JW17 commited on
Commit
e2010e0
·
verified ·
1 Parent(s): 091e92d

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +3 -0
  2. README.md +55 -0
  3. checkpoint-100/config.json +47 -0
  4. checkpoint-100/model-00001-of-00003.safetensors +3 -0
  5. checkpoint-100/model-00002-of-00003.safetensors +3 -0
  6. checkpoint-100/model-00003-of-00003.safetensors +3 -0
  7. checkpoint-100/model.safetensors.index.json +262 -0
  8. checkpoint-100/special_tokens_map.json +23 -0
  9. checkpoint-100/tokenizer.json +3 -0
  10. checkpoint-100/tokenizer_config.json +2064 -0
  11. checkpoint-100/trainer_state.json +1333 -0
  12. checkpoint-100/training_args.bin +3 -0
  13. checkpoint-200/config.json +47 -0
  14. checkpoint-200/model-00001-of-00003.safetensors +3 -0
  15. checkpoint-200/model-00002-of-00003.safetensors +3 -0
  16. checkpoint-200/model-00003-of-00003.safetensors +3 -0
  17. checkpoint-200/model.safetensors.index.json +262 -0
  18. checkpoint-200/special_tokens_map.json +23 -0
  19. checkpoint-200/tokenizer.json +3 -0
  20. checkpoint-200/tokenizer_config.json +2064 -0
  21. checkpoint-200/trainer_state.json +2633 -0
  22. checkpoint-200/training_args.bin +3 -0
  23. checkpoint-300/config.json +47 -0
  24. checkpoint-300/model-00001-of-00003.safetensors +3 -0
  25. checkpoint-300/model-00002-of-00003.safetensors +3 -0
  26. checkpoint-300/model-00003-of-00003.safetensors +3 -0
  27. checkpoint-300/model.safetensors.index.json +262 -0
  28. checkpoint-300/special_tokens_map.json +23 -0
  29. checkpoint-300/tokenizer.json +3 -0
  30. checkpoint-300/tokenizer_config.json +2064 -0
  31. checkpoint-300/trainer_state.json +3933 -0
  32. checkpoint-300/training_args.bin +3 -0
  33. checkpoint-400/config.json +47 -0
  34. checkpoint-400/model-00001-of-00003.safetensors +3 -0
  35. checkpoint-400/model-00002-of-00003.safetensors +3 -0
  36. checkpoint-400/model-00003-of-00003.safetensors +3 -0
  37. checkpoint-400/model.safetensors.index.json +262 -0
  38. checkpoint-400/special_tokens_map.json +23 -0
  39. checkpoint-400/tokenizer.json +3 -0
  40. checkpoint-400/tokenizer_config.json +2064 -0
  41. checkpoint-400/trainer_state.json +0 -0
  42. checkpoint-400/training_args.bin +3 -0
  43. config.json +47 -0
  44. model-00001-of-00003.safetensors +3 -0
  45. model-00002-of-00003.safetensors +3 -0
  46. model-00003-of-00003.safetensors +3 -0
  47. model.safetensors.index.json +262 -0
  48. special_tokens_map.json +23 -0
  49. tokenizer.json +3 -0
  50. tokenizer_config.json +2064 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: tlrm/L32-3B-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/L32-3B-UC](https://huggingface.co/tlrm/L32-3B-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/cs7ff1kl)
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: 2.5.1
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-100/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-3B-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": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
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": 24,
29
+ "num_hidden_layers": 28,
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-100/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b7905250792f7fc0961c298fb4d05a7db2b4d64a0001bea09b7a13d083e29b
3
+ size 4998767360
checkpoint-100/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c303ad49a5a4fb10adbccc711924b2b1995c2ec6e3ff949bdf8b538d74823c60
3
+ size 4932808968
checkpoint-100/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a58464746fbc1dd2980233819ffe5f8e8b1b7764b00f0b288018980389316bc
3
+ size 2919464544
checkpoint-100/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12851011584
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.norm.weight": "model-00003-of-00003.safetensors",
260
+ "score.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
checkpoint-100/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-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-100/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-100/trainer_state.json ADDED
@@ -0,0 +1,1333 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.25,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
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": 0.7002408504486084,
13
+ "accuracy": 0.53125,
14
+ "epoch": 0,
15
+ "step": 0
16
+ },
17
+ {
18
+ "epoch": 0.0025,
19
+ "grad_norm": 4.865061283111572,
20
+ "learning_rate": 1.5000000000000002e-07,
21
+ "loss": 0.6999,
22
+ "step": 1
23
+ },
24
+ {
25
+ "Batch Mean": 0.7006568908691406,
26
+ "accuracy": 0.5078125,
27
+ "epoch": 0.0025,
28
+ "step": 1
29
+ },
30
+ {
31
+ "epoch": 0.005,
32
+ "grad_norm": 5.116915702819824,
33
+ "learning_rate": 3.0000000000000004e-07,
34
+ "loss": 0.706,
35
+ "step": 2
36
+ },
37
+ {
38
+ "Batch Mean": 0.7036838531494141,
39
+ "accuracy": 0.5625,
40
+ "epoch": 0.005,
41
+ "step": 2
42
+ },
43
+ {
44
+ "epoch": 0.0075,
45
+ "grad_norm": 4.952433109283447,
46
+ "learning_rate": 4.5e-07,
47
+ "loss": 0.6957,
48
+ "step": 3
49
+ },
50
+ {
51
+ "Batch Mean": 0.7087974548339844,
52
+ "accuracy": 0.5546875,
53
+ "epoch": 0.0075,
54
+ "step": 3
55
+ },
56
+ {
57
+ "epoch": 0.01,
58
+ "grad_norm": 5.185088157653809,
59
+ "learning_rate": 6.000000000000001e-07,
60
+ "loss": 0.6974,
61
+ "step": 4
62
+ },
63
+ {
64
+ "Batch Mean": 0.7068939208984375,
65
+ "accuracy": 0.5234375,
66
+ "epoch": 0.01,
67
+ "step": 4
68
+ },
69
+ {
70
+ "epoch": 0.0125,
71
+ "grad_norm": 5.04327392578125,
72
+ "learning_rate": 7.5e-07,
73
+ "loss": 0.7047,
74
+ "step": 5
75
+ },
76
+ {
77
+ "Batch Mean": 0.6315479278564453,
78
+ "accuracy": 0.5234375,
79
+ "epoch": 0.0125,
80
+ "step": 5
81
+ },
82
+ {
83
+ "epoch": 0.015,
84
+ "grad_norm": 4.728168487548828,
85
+ "learning_rate": 9e-07,
86
+ "loss": 0.6932,
87
+ "step": 6
88
+ },
89
+ {
90
+ "Batch Mean": 0.5291571617126465,
91
+ "accuracy": 0.5234375,
92
+ "epoch": 0.015,
93
+ "step": 6
94
+ },
95
+ {
96
+ "epoch": 0.0175,
97
+ "grad_norm": 4.0146050453186035,
98
+ "learning_rate": 1.05e-06,
99
+ "loss": 0.691,
100
+ "step": 7
101
+ },
102
+ {
103
+ "Batch Mean": 0.42229437828063965,
104
+ "accuracy": 0.5546875,
105
+ "epoch": 0.0175,
106
+ "step": 7
107
+ },
108
+ {
109
+ "epoch": 0.02,
110
+ "grad_norm": 3.488922119140625,
111
+ "learning_rate": 1.2000000000000002e-06,
112
+ "loss": 0.6947,
113
+ "step": 8
114
+ },
115
+ {
116
+ "Batch Mean": 0.07428494095802307,
117
+ "accuracy": 0.515625,
118
+ "epoch": 0.02,
119
+ "step": 8
120
+ },
121
+ {
122
+ "epoch": 0.0225,
123
+ "grad_norm": 2.5626139640808105,
124
+ "learning_rate": 1.35e-06,
125
+ "loss": 0.6965,
126
+ "step": 9
127
+ },
128
+ {
129
+ "Batch Mean": -0.1413576304912567,
130
+ "accuracy": 0.5859375,
131
+ "epoch": 0.0225,
132
+ "step": 9
133
+ },
134
+ {
135
+ "epoch": 0.025,
136
+ "grad_norm": 2.776390790939331,
137
+ "learning_rate": 1.5e-06,
138
+ "loss": 0.6784,
139
+ "step": 10
140
+ },
141
+ {
142
+ "Batch Mean": -0.2741769552230835,
143
+ "accuracy": 0.5234375,
144
+ "epoch": 0.025,
145
+ "step": 10
146
+ },
147
+ {
148
+ "epoch": 0.0275,
149
+ "grad_norm": 3.4468233585357666,
150
+ "learning_rate": 1.65e-06,
151
+ "loss": 0.6844,
152
+ "step": 11
153
+ },
154
+ {
155
+ "Batch Mean": -0.45577430725097656,
156
+ "accuracy": 0.5859375,
157
+ "epoch": 0.0275,
158
+ "step": 11
159
+ },
160
+ {
161
+ "epoch": 0.03,
162
+ "grad_norm": 4.281182765960693,
163
+ "learning_rate": 1.8e-06,
164
+ "loss": 0.6753,
165
+ "step": 12
166
+ },
167
+ {
168
+ "Batch Mean": -1.0260009765625,
169
+ "accuracy": 0.65625,
170
+ "epoch": 0.03,
171
+ "step": 12
172
+ },
173
+ {
174
+ "epoch": 0.0325,
175
+ "grad_norm": 6.948849201202393,
176
+ "learning_rate": 1.95e-06,
177
+ "loss": 0.6734,
178
+ "step": 13
179
+ },
180
+ {
181
+ "Batch Mean": -1.1147994995117188,
182
+ "accuracy": 0.6171875,
183
+ "epoch": 0.0325,
184
+ "step": 13
185
+ },
186
+ {
187
+ "epoch": 0.035,
188
+ "grad_norm": 7.589419841766357,
189
+ "learning_rate": 2.1e-06,
190
+ "loss": 0.677,
191
+ "step": 14
192
+ },
193
+ {
194
+ "Batch Mean": -1.0315093994140625,
195
+ "accuracy": 0.65625,
196
+ "epoch": 0.035,
197
+ "step": 14
198
+ },
199
+ {
200
+ "epoch": 0.0375,
201
+ "grad_norm": 7.2146382331848145,
202
+ "learning_rate": 2.25e-06,
203
+ "loss": 0.677,
204
+ "step": 15
205
+ },
206
+ {
207
+ "Batch Mean": -0.8089427947998047,
208
+ "accuracy": 0.65625,
209
+ "epoch": 0.0375,
210
+ "step": 15
211
+ },
212
+ {
213
+ "epoch": 0.04,
214
+ "grad_norm": 6.308068752288818,
215
+ "learning_rate": 2.4000000000000003e-06,
216
+ "loss": 0.6503,
217
+ "step": 16
218
+ },
219
+ {
220
+ "Batch Mean": -0.3669371008872986,
221
+ "accuracy": 0.671875,
222
+ "epoch": 0.04,
223
+ "step": 16
224
+ },
225
+ {
226
+ "epoch": 0.0425,
227
+ "grad_norm": 4.996833324432373,
228
+ "learning_rate": 2.55e-06,
229
+ "loss": 0.617,
230
+ "step": 17
231
+ },
232
+ {
233
+ "Batch Mean": 0.2619136571884155,
234
+ "accuracy": 0.6796875,
235
+ "epoch": 0.0425,
236
+ "step": 17
237
+ },
238
+ {
239
+ "epoch": 0.045,
240
+ "grad_norm": 4.9718918800354,
241
+ "learning_rate": 2.7e-06,
242
+ "loss": 0.5981,
243
+ "step": 18
244
+ },
245
+ {
246
+ "Batch Mean": 1.0361242294311523,
247
+ "accuracy": 0.625,
248
+ "epoch": 0.045,
249
+ "step": 18
250
+ },
251
+ {
252
+ "epoch": 0.0475,
253
+ "grad_norm": 9.635746955871582,
254
+ "learning_rate": 2.85e-06,
255
+ "loss": 0.6236,
256
+ "step": 19
257
+ },
258
+ {
259
+ "Batch Mean": 1.5605192184448242,
260
+ "accuracy": 0.65625,
261
+ "epoch": 0.0475,
262
+ "step": 19
263
+ },
264
+ {
265
+ "epoch": 0.05,
266
+ "grad_norm": 14.90079116821289,
267
+ "learning_rate": 3e-06,
268
+ "loss": 0.6511,
269
+ "step": 20
270
+ },
271
+ {
272
+ "Batch Mean": 1.7601673603057861,
273
+ "accuracy": 0.6796875,
274
+ "epoch": 0.05,
275
+ "step": 20
276
+ },
277
+ {
278
+ "epoch": 0.0525,
279
+ "grad_norm": 16.801076889038086,
280
+ "learning_rate": 2.992105263157895e-06,
281
+ "loss": 0.6712,
282
+ "step": 21
283
+ },
284
+ {
285
+ "Batch Mean": 1.1987818479537964,
286
+ "accuracy": 0.7109375,
287
+ "epoch": 0.0525,
288
+ "step": 21
289
+ },
290
+ {
291
+ "epoch": 0.055,
292
+ "grad_norm": 11.280301094055176,
293
+ "learning_rate": 2.9842105263157896e-06,
294
+ "loss": 0.6033,
295
+ "step": 22
296
+ },
297
+ {
298
+ "Batch Mean": 0.5978413820266724,
299
+ "accuracy": 0.6875,
300
+ "epoch": 0.055,
301
+ "step": 22
302
+ },
303
+ {
304
+ "epoch": 0.0575,
305
+ "grad_norm": 7.414430141448975,
306
+ "learning_rate": 2.9763157894736843e-06,
307
+ "loss": 0.5819,
308
+ "step": 23
309
+ },
310
+ {
311
+ "Batch Mean": -0.20422333478927612,
312
+ "accuracy": 0.6640625,
313
+ "epoch": 0.0575,
314
+ "step": 23
315
+ },
316
+ {
317
+ "epoch": 0.06,
318
+ "grad_norm": 5.717103004455566,
319
+ "learning_rate": 2.968421052631579e-06,
320
+ "loss": 0.638,
321
+ "step": 24
322
+ },
323
+ {
324
+ "Batch Mean": -0.7162615060806274,
325
+ "accuracy": 0.75,
326
+ "epoch": 0.06,
327
+ "step": 24
328
+ },
329
+ {
330
+ "epoch": 0.0625,
331
+ "grad_norm": 7.513117790222168,
332
+ "learning_rate": 2.960526315789474e-06,
333
+ "loss": 0.5851,
334
+ "step": 25
335
+ },
336
+ {
337
+ "Batch Mean": -1.054888129234314,
338
+ "accuracy": 0.6796875,
339
+ "epoch": 0.0625,
340
+ "step": 25
341
+ },
342
+ {
343
+ "epoch": 0.065,
344
+ "grad_norm": 8.300326347351074,
345
+ "learning_rate": 2.9526315789473685e-06,
346
+ "loss": 0.6286,
347
+ "step": 26
348
+ },
349
+ {
350
+ "Batch Mean": -1.1319353580474854,
351
+ "accuracy": 0.703125,
352
+ "epoch": 0.065,
353
+ "step": 26
354
+ },
355
+ {
356
+ "epoch": 0.0675,
357
+ "grad_norm": 9.116662979125977,
358
+ "learning_rate": 2.9447368421052633e-06,
359
+ "loss": 0.6003,
360
+ "step": 27
361
+ },
362
+ {
363
+ "Batch Mean": -0.7403234839439392,
364
+ "accuracy": 0.7265625,
365
+ "epoch": 0.0675,
366
+ "step": 27
367
+ },
368
+ {
369
+ "epoch": 0.07,
370
+ "grad_norm": 6.799551486968994,
371
+ "learning_rate": 2.936842105263158e-06,
372
+ "loss": 0.5383,
373
+ "step": 28
374
+ },
375
+ {
376
+ "Batch Mean": -0.25867950916290283,
377
+ "accuracy": 0.703125,
378
+ "epoch": 0.07,
379
+ "step": 28
380
+ },
381
+ {
382
+ "epoch": 0.0725,
383
+ "grad_norm": 5.493288040161133,
384
+ "learning_rate": 2.9289473684210528e-06,
385
+ "loss": 0.5683,
386
+ "step": 29
387
+ },
388
+ {
389
+ "Batch Mean": 0.4318051338195801,
390
+ "accuracy": 0.6796875,
391
+ "epoch": 0.0725,
392
+ "step": 29
393
+ },
394
+ {
395
+ "epoch": 0.075,
396
+ "grad_norm": 6.373619556427002,
397
+ "learning_rate": 2.9210526315789475e-06,
398
+ "loss": 0.6126,
399
+ "step": 30
400
+ },
401
+ {
402
+ "Batch Mean": 0.8685734272003174,
403
+ "accuracy": 0.7265625,
404
+ "epoch": 0.075,
405
+ "step": 30
406
+ },
407
+ {
408
+ "epoch": 0.0775,
409
+ "grad_norm": 7.750959396362305,
410
+ "learning_rate": 2.9131578947368423e-06,
411
+ "loss": 0.5984,
412
+ "step": 31
413
+ },
414
+ {
415
+ "Batch Mean": 1.1348557472229004,
416
+ "accuracy": 0.6484375,
417
+ "epoch": 0.0775,
418
+ "step": 31
419
+ },
420
+ {
421
+ "epoch": 0.08,
422
+ "grad_norm": 8.742609977722168,
423
+ "learning_rate": 2.905263157894737e-06,
424
+ "loss": 0.6016,
425
+ "step": 32
426
+ },
427
+ {
428
+ "Batch Mean": 0.6863436698913574,
429
+ "accuracy": 0.7421875,
430
+ "epoch": 0.08,
431
+ "step": 32
432
+ },
433
+ {
434
+ "epoch": 0.0825,
435
+ "grad_norm": 6.586100101470947,
436
+ "learning_rate": 2.8973684210526318e-06,
437
+ "loss": 0.5485,
438
+ "step": 33
439
+ },
440
+ {
441
+ "Batch Mean": 0.23023658990859985,
442
+ "accuracy": 0.765625,
443
+ "epoch": 0.0825,
444
+ "step": 33
445
+ },
446
+ {
447
+ "epoch": 0.085,
448
+ "grad_norm": 5.231872081756592,
449
+ "learning_rate": 2.8894736842105265e-06,
450
+ "loss": 0.4999,
451
+ "step": 34
452
+ },
453
+ {
454
+ "Batch Mean": -0.2048710286617279,
455
+ "accuracy": 0.734375,
456
+ "epoch": 0.085,
457
+ "step": 34
458
+ },
459
+ {
460
+ "epoch": 0.0875,
461
+ "grad_norm": 5.551333427429199,
462
+ "learning_rate": 2.8815789473684213e-06,
463
+ "loss": 0.5541,
464
+ "step": 35
465
+ },
466
+ {
467
+ "Batch Mean": -0.4559789299964905,
468
+ "accuracy": 0.7421875,
469
+ "epoch": 0.0875,
470
+ "step": 35
471
+ },
472
+ {
473
+ "epoch": 0.09,
474
+ "grad_norm": 5.972931385040283,
475
+ "learning_rate": 2.873684210526316e-06,
476
+ "loss": 0.5698,
477
+ "step": 36
478
+ },
479
+ {
480
+ "Batch Mean": -0.7627459764480591,
481
+ "accuracy": 0.7734375,
482
+ "epoch": 0.09,
483
+ "step": 36
484
+ },
485
+ {
486
+ "epoch": 0.0925,
487
+ "grad_norm": 7.165839672088623,
488
+ "learning_rate": 2.8657894736842103e-06,
489
+ "loss": 0.5157,
490
+ "step": 37
491
+ },
492
+ {
493
+ "Batch Mean": -0.6894429326057434,
494
+ "accuracy": 0.671875,
495
+ "epoch": 0.0925,
496
+ "step": 37
497
+ },
498
+ {
499
+ "epoch": 0.095,
500
+ "grad_norm": 6.630836009979248,
501
+ "learning_rate": 2.857894736842105e-06,
502
+ "loss": 0.5955,
503
+ "step": 38
504
+ },
505
+ {
506
+ "Batch Mean": -0.2740752696990967,
507
+ "accuracy": 0.734375,
508
+ "epoch": 0.095,
509
+ "step": 38
510
+ },
511
+ {
512
+ "epoch": 0.0975,
513
+ "grad_norm": 6.181252956390381,
514
+ "learning_rate": 2.85e-06,
515
+ "loss": 0.5037,
516
+ "step": 39
517
+ },
518
+ {
519
+ "Batch Mean": -0.09357815980911255,
520
+ "accuracy": 0.734375,
521
+ "epoch": 0.0975,
522
+ "step": 39
523
+ },
524
+ {
525
+ "epoch": 0.1,
526
+ "grad_norm": 6.351346969604492,
527
+ "learning_rate": 2.8421052631578946e-06,
528
+ "loss": 0.5152,
529
+ "step": 40
530
+ },
531
+ {
532
+ "Batch Mean": 0.33483320474624634,
533
+ "accuracy": 0.796875,
534
+ "epoch": 0.1,
535
+ "step": 40
536
+ },
537
+ {
538
+ "epoch": 0.1025,
539
+ "grad_norm": 6.3938117027282715,
540
+ "learning_rate": 2.8342105263157897e-06,
541
+ "loss": 0.4573,
542
+ "step": 41
543
+ },
544
+ {
545
+ "Batch Mean": 0.503718376159668,
546
+ "accuracy": 0.7578125,
547
+ "epoch": 0.1025,
548
+ "step": 41
549
+ },
550
+ {
551
+ "epoch": 0.105,
552
+ "grad_norm": 6.795258522033691,
553
+ "learning_rate": 2.8263157894736845e-06,
554
+ "loss": 0.4923,
555
+ "step": 42
556
+ },
557
+ {
558
+ "Batch Mean": 0.4224682152271271,
559
+ "accuracy": 0.6875,
560
+ "epoch": 0.105,
561
+ "step": 42
562
+ },
563
+ {
564
+ "epoch": 0.1075,
565
+ "grad_norm": 9.03122329711914,
566
+ "learning_rate": 2.8184210526315792e-06,
567
+ "loss": 0.5803,
568
+ "step": 43
569
+ },
570
+ {
571
+ "Batch Mean": 0.11721980571746826,
572
+ "accuracy": 0.8046875,
573
+ "epoch": 0.1075,
574
+ "step": 43
575
+ },
576
+ {
577
+ "epoch": 0.11,
578
+ "grad_norm": 6.323685646057129,
579
+ "learning_rate": 2.810526315789474e-06,
580
+ "loss": 0.4518,
581
+ "step": 44
582
+ },
583
+ {
584
+ "Batch Mean": 0.11213397979736328,
585
+ "accuracy": 0.7734375,
586
+ "epoch": 0.11,
587
+ "step": 44
588
+ },
589
+ {
590
+ "epoch": 0.1125,
591
+ "grad_norm": 6.636176586151123,
592
+ "learning_rate": 2.8026315789473687e-06,
593
+ "loss": 0.4747,
594
+ "step": 45
595
+ },
596
+ {
597
+ "Batch Mean": -0.19074296951293945,
598
+ "accuracy": 0.7421875,
599
+ "epoch": 0.1125,
600
+ "step": 45
601
+ },
602
+ {
603
+ "epoch": 0.115,
604
+ "grad_norm": 8.862186431884766,
605
+ "learning_rate": 2.7947368421052635e-06,
606
+ "loss": 0.5295,
607
+ "step": 46
608
+ },
609
+ {
610
+ "Batch Mean": -0.26628145575523376,
611
+ "accuracy": 0.7578125,
612
+ "epoch": 0.115,
613
+ "step": 46
614
+ },
615
+ {
616
+ "epoch": 0.1175,
617
+ "grad_norm": 9.089022636413574,
618
+ "learning_rate": 2.7868421052631578e-06,
619
+ "loss": 0.5132,
620
+ "step": 47
621
+ },
622
+ {
623
+ "Batch Mean": -0.11882030963897705,
624
+ "accuracy": 0.765625,
625
+ "epoch": 0.1175,
626
+ "step": 47
627
+ },
628
+ {
629
+ "epoch": 0.12,
630
+ "grad_norm": 8.50251293182373,
631
+ "learning_rate": 2.7789473684210525e-06,
632
+ "loss": 0.4904,
633
+ "step": 48
634
+ },
635
+ {
636
+ "Batch Mean": -0.09545481204986572,
637
+ "accuracy": 0.7890625,
638
+ "epoch": 0.12,
639
+ "step": 48
640
+ },
641
+ {
642
+ "epoch": 0.1225,
643
+ "grad_norm": 8.091400146484375,
644
+ "learning_rate": 2.7710526315789473e-06,
645
+ "loss": 0.4615,
646
+ "step": 49
647
+ },
648
+ {
649
+ "Batch Mean": -0.01603543758392334,
650
+ "accuracy": 0.6328125,
651
+ "epoch": 0.1225,
652
+ "step": 49
653
+ },
654
+ {
655
+ "epoch": 0.125,
656
+ "grad_norm": 11.12177562713623,
657
+ "learning_rate": 2.763157894736842e-06,
658
+ "loss": 0.6245,
659
+ "step": 50
660
+ },
661
+ {
662
+ "Batch Mean": -0.03519377112388611,
663
+ "accuracy": 0.6953125,
664
+ "epoch": 0.125,
665
+ "step": 50
666
+ },
667
+ {
668
+ "epoch": 0.1275,
669
+ "grad_norm": 8.476814270019531,
670
+ "learning_rate": 2.7552631578947368e-06,
671
+ "loss": 0.5094,
672
+ "step": 51
673
+ },
674
+ {
675
+ "Batch Mean": -0.07445716857910156,
676
+ "accuracy": 0.765625,
677
+ "epoch": 0.1275,
678
+ "step": 51
679
+ },
680
+ {
681
+ "epoch": 0.13,
682
+ "grad_norm": 8.475494384765625,
683
+ "learning_rate": 2.7473684210526315e-06,
684
+ "loss": 0.464,
685
+ "step": 52
686
+ },
687
+ {
688
+ "Batch Mean": -0.08127522468566895,
689
+ "accuracy": 0.7890625,
690
+ "epoch": 0.13,
691
+ "step": 52
692
+ },
693
+ {
694
+ "epoch": 0.1325,
695
+ "grad_norm": 7.754316806793213,
696
+ "learning_rate": 2.7394736842105263e-06,
697
+ "loss": 0.4618,
698
+ "step": 53
699
+ },
700
+ {
701
+ "Batch Mean": 0.05236625671386719,
702
+ "accuracy": 0.75,
703
+ "epoch": 0.1325,
704
+ "step": 53
705
+ },
706
+ {
707
+ "epoch": 0.135,
708
+ "grad_norm": 7.3552751541137695,
709
+ "learning_rate": 2.7315789473684214e-06,
710
+ "loss": 0.5202,
711
+ "step": 54
712
+ },
713
+ {
714
+ "Batch Mean": -0.08030200004577637,
715
+ "accuracy": 0.765625,
716
+ "epoch": 0.135,
717
+ "step": 54
718
+ },
719
+ {
720
+ "epoch": 0.1375,
721
+ "grad_norm": 8.413111686706543,
722
+ "learning_rate": 2.723684210526316e-06,
723
+ "loss": 0.4902,
724
+ "step": 55
725
+ },
726
+ {
727
+ "Batch Mean": 0.20010590553283691,
728
+ "accuracy": 0.765625,
729
+ "epoch": 0.1375,
730
+ "step": 55
731
+ },
732
+ {
733
+ "epoch": 0.14,
734
+ "grad_norm": 9.49488353729248,
735
+ "learning_rate": 2.715789473684211e-06,
736
+ "loss": 0.4945,
737
+ "step": 56
738
+ },
739
+ {
740
+ "Batch Mean": 0.1068873256444931,
741
+ "accuracy": 0.765625,
742
+ "epoch": 0.14,
743
+ "step": 56
744
+ },
745
+ {
746
+ "epoch": 0.1425,
747
+ "grad_norm": 9.978996276855469,
748
+ "learning_rate": 2.7078947368421052e-06,
749
+ "loss": 0.5936,
750
+ "step": 57
751
+ },
752
+ {
753
+ "Batch Mean": 0.12400929629802704,
754
+ "accuracy": 0.8046875,
755
+ "epoch": 0.1425,
756
+ "step": 57
757
+ },
758
+ {
759
+ "epoch": 0.145,
760
+ "grad_norm": 8.332430839538574,
761
+ "learning_rate": 2.7e-06,
762
+ "loss": 0.4549,
763
+ "step": 58
764
+ },
765
+ {
766
+ "Batch Mean": 0.05874582380056381,
767
+ "accuracy": 0.8125,
768
+ "epoch": 0.145,
769
+ "step": 58
770
+ },
771
+ {
772
+ "epoch": 0.1475,
773
+ "grad_norm": 7.287342548370361,
774
+ "learning_rate": 2.6921052631578947e-06,
775
+ "loss": 0.3996,
776
+ "step": 59
777
+ },
778
+ {
779
+ "Batch Mean": 0.17911481857299805,
780
+ "accuracy": 0.828125,
781
+ "epoch": 0.1475,
782
+ "step": 59
783
+ },
784
+ {
785
+ "epoch": 0.15,
786
+ "grad_norm": 7.197307109832764,
787
+ "learning_rate": 2.6842105263157895e-06,
788
+ "loss": 0.4486,
789
+ "step": 60
790
+ },
791
+ {
792
+ "Batch Mean": -0.0680088996887207,
793
+ "accuracy": 0.7265625,
794
+ "epoch": 0.15,
795
+ "step": 60
796
+ },
797
+ {
798
+ "epoch": 0.1525,
799
+ "grad_norm": 8.422717094421387,
800
+ "learning_rate": 2.6763157894736842e-06,
801
+ "loss": 0.5283,
802
+ "step": 61
803
+ },
804
+ {
805
+ "Batch Mean": -0.1332111358642578,
806
+ "accuracy": 0.7890625,
807
+ "epoch": 0.1525,
808
+ "step": 61
809
+ },
810
+ {
811
+ "epoch": 0.155,
812
+ "grad_norm": 8.836848258972168,
813
+ "learning_rate": 2.668421052631579e-06,
814
+ "loss": 0.4547,
815
+ "step": 62
816
+ },
817
+ {
818
+ "Batch Mean": -0.005272388458251953,
819
+ "accuracy": 0.734375,
820
+ "epoch": 0.155,
821
+ "step": 62
822
+ },
823
+ {
824
+ "epoch": 0.1575,
825
+ "grad_norm": 7.995077133178711,
826
+ "learning_rate": 2.6605263157894737e-06,
827
+ "loss": 0.5227,
828
+ "step": 63
829
+ },
830
+ {
831
+ "Batch Mean": 0.3416769504547119,
832
+ "accuracy": 0.8359375,
833
+ "epoch": 0.1575,
834
+ "step": 63
835
+ },
836
+ {
837
+ "epoch": 0.16,
838
+ "grad_norm": 8.131783485412598,
839
+ "learning_rate": 2.6526315789473685e-06,
840
+ "loss": 0.4191,
841
+ "step": 64
842
+ },
843
+ {
844
+ "Batch Mean": 0.2797560691833496,
845
+ "accuracy": 0.765625,
846
+ "epoch": 0.16,
847
+ "step": 64
848
+ },
849
+ {
850
+ "epoch": 0.1625,
851
+ "grad_norm": 9.04648208618164,
852
+ "learning_rate": 2.644736842105263e-06,
853
+ "loss": 0.4893,
854
+ "step": 65
855
+ },
856
+ {
857
+ "Batch Mean": -0.14584161341190338,
858
+ "accuracy": 0.7734375,
859
+ "epoch": 0.1625,
860
+ "step": 65
861
+ },
862
+ {
863
+ "epoch": 0.165,
864
+ "grad_norm": 8.039698600769043,
865
+ "learning_rate": 2.636842105263158e-06,
866
+ "loss": 0.4753,
867
+ "step": 66
868
+ },
869
+ {
870
+ "Batch Mean": -0.37075191736221313,
871
+ "accuracy": 0.7421875,
872
+ "epoch": 0.165,
873
+ "step": 66
874
+ },
875
+ {
876
+ "epoch": 0.1675,
877
+ "grad_norm": 7.643855094909668,
878
+ "learning_rate": 2.6289473684210527e-06,
879
+ "loss": 0.4424,
880
+ "step": 67
881
+ },
882
+ {
883
+ "Batch Mean": -0.24360448122024536,
884
+ "accuracy": 0.828125,
885
+ "epoch": 0.1675,
886
+ "step": 67
887
+ },
888
+ {
889
+ "epoch": 0.17,
890
+ "grad_norm": 6.892768383026123,
891
+ "learning_rate": 2.6210526315789474e-06,
892
+ "loss": 0.4126,
893
+ "step": 68
894
+ },
895
+ {
896
+ "Batch Mean": -0.0484846830368042,
897
+ "accuracy": 0.734375,
898
+ "epoch": 0.17,
899
+ "step": 68
900
+ },
901
+ {
902
+ "epoch": 0.1725,
903
+ "grad_norm": 10.497048377990723,
904
+ "learning_rate": 2.613157894736842e-06,
905
+ "loss": 0.5242,
906
+ "step": 69
907
+ },
908
+ {
909
+ "Batch Mean": 0.07249626517295837,
910
+ "accuracy": 0.8125,
911
+ "epoch": 0.1725,
912
+ "step": 69
913
+ },
914
+ {
915
+ "epoch": 0.175,
916
+ "grad_norm": 6.990925312042236,
917
+ "learning_rate": 2.605263157894737e-06,
918
+ "loss": 0.4206,
919
+ "step": 70
920
+ },
921
+ {
922
+ "Batch Mean": -0.06337249279022217,
923
+ "accuracy": 0.8125,
924
+ "epoch": 0.175,
925
+ "step": 70
926
+ },
927
+ {
928
+ "epoch": 0.1775,
929
+ "grad_norm": 7.180996417999268,
930
+ "learning_rate": 2.5973684210526317e-06,
931
+ "loss": 0.4412,
932
+ "step": 71
933
+ },
934
+ {
935
+ "Batch Mean": 0.06033170223236084,
936
+ "accuracy": 0.8515625,
937
+ "epoch": 0.1775,
938
+ "step": 71
939
+ },
940
+ {
941
+ "epoch": 0.18,
942
+ "grad_norm": 6.108893871307373,
943
+ "learning_rate": 2.5894736842105264e-06,
944
+ "loss": 0.3576,
945
+ "step": 72
946
+ },
947
+ {
948
+ "Batch Mean": -0.04290449619293213,
949
+ "accuracy": 0.765625,
950
+ "epoch": 0.18,
951
+ "step": 72
952
+ },
953
+ {
954
+ "epoch": 0.1825,
955
+ "grad_norm": 7.272516250610352,
956
+ "learning_rate": 2.581578947368421e-06,
957
+ "loss": 0.487,
958
+ "step": 73
959
+ },
960
+ {
961
+ "Batch Mean": 0.09309220314025879,
962
+ "accuracy": 0.796875,
963
+ "epoch": 0.1825,
964
+ "step": 73
965
+ },
966
+ {
967
+ "epoch": 0.185,
968
+ "grad_norm": 6.689022064208984,
969
+ "learning_rate": 2.573684210526316e-06,
970
+ "loss": 0.4576,
971
+ "step": 74
972
+ },
973
+ {
974
+ "Batch Mean": -0.3521728515625,
975
+ "accuracy": 0.8046875,
976
+ "epoch": 0.185,
977
+ "step": 74
978
+ },
979
+ {
980
+ "epoch": 0.1875,
981
+ "grad_norm": 7.446789264678955,
982
+ "learning_rate": 2.5657894736842107e-06,
983
+ "loss": 0.4537,
984
+ "step": 75
985
+ },
986
+ {
987
+ "Batch Mean": -0.1267460584640503,
988
+ "accuracy": 0.7265625,
989
+ "epoch": 0.1875,
990
+ "step": 75
991
+ },
992
+ {
993
+ "epoch": 0.19,
994
+ "grad_norm": 8.600646018981934,
995
+ "learning_rate": 2.5578947368421054e-06,
996
+ "loss": 0.5066,
997
+ "step": 76
998
+ },
999
+ {
1000
+ "Batch Mean": 0.02230433002114296,
1001
+ "accuracy": 0.7578125,
1002
+ "epoch": 0.19,
1003
+ "step": 76
1004
+ },
1005
+ {
1006
+ "epoch": 0.1925,
1007
+ "grad_norm": 8.842095375061035,
1008
+ "learning_rate": 2.55e-06,
1009
+ "loss": 0.4823,
1010
+ "step": 77
1011
+ },
1012
+ {
1013
+ "Batch Mean": 0.17012596130371094,
1014
+ "accuracy": 0.7890625,
1015
+ "epoch": 0.1925,
1016
+ "step": 77
1017
+ },
1018
+ {
1019
+ "epoch": 0.195,
1020
+ "grad_norm": 6.993001937866211,
1021
+ "learning_rate": 2.542105263157895e-06,
1022
+ "loss": 0.3959,
1023
+ "step": 78
1024
+ },
1025
+ {
1026
+ "Batch Mean": -0.11112558841705322,
1027
+ "accuracy": 0.78125,
1028
+ "epoch": 0.195,
1029
+ "step": 78
1030
+ },
1031
+ {
1032
+ "epoch": 0.1975,
1033
+ "grad_norm": 8.71827220916748,
1034
+ "learning_rate": 2.5342105263157892e-06,
1035
+ "loss": 0.4407,
1036
+ "step": 79
1037
+ },
1038
+ {
1039
+ "Batch Mean": 0.11298668384552002,
1040
+ "accuracy": 0.8515625,
1041
+ "epoch": 0.1975,
1042
+ "step": 79
1043
+ },
1044
+ {
1045
+ "epoch": 0.2,
1046
+ "grad_norm": 7.829047679901123,
1047
+ "learning_rate": 2.526315789473684e-06,
1048
+ "loss": 0.3905,
1049
+ "step": 80
1050
+ },
1051
+ {
1052
+ "Batch Mean": 0.010145187377929688,
1053
+ "accuracy": 0.78125,
1054
+ "epoch": 0.2,
1055
+ "step": 80
1056
+ },
1057
+ {
1058
+ "epoch": 0.2025,
1059
+ "grad_norm": 10.1448335647583,
1060
+ "learning_rate": 2.5184210526315787e-06,
1061
+ "loss": 0.4667,
1062
+ "step": 81
1063
+ },
1064
+ {
1065
+ "Batch Mean": 0.1327219009399414,
1066
+ "accuracy": 0.7890625,
1067
+ "epoch": 0.2025,
1068
+ "step": 81
1069
+ },
1070
+ {
1071
+ "epoch": 0.205,
1072
+ "grad_norm": 7.784322738647461,
1073
+ "learning_rate": 2.510526315789474e-06,
1074
+ "loss": 0.408,
1075
+ "step": 82
1076
+ },
1077
+ {
1078
+ "Batch Mean": 0.3474133014678955,
1079
+ "accuracy": 0.7421875,
1080
+ "epoch": 0.205,
1081
+ "step": 82
1082
+ },
1083
+ {
1084
+ "epoch": 0.2075,
1085
+ "grad_norm": 8.116996765136719,
1086
+ "learning_rate": 2.5026315789473686e-06,
1087
+ "loss": 0.438,
1088
+ "step": 83
1089
+ },
1090
+ {
1091
+ "Batch Mean": 0.2660253047943115,
1092
+ "accuracy": 0.75,
1093
+ "epoch": 0.2075,
1094
+ "step": 83
1095
+ },
1096
+ {
1097
+ "epoch": 0.21,
1098
+ "grad_norm": 7.8381452560424805,
1099
+ "learning_rate": 2.4947368421052634e-06,
1100
+ "loss": 0.4639,
1101
+ "step": 84
1102
+ },
1103
+ {
1104
+ "Batch Mean": 0.004191964864730835,
1105
+ "accuracy": 0.8125,
1106
+ "epoch": 0.21,
1107
+ "step": 84
1108
+ },
1109
+ {
1110
+ "epoch": 0.2125,
1111
+ "grad_norm": 6.7916412353515625,
1112
+ "learning_rate": 2.486842105263158e-06,
1113
+ "loss": 0.3937,
1114
+ "step": 85
1115
+ },
1116
+ {
1117
+ "Batch Mean": -0.4819910526275635,
1118
+ "accuracy": 0.75,
1119
+ "epoch": 0.2125,
1120
+ "step": 85
1121
+ },
1122
+ {
1123
+ "epoch": 0.215,
1124
+ "grad_norm": 8.073772430419922,
1125
+ "learning_rate": 2.478947368421053e-06,
1126
+ "loss": 0.4866,
1127
+ "step": 86
1128
+ },
1129
+ {
1130
+ "Batch Mean": -0.5541934967041016,
1131
+ "accuracy": 0.75,
1132
+ "epoch": 0.215,
1133
+ "step": 86
1134
+ },
1135
+ {
1136
+ "epoch": 0.2175,
1137
+ "grad_norm": 8.677484512329102,
1138
+ "learning_rate": 2.4710526315789476e-06,
1139
+ "loss": 0.503,
1140
+ "step": 87
1141
+ },
1142
+ {
1143
+ "Batch Mean": 0.14371705055236816,
1144
+ "accuracy": 0.7890625,
1145
+ "epoch": 0.2175,
1146
+ "step": 87
1147
+ },
1148
+ {
1149
+ "epoch": 0.22,
1150
+ "grad_norm": 7.931331634521484,
1151
+ "learning_rate": 2.4631578947368424e-06,
1152
+ "loss": 0.4483,
1153
+ "step": 88
1154
+ },
1155
+ {
1156
+ "Batch Mean": 0.013556957244873047,
1157
+ "accuracy": 0.859375,
1158
+ "epoch": 0.22,
1159
+ "step": 88
1160
+ },
1161
+ {
1162
+ "epoch": 0.2225,
1163
+ "grad_norm": 6.920699119567871,
1164
+ "learning_rate": 2.4552631578947367e-06,
1165
+ "loss": 0.3674,
1166
+ "step": 89
1167
+ },
1168
+ {
1169
+ "Batch Mean": -0.11897921562194824,
1170
+ "accuracy": 0.8203125,
1171
+ "epoch": 0.2225,
1172
+ "step": 89
1173
+ },
1174
+ {
1175
+ "epoch": 0.225,
1176
+ "grad_norm": 7.135400295257568,
1177
+ "learning_rate": 2.4473684210526314e-06,
1178
+ "loss": 0.3953,
1179
+ "step": 90
1180
+ },
1181
+ {
1182
+ "Batch Mean": 0.33566761016845703,
1183
+ "accuracy": 0.7890625,
1184
+ "epoch": 0.225,
1185
+ "step": 90
1186
+ },
1187
+ {
1188
+ "epoch": 0.2275,
1189
+ "grad_norm": 10.429315567016602,
1190
+ "learning_rate": 2.439473684210526e-06,
1191
+ "loss": 0.4943,
1192
+ "step": 91
1193
+ },
1194
+ {
1195
+ "Batch Mean": 0.4449765682220459,
1196
+ "accuracy": 0.84375,
1197
+ "epoch": 0.2275,
1198
+ "step": 91
1199
+ },
1200
+ {
1201
+ "epoch": 0.23,
1202
+ "grad_norm": 8.419116020202637,
1203
+ "learning_rate": 2.431578947368421e-06,
1204
+ "loss": 0.3647,
1205
+ "step": 92
1206
+ },
1207
+ {
1208
+ "Batch Mean": -0.06833112239837646,
1209
+ "accuracy": 0.8359375,
1210
+ "epoch": 0.23,
1211
+ "step": 92
1212
+ },
1213
+ {
1214
+ "epoch": 0.2325,
1215
+ "grad_norm": 7.288305282592773,
1216
+ "learning_rate": 2.4236842105263157e-06,
1217
+ "loss": 0.3719,
1218
+ "step": 93
1219
+ },
1220
+ {
1221
+ "Batch Mean": -0.36795759201049805,
1222
+ "accuracy": 0.8046875,
1223
+ "epoch": 0.2325,
1224
+ "step": 93
1225
+ },
1226
+ {
1227
+ "epoch": 0.235,
1228
+ "grad_norm": 8.255443572998047,
1229
+ "learning_rate": 2.4157894736842104e-06,
1230
+ "loss": 0.3983,
1231
+ "step": 94
1232
+ },
1233
+ {
1234
+ "Batch Mean": -0.3381902277469635,
1235
+ "accuracy": 0.8515625,
1236
+ "epoch": 0.235,
1237
+ "step": 94
1238
+ },
1239
+ {
1240
+ "epoch": 0.2375,
1241
+ "grad_norm": 8.25379467010498,
1242
+ "learning_rate": 2.4078947368421056e-06,
1243
+ "loss": 0.3602,
1244
+ "step": 95
1245
+ },
1246
+ {
1247
+ "Batch Mean": -0.2966504693031311,
1248
+ "accuracy": 0.75,
1249
+ "epoch": 0.2375,
1250
+ "step": 95
1251
+ },
1252
+ {
1253
+ "epoch": 0.24,
1254
+ "grad_norm": 9.554913520812988,
1255
+ "learning_rate": 2.4000000000000003e-06,
1256
+ "loss": 0.4499,
1257
+ "step": 96
1258
+ },
1259
+ {
1260
+ "Batch Mean": -0.02951526641845703,
1261
+ "accuracy": 0.796875,
1262
+ "epoch": 0.24,
1263
+ "step": 96
1264
+ },
1265
+ {
1266
+ "epoch": 0.2425,
1267
+ "grad_norm": 8.300037384033203,
1268
+ "learning_rate": 2.392105263157895e-06,
1269
+ "loss": 0.41,
1270
+ "step": 97
1271
+ },
1272
+ {
1273
+ "Batch Mean": 0.4994839131832123,
1274
+ "accuracy": 0.84375,
1275
+ "epoch": 0.2425,
1276
+ "step": 97
1277
+ },
1278
+ {
1279
+ "epoch": 0.245,
1280
+ "grad_norm": 9.282505989074707,
1281
+ "learning_rate": 2.38421052631579e-06,
1282
+ "loss": 0.3631,
1283
+ "step": 98
1284
+ },
1285
+ {
1286
+ "Batch Mean": 0.5059927701950073,
1287
+ "accuracy": 0.84375,
1288
+ "epoch": 0.245,
1289
+ "step": 98
1290
+ },
1291
+ {
1292
+ "epoch": 0.2475,
1293
+ "grad_norm": 10.97496509552002,
1294
+ "learning_rate": 2.376315789473684e-06,
1295
+ "loss": 0.4266,
1296
+ "step": 99
1297
+ },
1298
+ {
1299
+ "Batch Mean": 0.5012010335922241,
1300
+ "accuracy": 0.7890625,
1301
+ "epoch": 0.2475,
1302
+ "step": 99
1303
+ },
1304
+ {
1305
+ "epoch": 0.25,
1306
+ "grad_norm": 10.482470512390137,
1307
+ "learning_rate": 2.368421052631579e-06,
1308
+ "loss": 0.4402,
1309
+ "step": 100
1310
+ }
1311
+ ],
1312
+ "logging_steps": 1,
1313
+ "max_steps": 400,
1314
+ "num_input_tokens_seen": 0,
1315
+ "num_train_epochs": 1,
1316
+ "save_steps": 100,
1317
+ "stateful_callbacks": {
1318
+ "TrainerControl": {
1319
+ "args": {
1320
+ "should_epoch_stop": false,
1321
+ "should_evaluate": false,
1322
+ "should_log": false,
1323
+ "should_save": true,
1324
+ "should_training_stop": false
1325
+ },
1326
+ "attributes": {}
1327
+ }
1328
+ },
1329
+ "total_flos": 0.0,
1330
+ "train_batch_size": 16,
1331
+ "trial_name": null,
1332
+ "trial_params": null
1333
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd1362576452dc1dede51df1a8532cf1318d832a39af9b44e8dcc8537827bc1
3
+ size 5688
checkpoint-200/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-3B-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": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
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": 24,
29
+ "num_hidden_layers": 28,
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-200/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e497bccc325710b2583eb962b455920d718cc59130f77e09e3d46e63c2dc3e8
3
+ size 4998767360
checkpoint-200/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a09f9593364444597c9c2897e1b6f85d0910e5799d83ff8a06982fc7f83ce10
3
+ size 4932808968
checkpoint-200/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0bd8b1802bce87915b5ed09b0d5b011f9be61790379cdc1bcc330dc9968a6b2
3
+ size 2919464544
checkpoint-200/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12851011584
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.norm.weight": "model-00003-of-00003.safetensors",
260
+ "score.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
checkpoint-200/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-200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-200/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-200/trainer_state.json ADDED
@@ -0,0 +1,2633 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
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": 0.7002408504486084,
13
+ "accuracy": 0.53125,
14
+ "epoch": 0,
15
+ "step": 0
16
+ },
17
+ {
18
+ "epoch": 0.0025,
19
+ "grad_norm": 4.865061283111572,
20
+ "learning_rate": 1.5000000000000002e-07,
21
+ "loss": 0.6999,
22
+ "step": 1
23
+ },
24
+ {
25
+ "Batch Mean": 0.7006568908691406,
26
+ "accuracy": 0.5078125,
27
+ "epoch": 0.0025,
28
+ "step": 1
29
+ },
30
+ {
31
+ "epoch": 0.005,
32
+ "grad_norm": 5.116915702819824,
33
+ "learning_rate": 3.0000000000000004e-07,
34
+ "loss": 0.706,
35
+ "step": 2
36
+ },
37
+ {
38
+ "Batch Mean": 0.7036838531494141,
39
+ "accuracy": 0.5625,
40
+ "epoch": 0.005,
41
+ "step": 2
42
+ },
43
+ {
44
+ "epoch": 0.0075,
45
+ "grad_norm": 4.952433109283447,
46
+ "learning_rate": 4.5e-07,
47
+ "loss": 0.6957,
48
+ "step": 3
49
+ },
50
+ {
51
+ "Batch Mean": 0.7087974548339844,
52
+ "accuracy": 0.5546875,
53
+ "epoch": 0.0075,
54
+ "step": 3
55
+ },
56
+ {
57
+ "epoch": 0.01,
58
+ "grad_norm": 5.185088157653809,
59
+ "learning_rate": 6.000000000000001e-07,
60
+ "loss": 0.6974,
61
+ "step": 4
62
+ },
63
+ {
64
+ "Batch Mean": 0.7068939208984375,
65
+ "accuracy": 0.5234375,
66
+ "epoch": 0.01,
67
+ "step": 4
68
+ },
69
+ {
70
+ "epoch": 0.0125,
71
+ "grad_norm": 5.04327392578125,
72
+ "learning_rate": 7.5e-07,
73
+ "loss": 0.7047,
74
+ "step": 5
75
+ },
76
+ {
77
+ "Batch Mean": 0.6315479278564453,
78
+ "accuracy": 0.5234375,
79
+ "epoch": 0.0125,
80
+ "step": 5
81
+ },
82
+ {
83
+ "epoch": 0.015,
84
+ "grad_norm": 4.728168487548828,
85
+ "learning_rate": 9e-07,
86
+ "loss": 0.6932,
87
+ "step": 6
88
+ },
89
+ {
90
+ "Batch Mean": 0.5291571617126465,
91
+ "accuracy": 0.5234375,
92
+ "epoch": 0.015,
93
+ "step": 6
94
+ },
95
+ {
96
+ "epoch": 0.0175,
97
+ "grad_norm": 4.0146050453186035,
98
+ "learning_rate": 1.05e-06,
99
+ "loss": 0.691,
100
+ "step": 7
101
+ },
102
+ {
103
+ "Batch Mean": 0.42229437828063965,
104
+ "accuracy": 0.5546875,
105
+ "epoch": 0.0175,
106
+ "step": 7
107
+ },
108
+ {
109
+ "epoch": 0.02,
110
+ "grad_norm": 3.488922119140625,
111
+ "learning_rate": 1.2000000000000002e-06,
112
+ "loss": 0.6947,
113
+ "step": 8
114
+ },
115
+ {
116
+ "Batch Mean": 0.07428494095802307,
117
+ "accuracy": 0.515625,
118
+ "epoch": 0.02,
119
+ "step": 8
120
+ },
121
+ {
122
+ "epoch": 0.0225,
123
+ "grad_norm": 2.5626139640808105,
124
+ "learning_rate": 1.35e-06,
125
+ "loss": 0.6965,
126
+ "step": 9
127
+ },
128
+ {
129
+ "Batch Mean": -0.1413576304912567,
130
+ "accuracy": 0.5859375,
131
+ "epoch": 0.0225,
132
+ "step": 9
133
+ },
134
+ {
135
+ "epoch": 0.025,
136
+ "grad_norm": 2.776390790939331,
137
+ "learning_rate": 1.5e-06,
138
+ "loss": 0.6784,
139
+ "step": 10
140
+ },
141
+ {
142
+ "Batch Mean": -0.2741769552230835,
143
+ "accuracy": 0.5234375,
144
+ "epoch": 0.025,
145
+ "step": 10
146
+ },
147
+ {
148
+ "epoch": 0.0275,
149
+ "grad_norm": 3.4468233585357666,
150
+ "learning_rate": 1.65e-06,
151
+ "loss": 0.6844,
152
+ "step": 11
153
+ },
154
+ {
155
+ "Batch Mean": -0.45577430725097656,
156
+ "accuracy": 0.5859375,
157
+ "epoch": 0.0275,
158
+ "step": 11
159
+ },
160
+ {
161
+ "epoch": 0.03,
162
+ "grad_norm": 4.281182765960693,
163
+ "learning_rate": 1.8e-06,
164
+ "loss": 0.6753,
165
+ "step": 12
166
+ },
167
+ {
168
+ "Batch Mean": -1.0260009765625,
169
+ "accuracy": 0.65625,
170
+ "epoch": 0.03,
171
+ "step": 12
172
+ },
173
+ {
174
+ "epoch": 0.0325,
175
+ "grad_norm": 6.948849201202393,
176
+ "learning_rate": 1.95e-06,
177
+ "loss": 0.6734,
178
+ "step": 13
179
+ },
180
+ {
181
+ "Batch Mean": -1.1147994995117188,
182
+ "accuracy": 0.6171875,
183
+ "epoch": 0.0325,
184
+ "step": 13
185
+ },
186
+ {
187
+ "epoch": 0.035,
188
+ "grad_norm": 7.589419841766357,
189
+ "learning_rate": 2.1e-06,
190
+ "loss": 0.677,
191
+ "step": 14
192
+ },
193
+ {
194
+ "Batch Mean": -1.0315093994140625,
195
+ "accuracy": 0.65625,
196
+ "epoch": 0.035,
197
+ "step": 14
198
+ },
199
+ {
200
+ "epoch": 0.0375,
201
+ "grad_norm": 7.2146382331848145,
202
+ "learning_rate": 2.25e-06,
203
+ "loss": 0.677,
204
+ "step": 15
205
+ },
206
+ {
207
+ "Batch Mean": -0.8089427947998047,
208
+ "accuracy": 0.65625,
209
+ "epoch": 0.0375,
210
+ "step": 15
211
+ },
212
+ {
213
+ "epoch": 0.04,
214
+ "grad_norm": 6.308068752288818,
215
+ "learning_rate": 2.4000000000000003e-06,
216
+ "loss": 0.6503,
217
+ "step": 16
218
+ },
219
+ {
220
+ "Batch Mean": -0.3669371008872986,
221
+ "accuracy": 0.671875,
222
+ "epoch": 0.04,
223
+ "step": 16
224
+ },
225
+ {
226
+ "epoch": 0.0425,
227
+ "grad_norm": 4.996833324432373,
228
+ "learning_rate": 2.55e-06,
229
+ "loss": 0.617,
230
+ "step": 17
231
+ },
232
+ {
233
+ "Batch Mean": 0.2619136571884155,
234
+ "accuracy": 0.6796875,
235
+ "epoch": 0.0425,
236
+ "step": 17
237
+ },
238
+ {
239
+ "epoch": 0.045,
240
+ "grad_norm": 4.9718918800354,
241
+ "learning_rate": 2.7e-06,
242
+ "loss": 0.5981,
243
+ "step": 18
244
+ },
245
+ {
246
+ "Batch Mean": 1.0361242294311523,
247
+ "accuracy": 0.625,
248
+ "epoch": 0.045,
249
+ "step": 18
250
+ },
251
+ {
252
+ "epoch": 0.0475,
253
+ "grad_norm": 9.635746955871582,
254
+ "learning_rate": 2.85e-06,
255
+ "loss": 0.6236,
256
+ "step": 19
257
+ },
258
+ {
259
+ "Batch Mean": 1.5605192184448242,
260
+ "accuracy": 0.65625,
261
+ "epoch": 0.0475,
262
+ "step": 19
263
+ },
264
+ {
265
+ "epoch": 0.05,
266
+ "grad_norm": 14.90079116821289,
267
+ "learning_rate": 3e-06,
268
+ "loss": 0.6511,
269
+ "step": 20
270
+ },
271
+ {
272
+ "Batch Mean": 1.7601673603057861,
273
+ "accuracy": 0.6796875,
274
+ "epoch": 0.05,
275
+ "step": 20
276
+ },
277
+ {
278
+ "epoch": 0.0525,
279
+ "grad_norm": 16.801076889038086,
280
+ "learning_rate": 2.992105263157895e-06,
281
+ "loss": 0.6712,
282
+ "step": 21
283
+ },
284
+ {
285
+ "Batch Mean": 1.1987818479537964,
286
+ "accuracy": 0.7109375,
287
+ "epoch": 0.0525,
288
+ "step": 21
289
+ },
290
+ {
291
+ "epoch": 0.055,
292
+ "grad_norm": 11.280301094055176,
293
+ "learning_rate": 2.9842105263157896e-06,
294
+ "loss": 0.6033,
295
+ "step": 22
296
+ },
297
+ {
298
+ "Batch Mean": 0.5978413820266724,
299
+ "accuracy": 0.6875,
300
+ "epoch": 0.055,
301
+ "step": 22
302
+ },
303
+ {
304
+ "epoch": 0.0575,
305
+ "grad_norm": 7.414430141448975,
306
+ "learning_rate": 2.9763157894736843e-06,
307
+ "loss": 0.5819,
308
+ "step": 23
309
+ },
310
+ {
311
+ "Batch Mean": -0.20422333478927612,
312
+ "accuracy": 0.6640625,
313
+ "epoch": 0.0575,
314
+ "step": 23
315
+ },
316
+ {
317
+ "epoch": 0.06,
318
+ "grad_norm": 5.717103004455566,
319
+ "learning_rate": 2.968421052631579e-06,
320
+ "loss": 0.638,
321
+ "step": 24
322
+ },
323
+ {
324
+ "Batch Mean": -0.7162615060806274,
325
+ "accuracy": 0.75,
326
+ "epoch": 0.06,
327
+ "step": 24
328
+ },
329
+ {
330
+ "epoch": 0.0625,
331
+ "grad_norm": 7.513117790222168,
332
+ "learning_rate": 2.960526315789474e-06,
333
+ "loss": 0.5851,
334
+ "step": 25
335
+ },
336
+ {
337
+ "Batch Mean": -1.054888129234314,
338
+ "accuracy": 0.6796875,
339
+ "epoch": 0.0625,
340
+ "step": 25
341
+ },
342
+ {
343
+ "epoch": 0.065,
344
+ "grad_norm": 8.300326347351074,
345
+ "learning_rate": 2.9526315789473685e-06,
346
+ "loss": 0.6286,
347
+ "step": 26
348
+ },
349
+ {
350
+ "Batch Mean": -1.1319353580474854,
351
+ "accuracy": 0.703125,
352
+ "epoch": 0.065,
353
+ "step": 26
354
+ },
355
+ {
356
+ "epoch": 0.0675,
357
+ "grad_norm": 9.116662979125977,
358
+ "learning_rate": 2.9447368421052633e-06,
359
+ "loss": 0.6003,
360
+ "step": 27
361
+ },
362
+ {
363
+ "Batch Mean": -0.7403234839439392,
364
+ "accuracy": 0.7265625,
365
+ "epoch": 0.0675,
366
+ "step": 27
367
+ },
368
+ {
369
+ "epoch": 0.07,
370
+ "grad_norm": 6.799551486968994,
371
+ "learning_rate": 2.936842105263158e-06,
372
+ "loss": 0.5383,
373
+ "step": 28
374
+ },
375
+ {
376
+ "Batch Mean": -0.25867950916290283,
377
+ "accuracy": 0.703125,
378
+ "epoch": 0.07,
379
+ "step": 28
380
+ },
381
+ {
382
+ "epoch": 0.0725,
383
+ "grad_norm": 5.493288040161133,
384
+ "learning_rate": 2.9289473684210528e-06,
385
+ "loss": 0.5683,
386
+ "step": 29
387
+ },
388
+ {
389
+ "Batch Mean": 0.4318051338195801,
390
+ "accuracy": 0.6796875,
391
+ "epoch": 0.0725,
392
+ "step": 29
393
+ },
394
+ {
395
+ "epoch": 0.075,
396
+ "grad_norm": 6.373619556427002,
397
+ "learning_rate": 2.9210526315789475e-06,
398
+ "loss": 0.6126,
399
+ "step": 30
400
+ },
401
+ {
402
+ "Batch Mean": 0.8685734272003174,
403
+ "accuracy": 0.7265625,
404
+ "epoch": 0.075,
405
+ "step": 30
406
+ },
407
+ {
408
+ "epoch": 0.0775,
409
+ "grad_norm": 7.750959396362305,
410
+ "learning_rate": 2.9131578947368423e-06,
411
+ "loss": 0.5984,
412
+ "step": 31
413
+ },
414
+ {
415
+ "Batch Mean": 1.1348557472229004,
416
+ "accuracy": 0.6484375,
417
+ "epoch": 0.0775,
418
+ "step": 31
419
+ },
420
+ {
421
+ "epoch": 0.08,
422
+ "grad_norm": 8.742609977722168,
423
+ "learning_rate": 2.905263157894737e-06,
424
+ "loss": 0.6016,
425
+ "step": 32
426
+ },
427
+ {
428
+ "Batch Mean": 0.6863436698913574,
429
+ "accuracy": 0.7421875,
430
+ "epoch": 0.08,
431
+ "step": 32
432
+ },
433
+ {
434
+ "epoch": 0.0825,
435
+ "grad_norm": 6.586100101470947,
436
+ "learning_rate": 2.8973684210526318e-06,
437
+ "loss": 0.5485,
438
+ "step": 33
439
+ },
440
+ {
441
+ "Batch Mean": 0.23023658990859985,
442
+ "accuracy": 0.765625,
443
+ "epoch": 0.0825,
444
+ "step": 33
445
+ },
446
+ {
447
+ "epoch": 0.085,
448
+ "grad_norm": 5.231872081756592,
449
+ "learning_rate": 2.8894736842105265e-06,
450
+ "loss": 0.4999,
451
+ "step": 34
452
+ },
453
+ {
454
+ "Batch Mean": -0.2048710286617279,
455
+ "accuracy": 0.734375,
456
+ "epoch": 0.085,
457
+ "step": 34
458
+ },
459
+ {
460
+ "epoch": 0.0875,
461
+ "grad_norm": 5.551333427429199,
462
+ "learning_rate": 2.8815789473684213e-06,
463
+ "loss": 0.5541,
464
+ "step": 35
465
+ },
466
+ {
467
+ "Batch Mean": -0.4559789299964905,
468
+ "accuracy": 0.7421875,
469
+ "epoch": 0.0875,
470
+ "step": 35
471
+ },
472
+ {
473
+ "epoch": 0.09,
474
+ "grad_norm": 5.972931385040283,
475
+ "learning_rate": 2.873684210526316e-06,
476
+ "loss": 0.5698,
477
+ "step": 36
478
+ },
479
+ {
480
+ "Batch Mean": -0.7627459764480591,
481
+ "accuracy": 0.7734375,
482
+ "epoch": 0.09,
483
+ "step": 36
484
+ },
485
+ {
486
+ "epoch": 0.0925,
487
+ "grad_norm": 7.165839672088623,
488
+ "learning_rate": 2.8657894736842103e-06,
489
+ "loss": 0.5157,
490
+ "step": 37
491
+ },
492
+ {
493
+ "Batch Mean": -0.6894429326057434,
494
+ "accuracy": 0.671875,
495
+ "epoch": 0.0925,
496
+ "step": 37
497
+ },
498
+ {
499
+ "epoch": 0.095,
500
+ "grad_norm": 6.630836009979248,
501
+ "learning_rate": 2.857894736842105e-06,
502
+ "loss": 0.5955,
503
+ "step": 38
504
+ },
505
+ {
506
+ "Batch Mean": -0.2740752696990967,
507
+ "accuracy": 0.734375,
508
+ "epoch": 0.095,
509
+ "step": 38
510
+ },
511
+ {
512
+ "epoch": 0.0975,
513
+ "grad_norm": 6.181252956390381,
514
+ "learning_rate": 2.85e-06,
515
+ "loss": 0.5037,
516
+ "step": 39
517
+ },
518
+ {
519
+ "Batch Mean": -0.09357815980911255,
520
+ "accuracy": 0.734375,
521
+ "epoch": 0.0975,
522
+ "step": 39
523
+ },
524
+ {
525
+ "epoch": 0.1,
526
+ "grad_norm": 6.351346969604492,
527
+ "learning_rate": 2.8421052631578946e-06,
528
+ "loss": 0.5152,
529
+ "step": 40
530
+ },
531
+ {
532
+ "Batch Mean": 0.33483320474624634,
533
+ "accuracy": 0.796875,
534
+ "epoch": 0.1,
535
+ "step": 40
536
+ },
537
+ {
538
+ "epoch": 0.1025,
539
+ "grad_norm": 6.3938117027282715,
540
+ "learning_rate": 2.8342105263157897e-06,
541
+ "loss": 0.4573,
542
+ "step": 41
543
+ },
544
+ {
545
+ "Batch Mean": 0.503718376159668,
546
+ "accuracy": 0.7578125,
547
+ "epoch": 0.1025,
548
+ "step": 41
549
+ },
550
+ {
551
+ "epoch": 0.105,
552
+ "grad_norm": 6.795258522033691,
553
+ "learning_rate": 2.8263157894736845e-06,
554
+ "loss": 0.4923,
555
+ "step": 42
556
+ },
557
+ {
558
+ "Batch Mean": 0.4224682152271271,
559
+ "accuracy": 0.6875,
560
+ "epoch": 0.105,
561
+ "step": 42
562
+ },
563
+ {
564
+ "epoch": 0.1075,
565
+ "grad_norm": 9.03122329711914,
566
+ "learning_rate": 2.8184210526315792e-06,
567
+ "loss": 0.5803,
568
+ "step": 43
569
+ },
570
+ {
571
+ "Batch Mean": 0.11721980571746826,
572
+ "accuracy": 0.8046875,
573
+ "epoch": 0.1075,
574
+ "step": 43
575
+ },
576
+ {
577
+ "epoch": 0.11,
578
+ "grad_norm": 6.323685646057129,
579
+ "learning_rate": 2.810526315789474e-06,
580
+ "loss": 0.4518,
581
+ "step": 44
582
+ },
583
+ {
584
+ "Batch Mean": 0.11213397979736328,
585
+ "accuracy": 0.7734375,
586
+ "epoch": 0.11,
587
+ "step": 44
588
+ },
589
+ {
590
+ "epoch": 0.1125,
591
+ "grad_norm": 6.636176586151123,
592
+ "learning_rate": 2.8026315789473687e-06,
593
+ "loss": 0.4747,
594
+ "step": 45
595
+ },
596
+ {
597
+ "Batch Mean": -0.19074296951293945,
598
+ "accuracy": 0.7421875,
599
+ "epoch": 0.1125,
600
+ "step": 45
601
+ },
602
+ {
603
+ "epoch": 0.115,
604
+ "grad_norm": 8.862186431884766,
605
+ "learning_rate": 2.7947368421052635e-06,
606
+ "loss": 0.5295,
607
+ "step": 46
608
+ },
609
+ {
610
+ "Batch Mean": -0.26628145575523376,
611
+ "accuracy": 0.7578125,
612
+ "epoch": 0.115,
613
+ "step": 46
614
+ },
615
+ {
616
+ "epoch": 0.1175,
617
+ "grad_norm": 9.089022636413574,
618
+ "learning_rate": 2.7868421052631578e-06,
619
+ "loss": 0.5132,
620
+ "step": 47
621
+ },
622
+ {
623
+ "Batch Mean": -0.11882030963897705,
624
+ "accuracy": 0.765625,
625
+ "epoch": 0.1175,
626
+ "step": 47
627
+ },
628
+ {
629
+ "epoch": 0.12,
630
+ "grad_norm": 8.50251293182373,
631
+ "learning_rate": 2.7789473684210525e-06,
632
+ "loss": 0.4904,
633
+ "step": 48
634
+ },
635
+ {
636
+ "Batch Mean": -0.09545481204986572,
637
+ "accuracy": 0.7890625,
638
+ "epoch": 0.12,
639
+ "step": 48
640
+ },
641
+ {
642
+ "epoch": 0.1225,
643
+ "grad_norm": 8.091400146484375,
644
+ "learning_rate": 2.7710526315789473e-06,
645
+ "loss": 0.4615,
646
+ "step": 49
647
+ },
648
+ {
649
+ "Batch Mean": -0.01603543758392334,
650
+ "accuracy": 0.6328125,
651
+ "epoch": 0.1225,
652
+ "step": 49
653
+ },
654
+ {
655
+ "epoch": 0.125,
656
+ "grad_norm": 11.12177562713623,
657
+ "learning_rate": 2.763157894736842e-06,
658
+ "loss": 0.6245,
659
+ "step": 50
660
+ },
661
+ {
662
+ "Batch Mean": -0.03519377112388611,
663
+ "accuracy": 0.6953125,
664
+ "epoch": 0.125,
665
+ "step": 50
666
+ },
667
+ {
668
+ "epoch": 0.1275,
669
+ "grad_norm": 8.476814270019531,
670
+ "learning_rate": 2.7552631578947368e-06,
671
+ "loss": 0.5094,
672
+ "step": 51
673
+ },
674
+ {
675
+ "Batch Mean": -0.07445716857910156,
676
+ "accuracy": 0.765625,
677
+ "epoch": 0.1275,
678
+ "step": 51
679
+ },
680
+ {
681
+ "epoch": 0.13,
682
+ "grad_norm": 8.475494384765625,
683
+ "learning_rate": 2.7473684210526315e-06,
684
+ "loss": 0.464,
685
+ "step": 52
686
+ },
687
+ {
688
+ "Batch Mean": -0.08127522468566895,
689
+ "accuracy": 0.7890625,
690
+ "epoch": 0.13,
691
+ "step": 52
692
+ },
693
+ {
694
+ "epoch": 0.1325,
695
+ "grad_norm": 7.754316806793213,
696
+ "learning_rate": 2.7394736842105263e-06,
697
+ "loss": 0.4618,
698
+ "step": 53
699
+ },
700
+ {
701
+ "Batch Mean": 0.05236625671386719,
702
+ "accuracy": 0.75,
703
+ "epoch": 0.1325,
704
+ "step": 53
705
+ },
706
+ {
707
+ "epoch": 0.135,
708
+ "grad_norm": 7.3552751541137695,
709
+ "learning_rate": 2.7315789473684214e-06,
710
+ "loss": 0.5202,
711
+ "step": 54
712
+ },
713
+ {
714
+ "Batch Mean": -0.08030200004577637,
715
+ "accuracy": 0.765625,
716
+ "epoch": 0.135,
717
+ "step": 54
718
+ },
719
+ {
720
+ "epoch": 0.1375,
721
+ "grad_norm": 8.413111686706543,
722
+ "learning_rate": 2.723684210526316e-06,
723
+ "loss": 0.4902,
724
+ "step": 55
725
+ },
726
+ {
727
+ "Batch Mean": 0.20010590553283691,
728
+ "accuracy": 0.765625,
729
+ "epoch": 0.1375,
730
+ "step": 55
731
+ },
732
+ {
733
+ "epoch": 0.14,
734
+ "grad_norm": 9.49488353729248,
735
+ "learning_rate": 2.715789473684211e-06,
736
+ "loss": 0.4945,
737
+ "step": 56
738
+ },
739
+ {
740
+ "Batch Mean": 0.1068873256444931,
741
+ "accuracy": 0.765625,
742
+ "epoch": 0.14,
743
+ "step": 56
744
+ },
745
+ {
746
+ "epoch": 0.1425,
747
+ "grad_norm": 9.978996276855469,
748
+ "learning_rate": 2.7078947368421052e-06,
749
+ "loss": 0.5936,
750
+ "step": 57
751
+ },
752
+ {
753
+ "Batch Mean": 0.12400929629802704,
754
+ "accuracy": 0.8046875,
755
+ "epoch": 0.1425,
756
+ "step": 57
757
+ },
758
+ {
759
+ "epoch": 0.145,
760
+ "grad_norm": 8.332430839538574,
761
+ "learning_rate": 2.7e-06,
762
+ "loss": 0.4549,
763
+ "step": 58
764
+ },
765
+ {
766
+ "Batch Mean": 0.05874582380056381,
767
+ "accuracy": 0.8125,
768
+ "epoch": 0.145,
769
+ "step": 58
770
+ },
771
+ {
772
+ "epoch": 0.1475,
773
+ "grad_norm": 7.287342548370361,
774
+ "learning_rate": 2.6921052631578947e-06,
775
+ "loss": 0.3996,
776
+ "step": 59
777
+ },
778
+ {
779
+ "Batch Mean": 0.17911481857299805,
780
+ "accuracy": 0.828125,
781
+ "epoch": 0.1475,
782
+ "step": 59
783
+ },
784
+ {
785
+ "epoch": 0.15,
786
+ "grad_norm": 7.197307109832764,
787
+ "learning_rate": 2.6842105263157895e-06,
788
+ "loss": 0.4486,
789
+ "step": 60
790
+ },
791
+ {
792
+ "Batch Mean": -0.0680088996887207,
793
+ "accuracy": 0.7265625,
794
+ "epoch": 0.15,
795
+ "step": 60
796
+ },
797
+ {
798
+ "epoch": 0.1525,
799
+ "grad_norm": 8.422717094421387,
800
+ "learning_rate": 2.6763157894736842e-06,
801
+ "loss": 0.5283,
802
+ "step": 61
803
+ },
804
+ {
805
+ "Batch Mean": -0.1332111358642578,
806
+ "accuracy": 0.7890625,
807
+ "epoch": 0.1525,
808
+ "step": 61
809
+ },
810
+ {
811
+ "epoch": 0.155,
812
+ "grad_norm": 8.836848258972168,
813
+ "learning_rate": 2.668421052631579e-06,
814
+ "loss": 0.4547,
815
+ "step": 62
816
+ },
817
+ {
818
+ "Batch Mean": -0.005272388458251953,
819
+ "accuracy": 0.734375,
820
+ "epoch": 0.155,
821
+ "step": 62
822
+ },
823
+ {
824
+ "epoch": 0.1575,
825
+ "grad_norm": 7.995077133178711,
826
+ "learning_rate": 2.6605263157894737e-06,
827
+ "loss": 0.5227,
828
+ "step": 63
829
+ },
830
+ {
831
+ "Batch Mean": 0.3416769504547119,
832
+ "accuracy": 0.8359375,
833
+ "epoch": 0.1575,
834
+ "step": 63
835
+ },
836
+ {
837
+ "epoch": 0.16,
838
+ "grad_norm": 8.131783485412598,
839
+ "learning_rate": 2.6526315789473685e-06,
840
+ "loss": 0.4191,
841
+ "step": 64
842
+ },
843
+ {
844
+ "Batch Mean": 0.2797560691833496,
845
+ "accuracy": 0.765625,
846
+ "epoch": 0.16,
847
+ "step": 64
848
+ },
849
+ {
850
+ "epoch": 0.1625,
851
+ "grad_norm": 9.04648208618164,
852
+ "learning_rate": 2.644736842105263e-06,
853
+ "loss": 0.4893,
854
+ "step": 65
855
+ },
856
+ {
857
+ "Batch Mean": -0.14584161341190338,
858
+ "accuracy": 0.7734375,
859
+ "epoch": 0.1625,
860
+ "step": 65
861
+ },
862
+ {
863
+ "epoch": 0.165,
864
+ "grad_norm": 8.039698600769043,
865
+ "learning_rate": 2.636842105263158e-06,
866
+ "loss": 0.4753,
867
+ "step": 66
868
+ },
869
+ {
870
+ "Batch Mean": -0.37075191736221313,
871
+ "accuracy": 0.7421875,
872
+ "epoch": 0.165,
873
+ "step": 66
874
+ },
875
+ {
876
+ "epoch": 0.1675,
877
+ "grad_norm": 7.643855094909668,
878
+ "learning_rate": 2.6289473684210527e-06,
879
+ "loss": 0.4424,
880
+ "step": 67
881
+ },
882
+ {
883
+ "Batch Mean": -0.24360448122024536,
884
+ "accuracy": 0.828125,
885
+ "epoch": 0.1675,
886
+ "step": 67
887
+ },
888
+ {
889
+ "epoch": 0.17,
890
+ "grad_norm": 6.892768383026123,
891
+ "learning_rate": 2.6210526315789474e-06,
892
+ "loss": 0.4126,
893
+ "step": 68
894
+ },
895
+ {
896
+ "Batch Mean": -0.0484846830368042,
897
+ "accuracy": 0.734375,
898
+ "epoch": 0.17,
899
+ "step": 68
900
+ },
901
+ {
902
+ "epoch": 0.1725,
903
+ "grad_norm": 10.497048377990723,
904
+ "learning_rate": 2.613157894736842e-06,
905
+ "loss": 0.5242,
906
+ "step": 69
907
+ },
908
+ {
909
+ "Batch Mean": 0.07249626517295837,
910
+ "accuracy": 0.8125,
911
+ "epoch": 0.1725,
912
+ "step": 69
913
+ },
914
+ {
915
+ "epoch": 0.175,
916
+ "grad_norm": 6.990925312042236,
917
+ "learning_rate": 2.605263157894737e-06,
918
+ "loss": 0.4206,
919
+ "step": 70
920
+ },
921
+ {
922
+ "Batch Mean": -0.06337249279022217,
923
+ "accuracy": 0.8125,
924
+ "epoch": 0.175,
925
+ "step": 70
926
+ },
927
+ {
928
+ "epoch": 0.1775,
929
+ "grad_norm": 7.180996417999268,
930
+ "learning_rate": 2.5973684210526317e-06,
931
+ "loss": 0.4412,
932
+ "step": 71
933
+ },
934
+ {
935
+ "Batch Mean": 0.06033170223236084,
936
+ "accuracy": 0.8515625,
937
+ "epoch": 0.1775,
938
+ "step": 71
939
+ },
940
+ {
941
+ "epoch": 0.18,
942
+ "grad_norm": 6.108893871307373,
943
+ "learning_rate": 2.5894736842105264e-06,
944
+ "loss": 0.3576,
945
+ "step": 72
946
+ },
947
+ {
948
+ "Batch Mean": -0.04290449619293213,
949
+ "accuracy": 0.765625,
950
+ "epoch": 0.18,
951
+ "step": 72
952
+ },
953
+ {
954
+ "epoch": 0.1825,
955
+ "grad_norm": 7.272516250610352,
956
+ "learning_rate": 2.581578947368421e-06,
957
+ "loss": 0.487,
958
+ "step": 73
959
+ },
960
+ {
961
+ "Batch Mean": 0.09309220314025879,
962
+ "accuracy": 0.796875,
963
+ "epoch": 0.1825,
964
+ "step": 73
965
+ },
966
+ {
967
+ "epoch": 0.185,
968
+ "grad_norm": 6.689022064208984,
969
+ "learning_rate": 2.573684210526316e-06,
970
+ "loss": 0.4576,
971
+ "step": 74
972
+ },
973
+ {
974
+ "Batch Mean": -0.3521728515625,
975
+ "accuracy": 0.8046875,
976
+ "epoch": 0.185,
977
+ "step": 74
978
+ },
979
+ {
980
+ "epoch": 0.1875,
981
+ "grad_norm": 7.446789264678955,
982
+ "learning_rate": 2.5657894736842107e-06,
983
+ "loss": 0.4537,
984
+ "step": 75
985
+ },
986
+ {
987
+ "Batch Mean": -0.1267460584640503,
988
+ "accuracy": 0.7265625,
989
+ "epoch": 0.1875,
990
+ "step": 75
991
+ },
992
+ {
993
+ "epoch": 0.19,
994
+ "grad_norm": 8.600646018981934,
995
+ "learning_rate": 2.5578947368421054e-06,
996
+ "loss": 0.5066,
997
+ "step": 76
998
+ },
999
+ {
1000
+ "Batch Mean": 0.02230433002114296,
1001
+ "accuracy": 0.7578125,
1002
+ "epoch": 0.19,
1003
+ "step": 76
1004
+ },
1005
+ {
1006
+ "epoch": 0.1925,
1007
+ "grad_norm": 8.842095375061035,
1008
+ "learning_rate": 2.55e-06,
1009
+ "loss": 0.4823,
1010
+ "step": 77
1011
+ },
1012
+ {
1013
+ "Batch Mean": 0.17012596130371094,
1014
+ "accuracy": 0.7890625,
1015
+ "epoch": 0.1925,
1016
+ "step": 77
1017
+ },
1018
+ {
1019
+ "epoch": 0.195,
1020
+ "grad_norm": 6.993001937866211,
1021
+ "learning_rate": 2.542105263157895e-06,
1022
+ "loss": 0.3959,
1023
+ "step": 78
1024
+ },
1025
+ {
1026
+ "Batch Mean": -0.11112558841705322,
1027
+ "accuracy": 0.78125,
1028
+ "epoch": 0.195,
1029
+ "step": 78
1030
+ },
1031
+ {
1032
+ "epoch": 0.1975,
1033
+ "grad_norm": 8.71827220916748,
1034
+ "learning_rate": 2.5342105263157892e-06,
1035
+ "loss": 0.4407,
1036
+ "step": 79
1037
+ },
1038
+ {
1039
+ "Batch Mean": 0.11298668384552002,
1040
+ "accuracy": 0.8515625,
1041
+ "epoch": 0.1975,
1042
+ "step": 79
1043
+ },
1044
+ {
1045
+ "epoch": 0.2,
1046
+ "grad_norm": 7.829047679901123,
1047
+ "learning_rate": 2.526315789473684e-06,
1048
+ "loss": 0.3905,
1049
+ "step": 80
1050
+ },
1051
+ {
1052
+ "Batch Mean": 0.010145187377929688,
1053
+ "accuracy": 0.78125,
1054
+ "epoch": 0.2,
1055
+ "step": 80
1056
+ },
1057
+ {
1058
+ "epoch": 0.2025,
1059
+ "grad_norm": 10.1448335647583,
1060
+ "learning_rate": 2.5184210526315787e-06,
1061
+ "loss": 0.4667,
1062
+ "step": 81
1063
+ },
1064
+ {
1065
+ "Batch Mean": 0.1327219009399414,
1066
+ "accuracy": 0.7890625,
1067
+ "epoch": 0.2025,
1068
+ "step": 81
1069
+ },
1070
+ {
1071
+ "epoch": 0.205,
1072
+ "grad_norm": 7.784322738647461,
1073
+ "learning_rate": 2.510526315789474e-06,
1074
+ "loss": 0.408,
1075
+ "step": 82
1076
+ },
1077
+ {
1078
+ "Batch Mean": 0.3474133014678955,
1079
+ "accuracy": 0.7421875,
1080
+ "epoch": 0.205,
1081
+ "step": 82
1082
+ },
1083
+ {
1084
+ "epoch": 0.2075,
1085
+ "grad_norm": 8.116996765136719,
1086
+ "learning_rate": 2.5026315789473686e-06,
1087
+ "loss": 0.438,
1088
+ "step": 83
1089
+ },
1090
+ {
1091
+ "Batch Mean": 0.2660253047943115,
1092
+ "accuracy": 0.75,
1093
+ "epoch": 0.2075,
1094
+ "step": 83
1095
+ },
1096
+ {
1097
+ "epoch": 0.21,
1098
+ "grad_norm": 7.8381452560424805,
1099
+ "learning_rate": 2.4947368421052634e-06,
1100
+ "loss": 0.4639,
1101
+ "step": 84
1102
+ },
1103
+ {
1104
+ "Batch Mean": 0.004191964864730835,
1105
+ "accuracy": 0.8125,
1106
+ "epoch": 0.21,
1107
+ "step": 84
1108
+ },
1109
+ {
1110
+ "epoch": 0.2125,
1111
+ "grad_norm": 6.7916412353515625,
1112
+ "learning_rate": 2.486842105263158e-06,
1113
+ "loss": 0.3937,
1114
+ "step": 85
1115
+ },
1116
+ {
1117
+ "Batch Mean": -0.4819910526275635,
1118
+ "accuracy": 0.75,
1119
+ "epoch": 0.2125,
1120
+ "step": 85
1121
+ },
1122
+ {
1123
+ "epoch": 0.215,
1124
+ "grad_norm": 8.073772430419922,
1125
+ "learning_rate": 2.478947368421053e-06,
1126
+ "loss": 0.4866,
1127
+ "step": 86
1128
+ },
1129
+ {
1130
+ "Batch Mean": -0.5541934967041016,
1131
+ "accuracy": 0.75,
1132
+ "epoch": 0.215,
1133
+ "step": 86
1134
+ },
1135
+ {
1136
+ "epoch": 0.2175,
1137
+ "grad_norm": 8.677484512329102,
1138
+ "learning_rate": 2.4710526315789476e-06,
1139
+ "loss": 0.503,
1140
+ "step": 87
1141
+ },
1142
+ {
1143
+ "Batch Mean": 0.14371705055236816,
1144
+ "accuracy": 0.7890625,
1145
+ "epoch": 0.2175,
1146
+ "step": 87
1147
+ },
1148
+ {
1149
+ "epoch": 0.22,
1150
+ "grad_norm": 7.931331634521484,
1151
+ "learning_rate": 2.4631578947368424e-06,
1152
+ "loss": 0.4483,
1153
+ "step": 88
1154
+ },
1155
+ {
1156
+ "Batch Mean": 0.013556957244873047,
1157
+ "accuracy": 0.859375,
1158
+ "epoch": 0.22,
1159
+ "step": 88
1160
+ },
1161
+ {
1162
+ "epoch": 0.2225,
1163
+ "grad_norm": 6.920699119567871,
1164
+ "learning_rate": 2.4552631578947367e-06,
1165
+ "loss": 0.3674,
1166
+ "step": 89
1167
+ },
1168
+ {
1169
+ "Batch Mean": -0.11897921562194824,
1170
+ "accuracy": 0.8203125,
1171
+ "epoch": 0.2225,
1172
+ "step": 89
1173
+ },
1174
+ {
1175
+ "epoch": 0.225,
1176
+ "grad_norm": 7.135400295257568,
1177
+ "learning_rate": 2.4473684210526314e-06,
1178
+ "loss": 0.3953,
1179
+ "step": 90
1180
+ },
1181
+ {
1182
+ "Batch Mean": 0.33566761016845703,
1183
+ "accuracy": 0.7890625,
1184
+ "epoch": 0.225,
1185
+ "step": 90
1186
+ },
1187
+ {
1188
+ "epoch": 0.2275,
1189
+ "grad_norm": 10.429315567016602,
1190
+ "learning_rate": 2.439473684210526e-06,
1191
+ "loss": 0.4943,
1192
+ "step": 91
1193
+ },
1194
+ {
1195
+ "Batch Mean": 0.4449765682220459,
1196
+ "accuracy": 0.84375,
1197
+ "epoch": 0.2275,
1198
+ "step": 91
1199
+ },
1200
+ {
1201
+ "epoch": 0.23,
1202
+ "grad_norm": 8.419116020202637,
1203
+ "learning_rate": 2.431578947368421e-06,
1204
+ "loss": 0.3647,
1205
+ "step": 92
1206
+ },
1207
+ {
1208
+ "Batch Mean": -0.06833112239837646,
1209
+ "accuracy": 0.8359375,
1210
+ "epoch": 0.23,
1211
+ "step": 92
1212
+ },
1213
+ {
1214
+ "epoch": 0.2325,
1215
+ "grad_norm": 7.288305282592773,
1216
+ "learning_rate": 2.4236842105263157e-06,
1217
+ "loss": 0.3719,
1218
+ "step": 93
1219
+ },
1220
+ {
1221
+ "Batch Mean": -0.36795759201049805,
1222
+ "accuracy": 0.8046875,
1223
+ "epoch": 0.2325,
1224
+ "step": 93
1225
+ },
1226
+ {
1227
+ "epoch": 0.235,
1228
+ "grad_norm": 8.255443572998047,
1229
+ "learning_rate": 2.4157894736842104e-06,
1230
+ "loss": 0.3983,
1231
+ "step": 94
1232
+ },
1233
+ {
1234
+ "Batch Mean": -0.3381902277469635,
1235
+ "accuracy": 0.8515625,
1236
+ "epoch": 0.235,
1237
+ "step": 94
1238
+ },
1239
+ {
1240
+ "epoch": 0.2375,
1241
+ "grad_norm": 8.25379467010498,
1242
+ "learning_rate": 2.4078947368421056e-06,
1243
+ "loss": 0.3602,
1244
+ "step": 95
1245
+ },
1246
+ {
1247
+ "Batch Mean": -0.2966504693031311,
1248
+ "accuracy": 0.75,
1249
+ "epoch": 0.2375,
1250
+ "step": 95
1251
+ },
1252
+ {
1253
+ "epoch": 0.24,
1254
+ "grad_norm": 9.554913520812988,
1255
+ "learning_rate": 2.4000000000000003e-06,
1256
+ "loss": 0.4499,
1257
+ "step": 96
1258
+ },
1259
+ {
1260
+ "Batch Mean": -0.02951526641845703,
1261
+ "accuracy": 0.796875,
1262
+ "epoch": 0.24,
1263
+ "step": 96
1264
+ },
1265
+ {
1266
+ "epoch": 0.2425,
1267
+ "grad_norm": 8.300037384033203,
1268
+ "learning_rate": 2.392105263157895e-06,
1269
+ "loss": 0.41,
1270
+ "step": 97
1271
+ },
1272
+ {
1273
+ "Batch Mean": 0.4994839131832123,
1274
+ "accuracy": 0.84375,
1275
+ "epoch": 0.2425,
1276
+ "step": 97
1277
+ },
1278
+ {
1279
+ "epoch": 0.245,
1280
+ "grad_norm": 9.282505989074707,
1281
+ "learning_rate": 2.38421052631579e-06,
1282
+ "loss": 0.3631,
1283
+ "step": 98
1284
+ },
1285
+ {
1286
+ "Batch Mean": 0.5059927701950073,
1287
+ "accuracy": 0.84375,
1288
+ "epoch": 0.245,
1289
+ "step": 98
1290
+ },
1291
+ {
1292
+ "epoch": 0.2475,
1293
+ "grad_norm": 10.97496509552002,
1294
+ "learning_rate": 2.376315789473684e-06,
1295
+ "loss": 0.4266,
1296
+ "step": 99
1297
+ },
1298
+ {
1299
+ "Batch Mean": 0.5012010335922241,
1300
+ "accuracy": 0.7890625,
1301
+ "epoch": 0.2475,
1302
+ "step": 99
1303
+ },
1304
+ {
1305
+ "epoch": 0.25,
1306
+ "grad_norm": 10.482470512390137,
1307
+ "learning_rate": 2.368421052631579e-06,
1308
+ "loss": 0.4402,
1309
+ "step": 100
1310
+ },
1311
+ {
1312
+ "Batch Mean": -0.34704887866973877,
1313
+ "accuracy": 0.7890625,
1314
+ "epoch": 0.25,
1315
+ "step": 100
1316
+ },
1317
+ {
1318
+ "epoch": 0.2525,
1319
+ "grad_norm": 10.026016235351562,
1320
+ "learning_rate": 2.3605263157894736e-06,
1321
+ "loss": 0.4576,
1322
+ "step": 101
1323
+ },
1324
+ {
1325
+ "Batch Mean": -0.5854883193969727,
1326
+ "accuracy": 0.7421875,
1327
+ "epoch": 0.2525,
1328
+ "step": 101
1329
+ },
1330
+ {
1331
+ "epoch": 0.255,
1332
+ "grad_norm": 11.113299369812012,
1333
+ "learning_rate": 2.3526315789473684e-06,
1334
+ "loss": 0.5302,
1335
+ "step": 102
1336
+ },
1337
+ {
1338
+ "Batch Mean": -0.6017556190490723,
1339
+ "accuracy": 0.8125,
1340
+ "epoch": 0.255,
1341
+ "step": 102
1342
+ },
1343
+ {
1344
+ "epoch": 0.2575,
1345
+ "grad_norm": 9.242813110351562,
1346
+ "learning_rate": 2.344736842105263e-06,
1347
+ "loss": 0.3451,
1348
+ "step": 103
1349
+ },
1350
+ {
1351
+ "Batch Mean": -0.14799189567565918,
1352
+ "accuracy": 0.78125,
1353
+ "epoch": 0.2575,
1354
+ "step": 103
1355
+ },
1356
+ {
1357
+ "epoch": 0.26,
1358
+ "grad_norm": 9.658228874206543,
1359
+ "learning_rate": 2.336842105263158e-06,
1360
+ "loss": 0.442,
1361
+ "step": 104
1362
+ },
1363
+ {
1364
+ "Batch Mean": 0.2693725824356079,
1365
+ "accuracy": 0.8203125,
1366
+ "epoch": 0.26,
1367
+ "step": 104
1368
+ },
1369
+ {
1370
+ "epoch": 0.2625,
1371
+ "grad_norm": 7.290228366851807,
1372
+ "learning_rate": 2.3289473684210526e-06,
1373
+ "loss": 0.3808,
1374
+ "step": 105
1375
+ },
1376
+ {
1377
+ "Batch Mean": 0.3339729309082031,
1378
+ "accuracy": 0.8828125,
1379
+ "epoch": 0.2625,
1380
+ "step": 105
1381
+ },
1382
+ {
1383
+ "epoch": 0.265,
1384
+ "grad_norm": 6.965331554412842,
1385
+ "learning_rate": 2.3210526315789473e-06,
1386
+ "loss": 0.326,
1387
+ "step": 106
1388
+ },
1389
+ {
1390
+ "Batch Mean": 0.03934955596923828,
1391
+ "accuracy": 0.765625,
1392
+ "epoch": 0.265,
1393
+ "step": 106
1394
+ },
1395
+ {
1396
+ "epoch": 0.2675,
1397
+ "grad_norm": 8.904206275939941,
1398
+ "learning_rate": 2.313157894736842e-06,
1399
+ "loss": 0.4804,
1400
+ "step": 107
1401
+ },
1402
+ {
1403
+ "Batch Mean": 0.48924458026885986,
1404
+ "accuracy": 0.7734375,
1405
+ "epoch": 0.2675,
1406
+ "step": 107
1407
+ },
1408
+ {
1409
+ "epoch": 0.27,
1410
+ "grad_norm": 11.731331825256348,
1411
+ "learning_rate": 2.305263157894737e-06,
1412
+ "loss": 0.4496,
1413
+ "step": 108
1414
+ },
1415
+ {
1416
+ "Batch Mean": 0.3033190965652466,
1417
+ "accuracy": 0.8671875,
1418
+ "epoch": 0.27,
1419
+ "step": 108
1420
+ },
1421
+ {
1422
+ "epoch": 0.2725,
1423
+ "grad_norm": 7.58432149887085,
1424
+ "learning_rate": 2.2973684210526316e-06,
1425
+ "loss": 0.3272,
1426
+ "step": 109
1427
+ },
1428
+ {
1429
+ "Batch Mean": 0.3258399963378906,
1430
+ "accuracy": 0.9296875,
1431
+ "epoch": 0.2725,
1432
+ "step": 109
1433
+ },
1434
+ {
1435
+ "epoch": 0.275,
1436
+ "grad_norm": 8.01420783996582,
1437
+ "learning_rate": 2.2894736842105263e-06,
1438
+ "loss": 0.2889,
1439
+ "step": 110
1440
+ },
1441
+ {
1442
+ "Batch Mean": -0.21785682439804077,
1443
+ "accuracy": 0.7734375,
1444
+ "epoch": 0.275,
1445
+ "step": 110
1446
+ },
1447
+ {
1448
+ "epoch": 0.2775,
1449
+ "grad_norm": 10.714860916137695,
1450
+ "learning_rate": 2.281578947368421e-06,
1451
+ "loss": 0.4938,
1452
+ "step": 111
1453
+ },
1454
+ {
1455
+ "Batch Mean": -0.23068951070308685,
1456
+ "accuracy": 0.7734375,
1457
+ "epoch": 0.2775,
1458
+ "step": 111
1459
+ },
1460
+ {
1461
+ "epoch": 0.28,
1462
+ "grad_norm": 9.543609619140625,
1463
+ "learning_rate": 2.273684210526316e-06,
1464
+ "loss": 0.4813,
1465
+ "step": 112
1466
+ },
1467
+ {
1468
+ "Batch Mean": -0.24743294715881348,
1469
+ "accuracy": 0.8515625,
1470
+ "epoch": 0.28,
1471
+ "step": 112
1472
+ },
1473
+ {
1474
+ "epoch": 0.2825,
1475
+ "grad_norm": 7.655090808868408,
1476
+ "learning_rate": 2.2657894736842106e-06,
1477
+ "loss": 0.3365,
1478
+ "step": 113
1479
+ },
1480
+ {
1481
+ "Batch Mean": -0.4790257215499878,
1482
+ "accuracy": 0.828125,
1483
+ "epoch": 0.2825,
1484
+ "step": 113
1485
+ },
1486
+ {
1487
+ "epoch": 0.285,
1488
+ "grad_norm": 9.270421028137207,
1489
+ "learning_rate": 2.2578947368421053e-06,
1490
+ "loss": 0.3654,
1491
+ "step": 114
1492
+ },
1493
+ {
1494
+ "Batch Mean": 0.39268895983695984,
1495
+ "accuracy": 0.7890625,
1496
+ "epoch": 0.285,
1497
+ "step": 114
1498
+ },
1499
+ {
1500
+ "epoch": 0.2875,
1501
+ "grad_norm": 10.442706108093262,
1502
+ "learning_rate": 2.25e-06,
1503
+ "loss": 0.4592,
1504
+ "step": 115
1505
+ },
1506
+ {
1507
+ "Batch Mean": 0.6092771291732788,
1508
+ "accuracy": 0.8515625,
1509
+ "epoch": 0.2875,
1510
+ "step": 115
1511
+ },
1512
+ {
1513
+ "epoch": 0.29,
1514
+ "grad_norm": 9.203109741210938,
1515
+ "learning_rate": 2.242105263157895e-06,
1516
+ "loss": 0.3579,
1517
+ "step": 116
1518
+ },
1519
+ {
1520
+ "Batch Mean": -0.1381063461303711,
1521
+ "accuracy": 0.7734375,
1522
+ "epoch": 0.29,
1523
+ "step": 116
1524
+ },
1525
+ {
1526
+ "epoch": 0.2925,
1527
+ "grad_norm": 11.316916465759277,
1528
+ "learning_rate": 2.2342105263157895e-06,
1529
+ "loss": 0.459,
1530
+ "step": 117
1531
+ },
1532
+ {
1533
+ "Batch Mean": -0.18764352798461914,
1534
+ "accuracy": 0.8125,
1535
+ "epoch": 0.2925,
1536
+ "step": 117
1537
+ },
1538
+ {
1539
+ "epoch": 0.295,
1540
+ "grad_norm": 9.715188026428223,
1541
+ "learning_rate": 2.2263157894736843e-06,
1542
+ "loss": 0.448,
1543
+ "step": 118
1544
+ },
1545
+ {
1546
+ "Batch Mean": -0.4390474557876587,
1547
+ "accuracy": 0.8359375,
1548
+ "epoch": 0.295,
1549
+ "step": 118
1550
+ },
1551
+ {
1552
+ "epoch": 0.2975,
1553
+ "grad_norm": 8.53513240814209,
1554
+ "learning_rate": 2.218421052631579e-06,
1555
+ "loss": 0.353,
1556
+ "step": 119
1557
+ },
1558
+ {
1559
+ "Batch Mean": -0.49342280626296997,
1560
+ "accuracy": 0.8203125,
1561
+ "epoch": 0.2975,
1562
+ "step": 119
1563
+ },
1564
+ {
1565
+ "epoch": 0.3,
1566
+ "grad_norm": 8.739898681640625,
1567
+ "learning_rate": 2.2105263157894738e-06,
1568
+ "loss": 0.3871,
1569
+ "step": 120
1570
+ },
1571
+ {
1572
+ "Batch Mean": -0.16289004683494568,
1573
+ "accuracy": 0.84375,
1574
+ "epoch": 0.3,
1575
+ "step": 120
1576
+ },
1577
+ {
1578
+ "epoch": 0.3025,
1579
+ "grad_norm": 8.066034317016602,
1580
+ "learning_rate": 2.2026315789473685e-06,
1581
+ "loss": 0.3778,
1582
+ "step": 121
1583
+ },
1584
+ {
1585
+ "Batch Mean": 0.11179280281066895,
1586
+ "accuracy": 0.8359375,
1587
+ "epoch": 0.3025,
1588
+ "step": 121
1589
+ },
1590
+ {
1591
+ "epoch": 0.305,
1592
+ "grad_norm": 8.85276985168457,
1593
+ "learning_rate": 2.1947368421052633e-06,
1594
+ "loss": 0.3953,
1595
+ "step": 122
1596
+ },
1597
+ {
1598
+ "Batch Mean": 0.6813234686851501,
1599
+ "accuracy": 0.828125,
1600
+ "epoch": 0.305,
1601
+ "step": 122
1602
+ },
1603
+ {
1604
+ "epoch": 0.3075,
1605
+ "grad_norm": 10.226161003112793,
1606
+ "learning_rate": 2.186842105263158e-06,
1607
+ "loss": 0.3787,
1608
+ "step": 123
1609
+ },
1610
+ {
1611
+ "Batch Mean": 0.08529806137084961,
1612
+ "accuracy": 0.8515625,
1613
+ "epoch": 0.3075,
1614
+ "step": 123
1615
+ },
1616
+ {
1617
+ "epoch": 0.31,
1618
+ "grad_norm": 9.13556957244873,
1619
+ "learning_rate": 2.1789473684210528e-06,
1620
+ "loss": 0.3313,
1621
+ "step": 124
1622
+ },
1623
+ {
1624
+ "Batch Mean": 0.24107074737548828,
1625
+ "accuracy": 0.7890625,
1626
+ "epoch": 0.31,
1627
+ "step": 124
1628
+ },
1629
+ {
1630
+ "epoch": 0.3125,
1631
+ "grad_norm": 12.641064643859863,
1632
+ "learning_rate": 2.1710526315789475e-06,
1633
+ "loss": 0.5176,
1634
+ "step": 125
1635
+ },
1636
+ {
1637
+ "Batch Mean": -0.1636943817138672,
1638
+ "accuracy": 0.7890625,
1639
+ "epoch": 0.3125,
1640
+ "step": 125
1641
+ },
1642
+ {
1643
+ "epoch": 0.315,
1644
+ "grad_norm": 9.701798439025879,
1645
+ "learning_rate": 2.1631578947368423e-06,
1646
+ "loss": 0.42,
1647
+ "step": 126
1648
+ },
1649
+ {
1650
+ "Batch Mean": -0.2857036590576172,
1651
+ "accuracy": 0.8515625,
1652
+ "epoch": 0.315,
1653
+ "step": 126
1654
+ },
1655
+ {
1656
+ "epoch": 0.3175,
1657
+ "grad_norm": 9.48480224609375,
1658
+ "learning_rate": 2.155263157894737e-06,
1659
+ "loss": 0.3539,
1660
+ "step": 127
1661
+ },
1662
+ {
1663
+ "Batch Mean": -0.7563860416412354,
1664
+ "accuracy": 0.765625,
1665
+ "epoch": 0.3175,
1666
+ "step": 127
1667
+ },
1668
+ {
1669
+ "epoch": 0.32,
1670
+ "grad_norm": 12.008138656616211,
1671
+ "learning_rate": 2.1473684210526317e-06,
1672
+ "loss": 0.4875,
1673
+ "step": 128
1674
+ },
1675
+ {
1676
+ "Batch Mean": 0.1351943016052246,
1677
+ "accuracy": 0.84375,
1678
+ "epoch": 0.32,
1679
+ "step": 128
1680
+ },
1681
+ {
1682
+ "epoch": 0.3225,
1683
+ "grad_norm": 8.202943801879883,
1684
+ "learning_rate": 2.1394736842105265e-06,
1685
+ "loss": 0.3432,
1686
+ "step": 129
1687
+ },
1688
+ {
1689
+ "Batch Mean": -0.002408236265182495,
1690
+ "accuracy": 0.8125,
1691
+ "epoch": 0.3225,
1692
+ "step": 129
1693
+ },
1694
+ {
1695
+ "epoch": 0.325,
1696
+ "grad_norm": 8.81209659576416,
1697
+ "learning_rate": 2.1315789473684212e-06,
1698
+ "loss": 0.418,
1699
+ "step": 130
1700
+ },
1701
+ {
1702
+ "Batch Mean": 0.00351560115814209,
1703
+ "accuracy": 0.7734375,
1704
+ "epoch": 0.325,
1705
+ "step": 130
1706
+ },
1707
+ {
1708
+ "epoch": 0.3275,
1709
+ "grad_norm": 9.197092056274414,
1710
+ "learning_rate": 2.123684210526316e-06,
1711
+ "loss": 0.4158,
1712
+ "step": 131
1713
+ },
1714
+ {
1715
+ "Batch Mean": 0.26228976249694824,
1716
+ "accuracy": 0.8515625,
1717
+ "epoch": 0.3275,
1718
+ "step": 131
1719
+ },
1720
+ {
1721
+ "epoch": 0.33,
1722
+ "grad_norm": 8.00036334991455,
1723
+ "learning_rate": 2.1157894736842103e-06,
1724
+ "loss": 0.3283,
1725
+ "step": 132
1726
+ },
1727
+ {
1728
+ "Batch Mean": 0.10788178443908691,
1729
+ "accuracy": 0.8125,
1730
+ "epoch": 0.33,
1731
+ "step": 132
1732
+ },
1733
+ {
1734
+ "epoch": 0.3325,
1735
+ "grad_norm": 7.9092116355896,
1736
+ "learning_rate": 2.107894736842105e-06,
1737
+ "loss": 0.3622,
1738
+ "step": 133
1739
+ },
1740
+ {
1741
+ "Batch Mean": 0.09739017486572266,
1742
+ "accuracy": 0.8515625,
1743
+ "epoch": 0.3325,
1744
+ "step": 133
1745
+ },
1746
+ {
1747
+ "epoch": 0.335,
1748
+ "grad_norm": 7.7380218505859375,
1749
+ "learning_rate": 2.1e-06,
1750
+ "loss": 0.3399,
1751
+ "step": 134
1752
+ },
1753
+ {
1754
+ "Batch Mean": -0.03578406572341919,
1755
+ "accuracy": 0.8203125,
1756
+ "epoch": 0.335,
1757
+ "step": 134
1758
+ },
1759
+ {
1760
+ "epoch": 0.3375,
1761
+ "grad_norm": 7.9607930183410645,
1762
+ "learning_rate": 2.0921052631578945e-06,
1763
+ "loss": 0.3681,
1764
+ "step": 135
1765
+ },
1766
+ {
1767
+ "Batch Mean": 0.2095022201538086,
1768
+ "accuracy": 0.7734375,
1769
+ "epoch": 0.3375,
1770
+ "step": 135
1771
+ },
1772
+ {
1773
+ "epoch": 0.34,
1774
+ "grad_norm": 9.16215705871582,
1775
+ "learning_rate": 2.0842105263157897e-06,
1776
+ "loss": 0.4474,
1777
+ "step": 136
1778
+ },
1779
+ {
1780
+ "Batch Mean": -0.12871003150939941,
1781
+ "accuracy": 0.78125,
1782
+ "epoch": 0.34,
1783
+ "step": 136
1784
+ },
1785
+ {
1786
+ "epoch": 0.3425,
1787
+ "grad_norm": 9.543075561523438,
1788
+ "learning_rate": 2.0763157894736845e-06,
1789
+ "loss": 0.4641,
1790
+ "step": 137
1791
+ },
1792
+ {
1793
+ "Batch Mean": -0.045391350984573364,
1794
+ "accuracy": 0.828125,
1795
+ "epoch": 0.3425,
1796
+ "step": 137
1797
+ },
1798
+ {
1799
+ "epoch": 0.345,
1800
+ "grad_norm": 8.620835304260254,
1801
+ "learning_rate": 2.068421052631579e-06,
1802
+ "loss": 0.388,
1803
+ "step": 138
1804
+ },
1805
+ {
1806
+ "Batch Mean": 0.023508906364440918,
1807
+ "accuracy": 0.7578125,
1808
+ "epoch": 0.345,
1809
+ "step": 138
1810
+ },
1811
+ {
1812
+ "epoch": 0.3475,
1813
+ "grad_norm": 10.10091781616211,
1814
+ "learning_rate": 2.060526315789474e-06,
1815
+ "loss": 0.4391,
1816
+ "step": 139
1817
+ },
1818
+ {
1819
+ "Batch Mean": -0.0003312826156616211,
1820
+ "accuracy": 0.8359375,
1821
+ "epoch": 0.3475,
1822
+ "step": 139
1823
+ },
1824
+ {
1825
+ "epoch": 0.35,
1826
+ "grad_norm": 8.200050354003906,
1827
+ "learning_rate": 2.0526315789473687e-06,
1828
+ "loss": 0.4196,
1829
+ "step": 140
1830
+ },
1831
+ {
1832
+ "Batch Mean": -0.304778516292572,
1833
+ "accuracy": 0.8359375,
1834
+ "epoch": 0.35,
1835
+ "step": 140
1836
+ },
1837
+ {
1838
+ "epoch": 0.3525,
1839
+ "grad_norm": 7.937561511993408,
1840
+ "learning_rate": 2.0447368421052634e-06,
1841
+ "loss": 0.3394,
1842
+ "step": 141
1843
+ },
1844
+ {
1845
+ "Batch Mean": -0.22019100189208984,
1846
+ "accuracy": 0.84375,
1847
+ "epoch": 0.3525,
1848
+ "step": 141
1849
+ },
1850
+ {
1851
+ "epoch": 0.355,
1852
+ "grad_norm": 8.111381530761719,
1853
+ "learning_rate": 2.0368421052631578e-06,
1854
+ "loss": 0.3878,
1855
+ "step": 142
1856
+ },
1857
+ {
1858
+ "Batch Mean": 0.4440329670906067,
1859
+ "accuracy": 0.8125,
1860
+ "epoch": 0.355,
1861
+ "step": 142
1862
+ },
1863
+ {
1864
+ "epoch": 0.3575,
1865
+ "grad_norm": 10.333617210388184,
1866
+ "learning_rate": 2.0289473684210525e-06,
1867
+ "loss": 0.4124,
1868
+ "step": 143
1869
+ },
1870
+ {
1871
+ "Batch Mean": 0.45398879051208496,
1872
+ "accuracy": 0.90625,
1873
+ "epoch": 0.3575,
1874
+ "step": 143
1875
+ },
1876
+ {
1877
+ "epoch": 0.36,
1878
+ "grad_norm": 7.195791721343994,
1879
+ "learning_rate": 2.0210526315789473e-06,
1880
+ "loss": 0.2869,
1881
+ "step": 144
1882
+ },
1883
+ {
1884
+ "Batch Mean": 0.13556790351867676,
1885
+ "accuracy": 0.8359375,
1886
+ "epoch": 0.36,
1887
+ "step": 144
1888
+ },
1889
+ {
1890
+ "epoch": 0.3625,
1891
+ "grad_norm": 8.249251365661621,
1892
+ "learning_rate": 2.013157894736842e-06,
1893
+ "loss": 0.3767,
1894
+ "step": 145
1895
+ },
1896
+ {
1897
+ "Batch Mean": 0.03792291879653931,
1898
+ "accuracy": 0.828125,
1899
+ "epoch": 0.3625,
1900
+ "step": 145
1901
+ },
1902
+ {
1903
+ "epoch": 0.365,
1904
+ "grad_norm": 10.333145141601562,
1905
+ "learning_rate": 2.0052631578947367e-06,
1906
+ "loss": 0.3784,
1907
+ "step": 146
1908
+ },
1909
+ {
1910
+ "Batch Mean": 0.05816793441772461,
1911
+ "accuracy": 0.828125,
1912
+ "epoch": 0.365,
1913
+ "step": 146
1914
+ },
1915
+ {
1916
+ "epoch": 0.3675,
1917
+ "grad_norm": 9.091706275939941,
1918
+ "learning_rate": 1.9973684210526315e-06,
1919
+ "loss": 0.4217,
1920
+ "step": 147
1921
+ },
1922
+ {
1923
+ "Batch Mean": 0.016840219497680664,
1924
+ "accuracy": 0.765625,
1925
+ "epoch": 0.3675,
1926
+ "step": 147
1927
+ },
1928
+ {
1929
+ "epoch": 0.37,
1930
+ "grad_norm": 12.988033294677734,
1931
+ "learning_rate": 1.9894736842105262e-06,
1932
+ "loss": 0.537,
1933
+ "step": 148
1934
+ },
1935
+ {
1936
+ "Batch Mean": -0.6307969093322754,
1937
+ "accuracy": 0.8671875,
1938
+ "epoch": 0.37,
1939
+ "step": 148
1940
+ },
1941
+ {
1942
+ "epoch": 0.3725,
1943
+ "grad_norm": 8.663951873779297,
1944
+ "learning_rate": 1.9815789473684214e-06,
1945
+ "loss": 0.2973,
1946
+ "step": 149
1947
+ },
1948
+ {
1949
+ "Batch Mean": -0.41460466384887695,
1950
+ "accuracy": 0.8359375,
1951
+ "epoch": 0.3725,
1952
+ "step": 149
1953
+ },
1954
+ {
1955
+ "epoch": 0.375,
1956
+ "grad_norm": 8.891082763671875,
1957
+ "learning_rate": 1.973684210526316e-06,
1958
+ "loss": 0.3553,
1959
+ "step": 150
1960
+ },
1961
+ {
1962
+ "Batch Mean": 0.045943260192871094,
1963
+ "accuracy": 0.859375,
1964
+ "epoch": 0.375,
1965
+ "step": 150
1966
+ },
1967
+ {
1968
+ "epoch": 0.3775,
1969
+ "grad_norm": 8.152697563171387,
1970
+ "learning_rate": 1.965789473684211e-06,
1971
+ "loss": 0.3515,
1972
+ "step": 151
1973
+ },
1974
+ {
1975
+ "Batch Mean": -0.18106698989868164,
1976
+ "accuracy": 0.796875,
1977
+ "epoch": 0.3775,
1978
+ "step": 151
1979
+ },
1980
+ {
1981
+ "epoch": 0.38,
1982
+ "grad_norm": 10.632974624633789,
1983
+ "learning_rate": 1.9578947368421052e-06,
1984
+ "loss": 0.4978,
1985
+ "step": 152
1986
+ },
1987
+ {
1988
+ "Batch Mean": 0.1395092010498047,
1989
+ "accuracy": 0.859375,
1990
+ "epoch": 0.38,
1991
+ "step": 152
1992
+ },
1993
+ {
1994
+ "epoch": 0.3825,
1995
+ "grad_norm": 8.301017761230469,
1996
+ "learning_rate": 1.95e-06,
1997
+ "loss": 0.3268,
1998
+ "step": 153
1999
+ },
2000
+ {
2001
+ "Batch Mean": 0.011521339416503906,
2002
+ "accuracy": 0.8046875,
2003
+ "epoch": 0.3825,
2004
+ "step": 153
2005
+ },
2006
+ {
2007
+ "epoch": 0.385,
2008
+ "grad_norm": 8.253169059753418,
2009
+ "learning_rate": 1.9421052631578947e-06,
2010
+ "loss": 0.3407,
2011
+ "step": 154
2012
+ },
2013
+ {
2014
+ "Batch Mean": -0.11399388313293457,
2015
+ "accuracy": 0.8515625,
2016
+ "epoch": 0.385,
2017
+ "step": 154
2018
+ },
2019
+ {
2020
+ "epoch": 0.3875,
2021
+ "grad_norm": 9.271583557128906,
2022
+ "learning_rate": 1.9342105263157895e-06,
2023
+ "loss": 0.3919,
2024
+ "step": 155
2025
+ },
2026
+ {
2027
+ "Batch Mean": 0.3950004577636719,
2028
+ "accuracy": 0.7890625,
2029
+ "epoch": 0.3875,
2030
+ "step": 155
2031
+ },
2032
+ {
2033
+ "epoch": 0.39,
2034
+ "grad_norm": 10.932522773742676,
2035
+ "learning_rate": 1.926315789473684e-06,
2036
+ "loss": 0.4111,
2037
+ "step": 156
2038
+ },
2039
+ {
2040
+ "Batch Mean": 0.24418425559997559,
2041
+ "accuracy": 0.8125,
2042
+ "epoch": 0.39,
2043
+ "step": 156
2044
+ },
2045
+ {
2046
+ "epoch": 0.3925,
2047
+ "grad_norm": 9.256501197814941,
2048
+ "learning_rate": 1.918421052631579e-06,
2049
+ "loss": 0.4292,
2050
+ "step": 157
2051
+ },
2052
+ {
2053
+ "Batch Mean": -0.1265101432800293,
2054
+ "accuracy": 0.8125,
2055
+ "epoch": 0.3925,
2056
+ "step": 157
2057
+ },
2058
+ {
2059
+ "epoch": 0.395,
2060
+ "grad_norm": 8.907751083374023,
2061
+ "learning_rate": 1.9105263157894737e-06,
2062
+ "loss": 0.3853,
2063
+ "step": 158
2064
+ },
2065
+ {
2066
+ "Batch Mean": -0.35911059379577637,
2067
+ "accuracy": 0.828125,
2068
+ "epoch": 0.395,
2069
+ "step": 158
2070
+ },
2071
+ {
2072
+ "epoch": 0.3975,
2073
+ "grad_norm": 9.353957176208496,
2074
+ "learning_rate": 1.9026315789473684e-06,
2075
+ "loss": 0.4177,
2076
+ "step": 159
2077
+ },
2078
+ {
2079
+ "Batch Mean": -0.49236249923706055,
2080
+ "accuracy": 0.828125,
2081
+ "epoch": 0.3975,
2082
+ "step": 159
2083
+ },
2084
+ {
2085
+ "epoch": 0.4,
2086
+ "grad_norm": 8.749178886413574,
2087
+ "learning_rate": 1.8947368421052632e-06,
2088
+ "loss": 0.3711,
2089
+ "step": 160
2090
+ },
2091
+ {
2092
+ "Batch Mean": 0.1534252166748047,
2093
+ "accuracy": 0.8671875,
2094
+ "epoch": 0.4,
2095
+ "step": 160
2096
+ },
2097
+ {
2098
+ "epoch": 0.4025,
2099
+ "grad_norm": 8.529258728027344,
2100
+ "learning_rate": 1.8868421052631577e-06,
2101
+ "loss": 0.3523,
2102
+ "step": 161
2103
+ },
2104
+ {
2105
+ "Batch Mean": 0.11423969268798828,
2106
+ "accuracy": 0.8125,
2107
+ "epoch": 0.4025,
2108
+ "step": 161
2109
+ },
2110
+ {
2111
+ "epoch": 0.405,
2112
+ "grad_norm": 8.786529541015625,
2113
+ "learning_rate": 1.8789473684210525e-06,
2114
+ "loss": 0.3942,
2115
+ "step": 162
2116
+ },
2117
+ {
2118
+ "Batch Mean": 0.15482479333877563,
2119
+ "accuracy": 0.828125,
2120
+ "epoch": 0.405,
2121
+ "step": 162
2122
+ },
2123
+ {
2124
+ "epoch": 0.4075,
2125
+ "grad_norm": 8.650775909423828,
2126
+ "learning_rate": 1.8710526315789476e-06,
2127
+ "loss": 0.3971,
2128
+ "step": 163
2129
+ },
2130
+ {
2131
+ "Batch Mean": 0.19225120544433594,
2132
+ "accuracy": 0.859375,
2133
+ "epoch": 0.4075,
2134
+ "step": 163
2135
+ },
2136
+ {
2137
+ "epoch": 0.41,
2138
+ "grad_norm": 7.860261917114258,
2139
+ "learning_rate": 1.8631578947368424e-06,
2140
+ "loss": 0.3098,
2141
+ "step": 164
2142
+ },
2143
+ {
2144
+ "Batch Mean": 0.570763111114502,
2145
+ "accuracy": 0.828125,
2146
+ "epoch": 0.41,
2147
+ "step": 164
2148
+ },
2149
+ {
2150
+ "epoch": 0.4125,
2151
+ "grad_norm": 9.458237648010254,
2152
+ "learning_rate": 1.855263157894737e-06,
2153
+ "loss": 0.4007,
2154
+ "step": 165
2155
+ },
2156
+ {
2157
+ "Batch Mean": 0.1940155029296875,
2158
+ "accuracy": 0.796875,
2159
+ "epoch": 0.4125,
2160
+ "step": 165
2161
+ },
2162
+ {
2163
+ "epoch": 0.415,
2164
+ "grad_norm": 8.419119834899902,
2165
+ "learning_rate": 1.8473684210526317e-06,
2166
+ "loss": 0.3679,
2167
+ "step": 166
2168
+ },
2169
+ {
2170
+ "Batch Mean": 0.13667702674865723,
2171
+ "accuracy": 0.8125,
2172
+ "epoch": 0.415,
2173
+ "step": 166
2174
+ },
2175
+ {
2176
+ "epoch": 0.4175,
2177
+ "grad_norm": 11.180956840515137,
2178
+ "learning_rate": 1.8394736842105264e-06,
2179
+ "loss": 0.4043,
2180
+ "step": 167
2181
+ },
2182
+ {
2183
+ "Batch Mean": -0.47870922088623047,
2184
+ "accuracy": 0.796875,
2185
+ "epoch": 0.4175,
2186
+ "step": 167
2187
+ },
2188
+ {
2189
+ "epoch": 0.42,
2190
+ "grad_norm": 11.080053329467773,
2191
+ "learning_rate": 1.8315789473684211e-06,
2192
+ "loss": 0.4806,
2193
+ "step": 168
2194
+ },
2195
+ {
2196
+ "Batch Mean": -0.07008326053619385,
2197
+ "accuracy": 0.8125,
2198
+ "epoch": 0.42,
2199
+ "step": 168
2200
+ },
2201
+ {
2202
+ "epoch": 0.4225,
2203
+ "grad_norm": 9.977706909179688,
2204
+ "learning_rate": 1.8236842105263159e-06,
2205
+ "loss": 0.3711,
2206
+ "step": 169
2207
+ },
2208
+ {
2209
+ "Batch Mean": -0.21228408813476562,
2210
+ "accuracy": 0.78125,
2211
+ "epoch": 0.4225,
2212
+ "step": 169
2213
+ },
2214
+ {
2215
+ "epoch": 0.425,
2216
+ "grad_norm": 9.771838188171387,
2217
+ "learning_rate": 1.8157894736842106e-06,
2218
+ "loss": 0.4154,
2219
+ "step": 170
2220
+ },
2221
+ {
2222
+ "Batch Mean": -0.014397621154785156,
2223
+ "accuracy": 0.8671875,
2224
+ "epoch": 0.425,
2225
+ "step": 170
2226
+ },
2227
+ {
2228
+ "epoch": 0.4275,
2229
+ "grad_norm": 7.314267158508301,
2230
+ "learning_rate": 1.8078947368421052e-06,
2231
+ "loss": 0.2636,
2232
+ "step": 171
2233
+ },
2234
+ {
2235
+ "Batch Mean": 0.3306160569190979,
2236
+ "accuracy": 0.828125,
2237
+ "epoch": 0.4275,
2238
+ "step": 171
2239
+ },
2240
+ {
2241
+ "epoch": 0.43,
2242
+ "grad_norm": 8.739150047302246,
2243
+ "learning_rate": 1.8e-06,
2244
+ "loss": 0.3611,
2245
+ "step": 172
2246
+ },
2247
+ {
2248
+ "Batch Mean": -0.0874967873096466,
2249
+ "accuracy": 0.7890625,
2250
+ "epoch": 0.43,
2251
+ "step": 172
2252
+ },
2253
+ {
2254
+ "epoch": 0.4325,
2255
+ "grad_norm": 9.247507095336914,
2256
+ "learning_rate": 1.7921052631578947e-06,
2257
+ "loss": 0.4175,
2258
+ "step": 173
2259
+ },
2260
+ {
2261
+ "Batch Mean": 0.2975928783416748,
2262
+ "accuracy": 0.84375,
2263
+ "epoch": 0.4325,
2264
+ "step": 173
2265
+ },
2266
+ {
2267
+ "epoch": 0.435,
2268
+ "grad_norm": 9.041180610656738,
2269
+ "learning_rate": 1.7842105263157894e-06,
2270
+ "loss": 0.3671,
2271
+ "step": 174
2272
+ },
2273
+ {
2274
+ "Batch Mean": 0.015955865383148193,
2275
+ "accuracy": 0.7421875,
2276
+ "epoch": 0.435,
2277
+ "step": 174
2278
+ },
2279
+ {
2280
+ "epoch": 0.4375,
2281
+ "grad_norm": 11.472379684448242,
2282
+ "learning_rate": 1.7763157894736842e-06,
2283
+ "loss": 0.4833,
2284
+ "step": 175
2285
+ },
2286
+ {
2287
+ "Batch Mean": -0.36949777603149414,
2288
+ "accuracy": 0.7421875,
2289
+ "epoch": 0.4375,
2290
+ "step": 175
2291
+ },
2292
+ {
2293
+ "epoch": 0.44,
2294
+ "grad_norm": 11.286201477050781,
2295
+ "learning_rate": 1.768421052631579e-06,
2296
+ "loss": 0.4855,
2297
+ "step": 176
2298
+ },
2299
+ {
2300
+ "Batch Mean": -0.3930339813232422,
2301
+ "accuracy": 0.828125,
2302
+ "epoch": 0.44,
2303
+ "step": 176
2304
+ },
2305
+ {
2306
+ "epoch": 0.4425,
2307
+ "grad_norm": 10.522198677062988,
2308
+ "learning_rate": 1.7605263157894739e-06,
2309
+ "loss": 0.3819,
2310
+ "step": 177
2311
+ },
2312
+ {
2313
+ "Batch Mean": 0.08716198801994324,
2314
+ "accuracy": 0.828125,
2315
+ "epoch": 0.4425,
2316
+ "step": 177
2317
+ },
2318
+ {
2319
+ "epoch": 0.445,
2320
+ "grad_norm": 9.067276000976562,
2321
+ "learning_rate": 1.7526315789473686e-06,
2322
+ "loss": 0.3921,
2323
+ "step": 178
2324
+ },
2325
+ {
2326
+ "Batch Mean": -0.25193285942077637,
2327
+ "accuracy": 0.8203125,
2328
+ "epoch": 0.445,
2329
+ "step": 178
2330
+ },
2331
+ {
2332
+ "epoch": 0.4475,
2333
+ "grad_norm": 9.11840534210205,
2334
+ "learning_rate": 1.7447368421052633e-06,
2335
+ "loss": 0.4172,
2336
+ "step": 179
2337
+ },
2338
+ {
2339
+ "Batch Mean": -0.23209238052368164,
2340
+ "accuracy": 0.8203125,
2341
+ "epoch": 0.4475,
2342
+ "step": 179
2343
+ },
2344
+ {
2345
+ "epoch": 0.45,
2346
+ "grad_norm": 11.945143699645996,
2347
+ "learning_rate": 1.736842105263158e-06,
2348
+ "loss": 0.3795,
2349
+ "step": 180
2350
+ },
2351
+ {
2352
+ "Batch Mean": -0.21220535039901733,
2353
+ "accuracy": 0.8984375,
2354
+ "epoch": 0.45,
2355
+ "step": 180
2356
+ },
2357
+ {
2358
+ "epoch": 0.4525,
2359
+ "grad_norm": 8.286118507385254,
2360
+ "learning_rate": 1.7289473684210526e-06,
2361
+ "loss": 0.2964,
2362
+ "step": 181
2363
+ },
2364
+ {
2365
+ "Batch Mean": 0.15385687351226807,
2366
+ "accuracy": 0.8203125,
2367
+ "epoch": 0.4525,
2368
+ "step": 181
2369
+ },
2370
+ {
2371
+ "epoch": 0.455,
2372
+ "grad_norm": 8.66666316986084,
2373
+ "learning_rate": 1.7210526315789474e-06,
2374
+ "loss": 0.3717,
2375
+ "step": 182
2376
+ },
2377
+ {
2378
+ "Batch Mean": 0.47098982334136963,
2379
+ "accuracy": 0.8125,
2380
+ "epoch": 0.455,
2381
+ "step": 182
2382
+ },
2383
+ {
2384
+ "epoch": 0.4575,
2385
+ "grad_norm": 9.041359901428223,
2386
+ "learning_rate": 1.7131578947368421e-06,
2387
+ "loss": 0.3627,
2388
+ "step": 183
2389
+ },
2390
+ {
2391
+ "Batch Mean": 0.2258845567703247,
2392
+ "accuracy": 0.8359375,
2393
+ "epoch": 0.4575,
2394
+ "step": 183
2395
+ },
2396
+ {
2397
+ "epoch": 0.46,
2398
+ "grad_norm": 10.031190872192383,
2399
+ "learning_rate": 1.7052631578947369e-06,
2400
+ "loss": 0.4308,
2401
+ "step": 184
2402
+ },
2403
+ {
2404
+ "Batch Mean": 0.1376625895500183,
2405
+ "accuracy": 0.7890625,
2406
+ "epoch": 0.46,
2407
+ "step": 184
2408
+ },
2409
+ {
2410
+ "epoch": 0.4625,
2411
+ "grad_norm": 8.849730491638184,
2412
+ "learning_rate": 1.6973684210526316e-06,
2413
+ "loss": 0.3612,
2414
+ "step": 185
2415
+ },
2416
+ {
2417
+ "Batch Mean": -0.25082847476005554,
2418
+ "accuracy": 0.8359375,
2419
+ "epoch": 0.4625,
2420
+ "step": 185
2421
+ },
2422
+ {
2423
+ "epoch": 0.465,
2424
+ "grad_norm": 9.715136528015137,
2425
+ "learning_rate": 1.6894736842105264e-06,
2426
+ "loss": 0.4192,
2427
+ "step": 186
2428
+ },
2429
+ {
2430
+ "Batch Mean": -0.43356090784072876,
2431
+ "accuracy": 0.859375,
2432
+ "epoch": 0.465,
2433
+ "step": 186
2434
+ },
2435
+ {
2436
+ "epoch": 0.4675,
2437
+ "grad_norm": 8.193946838378906,
2438
+ "learning_rate": 1.6815789473684209e-06,
2439
+ "loss": 0.3504,
2440
+ "step": 187
2441
+ },
2442
+ {
2443
+ "Batch Mean": -0.013092756271362305,
2444
+ "accuracy": 0.875,
2445
+ "epoch": 0.4675,
2446
+ "step": 187
2447
+ },
2448
+ {
2449
+ "epoch": 0.47,
2450
+ "grad_norm": 8.71420955657959,
2451
+ "learning_rate": 1.6736842105263156e-06,
2452
+ "loss": 0.3437,
2453
+ "step": 188
2454
+ },
2455
+ {
2456
+ "Batch Mean": 0.13508832454681396,
2457
+ "accuracy": 0.78125,
2458
+ "epoch": 0.47,
2459
+ "step": 188
2460
+ },
2461
+ {
2462
+ "epoch": 0.4725,
2463
+ "grad_norm": 10.5387544631958,
2464
+ "learning_rate": 1.6657894736842104e-06,
2465
+ "loss": 0.4141,
2466
+ "step": 189
2467
+ },
2468
+ {
2469
+ "Batch Mean": 0.12293338775634766,
2470
+ "accuracy": 0.84375,
2471
+ "epoch": 0.4725,
2472
+ "step": 189
2473
+ },
2474
+ {
2475
+ "epoch": 0.475,
2476
+ "grad_norm": 8.671295166015625,
2477
+ "learning_rate": 1.6578947368421056e-06,
2478
+ "loss": 0.3752,
2479
+ "step": 190
2480
+ },
2481
+ {
2482
+ "Batch Mean": 0.47929099202156067,
2483
+ "accuracy": 0.8203125,
2484
+ "epoch": 0.475,
2485
+ "step": 190
2486
+ },
2487
+ {
2488
+ "epoch": 0.4775,
2489
+ "grad_norm": 11.653754234313965,
2490
+ "learning_rate": 1.65e-06,
2491
+ "loss": 0.4854,
2492
+ "step": 191
2493
+ },
2494
+ {
2495
+ "Batch Mean": 0.49117136001586914,
2496
+ "accuracy": 0.84375,
2497
+ "epoch": 0.4775,
2498
+ "step": 191
2499
+ },
2500
+ {
2501
+ "epoch": 0.48,
2502
+ "grad_norm": 8.04267406463623,
2503
+ "learning_rate": 1.6421052631578948e-06,
2504
+ "loss": 0.3098,
2505
+ "step": 192
2506
+ },
2507
+ {
2508
+ "Batch Mean": 0.5062227249145508,
2509
+ "accuracy": 0.8828125,
2510
+ "epoch": 0.48,
2511
+ "step": 192
2512
+ },
2513
+ {
2514
+ "epoch": 0.4825,
2515
+ "grad_norm": 8.732284545898438,
2516
+ "learning_rate": 1.6342105263157896e-06,
2517
+ "loss": 0.3193,
2518
+ "step": 193
2519
+ },
2520
+ {
2521
+ "Batch Mean": -0.3749980926513672,
2522
+ "accuracy": 0.859375,
2523
+ "epoch": 0.4825,
2524
+ "step": 193
2525
+ },
2526
+ {
2527
+ "epoch": 0.485,
2528
+ "grad_norm": 8.27978515625,
2529
+ "learning_rate": 1.6263157894736843e-06,
2530
+ "loss": 0.337,
2531
+ "step": 194
2532
+ },
2533
+ {
2534
+ "Batch Mean": -0.6132583618164062,
2535
+ "accuracy": 0.765625,
2536
+ "epoch": 0.485,
2537
+ "step": 194
2538
+ },
2539
+ {
2540
+ "epoch": 0.4875,
2541
+ "grad_norm": 9.447763442993164,
2542
+ "learning_rate": 1.618421052631579e-06,
2543
+ "loss": 0.4433,
2544
+ "step": 195
2545
+ },
2546
+ {
2547
+ "Batch Mean": -0.452798068523407,
2548
+ "accuracy": 0.859375,
2549
+ "epoch": 0.4875,
2550
+ "step": 195
2551
+ },
2552
+ {
2553
+ "epoch": 0.49,
2554
+ "grad_norm": 8.492661476135254,
2555
+ "learning_rate": 1.6105263157894738e-06,
2556
+ "loss": 0.3995,
2557
+ "step": 196
2558
+ },
2559
+ {
2560
+ "Batch Mean": -0.3771591782569885,
2561
+ "accuracy": 0.828125,
2562
+ "epoch": 0.49,
2563
+ "step": 196
2564
+ },
2565
+ {
2566
+ "epoch": 0.4925,
2567
+ "grad_norm": 8.175331115722656,
2568
+ "learning_rate": 1.6026315789473683e-06,
2569
+ "loss": 0.3677,
2570
+ "step": 197
2571
+ },
2572
+ {
2573
+ "Batch Mean": 0.2654750347137451,
2574
+ "accuracy": 0.84375,
2575
+ "epoch": 0.4925,
2576
+ "step": 197
2577
+ },
2578
+ {
2579
+ "epoch": 0.495,
2580
+ "grad_norm": 8.926229476928711,
2581
+ "learning_rate": 1.594736842105263e-06,
2582
+ "loss": 0.3555,
2583
+ "step": 198
2584
+ },
2585
+ {
2586
+ "Batch Mean": 0.09074139595031738,
2587
+ "accuracy": 0.765625,
2588
+ "epoch": 0.495,
2589
+ "step": 198
2590
+ },
2591
+ {
2592
+ "epoch": 0.4975,
2593
+ "grad_norm": 10.059514999389648,
2594
+ "learning_rate": 1.5868421052631578e-06,
2595
+ "loss": 0.4346,
2596
+ "step": 199
2597
+ },
2598
+ {
2599
+ "Batch Mean": 0.15778541564941406,
2600
+ "accuracy": 0.7578125,
2601
+ "epoch": 0.4975,
2602
+ "step": 199
2603
+ },
2604
+ {
2605
+ "epoch": 0.5,
2606
+ "grad_norm": 8.965482711791992,
2607
+ "learning_rate": 1.5789473684210526e-06,
2608
+ "loss": 0.4118,
2609
+ "step": 200
2610
+ }
2611
+ ],
2612
+ "logging_steps": 1,
2613
+ "max_steps": 400,
2614
+ "num_input_tokens_seen": 0,
2615
+ "num_train_epochs": 1,
2616
+ "save_steps": 100,
2617
+ "stateful_callbacks": {
2618
+ "TrainerControl": {
2619
+ "args": {
2620
+ "should_epoch_stop": false,
2621
+ "should_evaluate": false,
2622
+ "should_log": false,
2623
+ "should_save": true,
2624
+ "should_training_stop": false
2625
+ },
2626
+ "attributes": {}
2627
+ }
2628
+ },
2629
+ "total_flos": 0.0,
2630
+ "train_batch_size": 16,
2631
+ "trial_name": null,
2632
+ "trial_params": null
2633
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd1362576452dc1dede51df1a8532cf1318d832a39af9b44e8dcc8537827bc1
3
+ size 5688
checkpoint-300/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-3B-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": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
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": 24,
29
+ "num_hidden_layers": 28,
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-300/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d06c3a5cfa17f9e738a73e9f092bf3c554c6004f0f9ca31a7756d0dca8ab7736
3
+ size 4998767360
checkpoint-300/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1085c4a5e6864649eefcb3b2be785cb4ed263fd1bae46271f70edb331b791ed
3
+ size 4932808968
checkpoint-300/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f0ee34f9f79abfa64d2cfdd51771e13809ca5bb3a64c42279c291169aad0ae
3
+ size 2919464544
checkpoint-300/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12851011584
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.norm.weight": "model-00003-of-00003.safetensors",
260
+ "score.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
checkpoint-300/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-300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-300/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-300/trainer_state.json ADDED
@@ -0,0 +1,3933 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.75,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
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": 0.7002408504486084,
13
+ "accuracy": 0.53125,
14
+ "epoch": 0,
15
+ "step": 0
16
+ },
17
+ {
18
+ "epoch": 0.0025,
19
+ "grad_norm": 4.865061283111572,
20
+ "learning_rate": 1.5000000000000002e-07,
21
+ "loss": 0.6999,
22
+ "step": 1
23
+ },
24
+ {
25
+ "Batch Mean": 0.7006568908691406,
26
+ "accuracy": 0.5078125,
27
+ "epoch": 0.0025,
28
+ "step": 1
29
+ },
30
+ {
31
+ "epoch": 0.005,
32
+ "grad_norm": 5.116915702819824,
33
+ "learning_rate": 3.0000000000000004e-07,
34
+ "loss": 0.706,
35
+ "step": 2
36
+ },
37
+ {
38
+ "Batch Mean": 0.7036838531494141,
39
+ "accuracy": 0.5625,
40
+ "epoch": 0.005,
41
+ "step": 2
42
+ },
43
+ {
44
+ "epoch": 0.0075,
45
+ "grad_norm": 4.952433109283447,
46
+ "learning_rate": 4.5e-07,
47
+ "loss": 0.6957,
48
+ "step": 3
49
+ },
50
+ {
51
+ "Batch Mean": 0.7087974548339844,
52
+ "accuracy": 0.5546875,
53
+ "epoch": 0.0075,
54
+ "step": 3
55
+ },
56
+ {
57
+ "epoch": 0.01,
58
+ "grad_norm": 5.185088157653809,
59
+ "learning_rate": 6.000000000000001e-07,
60
+ "loss": 0.6974,
61
+ "step": 4
62
+ },
63
+ {
64
+ "Batch Mean": 0.7068939208984375,
65
+ "accuracy": 0.5234375,
66
+ "epoch": 0.01,
67
+ "step": 4
68
+ },
69
+ {
70
+ "epoch": 0.0125,
71
+ "grad_norm": 5.04327392578125,
72
+ "learning_rate": 7.5e-07,
73
+ "loss": 0.7047,
74
+ "step": 5
75
+ },
76
+ {
77
+ "Batch Mean": 0.6315479278564453,
78
+ "accuracy": 0.5234375,
79
+ "epoch": 0.0125,
80
+ "step": 5
81
+ },
82
+ {
83
+ "epoch": 0.015,
84
+ "grad_norm": 4.728168487548828,
85
+ "learning_rate": 9e-07,
86
+ "loss": 0.6932,
87
+ "step": 6
88
+ },
89
+ {
90
+ "Batch Mean": 0.5291571617126465,
91
+ "accuracy": 0.5234375,
92
+ "epoch": 0.015,
93
+ "step": 6
94
+ },
95
+ {
96
+ "epoch": 0.0175,
97
+ "grad_norm": 4.0146050453186035,
98
+ "learning_rate": 1.05e-06,
99
+ "loss": 0.691,
100
+ "step": 7
101
+ },
102
+ {
103
+ "Batch Mean": 0.42229437828063965,
104
+ "accuracy": 0.5546875,
105
+ "epoch": 0.0175,
106
+ "step": 7
107
+ },
108
+ {
109
+ "epoch": 0.02,
110
+ "grad_norm": 3.488922119140625,
111
+ "learning_rate": 1.2000000000000002e-06,
112
+ "loss": 0.6947,
113
+ "step": 8
114
+ },
115
+ {
116
+ "Batch Mean": 0.07428494095802307,
117
+ "accuracy": 0.515625,
118
+ "epoch": 0.02,
119
+ "step": 8
120
+ },
121
+ {
122
+ "epoch": 0.0225,
123
+ "grad_norm": 2.5626139640808105,
124
+ "learning_rate": 1.35e-06,
125
+ "loss": 0.6965,
126
+ "step": 9
127
+ },
128
+ {
129
+ "Batch Mean": -0.1413576304912567,
130
+ "accuracy": 0.5859375,
131
+ "epoch": 0.0225,
132
+ "step": 9
133
+ },
134
+ {
135
+ "epoch": 0.025,
136
+ "grad_norm": 2.776390790939331,
137
+ "learning_rate": 1.5e-06,
138
+ "loss": 0.6784,
139
+ "step": 10
140
+ },
141
+ {
142
+ "Batch Mean": -0.2741769552230835,
143
+ "accuracy": 0.5234375,
144
+ "epoch": 0.025,
145
+ "step": 10
146
+ },
147
+ {
148
+ "epoch": 0.0275,
149
+ "grad_norm": 3.4468233585357666,
150
+ "learning_rate": 1.65e-06,
151
+ "loss": 0.6844,
152
+ "step": 11
153
+ },
154
+ {
155
+ "Batch Mean": -0.45577430725097656,
156
+ "accuracy": 0.5859375,
157
+ "epoch": 0.0275,
158
+ "step": 11
159
+ },
160
+ {
161
+ "epoch": 0.03,
162
+ "grad_norm": 4.281182765960693,
163
+ "learning_rate": 1.8e-06,
164
+ "loss": 0.6753,
165
+ "step": 12
166
+ },
167
+ {
168
+ "Batch Mean": -1.0260009765625,
169
+ "accuracy": 0.65625,
170
+ "epoch": 0.03,
171
+ "step": 12
172
+ },
173
+ {
174
+ "epoch": 0.0325,
175
+ "grad_norm": 6.948849201202393,
176
+ "learning_rate": 1.95e-06,
177
+ "loss": 0.6734,
178
+ "step": 13
179
+ },
180
+ {
181
+ "Batch Mean": -1.1147994995117188,
182
+ "accuracy": 0.6171875,
183
+ "epoch": 0.0325,
184
+ "step": 13
185
+ },
186
+ {
187
+ "epoch": 0.035,
188
+ "grad_norm": 7.589419841766357,
189
+ "learning_rate": 2.1e-06,
190
+ "loss": 0.677,
191
+ "step": 14
192
+ },
193
+ {
194
+ "Batch Mean": -1.0315093994140625,
195
+ "accuracy": 0.65625,
196
+ "epoch": 0.035,
197
+ "step": 14
198
+ },
199
+ {
200
+ "epoch": 0.0375,
201
+ "grad_norm": 7.2146382331848145,
202
+ "learning_rate": 2.25e-06,
203
+ "loss": 0.677,
204
+ "step": 15
205
+ },
206
+ {
207
+ "Batch Mean": -0.8089427947998047,
208
+ "accuracy": 0.65625,
209
+ "epoch": 0.0375,
210
+ "step": 15
211
+ },
212
+ {
213
+ "epoch": 0.04,
214
+ "grad_norm": 6.308068752288818,
215
+ "learning_rate": 2.4000000000000003e-06,
216
+ "loss": 0.6503,
217
+ "step": 16
218
+ },
219
+ {
220
+ "Batch Mean": -0.3669371008872986,
221
+ "accuracy": 0.671875,
222
+ "epoch": 0.04,
223
+ "step": 16
224
+ },
225
+ {
226
+ "epoch": 0.0425,
227
+ "grad_norm": 4.996833324432373,
228
+ "learning_rate": 2.55e-06,
229
+ "loss": 0.617,
230
+ "step": 17
231
+ },
232
+ {
233
+ "Batch Mean": 0.2619136571884155,
234
+ "accuracy": 0.6796875,
235
+ "epoch": 0.0425,
236
+ "step": 17
237
+ },
238
+ {
239
+ "epoch": 0.045,
240
+ "grad_norm": 4.9718918800354,
241
+ "learning_rate": 2.7e-06,
242
+ "loss": 0.5981,
243
+ "step": 18
244
+ },
245
+ {
246
+ "Batch Mean": 1.0361242294311523,
247
+ "accuracy": 0.625,
248
+ "epoch": 0.045,
249
+ "step": 18
250
+ },
251
+ {
252
+ "epoch": 0.0475,
253
+ "grad_norm": 9.635746955871582,
254
+ "learning_rate": 2.85e-06,
255
+ "loss": 0.6236,
256
+ "step": 19
257
+ },
258
+ {
259
+ "Batch Mean": 1.5605192184448242,
260
+ "accuracy": 0.65625,
261
+ "epoch": 0.0475,
262
+ "step": 19
263
+ },
264
+ {
265
+ "epoch": 0.05,
266
+ "grad_norm": 14.90079116821289,
267
+ "learning_rate": 3e-06,
268
+ "loss": 0.6511,
269
+ "step": 20
270
+ },
271
+ {
272
+ "Batch Mean": 1.7601673603057861,
273
+ "accuracy": 0.6796875,
274
+ "epoch": 0.05,
275
+ "step": 20
276
+ },
277
+ {
278
+ "epoch": 0.0525,
279
+ "grad_norm": 16.801076889038086,
280
+ "learning_rate": 2.992105263157895e-06,
281
+ "loss": 0.6712,
282
+ "step": 21
283
+ },
284
+ {
285
+ "Batch Mean": 1.1987818479537964,
286
+ "accuracy": 0.7109375,
287
+ "epoch": 0.0525,
288
+ "step": 21
289
+ },
290
+ {
291
+ "epoch": 0.055,
292
+ "grad_norm": 11.280301094055176,
293
+ "learning_rate": 2.9842105263157896e-06,
294
+ "loss": 0.6033,
295
+ "step": 22
296
+ },
297
+ {
298
+ "Batch Mean": 0.5978413820266724,
299
+ "accuracy": 0.6875,
300
+ "epoch": 0.055,
301
+ "step": 22
302
+ },
303
+ {
304
+ "epoch": 0.0575,
305
+ "grad_norm": 7.414430141448975,
306
+ "learning_rate": 2.9763157894736843e-06,
307
+ "loss": 0.5819,
308
+ "step": 23
309
+ },
310
+ {
311
+ "Batch Mean": -0.20422333478927612,
312
+ "accuracy": 0.6640625,
313
+ "epoch": 0.0575,
314
+ "step": 23
315
+ },
316
+ {
317
+ "epoch": 0.06,
318
+ "grad_norm": 5.717103004455566,
319
+ "learning_rate": 2.968421052631579e-06,
320
+ "loss": 0.638,
321
+ "step": 24
322
+ },
323
+ {
324
+ "Batch Mean": -0.7162615060806274,
325
+ "accuracy": 0.75,
326
+ "epoch": 0.06,
327
+ "step": 24
328
+ },
329
+ {
330
+ "epoch": 0.0625,
331
+ "grad_norm": 7.513117790222168,
332
+ "learning_rate": 2.960526315789474e-06,
333
+ "loss": 0.5851,
334
+ "step": 25
335
+ },
336
+ {
337
+ "Batch Mean": -1.054888129234314,
338
+ "accuracy": 0.6796875,
339
+ "epoch": 0.0625,
340
+ "step": 25
341
+ },
342
+ {
343
+ "epoch": 0.065,
344
+ "grad_norm": 8.300326347351074,
345
+ "learning_rate": 2.9526315789473685e-06,
346
+ "loss": 0.6286,
347
+ "step": 26
348
+ },
349
+ {
350
+ "Batch Mean": -1.1319353580474854,
351
+ "accuracy": 0.703125,
352
+ "epoch": 0.065,
353
+ "step": 26
354
+ },
355
+ {
356
+ "epoch": 0.0675,
357
+ "grad_norm": 9.116662979125977,
358
+ "learning_rate": 2.9447368421052633e-06,
359
+ "loss": 0.6003,
360
+ "step": 27
361
+ },
362
+ {
363
+ "Batch Mean": -0.7403234839439392,
364
+ "accuracy": 0.7265625,
365
+ "epoch": 0.0675,
366
+ "step": 27
367
+ },
368
+ {
369
+ "epoch": 0.07,
370
+ "grad_norm": 6.799551486968994,
371
+ "learning_rate": 2.936842105263158e-06,
372
+ "loss": 0.5383,
373
+ "step": 28
374
+ },
375
+ {
376
+ "Batch Mean": -0.25867950916290283,
377
+ "accuracy": 0.703125,
378
+ "epoch": 0.07,
379
+ "step": 28
380
+ },
381
+ {
382
+ "epoch": 0.0725,
383
+ "grad_norm": 5.493288040161133,
384
+ "learning_rate": 2.9289473684210528e-06,
385
+ "loss": 0.5683,
386
+ "step": 29
387
+ },
388
+ {
389
+ "Batch Mean": 0.4318051338195801,
390
+ "accuracy": 0.6796875,
391
+ "epoch": 0.0725,
392
+ "step": 29
393
+ },
394
+ {
395
+ "epoch": 0.075,
396
+ "grad_norm": 6.373619556427002,
397
+ "learning_rate": 2.9210526315789475e-06,
398
+ "loss": 0.6126,
399
+ "step": 30
400
+ },
401
+ {
402
+ "Batch Mean": 0.8685734272003174,
403
+ "accuracy": 0.7265625,
404
+ "epoch": 0.075,
405
+ "step": 30
406
+ },
407
+ {
408
+ "epoch": 0.0775,
409
+ "grad_norm": 7.750959396362305,
410
+ "learning_rate": 2.9131578947368423e-06,
411
+ "loss": 0.5984,
412
+ "step": 31
413
+ },
414
+ {
415
+ "Batch Mean": 1.1348557472229004,
416
+ "accuracy": 0.6484375,
417
+ "epoch": 0.0775,
418
+ "step": 31
419
+ },
420
+ {
421
+ "epoch": 0.08,
422
+ "grad_norm": 8.742609977722168,
423
+ "learning_rate": 2.905263157894737e-06,
424
+ "loss": 0.6016,
425
+ "step": 32
426
+ },
427
+ {
428
+ "Batch Mean": 0.6863436698913574,
429
+ "accuracy": 0.7421875,
430
+ "epoch": 0.08,
431
+ "step": 32
432
+ },
433
+ {
434
+ "epoch": 0.0825,
435
+ "grad_norm": 6.586100101470947,
436
+ "learning_rate": 2.8973684210526318e-06,
437
+ "loss": 0.5485,
438
+ "step": 33
439
+ },
440
+ {
441
+ "Batch Mean": 0.23023658990859985,
442
+ "accuracy": 0.765625,
443
+ "epoch": 0.0825,
444
+ "step": 33
445
+ },
446
+ {
447
+ "epoch": 0.085,
448
+ "grad_norm": 5.231872081756592,
449
+ "learning_rate": 2.8894736842105265e-06,
450
+ "loss": 0.4999,
451
+ "step": 34
452
+ },
453
+ {
454
+ "Batch Mean": -0.2048710286617279,
455
+ "accuracy": 0.734375,
456
+ "epoch": 0.085,
457
+ "step": 34
458
+ },
459
+ {
460
+ "epoch": 0.0875,
461
+ "grad_norm": 5.551333427429199,
462
+ "learning_rate": 2.8815789473684213e-06,
463
+ "loss": 0.5541,
464
+ "step": 35
465
+ },
466
+ {
467
+ "Batch Mean": -0.4559789299964905,
468
+ "accuracy": 0.7421875,
469
+ "epoch": 0.0875,
470
+ "step": 35
471
+ },
472
+ {
473
+ "epoch": 0.09,
474
+ "grad_norm": 5.972931385040283,
475
+ "learning_rate": 2.873684210526316e-06,
476
+ "loss": 0.5698,
477
+ "step": 36
478
+ },
479
+ {
480
+ "Batch Mean": -0.7627459764480591,
481
+ "accuracy": 0.7734375,
482
+ "epoch": 0.09,
483
+ "step": 36
484
+ },
485
+ {
486
+ "epoch": 0.0925,
487
+ "grad_norm": 7.165839672088623,
488
+ "learning_rate": 2.8657894736842103e-06,
489
+ "loss": 0.5157,
490
+ "step": 37
491
+ },
492
+ {
493
+ "Batch Mean": -0.6894429326057434,
494
+ "accuracy": 0.671875,
495
+ "epoch": 0.0925,
496
+ "step": 37
497
+ },
498
+ {
499
+ "epoch": 0.095,
500
+ "grad_norm": 6.630836009979248,
501
+ "learning_rate": 2.857894736842105e-06,
502
+ "loss": 0.5955,
503
+ "step": 38
504
+ },
505
+ {
506
+ "Batch Mean": -0.2740752696990967,
507
+ "accuracy": 0.734375,
508
+ "epoch": 0.095,
509
+ "step": 38
510
+ },
511
+ {
512
+ "epoch": 0.0975,
513
+ "grad_norm": 6.181252956390381,
514
+ "learning_rate": 2.85e-06,
515
+ "loss": 0.5037,
516
+ "step": 39
517
+ },
518
+ {
519
+ "Batch Mean": -0.09357815980911255,
520
+ "accuracy": 0.734375,
521
+ "epoch": 0.0975,
522
+ "step": 39
523
+ },
524
+ {
525
+ "epoch": 0.1,
526
+ "grad_norm": 6.351346969604492,
527
+ "learning_rate": 2.8421052631578946e-06,
528
+ "loss": 0.5152,
529
+ "step": 40
530
+ },
531
+ {
532
+ "Batch Mean": 0.33483320474624634,
533
+ "accuracy": 0.796875,
534
+ "epoch": 0.1,
535
+ "step": 40
536
+ },
537
+ {
538
+ "epoch": 0.1025,
539
+ "grad_norm": 6.3938117027282715,
540
+ "learning_rate": 2.8342105263157897e-06,
541
+ "loss": 0.4573,
542
+ "step": 41
543
+ },
544
+ {
545
+ "Batch Mean": 0.503718376159668,
546
+ "accuracy": 0.7578125,
547
+ "epoch": 0.1025,
548
+ "step": 41
549
+ },
550
+ {
551
+ "epoch": 0.105,
552
+ "grad_norm": 6.795258522033691,
553
+ "learning_rate": 2.8263157894736845e-06,
554
+ "loss": 0.4923,
555
+ "step": 42
556
+ },
557
+ {
558
+ "Batch Mean": 0.4224682152271271,
559
+ "accuracy": 0.6875,
560
+ "epoch": 0.105,
561
+ "step": 42
562
+ },
563
+ {
564
+ "epoch": 0.1075,
565
+ "grad_norm": 9.03122329711914,
566
+ "learning_rate": 2.8184210526315792e-06,
567
+ "loss": 0.5803,
568
+ "step": 43
569
+ },
570
+ {
571
+ "Batch Mean": 0.11721980571746826,
572
+ "accuracy": 0.8046875,
573
+ "epoch": 0.1075,
574
+ "step": 43
575
+ },
576
+ {
577
+ "epoch": 0.11,
578
+ "grad_norm": 6.323685646057129,
579
+ "learning_rate": 2.810526315789474e-06,
580
+ "loss": 0.4518,
581
+ "step": 44
582
+ },
583
+ {
584
+ "Batch Mean": 0.11213397979736328,
585
+ "accuracy": 0.7734375,
586
+ "epoch": 0.11,
587
+ "step": 44
588
+ },
589
+ {
590
+ "epoch": 0.1125,
591
+ "grad_norm": 6.636176586151123,
592
+ "learning_rate": 2.8026315789473687e-06,
593
+ "loss": 0.4747,
594
+ "step": 45
595
+ },
596
+ {
597
+ "Batch Mean": -0.19074296951293945,
598
+ "accuracy": 0.7421875,
599
+ "epoch": 0.1125,
600
+ "step": 45
601
+ },
602
+ {
603
+ "epoch": 0.115,
604
+ "grad_norm": 8.862186431884766,
605
+ "learning_rate": 2.7947368421052635e-06,
606
+ "loss": 0.5295,
607
+ "step": 46
608
+ },
609
+ {
610
+ "Batch Mean": -0.26628145575523376,
611
+ "accuracy": 0.7578125,
612
+ "epoch": 0.115,
613
+ "step": 46
614
+ },
615
+ {
616
+ "epoch": 0.1175,
617
+ "grad_norm": 9.089022636413574,
618
+ "learning_rate": 2.7868421052631578e-06,
619
+ "loss": 0.5132,
620
+ "step": 47
621
+ },
622
+ {
623
+ "Batch Mean": -0.11882030963897705,
624
+ "accuracy": 0.765625,
625
+ "epoch": 0.1175,
626
+ "step": 47
627
+ },
628
+ {
629
+ "epoch": 0.12,
630
+ "grad_norm": 8.50251293182373,
631
+ "learning_rate": 2.7789473684210525e-06,
632
+ "loss": 0.4904,
633
+ "step": 48
634
+ },
635
+ {
636
+ "Batch Mean": -0.09545481204986572,
637
+ "accuracy": 0.7890625,
638
+ "epoch": 0.12,
639
+ "step": 48
640
+ },
641
+ {
642
+ "epoch": 0.1225,
643
+ "grad_norm": 8.091400146484375,
644
+ "learning_rate": 2.7710526315789473e-06,
645
+ "loss": 0.4615,
646
+ "step": 49
647
+ },
648
+ {
649
+ "Batch Mean": -0.01603543758392334,
650
+ "accuracy": 0.6328125,
651
+ "epoch": 0.1225,
652
+ "step": 49
653
+ },
654
+ {
655
+ "epoch": 0.125,
656
+ "grad_norm": 11.12177562713623,
657
+ "learning_rate": 2.763157894736842e-06,
658
+ "loss": 0.6245,
659
+ "step": 50
660
+ },
661
+ {
662
+ "Batch Mean": -0.03519377112388611,
663
+ "accuracy": 0.6953125,
664
+ "epoch": 0.125,
665
+ "step": 50
666
+ },
667
+ {
668
+ "epoch": 0.1275,
669
+ "grad_norm": 8.476814270019531,
670
+ "learning_rate": 2.7552631578947368e-06,
671
+ "loss": 0.5094,
672
+ "step": 51
673
+ },
674
+ {
675
+ "Batch Mean": -0.07445716857910156,
676
+ "accuracy": 0.765625,
677
+ "epoch": 0.1275,
678
+ "step": 51
679
+ },
680
+ {
681
+ "epoch": 0.13,
682
+ "grad_norm": 8.475494384765625,
683
+ "learning_rate": 2.7473684210526315e-06,
684
+ "loss": 0.464,
685
+ "step": 52
686
+ },
687
+ {
688
+ "Batch Mean": -0.08127522468566895,
689
+ "accuracy": 0.7890625,
690
+ "epoch": 0.13,
691
+ "step": 52
692
+ },
693
+ {
694
+ "epoch": 0.1325,
695
+ "grad_norm": 7.754316806793213,
696
+ "learning_rate": 2.7394736842105263e-06,
697
+ "loss": 0.4618,
698
+ "step": 53
699
+ },
700
+ {
701
+ "Batch Mean": 0.05236625671386719,
702
+ "accuracy": 0.75,
703
+ "epoch": 0.1325,
704
+ "step": 53
705
+ },
706
+ {
707
+ "epoch": 0.135,
708
+ "grad_norm": 7.3552751541137695,
709
+ "learning_rate": 2.7315789473684214e-06,
710
+ "loss": 0.5202,
711
+ "step": 54
712
+ },
713
+ {
714
+ "Batch Mean": -0.08030200004577637,
715
+ "accuracy": 0.765625,
716
+ "epoch": 0.135,
717
+ "step": 54
718
+ },
719
+ {
720
+ "epoch": 0.1375,
721
+ "grad_norm": 8.413111686706543,
722
+ "learning_rate": 2.723684210526316e-06,
723
+ "loss": 0.4902,
724
+ "step": 55
725
+ },
726
+ {
727
+ "Batch Mean": 0.20010590553283691,
728
+ "accuracy": 0.765625,
729
+ "epoch": 0.1375,
730
+ "step": 55
731
+ },
732
+ {
733
+ "epoch": 0.14,
734
+ "grad_norm": 9.49488353729248,
735
+ "learning_rate": 2.715789473684211e-06,
736
+ "loss": 0.4945,
737
+ "step": 56
738
+ },
739
+ {
740
+ "Batch Mean": 0.1068873256444931,
741
+ "accuracy": 0.765625,
742
+ "epoch": 0.14,
743
+ "step": 56
744
+ },
745
+ {
746
+ "epoch": 0.1425,
747
+ "grad_norm": 9.978996276855469,
748
+ "learning_rate": 2.7078947368421052e-06,
749
+ "loss": 0.5936,
750
+ "step": 57
751
+ },
752
+ {
753
+ "Batch Mean": 0.12400929629802704,
754
+ "accuracy": 0.8046875,
755
+ "epoch": 0.1425,
756
+ "step": 57
757
+ },
758
+ {
759
+ "epoch": 0.145,
760
+ "grad_norm": 8.332430839538574,
761
+ "learning_rate": 2.7e-06,
762
+ "loss": 0.4549,
763
+ "step": 58
764
+ },
765
+ {
766
+ "Batch Mean": 0.05874582380056381,
767
+ "accuracy": 0.8125,
768
+ "epoch": 0.145,
769
+ "step": 58
770
+ },
771
+ {
772
+ "epoch": 0.1475,
773
+ "grad_norm": 7.287342548370361,
774
+ "learning_rate": 2.6921052631578947e-06,
775
+ "loss": 0.3996,
776
+ "step": 59
777
+ },
778
+ {
779
+ "Batch Mean": 0.17911481857299805,
780
+ "accuracy": 0.828125,
781
+ "epoch": 0.1475,
782
+ "step": 59
783
+ },
784
+ {
785
+ "epoch": 0.15,
786
+ "grad_norm": 7.197307109832764,
787
+ "learning_rate": 2.6842105263157895e-06,
788
+ "loss": 0.4486,
789
+ "step": 60
790
+ },
791
+ {
792
+ "Batch Mean": -0.0680088996887207,
793
+ "accuracy": 0.7265625,
794
+ "epoch": 0.15,
795
+ "step": 60
796
+ },
797
+ {
798
+ "epoch": 0.1525,
799
+ "grad_norm": 8.422717094421387,
800
+ "learning_rate": 2.6763157894736842e-06,
801
+ "loss": 0.5283,
802
+ "step": 61
803
+ },
804
+ {
805
+ "Batch Mean": -0.1332111358642578,
806
+ "accuracy": 0.7890625,
807
+ "epoch": 0.1525,
808
+ "step": 61
809
+ },
810
+ {
811
+ "epoch": 0.155,
812
+ "grad_norm": 8.836848258972168,
813
+ "learning_rate": 2.668421052631579e-06,
814
+ "loss": 0.4547,
815
+ "step": 62
816
+ },
817
+ {
818
+ "Batch Mean": -0.005272388458251953,
819
+ "accuracy": 0.734375,
820
+ "epoch": 0.155,
821
+ "step": 62
822
+ },
823
+ {
824
+ "epoch": 0.1575,
825
+ "grad_norm": 7.995077133178711,
826
+ "learning_rate": 2.6605263157894737e-06,
827
+ "loss": 0.5227,
828
+ "step": 63
829
+ },
830
+ {
831
+ "Batch Mean": 0.3416769504547119,
832
+ "accuracy": 0.8359375,
833
+ "epoch": 0.1575,
834
+ "step": 63
835
+ },
836
+ {
837
+ "epoch": 0.16,
838
+ "grad_norm": 8.131783485412598,
839
+ "learning_rate": 2.6526315789473685e-06,
840
+ "loss": 0.4191,
841
+ "step": 64
842
+ },
843
+ {
844
+ "Batch Mean": 0.2797560691833496,
845
+ "accuracy": 0.765625,
846
+ "epoch": 0.16,
847
+ "step": 64
848
+ },
849
+ {
850
+ "epoch": 0.1625,
851
+ "grad_norm": 9.04648208618164,
852
+ "learning_rate": 2.644736842105263e-06,
853
+ "loss": 0.4893,
854
+ "step": 65
855
+ },
856
+ {
857
+ "Batch Mean": -0.14584161341190338,
858
+ "accuracy": 0.7734375,
859
+ "epoch": 0.1625,
860
+ "step": 65
861
+ },
862
+ {
863
+ "epoch": 0.165,
864
+ "grad_norm": 8.039698600769043,
865
+ "learning_rate": 2.636842105263158e-06,
866
+ "loss": 0.4753,
867
+ "step": 66
868
+ },
869
+ {
870
+ "Batch Mean": -0.37075191736221313,
871
+ "accuracy": 0.7421875,
872
+ "epoch": 0.165,
873
+ "step": 66
874
+ },
875
+ {
876
+ "epoch": 0.1675,
877
+ "grad_norm": 7.643855094909668,
878
+ "learning_rate": 2.6289473684210527e-06,
879
+ "loss": 0.4424,
880
+ "step": 67
881
+ },
882
+ {
883
+ "Batch Mean": -0.24360448122024536,
884
+ "accuracy": 0.828125,
885
+ "epoch": 0.1675,
886
+ "step": 67
887
+ },
888
+ {
889
+ "epoch": 0.17,
890
+ "grad_norm": 6.892768383026123,
891
+ "learning_rate": 2.6210526315789474e-06,
892
+ "loss": 0.4126,
893
+ "step": 68
894
+ },
895
+ {
896
+ "Batch Mean": -0.0484846830368042,
897
+ "accuracy": 0.734375,
898
+ "epoch": 0.17,
899
+ "step": 68
900
+ },
901
+ {
902
+ "epoch": 0.1725,
903
+ "grad_norm": 10.497048377990723,
904
+ "learning_rate": 2.613157894736842e-06,
905
+ "loss": 0.5242,
906
+ "step": 69
907
+ },
908
+ {
909
+ "Batch Mean": 0.07249626517295837,
910
+ "accuracy": 0.8125,
911
+ "epoch": 0.1725,
912
+ "step": 69
913
+ },
914
+ {
915
+ "epoch": 0.175,
916
+ "grad_norm": 6.990925312042236,
917
+ "learning_rate": 2.605263157894737e-06,
918
+ "loss": 0.4206,
919
+ "step": 70
920
+ },
921
+ {
922
+ "Batch Mean": -0.06337249279022217,
923
+ "accuracy": 0.8125,
924
+ "epoch": 0.175,
925
+ "step": 70
926
+ },
927
+ {
928
+ "epoch": 0.1775,
929
+ "grad_norm": 7.180996417999268,
930
+ "learning_rate": 2.5973684210526317e-06,
931
+ "loss": 0.4412,
932
+ "step": 71
933
+ },
934
+ {
935
+ "Batch Mean": 0.06033170223236084,
936
+ "accuracy": 0.8515625,
937
+ "epoch": 0.1775,
938
+ "step": 71
939
+ },
940
+ {
941
+ "epoch": 0.18,
942
+ "grad_norm": 6.108893871307373,
943
+ "learning_rate": 2.5894736842105264e-06,
944
+ "loss": 0.3576,
945
+ "step": 72
946
+ },
947
+ {
948
+ "Batch Mean": -0.04290449619293213,
949
+ "accuracy": 0.765625,
950
+ "epoch": 0.18,
951
+ "step": 72
952
+ },
953
+ {
954
+ "epoch": 0.1825,
955
+ "grad_norm": 7.272516250610352,
956
+ "learning_rate": 2.581578947368421e-06,
957
+ "loss": 0.487,
958
+ "step": 73
959
+ },
960
+ {
961
+ "Batch Mean": 0.09309220314025879,
962
+ "accuracy": 0.796875,
963
+ "epoch": 0.1825,
964
+ "step": 73
965
+ },
966
+ {
967
+ "epoch": 0.185,
968
+ "grad_norm": 6.689022064208984,
969
+ "learning_rate": 2.573684210526316e-06,
970
+ "loss": 0.4576,
971
+ "step": 74
972
+ },
973
+ {
974
+ "Batch Mean": -0.3521728515625,
975
+ "accuracy": 0.8046875,
976
+ "epoch": 0.185,
977
+ "step": 74
978
+ },
979
+ {
980
+ "epoch": 0.1875,
981
+ "grad_norm": 7.446789264678955,
982
+ "learning_rate": 2.5657894736842107e-06,
983
+ "loss": 0.4537,
984
+ "step": 75
985
+ },
986
+ {
987
+ "Batch Mean": -0.1267460584640503,
988
+ "accuracy": 0.7265625,
989
+ "epoch": 0.1875,
990
+ "step": 75
991
+ },
992
+ {
993
+ "epoch": 0.19,
994
+ "grad_norm": 8.600646018981934,
995
+ "learning_rate": 2.5578947368421054e-06,
996
+ "loss": 0.5066,
997
+ "step": 76
998
+ },
999
+ {
1000
+ "Batch Mean": 0.02230433002114296,
1001
+ "accuracy": 0.7578125,
1002
+ "epoch": 0.19,
1003
+ "step": 76
1004
+ },
1005
+ {
1006
+ "epoch": 0.1925,
1007
+ "grad_norm": 8.842095375061035,
1008
+ "learning_rate": 2.55e-06,
1009
+ "loss": 0.4823,
1010
+ "step": 77
1011
+ },
1012
+ {
1013
+ "Batch Mean": 0.17012596130371094,
1014
+ "accuracy": 0.7890625,
1015
+ "epoch": 0.1925,
1016
+ "step": 77
1017
+ },
1018
+ {
1019
+ "epoch": 0.195,
1020
+ "grad_norm": 6.993001937866211,
1021
+ "learning_rate": 2.542105263157895e-06,
1022
+ "loss": 0.3959,
1023
+ "step": 78
1024
+ },
1025
+ {
1026
+ "Batch Mean": -0.11112558841705322,
1027
+ "accuracy": 0.78125,
1028
+ "epoch": 0.195,
1029
+ "step": 78
1030
+ },
1031
+ {
1032
+ "epoch": 0.1975,
1033
+ "grad_norm": 8.71827220916748,
1034
+ "learning_rate": 2.5342105263157892e-06,
1035
+ "loss": 0.4407,
1036
+ "step": 79
1037
+ },
1038
+ {
1039
+ "Batch Mean": 0.11298668384552002,
1040
+ "accuracy": 0.8515625,
1041
+ "epoch": 0.1975,
1042
+ "step": 79
1043
+ },
1044
+ {
1045
+ "epoch": 0.2,
1046
+ "grad_norm": 7.829047679901123,
1047
+ "learning_rate": 2.526315789473684e-06,
1048
+ "loss": 0.3905,
1049
+ "step": 80
1050
+ },
1051
+ {
1052
+ "Batch Mean": 0.010145187377929688,
1053
+ "accuracy": 0.78125,
1054
+ "epoch": 0.2,
1055
+ "step": 80
1056
+ },
1057
+ {
1058
+ "epoch": 0.2025,
1059
+ "grad_norm": 10.1448335647583,
1060
+ "learning_rate": 2.5184210526315787e-06,
1061
+ "loss": 0.4667,
1062
+ "step": 81
1063
+ },
1064
+ {
1065
+ "Batch Mean": 0.1327219009399414,
1066
+ "accuracy": 0.7890625,
1067
+ "epoch": 0.2025,
1068
+ "step": 81
1069
+ },
1070
+ {
1071
+ "epoch": 0.205,
1072
+ "grad_norm": 7.784322738647461,
1073
+ "learning_rate": 2.510526315789474e-06,
1074
+ "loss": 0.408,
1075
+ "step": 82
1076
+ },
1077
+ {
1078
+ "Batch Mean": 0.3474133014678955,
1079
+ "accuracy": 0.7421875,
1080
+ "epoch": 0.205,
1081
+ "step": 82
1082
+ },
1083
+ {
1084
+ "epoch": 0.2075,
1085
+ "grad_norm": 8.116996765136719,
1086
+ "learning_rate": 2.5026315789473686e-06,
1087
+ "loss": 0.438,
1088
+ "step": 83
1089
+ },
1090
+ {
1091
+ "Batch Mean": 0.2660253047943115,
1092
+ "accuracy": 0.75,
1093
+ "epoch": 0.2075,
1094
+ "step": 83
1095
+ },
1096
+ {
1097
+ "epoch": 0.21,
1098
+ "grad_norm": 7.8381452560424805,
1099
+ "learning_rate": 2.4947368421052634e-06,
1100
+ "loss": 0.4639,
1101
+ "step": 84
1102
+ },
1103
+ {
1104
+ "Batch Mean": 0.004191964864730835,
1105
+ "accuracy": 0.8125,
1106
+ "epoch": 0.21,
1107
+ "step": 84
1108
+ },
1109
+ {
1110
+ "epoch": 0.2125,
1111
+ "grad_norm": 6.7916412353515625,
1112
+ "learning_rate": 2.486842105263158e-06,
1113
+ "loss": 0.3937,
1114
+ "step": 85
1115
+ },
1116
+ {
1117
+ "Batch Mean": -0.4819910526275635,
1118
+ "accuracy": 0.75,
1119
+ "epoch": 0.2125,
1120
+ "step": 85
1121
+ },
1122
+ {
1123
+ "epoch": 0.215,
1124
+ "grad_norm": 8.073772430419922,
1125
+ "learning_rate": 2.478947368421053e-06,
1126
+ "loss": 0.4866,
1127
+ "step": 86
1128
+ },
1129
+ {
1130
+ "Batch Mean": -0.5541934967041016,
1131
+ "accuracy": 0.75,
1132
+ "epoch": 0.215,
1133
+ "step": 86
1134
+ },
1135
+ {
1136
+ "epoch": 0.2175,
1137
+ "grad_norm": 8.677484512329102,
1138
+ "learning_rate": 2.4710526315789476e-06,
1139
+ "loss": 0.503,
1140
+ "step": 87
1141
+ },
1142
+ {
1143
+ "Batch Mean": 0.14371705055236816,
1144
+ "accuracy": 0.7890625,
1145
+ "epoch": 0.2175,
1146
+ "step": 87
1147
+ },
1148
+ {
1149
+ "epoch": 0.22,
1150
+ "grad_norm": 7.931331634521484,
1151
+ "learning_rate": 2.4631578947368424e-06,
1152
+ "loss": 0.4483,
1153
+ "step": 88
1154
+ },
1155
+ {
1156
+ "Batch Mean": 0.013556957244873047,
1157
+ "accuracy": 0.859375,
1158
+ "epoch": 0.22,
1159
+ "step": 88
1160
+ },
1161
+ {
1162
+ "epoch": 0.2225,
1163
+ "grad_norm": 6.920699119567871,
1164
+ "learning_rate": 2.4552631578947367e-06,
1165
+ "loss": 0.3674,
1166
+ "step": 89
1167
+ },
1168
+ {
1169
+ "Batch Mean": -0.11897921562194824,
1170
+ "accuracy": 0.8203125,
1171
+ "epoch": 0.2225,
1172
+ "step": 89
1173
+ },
1174
+ {
1175
+ "epoch": 0.225,
1176
+ "grad_norm": 7.135400295257568,
1177
+ "learning_rate": 2.4473684210526314e-06,
1178
+ "loss": 0.3953,
1179
+ "step": 90
1180
+ },
1181
+ {
1182
+ "Batch Mean": 0.33566761016845703,
1183
+ "accuracy": 0.7890625,
1184
+ "epoch": 0.225,
1185
+ "step": 90
1186
+ },
1187
+ {
1188
+ "epoch": 0.2275,
1189
+ "grad_norm": 10.429315567016602,
1190
+ "learning_rate": 2.439473684210526e-06,
1191
+ "loss": 0.4943,
1192
+ "step": 91
1193
+ },
1194
+ {
1195
+ "Batch Mean": 0.4449765682220459,
1196
+ "accuracy": 0.84375,
1197
+ "epoch": 0.2275,
1198
+ "step": 91
1199
+ },
1200
+ {
1201
+ "epoch": 0.23,
1202
+ "grad_norm": 8.419116020202637,
1203
+ "learning_rate": 2.431578947368421e-06,
1204
+ "loss": 0.3647,
1205
+ "step": 92
1206
+ },
1207
+ {
1208
+ "Batch Mean": -0.06833112239837646,
1209
+ "accuracy": 0.8359375,
1210
+ "epoch": 0.23,
1211
+ "step": 92
1212
+ },
1213
+ {
1214
+ "epoch": 0.2325,
1215
+ "grad_norm": 7.288305282592773,
1216
+ "learning_rate": 2.4236842105263157e-06,
1217
+ "loss": 0.3719,
1218
+ "step": 93
1219
+ },
1220
+ {
1221
+ "Batch Mean": -0.36795759201049805,
1222
+ "accuracy": 0.8046875,
1223
+ "epoch": 0.2325,
1224
+ "step": 93
1225
+ },
1226
+ {
1227
+ "epoch": 0.235,
1228
+ "grad_norm": 8.255443572998047,
1229
+ "learning_rate": 2.4157894736842104e-06,
1230
+ "loss": 0.3983,
1231
+ "step": 94
1232
+ },
1233
+ {
1234
+ "Batch Mean": -0.3381902277469635,
1235
+ "accuracy": 0.8515625,
1236
+ "epoch": 0.235,
1237
+ "step": 94
1238
+ },
1239
+ {
1240
+ "epoch": 0.2375,
1241
+ "grad_norm": 8.25379467010498,
1242
+ "learning_rate": 2.4078947368421056e-06,
1243
+ "loss": 0.3602,
1244
+ "step": 95
1245
+ },
1246
+ {
1247
+ "Batch Mean": -0.2966504693031311,
1248
+ "accuracy": 0.75,
1249
+ "epoch": 0.2375,
1250
+ "step": 95
1251
+ },
1252
+ {
1253
+ "epoch": 0.24,
1254
+ "grad_norm": 9.554913520812988,
1255
+ "learning_rate": 2.4000000000000003e-06,
1256
+ "loss": 0.4499,
1257
+ "step": 96
1258
+ },
1259
+ {
1260
+ "Batch Mean": -0.02951526641845703,
1261
+ "accuracy": 0.796875,
1262
+ "epoch": 0.24,
1263
+ "step": 96
1264
+ },
1265
+ {
1266
+ "epoch": 0.2425,
1267
+ "grad_norm": 8.300037384033203,
1268
+ "learning_rate": 2.392105263157895e-06,
1269
+ "loss": 0.41,
1270
+ "step": 97
1271
+ },
1272
+ {
1273
+ "Batch Mean": 0.4994839131832123,
1274
+ "accuracy": 0.84375,
1275
+ "epoch": 0.2425,
1276
+ "step": 97
1277
+ },
1278
+ {
1279
+ "epoch": 0.245,
1280
+ "grad_norm": 9.282505989074707,
1281
+ "learning_rate": 2.38421052631579e-06,
1282
+ "loss": 0.3631,
1283
+ "step": 98
1284
+ },
1285
+ {
1286
+ "Batch Mean": 0.5059927701950073,
1287
+ "accuracy": 0.84375,
1288
+ "epoch": 0.245,
1289
+ "step": 98
1290
+ },
1291
+ {
1292
+ "epoch": 0.2475,
1293
+ "grad_norm": 10.97496509552002,
1294
+ "learning_rate": 2.376315789473684e-06,
1295
+ "loss": 0.4266,
1296
+ "step": 99
1297
+ },
1298
+ {
1299
+ "Batch Mean": 0.5012010335922241,
1300
+ "accuracy": 0.7890625,
1301
+ "epoch": 0.2475,
1302
+ "step": 99
1303
+ },
1304
+ {
1305
+ "epoch": 0.25,
1306
+ "grad_norm": 10.482470512390137,
1307
+ "learning_rate": 2.368421052631579e-06,
1308
+ "loss": 0.4402,
1309
+ "step": 100
1310
+ },
1311
+ {
1312
+ "Batch Mean": -0.34704887866973877,
1313
+ "accuracy": 0.7890625,
1314
+ "epoch": 0.25,
1315
+ "step": 100
1316
+ },
1317
+ {
1318
+ "epoch": 0.2525,
1319
+ "grad_norm": 10.026016235351562,
1320
+ "learning_rate": 2.3605263157894736e-06,
1321
+ "loss": 0.4576,
1322
+ "step": 101
1323
+ },
1324
+ {
1325
+ "Batch Mean": -0.5854883193969727,
1326
+ "accuracy": 0.7421875,
1327
+ "epoch": 0.2525,
1328
+ "step": 101
1329
+ },
1330
+ {
1331
+ "epoch": 0.255,
1332
+ "grad_norm": 11.113299369812012,
1333
+ "learning_rate": 2.3526315789473684e-06,
1334
+ "loss": 0.5302,
1335
+ "step": 102
1336
+ },
1337
+ {
1338
+ "Batch Mean": -0.6017556190490723,
1339
+ "accuracy": 0.8125,
1340
+ "epoch": 0.255,
1341
+ "step": 102
1342
+ },
1343
+ {
1344
+ "epoch": 0.2575,
1345
+ "grad_norm": 9.242813110351562,
1346
+ "learning_rate": 2.344736842105263e-06,
1347
+ "loss": 0.3451,
1348
+ "step": 103
1349
+ },
1350
+ {
1351
+ "Batch Mean": -0.14799189567565918,
1352
+ "accuracy": 0.78125,
1353
+ "epoch": 0.2575,
1354
+ "step": 103
1355
+ },
1356
+ {
1357
+ "epoch": 0.26,
1358
+ "grad_norm": 9.658228874206543,
1359
+ "learning_rate": 2.336842105263158e-06,
1360
+ "loss": 0.442,
1361
+ "step": 104
1362
+ },
1363
+ {
1364
+ "Batch Mean": 0.2693725824356079,
1365
+ "accuracy": 0.8203125,
1366
+ "epoch": 0.26,
1367
+ "step": 104
1368
+ },
1369
+ {
1370
+ "epoch": 0.2625,
1371
+ "grad_norm": 7.290228366851807,
1372
+ "learning_rate": 2.3289473684210526e-06,
1373
+ "loss": 0.3808,
1374
+ "step": 105
1375
+ },
1376
+ {
1377
+ "Batch Mean": 0.3339729309082031,
1378
+ "accuracy": 0.8828125,
1379
+ "epoch": 0.2625,
1380
+ "step": 105
1381
+ },
1382
+ {
1383
+ "epoch": 0.265,
1384
+ "grad_norm": 6.965331554412842,
1385
+ "learning_rate": 2.3210526315789473e-06,
1386
+ "loss": 0.326,
1387
+ "step": 106
1388
+ },
1389
+ {
1390
+ "Batch Mean": 0.03934955596923828,
1391
+ "accuracy": 0.765625,
1392
+ "epoch": 0.265,
1393
+ "step": 106
1394
+ },
1395
+ {
1396
+ "epoch": 0.2675,
1397
+ "grad_norm": 8.904206275939941,
1398
+ "learning_rate": 2.313157894736842e-06,
1399
+ "loss": 0.4804,
1400
+ "step": 107
1401
+ },
1402
+ {
1403
+ "Batch Mean": 0.48924458026885986,
1404
+ "accuracy": 0.7734375,
1405
+ "epoch": 0.2675,
1406
+ "step": 107
1407
+ },
1408
+ {
1409
+ "epoch": 0.27,
1410
+ "grad_norm": 11.731331825256348,
1411
+ "learning_rate": 2.305263157894737e-06,
1412
+ "loss": 0.4496,
1413
+ "step": 108
1414
+ },
1415
+ {
1416
+ "Batch Mean": 0.3033190965652466,
1417
+ "accuracy": 0.8671875,
1418
+ "epoch": 0.27,
1419
+ "step": 108
1420
+ },
1421
+ {
1422
+ "epoch": 0.2725,
1423
+ "grad_norm": 7.58432149887085,
1424
+ "learning_rate": 2.2973684210526316e-06,
1425
+ "loss": 0.3272,
1426
+ "step": 109
1427
+ },
1428
+ {
1429
+ "Batch Mean": 0.3258399963378906,
1430
+ "accuracy": 0.9296875,
1431
+ "epoch": 0.2725,
1432
+ "step": 109
1433
+ },
1434
+ {
1435
+ "epoch": 0.275,
1436
+ "grad_norm": 8.01420783996582,
1437
+ "learning_rate": 2.2894736842105263e-06,
1438
+ "loss": 0.2889,
1439
+ "step": 110
1440
+ },
1441
+ {
1442
+ "Batch Mean": -0.21785682439804077,
1443
+ "accuracy": 0.7734375,
1444
+ "epoch": 0.275,
1445
+ "step": 110
1446
+ },
1447
+ {
1448
+ "epoch": 0.2775,
1449
+ "grad_norm": 10.714860916137695,
1450
+ "learning_rate": 2.281578947368421e-06,
1451
+ "loss": 0.4938,
1452
+ "step": 111
1453
+ },
1454
+ {
1455
+ "Batch Mean": -0.23068951070308685,
1456
+ "accuracy": 0.7734375,
1457
+ "epoch": 0.2775,
1458
+ "step": 111
1459
+ },
1460
+ {
1461
+ "epoch": 0.28,
1462
+ "grad_norm": 9.543609619140625,
1463
+ "learning_rate": 2.273684210526316e-06,
1464
+ "loss": 0.4813,
1465
+ "step": 112
1466
+ },
1467
+ {
1468
+ "Batch Mean": -0.24743294715881348,
1469
+ "accuracy": 0.8515625,
1470
+ "epoch": 0.28,
1471
+ "step": 112
1472
+ },
1473
+ {
1474
+ "epoch": 0.2825,
1475
+ "grad_norm": 7.655090808868408,
1476
+ "learning_rate": 2.2657894736842106e-06,
1477
+ "loss": 0.3365,
1478
+ "step": 113
1479
+ },
1480
+ {
1481
+ "Batch Mean": -0.4790257215499878,
1482
+ "accuracy": 0.828125,
1483
+ "epoch": 0.2825,
1484
+ "step": 113
1485
+ },
1486
+ {
1487
+ "epoch": 0.285,
1488
+ "grad_norm": 9.270421028137207,
1489
+ "learning_rate": 2.2578947368421053e-06,
1490
+ "loss": 0.3654,
1491
+ "step": 114
1492
+ },
1493
+ {
1494
+ "Batch Mean": 0.39268895983695984,
1495
+ "accuracy": 0.7890625,
1496
+ "epoch": 0.285,
1497
+ "step": 114
1498
+ },
1499
+ {
1500
+ "epoch": 0.2875,
1501
+ "grad_norm": 10.442706108093262,
1502
+ "learning_rate": 2.25e-06,
1503
+ "loss": 0.4592,
1504
+ "step": 115
1505
+ },
1506
+ {
1507
+ "Batch Mean": 0.6092771291732788,
1508
+ "accuracy": 0.8515625,
1509
+ "epoch": 0.2875,
1510
+ "step": 115
1511
+ },
1512
+ {
1513
+ "epoch": 0.29,
1514
+ "grad_norm": 9.203109741210938,
1515
+ "learning_rate": 2.242105263157895e-06,
1516
+ "loss": 0.3579,
1517
+ "step": 116
1518
+ },
1519
+ {
1520
+ "Batch Mean": -0.1381063461303711,
1521
+ "accuracy": 0.7734375,
1522
+ "epoch": 0.29,
1523
+ "step": 116
1524
+ },
1525
+ {
1526
+ "epoch": 0.2925,
1527
+ "grad_norm": 11.316916465759277,
1528
+ "learning_rate": 2.2342105263157895e-06,
1529
+ "loss": 0.459,
1530
+ "step": 117
1531
+ },
1532
+ {
1533
+ "Batch Mean": -0.18764352798461914,
1534
+ "accuracy": 0.8125,
1535
+ "epoch": 0.2925,
1536
+ "step": 117
1537
+ },
1538
+ {
1539
+ "epoch": 0.295,
1540
+ "grad_norm": 9.715188026428223,
1541
+ "learning_rate": 2.2263157894736843e-06,
1542
+ "loss": 0.448,
1543
+ "step": 118
1544
+ },
1545
+ {
1546
+ "Batch Mean": -0.4390474557876587,
1547
+ "accuracy": 0.8359375,
1548
+ "epoch": 0.295,
1549
+ "step": 118
1550
+ },
1551
+ {
1552
+ "epoch": 0.2975,
1553
+ "grad_norm": 8.53513240814209,
1554
+ "learning_rate": 2.218421052631579e-06,
1555
+ "loss": 0.353,
1556
+ "step": 119
1557
+ },
1558
+ {
1559
+ "Batch Mean": -0.49342280626296997,
1560
+ "accuracy": 0.8203125,
1561
+ "epoch": 0.2975,
1562
+ "step": 119
1563
+ },
1564
+ {
1565
+ "epoch": 0.3,
1566
+ "grad_norm": 8.739898681640625,
1567
+ "learning_rate": 2.2105263157894738e-06,
1568
+ "loss": 0.3871,
1569
+ "step": 120
1570
+ },
1571
+ {
1572
+ "Batch Mean": -0.16289004683494568,
1573
+ "accuracy": 0.84375,
1574
+ "epoch": 0.3,
1575
+ "step": 120
1576
+ },
1577
+ {
1578
+ "epoch": 0.3025,
1579
+ "grad_norm": 8.066034317016602,
1580
+ "learning_rate": 2.2026315789473685e-06,
1581
+ "loss": 0.3778,
1582
+ "step": 121
1583
+ },
1584
+ {
1585
+ "Batch Mean": 0.11179280281066895,
1586
+ "accuracy": 0.8359375,
1587
+ "epoch": 0.3025,
1588
+ "step": 121
1589
+ },
1590
+ {
1591
+ "epoch": 0.305,
1592
+ "grad_norm": 8.85276985168457,
1593
+ "learning_rate": 2.1947368421052633e-06,
1594
+ "loss": 0.3953,
1595
+ "step": 122
1596
+ },
1597
+ {
1598
+ "Batch Mean": 0.6813234686851501,
1599
+ "accuracy": 0.828125,
1600
+ "epoch": 0.305,
1601
+ "step": 122
1602
+ },
1603
+ {
1604
+ "epoch": 0.3075,
1605
+ "grad_norm": 10.226161003112793,
1606
+ "learning_rate": 2.186842105263158e-06,
1607
+ "loss": 0.3787,
1608
+ "step": 123
1609
+ },
1610
+ {
1611
+ "Batch Mean": 0.08529806137084961,
1612
+ "accuracy": 0.8515625,
1613
+ "epoch": 0.3075,
1614
+ "step": 123
1615
+ },
1616
+ {
1617
+ "epoch": 0.31,
1618
+ "grad_norm": 9.13556957244873,
1619
+ "learning_rate": 2.1789473684210528e-06,
1620
+ "loss": 0.3313,
1621
+ "step": 124
1622
+ },
1623
+ {
1624
+ "Batch Mean": 0.24107074737548828,
1625
+ "accuracy": 0.7890625,
1626
+ "epoch": 0.31,
1627
+ "step": 124
1628
+ },
1629
+ {
1630
+ "epoch": 0.3125,
1631
+ "grad_norm": 12.641064643859863,
1632
+ "learning_rate": 2.1710526315789475e-06,
1633
+ "loss": 0.5176,
1634
+ "step": 125
1635
+ },
1636
+ {
1637
+ "Batch Mean": -0.1636943817138672,
1638
+ "accuracy": 0.7890625,
1639
+ "epoch": 0.3125,
1640
+ "step": 125
1641
+ },
1642
+ {
1643
+ "epoch": 0.315,
1644
+ "grad_norm": 9.701798439025879,
1645
+ "learning_rate": 2.1631578947368423e-06,
1646
+ "loss": 0.42,
1647
+ "step": 126
1648
+ },
1649
+ {
1650
+ "Batch Mean": -0.2857036590576172,
1651
+ "accuracy": 0.8515625,
1652
+ "epoch": 0.315,
1653
+ "step": 126
1654
+ },
1655
+ {
1656
+ "epoch": 0.3175,
1657
+ "grad_norm": 9.48480224609375,
1658
+ "learning_rate": 2.155263157894737e-06,
1659
+ "loss": 0.3539,
1660
+ "step": 127
1661
+ },
1662
+ {
1663
+ "Batch Mean": -0.7563860416412354,
1664
+ "accuracy": 0.765625,
1665
+ "epoch": 0.3175,
1666
+ "step": 127
1667
+ },
1668
+ {
1669
+ "epoch": 0.32,
1670
+ "grad_norm": 12.008138656616211,
1671
+ "learning_rate": 2.1473684210526317e-06,
1672
+ "loss": 0.4875,
1673
+ "step": 128
1674
+ },
1675
+ {
1676
+ "Batch Mean": 0.1351943016052246,
1677
+ "accuracy": 0.84375,
1678
+ "epoch": 0.32,
1679
+ "step": 128
1680
+ },
1681
+ {
1682
+ "epoch": 0.3225,
1683
+ "grad_norm": 8.202943801879883,
1684
+ "learning_rate": 2.1394736842105265e-06,
1685
+ "loss": 0.3432,
1686
+ "step": 129
1687
+ },
1688
+ {
1689
+ "Batch Mean": -0.002408236265182495,
1690
+ "accuracy": 0.8125,
1691
+ "epoch": 0.3225,
1692
+ "step": 129
1693
+ },
1694
+ {
1695
+ "epoch": 0.325,
1696
+ "grad_norm": 8.81209659576416,
1697
+ "learning_rate": 2.1315789473684212e-06,
1698
+ "loss": 0.418,
1699
+ "step": 130
1700
+ },
1701
+ {
1702
+ "Batch Mean": 0.00351560115814209,
1703
+ "accuracy": 0.7734375,
1704
+ "epoch": 0.325,
1705
+ "step": 130
1706
+ },
1707
+ {
1708
+ "epoch": 0.3275,
1709
+ "grad_norm": 9.197092056274414,
1710
+ "learning_rate": 2.123684210526316e-06,
1711
+ "loss": 0.4158,
1712
+ "step": 131
1713
+ },
1714
+ {
1715
+ "Batch Mean": 0.26228976249694824,
1716
+ "accuracy": 0.8515625,
1717
+ "epoch": 0.3275,
1718
+ "step": 131
1719
+ },
1720
+ {
1721
+ "epoch": 0.33,
1722
+ "grad_norm": 8.00036334991455,
1723
+ "learning_rate": 2.1157894736842103e-06,
1724
+ "loss": 0.3283,
1725
+ "step": 132
1726
+ },
1727
+ {
1728
+ "Batch Mean": 0.10788178443908691,
1729
+ "accuracy": 0.8125,
1730
+ "epoch": 0.33,
1731
+ "step": 132
1732
+ },
1733
+ {
1734
+ "epoch": 0.3325,
1735
+ "grad_norm": 7.9092116355896,
1736
+ "learning_rate": 2.107894736842105e-06,
1737
+ "loss": 0.3622,
1738
+ "step": 133
1739
+ },
1740
+ {
1741
+ "Batch Mean": 0.09739017486572266,
1742
+ "accuracy": 0.8515625,
1743
+ "epoch": 0.3325,
1744
+ "step": 133
1745
+ },
1746
+ {
1747
+ "epoch": 0.335,
1748
+ "grad_norm": 7.7380218505859375,
1749
+ "learning_rate": 2.1e-06,
1750
+ "loss": 0.3399,
1751
+ "step": 134
1752
+ },
1753
+ {
1754
+ "Batch Mean": -0.03578406572341919,
1755
+ "accuracy": 0.8203125,
1756
+ "epoch": 0.335,
1757
+ "step": 134
1758
+ },
1759
+ {
1760
+ "epoch": 0.3375,
1761
+ "grad_norm": 7.9607930183410645,
1762
+ "learning_rate": 2.0921052631578945e-06,
1763
+ "loss": 0.3681,
1764
+ "step": 135
1765
+ },
1766
+ {
1767
+ "Batch Mean": 0.2095022201538086,
1768
+ "accuracy": 0.7734375,
1769
+ "epoch": 0.3375,
1770
+ "step": 135
1771
+ },
1772
+ {
1773
+ "epoch": 0.34,
1774
+ "grad_norm": 9.16215705871582,
1775
+ "learning_rate": 2.0842105263157897e-06,
1776
+ "loss": 0.4474,
1777
+ "step": 136
1778
+ },
1779
+ {
1780
+ "Batch Mean": -0.12871003150939941,
1781
+ "accuracy": 0.78125,
1782
+ "epoch": 0.34,
1783
+ "step": 136
1784
+ },
1785
+ {
1786
+ "epoch": 0.3425,
1787
+ "grad_norm": 9.543075561523438,
1788
+ "learning_rate": 2.0763157894736845e-06,
1789
+ "loss": 0.4641,
1790
+ "step": 137
1791
+ },
1792
+ {
1793
+ "Batch Mean": -0.045391350984573364,
1794
+ "accuracy": 0.828125,
1795
+ "epoch": 0.3425,
1796
+ "step": 137
1797
+ },
1798
+ {
1799
+ "epoch": 0.345,
1800
+ "grad_norm": 8.620835304260254,
1801
+ "learning_rate": 2.068421052631579e-06,
1802
+ "loss": 0.388,
1803
+ "step": 138
1804
+ },
1805
+ {
1806
+ "Batch Mean": 0.023508906364440918,
1807
+ "accuracy": 0.7578125,
1808
+ "epoch": 0.345,
1809
+ "step": 138
1810
+ },
1811
+ {
1812
+ "epoch": 0.3475,
1813
+ "grad_norm": 10.10091781616211,
1814
+ "learning_rate": 2.060526315789474e-06,
1815
+ "loss": 0.4391,
1816
+ "step": 139
1817
+ },
1818
+ {
1819
+ "Batch Mean": -0.0003312826156616211,
1820
+ "accuracy": 0.8359375,
1821
+ "epoch": 0.3475,
1822
+ "step": 139
1823
+ },
1824
+ {
1825
+ "epoch": 0.35,
1826
+ "grad_norm": 8.200050354003906,
1827
+ "learning_rate": 2.0526315789473687e-06,
1828
+ "loss": 0.4196,
1829
+ "step": 140
1830
+ },
1831
+ {
1832
+ "Batch Mean": -0.304778516292572,
1833
+ "accuracy": 0.8359375,
1834
+ "epoch": 0.35,
1835
+ "step": 140
1836
+ },
1837
+ {
1838
+ "epoch": 0.3525,
1839
+ "grad_norm": 7.937561511993408,
1840
+ "learning_rate": 2.0447368421052634e-06,
1841
+ "loss": 0.3394,
1842
+ "step": 141
1843
+ },
1844
+ {
1845
+ "Batch Mean": -0.22019100189208984,
1846
+ "accuracy": 0.84375,
1847
+ "epoch": 0.3525,
1848
+ "step": 141
1849
+ },
1850
+ {
1851
+ "epoch": 0.355,
1852
+ "grad_norm": 8.111381530761719,
1853
+ "learning_rate": 2.0368421052631578e-06,
1854
+ "loss": 0.3878,
1855
+ "step": 142
1856
+ },
1857
+ {
1858
+ "Batch Mean": 0.4440329670906067,
1859
+ "accuracy": 0.8125,
1860
+ "epoch": 0.355,
1861
+ "step": 142
1862
+ },
1863
+ {
1864
+ "epoch": 0.3575,
1865
+ "grad_norm": 10.333617210388184,
1866
+ "learning_rate": 2.0289473684210525e-06,
1867
+ "loss": 0.4124,
1868
+ "step": 143
1869
+ },
1870
+ {
1871
+ "Batch Mean": 0.45398879051208496,
1872
+ "accuracy": 0.90625,
1873
+ "epoch": 0.3575,
1874
+ "step": 143
1875
+ },
1876
+ {
1877
+ "epoch": 0.36,
1878
+ "grad_norm": 7.195791721343994,
1879
+ "learning_rate": 2.0210526315789473e-06,
1880
+ "loss": 0.2869,
1881
+ "step": 144
1882
+ },
1883
+ {
1884
+ "Batch Mean": 0.13556790351867676,
1885
+ "accuracy": 0.8359375,
1886
+ "epoch": 0.36,
1887
+ "step": 144
1888
+ },
1889
+ {
1890
+ "epoch": 0.3625,
1891
+ "grad_norm": 8.249251365661621,
1892
+ "learning_rate": 2.013157894736842e-06,
1893
+ "loss": 0.3767,
1894
+ "step": 145
1895
+ },
1896
+ {
1897
+ "Batch Mean": 0.03792291879653931,
1898
+ "accuracy": 0.828125,
1899
+ "epoch": 0.3625,
1900
+ "step": 145
1901
+ },
1902
+ {
1903
+ "epoch": 0.365,
1904
+ "grad_norm": 10.333145141601562,
1905
+ "learning_rate": 2.0052631578947367e-06,
1906
+ "loss": 0.3784,
1907
+ "step": 146
1908
+ },
1909
+ {
1910
+ "Batch Mean": 0.05816793441772461,
1911
+ "accuracy": 0.828125,
1912
+ "epoch": 0.365,
1913
+ "step": 146
1914
+ },
1915
+ {
1916
+ "epoch": 0.3675,
1917
+ "grad_norm": 9.091706275939941,
1918
+ "learning_rate": 1.9973684210526315e-06,
1919
+ "loss": 0.4217,
1920
+ "step": 147
1921
+ },
1922
+ {
1923
+ "Batch Mean": 0.016840219497680664,
1924
+ "accuracy": 0.765625,
1925
+ "epoch": 0.3675,
1926
+ "step": 147
1927
+ },
1928
+ {
1929
+ "epoch": 0.37,
1930
+ "grad_norm": 12.988033294677734,
1931
+ "learning_rate": 1.9894736842105262e-06,
1932
+ "loss": 0.537,
1933
+ "step": 148
1934
+ },
1935
+ {
1936
+ "Batch Mean": -0.6307969093322754,
1937
+ "accuracy": 0.8671875,
1938
+ "epoch": 0.37,
1939
+ "step": 148
1940
+ },
1941
+ {
1942
+ "epoch": 0.3725,
1943
+ "grad_norm": 8.663951873779297,
1944
+ "learning_rate": 1.9815789473684214e-06,
1945
+ "loss": 0.2973,
1946
+ "step": 149
1947
+ },
1948
+ {
1949
+ "Batch Mean": -0.41460466384887695,
1950
+ "accuracy": 0.8359375,
1951
+ "epoch": 0.3725,
1952
+ "step": 149
1953
+ },
1954
+ {
1955
+ "epoch": 0.375,
1956
+ "grad_norm": 8.891082763671875,
1957
+ "learning_rate": 1.973684210526316e-06,
1958
+ "loss": 0.3553,
1959
+ "step": 150
1960
+ },
1961
+ {
1962
+ "Batch Mean": 0.045943260192871094,
1963
+ "accuracy": 0.859375,
1964
+ "epoch": 0.375,
1965
+ "step": 150
1966
+ },
1967
+ {
1968
+ "epoch": 0.3775,
1969
+ "grad_norm": 8.152697563171387,
1970
+ "learning_rate": 1.965789473684211e-06,
1971
+ "loss": 0.3515,
1972
+ "step": 151
1973
+ },
1974
+ {
1975
+ "Batch Mean": -0.18106698989868164,
1976
+ "accuracy": 0.796875,
1977
+ "epoch": 0.3775,
1978
+ "step": 151
1979
+ },
1980
+ {
1981
+ "epoch": 0.38,
1982
+ "grad_norm": 10.632974624633789,
1983
+ "learning_rate": 1.9578947368421052e-06,
1984
+ "loss": 0.4978,
1985
+ "step": 152
1986
+ },
1987
+ {
1988
+ "Batch Mean": 0.1395092010498047,
1989
+ "accuracy": 0.859375,
1990
+ "epoch": 0.38,
1991
+ "step": 152
1992
+ },
1993
+ {
1994
+ "epoch": 0.3825,
1995
+ "grad_norm": 8.301017761230469,
1996
+ "learning_rate": 1.95e-06,
1997
+ "loss": 0.3268,
1998
+ "step": 153
1999
+ },
2000
+ {
2001
+ "Batch Mean": 0.011521339416503906,
2002
+ "accuracy": 0.8046875,
2003
+ "epoch": 0.3825,
2004
+ "step": 153
2005
+ },
2006
+ {
2007
+ "epoch": 0.385,
2008
+ "grad_norm": 8.253169059753418,
2009
+ "learning_rate": 1.9421052631578947e-06,
2010
+ "loss": 0.3407,
2011
+ "step": 154
2012
+ },
2013
+ {
2014
+ "Batch Mean": -0.11399388313293457,
2015
+ "accuracy": 0.8515625,
2016
+ "epoch": 0.385,
2017
+ "step": 154
2018
+ },
2019
+ {
2020
+ "epoch": 0.3875,
2021
+ "grad_norm": 9.271583557128906,
2022
+ "learning_rate": 1.9342105263157895e-06,
2023
+ "loss": 0.3919,
2024
+ "step": 155
2025
+ },
2026
+ {
2027
+ "Batch Mean": 0.3950004577636719,
2028
+ "accuracy": 0.7890625,
2029
+ "epoch": 0.3875,
2030
+ "step": 155
2031
+ },
2032
+ {
2033
+ "epoch": 0.39,
2034
+ "grad_norm": 10.932522773742676,
2035
+ "learning_rate": 1.926315789473684e-06,
2036
+ "loss": 0.4111,
2037
+ "step": 156
2038
+ },
2039
+ {
2040
+ "Batch Mean": 0.24418425559997559,
2041
+ "accuracy": 0.8125,
2042
+ "epoch": 0.39,
2043
+ "step": 156
2044
+ },
2045
+ {
2046
+ "epoch": 0.3925,
2047
+ "grad_norm": 9.256501197814941,
2048
+ "learning_rate": 1.918421052631579e-06,
2049
+ "loss": 0.4292,
2050
+ "step": 157
2051
+ },
2052
+ {
2053
+ "Batch Mean": -0.1265101432800293,
2054
+ "accuracy": 0.8125,
2055
+ "epoch": 0.3925,
2056
+ "step": 157
2057
+ },
2058
+ {
2059
+ "epoch": 0.395,
2060
+ "grad_norm": 8.907751083374023,
2061
+ "learning_rate": 1.9105263157894737e-06,
2062
+ "loss": 0.3853,
2063
+ "step": 158
2064
+ },
2065
+ {
2066
+ "Batch Mean": -0.35911059379577637,
2067
+ "accuracy": 0.828125,
2068
+ "epoch": 0.395,
2069
+ "step": 158
2070
+ },
2071
+ {
2072
+ "epoch": 0.3975,
2073
+ "grad_norm": 9.353957176208496,
2074
+ "learning_rate": 1.9026315789473684e-06,
2075
+ "loss": 0.4177,
2076
+ "step": 159
2077
+ },
2078
+ {
2079
+ "Batch Mean": -0.49236249923706055,
2080
+ "accuracy": 0.828125,
2081
+ "epoch": 0.3975,
2082
+ "step": 159
2083
+ },
2084
+ {
2085
+ "epoch": 0.4,
2086
+ "grad_norm": 8.749178886413574,
2087
+ "learning_rate": 1.8947368421052632e-06,
2088
+ "loss": 0.3711,
2089
+ "step": 160
2090
+ },
2091
+ {
2092
+ "Batch Mean": 0.1534252166748047,
2093
+ "accuracy": 0.8671875,
2094
+ "epoch": 0.4,
2095
+ "step": 160
2096
+ },
2097
+ {
2098
+ "epoch": 0.4025,
2099
+ "grad_norm": 8.529258728027344,
2100
+ "learning_rate": 1.8868421052631577e-06,
2101
+ "loss": 0.3523,
2102
+ "step": 161
2103
+ },
2104
+ {
2105
+ "Batch Mean": 0.11423969268798828,
2106
+ "accuracy": 0.8125,
2107
+ "epoch": 0.4025,
2108
+ "step": 161
2109
+ },
2110
+ {
2111
+ "epoch": 0.405,
2112
+ "grad_norm": 8.786529541015625,
2113
+ "learning_rate": 1.8789473684210525e-06,
2114
+ "loss": 0.3942,
2115
+ "step": 162
2116
+ },
2117
+ {
2118
+ "Batch Mean": 0.15482479333877563,
2119
+ "accuracy": 0.828125,
2120
+ "epoch": 0.405,
2121
+ "step": 162
2122
+ },
2123
+ {
2124
+ "epoch": 0.4075,
2125
+ "grad_norm": 8.650775909423828,
2126
+ "learning_rate": 1.8710526315789476e-06,
2127
+ "loss": 0.3971,
2128
+ "step": 163
2129
+ },
2130
+ {
2131
+ "Batch Mean": 0.19225120544433594,
2132
+ "accuracy": 0.859375,
2133
+ "epoch": 0.4075,
2134
+ "step": 163
2135
+ },
2136
+ {
2137
+ "epoch": 0.41,
2138
+ "grad_norm": 7.860261917114258,
2139
+ "learning_rate": 1.8631578947368424e-06,
2140
+ "loss": 0.3098,
2141
+ "step": 164
2142
+ },
2143
+ {
2144
+ "Batch Mean": 0.570763111114502,
2145
+ "accuracy": 0.828125,
2146
+ "epoch": 0.41,
2147
+ "step": 164
2148
+ },
2149
+ {
2150
+ "epoch": 0.4125,
2151
+ "grad_norm": 9.458237648010254,
2152
+ "learning_rate": 1.855263157894737e-06,
2153
+ "loss": 0.4007,
2154
+ "step": 165
2155
+ },
2156
+ {
2157
+ "Batch Mean": 0.1940155029296875,
2158
+ "accuracy": 0.796875,
2159
+ "epoch": 0.4125,
2160
+ "step": 165
2161
+ },
2162
+ {
2163
+ "epoch": 0.415,
2164
+ "grad_norm": 8.419119834899902,
2165
+ "learning_rate": 1.8473684210526317e-06,
2166
+ "loss": 0.3679,
2167
+ "step": 166
2168
+ },
2169
+ {
2170
+ "Batch Mean": 0.13667702674865723,
2171
+ "accuracy": 0.8125,
2172
+ "epoch": 0.415,
2173
+ "step": 166
2174
+ },
2175
+ {
2176
+ "epoch": 0.4175,
2177
+ "grad_norm": 11.180956840515137,
2178
+ "learning_rate": 1.8394736842105264e-06,
2179
+ "loss": 0.4043,
2180
+ "step": 167
2181
+ },
2182
+ {
2183
+ "Batch Mean": -0.47870922088623047,
2184
+ "accuracy": 0.796875,
2185
+ "epoch": 0.4175,
2186
+ "step": 167
2187
+ },
2188
+ {
2189
+ "epoch": 0.42,
2190
+ "grad_norm": 11.080053329467773,
2191
+ "learning_rate": 1.8315789473684211e-06,
2192
+ "loss": 0.4806,
2193
+ "step": 168
2194
+ },
2195
+ {
2196
+ "Batch Mean": -0.07008326053619385,
2197
+ "accuracy": 0.8125,
2198
+ "epoch": 0.42,
2199
+ "step": 168
2200
+ },
2201
+ {
2202
+ "epoch": 0.4225,
2203
+ "grad_norm": 9.977706909179688,
2204
+ "learning_rate": 1.8236842105263159e-06,
2205
+ "loss": 0.3711,
2206
+ "step": 169
2207
+ },
2208
+ {
2209
+ "Batch Mean": -0.21228408813476562,
2210
+ "accuracy": 0.78125,
2211
+ "epoch": 0.4225,
2212
+ "step": 169
2213
+ },
2214
+ {
2215
+ "epoch": 0.425,
2216
+ "grad_norm": 9.771838188171387,
2217
+ "learning_rate": 1.8157894736842106e-06,
2218
+ "loss": 0.4154,
2219
+ "step": 170
2220
+ },
2221
+ {
2222
+ "Batch Mean": -0.014397621154785156,
2223
+ "accuracy": 0.8671875,
2224
+ "epoch": 0.425,
2225
+ "step": 170
2226
+ },
2227
+ {
2228
+ "epoch": 0.4275,
2229
+ "grad_norm": 7.314267158508301,
2230
+ "learning_rate": 1.8078947368421052e-06,
2231
+ "loss": 0.2636,
2232
+ "step": 171
2233
+ },
2234
+ {
2235
+ "Batch Mean": 0.3306160569190979,
2236
+ "accuracy": 0.828125,
2237
+ "epoch": 0.4275,
2238
+ "step": 171
2239
+ },
2240
+ {
2241
+ "epoch": 0.43,
2242
+ "grad_norm": 8.739150047302246,
2243
+ "learning_rate": 1.8e-06,
2244
+ "loss": 0.3611,
2245
+ "step": 172
2246
+ },
2247
+ {
2248
+ "Batch Mean": -0.0874967873096466,
2249
+ "accuracy": 0.7890625,
2250
+ "epoch": 0.43,
2251
+ "step": 172
2252
+ },
2253
+ {
2254
+ "epoch": 0.4325,
2255
+ "grad_norm": 9.247507095336914,
2256
+ "learning_rate": 1.7921052631578947e-06,
2257
+ "loss": 0.4175,
2258
+ "step": 173
2259
+ },
2260
+ {
2261
+ "Batch Mean": 0.2975928783416748,
2262
+ "accuracy": 0.84375,
2263
+ "epoch": 0.4325,
2264
+ "step": 173
2265
+ },
2266
+ {
2267
+ "epoch": 0.435,
2268
+ "grad_norm": 9.041180610656738,
2269
+ "learning_rate": 1.7842105263157894e-06,
2270
+ "loss": 0.3671,
2271
+ "step": 174
2272
+ },
2273
+ {
2274
+ "Batch Mean": 0.015955865383148193,
2275
+ "accuracy": 0.7421875,
2276
+ "epoch": 0.435,
2277
+ "step": 174
2278
+ },
2279
+ {
2280
+ "epoch": 0.4375,
2281
+ "grad_norm": 11.472379684448242,
2282
+ "learning_rate": 1.7763157894736842e-06,
2283
+ "loss": 0.4833,
2284
+ "step": 175
2285
+ },
2286
+ {
2287
+ "Batch Mean": -0.36949777603149414,
2288
+ "accuracy": 0.7421875,
2289
+ "epoch": 0.4375,
2290
+ "step": 175
2291
+ },
2292
+ {
2293
+ "epoch": 0.44,
2294
+ "grad_norm": 11.286201477050781,
2295
+ "learning_rate": 1.768421052631579e-06,
2296
+ "loss": 0.4855,
2297
+ "step": 176
2298
+ },
2299
+ {
2300
+ "Batch Mean": -0.3930339813232422,
2301
+ "accuracy": 0.828125,
2302
+ "epoch": 0.44,
2303
+ "step": 176
2304
+ },
2305
+ {
2306
+ "epoch": 0.4425,
2307
+ "grad_norm": 10.522198677062988,
2308
+ "learning_rate": 1.7605263157894739e-06,
2309
+ "loss": 0.3819,
2310
+ "step": 177
2311
+ },
2312
+ {
2313
+ "Batch Mean": 0.08716198801994324,
2314
+ "accuracy": 0.828125,
2315
+ "epoch": 0.4425,
2316
+ "step": 177
2317
+ },
2318
+ {
2319
+ "epoch": 0.445,
2320
+ "grad_norm": 9.067276000976562,
2321
+ "learning_rate": 1.7526315789473686e-06,
2322
+ "loss": 0.3921,
2323
+ "step": 178
2324
+ },
2325
+ {
2326
+ "Batch Mean": -0.25193285942077637,
2327
+ "accuracy": 0.8203125,
2328
+ "epoch": 0.445,
2329
+ "step": 178
2330
+ },
2331
+ {
2332
+ "epoch": 0.4475,
2333
+ "grad_norm": 9.11840534210205,
2334
+ "learning_rate": 1.7447368421052633e-06,
2335
+ "loss": 0.4172,
2336
+ "step": 179
2337
+ },
2338
+ {
2339
+ "Batch Mean": -0.23209238052368164,
2340
+ "accuracy": 0.8203125,
2341
+ "epoch": 0.4475,
2342
+ "step": 179
2343
+ },
2344
+ {
2345
+ "epoch": 0.45,
2346
+ "grad_norm": 11.945143699645996,
2347
+ "learning_rate": 1.736842105263158e-06,
2348
+ "loss": 0.3795,
2349
+ "step": 180
2350
+ },
2351
+ {
2352
+ "Batch Mean": -0.21220535039901733,
2353
+ "accuracy": 0.8984375,
2354
+ "epoch": 0.45,
2355
+ "step": 180
2356
+ },
2357
+ {
2358
+ "epoch": 0.4525,
2359
+ "grad_norm": 8.286118507385254,
2360
+ "learning_rate": 1.7289473684210526e-06,
2361
+ "loss": 0.2964,
2362
+ "step": 181
2363
+ },
2364
+ {
2365
+ "Batch Mean": 0.15385687351226807,
2366
+ "accuracy": 0.8203125,
2367
+ "epoch": 0.4525,
2368
+ "step": 181
2369
+ },
2370
+ {
2371
+ "epoch": 0.455,
2372
+ "grad_norm": 8.66666316986084,
2373
+ "learning_rate": 1.7210526315789474e-06,
2374
+ "loss": 0.3717,
2375
+ "step": 182
2376
+ },
2377
+ {
2378
+ "Batch Mean": 0.47098982334136963,
2379
+ "accuracy": 0.8125,
2380
+ "epoch": 0.455,
2381
+ "step": 182
2382
+ },
2383
+ {
2384
+ "epoch": 0.4575,
2385
+ "grad_norm": 9.041359901428223,
2386
+ "learning_rate": 1.7131578947368421e-06,
2387
+ "loss": 0.3627,
2388
+ "step": 183
2389
+ },
2390
+ {
2391
+ "Batch Mean": 0.2258845567703247,
2392
+ "accuracy": 0.8359375,
2393
+ "epoch": 0.4575,
2394
+ "step": 183
2395
+ },
2396
+ {
2397
+ "epoch": 0.46,
2398
+ "grad_norm": 10.031190872192383,
2399
+ "learning_rate": 1.7052631578947369e-06,
2400
+ "loss": 0.4308,
2401
+ "step": 184
2402
+ },
2403
+ {
2404
+ "Batch Mean": 0.1376625895500183,
2405
+ "accuracy": 0.7890625,
2406
+ "epoch": 0.46,
2407
+ "step": 184
2408
+ },
2409
+ {
2410
+ "epoch": 0.4625,
2411
+ "grad_norm": 8.849730491638184,
2412
+ "learning_rate": 1.6973684210526316e-06,
2413
+ "loss": 0.3612,
2414
+ "step": 185
2415
+ },
2416
+ {
2417
+ "Batch Mean": -0.25082847476005554,
2418
+ "accuracy": 0.8359375,
2419
+ "epoch": 0.4625,
2420
+ "step": 185
2421
+ },
2422
+ {
2423
+ "epoch": 0.465,
2424
+ "grad_norm": 9.715136528015137,
2425
+ "learning_rate": 1.6894736842105264e-06,
2426
+ "loss": 0.4192,
2427
+ "step": 186
2428
+ },
2429
+ {
2430
+ "Batch Mean": -0.43356090784072876,
2431
+ "accuracy": 0.859375,
2432
+ "epoch": 0.465,
2433
+ "step": 186
2434
+ },
2435
+ {
2436
+ "epoch": 0.4675,
2437
+ "grad_norm": 8.193946838378906,
2438
+ "learning_rate": 1.6815789473684209e-06,
2439
+ "loss": 0.3504,
2440
+ "step": 187
2441
+ },
2442
+ {
2443
+ "Batch Mean": -0.013092756271362305,
2444
+ "accuracy": 0.875,
2445
+ "epoch": 0.4675,
2446
+ "step": 187
2447
+ },
2448
+ {
2449
+ "epoch": 0.47,
2450
+ "grad_norm": 8.71420955657959,
2451
+ "learning_rate": 1.6736842105263156e-06,
2452
+ "loss": 0.3437,
2453
+ "step": 188
2454
+ },
2455
+ {
2456
+ "Batch Mean": 0.13508832454681396,
2457
+ "accuracy": 0.78125,
2458
+ "epoch": 0.47,
2459
+ "step": 188
2460
+ },
2461
+ {
2462
+ "epoch": 0.4725,
2463
+ "grad_norm": 10.5387544631958,
2464
+ "learning_rate": 1.6657894736842104e-06,
2465
+ "loss": 0.4141,
2466
+ "step": 189
2467
+ },
2468
+ {
2469
+ "Batch Mean": 0.12293338775634766,
2470
+ "accuracy": 0.84375,
2471
+ "epoch": 0.4725,
2472
+ "step": 189
2473
+ },
2474
+ {
2475
+ "epoch": 0.475,
2476
+ "grad_norm": 8.671295166015625,
2477
+ "learning_rate": 1.6578947368421056e-06,
2478
+ "loss": 0.3752,
2479
+ "step": 190
2480
+ },
2481
+ {
2482
+ "Batch Mean": 0.47929099202156067,
2483
+ "accuracy": 0.8203125,
2484
+ "epoch": 0.475,
2485
+ "step": 190
2486
+ },
2487
+ {
2488
+ "epoch": 0.4775,
2489
+ "grad_norm": 11.653754234313965,
2490
+ "learning_rate": 1.65e-06,
2491
+ "loss": 0.4854,
2492
+ "step": 191
2493
+ },
2494
+ {
2495
+ "Batch Mean": 0.49117136001586914,
2496
+ "accuracy": 0.84375,
2497
+ "epoch": 0.4775,
2498
+ "step": 191
2499
+ },
2500
+ {
2501
+ "epoch": 0.48,
2502
+ "grad_norm": 8.04267406463623,
2503
+ "learning_rate": 1.6421052631578948e-06,
2504
+ "loss": 0.3098,
2505
+ "step": 192
2506
+ },
2507
+ {
2508
+ "Batch Mean": 0.5062227249145508,
2509
+ "accuracy": 0.8828125,
2510
+ "epoch": 0.48,
2511
+ "step": 192
2512
+ },
2513
+ {
2514
+ "epoch": 0.4825,
2515
+ "grad_norm": 8.732284545898438,
2516
+ "learning_rate": 1.6342105263157896e-06,
2517
+ "loss": 0.3193,
2518
+ "step": 193
2519
+ },
2520
+ {
2521
+ "Batch Mean": -0.3749980926513672,
2522
+ "accuracy": 0.859375,
2523
+ "epoch": 0.4825,
2524
+ "step": 193
2525
+ },
2526
+ {
2527
+ "epoch": 0.485,
2528
+ "grad_norm": 8.27978515625,
2529
+ "learning_rate": 1.6263157894736843e-06,
2530
+ "loss": 0.337,
2531
+ "step": 194
2532
+ },
2533
+ {
2534
+ "Batch Mean": -0.6132583618164062,
2535
+ "accuracy": 0.765625,
2536
+ "epoch": 0.485,
2537
+ "step": 194
2538
+ },
2539
+ {
2540
+ "epoch": 0.4875,
2541
+ "grad_norm": 9.447763442993164,
2542
+ "learning_rate": 1.618421052631579e-06,
2543
+ "loss": 0.4433,
2544
+ "step": 195
2545
+ },
2546
+ {
2547
+ "Batch Mean": -0.452798068523407,
2548
+ "accuracy": 0.859375,
2549
+ "epoch": 0.4875,
2550
+ "step": 195
2551
+ },
2552
+ {
2553
+ "epoch": 0.49,
2554
+ "grad_norm": 8.492661476135254,
2555
+ "learning_rate": 1.6105263157894738e-06,
2556
+ "loss": 0.3995,
2557
+ "step": 196
2558
+ },
2559
+ {
2560
+ "Batch Mean": -0.3771591782569885,
2561
+ "accuracy": 0.828125,
2562
+ "epoch": 0.49,
2563
+ "step": 196
2564
+ },
2565
+ {
2566
+ "epoch": 0.4925,
2567
+ "grad_norm": 8.175331115722656,
2568
+ "learning_rate": 1.6026315789473683e-06,
2569
+ "loss": 0.3677,
2570
+ "step": 197
2571
+ },
2572
+ {
2573
+ "Batch Mean": 0.2654750347137451,
2574
+ "accuracy": 0.84375,
2575
+ "epoch": 0.4925,
2576
+ "step": 197
2577
+ },
2578
+ {
2579
+ "epoch": 0.495,
2580
+ "grad_norm": 8.926229476928711,
2581
+ "learning_rate": 1.594736842105263e-06,
2582
+ "loss": 0.3555,
2583
+ "step": 198
2584
+ },
2585
+ {
2586
+ "Batch Mean": 0.09074139595031738,
2587
+ "accuracy": 0.765625,
2588
+ "epoch": 0.495,
2589
+ "step": 198
2590
+ },
2591
+ {
2592
+ "epoch": 0.4975,
2593
+ "grad_norm": 10.059514999389648,
2594
+ "learning_rate": 1.5868421052631578e-06,
2595
+ "loss": 0.4346,
2596
+ "step": 199
2597
+ },
2598
+ {
2599
+ "Batch Mean": 0.15778541564941406,
2600
+ "accuracy": 0.7578125,
2601
+ "epoch": 0.4975,
2602
+ "step": 199
2603
+ },
2604
+ {
2605
+ "epoch": 0.5,
2606
+ "grad_norm": 8.965482711791992,
2607
+ "learning_rate": 1.5789473684210526e-06,
2608
+ "loss": 0.4118,
2609
+ "step": 200
2610
+ },
2611
+ {
2612
+ "Batch Mean": 0.4453287124633789,
2613
+ "accuracy": 0.8359375,
2614
+ "epoch": 0.5,
2615
+ "step": 200
2616
+ },
2617
+ {
2618
+ "epoch": 0.5025,
2619
+ "grad_norm": 9.427848815917969,
2620
+ "learning_rate": 1.5710526315789473e-06,
2621
+ "loss": 0.4052,
2622
+ "step": 201
2623
+ },
2624
+ {
2625
+ "Batch Mean": 0.006826639175415039,
2626
+ "accuracy": 0.828125,
2627
+ "epoch": 0.5025,
2628
+ "step": 201
2629
+ },
2630
+ {
2631
+ "epoch": 0.505,
2632
+ "grad_norm": 8.063475608825684,
2633
+ "learning_rate": 1.563157894736842e-06,
2634
+ "loss": 0.3993,
2635
+ "step": 202
2636
+ },
2637
+ {
2638
+ "Batch Mean": 0.09803962707519531,
2639
+ "accuracy": 0.90625,
2640
+ "epoch": 0.505,
2641
+ "step": 202
2642
+ },
2643
+ {
2644
+ "epoch": 0.5075,
2645
+ "grad_norm": 7.630380153656006,
2646
+ "learning_rate": 1.5552631578947368e-06,
2647
+ "loss": 0.3072,
2648
+ "step": 203
2649
+ },
2650
+ {
2651
+ "Batch Mean": -0.07749080657958984,
2652
+ "accuracy": 0.765625,
2653
+ "epoch": 0.5075,
2654
+ "step": 203
2655
+ },
2656
+ {
2657
+ "epoch": 0.51,
2658
+ "grad_norm": 9.845494270324707,
2659
+ "learning_rate": 1.5473684210526318e-06,
2660
+ "loss": 0.4411,
2661
+ "step": 204
2662
+ },
2663
+ {
2664
+ "Batch Mean": -0.6465473175048828,
2665
+ "accuracy": 0.8046875,
2666
+ "epoch": 0.51,
2667
+ "step": 204
2668
+ },
2669
+ {
2670
+ "epoch": 0.5125,
2671
+ "grad_norm": 9.862820625305176,
2672
+ "learning_rate": 1.5394736842105265e-06,
2673
+ "loss": 0.4042,
2674
+ "step": 205
2675
+ },
2676
+ {
2677
+ "Batch Mean": -0.25893068313598633,
2678
+ "accuracy": 0.875,
2679
+ "epoch": 0.5125,
2680
+ "step": 205
2681
+ },
2682
+ {
2683
+ "epoch": 0.515,
2684
+ "grad_norm": 9.104493141174316,
2685
+ "learning_rate": 1.5315789473684213e-06,
2686
+ "loss": 0.3414,
2687
+ "step": 206
2688
+ },
2689
+ {
2690
+ "Batch Mean": -0.07256972789764404,
2691
+ "accuracy": 0.78125,
2692
+ "epoch": 0.515,
2693
+ "step": 206
2694
+ },
2695
+ {
2696
+ "epoch": 0.5175,
2697
+ "grad_norm": 10.120800971984863,
2698
+ "learning_rate": 1.5236842105263158e-06,
2699
+ "loss": 0.3988,
2700
+ "step": 207
2701
+ },
2702
+ {
2703
+ "Batch Mean": 0.04418504238128662,
2704
+ "accuracy": 0.8828125,
2705
+ "epoch": 0.5175,
2706
+ "step": 207
2707
+ },
2708
+ {
2709
+ "epoch": 0.52,
2710
+ "grad_norm": 7.554128646850586,
2711
+ "learning_rate": 1.5157894736842105e-06,
2712
+ "loss": 0.3051,
2713
+ "step": 208
2714
+ },
2715
+ {
2716
+ "Batch Mean": 0.6764199733734131,
2717
+ "accuracy": 0.8515625,
2718
+ "epoch": 0.52,
2719
+ "step": 208
2720
+ },
2721
+ {
2722
+ "epoch": 0.5225,
2723
+ "grad_norm": 10.835310935974121,
2724
+ "learning_rate": 1.5078947368421053e-06,
2725
+ "loss": 0.3987,
2726
+ "step": 209
2727
+ },
2728
+ {
2729
+ "Batch Mean": 0.7588990926742554,
2730
+ "accuracy": 0.78125,
2731
+ "epoch": 0.5225,
2732
+ "step": 209
2733
+ },
2734
+ {
2735
+ "epoch": 0.525,
2736
+ "grad_norm": 11.688884735107422,
2737
+ "learning_rate": 1.5e-06,
2738
+ "loss": 0.4125,
2739
+ "step": 210
2740
+ },
2741
+ {
2742
+ "Batch Mean": 0.1539628505706787,
2743
+ "accuracy": 0.78125,
2744
+ "epoch": 0.525,
2745
+ "step": 210
2746
+ },
2747
+ {
2748
+ "epoch": 0.5275,
2749
+ "grad_norm": 10.703190803527832,
2750
+ "learning_rate": 1.4921052631578948e-06,
2751
+ "loss": 0.4351,
2752
+ "step": 211
2753
+ },
2754
+ {
2755
+ "Batch Mean": 0.1315913200378418,
2756
+ "accuracy": 0.828125,
2757
+ "epoch": 0.5275,
2758
+ "step": 211
2759
+ },
2760
+ {
2761
+ "epoch": 0.53,
2762
+ "grad_norm": 10.159830093383789,
2763
+ "learning_rate": 1.4842105263157895e-06,
2764
+ "loss": 0.4016,
2765
+ "step": 212
2766
+ },
2767
+ {
2768
+ "Batch Mean": -0.20069313049316406,
2769
+ "accuracy": 0.8671875,
2770
+ "epoch": 0.53,
2771
+ "step": 212
2772
+ },
2773
+ {
2774
+ "epoch": 0.5325,
2775
+ "grad_norm": 9.962963104248047,
2776
+ "learning_rate": 1.4763157894736843e-06,
2777
+ "loss": 0.3707,
2778
+ "step": 213
2779
+ },
2780
+ {
2781
+ "Batch Mean": -0.14012432098388672,
2782
+ "accuracy": 0.8046875,
2783
+ "epoch": 0.5325,
2784
+ "step": 213
2785
+ },
2786
+ {
2787
+ "epoch": 0.535,
2788
+ "grad_norm": 10.636829376220703,
2789
+ "learning_rate": 1.468421052631579e-06,
2790
+ "loss": 0.4394,
2791
+ "step": 214
2792
+ },
2793
+ {
2794
+ "Batch Mean": 0.03688657283782959,
2795
+ "accuracy": 0.8515625,
2796
+ "epoch": 0.535,
2797
+ "step": 214
2798
+ },
2799
+ {
2800
+ "epoch": 0.5375,
2801
+ "grad_norm": 9.342628479003906,
2802
+ "learning_rate": 1.4605263157894738e-06,
2803
+ "loss": 0.3592,
2804
+ "step": 215
2805
+ },
2806
+ {
2807
+ "Batch Mean": -0.2712291479110718,
2808
+ "accuracy": 0.875,
2809
+ "epoch": 0.5375,
2810
+ "step": 215
2811
+ },
2812
+ {
2813
+ "epoch": 0.54,
2814
+ "grad_norm": 8.388570785522461,
2815
+ "learning_rate": 1.4526315789473685e-06,
2816
+ "loss": 0.3113,
2817
+ "step": 216
2818
+ },
2819
+ {
2820
+ "Batch Mean": -0.07314193248748779,
2821
+ "accuracy": 0.8203125,
2822
+ "epoch": 0.54,
2823
+ "step": 216
2824
+ },
2825
+ {
2826
+ "epoch": 0.5425,
2827
+ "grad_norm": 9.443964958190918,
2828
+ "learning_rate": 1.4447368421052633e-06,
2829
+ "loss": 0.4019,
2830
+ "step": 217
2831
+ },
2832
+ {
2833
+ "Batch Mean": -0.042542457580566406,
2834
+ "accuracy": 0.8203125,
2835
+ "epoch": 0.5425,
2836
+ "step": 217
2837
+ },
2838
+ {
2839
+ "epoch": 0.545,
2840
+ "grad_norm": 10.919589042663574,
2841
+ "learning_rate": 1.436842105263158e-06,
2842
+ "loss": 0.3703,
2843
+ "step": 218
2844
+ },
2845
+ {
2846
+ "Batch Mean": -0.03744637966156006,
2847
+ "accuracy": 0.828125,
2848
+ "epoch": 0.545,
2849
+ "step": 218
2850
+ },
2851
+ {
2852
+ "epoch": 0.5475,
2853
+ "grad_norm": 9.716089248657227,
2854
+ "learning_rate": 1.4289473684210525e-06,
2855
+ "loss": 0.3527,
2856
+ "step": 219
2857
+ },
2858
+ {
2859
+ "Batch Mean": -0.209802508354187,
2860
+ "accuracy": 0.8046875,
2861
+ "epoch": 0.5475,
2862
+ "step": 219
2863
+ },
2864
+ {
2865
+ "epoch": 0.55,
2866
+ "grad_norm": 10.598649024963379,
2867
+ "learning_rate": 1.4210526315789473e-06,
2868
+ "loss": 0.4273,
2869
+ "step": 220
2870
+ },
2871
+ {
2872
+ "Batch Mean": 0.34712672233581543,
2873
+ "accuracy": 0.828125,
2874
+ "epoch": 0.55,
2875
+ "step": 220
2876
+ },
2877
+ {
2878
+ "epoch": 0.5525,
2879
+ "grad_norm": 9.486217498779297,
2880
+ "learning_rate": 1.4131578947368422e-06,
2881
+ "loss": 0.341,
2882
+ "step": 221
2883
+ },
2884
+ {
2885
+ "Batch Mean": 0.03266429901123047,
2886
+ "accuracy": 0.8203125,
2887
+ "epoch": 0.5525,
2888
+ "step": 221
2889
+ },
2890
+ {
2891
+ "epoch": 0.555,
2892
+ "grad_norm": 10.724418640136719,
2893
+ "learning_rate": 1.405263157894737e-06,
2894
+ "loss": 0.3997,
2895
+ "step": 222
2896
+ },
2897
+ {
2898
+ "Batch Mean": -0.18854069709777832,
2899
+ "accuracy": 0.828125,
2900
+ "epoch": 0.555,
2901
+ "step": 222
2902
+ },
2903
+ {
2904
+ "epoch": 0.5575,
2905
+ "grad_norm": 9.75826358795166,
2906
+ "learning_rate": 1.3973684210526317e-06,
2907
+ "loss": 0.3694,
2908
+ "step": 223
2909
+ },
2910
+ {
2911
+ "Batch Mean": -0.41150808334350586,
2912
+ "accuracy": 0.859375,
2913
+ "epoch": 0.5575,
2914
+ "step": 223
2915
+ },
2916
+ {
2917
+ "epoch": 0.56,
2918
+ "grad_norm": 9.46369743347168,
2919
+ "learning_rate": 1.3894736842105263e-06,
2920
+ "loss": 0.3251,
2921
+ "step": 224
2922
+ },
2923
+ {
2924
+ "Batch Mean": -0.0464327335357666,
2925
+ "accuracy": 0.8203125,
2926
+ "epoch": 0.56,
2927
+ "step": 224
2928
+ },
2929
+ {
2930
+ "epoch": 0.5625,
2931
+ "grad_norm": 10.088607788085938,
2932
+ "learning_rate": 1.381578947368421e-06,
2933
+ "loss": 0.4025,
2934
+ "step": 225
2935
+ },
2936
+ {
2937
+ "Batch Mean": 0.4004335403442383,
2938
+ "accuracy": 0.7890625,
2939
+ "epoch": 0.5625,
2940
+ "step": 225
2941
+ },
2942
+ {
2943
+ "epoch": 0.565,
2944
+ "grad_norm": 12.501627922058105,
2945
+ "learning_rate": 1.3736842105263158e-06,
2946
+ "loss": 0.4476,
2947
+ "step": 226
2948
+ },
2949
+ {
2950
+ "Batch Mean": 0.3384718894958496,
2951
+ "accuracy": 0.7734375,
2952
+ "epoch": 0.565,
2953
+ "step": 226
2954
+ },
2955
+ {
2956
+ "epoch": 0.5675,
2957
+ "grad_norm": 11.507113456726074,
2958
+ "learning_rate": 1.3657894736842107e-06,
2959
+ "loss": 0.4509,
2960
+ "step": 227
2961
+ },
2962
+ {
2963
+ "Batch Mean": 0.10722827911376953,
2964
+ "accuracy": 0.8125,
2965
+ "epoch": 0.5675,
2966
+ "step": 227
2967
+ },
2968
+ {
2969
+ "epoch": 0.57,
2970
+ "grad_norm": 8.944846153259277,
2971
+ "learning_rate": 1.3578947368421055e-06,
2972
+ "loss": 0.4159,
2973
+ "step": 228
2974
+ },
2975
+ {
2976
+ "Batch Mean": -0.30047035217285156,
2977
+ "accuracy": 0.8359375,
2978
+ "epoch": 0.57,
2979
+ "step": 228
2980
+ },
2981
+ {
2982
+ "epoch": 0.5725,
2983
+ "grad_norm": 8.207252502441406,
2984
+ "learning_rate": 1.35e-06,
2985
+ "loss": 0.3531,
2986
+ "step": 229
2987
+ },
2988
+ {
2989
+ "Batch Mean": -0.2651713490486145,
2990
+ "accuracy": 0.8515625,
2991
+ "epoch": 0.5725,
2992
+ "step": 229
2993
+ },
2994
+ {
2995
+ "epoch": 0.575,
2996
+ "grad_norm": 8.584181785583496,
2997
+ "learning_rate": 1.3421052631578947e-06,
2998
+ "loss": 0.363,
2999
+ "step": 230
3000
+ },
3001
+ {
3002
+ "Batch Mean": -0.44047990441322327,
3003
+ "accuracy": 0.8203125,
3004
+ "epoch": 0.575,
3005
+ "step": 230
3006
+ },
3007
+ {
3008
+ "epoch": 0.5775,
3009
+ "grad_norm": 9.892334938049316,
3010
+ "learning_rate": 1.3342105263157895e-06,
3011
+ "loss": 0.3964,
3012
+ "step": 231
3013
+ },
3014
+ {
3015
+ "Batch Mean": -0.1500718593597412,
3016
+ "accuracy": 0.7890625,
3017
+ "epoch": 0.5775,
3018
+ "step": 231
3019
+ },
3020
+ {
3021
+ "epoch": 0.58,
3022
+ "grad_norm": 9.095638275146484,
3023
+ "learning_rate": 1.3263157894736842e-06,
3024
+ "loss": 0.3979,
3025
+ "step": 232
3026
+ },
3027
+ {
3028
+ "Batch Mean": 0.2158275842666626,
3029
+ "accuracy": 0.7578125,
3030
+ "epoch": 0.58,
3031
+ "step": 232
3032
+ },
3033
+ {
3034
+ "epoch": 0.5825,
3035
+ "grad_norm": 11.318427085876465,
3036
+ "learning_rate": 1.318421052631579e-06,
3037
+ "loss": 0.476,
3038
+ "step": 233
3039
+ },
3040
+ {
3041
+ "Batch Mean": 0.25293970108032227,
3042
+ "accuracy": 0.8125,
3043
+ "epoch": 0.5825,
3044
+ "step": 233
3045
+ },
3046
+ {
3047
+ "epoch": 0.585,
3048
+ "grad_norm": 8.678732872009277,
3049
+ "learning_rate": 1.3105263157894737e-06,
3050
+ "loss": 0.4024,
3051
+ "step": 234
3052
+ },
3053
+ {
3054
+ "Batch Mean": 0.30934906005859375,
3055
+ "accuracy": 0.8671875,
3056
+ "epoch": 0.585,
3057
+ "step": 234
3058
+ },
3059
+ {
3060
+ "epoch": 0.5875,
3061
+ "grad_norm": 7.908719062805176,
3062
+ "learning_rate": 1.3026315789473685e-06,
3063
+ "loss": 0.3039,
3064
+ "step": 235
3065
+ },
3066
+ {
3067
+ "Batch Mean": -0.057540178298950195,
3068
+ "accuracy": 0.8515625,
3069
+ "epoch": 0.5875,
3070
+ "step": 235
3071
+ },
3072
+ {
3073
+ "epoch": 0.59,
3074
+ "grad_norm": 7.79960823059082,
3075
+ "learning_rate": 1.2947368421052632e-06,
3076
+ "loss": 0.3345,
3077
+ "step": 236
3078
+ },
3079
+ {
3080
+ "Batch Mean": -0.08140373229980469,
3081
+ "accuracy": 0.796875,
3082
+ "epoch": 0.59,
3083
+ "step": 236
3084
+ },
3085
+ {
3086
+ "epoch": 0.5925,
3087
+ "grad_norm": 9.922690391540527,
3088
+ "learning_rate": 1.286842105263158e-06,
3089
+ "loss": 0.4089,
3090
+ "step": 237
3091
+ },
3092
+ {
3093
+ "Batch Mean": -0.31038880348205566,
3094
+ "accuracy": 0.8203125,
3095
+ "epoch": 0.5925,
3096
+ "step": 237
3097
+ },
3098
+ {
3099
+ "epoch": 0.595,
3100
+ "grad_norm": 9.403748512268066,
3101
+ "learning_rate": 1.2789473684210527e-06,
3102
+ "loss": 0.392,
3103
+ "step": 238
3104
+ },
3105
+ {
3106
+ "Batch Mean": -0.025382041931152344,
3107
+ "accuracy": 0.828125,
3108
+ "epoch": 0.595,
3109
+ "step": 238
3110
+ },
3111
+ {
3112
+ "epoch": 0.5975,
3113
+ "grad_norm": 9.586471557617188,
3114
+ "learning_rate": 1.2710526315789474e-06,
3115
+ "loss": 0.3332,
3116
+ "step": 239
3117
+ },
3118
+ {
3119
+ "Batch Mean": -0.09691180288791656,
3120
+ "accuracy": 0.890625,
3121
+ "epoch": 0.5975,
3122
+ "step": 239
3123
+ },
3124
+ {
3125
+ "epoch": 0.6,
3126
+ "grad_norm": 8.952404975891113,
3127
+ "learning_rate": 1.263157894736842e-06,
3128
+ "loss": 0.2919,
3129
+ "step": 240
3130
+ },
3131
+ {
3132
+ "Batch Mean": 0.24474626779556274,
3133
+ "accuracy": 0.796875,
3134
+ "epoch": 0.6,
3135
+ "step": 240
3136
+ },
3137
+ {
3138
+ "epoch": 0.6025,
3139
+ "grad_norm": 9.637041091918945,
3140
+ "learning_rate": 1.255263157894737e-06,
3141
+ "loss": 0.3659,
3142
+ "step": 241
3143
+ },
3144
+ {
3145
+ "Batch Mean": 0.3834969997406006,
3146
+ "accuracy": 0.84375,
3147
+ "epoch": 0.6025,
3148
+ "step": 241
3149
+ },
3150
+ {
3151
+ "epoch": 0.605,
3152
+ "grad_norm": 10.450284957885742,
3153
+ "learning_rate": 1.2473684210526317e-06,
3154
+ "loss": 0.3735,
3155
+ "step": 242
3156
+ },
3157
+ {
3158
+ "Batch Mean": 0.41518211364746094,
3159
+ "accuracy": 0.828125,
3160
+ "epoch": 0.605,
3161
+ "step": 242
3162
+ },
3163
+ {
3164
+ "epoch": 0.6075,
3165
+ "grad_norm": 13.025629043579102,
3166
+ "learning_rate": 1.2394736842105264e-06,
3167
+ "loss": 0.3474,
3168
+ "step": 243
3169
+ },
3170
+ {
3171
+ "Batch Mean": 0.43804705142974854,
3172
+ "accuracy": 0.8125,
3173
+ "epoch": 0.6075,
3174
+ "step": 243
3175
+ },
3176
+ {
3177
+ "epoch": 0.61,
3178
+ "grad_norm": 11.754925727844238,
3179
+ "learning_rate": 1.2315789473684212e-06,
3180
+ "loss": 0.4055,
3181
+ "step": 244
3182
+ },
3183
+ {
3184
+ "Batch Mean": 0.26791906356811523,
3185
+ "accuracy": 0.8125,
3186
+ "epoch": 0.61,
3187
+ "step": 244
3188
+ },
3189
+ {
3190
+ "epoch": 0.6125,
3191
+ "grad_norm": 8.931976318359375,
3192
+ "learning_rate": 1.2236842105263157e-06,
3193
+ "loss": 0.3545,
3194
+ "step": 245
3195
+ },
3196
+ {
3197
+ "Batch Mean": -0.04610109329223633,
3198
+ "accuracy": 0.8203125,
3199
+ "epoch": 0.6125,
3200
+ "step": 245
3201
+ },
3202
+ {
3203
+ "epoch": 0.615,
3204
+ "grad_norm": 10.400755882263184,
3205
+ "learning_rate": 1.2157894736842105e-06,
3206
+ "loss": 0.4299,
3207
+ "step": 246
3208
+ },
3209
+ {
3210
+ "Batch Mean": -0.7998272180557251,
3211
+ "accuracy": 0.8203125,
3212
+ "epoch": 0.615,
3213
+ "step": 246
3214
+ },
3215
+ {
3216
+ "epoch": 0.6175,
3217
+ "grad_norm": 11.944729804992676,
3218
+ "learning_rate": 1.2078947368421052e-06,
3219
+ "loss": 0.4358,
3220
+ "step": 247
3221
+ },
3222
+ {
3223
+ "Batch Mean": -0.2411341667175293,
3224
+ "accuracy": 0.828125,
3225
+ "epoch": 0.6175,
3226
+ "step": 247
3227
+ },
3228
+ {
3229
+ "epoch": 0.62,
3230
+ "grad_norm": 10.680310249328613,
3231
+ "learning_rate": 1.2000000000000002e-06,
3232
+ "loss": 0.3575,
3233
+ "step": 248
3234
+ },
3235
+ {
3236
+ "Batch Mean": -0.47270846366882324,
3237
+ "accuracy": 0.859375,
3238
+ "epoch": 0.62,
3239
+ "step": 248
3240
+ },
3241
+ {
3242
+ "epoch": 0.6225,
3243
+ "grad_norm": 9.311689376831055,
3244
+ "learning_rate": 1.192105263157895e-06,
3245
+ "loss": 0.3146,
3246
+ "step": 249
3247
+ },
3248
+ {
3249
+ "Batch Mean": -0.023276805877685547,
3250
+ "accuracy": 0.8203125,
3251
+ "epoch": 0.6225,
3252
+ "step": 249
3253
+ },
3254
+ {
3255
+ "epoch": 0.625,
3256
+ "grad_norm": 10.916861534118652,
3257
+ "learning_rate": 1.1842105263157894e-06,
3258
+ "loss": 0.3885,
3259
+ "step": 250
3260
+ },
3261
+ {
3262
+ "Batch Mean": -0.2923322916030884,
3263
+ "accuracy": 0.828125,
3264
+ "epoch": 0.625,
3265
+ "step": 250
3266
+ },
3267
+ {
3268
+ "epoch": 0.6275,
3269
+ "grad_norm": 9.724871635437012,
3270
+ "learning_rate": 1.1763157894736842e-06,
3271
+ "loss": 0.3544,
3272
+ "step": 251
3273
+ },
3274
+ {
3275
+ "Batch Mean": 0.03692519664764404,
3276
+ "accuracy": 0.828125,
3277
+ "epoch": 0.6275,
3278
+ "step": 251
3279
+ },
3280
+ {
3281
+ "epoch": 0.63,
3282
+ "grad_norm": 9.2437744140625,
3283
+ "learning_rate": 1.168421052631579e-06,
3284
+ "loss": 0.3548,
3285
+ "step": 252
3286
+ },
3287
+ {
3288
+ "Batch Mean": 0.9230005741119385,
3289
+ "accuracy": 0.8515625,
3290
+ "epoch": 0.63,
3291
+ "step": 252
3292
+ },
3293
+ {
3294
+ "epoch": 0.6325,
3295
+ "grad_norm": 14.65259075164795,
3296
+ "learning_rate": 1.1605263157894737e-06,
3297
+ "loss": 0.4183,
3298
+ "step": 253
3299
+ },
3300
+ {
3301
+ "Batch Mean": 0.45890212059020996,
3302
+ "accuracy": 0.828125,
3303
+ "epoch": 0.6325,
3304
+ "step": 253
3305
+ },
3306
+ {
3307
+ "epoch": 0.635,
3308
+ "grad_norm": 11.038723945617676,
3309
+ "learning_rate": 1.1526315789473684e-06,
3310
+ "loss": 0.4122,
3311
+ "step": 254
3312
+ },
3313
+ {
3314
+ "Batch Mean": 0.38666415214538574,
3315
+ "accuracy": 0.828125,
3316
+ "epoch": 0.635,
3317
+ "step": 254
3318
+ },
3319
+ {
3320
+ "epoch": 0.6375,
3321
+ "grad_norm": 11.32805061340332,
3322
+ "learning_rate": 1.1447368421052632e-06,
3323
+ "loss": 0.3961,
3324
+ "step": 255
3325
+ },
3326
+ {
3327
+ "Batch Mean": 0.4147815704345703,
3328
+ "accuracy": 0.828125,
3329
+ "epoch": 0.6375,
3330
+ "step": 255
3331
+ },
3332
+ {
3333
+ "epoch": 0.64,
3334
+ "grad_norm": 9.602386474609375,
3335
+ "learning_rate": 1.136842105263158e-06,
3336
+ "loss": 0.3741,
3337
+ "step": 256
3338
+ },
3339
+ {
3340
+ "Batch Mean": 0.006276130676269531,
3341
+ "accuracy": 0.78125,
3342
+ "epoch": 0.64,
3343
+ "step": 256
3344
+ },
3345
+ {
3346
+ "epoch": 0.6425,
3347
+ "grad_norm": 9.531057357788086,
3348
+ "learning_rate": 1.1289473684210527e-06,
3349
+ "loss": 0.4329,
3350
+ "step": 257
3351
+ },
3352
+ {
3353
+ "Batch Mean": -0.23307615518569946,
3354
+ "accuracy": 0.828125,
3355
+ "epoch": 0.6425,
3356
+ "step": 257
3357
+ },
3358
+ {
3359
+ "epoch": 0.645,
3360
+ "grad_norm": 8.362524032592773,
3361
+ "learning_rate": 1.1210526315789474e-06,
3362
+ "loss": 0.382,
3363
+ "step": 258
3364
+ },
3365
+ {
3366
+ "Batch Mean": 0.04139423370361328,
3367
+ "accuracy": 0.796875,
3368
+ "epoch": 0.645,
3369
+ "step": 258
3370
+ },
3371
+ {
3372
+ "epoch": 0.6475,
3373
+ "grad_norm": 9.12584114074707,
3374
+ "learning_rate": 1.1131578947368421e-06,
3375
+ "loss": 0.3852,
3376
+ "step": 259
3377
+ },
3378
+ {
3379
+ "Batch Mean": -0.3190183639526367,
3380
+ "accuracy": 0.8046875,
3381
+ "epoch": 0.6475,
3382
+ "step": 259
3383
+ },
3384
+ {
3385
+ "epoch": 0.65,
3386
+ "grad_norm": 9.95345401763916,
3387
+ "learning_rate": 1.1052631578947369e-06,
3388
+ "loss": 0.3966,
3389
+ "step": 260
3390
+ },
3391
+ {
3392
+ "Batch Mean": -0.8157808780670166,
3393
+ "accuracy": 0.828125,
3394
+ "epoch": 0.65,
3395
+ "step": 260
3396
+ },
3397
+ {
3398
+ "epoch": 0.6525,
3399
+ "grad_norm": 10.541975021362305,
3400
+ "learning_rate": 1.0973684210526316e-06,
3401
+ "loss": 0.367,
3402
+ "step": 261
3403
+ },
3404
+ {
3405
+ "Batch Mean": -0.5502346754074097,
3406
+ "accuracy": 0.796875,
3407
+ "epoch": 0.6525,
3408
+ "step": 261
3409
+ },
3410
+ {
3411
+ "epoch": 0.655,
3412
+ "grad_norm": 10.180998802185059,
3413
+ "learning_rate": 1.0894736842105264e-06,
3414
+ "loss": 0.4012,
3415
+ "step": 262
3416
+ },
3417
+ {
3418
+ "Batch Mean": -0.31228208541870117,
3419
+ "accuracy": 0.796875,
3420
+ "epoch": 0.655,
3421
+ "step": 262
3422
+ },
3423
+ {
3424
+ "epoch": 0.6575,
3425
+ "grad_norm": 8.454268455505371,
3426
+ "learning_rate": 1.0815789473684211e-06,
3427
+ "loss": 0.3794,
3428
+ "step": 263
3429
+ },
3430
+ {
3431
+ "Batch Mean": 0.023279190063476562,
3432
+ "accuracy": 0.8359375,
3433
+ "epoch": 0.6575,
3434
+ "step": 263
3435
+ },
3436
+ {
3437
+ "epoch": 0.66,
3438
+ "grad_norm": 8.542173385620117,
3439
+ "learning_rate": 1.0736842105263159e-06,
3440
+ "loss": 0.3667,
3441
+ "step": 264
3442
+ },
3443
+ {
3444
+ "Batch Mean": 0.25201869010925293,
3445
+ "accuracy": 0.8984375,
3446
+ "epoch": 0.66,
3447
+ "step": 264
3448
+ },
3449
+ {
3450
+ "epoch": 0.6625,
3451
+ "grad_norm": 9.752306938171387,
3452
+ "learning_rate": 1.0657894736842106e-06,
3453
+ "loss": 0.2916,
3454
+ "step": 265
3455
+ },
3456
+ {
3457
+ "Batch Mean": 0.21469709277153015,
3458
+ "accuracy": 0.890625,
3459
+ "epoch": 0.6625,
3460
+ "step": 265
3461
+ },
3462
+ {
3463
+ "epoch": 0.665,
3464
+ "grad_norm": 6.977869510650635,
3465
+ "learning_rate": 1.0578947368421052e-06,
3466
+ "loss": 0.2659,
3467
+ "step": 266
3468
+ },
3469
+ {
3470
+ "Batch Mean": 0.393679141998291,
3471
+ "accuracy": 0.8515625,
3472
+ "epoch": 0.665,
3473
+ "step": 266
3474
+ },
3475
+ {
3476
+ "epoch": 0.6675,
3477
+ "grad_norm": 9.701105117797852,
3478
+ "learning_rate": 1.05e-06,
3479
+ "loss": 0.3567,
3480
+ "step": 267
3481
+ },
3482
+ {
3483
+ "Batch Mean": 0.6953978538513184,
3484
+ "accuracy": 0.8046875,
3485
+ "epoch": 0.6675,
3486
+ "step": 267
3487
+ },
3488
+ {
3489
+ "epoch": 0.67,
3490
+ "grad_norm": 10.121991157531738,
3491
+ "learning_rate": 1.0421052631578949e-06,
3492
+ "loss": 0.404,
3493
+ "step": 268
3494
+ },
3495
+ {
3496
+ "Batch Mean": 0.3401451110839844,
3497
+ "accuracy": 0.8671875,
3498
+ "epoch": 0.67,
3499
+ "step": 268
3500
+ },
3501
+ {
3502
+ "epoch": 0.6725,
3503
+ "grad_norm": 8.189865112304688,
3504
+ "learning_rate": 1.0342105263157896e-06,
3505
+ "loss": 0.3378,
3506
+ "step": 269
3507
+ },
3508
+ {
3509
+ "Batch Mean": 0.2478356957435608,
3510
+ "accuracy": 0.75,
3511
+ "epoch": 0.6725,
3512
+ "step": 269
3513
+ },
3514
+ {
3515
+ "epoch": 0.675,
3516
+ "grad_norm": 10.778964042663574,
3517
+ "learning_rate": 1.0263157894736843e-06,
3518
+ "loss": 0.4703,
3519
+ "step": 270
3520
+ },
3521
+ {
3522
+ "Batch Mean": -0.22268009185791016,
3523
+ "accuracy": 0.8046875,
3524
+ "epoch": 0.675,
3525
+ "step": 270
3526
+ },
3527
+ {
3528
+ "epoch": 0.6775,
3529
+ "grad_norm": 9.94092845916748,
3530
+ "learning_rate": 1.0184210526315789e-06,
3531
+ "loss": 0.412,
3532
+ "step": 271
3533
+ },
3534
+ {
3535
+ "Batch Mean": -0.19172096252441406,
3536
+ "accuracy": 0.8671875,
3537
+ "epoch": 0.6775,
3538
+ "step": 271
3539
+ },
3540
+ {
3541
+ "epoch": 0.68,
3542
+ "grad_norm": 7.948995113372803,
3543
+ "learning_rate": 1.0105263157894736e-06,
3544
+ "loss": 0.3079,
3545
+ "step": 272
3546
+ },
3547
+ {
3548
+ "Batch Mean": -0.01717686653137207,
3549
+ "accuracy": 0.84375,
3550
+ "epoch": 0.68,
3551
+ "step": 272
3552
+ },
3553
+ {
3554
+ "epoch": 0.6825,
3555
+ "grad_norm": 8.31904125213623,
3556
+ "learning_rate": 1.0026315789473684e-06,
3557
+ "loss": 0.3627,
3558
+ "step": 273
3559
+ },
3560
+ {
3561
+ "Batch Mean": -0.17321079969406128,
3562
+ "accuracy": 0.8203125,
3563
+ "epoch": 0.6825,
3564
+ "step": 273
3565
+ },
3566
+ {
3567
+ "epoch": 0.685,
3568
+ "grad_norm": 9.820837020874023,
3569
+ "learning_rate": 9.947368421052631e-07,
3570
+ "loss": 0.4136,
3571
+ "step": 274
3572
+ },
3573
+ {
3574
+ "Batch Mean": -0.1444711685180664,
3575
+ "accuracy": 0.7421875,
3576
+ "epoch": 0.685,
3577
+ "step": 274
3578
+ },
3579
+ {
3580
+ "epoch": 0.6875,
3581
+ "grad_norm": 10.36066722869873,
3582
+ "learning_rate": 9.86842105263158e-07,
3583
+ "loss": 0.4474,
3584
+ "step": 275
3585
+ },
3586
+ {
3587
+ "Batch Mean": -0.26374632120132446,
3588
+ "accuracy": 0.796875,
3589
+ "epoch": 0.6875,
3590
+ "step": 275
3591
+ },
3592
+ {
3593
+ "epoch": 0.69,
3594
+ "grad_norm": 9.943070411682129,
3595
+ "learning_rate": 9.789473684210526e-07,
3596
+ "loss": 0.3974,
3597
+ "step": 276
3598
+ },
3599
+ {
3600
+ "Batch Mean": 0.056405067443847656,
3601
+ "accuracy": 0.828125,
3602
+ "epoch": 0.69,
3603
+ "step": 276
3604
+ },
3605
+ {
3606
+ "epoch": 0.6925,
3607
+ "grad_norm": 8.994078636169434,
3608
+ "learning_rate": 9.710526315789474e-07,
3609
+ "loss": 0.3722,
3610
+ "step": 277
3611
+ },
3612
+ {
3613
+ "Batch Mean": -0.03705739974975586,
3614
+ "accuracy": 0.84375,
3615
+ "epoch": 0.6925,
3616
+ "step": 277
3617
+ },
3618
+ {
3619
+ "epoch": 0.695,
3620
+ "grad_norm": 9.382537841796875,
3621
+ "learning_rate": 9.63157894736842e-07,
3622
+ "loss": 0.3764,
3623
+ "step": 278
3624
+ },
3625
+ {
3626
+ "Batch Mean": 0.1647498905658722,
3627
+ "accuracy": 0.84375,
3628
+ "epoch": 0.695,
3629
+ "step": 278
3630
+ },
3631
+ {
3632
+ "epoch": 0.6975,
3633
+ "grad_norm": 8.693201065063477,
3634
+ "learning_rate": 9.552631578947368e-07,
3635
+ "loss": 0.3984,
3636
+ "step": 279
3637
+ },
3638
+ {
3639
+ "Batch Mean": -0.195298433303833,
3640
+ "accuracy": 0.7890625,
3641
+ "epoch": 0.6975,
3642
+ "step": 279
3643
+ },
3644
+ {
3645
+ "epoch": 0.7,
3646
+ "grad_norm": 11.22012710571289,
3647
+ "learning_rate": 9.473684210526316e-07,
3648
+ "loss": 0.4338,
3649
+ "step": 280
3650
+ },
3651
+ {
3652
+ "Batch Mean": -0.1467556357383728,
3653
+ "accuracy": 0.84375,
3654
+ "epoch": 0.7,
3655
+ "step": 280
3656
+ },
3657
+ {
3658
+ "epoch": 0.7025,
3659
+ "grad_norm": 7.977049827575684,
3660
+ "learning_rate": 9.394736842105262e-07,
3661
+ "loss": 0.3062,
3662
+ "step": 281
3663
+ },
3664
+ {
3665
+ "Batch Mean": 0.15868717432022095,
3666
+ "accuracy": 0.8515625,
3667
+ "epoch": 0.7025,
3668
+ "step": 281
3669
+ },
3670
+ {
3671
+ "epoch": 0.705,
3672
+ "grad_norm": 8.255351066589355,
3673
+ "learning_rate": 9.315789473684212e-07,
3674
+ "loss": 0.3726,
3675
+ "step": 282
3676
+ },
3677
+ {
3678
+ "Batch Mean": -0.15160489082336426,
3679
+ "accuracy": 0.8125,
3680
+ "epoch": 0.705,
3681
+ "step": 282
3682
+ },
3683
+ {
3684
+ "epoch": 0.7075,
3685
+ "grad_norm": 9.976411819458008,
3686
+ "learning_rate": 9.236842105263158e-07,
3687
+ "loss": 0.3723,
3688
+ "step": 283
3689
+ },
3690
+ {
3691
+ "Batch Mean": -0.27870988845825195,
3692
+ "accuracy": 0.828125,
3693
+ "epoch": 0.7075,
3694
+ "step": 283
3695
+ },
3696
+ {
3697
+ "epoch": 0.71,
3698
+ "grad_norm": 8.676006317138672,
3699
+ "learning_rate": 9.157894736842106e-07,
3700
+ "loss": 0.3357,
3701
+ "step": 284
3702
+ },
3703
+ {
3704
+ "Batch Mean": 0.25218677520751953,
3705
+ "accuracy": 0.8046875,
3706
+ "epoch": 0.71,
3707
+ "step": 284
3708
+ },
3709
+ {
3710
+ "epoch": 0.7125,
3711
+ "grad_norm": 9.949384689331055,
3712
+ "learning_rate": 9.078947368421053e-07,
3713
+ "loss": 0.4071,
3714
+ "step": 285
3715
+ },
3716
+ {
3717
+ "Batch Mean": -0.13117164373397827,
3718
+ "accuracy": 0.8046875,
3719
+ "epoch": 0.7125,
3720
+ "step": 285
3721
+ },
3722
+ {
3723
+ "epoch": 0.715,
3724
+ "grad_norm": 9.771759033203125,
3725
+ "learning_rate": 9e-07,
3726
+ "loss": 0.3825,
3727
+ "step": 286
3728
+ },
3729
+ {
3730
+ "Batch Mean": -0.2633533477783203,
3731
+ "accuracy": 0.828125,
3732
+ "epoch": 0.715,
3733
+ "step": 286
3734
+ },
3735
+ {
3736
+ "epoch": 0.7175,
3737
+ "grad_norm": 9.035362243652344,
3738
+ "learning_rate": 8.921052631578947e-07,
3739
+ "loss": 0.3266,
3740
+ "step": 287
3741
+ },
3742
+ {
3743
+ "Batch Mean": 0.20660001039505005,
3744
+ "accuracy": 0.90625,
3745
+ "epoch": 0.7175,
3746
+ "step": 287
3747
+ },
3748
+ {
3749
+ "epoch": 0.72,
3750
+ "grad_norm": 8.132331848144531,
3751
+ "learning_rate": 8.842105263157895e-07,
3752
+ "loss": 0.2879,
3753
+ "step": 288
3754
+ },
3755
+ {
3756
+ "Batch Mean": 0.07574963569641113,
3757
+ "accuracy": 0.8828125,
3758
+ "epoch": 0.72,
3759
+ "step": 288
3760
+ },
3761
+ {
3762
+ "epoch": 0.7225,
3763
+ "grad_norm": 8.73331356048584,
3764
+ "learning_rate": 8.763157894736843e-07,
3765
+ "loss": 0.333,
3766
+ "step": 289
3767
+ },
3768
+ {
3769
+ "Batch Mean": -0.017863690853118896,
3770
+ "accuracy": 0.78125,
3771
+ "epoch": 0.7225,
3772
+ "step": 289
3773
+ },
3774
+ {
3775
+ "epoch": 0.725,
3776
+ "grad_norm": 10.603270530700684,
3777
+ "learning_rate": 8.68421052631579e-07,
3778
+ "loss": 0.4039,
3779
+ "step": 290
3780
+ },
3781
+ {
3782
+ "Batch Mean": 0.0752725601196289,
3783
+ "accuracy": 0.8515625,
3784
+ "epoch": 0.725,
3785
+ "step": 290
3786
+ },
3787
+ {
3788
+ "epoch": 0.7275,
3789
+ "grad_norm": 9.06254768371582,
3790
+ "learning_rate": 8.605263157894737e-07,
3791
+ "loss": 0.3526,
3792
+ "step": 291
3793
+ },
3794
+ {
3795
+ "Batch Mean": 0.02768230438232422,
3796
+ "accuracy": 0.8828125,
3797
+ "epoch": 0.7275,
3798
+ "step": 291
3799
+ },
3800
+ {
3801
+ "epoch": 0.73,
3802
+ "grad_norm": 8.968415260314941,
3803
+ "learning_rate": 8.526315789473684e-07,
3804
+ "loss": 0.291,
3805
+ "step": 292
3806
+ },
3807
+ {
3808
+ "Batch Mean": 0.21530699729919434,
3809
+ "accuracy": 0.8203125,
3810
+ "epoch": 0.73,
3811
+ "step": 292
3812
+ },
3813
+ {
3814
+ "epoch": 0.7325,
3815
+ "grad_norm": 10.839483261108398,
3816
+ "learning_rate": 8.447368421052632e-07,
3817
+ "loss": 0.4106,
3818
+ "step": 293
3819
+ },
3820
+ {
3821
+ "Batch Mean": 0.5640954971313477,
3822
+ "accuracy": 0.84375,
3823
+ "epoch": 0.7325,
3824
+ "step": 293
3825
+ },
3826
+ {
3827
+ "epoch": 0.735,
3828
+ "grad_norm": 9.728655815124512,
3829
+ "learning_rate": 8.368421052631578e-07,
3830
+ "loss": 0.3442,
3831
+ "step": 294
3832
+ },
3833
+ {
3834
+ "Batch Mean": -0.018077611923217773,
3835
+ "accuracy": 0.859375,
3836
+ "epoch": 0.735,
3837
+ "step": 294
3838
+ },
3839
+ {
3840
+ "epoch": 0.7375,
3841
+ "grad_norm": 10.114471435546875,
3842
+ "learning_rate": 8.289473684210528e-07,
3843
+ "loss": 0.3098,
3844
+ "step": 295
3845
+ },
3846
+ {
3847
+ "Batch Mean": 0.09554731845855713,
3848
+ "accuracy": 0.8671875,
3849
+ "epoch": 0.7375,
3850
+ "step": 295
3851
+ },
3852
+ {
3853
+ "epoch": 0.74,
3854
+ "grad_norm": 9.599811553955078,
3855
+ "learning_rate": 8.210526315789474e-07,
3856
+ "loss": 0.356,
3857
+ "step": 296
3858
+ },
3859
+ {
3860
+ "Batch Mean": 0.12642377614974976,
3861
+ "accuracy": 0.8359375,
3862
+ "epoch": 0.74,
3863
+ "step": 296
3864
+ },
3865
+ {
3866
+ "epoch": 0.7425,
3867
+ "grad_norm": 9.411256790161133,
3868
+ "learning_rate": 8.131578947368422e-07,
3869
+ "loss": 0.3861,
3870
+ "step": 297
3871
+ },
3872
+ {
3873
+ "Batch Mean": -0.05638265609741211,
3874
+ "accuracy": 0.828125,
3875
+ "epoch": 0.7425,
3876
+ "step": 297
3877
+ },
3878
+ {
3879
+ "epoch": 0.745,
3880
+ "grad_norm": 9.531231880187988,
3881
+ "learning_rate": 8.052631578947369e-07,
3882
+ "loss": 0.3093,
3883
+ "step": 298
3884
+ },
3885
+ {
3886
+ "Batch Mean": 0.13509082794189453,
3887
+ "accuracy": 0.8671875,
3888
+ "epoch": 0.745,
3889
+ "step": 298
3890
+ },
3891
+ {
3892
+ "epoch": 0.7475,
3893
+ "grad_norm": 8.823690414428711,
3894
+ "learning_rate": 7.973684210526315e-07,
3895
+ "loss": 0.3221,
3896
+ "step": 299
3897
+ },
3898
+ {
3899
+ "Batch Mean": -0.17625296115875244,
3900
+ "accuracy": 0.890625,
3901
+ "epoch": 0.7475,
3902
+ "step": 299
3903
+ },
3904
+ {
3905
+ "epoch": 0.75,
3906
+ "grad_norm": 8.370561599731445,
3907
+ "learning_rate": 7.894736842105263e-07,
3908
+ "loss": 0.2848,
3909
+ "step": 300
3910
+ }
3911
+ ],
3912
+ "logging_steps": 1,
3913
+ "max_steps": 400,
3914
+ "num_input_tokens_seen": 0,
3915
+ "num_train_epochs": 1,
3916
+ "save_steps": 100,
3917
+ "stateful_callbacks": {
3918
+ "TrainerControl": {
3919
+ "args": {
3920
+ "should_epoch_stop": false,
3921
+ "should_evaluate": false,
3922
+ "should_log": false,
3923
+ "should_save": true,
3924
+ "should_training_stop": false
3925
+ },
3926
+ "attributes": {}
3927
+ }
3928
+ },
3929
+ "total_flos": 0.0,
3930
+ "train_batch_size": 16,
3931
+ "trial_name": null,
3932
+ "trial_params": null
3933
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd1362576452dc1dede51df1a8532cf1318d832a39af9b44e8dcc8537827bc1
3
+ size 5688
checkpoint-400/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-3B-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": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
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": 24,
29
+ "num_hidden_layers": 28,
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-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47eccf2703540ab60bf1164d9bb23930f0e99c4affbb81b1234e9980f5037da
3
+ size 4998767360
checkpoint-400/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d627a80350b94d8620964f18915149ab72f9f796d594797ff386d1fa7e4ac1c1
3
+ size 4932808968
checkpoint-400/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d846957b44beccbd8bda123ca98b8c19581603a67b5f56f906f3e8f744fd39c
3
+ size 2919464544
checkpoint-400/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12851011584
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.norm.weight": "model-00003-of-00003.safetensors",
260
+ "score.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
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 sha256:1bd1362576452dc1dede51df1a8532cf1318d832a39af9b44e8dcc8537827bc1
3
+ size 5688
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tlrm/L32-3B-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": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
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": 24,
29
+ "num_hidden_layers": 28,
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-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47eccf2703540ab60bf1164d9bb23930f0e99c4affbb81b1234e9980f5037da
3
+ size 4998767360
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d627a80350b94d8620964f18915149ab72f9f796d594797ff386d1fa7e4ac1c1
3
+ size 4932808968
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d846957b44beccbd8bda123ca98b8c19581603a67b5f56f906f3e8f744fd39c
3
+ size 2919464544
model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12851011584
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.norm.weight": "model-00003-of-00003.safetensors",
260
+ "score.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
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
+ }