CodCodingCode commited on
Commit
622c937
·
verified ·
1 Parent(s): 11b358d

Upload folder using huggingface_hub

Browse files
Files changed (44) hide show
  1. .gitattributes +3 -0
  2. checkpoint-4500/config.json +36 -0
  3. checkpoint-4500/generation_config.json +9 -0
  4. checkpoint-4500/model-00001-of-00004.safetensors +3 -0
  5. checkpoint-4500/model-00002-of-00004.safetensors +3 -0
  6. checkpoint-4500/model-00003-of-00004.safetensors +3 -0
  7. checkpoint-4500/model-00004-of-00004.safetensors +3 -0
  8. checkpoint-4500/model.safetensors.index.json +298 -0
  9. checkpoint-4500/optimizer.pt +3 -0
  10. checkpoint-4500/rng_state.pth +3 -0
  11. checkpoint-4500/scheduler.pt +3 -0
  12. checkpoint-4500/special_tokens_map.json +17 -0
  13. checkpoint-4500/tokenizer.json +3 -0
  14. checkpoint-4500/tokenizer_config.json +2063 -0
  15. checkpoint-4500/trainer_state.json +3184 -0
  16. checkpoint-4500/training_args.bin +3 -0
  17. checkpoint-5000/config.json +36 -0
  18. checkpoint-5000/generation_config.json +9 -0
  19. checkpoint-5000/model-00001-of-00004.safetensors +3 -0
  20. checkpoint-5000/model-00002-of-00004.safetensors +3 -0
  21. checkpoint-5000/model-00003-of-00004.safetensors +3 -0
  22. checkpoint-5000/model-00004-of-00004.safetensors +3 -0
  23. checkpoint-5000/model.safetensors.index.json +298 -0
  24. checkpoint-5000/optimizer.pt +3 -0
  25. checkpoint-5000/rng_state.pth +3 -0
  26. checkpoint-5000/scheduler.pt +3 -0
  27. checkpoint-5000/special_tokens_map.json +17 -0
  28. checkpoint-5000/tokenizer.json +3 -0
  29. checkpoint-5000/tokenizer_config.json +2063 -0
  30. checkpoint-5000/trainer_state.json +3534 -0
  31. checkpoint-5000/training_args.bin +3 -0
  32. config.json +36 -0
  33. generation_config.json +9 -0
  34. model-00001-of-00004.safetensors +3 -0
  35. model-00002-of-00004.safetensors +3 -0
  36. model-00003-of-00004.safetensors +3 -0
  37. model-00004-of-00004.safetensors +3 -0
  38. model.safetensors.index.json +298 -0
  39. runs/Jun22_21-19-34_192-222-57-57/events.out.tfevents.1750627174.192-222-57-57.5985.0 +3 -0
  40. runs/Jun22_21-21-14_192-222-57-57/events.out.tfevents.1750627274.192-222-57-57.6587.0 +3 -0
  41. special_tokens_map.json +17 -0
  42. tokenizer.json +3 -0
  43. tokenizer_config.json +2063 -0
  44. training_args.bin +3 -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-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-4500/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128001,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.52.4",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
checkpoint-4500/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.52.4"
9
+ }
checkpoint-4500/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48bef05a7be33da9de95c4fa71d6fe107bf71a9ff01fe67df446b7c123dd81b
3
+ size 4976698672
checkpoint-4500/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0757f8d5bb6122e1d05e28e0631cb624a687fedc5cca9d1e177113d4a27edf72
3
+ size 4999802720
checkpoint-4500/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c068176a6cca5339871b3ee8d131607028c1ac18cd78af16ba9ddba6d234051c
3
+ size 4915916176
checkpoint-4500/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998114ae4fd9e44ceb7133310a1dcf2144fa8a61b6f6ebf8ae0e033a15ad9d52
3
+ size 1168138808
checkpoint-4500/model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
checkpoint-4500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d9faf260c4b29e7ba761e2d57c84766327861e45912593f4a67cfd915730221
3
+ size 32121300399
checkpoint-4500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
+ size 14645
checkpoint-4500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5241ecb74dba993ea087a99aaa9459d15659317e520880cabd15e499933ff94a
3
+ size 1465
checkpoint-4500/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
checkpoint-4500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-4500/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizer"
2063
+ }
checkpoint-4500/trainer_state.json ADDED
@@ -0,0 +1,3184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.1295465243998117,
6
+ "eval_steps": 500,
7
+ "global_step": 4500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002510591558135886,
14
+ "grad_norm": 2.53125,
15
+ "learning_rate": 1.9964e-05,
16
+ "loss": 1.2975,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.005021183116271772,
21
+ "grad_norm": 1.859375,
22
+ "learning_rate": 1.9924e-05,
23
+ "loss": 0.6792,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.007531774674407657,
28
+ "grad_norm": 1.921875,
29
+ "learning_rate": 1.9884e-05,
30
+ "loss": 0.6571,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.010042366232543544,
35
+ "grad_norm": 1.8046875,
36
+ "learning_rate": 1.9844000000000002e-05,
37
+ "loss": 0.6431,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.012552957790679428,
42
+ "grad_norm": 1.8984375,
43
+ "learning_rate": 1.9804000000000002e-05,
44
+ "loss": 0.6739,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.015063549348815314,
49
+ "grad_norm": 1.6953125,
50
+ "learning_rate": 1.9764000000000003e-05,
51
+ "loss": 0.6491,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0175741409069512,
56
+ "grad_norm": 1.6796875,
57
+ "learning_rate": 1.9724e-05,
58
+ "loss": 0.5911,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.020084732465087088,
63
+ "grad_norm": 2.0,
64
+ "learning_rate": 1.9684e-05,
65
+ "loss": 0.6117,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.022595324023222972,
70
+ "grad_norm": 1.734375,
71
+ "learning_rate": 1.9644e-05,
72
+ "loss": 0.5892,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.025105915581358856,
77
+ "grad_norm": 2.125,
78
+ "learning_rate": 1.9604e-05,
79
+ "loss": 0.5893,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.027616507139494744,
84
+ "grad_norm": 1.953125,
85
+ "learning_rate": 1.9564e-05,
86
+ "loss": 0.6412,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.03012709869763063,
91
+ "grad_norm": 1.796875,
92
+ "learning_rate": 1.9524e-05,
93
+ "loss": 0.5514,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.032637690255766516,
98
+ "grad_norm": 1.7421875,
99
+ "learning_rate": 1.9484000000000002e-05,
100
+ "loss": 0.6029,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.0351482818139024,
105
+ "grad_norm": 1.78125,
106
+ "learning_rate": 1.9444000000000002e-05,
107
+ "loss": 0.5723,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.037658873372038285,
112
+ "grad_norm": 1.9453125,
113
+ "learning_rate": 1.9404e-05,
114
+ "loss": 0.5721,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.040169464930174176,
119
+ "grad_norm": 2.0625,
120
+ "learning_rate": 1.9364e-05,
121
+ "loss": 0.5911,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.04268005648831006,
126
+ "grad_norm": 1.7265625,
127
+ "learning_rate": 1.9324e-05,
128
+ "loss": 0.5532,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.045190648046445944,
133
+ "grad_norm": 1.796875,
134
+ "learning_rate": 1.9284e-05,
135
+ "loss": 0.5836,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.04770123960458183,
140
+ "grad_norm": 1.890625,
141
+ "learning_rate": 1.9244000000000004e-05,
142
+ "loss": 0.5294,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.05021183116271771,
147
+ "grad_norm": 1.8125,
148
+ "learning_rate": 1.9204e-05,
149
+ "loss": 0.5675,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.052722422720853604,
154
+ "grad_norm": 1.421875,
155
+ "learning_rate": 1.9164e-05,
156
+ "loss": 0.4689,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.05523301427898949,
161
+ "grad_norm": 1.6484375,
162
+ "learning_rate": 1.9124000000000002e-05,
163
+ "loss": 0.5765,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.05774360583712537,
168
+ "grad_norm": 2.078125,
169
+ "learning_rate": 1.9084000000000002e-05,
170
+ "loss": 0.5369,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.06025419739526126,
175
+ "grad_norm": 1.65625,
176
+ "learning_rate": 1.9044000000000003e-05,
177
+ "loss": 0.4895,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.06276478895339714,
182
+ "grad_norm": 2.234375,
183
+ "learning_rate": 1.9004000000000003e-05,
184
+ "loss": 0.5191,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.06527538051153303,
189
+ "grad_norm": 1.90625,
190
+ "learning_rate": 1.8964000000000003e-05,
191
+ "loss": 0.5655,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.06778597206966891,
196
+ "grad_norm": 1.9921875,
197
+ "learning_rate": 1.8924000000000004e-05,
198
+ "loss": 0.5454,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.0702965636278048,
203
+ "grad_norm": 1.9765625,
204
+ "learning_rate": 1.8884e-05,
205
+ "loss": 0.5656,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.07280715518594069,
210
+ "grad_norm": 1.7890625,
211
+ "learning_rate": 1.8844e-05,
212
+ "loss": 0.481,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.07531774674407657,
217
+ "grad_norm": 1.6328125,
218
+ "learning_rate": 1.8804e-05,
219
+ "loss": 0.5365,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.07782833830221246,
224
+ "grad_norm": 1.7578125,
225
+ "learning_rate": 1.8764000000000002e-05,
226
+ "loss": 0.5271,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.08033892986034835,
231
+ "grad_norm": 1.65625,
232
+ "learning_rate": 1.8724000000000002e-05,
233
+ "loss": 0.5145,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.08284952141848423,
238
+ "grad_norm": 1.90625,
239
+ "learning_rate": 1.8684000000000003e-05,
240
+ "loss": 0.5129,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.08536011297662012,
245
+ "grad_norm": 1.6484375,
246
+ "learning_rate": 1.8644000000000003e-05,
247
+ "loss": 0.5539,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.087870704534756,
252
+ "grad_norm": 1.9453125,
253
+ "learning_rate": 1.8604000000000003e-05,
254
+ "loss": 0.5051,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.09038129609289189,
259
+ "grad_norm": 2.09375,
260
+ "learning_rate": 1.8564e-05,
261
+ "loss": 0.5034,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.09289188765102778,
266
+ "grad_norm": 1.625,
267
+ "learning_rate": 1.8524e-05,
268
+ "loss": 0.4867,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.09540247920916366,
273
+ "grad_norm": 1.71875,
274
+ "learning_rate": 1.8484e-05,
275
+ "loss": 0.5237,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.09791307076729955,
280
+ "grad_norm": 2.109375,
281
+ "learning_rate": 1.8444e-05,
282
+ "loss": 0.5305,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.10042366232543543,
287
+ "grad_norm": 1.859375,
288
+ "learning_rate": 1.8404000000000002e-05,
289
+ "loss": 0.498,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.10293425388357132,
294
+ "grad_norm": 1.921875,
295
+ "learning_rate": 1.8364000000000002e-05,
296
+ "loss": 0.512,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.10544484544170721,
301
+ "grad_norm": 2.046875,
302
+ "learning_rate": 1.8324000000000003e-05,
303
+ "loss": 0.4874,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.10795543699984309,
308
+ "grad_norm": 2.03125,
309
+ "learning_rate": 1.8284000000000003e-05,
310
+ "loss": 0.5123,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.11046602855797898,
315
+ "grad_norm": 1.78125,
316
+ "learning_rate": 1.8244e-05,
317
+ "loss": 0.4691,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.11297662011611485,
322
+ "grad_norm": 1.640625,
323
+ "learning_rate": 1.8204e-05,
324
+ "loss": 0.4485,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.11548721167425074,
329
+ "grad_norm": 1.7890625,
330
+ "learning_rate": 1.8164e-05,
331
+ "loss": 0.4647,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.11799780323238664,
336
+ "grad_norm": 1.7265625,
337
+ "learning_rate": 1.8124e-05,
338
+ "loss": 0.4518,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.12050839479052251,
343
+ "grad_norm": 2.34375,
344
+ "learning_rate": 1.8084e-05,
345
+ "loss": 0.4848,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.1230189863486584,
350
+ "grad_norm": 1.828125,
351
+ "learning_rate": 1.8044000000000002e-05,
352
+ "loss": 0.4624,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.12552957790679428,
357
+ "grad_norm": 2.3125,
358
+ "learning_rate": 1.8004000000000002e-05,
359
+ "loss": 0.489,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.1280401694649302,
364
+ "grad_norm": 1.828125,
365
+ "learning_rate": 1.7964000000000003e-05,
366
+ "loss": 0.4556,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.13055076102306606,
371
+ "grad_norm": 2.15625,
372
+ "learning_rate": 1.7924e-05,
373
+ "loss": 0.4726,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.13306135258120194,
378
+ "grad_norm": 2.03125,
379
+ "learning_rate": 1.7884e-05,
380
+ "loss": 0.4686,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.13557194413933782,
385
+ "grad_norm": 1.96875,
386
+ "learning_rate": 1.7844e-05,
387
+ "loss": 0.4228,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.13808253569747372,
392
+ "grad_norm": 2.125,
393
+ "learning_rate": 1.7804e-05,
394
+ "loss": 0.4523,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.1405931272556096,
399
+ "grad_norm": 1.9921875,
400
+ "learning_rate": 1.7764e-05,
401
+ "loss": 0.4235,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.14310371881374548,
406
+ "grad_norm": 1.875,
407
+ "learning_rate": 1.7724000000000002e-05,
408
+ "loss": 0.4474,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.14561431037188138,
413
+ "grad_norm": 2.0625,
414
+ "learning_rate": 1.7684000000000002e-05,
415
+ "loss": 0.4576,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.14812490193001726,
420
+ "grad_norm": 2.296875,
421
+ "learning_rate": 1.7644000000000003e-05,
422
+ "loss": 0.4345,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.15063549348815314,
427
+ "grad_norm": 2.0,
428
+ "learning_rate": 1.7604e-05,
429
+ "loss": 0.4124,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.15314608504628904,
434
+ "grad_norm": 1.9453125,
435
+ "learning_rate": 1.7564e-05,
436
+ "loss": 0.4457,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.15565667660442492,
441
+ "grad_norm": 2.125,
442
+ "learning_rate": 1.7524e-05,
443
+ "loss": 0.4569,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.1581672681625608,
448
+ "grad_norm": 1.8203125,
449
+ "learning_rate": 1.7484e-05,
450
+ "loss": 0.4065,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.1606778597206967,
455
+ "grad_norm": 1.9921875,
456
+ "learning_rate": 1.7444e-05,
457
+ "loss": 0.4231,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.16318845127883258,
462
+ "grad_norm": 2.328125,
463
+ "learning_rate": 1.7404e-05,
464
+ "loss": 0.4306,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.16569904283696846,
469
+ "grad_norm": 1.8359375,
470
+ "learning_rate": 1.7364000000000002e-05,
471
+ "loss": 0.4261,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.16820963439510433,
476
+ "grad_norm": 1.9140625,
477
+ "learning_rate": 1.7324000000000002e-05,
478
+ "loss": 0.3939,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.17072022595324024,
483
+ "grad_norm": 2.34375,
484
+ "learning_rate": 1.7284e-05,
485
+ "loss": 0.3979,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.17323081751137612,
490
+ "grad_norm": 2.0,
491
+ "learning_rate": 1.7244e-05,
492
+ "loss": 0.419,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.175741409069512,
497
+ "grad_norm": 2.078125,
498
+ "learning_rate": 1.7204e-05,
499
+ "loss": 0.4181,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.1782520006276479,
504
+ "grad_norm": 2.0625,
505
+ "learning_rate": 1.7164e-05,
506
+ "loss": 0.4345,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.18076259218578378,
511
+ "grad_norm": 2.078125,
512
+ "learning_rate": 1.7124e-05,
513
+ "loss": 0.436,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.18327318374391965,
518
+ "grad_norm": 2.15625,
519
+ "learning_rate": 1.7084e-05,
520
+ "loss": 0.3904,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.18578377530205556,
525
+ "grad_norm": 1.7265625,
526
+ "learning_rate": 1.7044e-05,
527
+ "loss": 0.3941,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.18829436686019144,
532
+ "grad_norm": 1.9453125,
533
+ "learning_rate": 1.7004000000000002e-05,
534
+ "loss": 0.403,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.19080495841832731,
539
+ "grad_norm": 2.09375,
540
+ "learning_rate": 1.6964e-05,
541
+ "loss": 0.397,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.1933155499764632,
546
+ "grad_norm": 2.078125,
547
+ "learning_rate": 1.6924e-05,
548
+ "loss": 0.3869,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.1958261415345991,
553
+ "grad_norm": 2.046875,
554
+ "learning_rate": 1.6884e-05,
555
+ "loss": 0.428,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.19833673309273497,
560
+ "grad_norm": 2.375,
561
+ "learning_rate": 1.6844e-05,
562
+ "loss": 0.4024,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.20084732465087085,
567
+ "grad_norm": 2.03125,
568
+ "learning_rate": 1.6804e-05,
569
+ "loss": 0.4061,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.20335791620900676,
574
+ "grad_norm": 2.171875,
575
+ "learning_rate": 1.6764e-05,
576
+ "loss": 0.3882,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.20586850776714263,
581
+ "grad_norm": 2.140625,
582
+ "learning_rate": 1.6724e-05,
583
+ "loss": 0.3973,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.2083790993252785,
588
+ "grad_norm": 2.203125,
589
+ "learning_rate": 1.6684e-05,
590
+ "loss": 0.3871,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.21088969088341442,
595
+ "grad_norm": 2.09375,
596
+ "learning_rate": 1.6644000000000002e-05,
597
+ "loss": 0.3666,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.2134002824415503,
602
+ "grad_norm": 2.046875,
603
+ "learning_rate": 1.6604000000000002e-05,
604
+ "loss": 0.3853,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.21591087399968617,
609
+ "grad_norm": 2.078125,
610
+ "learning_rate": 1.6564000000000003e-05,
611
+ "loss": 0.3772,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.21842146555782208,
616
+ "grad_norm": 2.3125,
617
+ "learning_rate": 1.6524000000000003e-05,
618
+ "loss": 0.3926,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.22093205711595795,
623
+ "grad_norm": 2.0625,
624
+ "learning_rate": 1.6484000000000003e-05,
625
+ "loss": 0.3824,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.22344264867409383,
630
+ "grad_norm": 2.078125,
631
+ "learning_rate": 1.6444000000000004e-05,
632
+ "loss": 0.3777,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.2259532402322297,
637
+ "grad_norm": 1.8984375,
638
+ "learning_rate": 1.6404e-05,
639
+ "loss": 0.3886,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.2284638317903656,
644
+ "grad_norm": 2.25,
645
+ "learning_rate": 1.6364e-05,
646
+ "loss": 0.4085,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.2309744233485015,
651
+ "grad_norm": 2.125,
652
+ "learning_rate": 1.6324e-05,
653
+ "loss": 0.3692,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.23348501490663737,
658
+ "grad_norm": 2.125,
659
+ "learning_rate": 1.6284000000000002e-05,
660
+ "loss": 0.3528,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.23599560646477327,
665
+ "grad_norm": 2.0625,
666
+ "learning_rate": 1.6244000000000002e-05,
667
+ "loss": 0.3708,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.23850619802290915,
672
+ "grad_norm": 1.9453125,
673
+ "learning_rate": 1.6204000000000003e-05,
674
+ "loss": 0.3625,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.24101678958104503,
679
+ "grad_norm": 2.140625,
680
+ "learning_rate": 1.6164000000000003e-05,
681
+ "loss": 0.3596,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.24352738113918093,
686
+ "grad_norm": 1.7265625,
687
+ "learning_rate": 1.6124000000000004e-05,
688
+ "loss": 0.3576,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.2460379726973168,
693
+ "grad_norm": 1.6015625,
694
+ "learning_rate": 1.6084e-05,
695
+ "loss": 0.3481,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.2485485642554527,
700
+ "grad_norm": 2.296875,
701
+ "learning_rate": 1.6044e-05,
702
+ "loss": 0.3899,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.25105915581358856,
707
+ "grad_norm": 2.0,
708
+ "learning_rate": 1.6004e-05,
709
+ "loss": 0.3838,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.25356974737172444,
714
+ "grad_norm": 1.78125,
715
+ "learning_rate": 1.5964e-05,
716
+ "loss": 0.3522,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.2560803389298604,
721
+ "grad_norm": 2.0625,
722
+ "learning_rate": 1.5924000000000002e-05,
723
+ "loss": 0.3277,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.25859093048799625,
728
+ "grad_norm": 2.109375,
729
+ "learning_rate": 1.5884000000000002e-05,
730
+ "loss": 0.3532,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.26110152204613213,
735
+ "grad_norm": 2.125,
736
+ "learning_rate": 1.5844000000000003e-05,
737
+ "loss": 0.3558,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.263612113604268,
742
+ "grad_norm": 2.375,
743
+ "learning_rate": 1.5804000000000003e-05,
744
+ "loss": 0.3617,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.2661227051624039,
749
+ "grad_norm": 2.421875,
750
+ "learning_rate": 1.5764e-05,
751
+ "loss": 0.3607,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.26863329672053976,
756
+ "grad_norm": 2.140625,
757
+ "learning_rate": 1.5724e-05,
758
+ "loss": 0.3948,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.27114388827867564,
763
+ "grad_norm": 1.8203125,
764
+ "learning_rate": 1.5684e-05,
765
+ "loss": 0.3776,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.27365447983681157,
770
+ "grad_norm": 2.15625,
771
+ "learning_rate": 1.5644e-05,
772
+ "loss": 0.3324,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.27616507139494745,
777
+ "grad_norm": 2.125,
778
+ "learning_rate": 1.5604000000000002e-05,
779
+ "loss": 0.3536,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.2786756629530833,
784
+ "grad_norm": 2.34375,
785
+ "learning_rate": 1.5564000000000002e-05,
786
+ "loss": 0.3591,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.2811862545112192,
791
+ "grad_norm": 2.015625,
792
+ "learning_rate": 1.5524000000000002e-05,
793
+ "loss": 0.3598,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.2836968460693551,
798
+ "grad_norm": 1.734375,
799
+ "learning_rate": 1.5484000000000003e-05,
800
+ "loss": 0.323,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.28620743762749096,
805
+ "grad_norm": 1.421875,
806
+ "learning_rate": 1.5444e-05,
807
+ "loss": 0.3496,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.2887180291856269,
812
+ "grad_norm": 2.1875,
813
+ "learning_rate": 1.5404e-05,
814
+ "loss": 0.3442,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.29122862074376277,
819
+ "grad_norm": 2.09375,
820
+ "learning_rate": 1.5364e-05,
821
+ "loss": 0.3392,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.29373921230189864,
826
+ "grad_norm": 1.9296875,
827
+ "learning_rate": 1.5324e-05,
828
+ "loss": 0.3689,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.2962498038600345,
833
+ "grad_norm": 2.296875,
834
+ "learning_rate": 1.5284e-05,
835
+ "loss": 0.347,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.2987603954181704,
840
+ "grad_norm": 1.96875,
841
+ "learning_rate": 1.5244000000000002e-05,
842
+ "loss": 0.3487,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.3012709869763063,
847
+ "grad_norm": 2.46875,
848
+ "learning_rate": 1.5204e-05,
849
+ "loss": 0.3182,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.30378157853444215,
854
+ "grad_norm": 2.109375,
855
+ "learning_rate": 1.5164e-05,
856
+ "loss": 0.3298,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.3062921700925781,
861
+ "grad_norm": 2.40625,
862
+ "learning_rate": 1.5124000000000001e-05,
863
+ "loss": 0.3299,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.30880276165071396,
868
+ "grad_norm": 2.53125,
869
+ "learning_rate": 1.5084000000000002e-05,
870
+ "loss": 0.3685,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.31131335320884984,
875
+ "grad_norm": 2.09375,
876
+ "learning_rate": 1.5044e-05,
877
+ "loss": 0.3321,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.3138239447669857,
882
+ "grad_norm": 1.9453125,
883
+ "learning_rate": 1.5004e-05,
884
+ "loss": 0.3397,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.3163345363251216,
889
+ "grad_norm": 1.8359375,
890
+ "learning_rate": 1.4964000000000001e-05,
891
+ "loss": 0.3296,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.3188451278832575,
896
+ "grad_norm": 1.875,
897
+ "learning_rate": 1.4924000000000001e-05,
898
+ "loss": 0.3122,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.3213557194413934,
903
+ "grad_norm": 2.0,
904
+ "learning_rate": 1.4884e-05,
905
+ "loss": 0.3325,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.3238663109995293,
910
+ "grad_norm": 1.9453125,
911
+ "learning_rate": 1.4844e-05,
912
+ "loss": 0.343,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.32637690255766516,
917
+ "grad_norm": 2.21875,
918
+ "learning_rate": 1.4804000000000001e-05,
919
+ "loss": 0.332,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.32888749411580104,
924
+ "grad_norm": 2.234375,
925
+ "learning_rate": 1.4764000000000001e-05,
926
+ "loss": 0.3303,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.3313980856739369,
931
+ "grad_norm": 2.25,
932
+ "learning_rate": 1.4724e-05,
933
+ "loss": 0.3302,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.3339086772320728,
938
+ "grad_norm": 1.6796875,
939
+ "learning_rate": 1.4684e-05,
940
+ "loss": 0.3304,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.33641926879020867,
945
+ "grad_norm": 1.7734375,
946
+ "learning_rate": 1.4644e-05,
947
+ "loss": 0.3247,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.3389298603483446,
952
+ "grad_norm": 1.9375,
953
+ "learning_rate": 1.4604000000000001e-05,
954
+ "loss": 0.324,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.3414404519064805,
959
+ "grad_norm": 1.5390625,
960
+ "learning_rate": 1.4564e-05,
961
+ "loss": 0.3353,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.34395104346461636,
966
+ "grad_norm": 2.03125,
967
+ "learning_rate": 1.4524e-05,
968
+ "loss": 0.321,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.34646163502275223,
973
+ "grad_norm": 2.5625,
974
+ "learning_rate": 1.4484e-05,
975
+ "loss": 0.3133,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.3489722265808881,
980
+ "grad_norm": 2.34375,
981
+ "learning_rate": 1.4444000000000001e-05,
982
+ "loss": 0.3516,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.351482818139024,
987
+ "grad_norm": 1.6015625,
988
+ "learning_rate": 1.4404e-05,
989
+ "loss": 0.3093,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.35399340969715987,
994
+ "grad_norm": 1.4765625,
995
+ "learning_rate": 1.4364e-05,
996
+ "loss": 0.3171,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.3565040012552958,
1001
+ "grad_norm": 2.0,
1002
+ "learning_rate": 1.4324e-05,
1003
+ "loss": 0.3321,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.3590145928134317,
1008
+ "grad_norm": 2.0625,
1009
+ "learning_rate": 1.4284e-05,
1010
+ "loss": 0.3111,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.36152518437156755,
1015
+ "grad_norm": 1.9375,
1016
+ "learning_rate": 1.4244000000000003e-05,
1017
+ "loss": 0.3403,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.36403577592970343,
1022
+ "grad_norm": 1.859375,
1023
+ "learning_rate": 1.4204000000000002e-05,
1024
+ "loss": 0.3174,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.3665463674878393,
1029
+ "grad_norm": 2.03125,
1030
+ "learning_rate": 1.4164000000000002e-05,
1031
+ "loss": 0.3332,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.3690569590459752,
1036
+ "grad_norm": 1.7734375,
1037
+ "learning_rate": 1.4124000000000002e-05,
1038
+ "loss": 0.3139,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.3715675506041111,
1043
+ "grad_norm": 1.9375,
1044
+ "learning_rate": 1.4084000000000003e-05,
1045
+ "loss": 0.328,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.374078142162247,
1050
+ "grad_norm": 2.015625,
1051
+ "learning_rate": 1.4044000000000001e-05,
1052
+ "loss": 0.3301,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.3765887337203829,
1057
+ "grad_norm": 2.6875,
1058
+ "learning_rate": 1.4004000000000002e-05,
1059
+ "loss": 0.3218,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.37909932527851875,
1064
+ "grad_norm": 2.453125,
1065
+ "learning_rate": 1.3964000000000002e-05,
1066
+ "loss": 0.3371,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.38160991683665463,
1071
+ "grad_norm": 1.515625,
1072
+ "learning_rate": 1.3924000000000003e-05,
1073
+ "loss": 0.3162,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.3841205083947905,
1078
+ "grad_norm": 1.9765625,
1079
+ "learning_rate": 1.3884000000000001e-05,
1080
+ "loss": 0.3092,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.3866310999529264,
1085
+ "grad_norm": 2.1875,
1086
+ "learning_rate": 1.3844000000000002e-05,
1087
+ "loss": 0.3224,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.3891416915110623,
1092
+ "grad_norm": 2.390625,
1093
+ "learning_rate": 1.3804000000000002e-05,
1094
+ "loss": 0.3027,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.3916522830691982,
1099
+ "grad_norm": 2.375,
1100
+ "learning_rate": 1.3764000000000002e-05,
1101
+ "loss": 0.3303,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.39416287462733407,
1106
+ "grad_norm": 1.828125,
1107
+ "learning_rate": 1.3724000000000001e-05,
1108
+ "loss": 0.3317,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.39667346618546995,
1113
+ "grad_norm": 1.9140625,
1114
+ "learning_rate": 1.3684000000000001e-05,
1115
+ "loss": 0.3195,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.3991840577436058,
1120
+ "grad_norm": 2.03125,
1121
+ "learning_rate": 1.3644000000000002e-05,
1122
+ "loss": 0.3185,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.4016946493017417,
1127
+ "grad_norm": 1.75,
1128
+ "learning_rate": 1.3604000000000002e-05,
1129
+ "loss": 0.2818,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.40420524085987763,
1134
+ "grad_norm": 1.8515625,
1135
+ "learning_rate": 1.3564000000000001e-05,
1136
+ "loss": 0.2996,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.4067158324180135,
1141
+ "grad_norm": 1.7578125,
1142
+ "learning_rate": 1.3524000000000001e-05,
1143
+ "loss": 0.3167,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.4092264239761494,
1148
+ "grad_norm": 2.25,
1149
+ "learning_rate": 1.3484000000000002e-05,
1150
+ "loss": 0.3257,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.41173701553428527,
1155
+ "grad_norm": 1.671875,
1156
+ "learning_rate": 1.3444000000000002e-05,
1157
+ "loss": 0.3145,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.41424760709242114,
1162
+ "grad_norm": 1.59375,
1163
+ "learning_rate": 1.3404e-05,
1164
+ "loss": 0.2936,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.416758198650557,
1169
+ "grad_norm": 1.953125,
1170
+ "learning_rate": 1.3364000000000001e-05,
1171
+ "loss": 0.3158,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.4192687902086929,
1176
+ "grad_norm": 1.53125,
1177
+ "learning_rate": 1.3324000000000002e-05,
1178
+ "loss": 0.3233,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.42177938176682883,
1183
+ "grad_norm": 2.28125,
1184
+ "learning_rate": 1.3284000000000002e-05,
1185
+ "loss": 0.2975,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.4242899733249647,
1190
+ "grad_norm": 2.046875,
1191
+ "learning_rate": 1.3244e-05,
1192
+ "loss": 0.3058,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.4268005648831006,
1197
+ "grad_norm": 2.15625,
1198
+ "learning_rate": 1.3204000000000001e-05,
1199
+ "loss": 0.3107,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.42931115644123646,
1204
+ "grad_norm": 1.8203125,
1205
+ "learning_rate": 1.3164000000000001e-05,
1206
+ "loss": 0.3096,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.43182174799937234,
1211
+ "grad_norm": 1.3828125,
1212
+ "learning_rate": 1.3124000000000002e-05,
1213
+ "loss": 0.3052,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.4343323395575082,
1218
+ "grad_norm": 1.8515625,
1219
+ "learning_rate": 1.3084e-05,
1220
+ "loss": 0.3029,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.43684293111564415,
1225
+ "grad_norm": 1.8203125,
1226
+ "learning_rate": 1.3044e-05,
1227
+ "loss": 0.3147,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.43935352267378003,
1232
+ "grad_norm": 1.984375,
1233
+ "learning_rate": 1.3004000000000001e-05,
1234
+ "loss": 0.3053,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.4418641142319159,
1239
+ "grad_norm": 1.953125,
1240
+ "learning_rate": 1.2964000000000002e-05,
1241
+ "loss": 0.2913,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.4443747057900518,
1246
+ "grad_norm": 1.8515625,
1247
+ "learning_rate": 1.2924e-05,
1248
+ "loss": 0.2916,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.44688529734818766,
1253
+ "grad_norm": 2.046875,
1254
+ "learning_rate": 1.2884e-05,
1255
+ "loss": 0.3159,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.44939588890632354,
1260
+ "grad_norm": 1.90625,
1261
+ "learning_rate": 1.2844000000000001e-05,
1262
+ "loss": 0.2987,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.4519064804644594,
1267
+ "grad_norm": 1.953125,
1268
+ "learning_rate": 1.2804000000000001e-05,
1269
+ "loss": 0.3136,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.45441707202259535,
1274
+ "grad_norm": 1.6015625,
1275
+ "learning_rate": 1.2764e-05,
1276
+ "loss": 0.3038,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.4569276635807312,
1281
+ "grad_norm": 2.0,
1282
+ "learning_rate": 1.2724e-05,
1283
+ "loss": 0.2916,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.4594382551388671,
1288
+ "grad_norm": 1.9765625,
1289
+ "learning_rate": 1.2684000000000001e-05,
1290
+ "loss": 0.3113,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.461948846697003,
1295
+ "grad_norm": 1.5625,
1296
+ "learning_rate": 1.2644000000000001e-05,
1297
+ "loss": 0.2728,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.46445943825513886,
1302
+ "grad_norm": 1.9296875,
1303
+ "learning_rate": 1.2604e-05,
1304
+ "loss": 0.2868,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.46697002981327473,
1309
+ "grad_norm": 2.140625,
1310
+ "learning_rate": 1.2564e-05,
1311
+ "loss": 0.289,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.4694806213714106,
1316
+ "grad_norm": 1.4921875,
1317
+ "learning_rate": 1.2524e-05,
1318
+ "loss": 0.2881,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.47199121292954654,
1323
+ "grad_norm": 1.8984375,
1324
+ "learning_rate": 1.2484000000000001e-05,
1325
+ "loss": 0.2803,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.4745018044876824,
1330
+ "grad_norm": 1.9375,
1331
+ "learning_rate": 1.2444e-05,
1332
+ "loss": 0.2785,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.4770123960458183,
1337
+ "grad_norm": 1.71875,
1338
+ "learning_rate": 1.2404e-05,
1339
+ "loss": 0.2976,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.4795229876039542,
1344
+ "grad_norm": 1.9296875,
1345
+ "learning_rate": 1.2364e-05,
1346
+ "loss": 0.2737,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.48203357916209005,
1351
+ "grad_norm": 1.7421875,
1352
+ "learning_rate": 1.2324000000000001e-05,
1353
+ "loss": 0.3237,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.48454417072022593,
1358
+ "grad_norm": 1.859375,
1359
+ "learning_rate": 1.2284e-05,
1360
+ "loss": 0.297,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.48705476227836186,
1365
+ "grad_norm": 2.046875,
1366
+ "learning_rate": 1.2244e-05,
1367
+ "loss": 0.2745,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.48956535383649774,
1372
+ "grad_norm": 2.1875,
1373
+ "learning_rate": 1.2204e-05,
1374
+ "loss": 0.3059,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.4920759453946336,
1379
+ "grad_norm": 2.359375,
1380
+ "learning_rate": 1.2164e-05,
1381
+ "loss": 0.2876,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.4945865369527695,
1386
+ "grad_norm": 2.6875,
1387
+ "learning_rate": 1.2124e-05,
1388
+ "loss": 0.2801,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.4970971285109054,
1393
+ "grad_norm": 1.921875,
1394
+ "learning_rate": 1.2084e-05,
1395
+ "loss": 0.2971,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.49960772006904125,
1400
+ "grad_norm": 1.6484375,
1401
+ "learning_rate": 1.2044e-05,
1402
+ "loss": 0.2979,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.5021183116271771,
1407
+ "grad_norm": 1.9296875,
1408
+ "learning_rate": 1.2004e-05,
1409
+ "loss": 0.306,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.5046289031853131,
1414
+ "grad_norm": 1.5859375,
1415
+ "learning_rate": 1.1964e-05,
1416
+ "loss": 0.2975,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.5071394947434489,
1421
+ "grad_norm": 1.9296875,
1422
+ "learning_rate": 1.1924e-05,
1423
+ "loss": 0.2771,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.5096500863015848,
1428
+ "grad_norm": 2.265625,
1429
+ "learning_rate": 1.1884e-05,
1430
+ "loss": 0.2903,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.5121606778597207,
1435
+ "grad_norm": 1.7109375,
1436
+ "learning_rate": 1.1844e-05,
1437
+ "loss": 0.2808,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.5146712694178566,
1442
+ "grad_norm": 1.7890625,
1443
+ "learning_rate": 1.1803999999999999e-05,
1444
+ "loss": 0.2856,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.5171818609759925,
1449
+ "grad_norm": 1.6796875,
1450
+ "learning_rate": 1.1764e-05,
1451
+ "loss": 0.2868,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.5196924525341283,
1456
+ "grad_norm": 1.7109375,
1457
+ "learning_rate": 1.1724000000000002e-05,
1458
+ "loss": 0.2973,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.5222030440922643,
1463
+ "grad_norm": 1.8828125,
1464
+ "learning_rate": 1.1684000000000002e-05,
1465
+ "loss": 0.3097,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.5247136356504001,
1470
+ "grad_norm": 1.6953125,
1471
+ "learning_rate": 1.1644000000000002e-05,
1472
+ "loss": 0.2731,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.527224227208536,
1477
+ "grad_norm": 2.0625,
1478
+ "learning_rate": 1.1604000000000003e-05,
1479
+ "loss": 0.2849,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.5297348187666719,
1484
+ "grad_norm": 2.203125,
1485
+ "learning_rate": 1.1564000000000001e-05,
1486
+ "loss": 0.2949,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.5322454103248078,
1491
+ "grad_norm": 2.203125,
1492
+ "learning_rate": 1.1524000000000002e-05,
1493
+ "loss": 0.3049,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.5347560018829437,
1498
+ "grad_norm": 1.7421875,
1499
+ "learning_rate": 1.1484000000000002e-05,
1500
+ "loss": 0.2851,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.5372665934410795,
1505
+ "grad_norm": 1.84375,
1506
+ "learning_rate": 1.1444000000000003e-05,
1507
+ "loss": 0.2919,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.5397771849992155,
1512
+ "grad_norm": 1.765625,
1513
+ "learning_rate": 1.1404000000000001e-05,
1514
+ "loss": 0.2967,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.5422877765573513,
1519
+ "grad_norm": 1.5546875,
1520
+ "learning_rate": 1.1364000000000002e-05,
1521
+ "loss": 0.2801,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.5447983681154872,
1526
+ "grad_norm": 2.0,
1527
+ "learning_rate": 1.1324000000000002e-05,
1528
+ "loss": 0.3012,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.5473089596736231,
1533
+ "grad_norm": 1.8984375,
1534
+ "learning_rate": 1.1284000000000002e-05,
1535
+ "loss": 0.2925,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.549819551231759,
1540
+ "grad_norm": 1.609375,
1541
+ "learning_rate": 1.1244000000000001e-05,
1542
+ "loss": 0.2954,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.5523301427898949,
1547
+ "grad_norm": 1.734375,
1548
+ "learning_rate": 1.1204000000000001e-05,
1549
+ "loss": 0.2799,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.5548407343480307,
1554
+ "grad_norm": 1.515625,
1555
+ "learning_rate": 1.1164000000000002e-05,
1556
+ "loss": 0.2704,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.5573513259061667,
1561
+ "grad_norm": 1.6953125,
1562
+ "learning_rate": 1.1124000000000002e-05,
1563
+ "loss": 0.2876,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.5598619174643025,
1568
+ "grad_norm": 1.7421875,
1569
+ "learning_rate": 1.1084000000000001e-05,
1570
+ "loss": 0.2633,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.5623725090224384,
1575
+ "grad_norm": 1.796875,
1576
+ "learning_rate": 1.1044000000000001e-05,
1577
+ "loss": 0.2867,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.5648831005805743,
1582
+ "grad_norm": 1.4609375,
1583
+ "learning_rate": 1.1004000000000002e-05,
1584
+ "loss": 0.2702,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.5673936921387102,
1589
+ "grad_norm": 1.828125,
1590
+ "learning_rate": 1.0964000000000002e-05,
1591
+ "loss": 0.2852,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.5699042836968461,
1596
+ "grad_norm": 1.703125,
1597
+ "learning_rate": 1.0924e-05,
1598
+ "loss": 0.2746,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.5724148752549819,
1603
+ "grad_norm": 1.90625,
1604
+ "learning_rate": 1.0884000000000001e-05,
1605
+ "loss": 0.2932,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.5749254668131178,
1610
+ "grad_norm": 1.84375,
1611
+ "learning_rate": 1.0844000000000002e-05,
1612
+ "loss": 0.2903,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.5774360583712538,
1617
+ "grad_norm": 2.15625,
1618
+ "learning_rate": 1.0804000000000002e-05,
1619
+ "loss": 0.2851,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.5799466499293896,
1624
+ "grad_norm": 2.0625,
1625
+ "learning_rate": 1.0764e-05,
1626
+ "loss": 0.2923,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.5824572414875255,
1631
+ "grad_norm": 2.109375,
1632
+ "learning_rate": 1.0724000000000001e-05,
1633
+ "loss": 0.3003,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.5849678330456614,
1638
+ "grad_norm": 2.046875,
1639
+ "learning_rate": 1.0684000000000001e-05,
1640
+ "loss": 0.291,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.5874784246037973,
1645
+ "grad_norm": 1.8828125,
1646
+ "learning_rate": 1.0644000000000002e-05,
1647
+ "loss": 0.2787,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.5899890161619331,
1652
+ "grad_norm": 1.8203125,
1653
+ "learning_rate": 1.0604e-05,
1654
+ "loss": 0.2764,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.592499607720069,
1659
+ "grad_norm": 1.65625,
1660
+ "learning_rate": 1.0564e-05,
1661
+ "loss": 0.2842,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.595010199278205,
1666
+ "grad_norm": 1.78125,
1667
+ "learning_rate": 1.0524000000000001e-05,
1668
+ "loss": 0.2922,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.5975207908363408,
1673
+ "grad_norm": 1.5625,
1674
+ "learning_rate": 1.0484000000000002e-05,
1675
+ "loss": 0.283,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.6000313823944767,
1680
+ "grad_norm": 1.5703125,
1681
+ "learning_rate": 1.0444e-05,
1682
+ "loss": 0.2796,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.6025419739526126,
1687
+ "grad_norm": 1.96875,
1688
+ "learning_rate": 1.0404e-05,
1689
+ "loss": 0.2828,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.6050525655107485,
1694
+ "grad_norm": 1.5703125,
1695
+ "learning_rate": 1.0364000000000001e-05,
1696
+ "loss": 0.2866,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.6075631570688843,
1701
+ "grad_norm": 2.109375,
1702
+ "learning_rate": 1.0324000000000001e-05,
1703
+ "loss": 0.2836,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.6100737486270202,
1708
+ "grad_norm": 1.875,
1709
+ "learning_rate": 1.0284e-05,
1710
+ "loss": 0.3037,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.6125843401851562,
1715
+ "grad_norm": 2.203125,
1716
+ "learning_rate": 1.0244e-05,
1717
+ "loss": 0.2774,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.615094931743292,
1722
+ "grad_norm": 1.8671875,
1723
+ "learning_rate": 1.0204000000000001e-05,
1724
+ "loss": 0.2922,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.6176055233014279,
1729
+ "grad_norm": 1.7109375,
1730
+ "learning_rate": 1.0164000000000001e-05,
1731
+ "loss": 0.283,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.6201161148595637,
1736
+ "grad_norm": 1.9453125,
1737
+ "learning_rate": 1.0124e-05,
1738
+ "loss": 0.2725,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.6226267064176997,
1743
+ "grad_norm": 1.6875,
1744
+ "learning_rate": 1.0084e-05,
1745
+ "loss": 0.2749,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.6251372979758355,
1750
+ "grad_norm": 1.703125,
1751
+ "learning_rate": 1.0044e-05,
1752
+ "loss": 0.2823,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.6276478895339714,
1757
+ "grad_norm": 1.9296875,
1758
+ "learning_rate": 1.0004000000000001e-05,
1759
+ "loss": 0.281,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.6301584810921074,
1764
+ "grad_norm": 1.9140625,
1765
+ "learning_rate": 9.964e-06,
1766
+ "loss": 0.2856,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.6326690726502432,
1771
+ "grad_norm": 1.4921875,
1772
+ "learning_rate": 9.924e-06,
1773
+ "loss": 0.28,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.6351796642083791,
1778
+ "grad_norm": 1.53125,
1779
+ "learning_rate": 9.884e-06,
1780
+ "loss": 0.267,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.637690255766515,
1785
+ "grad_norm": 1.5703125,
1786
+ "learning_rate": 9.844000000000001e-06,
1787
+ "loss": 0.2563,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.6402008473246509,
1792
+ "grad_norm": 1.46875,
1793
+ "learning_rate": 9.804000000000001e-06,
1794
+ "loss": 0.2911,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.6427114388827868,
1799
+ "grad_norm": 2.46875,
1800
+ "learning_rate": 9.764000000000002e-06,
1801
+ "loss": 0.2897,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.6452220304409226,
1806
+ "grad_norm": 1.90625,
1807
+ "learning_rate": 9.724e-06,
1808
+ "loss": 0.2975,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.6477326219990586,
1813
+ "grad_norm": 1.890625,
1814
+ "learning_rate": 9.684e-06,
1815
+ "loss": 0.2722,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.6502432135571944,
1820
+ "grad_norm": 1.6015625,
1821
+ "learning_rate": 9.644000000000001e-06,
1822
+ "loss": 0.2787,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.6527538051153303,
1827
+ "grad_norm": 2.046875,
1828
+ "learning_rate": 9.604000000000002e-06,
1829
+ "loss": 0.2822,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 0.6552643966734661,
1834
+ "grad_norm": 1.9296875,
1835
+ "learning_rate": 9.564e-06,
1836
+ "loss": 0.2903,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 0.6577749882316021,
1841
+ "grad_norm": 1.78125,
1842
+ "learning_rate": 9.524e-06,
1843
+ "loss": 0.2693,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 0.660285579789738,
1848
+ "grad_norm": 1.46875,
1849
+ "learning_rate": 9.484000000000001e-06,
1850
+ "loss": 0.2768,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 0.6627961713478738,
1855
+ "grad_norm": 1.734375,
1856
+ "learning_rate": 9.444000000000001e-06,
1857
+ "loss": 0.2707,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 0.6653067629060098,
1862
+ "grad_norm": 1.5703125,
1863
+ "learning_rate": 9.404e-06,
1864
+ "loss": 0.2791,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 0.6678173544641456,
1869
+ "grad_norm": 1.703125,
1870
+ "learning_rate": 9.364e-06,
1871
+ "loss": 0.2924,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 0.6703279460222815,
1876
+ "grad_norm": 1.9296875,
1877
+ "learning_rate": 9.324000000000001e-06,
1878
+ "loss": 0.2875,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 0.6728385375804173,
1883
+ "grad_norm": 1.78125,
1884
+ "learning_rate": 9.284000000000001e-06,
1885
+ "loss": 0.2602,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 0.6753491291385533,
1890
+ "grad_norm": 1.6875,
1891
+ "learning_rate": 9.244e-06,
1892
+ "loss": 0.2924,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 0.6778597206966892,
1897
+ "grad_norm": 1.578125,
1898
+ "learning_rate": 9.204e-06,
1899
+ "loss": 0.2841,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 0.680370312254825,
1904
+ "grad_norm": 1.390625,
1905
+ "learning_rate": 9.164e-06,
1906
+ "loss": 0.2745,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 0.682880903812961,
1911
+ "grad_norm": 2.28125,
1912
+ "learning_rate": 9.124000000000001e-06,
1913
+ "loss": 0.2876,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 0.6853914953710968,
1918
+ "grad_norm": 1.546875,
1919
+ "learning_rate": 9.084e-06,
1920
+ "loss": 0.2549,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 0.6879020869292327,
1925
+ "grad_norm": 1.3515625,
1926
+ "learning_rate": 9.044e-06,
1927
+ "loss": 0.2512,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 0.6904126784873685,
1932
+ "grad_norm": 2.203125,
1933
+ "learning_rate": 9.004e-06,
1934
+ "loss": 0.2686,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 0.6929232700455045,
1939
+ "grad_norm": 1.6484375,
1940
+ "learning_rate": 8.964000000000001e-06,
1941
+ "loss": 0.2714,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 0.6954338616036404,
1946
+ "grad_norm": 1.6796875,
1947
+ "learning_rate": 8.924e-06,
1948
+ "loss": 0.275,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 0.6979444531617762,
1953
+ "grad_norm": 1.8359375,
1954
+ "learning_rate": 8.884e-06,
1955
+ "loss": 0.2631,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 0.7004550447199122,
1960
+ "grad_norm": 1.3828125,
1961
+ "learning_rate": 8.844e-06,
1962
+ "loss": 0.2639,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 0.702965636278048,
1967
+ "grad_norm": 1.59375,
1968
+ "learning_rate": 8.804e-06,
1969
+ "loss": 0.2755,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 0.7054762278361839,
1974
+ "grad_norm": 1.8828125,
1975
+ "learning_rate": 8.764e-06,
1976
+ "loss": 0.282,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 0.7079868193943197,
1981
+ "grad_norm": 1.9140625,
1982
+ "learning_rate": 8.724e-06,
1983
+ "loss": 0.2672,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 0.7104974109524557,
1988
+ "grad_norm": 1.5859375,
1989
+ "learning_rate": 8.684e-06,
1990
+ "loss": 0.2663,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 0.7130080025105916,
1995
+ "grad_norm": 1.75,
1996
+ "learning_rate": 8.644e-06,
1997
+ "loss": 0.263,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 0.7155185940687274,
2002
+ "grad_norm": 1.9765625,
2003
+ "learning_rate": 8.604000000000001e-06,
2004
+ "loss": 0.276,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 0.7180291856268634,
2009
+ "grad_norm": 1.5078125,
2010
+ "learning_rate": 8.564000000000001e-06,
2011
+ "loss": 0.2622,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 0.7205397771849992,
2016
+ "grad_norm": 1.890625,
2017
+ "learning_rate": 8.524000000000002e-06,
2018
+ "loss": 0.2574,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 0.7230503687431351,
2023
+ "grad_norm": 1.65625,
2024
+ "learning_rate": 8.484e-06,
2025
+ "loss": 0.2586,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 0.725560960301271,
2030
+ "grad_norm": 2.234375,
2031
+ "learning_rate": 8.444e-06,
2032
+ "loss": 0.2694,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 0.7280715518594069,
2037
+ "grad_norm": 1.6953125,
2038
+ "learning_rate": 8.404000000000001e-06,
2039
+ "loss": 0.2817,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 0.7305821434175428,
2044
+ "grad_norm": 1.828125,
2045
+ "learning_rate": 8.364000000000002e-06,
2046
+ "loss": 0.2767,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 0.7330927349756786,
2051
+ "grad_norm": 1.40625,
2052
+ "learning_rate": 8.324e-06,
2053
+ "loss": 0.2547,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 0.7356033265338145,
2058
+ "grad_norm": 1.65625,
2059
+ "learning_rate": 8.284e-06,
2060
+ "loss": 0.2724,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 0.7381139180919504,
2065
+ "grad_norm": 2.078125,
2066
+ "learning_rate": 8.244000000000001e-06,
2067
+ "loss": 0.2972,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 0.7406245096500863,
2072
+ "grad_norm": 1.484375,
2073
+ "learning_rate": 8.204000000000001e-06,
2074
+ "loss": 0.2601,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 0.7431351012082222,
2079
+ "grad_norm": 2.015625,
2080
+ "learning_rate": 8.164e-06,
2081
+ "loss": 0.2552,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 0.7456456927663581,
2086
+ "grad_norm": 2.234375,
2087
+ "learning_rate": 8.124e-06,
2088
+ "loss": 0.274,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 0.748156284324494,
2093
+ "grad_norm": 1.8125,
2094
+ "learning_rate": 8.084000000000001e-06,
2095
+ "loss": 0.272,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 0.7506668758826298,
2100
+ "grad_norm": 1.6953125,
2101
+ "learning_rate": 8.044000000000001e-06,
2102
+ "loss": 0.2826,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 0.7531774674407657,
2107
+ "grad_norm": 1.7109375,
2108
+ "learning_rate": 8.004e-06,
2109
+ "loss": 0.2799,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 0.7556880589989016,
2114
+ "grad_norm": 1.640625,
2115
+ "learning_rate": 7.964e-06,
2116
+ "loss": 0.2919,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 0.7581986505570375,
2121
+ "grad_norm": 1.6953125,
2122
+ "learning_rate": 7.924e-06,
2123
+ "loss": 0.2634,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 0.7607092421151734,
2128
+ "grad_norm": 1.8515625,
2129
+ "learning_rate": 7.884000000000001e-06,
2130
+ "loss": 0.259,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 0.7632198336733093,
2135
+ "grad_norm": 1.7109375,
2136
+ "learning_rate": 7.844e-06,
2137
+ "loss": 0.2687,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 0.7657304252314452,
2142
+ "grad_norm": 1.6015625,
2143
+ "learning_rate": 7.804e-06,
2144
+ "loss": 0.2644,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 0.768241016789581,
2149
+ "grad_norm": 1.7421875,
2150
+ "learning_rate": 7.764e-06,
2151
+ "loss": 0.2541,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 0.7707516083477169,
2156
+ "grad_norm": 1.3203125,
2157
+ "learning_rate": 7.724000000000001e-06,
2158
+ "loss": 0.2555,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 0.7732621999058528,
2163
+ "grad_norm": 1.4609375,
2164
+ "learning_rate": 7.684e-06,
2165
+ "loss": 0.2745,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 0.7757727914639887,
2170
+ "grad_norm": 1.5546875,
2171
+ "learning_rate": 7.644e-06,
2172
+ "loss": 0.2924,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 0.7782833830221246,
2177
+ "grad_norm": 1.78125,
2178
+ "learning_rate": 7.604e-06,
2179
+ "loss": 0.2859,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 0.7807939745802605,
2184
+ "grad_norm": 1.75,
2185
+ "learning_rate": 7.564e-06,
2186
+ "loss": 0.2752,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 0.7833045661383964,
2191
+ "grad_norm": 1.6171875,
2192
+ "learning_rate": 7.524e-06,
2193
+ "loss": 0.2611,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 0.7858151576965322,
2198
+ "grad_norm": 1.578125,
2199
+ "learning_rate": 7.484e-06,
2200
+ "loss": 0.256,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 0.7883257492546681,
2205
+ "grad_norm": 1.578125,
2206
+ "learning_rate": 7.444e-06,
2207
+ "loss": 0.2707,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 0.790836340812804,
2212
+ "grad_norm": 1.765625,
2213
+ "learning_rate": 7.404e-06,
2214
+ "loss": 0.2711,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 0.7933469323709399,
2219
+ "grad_norm": 1.6484375,
2220
+ "learning_rate": 7.364000000000001e-06,
2221
+ "loss": 0.2588,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 0.7958575239290758,
2226
+ "grad_norm": 1.7890625,
2227
+ "learning_rate": 7.324000000000001e-06,
2228
+ "loss": 0.2618,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 0.7983681154872116,
2233
+ "grad_norm": 1.7734375,
2234
+ "learning_rate": 7.284000000000001e-06,
2235
+ "loss": 0.2755,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 0.8008787070453476,
2240
+ "grad_norm": 1.5703125,
2241
+ "learning_rate": 7.244000000000001e-06,
2242
+ "loss": 0.2727,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 0.8033892986034834,
2247
+ "grad_norm": 1.453125,
2248
+ "learning_rate": 7.204000000000001e-06,
2249
+ "loss": 0.2584,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 0.8058998901616193,
2254
+ "grad_norm": 1.7265625,
2255
+ "learning_rate": 7.164000000000001e-06,
2256
+ "loss": 0.2767,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 0.8084104817197553,
2261
+ "grad_norm": 1.5703125,
2262
+ "learning_rate": 7.124000000000001e-06,
2263
+ "loss": 0.2735,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 0.8109210732778911,
2268
+ "grad_norm": 1.8203125,
2269
+ "learning_rate": 7.084000000000001e-06,
2270
+ "loss": 0.277,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 0.813431664836027,
2275
+ "grad_norm": 1.8125,
2276
+ "learning_rate": 7.044000000000001e-06,
2277
+ "loss": 0.2743,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 0.8159422563941628,
2282
+ "grad_norm": 1.953125,
2283
+ "learning_rate": 7.004000000000001e-06,
2284
+ "loss": 0.2804,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 0.8184528479522988,
2289
+ "grad_norm": 1.71875,
2290
+ "learning_rate": 6.964000000000001e-06,
2291
+ "loss": 0.27,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 0.8209634395104346,
2296
+ "grad_norm": 1.578125,
2297
+ "learning_rate": 6.924000000000001e-06,
2298
+ "loss": 0.2672,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 0.8234740310685705,
2303
+ "grad_norm": 1.671875,
2304
+ "learning_rate": 6.8840000000000005e-06,
2305
+ "loss": 0.2787,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 0.8259846226267065,
2310
+ "grad_norm": 2.34375,
2311
+ "learning_rate": 6.844000000000001e-06,
2312
+ "loss": 0.2624,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 0.8284952141848423,
2317
+ "grad_norm": 1.9765625,
2318
+ "learning_rate": 6.804e-06,
2319
+ "loss": 0.2655,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 0.8310058057429782,
2324
+ "grad_norm": 1.65625,
2325
+ "learning_rate": 6.764000000000001e-06,
2326
+ "loss": 0.2677,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 0.833516397301114,
2331
+ "grad_norm": 2.015625,
2332
+ "learning_rate": 6.724e-06,
2333
+ "loss": 0.2655,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 0.83602698885925,
2338
+ "grad_norm": 1.5703125,
2339
+ "learning_rate": 6.684000000000001e-06,
2340
+ "loss": 0.27,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 0.8385375804173858,
2345
+ "grad_norm": 1.6015625,
2346
+ "learning_rate": 6.644e-06,
2347
+ "loss": 0.2503,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 0.8410481719755217,
2352
+ "grad_norm": 2.15625,
2353
+ "learning_rate": 6.604000000000001e-06,
2354
+ "loss": 0.2773,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 0.8435587635336577,
2359
+ "grad_norm": 1.609375,
2360
+ "learning_rate": 6.564e-06,
2361
+ "loss": 0.274,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 0.8460693550917935,
2366
+ "grad_norm": 1.578125,
2367
+ "learning_rate": 6.5240000000000006e-06,
2368
+ "loss": 0.2587,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 0.8485799466499294,
2373
+ "grad_norm": 1.828125,
2374
+ "learning_rate": 6.484e-06,
2375
+ "loss": 0.2699,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 0.8510905382080652,
2380
+ "grad_norm": 1.8125,
2381
+ "learning_rate": 6.4440000000000005e-06,
2382
+ "loss": 0.255,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 0.8536011297662012,
2387
+ "grad_norm": 1.65625,
2388
+ "learning_rate": 6.404e-06,
2389
+ "loss": 0.2532,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 0.856111721324337,
2394
+ "grad_norm": 1.6171875,
2395
+ "learning_rate": 6.364e-06,
2396
+ "loss": 0.2745,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 0.8586223128824729,
2401
+ "grad_norm": 1.7421875,
2402
+ "learning_rate": 6.324e-06,
2403
+ "loss": 0.2713,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 0.8611329044406089,
2408
+ "grad_norm": 1.6875,
2409
+ "learning_rate": 6.284e-06,
2410
+ "loss": 0.271,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 0.8636434959987447,
2415
+ "grad_norm": 1.4375,
2416
+ "learning_rate": 6.244e-06,
2417
+ "loss": 0.2485,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 0.8661540875568806,
2422
+ "grad_norm": 1.3203125,
2423
+ "learning_rate": 6.204e-06,
2424
+ "loss": 0.2648,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 0.8686646791150164,
2429
+ "grad_norm": 1.8203125,
2430
+ "learning_rate": 6.164e-06,
2431
+ "loss": 0.2683,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 0.8711752706731524,
2436
+ "grad_norm": 1.5703125,
2437
+ "learning_rate": 6.124000000000001e-06,
2438
+ "loss": 0.261,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 0.8736858622312883,
2443
+ "grad_norm": 1.4296875,
2444
+ "learning_rate": 6.084000000000001e-06,
2445
+ "loss": 0.2541,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 0.8761964537894241,
2450
+ "grad_norm": 1.859375,
2451
+ "learning_rate": 6.044000000000001e-06,
2452
+ "loss": 0.2607,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 0.8787070453475601,
2457
+ "grad_norm": 2.71875,
2458
+ "learning_rate": 6.004000000000001e-06,
2459
+ "loss": 0.2516,
2460
+ "step": 3500
2461
+ },
2462
+ {
2463
+ "epoch": 0.8812176369056959,
2464
+ "grad_norm": 1.578125,
2465
+ "learning_rate": 5.964000000000001e-06,
2466
+ "loss": 0.2678,
2467
+ "step": 3510
2468
+ },
2469
+ {
2470
+ "epoch": 0.8837282284638318,
2471
+ "grad_norm": 1.65625,
2472
+ "learning_rate": 5.924000000000001e-06,
2473
+ "loss": 0.2628,
2474
+ "step": 3520
2475
+ },
2476
+ {
2477
+ "epoch": 0.8862388200219676,
2478
+ "grad_norm": 1.5546875,
2479
+ "learning_rate": 5.884000000000001e-06,
2480
+ "loss": 0.2557,
2481
+ "step": 3530
2482
+ },
2483
+ {
2484
+ "epoch": 0.8887494115801036,
2485
+ "grad_norm": 1.8828125,
2486
+ "learning_rate": 5.844000000000001e-06,
2487
+ "loss": 0.2663,
2488
+ "step": 3540
2489
+ },
2490
+ {
2491
+ "epoch": 0.8912600031382395,
2492
+ "grad_norm": 2.125,
2493
+ "learning_rate": 5.804000000000001e-06,
2494
+ "loss": 0.2789,
2495
+ "step": 3550
2496
+ },
2497
+ {
2498
+ "epoch": 0.8937705946963753,
2499
+ "grad_norm": 1.78125,
2500
+ "learning_rate": 5.764000000000001e-06,
2501
+ "loss": 0.2646,
2502
+ "step": 3560
2503
+ },
2504
+ {
2505
+ "epoch": 0.8962811862545113,
2506
+ "grad_norm": 1.796875,
2507
+ "learning_rate": 5.724000000000001e-06,
2508
+ "loss": 0.2627,
2509
+ "step": 3570
2510
+ },
2511
+ {
2512
+ "epoch": 0.8987917778126471,
2513
+ "grad_norm": 1.609375,
2514
+ "learning_rate": 5.684000000000001e-06,
2515
+ "loss": 0.281,
2516
+ "step": 3580
2517
+ },
2518
+ {
2519
+ "epoch": 0.901302369370783,
2520
+ "grad_norm": 1.8515625,
2521
+ "learning_rate": 5.6440000000000005e-06,
2522
+ "loss": 0.2588,
2523
+ "step": 3590
2524
+ },
2525
+ {
2526
+ "epoch": 0.9038129609289188,
2527
+ "grad_norm": 1.9140625,
2528
+ "learning_rate": 5.604000000000001e-06,
2529
+ "loss": 0.267,
2530
+ "step": 3600
2531
+ },
2532
+ {
2533
+ "epoch": 0.9063235524870548,
2534
+ "grad_norm": 1.75,
2535
+ "learning_rate": 5.5640000000000004e-06,
2536
+ "loss": 0.2546,
2537
+ "step": 3610
2538
+ },
2539
+ {
2540
+ "epoch": 0.9088341440451907,
2541
+ "grad_norm": 1.484375,
2542
+ "learning_rate": 5.524000000000001e-06,
2543
+ "loss": 0.2607,
2544
+ "step": 3620
2545
+ },
2546
+ {
2547
+ "epoch": 0.9113447356033265,
2548
+ "grad_norm": 1.5703125,
2549
+ "learning_rate": 5.484e-06,
2550
+ "loss": 0.2804,
2551
+ "step": 3630
2552
+ },
2553
+ {
2554
+ "epoch": 0.9138553271614624,
2555
+ "grad_norm": 1.6328125,
2556
+ "learning_rate": 5.444000000000001e-06,
2557
+ "loss": 0.2595,
2558
+ "step": 3640
2559
+ },
2560
+ {
2561
+ "epoch": 0.9163659187195983,
2562
+ "grad_norm": 1.84375,
2563
+ "learning_rate": 5.404e-06,
2564
+ "loss": 0.2697,
2565
+ "step": 3650
2566
+ },
2567
+ {
2568
+ "epoch": 0.9188765102777342,
2569
+ "grad_norm": 1.5703125,
2570
+ "learning_rate": 5.364000000000001e-06,
2571
+ "loss": 0.2725,
2572
+ "step": 3660
2573
+ },
2574
+ {
2575
+ "epoch": 0.92138710183587,
2576
+ "grad_norm": 1.3984375,
2577
+ "learning_rate": 5.324e-06,
2578
+ "loss": 0.2613,
2579
+ "step": 3670
2580
+ },
2581
+ {
2582
+ "epoch": 0.923897693394006,
2583
+ "grad_norm": 1.8046875,
2584
+ "learning_rate": 5.2840000000000006e-06,
2585
+ "loss": 0.2708,
2586
+ "step": 3680
2587
+ },
2588
+ {
2589
+ "epoch": 0.9264082849521419,
2590
+ "grad_norm": 1.578125,
2591
+ "learning_rate": 5.244e-06,
2592
+ "loss": 0.2685,
2593
+ "step": 3690
2594
+ },
2595
+ {
2596
+ "epoch": 0.9289188765102777,
2597
+ "grad_norm": 1.8828125,
2598
+ "learning_rate": 5.2040000000000005e-06,
2599
+ "loss": 0.272,
2600
+ "step": 3700
2601
+ },
2602
+ {
2603
+ "epoch": 0.9314294680684136,
2604
+ "grad_norm": 1.6875,
2605
+ "learning_rate": 5.164e-06,
2606
+ "loss": 0.2801,
2607
+ "step": 3710
2608
+ },
2609
+ {
2610
+ "epoch": 0.9339400596265495,
2611
+ "grad_norm": 1.6015625,
2612
+ "learning_rate": 5.124e-06,
2613
+ "loss": 0.257,
2614
+ "step": 3720
2615
+ },
2616
+ {
2617
+ "epoch": 0.9364506511846854,
2618
+ "grad_norm": 1.5,
2619
+ "learning_rate": 5.084e-06,
2620
+ "loss": 0.2511,
2621
+ "step": 3730
2622
+ },
2623
+ {
2624
+ "epoch": 0.9389612427428212,
2625
+ "grad_norm": 1.5390625,
2626
+ "learning_rate": 5.044e-06,
2627
+ "loss": 0.2645,
2628
+ "step": 3740
2629
+ },
2630
+ {
2631
+ "epoch": 0.9414718343009572,
2632
+ "grad_norm": 1.6640625,
2633
+ "learning_rate": 5.004e-06,
2634
+ "loss": 0.2711,
2635
+ "step": 3750
2636
+ },
2637
+ {
2638
+ "epoch": 0.9439824258590931,
2639
+ "grad_norm": 1.7421875,
2640
+ "learning_rate": 4.964e-06,
2641
+ "loss": 0.2547,
2642
+ "step": 3760
2643
+ },
2644
+ {
2645
+ "epoch": 0.9464930174172289,
2646
+ "grad_norm": 1.7734375,
2647
+ "learning_rate": 4.924000000000001e-06,
2648
+ "loss": 0.2728,
2649
+ "step": 3770
2650
+ },
2651
+ {
2652
+ "epoch": 0.9490036089753648,
2653
+ "grad_norm": 1.421875,
2654
+ "learning_rate": 4.884e-06,
2655
+ "loss": 0.2666,
2656
+ "step": 3780
2657
+ },
2658
+ {
2659
+ "epoch": 0.9515142005335007,
2660
+ "grad_norm": 1.3515625,
2661
+ "learning_rate": 4.8440000000000005e-06,
2662
+ "loss": 0.2509,
2663
+ "step": 3790
2664
+ },
2665
+ {
2666
+ "epoch": 0.9540247920916366,
2667
+ "grad_norm": 1.6640625,
2668
+ "learning_rate": 4.804e-06,
2669
+ "loss": 0.2643,
2670
+ "step": 3800
2671
+ },
2672
+ {
2673
+ "epoch": 0.9565353836497725,
2674
+ "grad_norm": 1.5703125,
2675
+ "learning_rate": 4.7640000000000005e-06,
2676
+ "loss": 0.2568,
2677
+ "step": 3810
2678
+ },
2679
+ {
2680
+ "epoch": 0.9590459752079084,
2681
+ "grad_norm": 1.6796875,
2682
+ "learning_rate": 4.724e-06,
2683
+ "loss": 0.2673,
2684
+ "step": 3820
2685
+ },
2686
+ {
2687
+ "epoch": 0.9615565667660443,
2688
+ "grad_norm": 1.625,
2689
+ "learning_rate": 4.684e-06,
2690
+ "loss": 0.2622,
2691
+ "step": 3830
2692
+ },
2693
+ {
2694
+ "epoch": 0.9640671583241801,
2695
+ "grad_norm": 1.5625,
2696
+ "learning_rate": 4.644e-06,
2697
+ "loss": 0.2656,
2698
+ "step": 3840
2699
+ },
2700
+ {
2701
+ "epoch": 0.966577749882316,
2702
+ "grad_norm": 1.4609375,
2703
+ "learning_rate": 4.604e-06,
2704
+ "loss": 0.2581,
2705
+ "step": 3850
2706
+ },
2707
+ {
2708
+ "epoch": 0.9690883414404519,
2709
+ "grad_norm": 1.6875,
2710
+ "learning_rate": 4.564e-06,
2711
+ "loss": 0.2529,
2712
+ "step": 3860
2713
+ },
2714
+ {
2715
+ "epoch": 0.9715989329985878,
2716
+ "grad_norm": 1.8125,
2717
+ "learning_rate": 4.524e-06,
2718
+ "loss": 0.284,
2719
+ "step": 3870
2720
+ },
2721
+ {
2722
+ "epoch": 0.9741095245567237,
2723
+ "grad_norm": 2.484375,
2724
+ "learning_rate": 4.484000000000001e-06,
2725
+ "loss": 0.2596,
2726
+ "step": 3880
2727
+ },
2728
+ {
2729
+ "epoch": 0.9766201161148595,
2730
+ "grad_norm": 1.5390625,
2731
+ "learning_rate": 4.444e-06,
2732
+ "loss": 0.2759,
2733
+ "step": 3890
2734
+ },
2735
+ {
2736
+ "epoch": 0.9791307076729955,
2737
+ "grad_norm": 1.46875,
2738
+ "learning_rate": 4.4040000000000005e-06,
2739
+ "loss": 0.2563,
2740
+ "step": 3900
2741
+ },
2742
+ {
2743
+ "epoch": 0.9816412992311313,
2744
+ "grad_norm": 1.53125,
2745
+ "learning_rate": 4.364e-06,
2746
+ "loss": 0.25,
2747
+ "step": 3910
2748
+ },
2749
+ {
2750
+ "epoch": 0.9841518907892672,
2751
+ "grad_norm": 1.875,
2752
+ "learning_rate": 4.3240000000000004e-06,
2753
+ "loss": 0.2747,
2754
+ "step": 3920
2755
+ },
2756
+ {
2757
+ "epoch": 0.9866624823474031,
2758
+ "grad_norm": 1.6640625,
2759
+ "learning_rate": 4.284e-06,
2760
+ "loss": 0.2691,
2761
+ "step": 3930
2762
+ },
2763
+ {
2764
+ "epoch": 0.989173073905539,
2765
+ "grad_norm": 1.53125,
2766
+ "learning_rate": 4.244e-06,
2767
+ "loss": 0.2431,
2768
+ "step": 3940
2769
+ },
2770
+ {
2771
+ "epoch": 0.9916836654636749,
2772
+ "grad_norm": 1.46875,
2773
+ "learning_rate": 4.204e-06,
2774
+ "loss": 0.2422,
2775
+ "step": 3950
2776
+ },
2777
+ {
2778
+ "epoch": 0.9941942570218107,
2779
+ "grad_norm": 1.984375,
2780
+ "learning_rate": 4.164e-06,
2781
+ "loss": 0.2554,
2782
+ "step": 3960
2783
+ },
2784
+ {
2785
+ "epoch": 0.9967048485799467,
2786
+ "grad_norm": 1.671875,
2787
+ "learning_rate": 4.124e-06,
2788
+ "loss": 0.2659,
2789
+ "step": 3970
2790
+ },
2791
+ {
2792
+ "epoch": 0.9992154401380825,
2793
+ "grad_norm": 1.875,
2794
+ "learning_rate": 4.084e-06,
2795
+ "loss": 0.2563,
2796
+ "step": 3980
2797
+ },
2798
+ {
2799
+ "epoch": 1.0015063549348815,
2800
+ "grad_norm": 1.53125,
2801
+ "learning_rate": 4.044e-06,
2802
+ "loss": 0.2382,
2803
+ "step": 3990
2804
+ },
2805
+ {
2806
+ "epoch": 1.0040169464930173,
2807
+ "grad_norm": 1.34375,
2808
+ "learning_rate": 4.004e-06,
2809
+ "loss": 0.2385,
2810
+ "step": 4000
2811
+ },
2812
+ {
2813
+ "epoch": 1.0065275380511534,
2814
+ "grad_norm": 1.4921875,
2815
+ "learning_rate": 3.964e-06,
2816
+ "loss": 0.2354,
2817
+ "step": 4010
2818
+ },
2819
+ {
2820
+ "epoch": 1.0090381296092892,
2821
+ "grad_norm": 1.578125,
2822
+ "learning_rate": 3.924000000000001e-06,
2823
+ "loss": 0.2446,
2824
+ "step": 4020
2825
+ },
2826
+ {
2827
+ "epoch": 1.011548721167425,
2828
+ "grad_norm": 1.5703125,
2829
+ "learning_rate": 3.884e-06,
2830
+ "loss": 0.2355,
2831
+ "step": 4030
2832
+ },
2833
+ {
2834
+ "epoch": 1.014059312725561,
2835
+ "grad_norm": 1.4609375,
2836
+ "learning_rate": 3.844000000000001e-06,
2837
+ "loss": 0.2358,
2838
+ "step": 4040
2839
+ },
2840
+ {
2841
+ "epoch": 1.0165699042836969,
2842
+ "grad_norm": 1.6171875,
2843
+ "learning_rate": 3.8040000000000003e-06,
2844
+ "loss": 0.2387,
2845
+ "step": 4050
2846
+ },
2847
+ {
2848
+ "epoch": 1.0190804958418327,
2849
+ "grad_norm": 1.6015625,
2850
+ "learning_rate": 3.7640000000000003e-06,
2851
+ "loss": 0.2342,
2852
+ "step": 4060
2853
+ },
2854
+ {
2855
+ "epoch": 1.0215910873999685,
2856
+ "grad_norm": 1.5546875,
2857
+ "learning_rate": 3.7240000000000003e-06,
2858
+ "loss": 0.2381,
2859
+ "step": 4070
2860
+ },
2861
+ {
2862
+ "epoch": 1.0241016789581046,
2863
+ "grad_norm": 1.765625,
2864
+ "learning_rate": 3.6840000000000002e-06,
2865
+ "loss": 0.2392,
2866
+ "step": 4080
2867
+ },
2868
+ {
2869
+ "epoch": 1.0266122705162404,
2870
+ "grad_norm": 1.515625,
2871
+ "learning_rate": 3.644e-06,
2872
+ "loss": 0.2335,
2873
+ "step": 4090
2874
+ },
2875
+ {
2876
+ "epoch": 1.0291228620743762,
2877
+ "grad_norm": 1.453125,
2878
+ "learning_rate": 3.604e-06,
2879
+ "loss": 0.2544,
2880
+ "step": 4100
2881
+ },
2882
+ {
2883
+ "epoch": 1.0316334536325122,
2884
+ "grad_norm": 1.4296875,
2885
+ "learning_rate": 3.564e-06,
2886
+ "loss": 0.2254,
2887
+ "step": 4110
2888
+ },
2889
+ {
2890
+ "epoch": 1.034144045190648,
2891
+ "grad_norm": 1.7734375,
2892
+ "learning_rate": 3.524e-06,
2893
+ "loss": 0.2443,
2894
+ "step": 4120
2895
+ },
2896
+ {
2897
+ "epoch": 1.0366546367487839,
2898
+ "grad_norm": 1.6640625,
2899
+ "learning_rate": 3.484e-06,
2900
+ "loss": 0.2492,
2901
+ "step": 4130
2902
+ },
2903
+ {
2904
+ "epoch": 1.0391652283069197,
2905
+ "grad_norm": 1.4296875,
2906
+ "learning_rate": 3.444e-06,
2907
+ "loss": 0.2285,
2908
+ "step": 4140
2909
+ },
2910
+ {
2911
+ "epoch": 1.0416758198650558,
2912
+ "grad_norm": 1.7109375,
2913
+ "learning_rate": 3.404e-06,
2914
+ "loss": 0.2309,
2915
+ "step": 4150
2916
+ },
2917
+ {
2918
+ "epoch": 1.0441864114231916,
2919
+ "grad_norm": 1.78125,
2920
+ "learning_rate": 3.364e-06,
2921
+ "loss": 0.2477,
2922
+ "step": 4160
2923
+ },
2924
+ {
2925
+ "epoch": 1.0466970029813274,
2926
+ "grad_norm": 1.7265625,
2927
+ "learning_rate": 3.324e-06,
2928
+ "loss": 0.2395,
2929
+ "step": 4170
2930
+ },
2931
+ {
2932
+ "epoch": 1.0492075945394634,
2933
+ "grad_norm": 1.5234375,
2934
+ "learning_rate": 3.2840000000000007e-06,
2935
+ "loss": 0.2266,
2936
+ "step": 4180
2937
+ },
2938
+ {
2939
+ "epoch": 1.0517181860975993,
2940
+ "grad_norm": 2.046875,
2941
+ "learning_rate": 3.2440000000000006e-06,
2942
+ "loss": 0.2382,
2943
+ "step": 4190
2944
+ },
2945
+ {
2946
+ "epoch": 1.054228777655735,
2947
+ "grad_norm": 1.8125,
2948
+ "learning_rate": 3.2040000000000006e-06,
2949
+ "loss": 0.2315,
2950
+ "step": 4200
2951
+ },
2952
+ {
2953
+ "epoch": 1.056739369213871,
2954
+ "grad_norm": 1.7109375,
2955
+ "learning_rate": 3.1640000000000005e-06,
2956
+ "loss": 0.2399,
2957
+ "step": 4210
2958
+ },
2959
+ {
2960
+ "epoch": 1.059249960772007,
2961
+ "grad_norm": 1.5703125,
2962
+ "learning_rate": 3.1240000000000005e-06,
2963
+ "loss": 0.2287,
2964
+ "step": 4220
2965
+ },
2966
+ {
2967
+ "epoch": 1.0617605523301428,
2968
+ "grad_norm": 1.4453125,
2969
+ "learning_rate": 3.0840000000000005e-06,
2970
+ "loss": 0.2399,
2971
+ "step": 4230
2972
+ },
2973
+ {
2974
+ "epoch": 1.0642711438882786,
2975
+ "grad_norm": 1.6171875,
2976
+ "learning_rate": 3.0440000000000004e-06,
2977
+ "loss": 0.2334,
2978
+ "step": 4240
2979
+ },
2980
+ {
2981
+ "epoch": 1.0667817354464146,
2982
+ "grad_norm": 1.671875,
2983
+ "learning_rate": 3.0040000000000004e-06,
2984
+ "loss": 0.2324,
2985
+ "step": 4250
2986
+ },
2987
+ {
2988
+ "epoch": 1.0692923270045505,
2989
+ "grad_norm": 1.5859375,
2990
+ "learning_rate": 2.9640000000000003e-06,
2991
+ "loss": 0.231,
2992
+ "step": 4260
2993
+ },
2994
+ {
2995
+ "epoch": 1.0718029185626863,
2996
+ "grad_norm": 1.640625,
2997
+ "learning_rate": 2.9240000000000003e-06,
2998
+ "loss": 0.2465,
2999
+ "step": 4270
3000
+ },
3001
+ {
3002
+ "epoch": 1.074313510120822,
3003
+ "grad_norm": 1.796875,
3004
+ "learning_rate": 2.8840000000000003e-06,
3005
+ "loss": 0.2465,
3006
+ "step": 4280
3007
+ },
3008
+ {
3009
+ "epoch": 1.0768241016789581,
3010
+ "grad_norm": 1.4375,
3011
+ "learning_rate": 2.8440000000000002e-06,
3012
+ "loss": 0.2514,
3013
+ "step": 4290
3014
+ },
3015
+ {
3016
+ "epoch": 1.079334693237094,
3017
+ "grad_norm": 1.71875,
3018
+ "learning_rate": 2.804e-06,
3019
+ "loss": 0.2318,
3020
+ "step": 4300
3021
+ },
3022
+ {
3023
+ "epoch": 1.0818452847952298,
3024
+ "grad_norm": 1.5234375,
3025
+ "learning_rate": 2.764e-06,
3026
+ "loss": 0.2366,
3027
+ "step": 4310
3028
+ },
3029
+ {
3030
+ "epoch": 1.0843558763533658,
3031
+ "grad_norm": 1.46875,
3032
+ "learning_rate": 2.724e-06,
3033
+ "loss": 0.2328,
3034
+ "step": 4320
3035
+ },
3036
+ {
3037
+ "epoch": 1.0868664679115017,
3038
+ "grad_norm": 1.734375,
3039
+ "learning_rate": 2.6840000000000005e-06,
3040
+ "loss": 0.2566,
3041
+ "step": 4330
3042
+ },
3043
+ {
3044
+ "epoch": 1.0893770594696375,
3045
+ "grad_norm": 1.4296875,
3046
+ "learning_rate": 2.6440000000000004e-06,
3047
+ "loss": 0.2243,
3048
+ "step": 4340
3049
+ },
3050
+ {
3051
+ "epoch": 1.0918876510277735,
3052
+ "grad_norm": 1.703125,
3053
+ "learning_rate": 2.6040000000000004e-06,
3054
+ "loss": 0.2234,
3055
+ "step": 4350
3056
+ },
3057
+ {
3058
+ "epoch": 1.0943982425859093,
3059
+ "grad_norm": 1.7421875,
3060
+ "learning_rate": 2.5640000000000004e-06,
3061
+ "loss": 0.2287,
3062
+ "step": 4360
3063
+ },
3064
+ {
3065
+ "epoch": 1.0969088341440452,
3066
+ "grad_norm": 1.5703125,
3067
+ "learning_rate": 2.5240000000000003e-06,
3068
+ "loss": 0.2365,
3069
+ "step": 4370
3070
+ },
3071
+ {
3072
+ "epoch": 1.099419425702181,
3073
+ "grad_norm": 1.4296875,
3074
+ "learning_rate": 2.4840000000000003e-06,
3075
+ "loss": 0.2299,
3076
+ "step": 4380
3077
+ },
3078
+ {
3079
+ "epoch": 1.101930017260317,
3080
+ "grad_norm": 1.8359375,
3081
+ "learning_rate": 2.4440000000000002e-06,
3082
+ "loss": 0.24,
3083
+ "step": 4390
3084
+ },
3085
+ {
3086
+ "epoch": 1.1044406088184529,
3087
+ "grad_norm": 1.5703125,
3088
+ "learning_rate": 2.404e-06,
3089
+ "loss": 0.2292,
3090
+ "step": 4400
3091
+ },
3092
+ {
3093
+ "epoch": 1.1069512003765887,
3094
+ "grad_norm": 1.59375,
3095
+ "learning_rate": 2.364e-06,
3096
+ "loss": 0.2356,
3097
+ "step": 4410
3098
+ },
3099
+ {
3100
+ "epoch": 1.1094617919347247,
3101
+ "grad_norm": 1.8671875,
3102
+ "learning_rate": 2.324e-06,
3103
+ "loss": 0.2395,
3104
+ "step": 4420
3105
+ },
3106
+ {
3107
+ "epoch": 1.1119723834928605,
3108
+ "grad_norm": 1.7734375,
3109
+ "learning_rate": 2.284e-06,
3110
+ "loss": 0.2534,
3111
+ "step": 4430
3112
+ },
3113
+ {
3114
+ "epoch": 1.1144829750509964,
3115
+ "grad_norm": 1.6328125,
3116
+ "learning_rate": 2.244e-06,
3117
+ "loss": 0.2294,
3118
+ "step": 4440
3119
+ },
3120
+ {
3121
+ "epoch": 1.1169935666091322,
3122
+ "grad_norm": 1.6796875,
3123
+ "learning_rate": 2.2040000000000004e-06,
3124
+ "loss": 0.2428,
3125
+ "step": 4450
3126
+ },
3127
+ {
3128
+ "epoch": 1.1195041581672682,
3129
+ "grad_norm": 1.5,
3130
+ "learning_rate": 2.1640000000000004e-06,
3131
+ "loss": 0.2486,
3132
+ "step": 4460
3133
+ },
3134
+ {
3135
+ "epoch": 1.122014749725404,
3136
+ "grad_norm": 1.515625,
3137
+ "learning_rate": 2.1240000000000003e-06,
3138
+ "loss": 0.2428,
3139
+ "step": 4470
3140
+ },
3141
+ {
3142
+ "epoch": 1.1245253412835399,
3143
+ "grad_norm": 1.65625,
3144
+ "learning_rate": 2.0840000000000003e-06,
3145
+ "loss": 0.2438,
3146
+ "step": 4480
3147
+ },
3148
+ {
3149
+ "epoch": 1.127035932841676,
3150
+ "grad_norm": 1.796875,
3151
+ "learning_rate": 2.0440000000000003e-06,
3152
+ "loss": 0.2278,
3153
+ "step": 4490
3154
+ },
3155
+ {
3156
+ "epoch": 1.1295465243998117,
3157
+ "grad_norm": 1.640625,
3158
+ "learning_rate": 2.004e-06,
3159
+ "loss": 0.2306,
3160
+ "step": 4500
3161
+ }
3162
+ ],
3163
+ "logging_steps": 10,
3164
+ "max_steps": 5000,
3165
+ "num_input_tokens_seen": 0,
3166
+ "num_train_epochs": 2,
3167
+ "save_steps": 500,
3168
+ "stateful_callbacks": {
3169
+ "TrainerControl": {
3170
+ "args": {
3171
+ "should_epoch_stop": false,
3172
+ "should_evaluate": false,
3173
+ "should_log": false,
3174
+ "should_save": true,
3175
+ "should_training_stop": false
3176
+ },
3177
+ "attributes": {}
3178
+ }
3179
+ },
3180
+ "total_flos": 3.194052832115884e+18,
3181
+ "train_batch_size": 1,
3182
+ "trial_name": null,
3183
+ "trial_params": null
3184
+ }
checkpoint-4500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453a573b76b43963ddfc5159ef89ab0e258df03a82b42d345c3f13a661915b1f
3
+ size 5713
checkpoint-5000/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128001,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.52.4",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
checkpoint-5000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.52.4"
9
+ }
checkpoint-5000/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f3a42cf3e7cfda21946e76131d2b59ed98c6465cd74051c5f9693ed54c6aa4
3
+ size 4976698672
checkpoint-5000/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a81226bcdf2579911c160f4f39dbfbb92a4759fc7c2a7d27af55245bda8b13
3
+ size 4999802720
checkpoint-5000/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ffb7741da438a74a56dca55a4d9315aed10dcdf64bb10e1d2dac3232c8aa57e
3
+ size 4915916176
checkpoint-5000/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac46fce1898f637da07a978aade60c7bd8f839c126b4332c0d235fd7a01a7e1
3
+ size 1168138808
checkpoint-5000/model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9410f15a9948197563b55cff3a132c2300f7091efcb98635df5640753a7f43
3
+ size 32121300399
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
+ size 14645
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd8f1a4cffab56686fdade86404d8b871f35c88cd1eef5668969ab89bbd29a29
3
+ size 1465
checkpoint-5000/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
checkpoint-5000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-5000/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizer"
2063
+ }
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,3534 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.255076102306606,
6
+ "eval_steps": 500,
7
+ "global_step": 5000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002510591558135886,
14
+ "grad_norm": 2.53125,
15
+ "learning_rate": 1.9964e-05,
16
+ "loss": 1.2975,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.005021183116271772,
21
+ "grad_norm": 1.859375,
22
+ "learning_rate": 1.9924e-05,
23
+ "loss": 0.6792,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.007531774674407657,
28
+ "grad_norm": 1.921875,
29
+ "learning_rate": 1.9884e-05,
30
+ "loss": 0.6571,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.010042366232543544,
35
+ "grad_norm": 1.8046875,
36
+ "learning_rate": 1.9844000000000002e-05,
37
+ "loss": 0.6431,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.012552957790679428,
42
+ "grad_norm": 1.8984375,
43
+ "learning_rate": 1.9804000000000002e-05,
44
+ "loss": 0.6739,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.015063549348815314,
49
+ "grad_norm": 1.6953125,
50
+ "learning_rate": 1.9764000000000003e-05,
51
+ "loss": 0.6491,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0175741409069512,
56
+ "grad_norm": 1.6796875,
57
+ "learning_rate": 1.9724e-05,
58
+ "loss": 0.5911,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.020084732465087088,
63
+ "grad_norm": 2.0,
64
+ "learning_rate": 1.9684e-05,
65
+ "loss": 0.6117,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.022595324023222972,
70
+ "grad_norm": 1.734375,
71
+ "learning_rate": 1.9644e-05,
72
+ "loss": 0.5892,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.025105915581358856,
77
+ "grad_norm": 2.125,
78
+ "learning_rate": 1.9604e-05,
79
+ "loss": 0.5893,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.027616507139494744,
84
+ "grad_norm": 1.953125,
85
+ "learning_rate": 1.9564e-05,
86
+ "loss": 0.6412,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.03012709869763063,
91
+ "grad_norm": 1.796875,
92
+ "learning_rate": 1.9524e-05,
93
+ "loss": 0.5514,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.032637690255766516,
98
+ "grad_norm": 1.7421875,
99
+ "learning_rate": 1.9484000000000002e-05,
100
+ "loss": 0.6029,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.0351482818139024,
105
+ "grad_norm": 1.78125,
106
+ "learning_rate": 1.9444000000000002e-05,
107
+ "loss": 0.5723,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.037658873372038285,
112
+ "grad_norm": 1.9453125,
113
+ "learning_rate": 1.9404e-05,
114
+ "loss": 0.5721,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.040169464930174176,
119
+ "grad_norm": 2.0625,
120
+ "learning_rate": 1.9364e-05,
121
+ "loss": 0.5911,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.04268005648831006,
126
+ "grad_norm": 1.7265625,
127
+ "learning_rate": 1.9324e-05,
128
+ "loss": 0.5532,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.045190648046445944,
133
+ "grad_norm": 1.796875,
134
+ "learning_rate": 1.9284e-05,
135
+ "loss": 0.5836,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.04770123960458183,
140
+ "grad_norm": 1.890625,
141
+ "learning_rate": 1.9244000000000004e-05,
142
+ "loss": 0.5294,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.05021183116271771,
147
+ "grad_norm": 1.8125,
148
+ "learning_rate": 1.9204e-05,
149
+ "loss": 0.5675,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.052722422720853604,
154
+ "grad_norm": 1.421875,
155
+ "learning_rate": 1.9164e-05,
156
+ "loss": 0.4689,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.05523301427898949,
161
+ "grad_norm": 1.6484375,
162
+ "learning_rate": 1.9124000000000002e-05,
163
+ "loss": 0.5765,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.05774360583712537,
168
+ "grad_norm": 2.078125,
169
+ "learning_rate": 1.9084000000000002e-05,
170
+ "loss": 0.5369,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.06025419739526126,
175
+ "grad_norm": 1.65625,
176
+ "learning_rate": 1.9044000000000003e-05,
177
+ "loss": 0.4895,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.06276478895339714,
182
+ "grad_norm": 2.234375,
183
+ "learning_rate": 1.9004000000000003e-05,
184
+ "loss": 0.5191,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.06527538051153303,
189
+ "grad_norm": 1.90625,
190
+ "learning_rate": 1.8964000000000003e-05,
191
+ "loss": 0.5655,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.06778597206966891,
196
+ "grad_norm": 1.9921875,
197
+ "learning_rate": 1.8924000000000004e-05,
198
+ "loss": 0.5454,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.0702965636278048,
203
+ "grad_norm": 1.9765625,
204
+ "learning_rate": 1.8884e-05,
205
+ "loss": 0.5656,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.07280715518594069,
210
+ "grad_norm": 1.7890625,
211
+ "learning_rate": 1.8844e-05,
212
+ "loss": 0.481,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.07531774674407657,
217
+ "grad_norm": 1.6328125,
218
+ "learning_rate": 1.8804e-05,
219
+ "loss": 0.5365,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.07782833830221246,
224
+ "grad_norm": 1.7578125,
225
+ "learning_rate": 1.8764000000000002e-05,
226
+ "loss": 0.5271,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.08033892986034835,
231
+ "grad_norm": 1.65625,
232
+ "learning_rate": 1.8724000000000002e-05,
233
+ "loss": 0.5145,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.08284952141848423,
238
+ "grad_norm": 1.90625,
239
+ "learning_rate": 1.8684000000000003e-05,
240
+ "loss": 0.5129,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.08536011297662012,
245
+ "grad_norm": 1.6484375,
246
+ "learning_rate": 1.8644000000000003e-05,
247
+ "loss": 0.5539,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.087870704534756,
252
+ "grad_norm": 1.9453125,
253
+ "learning_rate": 1.8604000000000003e-05,
254
+ "loss": 0.5051,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.09038129609289189,
259
+ "grad_norm": 2.09375,
260
+ "learning_rate": 1.8564e-05,
261
+ "loss": 0.5034,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.09289188765102778,
266
+ "grad_norm": 1.625,
267
+ "learning_rate": 1.8524e-05,
268
+ "loss": 0.4867,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.09540247920916366,
273
+ "grad_norm": 1.71875,
274
+ "learning_rate": 1.8484e-05,
275
+ "loss": 0.5237,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.09791307076729955,
280
+ "grad_norm": 2.109375,
281
+ "learning_rate": 1.8444e-05,
282
+ "loss": 0.5305,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.10042366232543543,
287
+ "grad_norm": 1.859375,
288
+ "learning_rate": 1.8404000000000002e-05,
289
+ "loss": 0.498,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.10293425388357132,
294
+ "grad_norm": 1.921875,
295
+ "learning_rate": 1.8364000000000002e-05,
296
+ "loss": 0.512,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.10544484544170721,
301
+ "grad_norm": 2.046875,
302
+ "learning_rate": 1.8324000000000003e-05,
303
+ "loss": 0.4874,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.10795543699984309,
308
+ "grad_norm": 2.03125,
309
+ "learning_rate": 1.8284000000000003e-05,
310
+ "loss": 0.5123,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.11046602855797898,
315
+ "grad_norm": 1.78125,
316
+ "learning_rate": 1.8244e-05,
317
+ "loss": 0.4691,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.11297662011611485,
322
+ "grad_norm": 1.640625,
323
+ "learning_rate": 1.8204e-05,
324
+ "loss": 0.4485,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.11548721167425074,
329
+ "grad_norm": 1.7890625,
330
+ "learning_rate": 1.8164e-05,
331
+ "loss": 0.4647,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.11799780323238664,
336
+ "grad_norm": 1.7265625,
337
+ "learning_rate": 1.8124e-05,
338
+ "loss": 0.4518,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.12050839479052251,
343
+ "grad_norm": 2.34375,
344
+ "learning_rate": 1.8084e-05,
345
+ "loss": 0.4848,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.1230189863486584,
350
+ "grad_norm": 1.828125,
351
+ "learning_rate": 1.8044000000000002e-05,
352
+ "loss": 0.4624,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.12552957790679428,
357
+ "grad_norm": 2.3125,
358
+ "learning_rate": 1.8004000000000002e-05,
359
+ "loss": 0.489,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.1280401694649302,
364
+ "grad_norm": 1.828125,
365
+ "learning_rate": 1.7964000000000003e-05,
366
+ "loss": 0.4556,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.13055076102306606,
371
+ "grad_norm": 2.15625,
372
+ "learning_rate": 1.7924e-05,
373
+ "loss": 0.4726,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.13306135258120194,
378
+ "grad_norm": 2.03125,
379
+ "learning_rate": 1.7884e-05,
380
+ "loss": 0.4686,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.13557194413933782,
385
+ "grad_norm": 1.96875,
386
+ "learning_rate": 1.7844e-05,
387
+ "loss": 0.4228,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.13808253569747372,
392
+ "grad_norm": 2.125,
393
+ "learning_rate": 1.7804e-05,
394
+ "loss": 0.4523,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.1405931272556096,
399
+ "grad_norm": 1.9921875,
400
+ "learning_rate": 1.7764e-05,
401
+ "loss": 0.4235,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.14310371881374548,
406
+ "grad_norm": 1.875,
407
+ "learning_rate": 1.7724000000000002e-05,
408
+ "loss": 0.4474,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.14561431037188138,
413
+ "grad_norm": 2.0625,
414
+ "learning_rate": 1.7684000000000002e-05,
415
+ "loss": 0.4576,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.14812490193001726,
420
+ "grad_norm": 2.296875,
421
+ "learning_rate": 1.7644000000000003e-05,
422
+ "loss": 0.4345,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.15063549348815314,
427
+ "grad_norm": 2.0,
428
+ "learning_rate": 1.7604e-05,
429
+ "loss": 0.4124,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.15314608504628904,
434
+ "grad_norm": 1.9453125,
435
+ "learning_rate": 1.7564e-05,
436
+ "loss": 0.4457,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.15565667660442492,
441
+ "grad_norm": 2.125,
442
+ "learning_rate": 1.7524e-05,
443
+ "loss": 0.4569,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.1581672681625608,
448
+ "grad_norm": 1.8203125,
449
+ "learning_rate": 1.7484e-05,
450
+ "loss": 0.4065,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.1606778597206967,
455
+ "grad_norm": 1.9921875,
456
+ "learning_rate": 1.7444e-05,
457
+ "loss": 0.4231,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.16318845127883258,
462
+ "grad_norm": 2.328125,
463
+ "learning_rate": 1.7404e-05,
464
+ "loss": 0.4306,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.16569904283696846,
469
+ "grad_norm": 1.8359375,
470
+ "learning_rate": 1.7364000000000002e-05,
471
+ "loss": 0.4261,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.16820963439510433,
476
+ "grad_norm": 1.9140625,
477
+ "learning_rate": 1.7324000000000002e-05,
478
+ "loss": 0.3939,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.17072022595324024,
483
+ "grad_norm": 2.34375,
484
+ "learning_rate": 1.7284e-05,
485
+ "loss": 0.3979,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.17323081751137612,
490
+ "grad_norm": 2.0,
491
+ "learning_rate": 1.7244e-05,
492
+ "loss": 0.419,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.175741409069512,
497
+ "grad_norm": 2.078125,
498
+ "learning_rate": 1.7204e-05,
499
+ "loss": 0.4181,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.1782520006276479,
504
+ "grad_norm": 2.0625,
505
+ "learning_rate": 1.7164e-05,
506
+ "loss": 0.4345,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.18076259218578378,
511
+ "grad_norm": 2.078125,
512
+ "learning_rate": 1.7124e-05,
513
+ "loss": 0.436,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.18327318374391965,
518
+ "grad_norm": 2.15625,
519
+ "learning_rate": 1.7084e-05,
520
+ "loss": 0.3904,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.18578377530205556,
525
+ "grad_norm": 1.7265625,
526
+ "learning_rate": 1.7044e-05,
527
+ "loss": 0.3941,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.18829436686019144,
532
+ "grad_norm": 1.9453125,
533
+ "learning_rate": 1.7004000000000002e-05,
534
+ "loss": 0.403,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.19080495841832731,
539
+ "grad_norm": 2.09375,
540
+ "learning_rate": 1.6964e-05,
541
+ "loss": 0.397,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.1933155499764632,
546
+ "grad_norm": 2.078125,
547
+ "learning_rate": 1.6924e-05,
548
+ "loss": 0.3869,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.1958261415345991,
553
+ "grad_norm": 2.046875,
554
+ "learning_rate": 1.6884e-05,
555
+ "loss": 0.428,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.19833673309273497,
560
+ "grad_norm": 2.375,
561
+ "learning_rate": 1.6844e-05,
562
+ "loss": 0.4024,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.20084732465087085,
567
+ "grad_norm": 2.03125,
568
+ "learning_rate": 1.6804e-05,
569
+ "loss": 0.4061,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.20335791620900676,
574
+ "grad_norm": 2.171875,
575
+ "learning_rate": 1.6764e-05,
576
+ "loss": 0.3882,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.20586850776714263,
581
+ "grad_norm": 2.140625,
582
+ "learning_rate": 1.6724e-05,
583
+ "loss": 0.3973,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.2083790993252785,
588
+ "grad_norm": 2.203125,
589
+ "learning_rate": 1.6684e-05,
590
+ "loss": 0.3871,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.21088969088341442,
595
+ "grad_norm": 2.09375,
596
+ "learning_rate": 1.6644000000000002e-05,
597
+ "loss": 0.3666,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.2134002824415503,
602
+ "grad_norm": 2.046875,
603
+ "learning_rate": 1.6604000000000002e-05,
604
+ "loss": 0.3853,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.21591087399968617,
609
+ "grad_norm": 2.078125,
610
+ "learning_rate": 1.6564000000000003e-05,
611
+ "loss": 0.3772,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.21842146555782208,
616
+ "grad_norm": 2.3125,
617
+ "learning_rate": 1.6524000000000003e-05,
618
+ "loss": 0.3926,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.22093205711595795,
623
+ "grad_norm": 2.0625,
624
+ "learning_rate": 1.6484000000000003e-05,
625
+ "loss": 0.3824,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.22344264867409383,
630
+ "grad_norm": 2.078125,
631
+ "learning_rate": 1.6444000000000004e-05,
632
+ "loss": 0.3777,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.2259532402322297,
637
+ "grad_norm": 1.8984375,
638
+ "learning_rate": 1.6404e-05,
639
+ "loss": 0.3886,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.2284638317903656,
644
+ "grad_norm": 2.25,
645
+ "learning_rate": 1.6364e-05,
646
+ "loss": 0.4085,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.2309744233485015,
651
+ "grad_norm": 2.125,
652
+ "learning_rate": 1.6324e-05,
653
+ "loss": 0.3692,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.23348501490663737,
658
+ "grad_norm": 2.125,
659
+ "learning_rate": 1.6284000000000002e-05,
660
+ "loss": 0.3528,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.23599560646477327,
665
+ "grad_norm": 2.0625,
666
+ "learning_rate": 1.6244000000000002e-05,
667
+ "loss": 0.3708,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.23850619802290915,
672
+ "grad_norm": 1.9453125,
673
+ "learning_rate": 1.6204000000000003e-05,
674
+ "loss": 0.3625,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.24101678958104503,
679
+ "grad_norm": 2.140625,
680
+ "learning_rate": 1.6164000000000003e-05,
681
+ "loss": 0.3596,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.24352738113918093,
686
+ "grad_norm": 1.7265625,
687
+ "learning_rate": 1.6124000000000004e-05,
688
+ "loss": 0.3576,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.2460379726973168,
693
+ "grad_norm": 1.6015625,
694
+ "learning_rate": 1.6084e-05,
695
+ "loss": 0.3481,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.2485485642554527,
700
+ "grad_norm": 2.296875,
701
+ "learning_rate": 1.6044e-05,
702
+ "loss": 0.3899,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.25105915581358856,
707
+ "grad_norm": 2.0,
708
+ "learning_rate": 1.6004e-05,
709
+ "loss": 0.3838,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.25356974737172444,
714
+ "grad_norm": 1.78125,
715
+ "learning_rate": 1.5964e-05,
716
+ "loss": 0.3522,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.2560803389298604,
721
+ "grad_norm": 2.0625,
722
+ "learning_rate": 1.5924000000000002e-05,
723
+ "loss": 0.3277,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.25859093048799625,
728
+ "grad_norm": 2.109375,
729
+ "learning_rate": 1.5884000000000002e-05,
730
+ "loss": 0.3532,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.26110152204613213,
735
+ "grad_norm": 2.125,
736
+ "learning_rate": 1.5844000000000003e-05,
737
+ "loss": 0.3558,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.263612113604268,
742
+ "grad_norm": 2.375,
743
+ "learning_rate": 1.5804000000000003e-05,
744
+ "loss": 0.3617,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.2661227051624039,
749
+ "grad_norm": 2.421875,
750
+ "learning_rate": 1.5764e-05,
751
+ "loss": 0.3607,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.26863329672053976,
756
+ "grad_norm": 2.140625,
757
+ "learning_rate": 1.5724e-05,
758
+ "loss": 0.3948,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.27114388827867564,
763
+ "grad_norm": 1.8203125,
764
+ "learning_rate": 1.5684e-05,
765
+ "loss": 0.3776,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.27365447983681157,
770
+ "grad_norm": 2.15625,
771
+ "learning_rate": 1.5644e-05,
772
+ "loss": 0.3324,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.27616507139494745,
777
+ "grad_norm": 2.125,
778
+ "learning_rate": 1.5604000000000002e-05,
779
+ "loss": 0.3536,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.2786756629530833,
784
+ "grad_norm": 2.34375,
785
+ "learning_rate": 1.5564000000000002e-05,
786
+ "loss": 0.3591,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.2811862545112192,
791
+ "grad_norm": 2.015625,
792
+ "learning_rate": 1.5524000000000002e-05,
793
+ "loss": 0.3598,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.2836968460693551,
798
+ "grad_norm": 1.734375,
799
+ "learning_rate": 1.5484000000000003e-05,
800
+ "loss": 0.323,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.28620743762749096,
805
+ "grad_norm": 1.421875,
806
+ "learning_rate": 1.5444e-05,
807
+ "loss": 0.3496,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.2887180291856269,
812
+ "grad_norm": 2.1875,
813
+ "learning_rate": 1.5404e-05,
814
+ "loss": 0.3442,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.29122862074376277,
819
+ "grad_norm": 2.09375,
820
+ "learning_rate": 1.5364e-05,
821
+ "loss": 0.3392,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.29373921230189864,
826
+ "grad_norm": 1.9296875,
827
+ "learning_rate": 1.5324e-05,
828
+ "loss": 0.3689,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.2962498038600345,
833
+ "grad_norm": 2.296875,
834
+ "learning_rate": 1.5284e-05,
835
+ "loss": 0.347,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.2987603954181704,
840
+ "grad_norm": 1.96875,
841
+ "learning_rate": 1.5244000000000002e-05,
842
+ "loss": 0.3487,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.3012709869763063,
847
+ "grad_norm": 2.46875,
848
+ "learning_rate": 1.5204e-05,
849
+ "loss": 0.3182,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.30378157853444215,
854
+ "grad_norm": 2.109375,
855
+ "learning_rate": 1.5164e-05,
856
+ "loss": 0.3298,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.3062921700925781,
861
+ "grad_norm": 2.40625,
862
+ "learning_rate": 1.5124000000000001e-05,
863
+ "loss": 0.3299,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.30880276165071396,
868
+ "grad_norm": 2.53125,
869
+ "learning_rate": 1.5084000000000002e-05,
870
+ "loss": 0.3685,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.31131335320884984,
875
+ "grad_norm": 2.09375,
876
+ "learning_rate": 1.5044e-05,
877
+ "loss": 0.3321,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.3138239447669857,
882
+ "grad_norm": 1.9453125,
883
+ "learning_rate": 1.5004e-05,
884
+ "loss": 0.3397,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.3163345363251216,
889
+ "grad_norm": 1.8359375,
890
+ "learning_rate": 1.4964000000000001e-05,
891
+ "loss": 0.3296,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.3188451278832575,
896
+ "grad_norm": 1.875,
897
+ "learning_rate": 1.4924000000000001e-05,
898
+ "loss": 0.3122,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.3213557194413934,
903
+ "grad_norm": 2.0,
904
+ "learning_rate": 1.4884e-05,
905
+ "loss": 0.3325,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.3238663109995293,
910
+ "grad_norm": 1.9453125,
911
+ "learning_rate": 1.4844e-05,
912
+ "loss": 0.343,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.32637690255766516,
917
+ "grad_norm": 2.21875,
918
+ "learning_rate": 1.4804000000000001e-05,
919
+ "loss": 0.332,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.32888749411580104,
924
+ "grad_norm": 2.234375,
925
+ "learning_rate": 1.4764000000000001e-05,
926
+ "loss": 0.3303,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.3313980856739369,
931
+ "grad_norm": 2.25,
932
+ "learning_rate": 1.4724e-05,
933
+ "loss": 0.3302,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.3339086772320728,
938
+ "grad_norm": 1.6796875,
939
+ "learning_rate": 1.4684e-05,
940
+ "loss": 0.3304,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.33641926879020867,
945
+ "grad_norm": 1.7734375,
946
+ "learning_rate": 1.4644e-05,
947
+ "loss": 0.3247,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.3389298603483446,
952
+ "grad_norm": 1.9375,
953
+ "learning_rate": 1.4604000000000001e-05,
954
+ "loss": 0.324,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.3414404519064805,
959
+ "grad_norm": 1.5390625,
960
+ "learning_rate": 1.4564e-05,
961
+ "loss": 0.3353,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.34395104346461636,
966
+ "grad_norm": 2.03125,
967
+ "learning_rate": 1.4524e-05,
968
+ "loss": 0.321,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.34646163502275223,
973
+ "grad_norm": 2.5625,
974
+ "learning_rate": 1.4484e-05,
975
+ "loss": 0.3133,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.3489722265808881,
980
+ "grad_norm": 2.34375,
981
+ "learning_rate": 1.4444000000000001e-05,
982
+ "loss": 0.3516,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.351482818139024,
987
+ "grad_norm": 1.6015625,
988
+ "learning_rate": 1.4404e-05,
989
+ "loss": 0.3093,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.35399340969715987,
994
+ "grad_norm": 1.4765625,
995
+ "learning_rate": 1.4364e-05,
996
+ "loss": 0.3171,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.3565040012552958,
1001
+ "grad_norm": 2.0,
1002
+ "learning_rate": 1.4324e-05,
1003
+ "loss": 0.3321,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.3590145928134317,
1008
+ "grad_norm": 2.0625,
1009
+ "learning_rate": 1.4284e-05,
1010
+ "loss": 0.3111,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.36152518437156755,
1015
+ "grad_norm": 1.9375,
1016
+ "learning_rate": 1.4244000000000003e-05,
1017
+ "loss": 0.3403,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.36403577592970343,
1022
+ "grad_norm": 1.859375,
1023
+ "learning_rate": 1.4204000000000002e-05,
1024
+ "loss": 0.3174,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.3665463674878393,
1029
+ "grad_norm": 2.03125,
1030
+ "learning_rate": 1.4164000000000002e-05,
1031
+ "loss": 0.3332,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.3690569590459752,
1036
+ "grad_norm": 1.7734375,
1037
+ "learning_rate": 1.4124000000000002e-05,
1038
+ "loss": 0.3139,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.3715675506041111,
1043
+ "grad_norm": 1.9375,
1044
+ "learning_rate": 1.4084000000000003e-05,
1045
+ "loss": 0.328,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.374078142162247,
1050
+ "grad_norm": 2.015625,
1051
+ "learning_rate": 1.4044000000000001e-05,
1052
+ "loss": 0.3301,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.3765887337203829,
1057
+ "grad_norm": 2.6875,
1058
+ "learning_rate": 1.4004000000000002e-05,
1059
+ "loss": 0.3218,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.37909932527851875,
1064
+ "grad_norm": 2.453125,
1065
+ "learning_rate": 1.3964000000000002e-05,
1066
+ "loss": 0.3371,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.38160991683665463,
1071
+ "grad_norm": 1.515625,
1072
+ "learning_rate": 1.3924000000000003e-05,
1073
+ "loss": 0.3162,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.3841205083947905,
1078
+ "grad_norm": 1.9765625,
1079
+ "learning_rate": 1.3884000000000001e-05,
1080
+ "loss": 0.3092,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.3866310999529264,
1085
+ "grad_norm": 2.1875,
1086
+ "learning_rate": 1.3844000000000002e-05,
1087
+ "loss": 0.3224,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.3891416915110623,
1092
+ "grad_norm": 2.390625,
1093
+ "learning_rate": 1.3804000000000002e-05,
1094
+ "loss": 0.3027,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.3916522830691982,
1099
+ "grad_norm": 2.375,
1100
+ "learning_rate": 1.3764000000000002e-05,
1101
+ "loss": 0.3303,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.39416287462733407,
1106
+ "grad_norm": 1.828125,
1107
+ "learning_rate": 1.3724000000000001e-05,
1108
+ "loss": 0.3317,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.39667346618546995,
1113
+ "grad_norm": 1.9140625,
1114
+ "learning_rate": 1.3684000000000001e-05,
1115
+ "loss": 0.3195,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.3991840577436058,
1120
+ "grad_norm": 2.03125,
1121
+ "learning_rate": 1.3644000000000002e-05,
1122
+ "loss": 0.3185,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.4016946493017417,
1127
+ "grad_norm": 1.75,
1128
+ "learning_rate": 1.3604000000000002e-05,
1129
+ "loss": 0.2818,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.40420524085987763,
1134
+ "grad_norm": 1.8515625,
1135
+ "learning_rate": 1.3564000000000001e-05,
1136
+ "loss": 0.2996,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.4067158324180135,
1141
+ "grad_norm": 1.7578125,
1142
+ "learning_rate": 1.3524000000000001e-05,
1143
+ "loss": 0.3167,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.4092264239761494,
1148
+ "grad_norm": 2.25,
1149
+ "learning_rate": 1.3484000000000002e-05,
1150
+ "loss": 0.3257,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.41173701553428527,
1155
+ "grad_norm": 1.671875,
1156
+ "learning_rate": 1.3444000000000002e-05,
1157
+ "loss": 0.3145,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.41424760709242114,
1162
+ "grad_norm": 1.59375,
1163
+ "learning_rate": 1.3404e-05,
1164
+ "loss": 0.2936,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.416758198650557,
1169
+ "grad_norm": 1.953125,
1170
+ "learning_rate": 1.3364000000000001e-05,
1171
+ "loss": 0.3158,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.4192687902086929,
1176
+ "grad_norm": 1.53125,
1177
+ "learning_rate": 1.3324000000000002e-05,
1178
+ "loss": 0.3233,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.42177938176682883,
1183
+ "grad_norm": 2.28125,
1184
+ "learning_rate": 1.3284000000000002e-05,
1185
+ "loss": 0.2975,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.4242899733249647,
1190
+ "grad_norm": 2.046875,
1191
+ "learning_rate": 1.3244e-05,
1192
+ "loss": 0.3058,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.4268005648831006,
1197
+ "grad_norm": 2.15625,
1198
+ "learning_rate": 1.3204000000000001e-05,
1199
+ "loss": 0.3107,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.42931115644123646,
1204
+ "grad_norm": 1.8203125,
1205
+ "learning_rate": 1.3164000000000001e-05,
1206
+ "loss": 0.3096,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.43182174799937234,
1211
+ "grad_norm": 1.3828125,
1212
+ "learning_rate": 1.3124000000000002e-05,
1213
+ "loss": 0.3052,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.4343323395575082,
1218
+ "grad_norm": 1.8515625,
1219
+ "learning_rate": 1.3084e-05,
1220
+ "loss": 0.3029,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.43684293111564415,
1225
+ "grad_norm": 1.8203125,
1226
+ "learning_rate": 1.3044e-05,
1227
+ "loss": 0.3147,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.43935352267378003,
1232
+ "grad_norm": 1.984375,
1233
+ "learning_rate": 1.3004000000000001e-05,
1234
+ "loss": 0.3053,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.4418641142319159,
1239
+ "grad_norm": 1.953125,
1240
+ "learning_rate": 1.2964000000000002e-05,
1241
+ "loss": 0.2913,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.4443747057900518,
1246
+ "grad_norm": 1.8515625,
1247
+ "learning_rate": 1.2924e-05,
1248
+ "loss": 0.2916,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.44688529734818766,
1253
+ "grad_norm": 2.046875,
1254
+ "learning_rate": 1.2884e-05,
1255
+ "loss": 0.3159,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.44939588890632354,
1260
+ "grad_norm": 1.90625,
1261
+ "learning_rate": 1.2844000000000001e-05,
1262
+ "loss": 0.2987,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.4519064804644594,
1267
+ "grad_norm": 1.953125,
1268
+ "learning_rate": 1.2804000000000001e-05,
1269
+ "loss": 0.3136,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.45441707202259535,
1274
+ "grad_norm": 1.6015625,
1275
+ "learning_rate": 1.2764e-05,
1276
+ "loss": 0.3038,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.4569276635807312,
1281
+ "grad_norm": 2.0,
1282
+ "learning_rate": 1.2724e-05,
1283
+ "loss": 0.2916,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.4594382551388671,
1288
+ "grad_norm": 1.9765625,
1289
+ "learning_rate": 1.2684000000000001e-05,
1290
+ "loss": 0.3113,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.461948846697003,
1295
+ "grad_norm": 1.5625,
1296
+ "learning_rate": 1.2644000000000001e-05,
1297
+ "loss": 0.2728,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.46445943825513886,
1302
+ "grad_norm": 1.9296875,
1303
+ "learning_rate": 1.2604e-05,
1304
+ "loss": 0.2868,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.46697002981327473,
1309
+ "grad_norm": 2.140625,
1310
+ "learning_rate": 1.2564e-05,
1311
+ "loss": 0.289,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.4694806213714106,
1316
+ "grad_norm": 1.4921875,
1317
+ "learning_rate": 1.2524e-05,
1318
+ "loss": 0.2881,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.47199121292954654,
1323
+ "grad_norm": 1.8984375,
1324
+ "learning_rate": 1.2484000000000001e-05,
1325
+ "loss": 0.2803,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.4745018044876824,
1330
+ "grad_norm": 1.9375,
1331
+ "learning_rate": 1.2444e-05,
1332
+ "loss": 0.2785,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.4770123960458183,
1337
+ "grad_norm": 1.71875,
1338
+ "learning_rate": 1.2404e-05,
1339
+ "loss": 0.2976,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.4795229876039542,
1344
+ "grad_norm": 1.9296875,
1345
+ "learning_rate": 1.2364e-05,
1346
+ "loss": 0.2737,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.48203357916209005,
1351
+ "grad_norm": 1.7421875,
1352
+ "learning_rate": 1.2324000000000001e-05,
1353
+ "loss": 0.3237,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.48454417072022593,
1358
+ "grad_norm": 1.859375,
1359
+ "learning_rate": 1.2284e-05,
1360
+ "loss": 0.297,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.48705476227836186,
1365
+ "grad_norm": 2.046875,
1366
+ "learning_rate": 1.2244e-05,
1367
+ "loss": 0.2745,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.48956535383649774,
1372
+ "grad_norm": 2.1875,
1373
+ "learning_rate": 1.2204e-05,
1374
+ "loss": 0.3059,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.4920759453946336,
1379
+ "grad_norm": 2.359375,
1380
+ "learning_rate": 1.2164e-05,
1381
+ "loss": 0.2876,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.4945865369527695,
1386
+ "grad_norm": 2.6875,
1387
+ "learning_rate": 1.2124e-05,
1388
+ "loss": 0.2801,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.4970971285109054,
1393
+ "grad_norm": 1.921875,
1394
+ "learning_rate": 1.2084e-05,
1395
+ "loss": 0.2971,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.49960772006904125,
1400
+ "grad_norm": 1.6484375,
1401
+ "learning_rate": 1.2044e-05,
1402
+ "loss": 0.2979,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.5021183116271771,
1407
+ "grad_norm": 1.9296875,
1408
+ "learning_rate": 1.2004e-05,
1409
+ "loss": 0.306,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.5046289031853131,
1414
+ "grad_norm": 1.5859375,
1415
+ "learning_rate": 1.1964e-05,
1416
+ "loss": 0.2975,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.5071394947434489,
1421
+ "grad_norm": 1.9296875,
1422
+ "learning_rate": 1.1924e-05,
1423
+ "loss": 0.2771,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.5096500863015848,
1428
+ "grad_norm": 2.265625,
1429
+ "learning_rate": 1.1884e-05,
1430
+ "loss": 0.2903,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.5121606778597207,
1435
+ "grad_norm": 1.7109375,
1436
+ "learning_rate": 1.1844e-05,
1437
+ "loss": 0.2808,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.5146712694178566,
1442
+ "grad_norm": 1.7890625,
1443
+ "learning_rate": 1.1803999999999999e-05,
1444
+ "loss": 0.2856,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.5171818609759925,
1449
+ "grad_norm": 1.6796875,
1450
+ "learning_rate": 1.1764e-05,
1451
+ "loss": 0.2868,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.5196924525341283,
1456
+ "grad_norm": 1.7109375,
1457
+ "learning_rate": 1.1724000000000002e-05,
1458
+ "loss": 0.2973,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.5222030440922643,
1463
+ "grad_norm": 1.8828125,
1464
+ "learning_rate": 1.1684000000000002e-05,
1465
+ "loss": 0.3097,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.5247136356504001,
1470
+ "grad_norm": 1.6953125,
1471
+ "learning_rate": 1.1644000000000002e-05,
1472
+ "loss": 0.2731,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.527224227208536,
1477
+ "grad_norm": 2.0625,
1478
+ "learning_rate": 1.1604000000000003e-05,
1479
+ "loss": 0.2849,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.5297348187666719,
1484
+ "grad_norm": 2.203125,
1485
+ "learning_rate": 1.1564000000000001e-05,
1486
+ "loss": 0.2949,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.5322454103248078,
1491
+ "grad_norm": 2.203125,
1492
+ "learning_rate": 1.1524000000000002e-05,
1493
+ "loss": 0.3049,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.5347560018829437,
1498
+ "grad_norm": 1.7421875,
1499
+ "learning_rate": 1.1484000000000002e-05,
1500
+ "loss": 0.2851,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.5372665934410795,
1505
+ "grad_norm": 1.84375,
1506
+ "learning_rate": 1.1444000000000003e-05,
1507
+ "loss": 0.2919,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.5397771849992155,
1512
+ "grad_norm": 1.765625,
1513
+ "learning_rate": 1.1404000000000001e-05,
1514
+ "loss": 0.2967,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.5422877765573513,
1519
+ "grad_norm": 1.5546875,
1520
+ "learning_rate": 1.1364000000000002e-05,
1521
+ "loss": 0.2801,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.5447983681154872,
1526
+ "grad_norm": 2.0,
1527
+ "learning_rate": 1.1324000000000002e-05,
1528
+ "loss": 0.3012,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.5473089596736231,
1533
+ "grad_norm": 1.8984375,
1534
+ "learning_rate": 1.1284000000000002e-05,
1535
+ "loss": 0.2925,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.549819551231759,
1540
+ "grad_norm": 1.609375,
1541
+ "learning_rate": 1.1244000000000001e-05,
1542
+ "loss": 0.2954,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.5523301427898949,
1547
+ "grad_norm": 1.734375,
1548
+ "learning_rate": 1.1204000000000001e-05,
1549
+ "loss": 0.2799,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.5548407343480307,
1554
+ "grad_norm": 1.515625,
1555
+ "learning_rate": 1.1164000000000002e-05,
1556
+ "loss": 0.2704,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.5573513259061667,
1561
+ "grad_norm": 1.6953125,
1562
+ "learning_rate": 1.1124000000000002e-05,
1563
+ "loss": 0.2876,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.5598619174643025,
1568
+ "grad_norm": 1.7421875,
1569
+ "learning_rate": 1.1084000000000001e-05,
1570
+ "loss": 0.2633,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.5623725090224384,
1575
+ "grad_norm": 1.796875,
1576
+ "learning_rate": 1.1044000000000001e-05,
1577
+ "loss": 0.2867,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.5648831005805743,
1582
+ "grad_norm": 1.4609375,
1583
+ "learning_rate": 1.1004000000000002e-05,
1584
+ "loss": 0.2702,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.5673936921387102,
1589
+ "grad_norm": 1.828125,
1590
+ "learning_rate": 1.0964000000000002e-05,
1591
+ "loss": 0.2852,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.5699042836968461,
1596
+ "grad_norm": 1.703125,
1597
+ "learning_rate": 1.0924e-05,
1598
+ "loss": 0.2746,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.5724148752549819,
1603
+ "grad_norm": 1.90625,
1604
+ "learning_rate": 1.0884000000000001e-05,
1605
+ "loss": 0.2932,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.5749254668131178,
1610
+ "grad_norm": 1.84375,
1611
+ "learning_rate": 1.0844000000000002e-05,
1612
+ "loss": 0.2903,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.5774360583712538,
1617
+ "grad_norm": 2.15625,
1618
+ "learning_rate": 1.0804000000000002e-05,
1619
+ "loss": 0.2851,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.5799466499293896,
1624
+ "grad_norm": 2.0625,
1625
+ "learning_rate": 1.0764e-05,
1626
+ "loss": 0.2923,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.5824572414875255,
1631
+ "grad_norm": 2.109375,
1632
+ "learning_rate": 1.0724000000000001e-05,
1633
+ "loss": 0.3003,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.5849678330456614,
1638
+ "grad_norm": 2.046875,
1639
+ "learning_rate": 1.0684000000000001e-05,
1640
+ "loss": 0.291,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.5874784246037973,
1645
+ "grad_norm": 1.8828125,
1646
+ "learning_rate": 1.0644000000000002e-05,
1647
+ "loss": 0.2787,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.5899890161619331,
1652
+ "grad_norm": 1.8203125,
1653
+ "learning_rate": 1.0604e-05,
1654
+ "loss": 0.2764,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.592499607720069,
1659
+ "grad_norm": 1.65625,
1660
+ "learning_rate": 1.0564e-05,
1661
+ "loss": 0.2842,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.595010199278205,
1666
+ "grad_norm": 1.78125,
1667
+ "learning_rate": 1.0524000000000001e-05,
1668
+ "loss": 0.2922,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.5975207908363408,
1673
+ "grad_norm": 1.5625,
1674
+ "learning_rate": 1.0484000000000002e-05,
1675
+ "loss": 0.283,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.6000313823944767,
1680
+ "grad_norm": 1.5703125,
1681
+ "learning_rate": 1.0444e-05,
1682
+ "loss": 0.2796,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.6025419739526126,
1687
+ "grad_norm": 1.96875,
1688
+ "learning_rate": 1.0404e-05,
1689
+ "loss": 0.2828,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.6050525655107485,
1694
+ "grad_norm": 1.5703125,
1695
+ "learning_rate": 1.0364000000000001e-05,
1696
+ "loss": 0.2866,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.6075631570688843,
1701
+ "grad_norm": 2.109375,
1702
+ "learning_rate": 1.0324000000000001e-05,
1703
+ "loss": 0.2836,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.6100737486270202,
1708
+ "grad_norm": 1.875,
1709
+ "learning_rate": 1.0284e-05,
1710
+ "loss": 0.3037,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.6125843401851562,
1715
+ "grad_norm": 2.203125,
1716
+ "learning_rate": 1.0244e-05,
1717
+ "loss": 0.2774,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.615094931743292,
1722
+ "grad_norm": 1.8671875,
1723
+ "learning_rate": 1.0204000000000001e-05,
1724
+ "loss": 0.2922,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.6176055233014279,
1729
+ "grad_norm": 1.7109375,
1730
+ "learning_rate": 1.0164000000000001e-05,
1731
+ "loss": 0.283,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.6201161148595637,
1736
+ "grad_norm": 1.9453125,
1737
+ "learning_rate": 1.0124e-05,
1738
+ "loss": 0.2725,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.6226267064176997,
1743
+ "grad_norm": 1.6875,
1744
+ "learning_rate": 1.0084e-05,
1745
+ "loss": 0.2749,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.6251372979758355,
1750
+ "grad_norm": 1.703125,
1751
+ "learning_rate": 1.0044e-05,
1752
+ "loss": 0.2823,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.6276478895339714,
1757
+ "grad_norm": 1.9296875,
1758
+ "learning_rate": 1.0004000000000001e-05,
1759
+ "loss": 0.281,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.6301584810921074,
1764
+ "grad_norm": 1.9140625,
1765
+ "learning_rate": 9.964e-06,
1766
+ "loss": 0.2856,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.6326690726502432,
1771
+ "grad_norm": 1.4921875,
1772
+ "learning_rate": 9.924e-06,
1773
+ "loss": 0.28,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.6351796642083791,
1778
+ "grad_norm": 1.53125,
1779
+ "learning_rate": 9.884e-06,
1780
+ "loss": 0.267,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.637690255766515,
1785
+ "grad_norm": 1.5703125,
1786
+ "learning_rate": 9.844000000000001e-06,
1787
+ "loss": 0.2563,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.6402008473246509,
1792
+ "grad_norm": 1.46875,
1793
+ "learning_rate": 9.804000000000001e-06,
1794
+ "loss": 0.2911,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.6427114388827868,
1799
+ "grad_norm": 2.46875,
1800
+ "learning_rate": 9.764000000000002e-06,
1801
+ "loss": 0.2897,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.6452220304409226,
1806
+ "grad_norm": 1.90625,
1807
+ "learning_rate": 9.724e-06,
1808
+ "loss": 0.2975,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.6477326219990586,
1813
+ "grad_norm": 1.890625,
1814
+ "learning_rate": 9.684e-06,
1815
+ "loss": 0.2722,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.6502432135571944,
1820
+ "grad_norm": 1.6015625,
1821
+ "learning_rate": 9.644000000000001e-06,
1822
+ "loss": 0.2787,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.6527538051153303,
1827
+ "grad_norm": 2.046875,
1828
+ "learning_rate": 9.604000000000002e-06,
1829
+ "loss": 0.2822,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 0.6552643966734661,
1834
+ "grad_norm": 1.9296875,
1835
+ "learning_rate": 9.564e-06,
1836
+ "loss": 0.2903,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 0.6577749882316021,
1841
+ "grad_norm": 1.78125,
1842
+ "learning_rate": 9.524e-06,
1843
+ "loss": 0.2693,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 0.660285579789738,
1848
+ "grad_norm": 1.46875,
1849
+ "learning_rate": 9.484000000000001e-06,
1850
+ "loss": 0.2768,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 0.6627961713478738,
1855
+ "grad_norm": 1.734375,
1856
+ "learning_rate": 9.444000000000001e-06,
1857
+ "loss": 0.2707,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 0.6653067629060098,
1862
+ "grad_norm": 1.5703125,
1863
+ "learning_rate": 9.404e-06,
1864
+ "loss": 0.2791,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 0.6678173544641456,
1869
+ "grad_norm": 1.703125,
1870
+ "learning_rate": 9.364e-06,
1871
+ "loss": 0.2924,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 0.6703279460222815,
1876
+ "grad_norm": 1.9296875,
1877
+ "learning_rate": 9.324000000000001e-06,
1878
+ "loss": 0.2875,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 0.6728385375804173,
1883
+ "grad_norm": 1.78125,
1884
+ "learning_rate": 9.284000000000001e-06,
1885
+ "loss": 0.2602,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 0.6753491291385533,
1890
+ "grad_norm": 1.6875,
1891
+ "learning_rate": 9.244e-06,
1892
+ "loss": 0.2924,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 0.6778597206966892,
1897
+ "grad_norm": 1.578125,
1898
+ "learning_rate": 9.204e-06,
1899
+ "loss": 0.2841,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 0.680370312254825,
1904
+ "grad_norm": 1.390625,
1905
+ "learning_rate": 9.164e-06,
1906
+ "loss": 0.2745,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 0.682880903812961,
1911
+ "grad_norm": 2.28125,
1912
+ "learning_rate": 9.124000000000001e-06,
1913
+ "loss": 0.2876,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 0.6853914953710968,
1918
+ "grad_norm": 1.546875,
1919
+ "learning_rate": 9.084e-06,
1920
+ "loss": 0.2549,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 0.6879020869292327,
1925
+ "grad_norm": 1.3515625,
1926
+ "learning_rate": 9.044e-06,
1927
+ "loss": 0.2512,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 0.6904126784873685,
1932
+ "grad_norm": 2.203125,
1933
+ "learning_rate": 9.004e-06,
1934
+ "loss": 0.2686,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 0.6929232700455045,
1939
+ "grad_norm": 1.6484375,
1940
+ "learning_rate": 8.964000000000001e-06,
1941
+ "loss": 0.2714,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 0.6954338616036404,
1946
+ "grad_norm": 1.6796875,
1947
+ "learning_rate": 8.924e-06,
1948
+ "loss": 0.275,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 0.6979444531617762,
1953
+ "grad_norm": 1.8359375,
1954
+ "learning_rate": 8.884e-06,
1955
+ "loss": 0.2631,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 0.7004550447199122,
1960
+ "grad_norm": 1.3828125,
1961
+ "learning_rate": 8.844e-06,
1962
+ "loss": 0.2639,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 0.702965636278048,
1967
+ "grad_norm": 1.59375,
1968
+ "learning_rate": 8.804e-06,
1969
+ "loss": 0.2755,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 0.7054762278361839,
1974
+ "grad_norm": 1.8828125,
1975
+ "learning_rate": 8.764e-06,
1976
+ "loss": 0.282,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 0.7079868193943197,
1981
+ "grad_norm": 1.9140625,
1982
+ "learning_rate": 8.724e-06,
1983
+ "loss": 0.2672,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 0.7104974109524557,
1988
+ "grad_norm": 1.5859375,
1989
+ "learning_rate": 8.684e-06,
1990
+ "loss": 0.2663,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 0.7130080025105916,
1995
+ "grad_norm": 1.75,
1996
+ "learning_rate": 8.644e-06,
1997
+ "loss": 0.263,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 0.7155185940687274,
2002
+ "grad_norm": 1.9765625,
2003
+ "learning_rate": 8.604000000000001e-06,
2004
+ "loss": 0.276,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 0.7180291856268634,
2009
+ "grad_norm": 1.5078125,
2010
+ "learning_rate": 8.564000000000001e-06,
2011
+ "loss": 0.2622,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 0.7205397771849992,
2016
+ "grad_norm": 1.890625,
2017
+ "learning_rate": 8.524000000000002e-06,
2018
+ "loss": 0.2574,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 0.7230503687431351,
2023
+ "grad_norm": 1.65625,
2024
+ "learning_rate": 8.484e-06,
2025
+ "loss": 0.2586,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 0.725560960301271,
2030
+ "grad_norm": 2.234375,
2031
+ "learning_rate": 8.444e-06,
2032
+ "loss": 0.2694,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 0.7280715518594069,
2037
+ "grad_norm": 1.6953125,
2038
+ "learning_rate": 8.404000000000001e-06,
2039
+ "loss": 0.2817,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 0.7305821434175428,
2044
+ "grad_norm": 1.828125,
2045
+ "learning_rate": 8.364000000000002e-06,
2046
+ "loss": 0.2767,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 0.7330927349756786,
2051
+ "grad_norm": 1.40625,
2052
+ "learning_rate": 8.324e-06,
2053
+ "loss": 0.2547,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 0.7356033265338145,
2058
+ "grad_norm": 1.65625,
2059
+ "learning_rate": 8.284e-06,
2060
+ "loss": 0.2724,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 0.7381139180919504,
2065
+ "grad_norm": 2.078125,
2066
+ "learning_rate": 8.244000000000001e-06,
2067
+ "loss": 0.2972,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 0.7406245096500863,
2072
+ "grad_norm": 1.484375,
2073
+ "learning_rate": 8.204000000000001e-06,
2074
+ "loss": 0.2601,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 0.7431351012082222,
2079
+ "grad_norm": 2.015625,
2080
+ "learning_rate": 8.164e-06,
2081
+ "loss": 0.2552,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 0.7456456927663581,
2086
+ "grad_norm": 2.234375,
2087
+ "learning_rate": 8.124e-06,
2088
+ "loss": 0.274,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 0.748156284324494,
2093
+ "grad_norm": 1.8125,
2094
+ "learning_rate": 8.084000000000001e-06,
2095
+ "loss": 0.272,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 0.7506668758826298,
2100
+ "grad_norm": 1.6953125,
2101
+ "learning_rate": 8.044000000000001e-06,
2102
+ "loss": 0.2826,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 0.7531774674407657,
2107
+ "grad_norm": 1.7109375,
2108
+ "learning_rate": 8.004e-06,
2109
+ "loss": 0.2799,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 0.7556880589989016,
2114
+ "grad_norm": 1.640625,
2115
+ "learning_rate": 7.964e-06,
2116
+ "loss": 0.2919,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 0.7581986505570375,
2121
+ "grad_norm": 1.6953125,
2122
+ "learning_rate": 7.924e-06,
2123
+ "loss": 0.2634,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 0.7607092421151734,
2128
+ "grad_norm": 1.8515625,
2129
+ "learning_rate": 7.884000000000001e-06,
2130
+ "loss": 0.259,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 0.7632198336733093,
2135
+ "grad_norm": 1.7109375,
2136
+ "learning_rate": 7.844e-06,
2137
+ "loss": 0.2687,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 0.7657304252314452,
2142
+ "grad_norm": 1.6015625,
2143
+ "learning_rate": 7.804e-06,
2144
+ "loss": 0.2644,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 0.768241016789581,
2149
+ "grad_norm": 1.7421875,
2150
+ "learning_rate": 7.764e-06,
2151
+ "loss": 0.2541,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 0.7707516083477169,
2156
+ "grad_norm": 1.3203125,
2157
+ "learning_rate": 7.724000000000001e-06,
2158
+ "loss": 0.2555,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 0.7732621999058528,
2163
+ "grad_norm": 1.4609375,
2164
+ "learning_rate": 7.684e-06,
2165
+ "loss": 0.2745,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 0.7757727914639887,
2170
+ "grad_norm": 1.5546875,
2171
+ "learning_rate": 7.644e-06,
2172
+ "loss": 0.2924,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 0.7782833830221246,
2177
+ "grad_norm": 1.78125,
2178
+ "learning_rate": 7.604e-06,
2179
+ "loss": 0.2859,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 0.7807939745802605,
2184
+ "grad_norm": 1.75,
2185
+ "learning_rate": 7.564e-06,
2186
+ "loss": 0.2752,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 0.7833045661383964,
2191
+ "grad_norm": 1.6171875,
2192
+ "learning_rate": 7.524e-06,
2193
+ "loss": 0.2611,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 0.7858151576965322,
2198
+ "grad_norm": 1.578125,
2199
+ "learning_rate": 7.484e-06,
2200
+ "loss": 0.256,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 0.7883257492546681,
2205
+ "grad_norm": 1.578125,
2206
+ "learning_rate": 7.444e-06,
2207
+ "loss": 0.2707,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 0.790836340812804,
2212
+ "grad_norm": 1.765625,
2213
+ "learning_rate": 7.404e-06,
2214
+ "loss": 0.2711,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 0.7933469323709399,
2219
+ "grad_norm": 1.6484375,
2220
+ "learning_rate": 7.364000000000001e-06,
2221
+ "loss": 0.2588,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 0.7958575239290758,
2226
+ "grad_norm": 1.7890625,
2227
+ "learning_rate": 7.324000000000001e-06,
2228
+ "loss": 0.2618,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 0.7983681154872116,
2233
+ "grad_norm": 1.7734375,
2234
+ "learning_rate": 7.284000000000001e-06,
2235
+ "loss": 0.2755,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 0.8008787070453476,
2240
+ "grad_norm": 1.5703125,
2241
+ "learning_rate": 7.244000000000001e-06,
2242
+ "loss": 0.2727,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 0.8033892986034834,
2247
+ "grad_norm": 1.453125,
2248
+ "learning_rate": 7.204000000000001e-06,
2249
+ "loss": 0.2584,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 0.8058998901616193,
2254
+ "grad_norm": 1.7265625,
2255
+ "learning_rate": 7.164000000000001e-06,
2256
+ "loss": 0.2767,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 0.8084104817197553,
2261
+ "grad_norm": 1.5703125,
2262
+ "learning_rate": 7.124000000000001e-06,
2263
+ "loss": 0.2735,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 0.8109210732778911,
2268
+ "grad_norm": 1.8203125,
2269
+ "learning_rate": 7.084000000000001e-06,
2270
+ "loss": 0.277,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 0.813431664836027,
2275
+ "grad_norm": 1.8125,
2276
+ "learning_rate": 7.044000000000001e-06,
2277
+ "loss": 0.2743,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 0.8159422563941628,
2282
+ "grad_norm": 1.953125,
2283
+ "learning_rate": 7.004000000000001e-06,
2284
+ "loss": 0.2804,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 0.8184528479522988,
2289
+ "grad_norm": 1.71875,
2290
+ "learning_rate": 6.964000000000001e-06,
2291
+ "loss": 0.27,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 0.8209634395104346,
2296
+ "grad_norm": 1.578125,
2297
+ "learning_rate": 6.924000000000001e-06,
2298
+ "loss": 0.2672,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 0.8234740310685705,
2303
+ "grad_norm": 1.671875,
2304
+ "learning_rate": 6.8840000000000005e-06,
2305
+ "loss": 0.2787,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 0.8259846226267065,
2310
+ "grad_norm": 2.34375,
2311
+ "learning_rate": 6.844000000000001e-06,
2312
+ "loss": 0.2624,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 0.8284952141848423,
2317
+ "grad_norm": 1.9765625,
2318
+ "learning_rate": 6.804e-06,
2319
+ "loss": 0.2655,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 0.8310058057429782,
2324
+ "grad_norm": 1.65625,
2325
+ "learning_rate": 6.764000000000001e-06,
2326
+ "loss": 0.2677,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 0.833516397301114,
2331
+ "grad_norm": 2.015625,
2332
+ "learning_rate": 6.724e-06,
2333
+ "loss": 0.2655,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 0.83602698885925,
2338
+ "grad_norm": 1.5703125,
2339
+ "learning_rate": 6.684000000000001e-06,
2340
+ "loss": 0.27,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 0.8385375804173858,
2345
+ "grad_norm": 1.6015625,
2346
+ "learning_rate": 6.644e-06,
2347
+ "loss": 0.2503,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 0.8410481719755217,
2352
+ "grad_norm": 2.15625,
2353
+ "learning_rate": 6.604000000000001e-06,
2354
+ "loss": 0.2773,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 0.8435587635336577,
2359
+ "grad_norm": 1.609375,
2360
+ "learning_rate": 6.564e-06,
2361
+ "loss": 0.274,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 0.8460693550917935,
2366
+ "grad_norm": 1.578125,
2367
+ "learning_rate": 6.5240000000000006e-06,
2368
+ "loss": 0.2587,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 0.8485799466499294,
2373
+ "grad_norm": 1.828125,
2374
+ "learning_rate": 6.484e-06,
2375
+ "loss": 0.2699,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 0.8510905382080652,
2380
+ "grad_norm": 1.8125,
2381
+ "learning_rate": 6.4440000000000005e-06,
2382
+ "loss": 0.255,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 0.8536011297662012,
2387
+ "grad_norm": 1.65625,
2388
+ "learning_rate": 6.404e-06,
2389
+ "loss": 0.2532,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 0.856111721324337,
2394
+ "grad_norm": 1.6171875,
2395
+ "learning_rate": 6.364e-06,
2396
+ "loss": 0.2745,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 0.8586223128824729,
2401
+ "grad_norm": 1.7421875,
2402
+ "learning_rate": 6.324e-06,
2403
+ "loss": 0.2713,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 0.8611329044406089,
2408
+ "grad_norm": 1.6875,
2409
+ "learning_rate": 6.284e-06,
2410
+ "loss": 0.271,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 0.8636434959987447,
2415
+ "grad_norm": 1.4375,
2416
+ "learning_rate": 6.244e-06,
2417
+ "loss": 0.2485,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 0.8661540875568806,
2422
+ "grad_norm": 1.3203125,
2423
+ "learning_rate": 6.204e-06,
2424
+ "loss": 0.2648,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 0.8686646791150164,
2429
+ "grad_norm": 1.8203125,
2430
+ "learning_rate": 6.164e-06,
2431
+ "loss": 0.2683,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 0.8711752706731524,
2436
+ "grad_norm": 1.5703125,
2437
+ "learning_rate": 6.124000000000001e-06,
2438
+ "loss": 0.261,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 0.8736858622312883,
2443
+ "grad_norm": 1.4296875,
2444
+ "learning_rate": 6.084000000000001e-06,
2445
+ "loss": 0.2541,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 0.8761964537894241,
2450
+ "grad_norm": 1.859375,
2451
+ "learning_rate": 6.044000000000001e-06,
2452
+ "loss": 0.2607,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 0.8787070453475601,
2457
+ "grad_norm": 2.71875,
2458
+ "learning_rate": 6.004000000000001e-06,
2459
+ "loss": 0.2516,
2460
+ "step": 3500
2461
+ },
2462
+ {
2463
+ "epoch": 0.8812176369056959,
2464
+ "grad_norm": 1.578125,
2465
+ "learning_rate": 5.964000000000001e-06,
2466
+ "loss": 0.2678,
2467
+ "step": 3510
2468
+ },
2469
+ {
2470
+ "epoch": 0.8837282284638318,
2471
+ "grad_norm": 1.65625,
2472
+ "learning_rate": 5.924000000000001e-06,
2473
+ "loss": 0.2628,
2474
+ "step": 3520
2475
+ },
2476
+ {
2477
+ "epoch": 0.8862388200219676,
2478
+ "grad_norm": 1.5546875,
2479
+ "learning_rate": 5.884000000000001e-06,
2480
+ "loss": 0.2557,
2481
+ "step": 3530
2482
+ },
2483
+ {
2484
+ "epoch": 0.8887494115801036,
2485
+ "grad_norm": 1.8828125,
2486
+ "learning_rate": 5.844000000000001e-06,
2487
+ "loss": 0.2663,
2488
+ "step": 3540
2489
+ },
2490
+ {
2491
+ "epoch": 0.8912600031382395,
2492
+ "grad_norm": 2.125,
2493
+ "learning_rate": 5.804000000000001e-06,
2494
+ "loss": 0.2789,
2495
+ "step": 3550
2496
+ },
2497
+ {
2498
+ "epoch": 0.8937705946963753,
2499
+ "grad_norm": 1.78125,
2500
+ "learning_rate": 5.764000000000001e-06,
2501
+ "loss": 0.2646,
2502
+ "step": 3560
2503
+ },
2504
+ {
2505
+ "epoch": 0.8962811862545113,
2506
+ "grad_norm": 1.796875,
2507
+ "learning_rate": 5.724000000000001e-06,
2508
+ "loss": 0.2627,
2509
+ "step": 3570
2510
+ },
2511
+ {
2512
+ "epoch": 0.8987917778126471,
2513
+ "grad_norm": 1.609375,
2514
+ "learning_rate": 5.684000000000001e-06,
2515
+ "loss": 0.281,
2516
+ "step": 3580
2517
+ },
2518
+ {
2519
+ "epoch": 0.901302369370783,
2520
+ "grad_norm": 1.8515625,
2521
+ "learning_rate": 5.6440000000000005e-06,
2522
+ "loss": 0.2588,
2523
+ "step": 3590
2524
+ },
2525
+ {
2526
+ "epoch": 0.9038129609289188,
2527
+ "grad_norm": 1.9140625,
2528
+ "learning_rate": 5.604000000000001e-06,
2529
+ "loss": 0.267,
2530
+ "step": 3600
2531
+ },
2532
+ {
2533
+ "epoch": 0.9063235524870548,
2534
+ "grad_norm": 1.75,
2535
+ "learning_rate": 5.5640000000000004e-06,
2536
+ "loss": 0.2546,
2537
+ "step": 3610
2538
+ },
2539
+ {
2540
+ "epoch": 0.9088341440451907,
2541
+ "grad_norm": 1.484375,
2542
+ "learning_rate": 5.524000000000001e-06,
2543
+ "loss": 0.2607,
2544
+ "step": 3620
2545
+ },
2546
+ {
2547
+ "epoch": 0.9113447356033265,
2548
+ "grad_norm": 1.5703125,
2549
+ "learning_rate": 5.484e-06,
2550
+ "loss": 0.2804,
2551
+ "step": 3630
2552
+ },
2553
+ {
2554
+ "epoch": 0.9138553271614624,
2555
+ "grad_norm": 1.6328125,
2556
+ "learning_rate": 5.444000000000001e-06,
2557
+ "loss": 0.2595,
2558
+ "step": 3640
2559
+ },
2560
+ {
2561
+ "epoch": 0.9163659187195983,
2562
+ "grad_norm": 1.84375,
2563
+ "learning_rate": 5.404e-06,
2564
+ "loss": 0.2697,
2565
+ "step": 3650
2566
+ },
2567
+ {
2568
+ "epoch": 0.9188765102777342,
2569
+ "grad_norm": 1.5703125,
2570
+ "learning_rate": 5.364000000000001e-06,
2571
+ "loss": 0.2725,
2572
+ "step": 3660
2573
+ },
2574
+ {
2575
+ "epoch": 0.92138710183587,
2576
+ "grad_norm": 1.3984375,
2577
+ "learning_rate": 5.324e-06,
2578
+ "loss": 0.2613,
2579
+ "step": 3670
2580
+ },
2581
+ {
2582
+ "epoch": 0.923897693394006,
2583
+ "grad_norm": 1.8046875,
2584
+ "learning_rate": 5.2840000000000006e-06,
2585
+ "loss": 0.2708,
2586
+ "step": 3680
2587
+ },
2588
+ {
2589
+ "epoch": 0.9264082849521419,
2590
+ "grad_norm": 1.578125,
2591
+ "learning_rate": 5.244e-06,
2592
+ "loss": 0.2685,
2593
+ "step": 3690
2594
+ },
2595
+ {
2596
+ "epoch": 0.9289188765102777,
2597
+ "grad_norm": 1.8828125,
2598
+ "learning_rate": 5.2040000000000005e-06,
2599
+ "loss": 0.272,
2600
+ "step": 3700
2601
+ },
2602
+ {
2603
+ "epoch": 0.9314294680684136,
2604
+ "grad_norm": 1.6875,
2605
+ "learning_rate": 5.164e-06,
2606
+ "loss": 0.2801,
2607
+ "step": 3710
2608
+ },
2609
+ {
2610
+ "epoch": 0.9339400596265495,
2611
+ "grad_norm": 1.6015625,
2612
+ "learning_rate": 5.124e-06,
2613
+ "loss": 0.257,
2614
+ "step": 3720
2615
+ },
2616
+ {
2617
+ "epoch": 0.9364506511846854,
2618
+ "grad_norm": 1.5,
2619
+ "learning_rate": 5.084e-06,
2620
+ "loss": 0.2511,
2621
+ "step": 3730
2622
+ },
2623
+ {
2624
+ "epoch": 0.9389612427428212,
2625
+ "grad_norm": 1.5390625,
2626
+ "learning_rate": 5.044e-06,
2627
+ "loss": 0.2645,
2628
+ "step": 3740
2629
+ },
2630
+ {
2631
+ "epoch": 0.9414718343009572,
2632
+ "grad_norm": 1.6640625,
2633
+ "learning_rate": 5.004e-06,
2634
+ "loss": 0.2711,
2635
+ "step": 3750
2636
+ },
2637
+ {
2638
+ "epoch": 0.9439824258590931,
2639
+ "grad_norm": 1.7421875,
2640
+ "learning_rate": 4.964e-06,
2641
+ "loss": 0.2547,
2642
+ "step": 3760
2643
+ },
2644
+ {
2645
+ "epoch": 0.9464930174172289,
2646
+ "grad_norm": 1.7734375,
2647
+ "learning_rate": 4.924000000000001e-06,
2648
+ "loss": 0.2728,
2649
+ "step": 3770
2650
+ },
2651
+ {
2652
+ "epoch": 0.9490036089753648,
2653
+ "grad_norm": 1.421875,
2654
+ "learning_rate": 4.884e-06,
2655
+ "loss": 0.2666,
2656
+ "step": 3780
2657
+ },
2658
+ {
2659
+ "epoch": 0.9515142005335007,
2660
+ "grad_norm": 1.3515625,
2661
+ "learning_rate": 4.8440000000000005e-06,
2662
+ "loss": 0.2509,
2663
+ "step": 3790
2664
+ },
2665
+ {
2666
+ "epoch": 0.9540247920916366,
2667
+ "grad_norm": 1.6640625,
2668
+ "learning_rate": 4.804e-06,
2669
+ "loss": 0.2643,
2670
+ "step": 3800
2671
+ },
2672
+ {
2673
+ "epoch": 0.9565353836497725,
2674
+ "grad_norm": 1.5703125,
2675
+ "learning_rate": 4.7640000000000005e-06,
2676
+ "loss": 0.2568,
2677
+ "step": 3810
2678
+ },
2679
+ {
2680
+ "epoch": 0.9590459752079084,
2681
+ "grad_norm": 1.6796875,
2682
+ "learning_rate": 4.724e-06,
2683
+ "loss": 0.2673,
2684
+ "step": 3820
2685
+ },
2686
+ {
2687
+ "epoch": 0.9615565667660443,
2688
+ "grad_norm": 1.625,
2689
+ "learning_rate": 4.684e-06,
2690
+ "loss": 0.2622,
2691
+ "step": 3830
2692
+ },
2693
+ {
2694
+ "epoch": 0.9640671583241801,
2695
+ "grad_norm": 1.5625,
2696
+ "learning_rate": 4.644e-06,
2697
+ "loss": 0.2656,
2698
+ "step": 3840
2699
+ },
2700
+ {
2701
+ "epoch": 0.966577749882316,
2702
+ "grad_norm": 1.4609375,
2703
+ "learning_rate": 4.604e-06,
2704
+ "loss": 0.2581,
2705
+ "step": 3850
2706
+ },
2707
+ {
2708
+ "epoch": 0.9690883414404519,
2709
+ "grad_norm": 1.6875,
2710
+ "learning_rate": 4.564e-06,
2711
+ "loss": 0.2529,
2712
+ "step": 3860
2713
+ },
2714
+ {
2715
+ "epoch": 0.9715989329985878,
2716
+ "grad_norm": 1.8125,
2717
+ "learning_rate": 4.524e-06,
2718
+ "loss": 0.284,
2719
+ "step": 3870
2720
+ },
2721
+ {
2722
+ "epoch": 0.9741095245567237,
2723
+ "grad_norm": 2.484375,
2724
+ "learning_rate": 4.484000000000001e-06,
2725
+ "loss": 0.2596,
2726
+ "step": 3880
2727
+ },
2728
+ {
2729
+ "epoch": 0.9766201161148595,
2730
+ "grad_norm": 1.5390625,
2731
+ "learning_rate": 4.444e-06,
2732
+ "loss": 0.2759,
2733
+ "step": 3890
2734
+ },
2735
+ {
2736
+ "epoch": 0.9791307076729955,
2737
+ "grad_norm": 1.46875,
2738
+ "learning_rate": 4.4040000000000005e-06,
2739
+ "loss": 0.2563,
2740
+ "step": 3900
2741
+ },
2742
+ {
2743
+ "epoch": 0.9816412992311313,
2744
+ "grad_norm": 1.53125,
2745
+ "learning_rate": 4.364e-06,
2746
+ "loss": 0.25,
2747
+ "step": 3910
2748
+ },
2749
+ {
2750
+ "epoch": 0.9841518907892672,
2751
+ "grad_norm": 1.875,
2752
+ "learning_rate": 4.3240000000000004e-06,
2753
+ "loss": 0.2747,
2754
+ "step": 3920
2755
+ },
2756
+ {
2757
+ "epoch": 0.9866624823474031,
2758
+ "grad_norm": 1.6640625,
2759
+ "learning_rate": 4.284e-06,
2760
+ "loss": 0.2691,
2761
+ "step": 3930
2762
+ },
2763
+ {
2764
+ "epoch": 0.989173073905539,
2765
+ "grad_norm": 1.53125,
2766
+ "learning_rate": 4.244e-06,
2767
+ "loss": 0.2431,
2768
+ "step": 3940
2769
+ },
2770
+ {
2771
+ "epoch": 0.9916836654636749,
2772
+ "grad_norm": 1.46875,
2773
+ "learning_rate": 4.204e-06,
2774
+ "loss": 0.2422,
2775
+ "step": 3950
2776
+ },
2777
+ {
2778
+ "epoch": 0.9941942570218107,
2779
+ "grad_norm": 1.984375,
2780
+ "learning_rate": 4.164e-06,
2781
+ "loss": 0.2554,
2782
+ "step": 3960
2783
+ },
2784
+ {
2785
+ "epoch": 0.9967048485799467,
2786
+ "grad_norm": 1.671875,
2787
+ "learning_rate": 4.124e-06,
2788
+ "loss": 0.2659,
2789
+ "step": 3970
2790
+ },
2791
+ {
2792
+ "epoch": 0.9992154401380825,
2793
+ "grad_norm": 1.875,
2794
+ "learning_rate": 4.084e-06,
2795
+ "loss": 0.2563,
2796
+ "step": 3980
2797
+ },
2798
+ {
2799
+ "epoch": 1.0015063549348815,
2800
+ "grad_norm": 1.53125,
2801
+ "learning_rate": 4.044e-06,
2802
+ "loss": 0.2382,
2803
+ "step": 3990
2804
+ },
2805
+ {
2806
+ "epoch": 1.0040169464930173,
2807
+ "grad_norm": 1.34375,
2808
+ "learning_rate": 4.004e-06,
2809
+ "loss": 0.2385,
2810
+ "step": 4000
2811
+ },
2812
+ {
2813
+ "epoch": 1.0065275380511534,
2814
+ "grad_norm": 1.4921875,
2815
+ "learning_rate": 3.964e-06,
2816
+ "loss": 0.2354,
2817
+ "step": 4010
2818
+ },
2819
+ {
2820
+ "epoch": 1.0090381296092892,
2821
+ "grad_norm": 1.578125,
2822
+ "learning_rate": 3.924000000000001e-06,
2823
+ "loss": 0.2446,
2824
+ "step": 4020
2825
+ },
2826
+ {
2827
+ "epoch": 1.011548721167425,
2828
+ "grad_norm": 1.5703125,
2829
+ "learning_rate": 3.884e-06,
2830
+ "loss": 0.2355,
2831
+ "step": 4030
2832
+ },
2833
+ {
2834
+ "epoch": 1.014059312725561,
2835
+ "grad_norm": 1.4609375,
2836
+ "learning_rate": 3.844000000000001e-06,
2837
+ "loss": 0.2358,
2838
+ "step": 4040
2839
+ },
2840
+ {
2841
+ "epoch": 1.0165699042836969,
2842
+ "grad_norm": 1.6171875,
2843
+ "learning_rate": 3.8040000000000003e-06,
2844
+ "loss": 0.2387,
2845
+ "step": 4050
2846
+ },
2847
+ {
2848
+ "epoch": 1.0190804958418327,
2849
+ "grad_norm": 1.6015625,
2850
+ "learning_rate": 3.7640000000000003e-06,
2851
+ "loss": 0.2342,
2852
+ "step": 4060
2853
+ },
2854
+ {
2855
+ "epoch": 1.0215910873999685,
2856
+ "grad_norm": 1.5546875,
2857
+ "learning_rate": 3.7240000000000003e-06,
2858
+ "loss": 0.2381,
2859
+ "step": 4070
2860
+ },
2861
+ {
2862
+ "epoch": 1.0241016789581046,
2863
+ "grad_norm": 1.765625,
2864
+ "learning_rate": 3.6840000000000002e-06,
2865
+ "loss": 0.2392,
2866
+ "step": 4080
2867
+ },
2868
+ {
2869
+ "epoch": 1.0266122705162404,
2870
+ "grad_norm": 1.515625,
2871
+ "learning_rate": 3.644e-06,
2872
+ "loss": 0.2335,
2873
+ "step": 4090
2874
+ },
2875
+ {
2876
+ "epoch": 1.0291228620743762,
2877
+ "grad_norm": 1.453125,
2878
+ "learning_rate": 3.604e-06,
2879
+ "loss": 0.2544,
2880
+ "step": 4100
2881
+ },
2882
+ {
2883
+ "epoch": 1.0316334536325122,
2884
+ "grad_norm": 1.4296875,
2885
+ "learning_rate": 3.564e-06,
2886
+ "loss": 0.2254,
2887
+ "step": 4110
2888
+ },
2889
+ {
2890
+ "epoch": 1.034144045190648,
2891
+ "grad_norm": 1.7734375,
2892
+ "learning_rate": 3.524e-06,
2893
+ "loss": 0.2443,
2894
+ "step": 4120
2895
+ },
2896
+ {
2897
+ "epoch": 1.0366546367487839,
2898
+ "grad_norm": 1.6640625,
2899
+ "learning_rate": 3.484e-06,
2900
+ "loss": 0.2492,
2901
+ "step": 4130
2902
+ },
2903
+ {
2904
+ "epoch": 1.0391652283069197,
2905
+ "grad_norm": 1.4296875,
2906
+ "learning_rate": 3.444e-06,
2907
+ "loss": 0.2285,
2908
+ "step": 4140
2909
+ },
2910
+ {
2911
+ "epoch": 1.0416758198650558,
2912
+ "grad_norm": 1.7109375,
2913
+ "learning_rate": 3.404e-06,
2914
+ "loss": 0.2309,
2915
+ "step": 4150
2916
+ },
2917
+ {
2918
+ "epoch": 1.0441864114231916,
2919
+ "grad_norm": 1.78125,
2920
+ "learning_rate": 3.364e-06,
2921
+ "loss": 0.2477,
2922
+ "step": 4160
2923
+ },
2924
+ {
2925
+ "epoch": 1.0466970029813274,
2926
+ "grad_norm": 1.7265625,
2927
+ "learning_rate": 3.324e-06,
2928
+ "loss": 0.2395,
2929
+ "step": 4170
2930
+ },
2931
+ {
2932
+ "epoch": 1.0492075945394634,
2933
+ "grad_norm": 1.5234375,
2934
+ "learning_rate": 3.2840000000000007e-06,
2935
+ "loss": 0.2266,
2936
+ "step": 4180
2937
+ },
2938
+ {
2939
+ "epoch": 1.0517181860975993,
2940
+ "grad_norm": 2.046875,
2941
+ "learning_rate": 3.2440000000000006e-06,
2942
+ "loss": 0.2382,
2943
+ "step": 4190
2944
+ },
2945
+ {
2946
+ "epoch": 1.054228777655735,
2947
+ "grad_norm": 1.8125,
2948
+ "learning_rate": 3.2040000000000006e-06,
2949
+ "loss": 0.2315,
2950
+ "step": 4200
2951
+ },
2952
+ {
2953
+ "epoch": 1.056739369213871,
2954
+ "grad_norm": 1.7109375,
2955
+ "learning_rate": 3.1640000000000005e-06,
2956
+ "loss": 0.2399,
2957
+ "step": 4210
2958
+ },
2959
+ {
2960
+ "epoch": 1.059249960772007,
2961
+ "grad_norm": 1.5703125,
2962
+ "learning_rate": 3.1240000000000005e-06,
2963
+ "loss": 0.2287,
2964
+ "step": 4220
2965
+ },
2966
+ {
2967
+ "epoch": 1.0617605523301428,
2968
+ "grad_norm": 1.4453125,
2969
+ "learning_rate": 3.0840000000000005e-06,
2970
+ "loss": 0.2399,
2971
+ "step": 4230
2972
+ },
2973
+ {
2974
+ "epoch": 1.0642711438882786,
2975
+ "grad_norm": 1.6171875,
2976
+ "learning_rate": 3.0440000000000004e-06,
2977
+ "loss": 0.2334,
2978
+ "step": 4240
2979
+ },
2980
+ {
2981
+ "epoch": 1.0667817354464146,
2982
+ "grad_norm": 1.671875,
2983
+ "learning_rate": 3.0040000000000004e-06,
2984
+ "loss": 0.2324,
2985
+ "step": 4250
2986
+ },
2987
+ {
2988
+ "epoch": 1.0692923270045505,
2989
+ "grad_norm": 1.5859375,
2990
+ "learning_rate": 2.9640000000000003e-06,
2991
+ "loss": 0.231,
2992
+ "step": 4260
2993
+ },
2994
+ {
2995
+ "epoch": 1.0718029185626863,
2996
+ "grad_norm": 1.640625,
2997
+ "learning_rate": 2.9240000000000003e-06,
2998
+ "loss": 0.2465,
2999
+ "step": 4270
3000
+ },
3001
+ {
3002
+ "epoch": 1.074313510120822,
3003
+ "grad_norm": 1.796875,
3004
+ "learning_rate": 2.8840000000000003e-06,
3005
+ "loss": 0.2465,
3006
+ "step": 4280
3007
+ },
3008
+ {
3009
+ "epoch": 1.0768241016789581,
3010
+ "grad_norm": 1.4375,
3011
+ "learning_rate": 2.8440000000000002e-06,
3012
+ "loss": 0.2514,
3013
+ "step": 4290
3014
+ },
3015
+ {
3016
+ "epoch": 1.079334693237094,
3017
+ "grad_norm": 1.71875,
3018
+ "learning_rate": 2.804e-06,
3019
+ "loss": 0.2318,
3020
+ "step": 4300
3021
+ },
3022
+ {
3023
+ "epoch": 1.0818452847952298,
3024
+ "grad_norm": 1.5234375,
3025
+ "learning_rate": 2.764e-06,
3026
+ "loss": 0.2366,
3027
+ "step": 4310
3028
+ },
3029
+ {
3030
+ "epoch": 1.0843558763533658,
3031
+ "grad_norm": 1.46875,
3032
+ "learning_rate": 2.724e-06,
3033
+ "loss": 0.2328,
3034
+ "step": 4320
3035
+ },
3036
+ {
3037
+ "epoch": 1.0868664679115017,
3038
+ "grad_norm": 1.734375,
3039
+ "learning_rate": 2.6840000000000005e-06,
3040
+ "loss": 0.2566,
3041
+ "step": 4330
3042
+ },
3043
+ {
3044
+ "epoch": 1.0893770594696375,
3045
+ "grad_norm": 1.4296875,
3046
+ "learning_rate": 2.6440000000000004e-06,
3047
+ "loss": 0.2243,
3048
+ "step": 4340
3049
+ },
3050
+ {
3051
+ "epoch": 1.0918876510277735,
3052
+ "grad_norm": 1.703125,
3053
+ "learning_rate": 2.6040000000000004e-06,
3054
+ "loss": 0.2234,
3055
+ "step": 4350
3056
+ },
3057
+ {
3058
+ "epoch": 1.0943982425859093,
3059
+ "grad_norm": 1.7421875,
3060
+ "learning_rate": 2.5640000000000004e-06,
3061
+ "loss": 0.2287,
3062
+ "step": 4360
3063
+ },
3064
+ {
3065
+ "epoch": 1.0969088341440452,
3066
+ "grad_norm": 1.5703125,
3067
+ "learning_rate": 2.5240000000000003e-06,
3068
+ "loss": 0.2365,
3069
+ "step": 4370
3070
+ },
3071
+ {
3072
+ "epoch": 1.099419425702181,
3073
+ "grad_norm": 1.4296875,
3074
+ "learning_rate": 2.4840000000000003e-06,
3075
+ "loss": 0.2299,
3076
+ "step": 4380
3077
+ },
3078
+ {
3079
+ "epoch": 1.101930017260317,
3080
+ "grad_norm": 1.8359375,
3081
+ "learning_rate": 2.4440000000000002e-06,
3082
+ "loss": 0.24,
3083
+ "step": 4390
3084
+ },
3085
+ {
3086
+ "epoch": 1.1044406088184529,
3087
+ "grad_norm": 1.5703125,
3088
+ "learning_rate": 2.404e-06,
3089
+ "loss": 0.2292,
3090
+ "step": 4400
3091
+ },
3092
+ {
3093
+ "epoch": 1.1069512003765887,
3094
+ "grad_norm": 1.59375,
3095
+ "learning_rate": 2.364e-06,
3096
+ "loss": 0.2356,
3097
+ "step": 4410
3098
+ },
3099
+ {
3100
+ "epoch": 1.1094617919347247,
3101
+ "grad_norm": 1.8671875,
3102
+ "learning_rate": 2.324e-06,
3103
+ "loss": 0.2395,
3104
+ "step": 4420
3105
+ },
3106
+ {
3107
+ "epoch": 1.1119723834928605,
3108
+ "grad_norm": 1.7734375,
3109
+ "learning_rate": 2.284e-06,
3110
+ "loss": 0.2534,
3111
+ "step": 4430
3112
+ },
3113
+ {
3114
+ "epoch": 1.1144829750509964,
3115
+ "grad_norm": 1.6328125,
3116
+ "learning_rate": 2.244e-06,
3117
+ "loss": 0.2294,
3118
+ "step": 4440
3119
+ },
3120
+ {
3121
+ "epoch": 1.1169935666091322,
3122
+ "grad_norm": 1.6796875,
3123
+ "learning_rate": 2.2040000000000004e-06,
3124
+ "loss": 0.2428,
3125
+ "step": 4450
3126
+ },
3127
+ {
3128
+ "epoch": 1.1195041581672682,
3129
+ "grad_norm": 1.5,
3130
+ "learning_rate": 2.1640000000000004e-06,
3131
+ "loss": 0.2486,
3132
+ "step": 4460
3133
+ },
3134
+ {
3135
+ "epoch": 1.122014749725404,
3136
+ "grad_norm": 1.515625,
3137
+ "learning_rate": 2.1240000000000003e-06,
3138
+ "loss": 0.2428,
3139
+ "step": 4470
3140
+ },
3141
+ {
3142
+ "epoch": 1.1245253412835399,
3143
+ "grad_norm": 1.65625,
3144
+ "learning_rate": 2.0840000000000003e-06,
3145
+ "loss": 0.2438,
3146
+ "step": 4480
3147
+ },
3148
+ {
3149
+ "epoch": 1.127035932841676,
3150
+ "grad_norm": 1.796875,
3151
+ "learning_rate": 2.0440000000000003e-06,
3152
+ "loss": 0.2278,
3153
+ "step": 4490
3154
+ },
3155
+ {
3156
+ "epoch": 1.1295465243998117,
3157
+ "grad_norm": 1.640625,
3158
+ "learning_rate": 2.004e-06,
3159
+ "loss": 0.2306,
3160
+ "step": 4500
3161
+ },
3162
+ {
3163
+ "epoch": 1.1320571159579476,
3164
+ "grad_norm": 1.8203125,
3165
+ "learning_rate": 1.964e-06,
3166
+ "loss": 0.24,
3167
+ "step": 4510
3168
+ },
3169
+ {
3170
+ "epoch": 1.1345677075160836,
3171
+ "grad_norm": 1.96875,
3172
+ "learning_rate": 1.924e-06,
3173
+ "loss": 0.2492,
3174
+ "step": 4520
3175
+ },
3176
+ {
3177
+ "epoch": 1.1370782990742194,
3178
+ "grad_norm": 1.765625,
3179
+ "learning_rate": 1.8840000000000003e-06,
3180
+ "loss": 0.251,
3181
+ "step": 4530
3182
+ },
3183
+ {
3184
+ "epoch": 1.1395888906323552,
3185
+ "grad_norm": 1.6640625,
3186
+ "learning_rate": 1.8440000000000003e-06,
3187
+ "loss": 0.238,
3188
+ "step": 4540
3189
+ },
3190
+ {
3191
+ "epoch": 1.142099482190491,
3192
+ "grad_norm": 1.671875,
3193
+ "learning_rate": 1.8040000000000002e-06,
3194
+ "loss": 0.2424,
3195
+ "step": 4550
3196
+ },
3197
+ {
3198
+ "epoch": 1.144610073748627,
3199
+ "grad_norm": 1.515625,
3200
+ "learning_rate": 1.7640000000000002e-06,
3201
+ "loss": 0.2433,
3202
+ "step": 4560
3203
+ },
3204
+ {
3205
+ "epoch": 1.147120665306763,
3206
+ "grad_norm": 1.9453125,
3207
+ "learning_rate": 1.7240000000000001e-06,
3208
+ "loss": 0.2496,
3209
+ "step": 4570
3210
+ },
3211
+ {
3212
+ "epoch": 1.1496312568648988,
3213
+ "grad_norm": 1.484375,
3214
+ "learning_rate": 1.684e-06,
3215
+ "loss": 0.2571,
3216
+ "step": 4580
3217
+ },
3218
+ {
3219
+ "epoch": 1.1521418484230348,
3220
+ "grad_norm": 1.640625,
3221
+ "learning_rate": 1.644e-06,
3222
+ "loss": 0.2407,
3223
+ "step": 4590
3224
+ },
3225
+ {
3226
+ "epoch": 1.1546524399811706,
3227
+ "grad_norm": 1.375,
3228
+ "learning_rate": 1.604e-06,
3229
+ "loss": 0.2283,
3230
+ "step": 4600
3231
+ },
3232
+ {
3233
+ "epoch": 1.1571630315393064,
3234
+ "grad_norm": 1.71875,
3235
+ "learning_rate": 1.5640000000000002e-06,
3236
+ "loss": 0.2366,
3237
+ "step": 4610
3238
+ },
3239
+ {
3240
+ "epoch": 1.1596736230974423,
3241
+ "grad_norm": 1.546875,
3242
+ "learning_rate": 1.5240000000000001e-06,
3243
+ "loss": 0.2286,
3244
+ "step": 4620
3245
+ },
3246
+ {
3247
+ "epoch": 1.1621842146555783,
3248
+ "grad_norm": 1.8046875,
3249
+ "learning_rate": 1.4840000000000001e-06,
3250
+ "loss": 0.2388,
3251
+ "step": 4630
3252
+ },
3253
+ {
3254
+ "epoch": 1.1646948062137141,
3255
+ "grad_norm": 1.65625,
3256
+ "learning_rate": 1.444e-06,
3257
+ "loss": 0.2334,
3258
+ "step": 4640
3259
+ },
3260
+ {
3261
+ "epoch": 1.16720539777185,
3262
+ "grad_norm": 1.3984375,
3263
+ "learning_rate": 1.404e-06,
3264
+ "loss": 0.2291,
3265
+ "step": 4650
3266
+ },
3267
+ {
3268
+ "epoch": 1.169715989329986,
3269
+ "grad_norm": 1.6953125,
3270
+ "learning_rate": 1.364e-06,
3271
+ "loss": 0.237,
3272
+ "step": 4660
3273
+ },
3274
+ {
3275
+ "epoch": 1.1722265808881218,
3276
+ "grad_norm": 1.6796875,
3277
+ "learning_rate": 1.324e-06,
3278
+ "loss": 0.2413,
3279
+ "step": 4670
3280
+ },
3281
+ {
3282
+ "epoch": 1.1747371724462576,
3283
+ "grad_norm": 1.75,
3284
+ "learning_rate": 1.284e-06,
3285
+ "loss": 0.2466,
3286
+ "step": 4680
3287
+ },
3288
+ {
3289
+ "epoch": 1.1772477640043935,
3290
+ "grad_norm": 1.5859375,
3291
+ "learning_rate": 1.244e-06,
3292
+ "loss": 0.2375,
3293
+ "step": 4690
3294
+ },
3295
+ {
3296
+ "epoch": 1.1797583555625295,
3297
+ "grad_norm": 1.8046875,
3298
+ "learning_rate": 1.204e-06,
3299
+ "loss": 0.2333,
3300
+ "step": 4700
3301
+ },
3302
+ {
3303
+ "epoch": 1.1822689471206653,
3304
+ "grad_norm": 1.6640625,
3305
+ "learning_rate": 1.1640000000000002e-06,
3306
+ "loss": 0.222,
3307
+ "step": 4710
3308
+ },
3309
+ {
3310
+ "epoch": 1.1847795386788011,
3311
+ "grad_norm": 1.71875,
3312
+ "learning_rate": 1.1240000000000002e-06,
3313
+ "loss": 0.238,
3314
+ "step": 4720
3315
+ },
3316
+ {
3317
+ "epoch": 1.1872901302369372,
3318
+ "grad_norm": 1.5859375,
3319
+ "learning_rate": 1.0840000000000001e-06,
3320
+ "loss": 0.2399,
3321
+ "step": 4730
3322
+ },
3323
+ {
3324
+ "epoch": 1.189800721795073,
3325
+ "grad_norm": 1.703125,
3326
+ "learning_rate": 1.044e-06,
3327
+ "loss": 0.2276,
3328
+ "step": 4740
3329
+ },
3330
+ {
3331
+ "epoch": 1.1923113133532088,
3332
+ "grad_norm": 1.734375,
3333
+ "learning_rate": 1.004e-06,
3334
+ "loss": 0.2247,
3335
+ "step": 4750
3336
+ },
3337
+ {
3338
+ "epoch": 1.1948219049113447,
3339
+ "grad_norm": 1.6953125,
3340
+ "learning_rate": 9.64e-07,
3341
+ "loss": 0.2379,
3342
+ "step": 4760
3343
+ },
3344
+ {
3345
+ "epoch": 1.1973324964694807,
3346
+ "grad_norm": 1.5859375,
3347
+ "learning_rate": 9.240000000000001e-07,
3348
+ "loss": 0.233,
3349
+ "step": 4770
3350
+ },
3351
+ {
3352
+ "epoch": 1.1998430880276165,
3353
+ "grad_norm": 1.4921875,
3354
+ "learning_rate": 8.840000000000001e-07,
3355
+ "loss": 0.233,
3356
+ "step": 4780
3357
+ },
3358
+ {
3359
+ "epoch": 1.2023536795857523,
3360
+ "grad_norm": 1.671875,
3361
+ "learning_rate": 8.440000000000001e-07,
3362
+ "loss": 0.2334,
3363
+ "step": 4790
3364
+ },
3365
+ {
3366
+ "epoch": 1.2048642711438884,
3367
+ "grad_norm": 1.3984375,
3368
+ "learning_rate": 8.04e-07,
3369
+ "loss": 0.2459,
3370
+ "step": 4800
3371
+ },
3372
+ {
3373
+ "epoch": 1.2073748627020242,
3374
+ "grad_norm": 1.40625,
3375
+ "learning_rate": 7.64e-07,
3376
+ "loss": 0.2286,
3377
+ "step": 4810
3378
+ },
3379
+ {
3380
+ "epoch": 1.20988545426016,
3381
+ "grad_norm": 1.546875,
3382
+ "learning_rate": 7.240000000000001e-07,
3383
+ "loss": 0.2372,
3384
+ "step": 4820
3385
+ },
3386
+ {
3387
+ "epoch": 1.2123960458182959,
3388
+ "grad_norm": 1.578125,
3389
+ "learning_rate": 6.84e-07,
3390
+ "loss": 0.2399,
3391
+ "step": 4830
3392
+ },
3393
+ {
3394
+ "epoch": 1.214906637376432,
3395
+ "grad_norm": 1.6640625,
3396
+ "learning_rate": 6.44e-07,
3397
+ "loss": 0.2309,
3398
+ "step": 4840
3399
+ },
3400
+ {
3401
+ "epoch": 1.2174172289345677,
3402
+ "grad_norm": 1.5234375,
3403
+ "learning_rate": 6.040000000000001e-07,
3404
+ "loss": 0.2481,
3405
+ "step": 4850
3406
+ },
3407
+ {
3408
+ "epoch": 1.2199278204927035,
3409
+ "grad_norm": 1.6015625,
3410
+ "learning_rate": 5.64e-07,
3411
+ "loss": 0.234,
3412
+ "step": 4860
3413
+ },
3414
+ {
3415
+ "epoch": 1.2224384120508396,
3416
+ "grad_norm": 1.46875,
3417
+ "learning_rate": 5.240000000000001e-07,
3418
+ "loss": 0.2331,
3419
+ "step": 4870
3420
+ },
3421
+ {
3422
+ "epoch": 1.2249490036089754,
3423
+ "grad_norm": 1.8984375,
3424
+ "learning_rate": 4.84e-07,
3425
+ "loss": 0.2528,
3426
+ "step": 4880
3427
+ },
3428
+ {
3429
+ "epoch": 1.2274595951671112,
3430
+ "grad_norm": 1.8515625,
3431
+ "learning_rate": 4.4400000000000006e-07,
3432
+ "loss": 0.2312,
3433
+ "step": 4890
3434
+ },
3435
+ {
3436
+ "epoch": 1.229970186725247,
3437
+ "grad_norm": 1.609375,
3438
+ "learning_rate": 4.04e-07,
3439
+ "loss": 0.241,
3440
+ "step": 4900
3441
+ },
3442
+ {
3443
+ "epoch": 1.232480778283383,
3444
+ "grad_norm": 1.6328125,
3445
+ "learning_rate": 3.6400000000000003e-07,
3446
+ "loss": 0.2346,
3447
+ "step": 4910
3448
+ },
3449
+ {
3450
+ "epoch": 1.234991369841519,
3451
+ "grad_norm": 1.6484375,
3452
+ "learning_rate": 3.24e-07,
3453
+ "loss": 0.2492,
3454
+ "step": 4920
3455
+ },
3456
+ {
3457
+ "epoch": 1.2375019613996547,
3458
+ "grad_norm": 1.625,
3459
+ "learning_rate": 2.8400000000000005e-07,
3460
+ "loss": 0.2437,
3461
+ "step": 4930
3462
+ },
3463
+ {
3464
+ "epoch": 1.2400125529577908,
3465
+ "grad_norm": 2.0,
3466
+ "learning_rate": 2.44e-07,
3467
+ "loss": 0.2566,
3468
+ "step": 4940
3469
+ },
3470
+ {
3471
+ "epoch": 1.2425231445159266,
3472
+ "grad_norm": 1.7734375,
3473
+ "learning_rate": 2.0400000000000003e-07,
3474
+ "loss": 0.2319,
3475
+ "step": 4950
3476
+ },
3477
+ {
3478
+ "epoch": 1.2450337360740624,
3479
+ "grad_norm": 1.453125,
3480
+ "learning_rate": 1.6400000000000004e-07,
3481
+ "loss": 0.2338,
3482
+ "step": 4960
3483
+ },
3484
+ {
3485
+ "epoch": 1.2475443276321982,
3486
+ "grad_norm": 1.75,
3487
+ "learning_rate": 1.24e-07,
3488
+ "loss": 0.2302,
3489
+ "step": 4970
3490
+ },
3491
+ {
3492
+ "epoch": 1.2500549191903343,
3493
+ "grad_norm": 1.6953125,
3494
+ "learning_rate": 8.4e-08,
3495
+ "loss": 0.2347,
3496
+ "step": 4980
3497
+ },
3498
+ {
3499
+ "epoch": 1.2525655107484701,
3500
+ "grad_norm": 1.5859375,
3501
+ "learning_rate": 4.4000000000000004e-08,
3502
+ "loss": 0.2331,
3503
+ "step": 4990
3504
+ },
3505
+ {
3506
+ "epoch": 1.255076102306606,
3507
+ "grad_norm": 1.4765625,
3508
+ "learning_rate": 4e-09,
3509
+ "loss": 0.2249,
3510
+ "step": 5000
3511
+ }
3512
+ ],
3513
+ "logging_steps": 10,
3514
+ "max_steps": 5000,
3515
+ "num_input_tokens_seen": 0,
3516
+ "num_train_epochs": 2,
3517
+ "save_steps": 500,
3518
+ "stateful_callbacks": {
3519
+ "TrainerControl": {
3520
+ "args": {
3521
+ "should_epoch_stop": false,
3522
+ "should_evaluate": false,
3523
+ "should_log": false,
3524
+ "should_save": true,
3525
+ "should_training_stop": true
3526
+ },
3527
+ "attributes": {}
3528
+ }
3529
+ },
3530
+ "total_flos": 3.5481985197050757e+18,
3531
+ "train_batch_size": 1,
3532
+ "trial_name": null,
3533
+ "trial_params": null
3534
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453a573b76b43963ddfc5159ef89ab0e258df03a82b42d345c3f13a661915b1f
3
+ size 5713
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128001,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.52.4",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.52.4"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f3a42cf3e7cfda21946e76131d2b59ed98c6465cd74051c5f9693ed54c6aa4
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a81226bcdf2579911c160f4f39dbfbb92a4759fc7c2a7d27af55245bda8b13
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ffb7741da438a74a56dca55a4d9315aed10dcdf64bb10e1d2dac3232c8aa57e
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac46fce1898f637da07a978aade60c7bd8f839c126b4332c0d235fd7a01a7e1
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
runs/Jun22_21-19-34_192-222-57-57/events.out.tfevents.1750627174.192-222-57-57.5985.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d46eafc3fcb28f0baf3a00b88639937a8e5d29f5a35bef424a563b7bc43480
3
+ size 5564
runs/Jun22_21-21-14_192-222-57-57/events.out.tfevents.1750627274.192-222-57-57.6587.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5975787734ced78ed093812a28a227a75d071a3ab8fb905b9cc35f78d200633a
3
+ size 110956
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
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 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizer"
2063
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453a573b76b43963ddfc5159ef89ab0e258df03a82b42d345c3f13a661915b1f
3
+ size 5713