,
715
+ "accuracy": 0.6953125,
716
+ "epoch": 0.135,
717
+ "step": 54
718
+ },
719
+ {
720
+ "epoch": 0.1375,
721
+ "grad_norm": 9.597841262817383,
722
+ "learning_rate": 4.539473684210527e-06,
723
+ "loss": 0.5034,
724
+ "step": 55
725
+ },
726
+ {
727
+ "Batch Mean": 3.3833670616149902,
728
+ "accuracy": 0.7578125,
729
+ "epoch": 0.1375,
730
+ "step": 55
731
+ },
732
+ {
733
+ "epoch": 0.14,
734
+ "grad_norm": 9.208806037902832,
735
+ "learning_rate": 4.526315789473685e-06,
736
+ "loss": 0.53,
737
+ "step": 56
738
+ },
739
+ {
740
+ "Batch Mean": 3.255979537963867,
741
+ "accuracy": 0.7890625,
742
+ "epoch": 0.14,
743
+ "step": 56
744
+ },
745
+ {
746
+ "epoch": 0.1425,
747
+ "grad_norm": 7.923739910125732,
748
+ "learning_rate": 4.513157894736843e-06,
749
+ "loss": 0.4315,
750
+ "step": 57
751
+ },
752
+ {
753
+ "Batch Mean": 3.003221273422241,
754
+ "accuracy": 0.7265625,
755
+ "epoch": 0.1425,
756
+ "step": 57
757
+ },
758
+ {
759
+ "epoch": 0.145,
760
+ "grad_norm": 8.64991569519043,
761
+ "learning_rate": 4.5e-06,
762
+ "loss": 0.5038,
763
+ "step": 58
764
+ },
765
+ {
766
+ "Batch Mean": 3.122058868408203,
767
+ "accuracy": 0.78125,
768
+ "epoch": 0.145,
769
+ "step": 58
770
+ },
771
+ {
772
+ "epoch": 0.1475,
773
+ "grad_norm": 8.633460998535156,
774
+ "learning_rate": 4.4868421052631584e-06,
775
+ "loss": 0.4886,
776
+ "step": 59
777
+ },
778
+ {
779
+ "Batch Mean": 2.8752236366271973,
780
+ "accuracy": 0.7109375,
781
+ "epoch": 0.1475,
782
+ "step": 59
783
+ },
784
+ {
785
+ "epoch": 0.15,
786
+ "grad_norm": 8.399279594421387,
787
+ "learning_rate": 4.473684210526316e-06,
788
+ "loss": 0.5239,
789
+ "step": 60
790
+ },
791
+ {
792
+ "Batch Mean": 2.694100856781006,
793
+ "accuracy": 0.7578125,
794
+ "epoch": 0.15,
795
+ "step": 60
796
+ },
797
+ {
798
+ "epoch": 0.1525,
799
+ "grad_norm": 7.846778869628906,
800
+ "learning_rate": 4.460526315789474e-06,
801
+ "loss": 0.4538,
802
+ "step": 61
803
+ },
804
+ {
805
+ "Batch Mean": 2.59914493560791,
806
+ "accuracy": 0.8046875,
807
+ "epoch": 0.1525,
808
+ "step": 61
809
+ },
810
+ {
811
+ "epoch": 0.155,
812
+ "grad_norm": 7.844125270843506,
813
+ "learning_rate": 4.447368421052632e-06,
814
+ "loss": 0.4234,
815
+ "step": 62
816
+ },
817
+ {
818
+ "Batch Mean": 2.431262493133545,
819
+ "accuracy": 0.75,
820
+ "epoch": 0.155,
821
+ "step": 62
822
+ },
823
+ {
824
+ "epoch": 0.1575,
825
+ "grad_norm": 8.15548038482666,
826
+ "learning_rate": 4.43421052631579e-06,
827
+ "loss": 0.4695,
828
+ "step": 63
829
+ },
830
+ {
831
+ "Batch Mean": 2.162135124206543,
832
+ "accuracy": 0.7421875,
833
+ "epoch": 0.1575,
834
+ "step": 63
835
+ },
836
+ {
837
+ "epoch": 0.16,
838
+ "grad_norm": 9.166322708129883,
839
+ "learning_rate": 4.4210526315789476e-06,
840
+ "loss": 0.4898,
841
+ "step": 64
842
+ },
843
+ {
844
+ "Batch Mean": 1.8282737731933594,
845
+ "accuracy": 0.75,
846
+ "epoch": 0.16,
847
+ "step": 64
848
+ },
849
+ {
850
+ "epoch": 0.1625,
851
+ "grad_norm": 9.52655029296875,
852
+ "learning_rate": 4.407894736842105e-06,
853
+ "loss": 0.4651,
854
+ "step": 65
855
+ },
856
+ {
857
+ "Batch Mean": 1.9480819702148438,
858
+ "accuracy": 0.7890625,
859
+ "epoch": 0.1625,
860
+ "step": 65
861
+ },
862
+ {
863
+ "epoch": 0.165,
864
+ "grad_norm": 8.491720199584961,
865
+ "learning_rate": 4.394736842105263e-06,
866
+ "loss": 0.4578,
867
+ "step": 66
868
+ },
869
+ {
870
+ "Batch Mean": 1.8442394733428955,
871
+ "accuracy": 0.7734375,
872
+ "epoch": 0.165,
873
+ "step": 66
874
+ },
875
+ {
876
+ "epoch": 0.1675,
877
+ "grad_norm": 9.01707649230957,
878
+ "learning_rate": 4.381578947368421e-06,
879
+ "loss": 0.4858,
880
+ "step": 67
881
+ },
882
+ {
883
+ "Batch Mean": 1.2759554386138916,
884
+ "accuracy": 0.6953125,
885
+ "epoch": 0.1675,
886
+ "step": 67
887
+ },
888
+ {
889
+ "epoch": 0.17,
890
+ "grad_norm": 10.790990829467773,
891
+ "learning_rate": 4.368421052631579e-06,
892
+ "loss": 0.5368,
893
+ "step": 68
894
+ },
895
+ {
896
+ "Batch Mean": 0.916658878326416,
897
+ "accuracy": 0.7109375,
898
+ "epoch": 0.17,
899
+ "step": 68
900
+ },
901
+ {
902
+ "epoch": 0.1725,
903
+ "grad_norm": 10.27574634552002,
904
+ "learning_rate": 4.3552631578947375e-06,
905
+ "loss": 0.5475,
906
+ "step": 69
907
+ },
908
+ {
909
+ "Batch Mean": 0.9389474391937256,
910
+ "accuracy": 0.6875,
911
+ "epoch": 0.1725,
912
+ "step": 69
913
+ },
914
+ {
915
+ "epoch": 0.175,
916
+ "grad_norm": 9.463624954223633,
917
+ "learning_rate": 4.342105263157895e-06,
918
+ "loss": 0.5295,
919
+ "step": 70
920
+ },
921
+ {
922
+ "Batch Mean": 0.6801865100860596,
923
+ "accuracy": 0.78125,
924
+ "epoch": 0.175,
925
+ "step": 70
926
+ },
927
+ {
928
+ "epoch": 0.1775,
929
+ "grad_norm": 7.813968658447266,
930
+ "learning_rate": 4.328947368421053e-06,
931
+ "loss": 0.4602,
932
+ "step": 71
933
+ },
934
+ {
935
+ "Batch Mean": 0.6634016036987305,
936
+ "accuracy": 0.78125,
937
+ "epoch": 0.1775,
938
+ "step": 71
939
+ },
940
+ {
941
+ "epoch": 0.18,
942
+ "grad_norm": 7.322629928588867,
943
+ "learning_rate": 4.315789473684211e-06,
944
+ "loss": 0.4328,
945
+ "step": 72
946
+ },
947
+ {
948
+ "Batch Mean": 0.518225908279419,
949
+ "accuracy": 0.8359375,
950
+ "epoch": 0.18,
951
+ "step": 72
952
+ },
953
+ {
954
+ "epoch": 0.1825,
955
+ "grad_norm": 7.121971130371094,
956
+ "learning_rate": 4.302631578947369e-06,
957
+ "loss": 0.3997,
958
+ "step": 73
959
+ },
960
+ {
961
+ "Batch Mean": 0.6286078691482544,
962
+ "accuracy": 0.75,
963
+ "epoch": 0.1825,
964
+ "step": 73
965
+ },
966
+ {
967
+ "epoch": 0.185,
968
+ "grad_norm": 8.812067031860352,
969
+ "learning_rate": 4.289473684210527e-06,
970
+ "loss": 0.5345,
971
+ "step": 74
972
+ },
973
+ {
974
+ "Batch Mean": 0.4055500030517578,
975
+ "accuracy": 0.78125,
976
+ "epoch": 0.185,
977
+ "step": 74
978
+ },
979
+ {
980
+ "epoch": 0.1875,
981
+ "grad_norm": 8.031818389892578,
982
+ "learning_rate": 4.276315789473684e-06,
983
+ "loss": 0.4436,
984
+ "step": 75
985
+ },
986
+ {
987
+ "Batch Mean": 0.6844688057899475,
988
+ "accuracy": 0.6640625,
989
+ "epoch": 0.1875,
990
+ "step": 75
991
+ },
992
+ {
993
+ "epoch": 0.19,
994
+ "grad_norm": 9.14492130279541,
995
+ "learning_rate": 4.2631578947368425e-06,
996
+ "loss": 0.5727,
997
+ "step": 76
998
+ },
999
+ {
1000
+ "Batch Mean": 0.549891471862793,
1001
+ "accuracy": 0.7578125,
1002
+ "epoch": 0.19,
1003
+ "step": 76
1004
+ },
1005
+ {
1006
+ "epoch": 0.1925,
1007
+ "grad_norm": 8.721407890319824,
1008
+ "learning_rate": 4.25e-06,
1009
+ "loss": 0.4997,
1010
+ "step": 77
1011
+ },
1012
+ {
1013
+ "Batch Mean": 0.3632768988609314,
1014
+ "accuracy": 0.703125,
1015
+ "epoch": 0.1925,
1016
+ "step": 77
1017
+ },
1018
+ {
1019
+ "epoch": 0.195,
1020
+ "grad_norm": 8.776328086853027,
1021
+ "learning_rate": 4.236842105263158e-06,
1022
+ "loss": 0.5442,
1023
+ "step": 78
1024
+ },
1025
+ {
1026
+ "Batch Mean": 0.4604153633117676,
1027
+ "accuracy": 0.7421875,
1028
+ "epoch": 0.195,
1029
+ "step": 78
1030
+ },
1031
+ {
1032
+ "epoch": 0.1975,
1033
+ "grad_norm": 7.281062126159668,
1034
+ "learning_rate": 4.223684210526316e-06,
1035
+ "loss": 0.4793,
1036
+ "step": 79
1037
+ },
1038
+ {
1039
+ "Batch Mean": 0.605268120765686,
1040
+ "accuracy": 0.765625,
1041
+ "epoch": 0.1975,
1042
+ "step": 79
1043
+ },
1044
+ {
1045
+ "epoch": 0.2,
1046
+ "grad_norm": 7.533178329467773,
1047
+ "learning_rate": 4.210526315789474e-06,
1048
+ "loss": 0.4338,
1049
+ "step": 80
1050
+ }
1051
+ ],
1052
+ "logging_steps": 1,
1053
+ "max_steps": 400,
1054
+ "num_input_tokens_seen": 0,
1055
+ "num_train_epochs": 1,
1056
+ "save_steps": 80,
1057
+ "stateful_callbacks": {
1058
+ "TrainerControl": {
1059
+ "args": {
1060
+ "should_epoch_stop": false,
1061
+ "should_evaluate": false,
1062
+ "should_log": false,
1063
+ "should_save": true,
1064
+ "should_training_stop": false
1065
+ },
1066
+ "attributes": {}
1067
+ }
1068
+ },
1069
+ "total_flos": 0.0,
1070
+ "train_batch_size": 64,
1071
+ "trial_name": null,
1072
+ "trial_params": null
1073
+ }
checkpoint-80/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130b9bda9b58e60760405321a76b9b11a12c69620b1886f49451f28ec3960f24
3
+ size 5752
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-1B-UC",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "max_position_embeddings": 131072,
26
+ "mlp_bias": false,
27
+ "model_type": "llama",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 16,
30
+ "num_key_value_heads": 8,
31
+ "pad_token_id": 128001,
32
+ "pretraining_tp": 1,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "factor": 32.0,
36
+ "high_freq_factor": 4.0,
37
+ "low_freq_factor": 1.0,
38
+ "original_max_position_embeddings": 8192,
39
+ "rope_type": "llama3"
40
+ },
41
+ "rope_theta": 500000.0,
42
+ "tie_word_embeddings": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.48.0",
45
+ "use_cache": false,
46
+ "vocab_size": 128256
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e031fe59032f0d93a3d7ff05b080ca8a848a41fd886b7759ce5dede721263f
3
+ size 4943282608
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130b9bda9b58e60760405321a76b9b11a12c69620b1886f49451f28ec3960f24
3
+ size 5752