flydust commited on
Commit
87bf7fc
1 Parent(s): e647bca

update ckps

Browse files
Files changed (36) hide show
  1. checkpoint-1100/config.json +28 -0
  2. checkpoint-1100/generation_config.json +9 -0
  3. checkpoint-1100/model-00001-of-00004.safetensors +3 -0
  4. checkpoint-1100/model-00002-of-00004.safetensors +3 -0
  5. checkpoint-1100/model-00003-of-00004.safetensors +3 -0
  6. checkpoint-1100/model-00004-of-00004.safetensors +3 -0
  7. checkpoint-1100/model.safetensors.index.json +298 -0
  8. checkpoint-1100/optimizer.pt +3 -0
  9. checkpoint-1100/rng_state_0.pth +3 -0
  10. checkpoint-1100/rng_state_1.pth +3 -0
  11. checkpoint-1100/rng_state_2.pth +3 -0
  12. checkpoint-1100/rng_state_3.pth +3 -0
  13. checkpoint-1100/scheduler.pt +3 -0
  14. checkpoint-1100/special_tokens_map.json +23 -0
  15. checkpoint-1100/tokenizer.json +0 -0
  16. checkpoint-1100/tokenizer_config.json +2062 -0
  17. checkpoint-1100/trainer_state.json +0 -0
  18. checkpoint-1100/training_args.bin +3 -0
  19. checkpoint-550/config.json +28 -0
  20. checkpoint-550/generation_config.json +9 -0
  21. checkpoint-550/model-00001-of-00004.safetensors +3 -0
  22. checkpoint-550/model-00002-of-00004.safetensors +3 -0
  23. checkpoint-550/model-00003-of-00004.safetensors +3 -0
  24. checkpoint-550/model-00004-of-00004.safetensors +3 -0
  25. checkpoint-550/model.safetensors.index.json +298 -0
  26. checkpoint-550/optimizer.pt +3 -0
  27. checkpoint-550/rng_state_0.pth +3 -0
  28. checkpoint-550/rng_state_1.pth +3 -0
  29. checkpoint-550/rng_state_2.pth +3 -0
  30. checkpoint-550/rng_state_3.pth +3 -0
  31. checkpoint-550/scheduler.pt +3 -0
  32. checkpoint-550/special_tokens_map.json +23 -0
  33. checkpoint-550/tokenizer.json +0 -0
  34. checkpoint-550/tokenizer_config.json +2062 -0
  35. checkpoint-550/trainer_state.json +3895 -0
  36. checkpoint-550/training_args.bin +3 -0
checkpoint-1100/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.2",
26
+ "use_cache": false,
27
+ "vocab_size": 128256
28
+ }
checkpoint-1100/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": 128001,
5
+ "max_length": 4096,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.40.2"
9
+ }
checkpoint-1100/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232fcf8d569cd08a6d092fa9516b60fc8384a77e3f92a2cc544c74afa21034ee
3
+ size 4976698672
checkpoint-1100/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb482b6cbc5ff15f9549ccd12ea316d677540c453ee4fb8a9089734aecd91bb
3
+ size 4999802720
checkpoint-1100/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d85e5b0f7abb7610b0f2ea847aa2e8aa22eab09159fa660a0fcaff5eedd7099
3
+ size 4915916176
checkpoint-1100/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:723fa80970a3e347fd557efb2c6ce1f78bf9044342ed3e3a4fca905c5eaac315
3
+ size 1168138808
checkpoint-1100/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-1100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca401f13639026fc097de7815d2a54dd21e8338ff8f0ac2760a66334d651d46
3
+ size 16092247096
checkpoint-1100/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee97cd82dba4d425fdd8dfdb88d4a43d0d4b1979b5c81ab4a24914fb00d4f332
3
+ size 15024
checkpoint-1100/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91dad95440fb85dc4a31745642117165c1a72173b2e389679ea8c0b2b6fcd7e2
3
+ size 15024
checkpoint-1100/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98698326b023c2af02c94f18726ce52c7f7a6fe290734dd7edbe99bc807fcfa0
3
+ size 15024
checkpoint-1100/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:708e7c6b5bf8a327e688779ebc08830ce249928bcb1ff5c82b1b1d0bf6d2660b
3
+ size 15024
checkpoint-1100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb2acb191f948e5d92b9d269536618098e784289d6c134859ed5a871e7d297b
3
+ size 1064
checkpoint-1100/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-1100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
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
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-1100/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acfdd936d2ba45f8c9b9b7cbbc505a6f7b90e583f2d68f5ad65a25f1ea2d340d
3
+ size 6008
checkpoint-550/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.2",
26
+ "use_cache": false,
27
+ "vocab_size": 128256
28
+ }
checkpoint-550/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": 128001,
5
+ "max_length": 4096,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.40.2"
9
+ }
checkpoint-550/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5cf9c64d41b3ed25a1e5c37da50b864a51cc4d390c31090d7256adbeb73bb31
3
+ size 4976698672
checkpoint-550/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7786d405fd24a71db08c670b1a419b36feca494d8af05e075b82beea86ca75df
3
+ size 4999802720
checkpoint-550/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a17ae61bab7e91b19b9cc2eb9a4406c9e449184b3d54d180f213fff9b5f25e
3
+ size 4915916176
checkpoint-550/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ceda98323c59def29fb175cb5960f964c4cc1c45d231829cb7e8d356ffe0732
3
+ size 1168138808
checkpoint-550/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-550/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e959379ed2faf7c372e6cfa4a75a8893b414b46a1e7aecf8c127943c2603059d
3
+ size 16092247096
checkpoint-550/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70cc56408014c410353d4dd58ae9b03f4be043f5f800324f66fd8e20e99b840e
3
+ size 15024
checkpoint-550/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d1438e98cc9c53a6852464635ce62e9788e61eb3646b73e33813f487c4b6ae
3
+ size 15024
checkpoint-550/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4388add9cec90932f8ff0100d27a0574d98e1bad52ff89d44e31967d2b4fbfde
3
+ size 15024
checkpoint-550/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a705d6dfaae4f2c1b4b2be6b25a6eb521ffae6fcba21cc1531e97b60037ed079
3
+ size 15024
checkpoint-550/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3366184b3ff7fb80feac8e903a0f377f50ff4dce166ec2a60f98e82bf75e3b08
3
+ size 1064
checkpoint-550/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-550/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-550/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
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
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-550/trainer_state.json ADDED
@@ -0,0 +1,3895 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9990917347865577,
5
+ "eval_steps": 184,
6
+ "global_step": 550,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0018165304268846503,
13
+ "grad_norm": 38.5,
14
+ "learning_rate": 2.0000000000000002e-07,
15
+ "loss": 0.8686,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0018165304268846503,
20
+ "eval_loss": 0.866981029510498,
21
+ "eval_runtime": 34.9333,
22
+ "eval_samples_per_second": 5.725,
23
+ "eval_steps_per_second": 1.431,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0036330608537693005,
28
+ "grad_norm": 45.5,
29
+ "learning_rate": 4.0000000000000003e-07,
30
+ "loss": 0.8814,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.005449591280653951,
35
+ "grad_norm": 34.75,
36
+ "learning_rate": 6.000000000000001e-07,
37
+ "loss": 0.8713,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.007266121707538601,
42
+ "grad_norm": 26.625,
43
+ "learning_rate": 8.000000000000001e-07,
44
+ "loss": 0.8797,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.009082652134423252,
49
+ "grad_norm": 48.0,
50
+ "learning_rate": 1.0000000000000002e-06,
51
+ "loss": 0.8693,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.010899182561307902,
56
+ "grad_norm": 102.5,
57
+ "learning_rate": 1.2000000000000002e-06,
58
+ "loss": 0.877,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.012715712988192553,
63
+ "grad_norm": 73.5,
64
+ "learning_rate": 1.4000000000000001e-06,
65
+ "loss": 0.8732,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.014532243415077202,
70
+ "grad_norm": 143.0,
71
+ "learning_rate": 1.6000000000000001e-06,
72
+ "loss": 0.8666,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.01634877384196185,
77
+ "grad_norm": 58.75,
78
+ "learning_rate": 1.8000000000000001e-06,
79
+ "loss": 0.8559,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.018165304268846504,
84
+ "grad_norm": 56.0,
85
+ "learning_rate": 2.0000000000000003e-06,
86
+ "loss": 0.8493,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.019981834695731154,
91
+ "grad_norm": 68.5,
92
+ "learning_rate": 2.2e-06,
93
+ "loss": 0.8313,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.021798365122615803,
98
+ "grad_norm": 76.5,
99
+ "learning_rate": 2.4000000000000003e-06,
100
+ "loss": 0.8413,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.023614895549500452,
105
+ "grad_norm": 73.0,
106
+ "learning_rate": 2.6e-06,
107
+ "loss": 0.8287,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.025431425976385105,
112
+ "grad_norm": 21.875,
113
+ "learning_rate": 2.8000000000000003e-06,
114
+ "loss": 0.8349,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.027247956403269755,
119
+ "grad_norm": 62.75,
120
+ "learning_rate": 3e-06,
121
+ "loss": 0.8052,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.029064486830154404,
126
+ "grad_norm": 95.0,
127
+ "learning_rate": 3.2000000000000003e-06,
128
+ "loss": 0.8093,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.030881017257039057,
133
+ "grad_norm": 26.625,
134
+ "learning_rate": 3.4000000000000005e-06,
135
+ "loss": 0.7839,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.0326975476839237,
140
+ "grad_norm": 10.9375,
141
+ "learning_rate": 3.6000000000000003e-06,
142
+ "loss": 0.796,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.03451407811080836,
147
+ "grad_norm": 10.5,
148
+ "learning_rate": 3.8000000000000005e-06,
149
+ "loss": 0.7889,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.03633060853769301,
154
+ "grad_norm": 11.8125,
155
+ "learning_rate": 4.000000000000001e-06,
156
+ "loss": 0.776,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.03814713896457766,
161
+ "grad_norm": 5.65625,
162
+ "learning_rate": 4.2000000000000004e-06,
163
+ "loss": 0.7824,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.03996366939146231,
168
+ "grad_norm": 2.234375,
169
+ "learning_rate": 4.4e-06,
170
+ "loss": 0.7597,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.04178019981834696,
175
+ "grad_norm": 16.25,
176
+ "learning_rate": 4.600000000000001e-06,
177
+ "loss": 0.7666,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.043596730245231606,
182
+ "grad_norm": 11.75,
183
+ "learning_rate": 4.800000000000001e-06,
184
+ "loss": 0.7579,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.045413260672116255,
189
+ "grad_norm": 67.5,
190
+ "learning_rate": 5e-06,
191
+ "loss": 0.7548,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.047229791099000905,
196
+ "grad_norm": 78.5,
197
+ "learning_rate": 5.2e-06,
198
+ "loss": 0.754,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.04904632152588556,
203
+ "grad_norm": 71.5,
204
+ "learning_rate": 5.400000000000001e-06,
205
+ "loss": 0.7631,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.05086285195277021,
210
+ "grad_norm": 47.25,
211
+ "learning_rate": 5.600000000000001e-06,
212
+ "loss": 0.7508,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.05267938237965486,
217
+ "grad_norm": 14.6875,
218
+ "learning_rate": 5.8e-06,
219
+ "loss": 0.7522,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.05449591280653951,
224
+ "grad_norm": 7.5625,
225
+ "learning_rate": 6e-06,
226
+ "loss": 0.7282,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.05631244323342416,
231
+ "grad_norm": 8.375,
232
+ "learning_rate": 6.200000000000001e-06,
233
+ "loss": 0.7432,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.05812897366030881,
238
+ "grad_norm": 11.9375,
239
+ "learning_rate": 6.4000000000000006e-06,
240
+ "loss": 0.7436,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.05994550408719346,
245
+ "grad_norm": 3.046875,
246
+ "learning_rate": 6.600000000000001e-06,
247
+ "loss": 0.7403,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.061762034514078114,
252
+ "grad_norm": 3.6875,
253
+ "learning_rate": 6.800000000000001e-06,
254
+ "loss": 0.7307,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.06357856494096276,
259
+ "grad_norm": 2.171875,
260
+ "learning_rate": 7e-06,
261
+ "loss": 0.7297,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.0653950953678474,
266
+ "grad_norm": 35.0,
267
+ "learning_rate": 7.2000000000000005e-06,
268
+ "loss": 0.7254,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.06721162579473206,
273
+ "grad_norm": 2.609375,
274
+ "learning_rate": 7.4e-06,
275
+ "loss": 0.726,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.06902815622161672,
280
+ "grad_norm": 2.734375,
281
+ "learning_rate": 7.600000000000001e-06,
282
+ "loss": 0.7124,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.07084468664850137,
287
+ "grad_norm": 2.234375,
288
+ "learning_rate": 7.800000000000002e-06,
289
+ "loss": 0.7159,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.07266121707538602,
294
+ "grad_norm": 5.78125,
295
+ "learning_rate": 8.000000000000001e-06,
296
+ "loss": 0.7216,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.07447774750227067,
301
+ "grad_norm": 6.4375,
302
+ "learning_rate": 8.2e-06,
303
+ "loss": 0.7005,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.07629427792915532,
308
+ "grad_norm": 5.21875,
309
+ "learning_rate": 8.400000000000001e-06,
310
+ "loss": 0.7049,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.07811080835603997,
315
+ "grad_norm": 5.28125,
316
+ "learning_rate": 8.6e-06,
317
+ "loss": 0.6968,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.07992733878292461,
322
+ "grad_norm": 5.21875,
323
+ "learning_rate": 8.8e-06,
324
+ "loss": 0.6837,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.08174386920980926,
329
+ "grad_norm": 2.25,
330
+ "learning_rate": 9e-06,
331
+ "loss": 0.6973,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.08356039963669391,
336
+ "grad_norm": 24.25,
337
+ "learning_rate": 9.200000000000002e-06,
338
+ "loss": 0.6861,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.08537693006357856,
343
+ "grad_norm": 14.375,
344
+ "learning_rate": 9.4e-06,
345
+ "loss": 0.6894,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.08719346049046321,
350
+ "grad_norm": 7.84375,
351
+ "learning_rate": 9.600000000000001e-06,
352
+ "loss": 0.6908,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.08900999091734786,
357
+ "grad_norm": 3.28125,
358
+ "learning_rate": 9.800000000000001e-06,
359
+ "loss": 0.696,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.09082652134423251,
364
+ "grad_norm": 5.875,
365
+ "learning_rate": 1e-05,
366
+ "loss": 0.6732,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.09264305177111716,
371
+ "grad_norm": 3.109375,
372
+ "learning_rate": 1.02e-05,
373
+ "loss": 0.6765,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.09445958219800181,
378
+ "grad_norm": 3.953125,
379
+ "learning_rate": 1.04e-05,
380
+ "loss": 0.663,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.09627611262488647,
385
+ "grad_norm": 3.203125,
386
+ "learning_rate": 1.0600000000000002e-05,
387
+ "loss": 0.678,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.09809264305177112,
392
+ "grad_norm": 4.8125,
393
+ "learning_rate": 1.0800000000000002e-05,
394
+ "loss": 0.6655,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.09990917347865577,
399
+ "grad_norm": 2.59375,
400
+ "learning_rate": 1.1000000000000001e-05,
401
+ "loss": 0.6566,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.10172570390554042,
406
+ "grad_norm": 2.375,
407
+ "learning_rate": 1.1200000000000001e-05,
408
+ "loss": 0.6616,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.10354223433242507,
413
+ "grad_norm": 4.4375,
414
+ "learning_rate": 1.14e-05,
415
+ "loss": 0.6524,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.10535876475930972,
420
+ "grad_norm": 1.4375,
421
+ "learning_rate": 1.16e-05,
422
+ "loss": 0.6599,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.10717529518619437,
427
+ "grad_norm": 1.8828125,
428
+ "learning_rate": 1.18e-05,
429
+ "loss": 0.6574,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.10899182561307902,
434
+ "grad_norm": 3.0,
435
+ "learning_rate": 1.2e-05,
436
+ "loss": 0.6606,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.11080835603996367,
441
+ "grad_norm": 3.234375,
442
+ "learning_rate": 1.22e-05,
443
+ "loss": 0.6541,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.11262488646684832,
448
+ "grad_norm": 3.15625,
449
+ "learning_rate": 1.2400000000000002e-05,
450
+ "loss": 0.6331,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.11444141689373297,
455
+ "grad_norm": 1.390625,
456
+ "learning_rate": 1.2600000000000001e-05,
457
+ "loss": 0.6632,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.11625794732061762,
462
+ "grad_norm": 8.125,
463
+ "learning_rate": 1.2800000000000001e-05,
464
+ "loss": 0.6609,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.11807447774750227,
469
+ "grad_norm": 6.875,
470
+ "learning_rate": 1.3000000000000001e-05,
471
+ "loss": 0.6529,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.11989100817438691,
476
+ "grad_norm": 2.609375,
477
+ "learning_rate": 1.3200000000000002e-05,
478
+ "loss": 0.6448,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.12170753860127158,
483
+ "grad_norm": 3.078125,
484
+ "learning_rate": 1.3400000000000002e-05,
485
+ "loss": 0.6516,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.12352406902815623,
490
+ "grad_norm": 3.484375,
491
+ "learning_rate": 1.3600000000000002e-05,
492
+ "loss": 0.6437,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.12534059945504086,
497
+ "grad_norm": 2.140625,
498
+ "learning_rate": 1.38e-05,
499
+ "loss": 0.635,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.1271571298819255,
504
+ "grad_norm": 1.828125,
505
+ "learning_rate": 1.4e-05,
506
+ "loss": 0.6374,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.12897366030881016,
511
+ "grad_norm": 1.7265625,
512
+ "learning_rate": 1.4200000000000001e-05,
513
+ "loss": 0.648,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.1307901907356948,
518
+ "grad_norm": 2.015625,
519
+ "learning_rate": 1.4400000000000001e-05,
520
+ "loss": 0.6387,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.13260672116257946,
525
+ "grad_norm": 1.7734375,
526
+ "learning_rate": 1.46e-05,
527
+ "loss": 0.6249,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.1344232515894641,
532
+ "grad_norm": 1.453125,
533
+ "learning_rate": 1.48e-05,
534
+ "loss": 0.6266,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.1362397820163488,
539
+ "grad_norm": 2.265625,
540
+ "learning_rate": 1.5000000000000002e-05,
541
+ "loss": 0.6143,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.13805631244323344,
546
+ "grad_norm": 1.8203125,
547
+ "learning_rate": 1.5200000000000002e-05,
548
+ "loss": 0.6152,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.13987284287011809,
553
+ "grad_norm": 1.7578125,
554
+ "learning_rate": 1.54e-05,
555
+ "loss": 0.6254,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.14168937329700274,
560
+ "grad_norm": 1.9375,
561
+ "learning_rate": 1.5600000000000003e-05,
562
+ "loss": 0.6048,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.14350590372388738,
567
+ "grad_norm": 1.5390625,
568
+ "learning_rate": 1.58e-05,
569
+ "loss": 0.6151,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.14532243415077203,
574
+ "grad_norm": 1.5,
575
+ "learning_rate": 1.6000000000000003e-05,
576
+ "loss": 0.611,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.14713896457765668,
581
+ "grad_norm": 1.53125,
582
+ "learning_rate": 1.62e-05,
583
+ "loss": 0.6195,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.14895549500454133,
588
+ "grad_norm": 1.4140625,
589
+ "learning_rate": 1.64e-05,
590
+ "loss": 0.6244,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.15077202543142598,
595
+ "grad_norm": 1.90625,
596
+ "learning_rate": 1.66e-05,
597
+ "loss": 0.6003,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.15258855585831063,
602
+ "grad_norm": 1.4921875,
603
+ "learning_rate": 1.6800000000000002e-05,
604
+ "loss": 0.6004,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.15440508628519528,
609
+ "grad_norm": 1.640625,
610
+ "learning_rate": 1.7e-05,
611
+ "loss": 0.6015,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.15622161671207993,
616
+ "grad_norm": 1.453125,
617
+ "learning_rate": 1.72e-05,
618
+ "loss": 0.6015,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.15803814713896458,
623
+ "grad_norm": 1.328125,
624
+ "learning_rate": 1.7400000000000003e-05,
625
+ "loss": 0.596,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.15985467756584923,
630
+ "grad_norm": 1.6796875,
631
+ "learning_rate": 1.76e-05,
632
+ "loss": 0.6109,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.16167120799273388,
637
+ "grad_norm": 1.5,
638
+ "learning_rate": 1.7800000000000002e-05,
639
+ "loss": 0.5912,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.16348773841961853,
644
+ "grad_norm": 1.515625,
645
+ "learning_rate": 1.8e-05,
646
+ "loss": 0.6066,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.16530426884650318,
651
+ "grad_norm": 1.328125,
652
+ "learning_rate": 1.8200000000000002e-05,
653
+ "loss": 0.6014,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.16712079927338783,
658
+ "grad_norm": 1.6328125,
659
+ "learning_rate": 1.8400000000000003e-05,
660
+ "loss": 0.5858,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.16893732970027248,
665
+ "grad_norm": 1.296875,
666
+ "learning_rate": 1.86e-05,
667
+ "loss": 0.6087,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.17075386012715713,
672
+ "grad_norm": 1.4296875,
673
+ "learning_rate": 1.88e-05,
674
+ "loss": 0.609,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.17257039055404177,
679
+ "grad_norm": 1.9375,
680
+ "learning_rate": 1.9e-05,
681
+ "loss": 0.5747,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.17438692098092642,
686
+ "grad_norm": 1.3828125,
687
+ "learning_rate": 1.9200000000000003e-05,
688
+ "loss": 0.5767,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.17620345140781107,
693
+ "grad_norm": 1.8828125,
694
+ "learning_rate": 1.94e-05,
695
+ "loss": 0.5859,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.17801998183469572,
700
+ "grad_norm": 1.6484375,
701
+ "learning_rate": 1.9600000000000002e-05,
702
+ "loss": 0.5856,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.17983651226158037,
707
+ "grad_norm": 1.859375,
708
+ "learning_rate": 1.98e-05,
709
+ "loss": 0.5988,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.18165304268846502,
714
+ "grad_norm": 1.6328125,
715
+ "learning_rate": 2e-05,
716
+ "loss": 0.5928,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.18346957311534967,
721
+ "grad_norm": 1.6484375,
722
+ "learning_rate": 1.9999950652018585e-05,
723
+ "loss": 0.5682,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.18528610354223432,
728
+ "grad_norm": 1.3515625,
729
+ "learning_rate": 1.999980260856137e-05,
730
+ "loss": 0.5799,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.18710263396911897,
735
+ "grad_norm": 1.75,
736
+ "learning_rate": 1.99995558710895e-05,
737
+ "loss": 0.5892,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.18891916439600362,
742
+ "grad_norm": 1.25,
743
+ "learning_rate": 1.9999210442038164e-05,
744
+ "loss": 0.5722,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.1907356948228883,
749
+ "grad_norm": 1.7890625,
750
+ "learning_rate": 1.9998766324816606e-05,
751
+ "loss": 0.573,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.19255222524977295,
756
+ "grad_norm": 1.7890625,
757
+ "learning_rate": 1.9998223523808092e-05,
758
+ "loss": 0.5635,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.1943687556766576,
763
+ "grad_norm": 1.421875,
764
+ "learning_rate": 1.9997582044369843e-05,
765
+ "loss": 0.5743,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.19618528610354224,
770
+ "grad_norm": 1.609375,
771
+ "learning_rate": 1.9996841892833e-05,
772
+ "loss": 0.5653,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.1980018165304269,
777
+ "grad_norm": 1.3828125,
778
+ "learning_rate": 1.9996003076502567e-05,
779
+ "loss": 0.5792,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.19981834695731154,
784
+ "grad_norm": 1.515625,
785
+ "learning_rate": 1.9995065603657317e-05,
786
+ "loss": 0.5746,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.2016348773841962,
791
+ "grad_norm": 1.1796875,
792
+ "learning_rate": 1.9994029483549732e-05,
793
+ "loss": 0.5647,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.20345140781108084,
798
+ "grad_norm": 1.2890625,
799
+ "learning_rate": 1.9992894726405894e-05,
800
+ "loss": 0.5647,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.2052679382379655,
805
+ "grad_norm": 1.2890625,
806
+ "learning_rate": 1.9991661343425402e-05,
807
+ "loss": 0.5704,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.20708446866485014,
812
+ "grad_norm": 1.2890625,
813
+ "learning_rate": 1.999032934678125e-05,
814
+ "loss": 0.5676,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.2089009990917348,
819
+ "grad_norm": 1.203125,
820
+ "learning_rate": 1.9988898749619702e-05,
821
+ "loss": 0.568,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.21071752951861944,
826
+ "grad_norm": 1.40625,
827
+ "learning_rate": 1.998736956606018e-05,
828
+ "loss": 0.5689,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.2125340599455041,
833
+ "grad_norm": 1.328125,
834
+ "learning_rate": 1.9985741811195098e-05,
835
+ "loss": 0.5741,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.21435059037238874,
840
+ "grad_norm": 1.2890625,
841
+ "learning_rate": 1.998401550108975e-05,
842
+ "loss": 0.569,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.2161671207992734,
847
+ "grad_norm": 1.265625,
848
+ "learning_rate": 1.9982190652782122e-05,
849
+ "loss": 0.5636,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.21798365122615804,
854
+ "grad_norm": 1.28125,
855
+ "learning_rate": 1.9980267284282718e-05,
856
+ "loss": 0.5531,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.2198001816530427,
861
+ "grad_norm": 1.0625,
862
+ "learning_rate": 1.997824541457442e-05,
863
+ "loss": 0.5594,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.22161671207992734,
868
+ "grad_norm": 1.125,
869
+ "learning_rate": 1.9976125063612254e-05,
870
+ "loss": 0.5459,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.22343324250681199,
875
+ "grad_norm": 1.3046875,
876
+ "learning_rate": 1.997390625232324e-05,
877
+ "loss": 0.5517,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.22524977293369663,
882
+ "grad_norm": 1.609375,
883
+ "learning_rate": 1.997158900260614e-05,
884
+ "loss": 0.5602,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.22706630336058128,
889
+ "grad_norm": 1.1328125,
890
+ "learning_rate": 1.9969173337331283e-05,
891
+ "loss": 0.5568,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.22888283378746593,
896
+ "grad_norm": 1.2421875,
897
+ "learning_rate": 1.99666592803403e-05,
898
+ "loss": 0.5667,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.23069936421435058,
903
+ "grad_norm": 1.5703125,
904
+ "learning_rate": 1.9964046856445926e-05,
905
+ "loss": 0.5614,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.23251589464123523,
910
+ "grad_norm": 1.0703125,
911
+ "learning_rate": 1.9961336091431728e-05,
912
+ "loss": 0.5445,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.23433242506811988,
917
+ "grad_norm": 1.5078125,
918
+ "learning_rate": 1.995852701205186e-05,
919
+ "loss": 0.5668,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.23614895549500453,
924
+ "grad_norm": 1.15625,
925
+ "learning_rate": 1.99556196460308e-05,
926
+ "loss": 0.5474,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.23796548592188918,
931
+ "grad_norm": 1.53125,
932
+ "learning_rate": 1.9952614022063085e-05,
933
+ "loss": 0.5516,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.23978201634877383,
938
+ "grad_norm": 1.2734375,
939
+ "learning_rate": 1.9949510169813006e-05,
940
+ "loss": 0.5472,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.24159854677565848,
945
+ "grad_norm": 1.34375,
946
+ "learning_rate": 1.9946308119914323e-05,
947
+ "loss": 0.5502,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.24341507720254316,
952
+ "grad_norm": 1.5546875,
953
+ "learning_rate": 1.994300790396999e-05,
954
+ "loss": 0.5493,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.2452316076294278,
959
+ "grad_norm": 1.3125,
960
+ "learning_rate": 1.99396095545518e-05,
961
+ "loss": 0.5548,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.24704813805631246,
966
+ "grad_norm": 1.6328125,
967
+ "learning_rate": 1.9936113105200085e-05,
968
+ "loss": 0.5576,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.2488646684831971,
973
+ "grad_norm": 1.2421875,
974
+ "learning_rate": 1.9932518590423396e-05,
975
+ "loss": 0.5506,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.2506811989100817,
980
+ "grad_norm": 2.046875,
981
+ "learning_rate": 1.9928826045698138e-05,
982
+ "loss": 0.5462,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.2524977293369664,
987
+ "grad_norm": 1.71875,
988
+ "learning_rate": 1.992503550746824e-05,
989
+ "loss": 0.5623,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.254314259763851,
994
+ "grad_norm": 1.59375,
995
+ "learning_rate": 1.9921147013144782e-05,
996
+ "loss": 0.5529,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.2561307901907357,
1001
+ "grad_norm": 1.4375,
1002
+ "learning_rate": 1.9917160601105632e-05,
1003
+ "loss": 0.55,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.2579473206176203,
1008
+ "grad_norm": 1.421875,
1009
+ "learning_rate": 1.9913076310695068e-05,
1010
+ "loss": 0.5379,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.259763851044505,
1015
+ "grad_norm": 1.640625,
1016
+ "learning_rate": 1.990889418222339e-05,
1017
+ "loss": 0.5436,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.2615803814713896,
1022
+ "grad_norm": 1.3046875,
1023
+ "learning_rate": 1.9904614256966514e-05,
1024
+ "loss": 0.5423,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.2633969118982743,
1029
+ "grad_norm": 1.53125,
1030
+ "learning_rate": 1.990023657716558e-05,
1031
+ "loss": 0.5336,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.2652134423251589,
1036
+ "grad_norm": 1.1640625,
1037
+ "learning_rate": 1.989576118602651e-05,
1038
+ "loss": 0.5353,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.2670299727520436,
1043
+ "grad_norm": 1.65625,
1044
+ "learning_rate": 1.989118812771962e-05,
1045
+ "loss": 0.5512,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.2688465031789282,
1050
+ "grad_norm": 1.5546875,
1051
+ "learning_rate": 1.988651744737914e-05,
1052
+ "loss": 0.5402,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.2706630336058129,
1057
+ "grad_norm": 1.4453125,
1058
+ "learning_rate": 1.9881749191102807e-05,
1059
+ "loss": 0.5418,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.2724795640326976,
1064
+ "grad_norm": 1.390625,
1065
+ "learning_rate": 1.9876883405951378e-05,
1066
+ "loss": 0.5424,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.2742960944595822,
1071
+ "grad_norm": 1.28125,
1072
+ "learning_rate": 1.9871920139948193e-05,
1073
+ "loss": 0.522,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.2761126248864669,
1078
+ "grad_norm": 1.125,
1079
+ "learning_rate": 1.986685944207868e-05,
1080
+ "loss": 0.5352,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.2779291553133515,
1085
+ "grad_norm": 1.3984375,
1086
+ "learning_rate": 1.9861701362289892e-05,
1087
+ "loss": 0.5331,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.27974568574023617,
1092
+ "grad_norm": 1.1484375,
1093
+ "learning_rate": 1.9856445951489984e-05,
1094
+ "loss": 0.5345,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.2815622161671208,
1099
+ "grad_norm": 1.265625,
1100
+ "learning_rate": 1.985109326154774e-05,
1101
+ "loss": 0.5413,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.28337874659400547,
1106
+ "grad_norm": 1.1875,
1107
+ "learning_rate": 1.9845643345292055e-05,
1108
+ "loss": 0.5436,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.2851952770208901,
1113
+ "grad_norm": 1.265625,
1114
+ "learning_rate": 1.9840096256511398e-05,
1115
+ "loss": 0.5292,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.28701180744777477,
1120
+ "grad_norm": 1.265625,
1121
+ "learning_rate": 1.98344520499533e-05,
1122
+ "loss": 0.5216,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.2888283378746594,
1127
+ "grad_norm": 1.203125,
1128
+ "learning_rate": 1.9828710781323793e-05,
1129
+ "loss": 0.5282,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.29064486830154407,
1134
+ "grad_norm": 1.34375,
1135
+ "learning_rate": 1.982287250728689e-05,
1136
+ "loss": 0.5299,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.2924613987284287,
1141
+ "grad_norm": 1.3515625,
1142
+ "learning_rate": 1.9816937285463992e-05,
1143
+ "loss": 0.5237,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.29427792915531337,
1148
+ "grad_norm": 1.21875,
1149
+ "learning_rate": 1.981090517443334e-05,
1150
+ "loss": 0.5231,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.296094459582198,
1155
+ "grad_norm": 1.3203125,
1156
+ "learning_rate": 1.9804776233729446e-05,
1157
+ "loss": 0.544,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.29791099000908267,
1162
+ "grad_norm": 1.2578125,
1163
+ "learning_rate": 1.979855052384247e-05,
1164
+ "loss": 0.5439,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.2997275204359673,
1169
+ "grad_norm": 1.390625,
1170
+ "learning_rate": 1.979222810621766e-05,
1171
+ "loss": 0.5332,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.30154405086285196,
1176
+ "grad_norm": 1.2734375,
1177
+ "learning_rate": 1.978580904325472e-05,
1178
+ "loss": 0.5308,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.3033605812897366,
1183
+ "grad_norm": 1.234375,
1184
+ "learning_rate": 1.977929339830722e-05,
1185
+ "loss": 0.5259,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.30517711171662126,
1190
+ "grad_norm": 1.1796875,
1191
+ "learning_rate": 1.9772681235681936e-05,
1192
+ "loss": 0.5262,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 0.3069936421435059,
1197
+ "grad_norm": 1.6171875,
1198
+ "learning_rate": 1.976597262063825e-05,
1199
+ "loss": 0.5348,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 0.30881017257039056,
1204
+ "grad_norm": 1.2890625,
1205
+ "learning_rate": 1.9759167619387474e-05,
1206
+ "loss": 0.5412,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 0.3106267029972752,
1211
+ "grad_norm": 1.546875,
1212
+ "learning_rate": 1.9752266299092234e-05,
1213
+ "loss": 0.5194,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 0.31244323342415986,
1218
+ "grad_norm": 1.2421875,
1219
+ "learning_rate": 1.9745268727865774e-05,
1220
+ "loss": 0.5355,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 0.3142597638510445,
1225
+ "grad_norm": 1.3046875,
1226
+ "learning_rate": 1.9738174974771288e-05,
1227
+ "loss": 0.5241,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 0.31607629427792916,
1232
+ "grad_norm": 1.328125,
1233
+ "learning_rate": 1.9730985109821268e-05,
1234
+ "loss": 0.5317,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 0.3178928247048138,
1239
+ "grad_norm": 1.21875,
1240
+ "learning_rate": 1.9723699203976768e-05,
1241
+ "loss": 0.5216,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 0.31970935513169846,
1246
+ "grad_norm": 1.359375,
1247
+ "learning_rate": 1.971631732914674e-05,
1248
+ "loss": 0.5123,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 0.3215258855585831,
1253
+ "grad_norm": 1.09375,
1254
+ "learning_rate": 1.9708839558187313e-05,
1255
+ "loss": 0.5209,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 0.32334241598546776,
1260
+ "grad_norm": 1.3828125,
1261
+ "learning_rate": 1.970126596490106e-05,
1262
+ "loss": 0.5271,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 0.32515894641235243,
1267
+ "grad_norm": 1.15625,
1268
+ "learning_rate": 1.9693596624036294e-05,
1269
+ "loss": 0.5136,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 0.32697547683923706,
1274
+ "grad_norm": 1.34375,
1275
+ "learning_rate": 1.9685831611286312e-05,
1276
+ "loss": 0.5257,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.32879200726612173,
1281
+ "grad_norm": 1.375,
1282
+ "learning_rate": 1.9677971003288657e-05,
1283
+ "loss": 0.5186,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.33060853769300635,
1288
+ "grad_norm": 1.2578125,
1289
+ "learning_rate": 1.9670014877624353e-05,
1290
+ "loss": 0.5198,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.33242506811989103,
1295
+ "grad_norm": 1.203125,
1296
+ "learning_rate": 1.966196331281715e-05,
1297
+ "loss": 0.5207,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.33424159854677565,
1302
+ "grad_norm": 1.25,
1303
+ "learning_rate": 1.965381638833274e-05,
1304
+ "loss": 0.514,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.33424159854677565,
1309
+ "eval_loss": 0.5189763903617859,
1310
+ "eval_runtime": 34.9275,
1311
+ "eval_samples_per_second": 5.726,
1312
+ "eval_steps_per_second": 1.432,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 0.33605812897366033,
1317
+ "grad_norm": 1.109375,
1318
+ "learning_rate": 1.9645574184577982e-05,
1319
+ "loss": 0.5245,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 0.33787465940054495,
1324
+ "grad_norm": 1.328125,
1325
+ "learning_rate": 1.96372367829001e-05,
1326
+ "loss": 0.5097,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 0.33969118982742963,
1331
+ "grad_norm": 1.140625,
1332
+ "learning_rate": 1.9628804265585878e-05,
1333
+ "loss": 0.5277,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 0.34150772025431425,
1338
+ "grad_norm": 1.2734375,
1339
+ "learning_rate": 1.962027671586086e-05,
1340
+ "loss": 0.5154,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 0.34332425068119893,
1345
+ "grad_norm": 1.46875,
1346
+ "learning_rate": 1.961165421788852e-05,
1347
+ "loss": 0.5241,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.34514078110808355,
1352
+ "grad_norm": 1.171875,
1353
+ "learning_rate": 1.9602936856769432e-05,
1354
+ "loss": 0.5145,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.3469573115349682,
1359
+ "grad_norm": 1.3046875,
1360
+ "learning_rate": 1.959412471854043e-05,
1361
+ "loss": 0.5147,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.34877384196185285,
1366
+ "grad_norm": 1.1953125,
1367
+ "learning_rate": 1.958521789017376e-05,
1368
+ "loss": 0.5267,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.3505903723887375,
1373
+ "grad_norm": 1.09375,
1374
+ "learning_rate": 1.9576216459576222e-05,
1375
+ "loss": 0.5065,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.35240690281562215,
1380
+ "grad_norm": 1.15625,
1381
+ "learning_rate": 1.9567120515588307e-05,
1382
+ "loss": 0.5087,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.3542234332425068,
1387
+ "grad_norm": 1.2578125,
1388
+ "learning_rate": 1.9557930147983303e-05,
1389
+ "loss": 0.524,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.35603996366939145,
1394
+ "grad_norm": 1.3046875,
1395
+ "learning_rate": 1.9548645447466433e-05,
1396
+ "loss": 0.5176,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.3578564940962761,
1401
+ "grad_norm": 1.171875,
1402
+ "learning_rate": 1.9539266505673938e-05,
1403
+ "loss": 0.5081,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.35967302452316074,
1408
+ "grad_norm": 1.046875,
1409
+ "learning_rate": 1.952979341517219e-05,
1410
+ "loss": 0.5296,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.3614895549500454,
1415
+ "grad_norm": 1.140625,
1416
+ "learning_rate": 1.9520226269456767e-05,
1417
+ "loss": 0.4961,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.36330608537693004,
1422
+ "grad_norm": 1.1171875,
1423
+ "learning_rate": 1.9510565162951538e-05,
1424
+ "loss": 0.5091,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.3651226158038147,
1429
+ "grad_norm": 1.1015625,
1430
+ "learning_rate": 1.9500810191007717e-05,
1431
+ "loss": 0.5169,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.36693914623069934,
1436
+ "grad_norm": 1.015625,
1437
+ "learning_rate": 1.9490961449902946e-05,
1438
+ "loss": 0.5044,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.368755676657584,
1443
+ "grad_norm": 1.265625,
1444
+ "learning_rate": 1.948101903684032e-05,
1445
+ "loss": 0.5146,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.37057220708446864,
1450
+ "grad_norm": 1.1015625,
1451
+ "learning_rate": 1.9470983049947446e-05,
1452
+ "loss": 0.5171,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.3723887375113533,
1457
+ "grad_norm": 1.1484375,
1458
+ "learning_rate": 1.9460853588275454e-05,
1459
+ "loss": 0.5081,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.37420526793823794,
1464
+ "grad_norm": 1.1015625,
1465
+ "learning_rate": 1.945063075179805e-05,
1466
+ "loss": 0.5098,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.3760217983651226,
1471
+ "grad_norm": 1.0859375,
1472
+ "learning_rate": 1.94403146414105e-05,
1473
+ "loss": 0.5025,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.37783832879200724,
1478
+ "grad_norm": 1.125,
1479
+ "learning_rate": 1.9429905358928648e-05,
1480
+ "loss": 0.5231,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.3796548592188919,
1485
+ "grad_norm": 1.203125,
1486
+ "learning_rate": 1.9419403007087908e-05,
1487
+ "loss": 0.505,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.3814713896457766,
1492
+ "grad_norm": 1.203125,
1493
+ "learning_rate": 1.9408807689542257e-05,
1494
+ "loss": 0.4997,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.3832879200726612,
1499
+ "grad_norm": 1.0859375,
1500
+ "learning_rate": 1.9398119510863197e-05,
1501
+ "loss": 0.5099,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.3851044504995459,
1506
+ "grad_norm": 1.296875,
1507
+ "learning_rate": 1.9387338576538743e-05,
1508
+ "loss": 0.5036,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.3869209809264305,
1513
+ "grad_norm": 1.046875,
1514
+ "learning_rate": 1.9376464992972358e-05,
1515
+ "loss": 0.5158,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.3887375113533152,
1520
+ "grad_norm": 1.2421875,
1521
+ "learning_rate": 1.9365498867481926e-05,
1522
+ "loss": 0.5072,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.3905540417801998,
1527
+ "grad_norm": 1.0859375,
1528
+ "learning_rate": 1.9354440308298676e-05,
1529
+ "loss": 0.5058,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.3923705722070845,
1534
+ "grad_norm": 1.2421875,
1535
+ "learning_rate": 1.9343289424566122e-05,
1536
+ "loss": 0.4971,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.3941871026339691,
1541
+ "grad_norm": 1.15625,
1542
+ "learning_rate": 1.9332046326338985e-05,
1543
+ "loss": 0.504,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.3960036330608538,
1548
+ "grad_norm": 1.0859375,
1549
+ "learning_rate": 1.932071112458211e-05,
1550
+ "loss": 0.5174,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.3978201634877384,
1555
+ "grad_norm": 1.078125,
1556
+ "learning_rate": 1.930928393116936e-05,
1557
+ "loss": 0.5216,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.3996366939146231,
1562
+ "grad_norm": 1.15625,
1563
+ "learning_rate": 1.9297764858882516e-05,
1564
+ "loss": 0.4991,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.4014532243415077,
1569
+ "grad_norm": 1.0234375,
1570
+ "learning_rate": 1.9286154021410177e-05,
1571
+ "loss": 0.4929,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.4032697547683924,
1576
+ "grad_norm": 1.28125,
1577
+ "learning_rate": 1.9274451533346617e-05,
1578
+ "loss": 0.507,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.405086285195277,
1583
+ "grad_norm": 1.078125,
1584
+ "learning_rate": 1.926265751019067e-05,
1585
+ "loss": 0.4942,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.4069028156221617,
1590
+ "grad_norm": 1.2421875,
1591
+ "learning_rate": 1.925077206834458e-05,
1592
+ "loss": 0.4991,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.4087193460490463,
1597
+ "grad_norm": 1.1796875,
1598
+ "learning_rate": 1.9238795325112867e-05,
1599
+ "loss": 0.5008,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.410535876475931,
1604
+ "grad_norm": 1.09375,
1605
+ "learning_rate": 1.922672739870115e-05,
1606
+ "loss": 0.4975,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.4123524069028156,
1611
+ "grad_norm": 1.1796875,
1612
+ "learning_rate": 1.9214568408214986e-05,
1613
+ "loss": 0.4997,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.4141689373297003,
1618
+ "grad_norm": 0.984375,
1619
+ "learning_rate": 1.9202318473658707e-05,
1620
+ "loss": 0.5072,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.4159854677565849,
1625
+ "grad_norm": 1.3203125,
1626
+ "learning_rate": 1.9189977715934214e-05,
1627
+ "loss": 0.5099,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.4178019981834696,
1632
+ "grad_norm": 1.0390625,
1633
+ "learning_rate": 1.9177546256839814e-05,
1634
+ "loss": 0.508,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.4196185286103542,
1639
+ "grad_norm": 1.3046875,
1640
+ "learning_rate": 1.916502421906898e-05,
1641
+ "loss": 0.5061,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.4214350590372389,
1646
+ "grad_norm": 1.1171875,
1647
+ "learning_rate": 1.9152411726209176e-05,
1648
+ "loss": 0.511,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.4232515894641235,
1653
+ "grad_norm": 1.0703125,
1654
+ "learning_rate": 1.913970890274061e-05,
1655
+ "loss": 0.4973,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.4250681198910082,
1660
+ "grad_norm": 1.21875,
1661
+ "learning_rate": 1.912691587403503e-05,
1662
+ "loss": 0.5123,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.4268846503178928,
1667
+ "grad_norm": 1.0078125,
1668
+ "learning_rate": 1.9114032766354453e-05,
1669
+ "loss": 0.5033,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 0.4287011807447775,
1674
+ "grad_norm": 1.265625,
1675
+ "learning_rate": 1.9101059706849957e-05,
1676
+ "loss": 0.5,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 0.4305177111716621,
1681
+ "grad_norm": 1.1484375,
1682
+ "learning_rate": 1.9087996823560404e-05,
1683
+ "loss": 0.4999,
1684
+ "step": 237
1685
+ },
1686
+ {
1687
+ "epoch": 0.4323342415985468,
1688
+ "grad_norm": 1.21875,
1689
+ "learning_rate": 1.907484424541117e-05,
1690
+ "loss": 0.5152,
1691
+ "step": 238
1692
+ },
1693
+ {
1694
+ "epoch": 0.43415077202543145,
1695
+ "grad_norm": 0.98828125,
1696
+ "learning_rate": 1.9061602102212898e-05,
1697
+ "loss": 0.4996,
1698
+ "step": 239
1699
+ },
1700
+ {
1701
+ "epoch": 0.4359673024523161,
1702
+ "grad_norm": 1.140625,
1703
+ "learning_rate": 1.9048270524660197e-05,
1704
+ "loss": 0.4941,
1705
+ "step": 240
1706
+ },
1707
+ {
1708
+ "epoch": 0.43778383287920075,
1709
+ "grad_norm": 1.078125,
1710
+ "learning_rate": 1.903484964433035e-05,
1711
+ "loss": 0.4895,
1712
+ "step": 241
1713
+ },
1714
+ {
1715
+ "epoch": 0.4396003633060854,
1716
+ "grad_norm": 1.2109375,
1717
+ "learning_rate": 1.902133959368203e-05,
1718
+ "loss": 0.5014,
1719
+ "step": 242
1720
+ },
1721
+ {
1722
+ "epoch": 0.44141689373297005,
1723
+ "grad_norm": 0.96875,
1724
+ "learning_rate": 1.9007740506053983e-05,
1725
+ "loss": 0.4971,
1726
+ "step": 243
1727
+ },
1728
+ {
1729
+ "epoch": 0.44323342415985467,
1730
+ "grad_norm": 1.09375,
1731
+ "learning_rate": 1.899405251566371e-05,
1732
+ "loss": 0.4969,
1733
+ "step": 244
1734
+ },
1735
+ {
1736
+ "epoch": 0.44504995458673935,
1737
+ "grad_norm": 1.046875,
1738
+ "learning_rate": 1.8980275757606157e-05,
1739
+ "loss": 0.4883,
1740
+ "step": 245
1741
+ },
1742
+ {
1743
+ "epoch": 0.44686648501362397,
1744
+ "grad_norm": 1.1015625,
1745
+ "learning_rate": 1.896641036785236e-05,
1746
+ "loss": 0.5083,
1747
+ "step": 246
1748
+ },
1749
+ {
1750
+ "epoch": 0.44868301544050865,
1751
+ "grad_norm": 1.0078125,
1752
+ "learning_rate": 1.8952456483248117e-05,
1753
+ "loss": 0.4947,
1754
+ "step": 247
1755
+ },
1756
+ {
1757
+ "epoch": 0.45049954586739327,
1758
+ "grad_norm": 1.21875,
1759
+ "learning_rate": 1.893841424151264e-05,
1760
+ "loss": 0.5,
1761
+ "step": 248
1762
+ },
1763
+ {
1764
+ "epoch": 0.45231607629427795,
1765
+ "grad_norm": 1.0546875,
1766
+ "learning_rate": 1.892428378123718e-05,
1767
+ "loss": 0.4889,
1768
+ "step": 249
1769
+ },
1770
+ {
1771
+ "epoch": 0.45413260672116257,
1772
+ "grad_norm": 1.2734375,
1773
+ "learning_rate": 1.891006524188368e-05,
1774
+ "loss": 0.4956,
1775
+ "step": 250
1776
+ },
1777
+ {
1778
+ "epoch": 0.45594913714804725,
1779
+ "grad_norm": 1.28125,
1780
+ "learning_rate": 1.8895758763783383e-05,
1781
+ "loss": 0.5052,
1782
+ "step": 251
1783
+ },
1784
+ {
1785
+ "epoch": 0.45776566757493187,
1786
+ "grad_norm": 1.328125,
1787
+ "learning_rate": 1.8881364488135448e-05,
1788
+ "loss": 0.4849,
1789
+ "step": 252
1790
+ },
1791
+ {
1792
+ "epoch": 0.45958219800181654,
1793
+ "grad_norm": 1.25,
1794
+ "learning_rate": 1.8866882557005567e-05,
1795
+ "loss": 0.4914,
1796
+ "step": 253
1797
+ },
1798
+ {
1799
+ "epoch": 0.46139872842870117,
1800
+ "grad_norm": 1.296875,
1801
+ "learning_rate": 1.8852313113324553e-05,
1802
+ "loss": 0.5086,
1803
+ "step": 254
1804
+ },
1805
+ {
1806
+ "epoch": 0.46321525885558584,
1807
+ "grad_norm": 1.15625,
1808
+ "learning_rate": 1.8837656300886937e-05,
1809
+ "loss": 0.5043,
1810
+ "step": 255
1811
+ },
1812
+ {
1813
+ "epoch": 0.46503178928247046,
1814
+ "grad_norm": 1.125,
1815
+ "learning_rate": 1.8822912264349535e-05,
1816
+ "loss": 0.4941,
1817
+ "step": 256
1818
+ },
1819
+ {
1820
+ "epoch": 0.46684831970935514,
1821
+ "grad_norm": 1.21875,
1822
+ "learning_rate": 1.8808081149230036e-05,
1823
+ "loss": 0.497,
1824
+ "step": 257
1825
+ },
1826
+ {
1827
+ "epoch": 0.46866485013623976,
1828
+ "grad_norm": 1.109375,
1829
+ "learning_rate": 1.8793163101905562e-05,
1830
+ "loss": 0.4948,
1831
+ "step": 258
1832
+ },
1833
+ {
1834
+ "epoch": 0.47048138056312444,
1835
+ "grad_norm": 1.2890625,
1836
+ "learning_rate": 1.877815826961122e-05,
1837
+ "loss": 0.481,
1838
+ "step": 259
1839
+ },
1840
+ {
1841
+ "epoch": 0.47229791099000906,
1842
+ "grad_norm": 1.0234375,
1843
+ "learning_rate": 1.8763066800438638e-05,
1844
+ "loss": 0.4863,
1845
+ "step": 260
1846
+ },
1847
+ {
1848
+ "epoch": 0.47411444141689374,
1849
+ "grad_norm": 1.1875,
1850
+ "learning_rate": 1.8747888843334528e-05,
1851
+ "loss": 0.4854,
1852
+ "step": 261
1853
+ },
1854
+ {
1855
+ "epoch": 0.47593097184377836,
1856
+ "grad_norm": 1.0546875,
1857
+ "learning_rate": 1.8732624548099204e-05,
1858
+ "loss": 0.487,
1859
+ "step": 262
1860
+ },
1861
+ {
1862
+ "epoch": 0.47774750227066304,
1863
+ "grad_norm": 1.171875,
1864
+ "learning_rate": 1.8717274065385092e-05,
1865
+ "loss": 0.4972,
1866
+ "step": 263
1867
+ },
1868
+ {
1869
+ "epoch": 0.47956403269754766,
1870
+ "grad_norm": 0.96484375,
1871
+ "learning_rate": 1.870183754669526e-05,
1872
+ "loss": 0.4982,
1873
+ "step": 264
1874
+ },
1875
+ {
1876
+ "epoch": 0.48138056312443234,
1877
+ "grad_norm": 1.2265625,
1878
+ "learning_rate": 1.8686315144381914e-05,
1879
+ "loss": 0.5032,
1880
+ "step": 265
1881
+ },
1882
+ {
1883
+ "epoch": 0.48319709355131696,
1884
+ "grad_norm": 1.0078125,
1885
+ "learning_rate": 1.86707070116449e-05,
1886
+ "loss": 0.4951,
1887
+ "step": 266
1888
+ },
1889
+ {
1890
+ "epoch": 0.48501362397820164,
1891
+ "grad_norm": 1.234375,
1892
+ "learning_rate": 1.8655013302530193e-05,
1893
+ "loss": 0.487,
1894
+ "step": 267
1895
+ },
1896
+ {
1897
+ "epoch": 0.4868301544050863,
1898
+ "grad_norm": 1.0546875,
1899
+ "learning_rate": 1.8639234171928355e-05,
1900
+ "loss": 0.4897,
1901
+ "step": 268
1902
+ },
1903
+ {
1904
+ "epoch": 0.48864668483197093,
1905
+ "grad_norm": 1.375,
1906
+ "learning_rate": 1.862336977557304e-05,
1907
+ "loss": 0.4806,
1908
+ "step": 269
1909
+ },
1910
+ {
1911
+ "epoch": 0.4904632152588556,
1912
+ "grad_norm": 1.0390625,
1913
+ "learning_rate": 1.860742027003944e-05,
1914
+ "loss": 0.4892,
1915
+ "step": 270
1916
+ },
1917
+ {
1918
+ "epoch": 0.49227974568574023,
1919
+ "grad_norm": 1.21875,
1920
+ "learning_rate": 1.8591385812742724e-05,
1921
+ "loss": 0.4881,
1922
+ "step": 271
1923
+ },
1924
+ {
1925
+ "epoch": 0.4940962761126249,
1926
+ "grad_norm": 1.015625,
1927
+ "learning_rate": 1.8575266561936526e-05,
1928
+ "loss": 0.4903,
1929
+ "step": 272
1930
+ },
1931
+ {
1932
+ "epoch": 0.49591280653950953,
1933
+ "grad_norm": 1.1015625,
1934
+ "learning_rate": 1.855906267671133e-05,
1935
+ "loss": 0.4995,
1936
+ "step": 273
1937
+ },
1938
+ {
1939
+ "epoch": 0.4977293369663942,
1940
+ "grad_norm": 1.0859375,
1941
+ "learning_rate": 1.8542774316992953e-05,
1942
+ "loss": 0.4713,
1943
+ "step": 274
1944
+ },
1945
+ {
1946
+ "epoch": 0.49954586739327883,
1947
+ "grad_norm": 1.0859375,
1948
+ "learning_rate": 1.8526401643540924e-05,
1949
+ "loss": 0.4769,
1950
+ "step": 275
1951
+ },
1952
+ {
1953
+ "epoch": 0.5013623978201635,
1954
+ "grad_norm": 1.015625,
1955
+ "learning_rate": 1.850994481794692e-05,
1956
+ "loss": 0.4778,
1957
+ "step": 276
1958
+ },
1959
+ {
1960
+ "epoch": 0.5031789282470481,
1961
+ "grad_norm": 1.109375,
1962
+ "learning_rate": 1.8493404002633167e-05,
1963
+ "loss": 0.4859,
1964
+ "step": 277
1965
+ },
1966
+ {
1967
+ "epoch": 0.5049954586739328,
1968
+ "grad_norm": 1.265625,
1969
+ "learning_rate": 1.8476779360850833e-05,
1970
+ "loss": 0.4899,
1971
+ "step": 278
1972
+ },
1973
+ {
1974
+ "epoch": 0.5068119891008175,
1975
+ "grad_norm": 1.0,
1976
+ "learning_rate": 1.8460071056678424e-05,
1977
+ "loss": 0.4879,
1978
+ "step": 279
1979
+ },
1980
+ {
1981
+ "epoch": 0.508628519527702,
1982
+ "grad_norm": 1.2265625,
1983
+ "learning_rate": 1.8443279255020153e-05,
1984
+ "loss": 0.485,
1985
+ "step": 280
1986
+ },
1987
+ {
1988
+ "epoch": 0.5104450499545867,
1989
+ "grad_norm": 1.015625,
1990
+ "learning_rate": 1.8426404121604324e-05,
1991
+ "loss": 0.4809,
1992
+ "step": 281
1993
+ },
1994
+ {
1995
+ "epoch": 0.5122615803814714,
1996
+ "grad_norm": 1.109375,
1997
+ "learning_rate": 1.8409445822981694e-05,
1998
+ "loss": 0.4929,
1999
+ "step": 282
2000
+ },
2001
+ {
2002
+ "epoch": 0.5140781108083561,
2003
+ "grad_norm": 1.0,
2004
+ "learning_rate": 1.8392404526523816e-05,
2005
+ "loss": 0.4864,
2006
+ "step": 283
2007
+ },
2008
+ {
2009
+ "epoch": 0.5158946412352406,
2010
+ "grad_norm": 1.1171875,
2011
+ "learning_rate": 1.837528040042142e-05,
2012
+ "loss": 0.4846,
2013
+ "step": 284
2014
+ },
2015
+ {
2016
+ "epoch": 0.5177111716621253,
2017
+ "grad_norm": 0.9921875,
2018
+ "learning_rate": 1.8358073613682705e-05,
2019
+ "loss": 0.47,
2020
+ "step": 285
2021
+ },
2022
+ {
2023
+ "epoch": 0.51952770208901,
2024
+ "grad_norm": 1.1875,
2025
+ "learning_rate": 1.8340784336131715e-05,
2026
+ "loss": 0.4803,
2027
+ "step": 286
2028
+ },
2029
+ {
2030
+ "epoch": 0.5213442325158947,
2031
+ "grad_norm": 1.0390625,
2032
+ "learning_rate": 1.8323412738406638e-05,
2033
+ "loss": 0.4951,
2034
+ "step": 287
2035
+ },
2036
+ {
2037
+ "epoch": 0.5231607629427792,
2038
+ "grad_norm": 0.9609375,
2039
+ "learning_rate": 1.830595899195813e-05,
2040
+ "loss": 0.4787,
2041
+ "step": 288
2042
+ },
2043
+ {
2044
+ "epoch": 0.5249772933696639,
2045
+ "grad_norm": 0.98046875,
2046
+ "learning_rate": 1.828842326904762e-05,
2047
+ "loss": 0.4841,
2048
+ "step": 289
2049
+ },
2050
+ {
2051
+ "epoch": 0.5267938237965486,
2052
+ "grad_norm": 1.0625,
2053
+ "learning_rate": 1.827080574274562e-05,
2054
+ "loss": 0.4903,
2055
+ "step": 290
2056
+ },
2057
+ {
2058
+ "epoch": 0.5286103542234333,
2059
+ "grad_norm": 1.0703125,
2060
+ "learning_rate": 1.825310658693e-05,
2061
+ "loss": 0.4875,
2062
+ "step": 291
2063
+ },
2064
+ {
2065
+ "epoch": 0.5304268846503178,
2066
+ "grad_norm": 1.21875,
2067
+ "learning_rate": 1.8235325976284276e-05,
2068
+ "loss": 0.4772,
2069
+ "step": 292
2070
+ },
2071
+ {
2072
+ "epoch": 0.5322434150772025,
2073
+ "grad_norm": 1.1328125,
2074
+ "learning_rate": 1.8217464086295904e-05,
2075
+ "loss": 0.4805,
2076
+ "step": 293
2077
+ },
2078
+ {
2079
+ "epoch": 0.5340599455040872,
2080
+ "grad_norm": 1.140625,
2081
+ "learning_rate": 1.8199521093254524e-05,
2082
+ "loss": 0.4964,
2083
+ "step": 294
2084
+ },
2085
+ {
2086
+ "epoch": 0.5358764759309719,
2087
+ "grad_norm": 1.34375,
2088
+ "learning_rate": 1.8181497174250236e-05,
2089
+ "loss": 0.486,
2090
+ "step": 295
2091
+ },
2092
+ {
2093
+ "epoch": 0.5376930063578564,
2094
+ "grad_norm": 1.0859375,
2095
+ "learning_rate": 1.816339250717184e-05,
2096
+ "loss": 0.4828,
2097
+ "step": 296
2098
+ },
2099
+ {
2100
+ "epoch": 0.5395095367847411,
2101
+ "grad_norm": 1.1953125,
2102
+ "learning_rate": 1.8145207270705095e-05,
2103
+ "loss": 0.4772,
2104
+ "step": 297
2105
+ },
2106
+ {
2107
+ "epoch": 0.5413260672116258,
2108
+ "grad_norm": 1.03125,
2109
+ "learning_rate": 1.812694164433094e-05,
2110
+ "loss": 0.4739,
2111
+ "step": 298
2112
+ },
2113
+ {
2114
+ "epoch": 0.5431425976385105,
2115
+ "grad_norm": 1.1953125,
2116
+ "learning_rate": 1.8108595808323736e-05,
2117
+ "loss": 0.4746,
2118
+ "step": 299
2119
+ },
2120
+ {
2121
+ "epoch": 0.5449591280653951,
2122
+ "grad_norm": 1.0546875,
2123
+ "learning_rate": 1.8090169943749477e-05,
2124
+ "loss": 0.4777,
2125
+ "step": 300
2126
+ },
2127
+ {
2128
+ "epoch": 0.5467756584922797,
2129
+ "grad_norm": 1.2265625,
2130
+ "learning_rate": 1.8071664232464005e-05,
2131
+ "loss": 0.4825,
2132
+ "step": 301
2133
+ },
2134
+ {
2135
+ "epoch": 0.5485921889191644,
2136
+ "grad_norm": 0.96875,
2137
+ "learning_rate": 1.8053078857111218e-05,
2138
+ "loss": 0.4796,
2139
+ "step": 302
2140
+ },
2141
+ {
2142
+ "epoch": 0.5504087193460491,
2143
+ "grad_norm": 1.3203125,
2144
+ "learning_rate": 1.8034414001121278e-05,
2145
+ "loss": 0.4947,
2146
+ "step": 303
2147
+ },
2148
+ {
2149
+ "epoch": 0.5522252497729337,
2150
+ "grad_norm": 1.015625,
2151
+ "learning_rate": 1.8015669848708768e-05,
2152
+ "loss": 0.4741,
2153
+ "step": 304
2154
+ },
2155
+ {
2156
+ "epoch": 0.5540417801998183,
2157
+ "grad_norm": 1.328125,
2158
+ "learning_rate": 1.799684658487091e-05,
2159
+ "loss": 0.4742,
2160
+ "step": 305
2161
+ },
2162
+ {
2163
+ "epoch": 0.555858310626703,
2164
+ "grad_norm": 1.078125,
2165
+ "learning_rate": 1.7977944395385713e-05,
2166
+ "loss": 0.4848,
2167
+ "step": 306
2168
+ },
2169
+ {
2170
+ "epoch": 0.5576748410535877,
2171
+ "grad_norm": 1.3671875,
2172
+ "learning_rate": 1.795896346681016e-05,
2173
+ "loss": 0.4763,
2174
+ "step": 307
2175
+ },
2176
+ {
2177
+ "epoch": 0.5594913714804723,
2178
+ "grad_norm": 1.2578125,
2179
+ "learning_rate": 1.7939903986478354e-05,
2180
+ "loss": 0.4814,
2181
+ "step": 308
2182
+ },
2183
+ {
2184
+ "epoch": 0.5613079019073569,
2185
+ "grad_norm": 1.125,
2186
+ "learning_rate": 1.7920766142499673e-05,
2187
+ "loss": 0.4778,
2188
+ "step": 309
2189
+ },
2190
+ {
2191
+ "epoch": 0.5631244323342416,
2192
+ "grad_norm": 1.421875,
2193
+ "learning_rate": 1.7901550123756906e-05,
2194
+ "loss": 0.4781,
2195
+ "step": 310
2196
+ },
2197
+ {
2198
+ "epoch": 0.5649409627611263,
2199
+ "grad_norm": 0.953125,
2200
+ "learning_rate": 1.78822561199044e-05,
2201
+ "loss": 0.4747,
2202
+ "step": 311
2203
+ },
2204
+ {
2205
+ "epoch": 0.5667574931880109,
2206
+ "grad_norm": 1.4296875,
2207
+ "learning_rate": 1.786288432136619e-05,
2208
+ "loss": 0.4736,
2209
+ "step": 312
2210
+ },
2211
+ {
2212
+ "epoch": 0.5685740236148955,
2213
+ "grad_norm": 1.0078125,
2214
+ "learning_rate": 1.7843434919334103e-05,
2215
+ "loss": 0.4803,
2216
+ "step": 313
2217
+ },
2218
+ {
2219
+ "epoch": 0.5703905540417802,
2220
+ "grad_norm": 1.234375,
2221
+ "learning_rate": 1.7823908105765883e-05,
2222
+ "loss": 0.4774,
2223
+ "step": 314
2224
+ },
2225
+ {
2226
+ "epoch": 0.5722070844686649,
2227
+ "grad_norm": 1.15625,
2228
+ "learning_rate": 1.7804304073383298e-05,
2229
+ "loss": 0.4864,
2230
+ "step": 315
2231
+ },
2232
+ {
2233
+ "epoch": 0.5740236148955495,
2234
+ "grad_norm": 1.1015625,
2235
+ "learning_rate": 1.7784623015670237e-05,
2236
+ "loss": 0.4705,
2237
+ "step": 316
2238
+ },
2239
+ {
2240
+ "epoch": 0.5758401453224341,
2241
+ "grad_norm": 1.1015625,
2242
+ "learning_rate": 1.7764865126870788e-05,
2243
+ "loss": 0.4672,
2244
+ "step": 317
2245
+ },
2246
+ {
2247
+ "epoch": 0.5776566757493188,
2248
+ "grad_norm": 1.3125,
2249
+ "learning_rate": 1.7745030601987338e-05,
2250
+ "loss": 0.4758,
2251
+ "step": 318
2252
+ },
2253
+ {
2254
+ "epoch": 0.5794732061762035,
2255
+ "grad_norm": 1.0703125,
2256
+ "learning_rate": 1.7725119636778644e-05,
2257
+ "loss": 0.473,
2258
+ "step": 319
2259
+ },
2260
+ {
2261
+ "epoch": 0.5812897366030881,
2262
+ "grad_norm": 1.1640625,
2263
+ "learning_rate": 1.7705132427757895e-05,
2264
+ "loss": 0.4677,
2265
+ "step": 320
2266
+ },
2267
+ {
2268
+ "epoch": 0.5831062670299727,
2269
+ "grad_norm": 1.15625,
2270
+ "learning_rate": 1.7685069172190766e-05,
2271
+ "loss": 0.4733,
2272
+ "step": 321
2273
+ },
2274
+ {
2275
+ "epoch": 0.5849227974568574,
2276
+ "grad_norm": 1.140625,
2277
+ "learning_rate": 1.76649300680935e-05,
2278
+ "loss": 0.4816,
2279
+ "step": 322
2280
+ },
2281
+ {
2282
+ "epoch": 0.5867393278837421,
2283
+ "grad_norm": 1.1640625,
2284
+ "learning_rate": 1.764471531423092e-05,
2285
+ "loss": 0.4918,
2286
+ "step": 323
2287
+ },
2288
+ {
2289
+ "epoch": 0.5885558583106267,
2290
+ "grad_norm": 0.98828125,
2291
+ "learning_rate": 1.762442511011448e-05,
2292
+ "loss": 0.4732,
2293
+ "step": 324
2294
+ },
2295
+ {
2296
+ "epoch": 0.5903723887375113,
2297
+ "grad_norm": 1.0390625,
2298
+ "learning_rate": 1.7604059656000313e-05,
2299
+ "loss": 0.4685,
2300
+ "step": 325
2301
+ },
2302
+ {
2303
+ "epoch": 0.592188919164396,
2304
+ "grad_norm": 1.0625,
2305
+ "learning_rate": 1.7583619152887222e-05,
2306
+ "loss": 0.4748,
2307
+ "step": 326
2308
+ },
2309
+ {
2310
+ "epoch": 0.5940054495912807,
2311
+ "grad_norm": 0.95703125,
2312
+ "learning_rate": 1.756310380251472e-05,
2313
+ "loss": 0.4669,
2314
+ "step": 327
2315
+ },
2316
+ {
2317
+ "epoch": 0.5958219800181653,
2318
+ "grad_norm": 0.921875,
2319
+ "learning_rate": 1.754251380736104e-05,
2320
+ "loss": 0.466,
2321
+ "step": 328
2322
+ },
2323
+ {
2324
+ "epoch": 0.59763851044505,
2325
+ "grad_norm": 1.0078125,
2326
+ "learning_rate": 1.7521849370641116e-05,
2327
+ "loss": 0.4591,
2328
+ "step": 329
2329
+ },
2330
+ {
2331
+ "epoch": 0.5994550408719346,
2332
+ "grad_norm": 0.95703125,
2333
+ "learning_rate": 1.7501110696304598e-05,
2334
+ "loss": 0.4607,
2335
+ "step": 330
2336
+ },
2337
+ {
2338
+ "epoch": 0.6012715712988193,
2339
+ "grad_norm": 1.0234375,
2340
+ "learning_rate": 1.7480297989033824e-05,
2341
+ "loss": 0.4698,
2342
+ "step": 331
2343
+ },
2344
+ {
2345
+ "epoch": 0.6030881017257039,
2346
+ "grad_norm": 0.9921875,
2347
+ "learning_rate": 1.7459411454241822e-05,
2348
+ "loss": 0.4713,
2349
+ "step": 332
2350
+ },
2351
+ {
2352
+ "epoch": 0.6049046321525886,
2353
+ "grad_norm": 0.96484375,
2354
+ "learning_rate": 1.7438451298070252e-05,
2355
+ "loss": 0.4632,
2356
+ "step": 333
2357
+ },
2358
+ {
2359
+ "epoch": 0.6067211625794732,
2360
+ "grad_norm": 1.0625,
2361
+ "learning_rate": 1.7417417727387392e-05,
2362
+ "loss": 0.4675,
2363
+ "step": 334
2364
+ },
2365
+ {
2366
+ "epoch": 0.6085376930063578,
2367
+ "grad_norm": 1.046875,
2368
+ "learning_rate": 1.73963109497861e-05,
2369
+ "loss": 0.4812,
2370
+ "step": 335
2371
+ },
2372
+ {
2373
+ "epoch": 0.6103542234332425,
2374
+ "grad_norm": 1.1171875,
2375
+ "learning_rate": 1.737513117358174e-05,
2376
+ "loss": 0.4746,
2377
+ "step": 336
2378
+ },
2379
+ {
2380
+ "epoch": 0.6121707538601272,
2381
+ "grad_norm": 1.1484375,
2382
+ "learning_rate": 1.735387860781016e-05,
2383
+ "loss": 0.468,
2384
+ "step": 337
2385
+ },
2386
+ {
2387
+ "epoch": 0.6139872842870118,
2388
+ "grad_norm": 1.03125,
2389
+ "learning_rate": 1.7332553462225604e-05,
2390
+ "loss": 0.4721,
2391
+ "step": 338
2392
+ },
2393
+ {
2394
+ "epoch": 0.6158038147138964,
2395
+ "grad_norm": 0.96484375,
2396
+ "learning_rate": 1.7311155947298644e-05,
2397
+ "loss": 0.4696,
2398
+ "step": 339
2399
+ },
2400
+ {
2401
+ "epoch": 0.6176203451407811,
2402
+ "grad_norm": 1.0703125,
2403
+ "learning_rate": 1.7289686274214116e-05,
2404
+ "loss": 0.478,
2405
+ "step": 340
2406
+ },
2407
+ {
2408
+ "epoch": 0.6194368755676658,
2409
+ "grad_norm": 0.96875,
2410
+ "learning_rate": 1.726814465486903e-05,
2411
+ "loss": 0.47,
2412
+ "step": 341
2413
+ },
2414
+ {
2415
+ "epoch": 0.6212534059945504,
2416
+ "grad_norm": 1.0390625,
2417
+ "learning_rate": 1.7246531301870467e-05,
2418
+ "loss": 0.4697,
2419
+ "step": 342
2420
+ },
2421
+ {
2422
+ "epoch": 0.623069936421435,
2423
+ "grad_norm": 1.015625,
2424
+ "learning_rate": 1.7224846428533498e-05,
2425
+ "loss": 0.4752,
2426
+ "step": 343
2427
+ },
2428
+ {
2429
+ "epoch": 0.6248864668483197,
2430
+ "grad_norm": 1.015625,
2431
+ "learning_rate": 1.720309024887907e-05,
2432
+ "loss": 0.4713,
2433
+ "step": 344
2434
+ },
2435
+ {
2436
+ "epoch": 0.6267029972752044,
2437
+ "grad_norm": 1.1328125,
2438
+ "learning_rate": 1.718126297763189e-05,
2439
+ "loss": 0.4718,
2440
+ "step": 345
2441
+ },
2442
+ {
2443
+ "epoch": 0.628519527702089,
2444
+ "grad_norm": 1.1484375,
2445
+ "learning_rate": 1.7159364830218312e-05,
2446
+ "loss": 0.4798,
2447
+ "step": 346
2448
+ },
2449
+ {
2450
+ "epoch": 0.6303360581289736,
2451
+ "grad_norm": 1.0078125,
2452
+ "learning_rate": 1.7137396022764216e-05,
2453
+ "loss": 0.4691,
2454
+ "step": 347
2455
+ },
2456
+ {
2457
+ "epoch": 0.6321525885558583,
2458
+ "grad_norm": 1.171875,
2459
+ "learning_rate": 1.7115356772092858e-05,
2460
+ "loss": 0.4685,
2461
+ "step": 348
2462
+ },
2463
+ {
2464
+ "epoch": 0.633969118982743,
2465
+ "grad_norm": 1.109375,
2466
+ "learning_rate": 1.709324729572274e-05,
2467
+ "loss": 0.4716,
2468
+ "step": 349
2469
+ },
2470
+ {
2471
+ "epoch": 0.6357856494096276,
2472
+ "grad_norm": 1.0546875,
2473
+ "learning_rate": 1.7071067811865477e-05,
2474
+ "loss": 0.4775,
2475
+ "step": 350
2476
+ },
2477
+ {
2478
+ "epoch": 0.6376021798365122,
2479
+ "grad_norm": 1.078125,
2480
+ "learning_rate": 1.7048818539423616e-05,
2481
+ "loss": 0.473,
2482
+ "step": 351
2483
+ },
2484
+ {
2485
+ "epoch": 0.6394187102633969,
2486
+ "grad_norm": 1.0625,
2487
+ "learning_rate": 1.7026499697988496e-05,
2488
+ "loss": 0.4677,
2489
+ "step": 352
2490
+ },
2491
+ {
2492
+ "epoch": 0.6412352406902816,
2493
+ "grad_norm": 1.1953125,
2494
+ "learning_rate": 1.7004111507838067e-05,
2495
+ "loss": 0.4711,
2496
+ "step": 353
2497
+ },
2498
+ {
2499
+ "epoch": 0.6430517711171662,
2500
+ "grad_norm": 1.2265625,
2501
+ "learning_rate": 1.698165418993473e-05,
2502
+ "loss": 0.4677,
2503
+ "step": 354
2504
+ },
2505
+ {
2506
+ "epoch": 0.6448683015440508,
2507
+ "grad_norm": 1.1171875,
2508
+ "learning_rate": 1.6959127965923144e-05,
2509
+ "loss": 0.4761,
2510
+ "step": 355
2511
+ },
2512
+ {
2513
+ "epoch": 0.6466848319709355,
2514
+ "grad_norm": 1.1171875,
2515
+ "learning_rate": 1.693653305812805e-05,
2516
+ "loss": 0.4593,
2517
+ "step": 356
2518
+ },
2519
+ {
2520
+ "epoch": 0.6485013623978202,
2521
+ "grad_norm": 1.03125,
2522
+ "learning_rate": 1.6913869689552066e-05,
2523
+ "loss": 0.4805,
2524
+ "step": 357
2525
+ },
2526
+ {
2527
+ "epoch": 0.6503178928247049,
2528
+ "grad_norm": 1.109375,
2529
+ "learning_rate": 1.6891138083873486e-05,
2530
+ "loss": 0.4702,
2531
+ "step": 358
2532
+ },
2533
+ {
2534
+ "epoch": 0.6521344232515894,
2535
+ "grad_norm": 1.0625,
2536
+ "learning_rate": 1.6868338465444086e-05,
2537
+ "loss": 0.4714,
2538
+ "step": 359
2539
+ },
2540
+ {
2541
+ "epoch": 0.6539509536784741,
2542
+ "grad_norm": 1.03125,
2543
+ "learning_rate": 1.684547105928689e-05,
2544
+ "loss": 0.4627,
2545
+ "step": 360
2546
+ },
2547
+ {
2548
+ "epoch": 0.6557674841053588,
2549
+ "grad_norm": 1.171875,
2550
+ "learning_rate": 1.6822536091093967e-05,
2551
+ "loss": 0.4633,
2552
+ "step": 361
2553
+ },
2554
+ {
2555
+ "epoch": 0.6575840145322435,
2556
+ "grad_norm": 1.046875,
2557
+ "learning_rate": 1.6799533787224192e-05,
2558
+ "loss": 0.4751,
2559
+ "step": 362
2560
+ },
2561
+ {
2562
+ "epoch": 0.659400544959128,
2563
+ "grad_norm": 1.203125,
2564
+ "learning_rate": 1.6776464374701026e-05,
2565
+ "loss": 0.4731,
2566
+ "step": 363
2567
+ },
2568
+ {
2569
+ "epoch": 0.6612170753860127,
2570
+ "grad_norm": 0.98046875,
2571
+ "learning_rate": 1.6753328081210244e-05,
2572
+ "loss": 0.4631,
2573
+ "step": 364
2574
+ },
2575
+ {
2576
+ "epoch": 0.6630336058128974,
2577
+ "grad_norm": 1.0625,
2578
+ "learning_rate": 1.6730125135097736e-05,
2579
+ "loss": 0.4576,
2580
+ "step": 365
2581
+ },
2582
+ {
2583
+ "epoch": 0.6648501362397821,
2584
+ "grad_norm": 1.0,
2585
+ "learning_rate": 1.6706855765367202e-05,
2586
+ "loss": 0.4645,
2587
+ "step": 366
2588
+ },
2589
+ {
2590
+ "epoch": 0.6666666666666666,
2591
+ "grad_norm": 1.046875,
2592
+ "learning_rate": 1.6683520201677933e-05,
2593
+ "loss": 0.4628,
2594
+ "step": 367
2595
+ },
2596
+ {
2597
+ "epoch": 0.6684831970935513,
2598
+ "grad_norm": 1.078125,
2599
+ "learning_rate": 1.666011867434252e-05,
2600
+ "loss": 0.4769,
2601
+ "step": 368
2602
+ },
2603
+ {
2604
+ "epoch": 0.6684831970935513,
2605
+ "eval_loss": 0.4684128165245056,
2606
+ "eval_runtime": 34.9278,
2607
+ "eval_samples_per_second": 5.726,
2608
+ "eval_steps_per_second": 1.432,
2609
+ "step": 368
2610
+ },
2611
+ {
2612
+ "epoch": 0.670299727520436,
2613
+ "grad_norm": 0.96875,
2614
+ "learning_rate": 1.6636651414324586e-05,
2615
+ "loss": 0.466,
2616
+ "step": 369
2617
+ },
2618
+ {
2619
+ "epoch": 0.6721162579473207,
2620
+ "grad_norm": 1.0390625,
2621
+ "learning_rate": 1.661311865323652e-05,
2622
+ "loss": 0.4649,
2623
+ "step": 370
2624
+ },
2625
+ {
2626
+ "epoch": 0.6739327883742052,
2627
+ "grad_norm": 1.046875,
2628
+ "learning_rate": 1.6589520623337173e-05,
2629
+ "loss": 0.4734,
2630
+ "step": 371
2631
+ },
2632
+ {
2633
+ "epoch": 0.6757493188010899,
2634
+ "grad_norm": 1.0625,
2635
+ "learning_rate": 1.6565857557529567e-05,
2636
+ "loss": 0.4594,
2637
+ "step": 372
2638
+ },
2639
+ {
2640
+ "epoch": 0.6775658492279746,
2641
+ "grad_norm": 0.94140625,
2642
+ "learning_rate": 1.6542129689358613e-05,
2643
+ "loss": 0.4647,
2644
+ "step": 373
2645
+ },
2646
+ {
2647
+ "epoch": 0.6793823796548593,
2648
+ "grad_norm": 0.984375,
2649
+ "learning_rate": 1.651833725300879e-05,
2650
+ "loss": 0.4553,
2651
+ "step": 374
2652
+ },
2653
+ {
2654
+ "epoch": 0.6811989100817438,
2655
+ "grad_norm": 0.953125,
2656
+ "learning_rate": 1.6494480483301836e-05,
2657
+ "loss": 0.4703,
2658
+ "step": 375
2659
+ },
2660
+ {
2661
+ "epoch": 0.6830154405086285,
2662
+ "grad_norm": 1.0,
2663
+ "learning_rate": 1.6470559615694445e-05,
2664
+ "loss": 0.4627,
2665
+ "step": 376
2666
+ },
2667
+ {
2668
+ "epoch": 0.6848319709355132,
2669
+ "grad_norm": 0.9375,
2670
+ "learning_rate": 1.6446574886275914e-05,
2671
+ "loss": 0.4641,
2672
+ "step": 377
2673
+ },
2674
+ {
2675
+ "epoch": 0.6866485013623979,
2676
+ "grad_norm": 1.125,
2677
+ "learning_rate": 1.6422526531765846e-05,
2678
+ "loss": 0.4709,
2679
+ "step": 378
2680
+ },
2681
+ {
2682
+ "epoch": 0.6884650317892824,
2683
+ "grad_norm": 0.9609375,
2684
+ "learning_rate": 1.6398414789511784e-05,
2685
+ "loss": 0.4615,
2686
+ "step": 379
2687
+ },
2688
+ {
2689
+ "epoch": 0.6902815622161671,
2690
+ "grad_norm": 1.0234375,
2691
+ "learning_rate": 1.63742398974869e-05,
2692
+ "loss": 0.4565,
2693
+ "step": 380
2694
+ },
2695
+ {
2696
+ "epoch": 0.6920980926430518,
2697
+ "grad_norm": 1.015625,
2698
+ "learning_rate": 1.6350002094287608e-05,
2699
+ "loss": 0.4635,
2700
+ "step": 381
2701
+ },
2702
+ {
2703
+ "epoch": 0.6939146230699365,
2704
+ "grad_norm": 1.1015625,
2705
+ "learning_rate": 1.6325701619131246e-05,
2706
+ "loss": 0.4538,
2707
+ "step": 382
2708
+ },
2709
+ {
2710
+ "epoch": 0.695731153496821,
2711
+ "grad_norm": 1.015625,
2712
+ "learning_rate": 1.6301338711853695e-05,
2713
+ "loss": 0.4598,
2714
+ "step": 383
2715
+ },
2716
+ {
2717
+ "epoch": 0.6975476839237057,
2718
+ "grad_norm": 1.0546875,
2719
+ "learning_rate": 1.6276913612907005e-05,
2720
+ "loss": 0.4586,
2721
+ "step": 384
2722
+ },
2723
+ {
2724
+ "epoch": 0.6993642143505904,
2725
+ "grad_norm": 0.97265625,
2726
+ "learning_rate": 1.6252426563357054e-05,
2727
+ "loss": 0.4695,
2728
+ "step": 385
2729
+ },
2730
+ {
2731
+ "epoch": 0.701180744777475,
2732
+ "grad_norm": 1.015625,
2733
+ "learning_rate": 1.6227877804881126e-05,
2734
+ "loss": 0.4743,
2735
+ "step": 386
2736
+ },
2737
+ {
2738
+ "epoch": 0.7029972752043597,
2739
+ "grad_norm": 0.9296875,
2740
+ "learning_rate": 1.6203267579765563e-05,
2741
+ "loss": 0.4701,
2742
+ "step": 387
2743
+ },
2744
+ {
2745
+ "epoch": 0.7048138056312443,
2746
+ "grad_norm": 1.0390625,
2747
+ "learning_rate": 1.6178596130903345e-05,
2748
+ "loss": 0.4578,
2749
+ "step": 388
2750
+ },
2751
+ {
2752
+ "epoch": 0.706630336058129,
2753
+ "grad_norm": 0.9375,
2754
+ "learning_rate": 1.6153863701791717e-05,
2755
+ "loss": 0.4635,
2756
+ "step": 389
2757
+ },
2758
+ {
2759
+ "epoch": 0.7084468664850136,
2760
+ "grad_norm": 1.0078125,
2761
+ "learning_rate": 1.6129070536529767e-05,
2762
+ "loss": 0.4641,
2763
+ "step": 390
2764
+ },
2765
+ {
2766
+ "epoch": 0.7102633969118983,
2767
+ "grad_norm": 1.046875,
2768
+ "learning_rate": 1.6104216879816027e-05,
2769
+ "loss": 0.4715,
2770
+ "step": 391
2771
+ },
2772
+ {
2773
+ "epoch": 0.7120799273387829,
2774
+ "grad_norm": 0.96484375,
2775
+ "learning_rate": 1.6079302976946055e-05,
2776
+ "loss": 0.4641,
2777
+ "step": 392
2778
+ },
2779
+ {
2780
+ "epoch": 0.7138964577656676,
2781
+ "grad_norm": 1.0625,
2782
+ "learning_rate": 1.6054329073810016e-05,
2783
+ "loss": 0.4569,
2784
+ "step": 393
2785
+ },
2786
+ {
2787
+ "epoch": 0.7157129881925522,
2788
+ "grad_norm": 0.9921875,
2789
+ "learning_rate": 1.602929541689025e-05,
2790
+ "loss": 0.461,
2791
+ "step": 394
2792
+ },
2793
+ {
2794
+ "epoch": 0.7175295186194369,
2795
+ "grad_norm": 0.94140625,
2796
+ "learning_rate": 1.6004202253258844e-05,
2797
+ "loss": 0.4575,
2798
+ "step": 395
2799
+ },
2800
+ {
2801
+ "epoch": 0.7193460490463215,
2802
+ "grad_norm": 1.0390625,
2803
+ "learning_rate": 1.597904983057519e-05,
2804
+ "loss": 0.4693,
2805
+ "step": 396
2806
+ },
2807
+ {
2808
+ "epoch": 0.7211625794732062,
2809
+ "grad_norm": 0.9765625,
2810
+ "learning_rate": 1.595383839708355e-05,
2811
+ "loss": 0.46,
2812
+ "step": 397
2813
+ },
2814
+ {
2815
+ "epoch": 0.7229791099000908,
2816
+ "grad_norm": 1.0078125,
2817
+ "learning_rate": 1.5928568201610593e-05,
2818
+ "loss": 0.4654,
2819
+ "step": 398
2820
+ },
2821
+ {
2822
+ "epoch": 0.7247956403269755,
2823
+ "grad_norm": 0.90625,
2824
+ "learning_rate": 1.5903239493562948e-05,
2825
+ "loss": 0.4575,
2826
+ "step": 399
2827
+ },
2828
+ {
2829
+ "epoch": 0.7266121707538601,
2830
+ "grad_norm": 1.0,
2831
+ "learning_rate": 1.5877852522924733e-05,
2832
+ "loss": 0.4535,
2833
+ "step": 400
2834
+ },
2835
+ {
2836
+ "epoch": 0.7284287011807448,
2837
+ "grad_norm": 0.92578125,
2838
+ "learning_rate": 1.5852407540255103e-05,
2839
+ "loss": 0.4591,
2840
+ "step": 401
2841
+ },
2842
+ {
2843
+ "epoch": 0.7302452316076294,
2844
+ "grad_norm": 0.94140625,
2845
+ "learning_rate": 1.5826904796685763e-05,
2846
+ "loss": 0.4627,
2847
+ "step": 402
2848
+ },
2849
+ {
2850
+ "epoch": 0.7320617620345141,
2851
+ "grad_norm": 0.91796875,
2852
+ "learning_rate": 1.5801344543918495e-05,
2853
+ "loss": 0.4614,
2854
+ "step": 403
2855
+ },
2856
+ {
2857
+ "epoch": 0.7338782924613987,
2858
+ "grad_norm": 1.0,
2859
+ "learning_rate": 1.5775727034222675e-05,
2860
+ "loss": 0.4685,
2861
+ "step": 404
2862
+ },
2863
+ {
2864
+ "epoch": 0.7356948228882834,
2865
+ "grad_norm": 1.0234375,
2866
+ "learning_rate": 1.575005252043279e-05,
2867
+ "loss": 0.4719,
2868
+ "step": 405
2869
+ },
2870
+ {
2871
+ "epoch": 0.737511353315168,
2872
+ "grad_norm": 0.94921875,
2873
+ "learning_rate": 1.572432125594591e-05,
2874
+ "loss": 0.4637,
2875
+ "step": 406
2876
+ },
2877
+ {
2878
+ "epoch": 0.7393278837420527,
2879
+ "grad_norm": 1.0078125,
2880
+ "learning_rate": 1.5698533494719238e-05,
2881
+ "loss": 0.459,
2882
+ "step": 407
2883
+ },
2884
+ {
2885
+ "epoch": 0.7411444141689373,
2886
+ "grad_norm": 0.98828125,
2887
+ "learning_rate": 1.567268949126757e-05,
2888
+ "loss": 0.4762,
2889
+ "step": 408
2890
+ },
2891
+ {
2892
+ "epoch": 0.742960944595822,
2893
+ "grad_norm": 0.93359375,
2894
+ "learning_rate": 1.5646789500660772e-05,
2895
+ "loss": 0.457,
2896
+ "step": 409
2897
+ },
2898
+ {
2899
+ "epoch": 0.7447774750227066,
2900
+ "grad_norm": 1.0078125,
2901
+ "learning_rate": 1.5620833778521306e-05,
2902
+ "loss": 0.4666,
2903
+ "step": 410
2904
+ },
2905
+ {
2906
+ "epoch": 0.7465940054495913,
2907
+ "grad_norm": 1.0390625,
2908
+ "learning_rate": 1.5594822581021673e-05,
2909
+ "loss": 0.4609,
2910
+ "step": 411
2911
+ },
2912
+ {
2913
+ "epoch": 0.7484105358764759,
2914
+ "grad_norm": 1.03125,
2915
+ "learning_rate": 1.556875616488188e-05,
2916
+ "loss": 0.4581,
2917
+ "step": 412
2918
+ },
2919
+ {
2920
+ "epoch": 0.7502270663033606,
2921
+ "grad_norm": 0.9375,
2922
+ "learning_rate": 1.5542634787366942e-05,
2923
+ "loss": 0.4659,
2924
+ "step": 413
2925
+ },
2926
+ {
2927
+ "epoch": 0.7520435967302452,
2928
+ "grad_norm": 1.078125,
2929
+ "learning_rate": 1.5516458706284306e-05,
2930
+ "loss": 0.4686,
2931
+ "step": 414
2932
+ },
2933
+ {
2934
+ "epoch": 0.7538601271571299,
2935
+ "grad_norm": 0.9453125,
2936
+ "learning_rate": 1.549022817998132e-05,
2937
+ "loss": 0.454,
2938
+ "step": 415
2939
+ },
2940
+ {
2941
+ "epoch": 0.7556766575840145,
2942
+ "grad_norm": 1.078125,
2943
+ "learning_rate": 1.5463943467342694e-05,
2944
+ "loss": 0.4529,
2945
+ "step": 416
2946
+ },
2947
+ {
2948
+ "epoch": 0.7574931880108992,
2949
+ "grad_norm": 1.0390625,
2950
+ "learning_rate": 1.5437604827787925e-05,
2951
+ "loss": 0.4668,
2952
+ "step": 417
2953
+ },
2954
+ {
2955
+ "epoch": 0.7593097184377838,
2956
+ "grad_norm": 1.109375,
2957
+ "learning_rate": 1.541121252126876e-05,
2958
+ "loss": 0.4632,
2959
+ "step": 418
2960
+ },
2961
+ {
2962
+ "epoch": 0.7611262488646685,
2963
+ "grad_norm": 1.234375,
2964
+ "learning_rate": 1.5384766808266603e-05,
2965
+ "loss": 0.4579,
2966
+ "step": 419
2967
+ },
2968
+ {
2969
+ "epoch": 0.7629427792915532,
2970
+ "grad_norm": 0.9296875,
2971
+ "learning_rate": 1.5358267949789968e-05,
2972
+ "loss": 0.4507,
2973
+ "step": 420
2974
+ },
2975
+ {
2976
+ "epoch": 0.7647593097184378,
2977
+ "grad_norm": 1.1015625,
2978
+ "learning_rate": 1.5331716207371888e-05,
2979
+ "loss": 0.4527,
2980
+ "step": 421
2981
+ },
2982
+ {
2983
+ "epoch": 0.7665758401453224,
2984
+ "grad_norm": 1.0859375,
2985
+ "learning_rate": 1.5305111843067343e-05,
2986
+ "loss": 0.4684,
2987
+ "step": 422
2988
+ },
2989
+ {
2990
+ "epoch": 0.7683923705722071,
2991
+ "grad_norm": 1.015625,
2992
+ "learning_rate": 1.5278455119450666e-05,
2993
+ "loss": 0.4613,
2994
+ "step": 423
2995
+ },
2996
+ {
2997
+ "epoch": 0.7702089009990918,
2998
+ "grad_norm": 1.1953125,
2999
+ "learning_rate": 1.5251746299612959e-05,
3000
+ "loss": 0.4552,
3001
+ "step": 424
3002
+ },
3003
+ {
3004
+ "epoch": 0.7720254314259763,
3005
+ "grad_norm": 0.96875,
3006
+ "learning_rate": 1.5224985647159489e-05,
3007
+ "loss": 0.4582,
3008
+ "step": 425
3009
+ },
3010
+ {
3011
+ "epoch": 0.773841961852861,
3012
+ "grad_norm": 1.1796875,
3013
+ "learning_rate": 1.5198173426207095e-05,
3014
+ "loss": 0.4601,
3015
+ "step": 426
3016
+ },
3017
+ {
3018
+ "epoch": 0.7756584922797457,
3019
+ "grad_norm": 0.96484375,
3020
+ "learning_rate": 1.5171309901381572e-05,
3021
+ "loss": 0.4487,
3022
+ "step": 427
3023
+ },
3024
+ {
3025
+ "epoch": 0.7774750227066304,
3026
+ "grad_norm": 1.015625,
3027
+ "learning_rate": 1.5144395337815066e-05,
3028
+ "loss": 0.4581,
3029
+ "step": 428
3030
+ },
3031
+ {
3032
+ "epoch": 0.779291553133515,
3033
+ "grad_norm": 0.890625,
3034
+ "learning_rate": 1.5117430001143451e-05,
3035
+ "loss": 0.4645,
3036
+ "step": 429
3037
+ },
3038
+ {
3039
+ "epoch": 0.7811080835603996,
3040
+ "grad_norm": 1.0,
3041
+ "learning_rate": 1.5090414157503715e-05,
3042
+ "loss": 0.4586,
3043
+ "step": 430
3044
+ },
3045
+ {
3046
+ "epoch": 0.7829246139872843,
3047
+ "grad_norm": 0.98828125,
3048
+ "learning_rate": 1.5063348073531325e-05,
3049
+ "loss": 0.4542,
3050
+ "step": 431
3051
+ },
3052
+ {
3053
+ "epoch": 0.784741144414169,
3054
+ "grad_norm": 0.9765625,
3055
+ "learning_rate": 1.503623201635761e-05,
3056
+ "loss": 0.4485,
3057
+ "step": 432
3058
+ },
3059
+ {
3060
+ "epoch": 0.7865576748410535,
3061
+ "grad_norm": 1.015625,
3062
+ "learning_rate": 1.5009066253607101e-05,
3063
+ "loss": 0.4696,
3064
+ "step": 433
3065
+ },
3066
+ {
3067
+ "epoch": 0.7883742052679382,
3068
+ "grad_norm": 0.9375,
3069
+ "learning_rate": 1.498185105339491e-05,
3070
+ "loss": 0.4636,
3071
+ "step": 434
3072
+ },
3073
+ {
3074
+ "epoch": 0.7901907356948229,
3075
+ "grad_norm": 1.0546875,
3076
+ "learning_rate": 1.4954586684324077e-05,
3077
+ "loss": 0.4597,
3078
+ "step": 435
3079
+ },
3080
+ {
3081
+ "epoch": 0.7920072661217076,
3082
+ "grad_norm": 0.91015625,
3083
+ "learning_rate": 1.4927273415482916e-05,
3084
+ "loss": 0.453,
3085
+ "step": 436
3086
+ },
3087
+ {
3088
+ "epoch": 0.7938237965485921,
3089
+ "grad_norm": 0.90234375,
3090
+ "learning_rate": 1.4899911516442367e-05,
3091
+ "loss": 0.457,
3092
+ "step": 437
3093
+ },
3094
+ {
3095
+ "epoch": 0.7956403269754768,
3096
+ "grad_norm": 1.03125,
3097
+ "learning_rate": 1.4872501257253325e-05,
3098
+ "loss": 0.4625,
3099
+ "step": 438
3100
+ },
3101
+ {
3102
+ "epoch": 0.7974568574023615,
3103
+ "grad_norm": 0.85546875,
3104
+ "learning_rate": 1.484504290844398e-05,
3105
+ "loss": 0.4496,
3106
+ "step": 439
3107
+ },
3108
+ {
3109
+ "epoch": 0.7992733878292462,
3110
+ "grad_norm": 1.0390625,
3111
+ "learning_rate": 1.4817536741017153e-05,
3112
+ "loss": 0.4508,
3113
+ "step": 440
3114
+ },
3115
+ {
3116
+ "epoch": 0.8010899182561307,
3117
+ "grad_norm": 0.88671875,
3118
+ "learning_rate": 1.4789983026447612e-05,
3119
+ "loss": 0.4589,
3120
+ "step": 441
3121
+ },
3122
+ {
3123
+ "epoch": 0.8029064486830154,
3124
+ "grad_norm": 1.0,
3125
+ "learning_rate": 1.4762382036679393e-05,
3126
+ "loss": 0.4499,
3127
+ "step": 442
3128
+ },
3129
+ {
3130
+ "epoch": 0.8047229791099001,
3131
+ "grad_norm": 1.0078125,
3132
+ "learning_rate": 1.4734734044123123e-05,
3133
+ "loss": 0.4476,
3134
+ "step": 443
3135
+ },
3136
+ {
3137
+ "epoch": 0.8065395095367848,
3138
+ "grad_norm": 0.94921875,
3139
+ "learning_rate": 1.470703932165333e-05,
3140
+ "loss": 0.452,
3141
+ "step": 444
3142
+ },
3143
+ {
3144
+ "epoch": 0.8083560399636693,
3145
+ "grad_norm": 0.96875,
3146
+ "learning_rate": 1.4679298142605735e-05,
3147
+ "loss": 0.4438,
3148
+ "step": 445
3149
+ },
3150
+ {
3151
+ "epoch": 0.810172570390554,
3152
+ "grad_norm": 0.98828125,
3153
+ "learning_rate": 1.4651510780774585e-05,
3154
+ "loss": 0.4426,
3155
+ "step": 446
3156
+ },
3157
+ {
3158
+ "epoch": 0.8119891008174387,
3159
+ "grad_norm": 1.046875,
3160
+ "learning_rate": 1.462367751040992e-05,
3161
+ "loss": 0.451,
3162
+ "step": 447
3163
+ },
3164
+ {
3165
+ "epoch": 0.8138056312443234,
3166
+ "grad_norm": 1.046875,
3167
+ "learning_rate": 1.4595798606214882e-05,
3168
+ "loss": 0.4637,
3169
+ "step": 448
3170
+ },
3171
+ {
3172
+ "epoch": 0.815622161671208,
3173
+ "grad_norm": 0.984375,
3174
+ "learning_rate": 1.4567874343342996e-05,
3175
+ "loss": 0.4576,
3176
+ "step": 449
3177
+ },
3178
+ {
3179
+ "epoch": 0.8174386920980926,
3180
+ "grad_norm": 1.1171875,
3181
+ "learning_rate": 1.4539904997395468e-05,
3182
+ "loss": 0.4755,
3183
+ "step": 450
3184
+ },
3185
+ {
3186
+ "epoch": 0.8192552225249773,
3187
+ "grad_norm": 1.0390625,
3188
+ "learning_rate": 1.4511890844418453e-05,
3189
+ "loss": 0.4501,
3190
+ "step": 451
3191
+ },
3192
+ {
3193
+ "epoch": 0.821071752951862,
3194
+ "grad_norm": 1.0546875,
3195
+ "learning_rate": 1.4483832160900326e-05,
3196
+ "loss": 0.4471,
3197
+ "step": 452
3198
+ },
3199
+ {
3200
+ "epoch": 0.8228882833787466,
3201
+ "grad_norm": 0.91796875,
3202
+ "learning_rate": 1.4455729223768966e-05,
3203
+ "loss": 0.4491,
3204
+ "step": 453
3205
+ },
3206
+ {
3207
+ "epoch": 0.8247048138056312,
3208
+ "grad_norm": 0.890625,
3209
+ "learning_rate": 1.442758231038902e-05,
3210
+ "loss": 0.4429,
3211
+ "step": 454
3212
+ },
3213
+ {
3214
+ "epoch": 0.8265213442325159,
3215
+ "grad_norm": 0.93359375,
3216
+ "learning_rate": 1.4399391698559153e-05,
3217
+ "loss": 0.4597,
3218
+ "step": 455
3219
+ },
3220
+ {
3221
+ "epoch": 0.8283378746594006,
3222
+ "grad_norm": 0.99609375,
3223
+ "learning_rate": 1.437115766650933e-05,
3224
+ "loss": 0.4525,
3225
+ "step": 456
3226
+ },
3227
+ {
3228
+ "epoch": 0.8301544050862852,
3229
+ "grad_norm": 1.03125,
3230
+ "learning_rate": 1.4342880492898048e-05,
3231
+ "loss": 0.4568,
3232
+ "step": 457
3233
+ },
3234
+ {
3235
+ "epoch": 0.8319709355131698,
3236
+ "grad_norm": 1.0234375,
3237
+ "learning_rate": 1.4314560456809592e-05,
3238
+ "loss": 0.4491,
3239
+ "step": 458
3240
+ },
3241
+ {
3242
+ "epoch": 0.8337874659400545,
3243
+ "grad_norm": 0.97265625,
3244
+ "learning_rate": 1.4286197837751286e-05,
3245
+ "loss": 0.4501,
3246
+ "step": 459
3247
+ },
3248
+ {
3249
+ "epoch": 0.8356039963669392,
3250
+ "grad_norm": 1.0390625,
3251
+ "learning_rate": 1.4257792915650728e-05,
3252
+ "loss": 0.4601,
3253
+ "step": 460
3254
+ },
3255
+ {
3256
+ "epoch": 0.8374205267938238,
3257
+ "grad_norm": 1.0078125,
3258
+ "learning_rate": 1.4229345970853032e-05,
3259
+ "loss": 0.4474,
3260
+ "step": 461
3261
+ },
3262
+ {
3263
+ "epoch": 0.8392370572207084,
3264
+ "grad_norm": 1.0234375,
3265
+ "learning_rate": 1.4200857284118067e-05,
3266
+ "loss": 0.4454,
3267
+ "step": 462
3268
+ },
3269
+ {
3270
+ "epoch": 0.8410535876475931,
3271
+ "grad_norm": 1.0703125,
3272
+ "learning_rate": 1.4172327136617656e-05,
3273
+ "loss": 0.4454,
3274
+ "step": 463
3275
+ },
3276
+ {
3277
+ "epoch": 0.8428701180744778,
3278
+ "grad_norm": 1.2421875,
3279
+ "learning_rate": 1.4143755809932843e-05,
3280
+ "loss": 0.4471,
3281
+ "step": 464
3282
+ },
3283
+ {
3284
+ "epoch": 0.8446866485013624,
3285
+ "grad_norm": 1.109375,
3286
+ "learning_rate": 1.411514358605109e-05,
3287
+ "loss": 0.4513,
3288
+ "step": 465
3289
+ },
3290
+ {
3291
+ "epoch": 0.846503178928247,
3292
+ "grad_norm": 0.98828125,
3293
+ "learning_rate": 1.4086490747363492e-05,
3294
+ "loss": 0.4702,
3295
+ "step": 466
3296
+ },
3297
+ {
3298
+ "epoch": 0.8483197093551317,
3299
+ "grad_norm": 1.0234375,
3300
+ "learning_rate": 1.4057797576662e-05,
3301
+ "loss": 0.4456,
3302
+ "step": 467
3303
+ },
3304
+ {
3305
+ "epoch": 0.8501362397820164,
3306
+ "grad_norm": 0.93359375,
3307
+ "learning_rate": 1.4029064357136628e-05,
3308
+ "loss": 0.4347,
3309
+ "step": 468
3310
+ },
3311
+ {
3312
+ "epoch": 0.851952770208901,
3313
+ "grad_norm": 1.0234375,
3314
+ "learning_rate": 1.4000291372372647e-05,
3315
+ "loss": 0.4546,
3316
+ "step": 469
3317
+ },
3318
+ {
3319
+ "epoch": 0.8537693006357856,
3320
+ "grad_norm": 1.0,
3321
+ "learning_rate": 1.3971478906347806e-05,
3322
+ "loss": 0.4448,
3323
+ "step": 470
3324
+ },
3325
+ {
3326
+ "epoch": 0.8555858310626703,
3327
+ "grad_norm": 1.1328125,
3328
+ "learning_rate": 1.3942627243429512e-05,
3329
+ "loss": 0.4443,
3330
+ "step": 471
3331
+ },
3332
+ {
3333
+ "epoch": 0.857402361489555,
3334
+ "grad_norm": 1.171875,
3335
+ "learning_rate": 1.3913736668372027e-05,
3336
+ "loss": 0.4598,
3337
+ "step": 472
3338
+ },
3339
+ {
3340
+ "epoch": 0.8592188919164396,
3341
+ "grad_norm": 0.96875,
3342
+ "learning_rate": 1.3884807466313664e-05,
3343
+ "loss": 0.444,
3344
+ "step": 473
3345
+ },
3346
+ {
3347
+ "epoch": 0.8610354223433242,
3348
+ "grad_norm": 0.92578125,
3349
+ "learning_rate": 1.3855839922773968e-05,
3350
+ "loss": 0.4509,
3351
+ "step": 474
3352
+ },
3353
+ {
3354
+ "epoch": 0.8628519527702089,
3355
+ "grad_norm": 0.98828125,
3356
+ "learning_rate": 1.3826834323650899e-05,
3357
+ "loss": 0.4655,
3358
+ "step": 475
3359
+ },
3360
+ {
3361
+ "epoch": 0.8646684831970936,
3362
+ "grad_norm": 0.98828125,
3363
+ "learning_rate": 1.3797790955218014e-05,
3364
+ "loss": 0.4516,
3365
+ "step": 476
3366
+ },
3367
+ {
3368
+ "epoch": 0.8664850136239782,
3369
+ "grad_norm": 0.90234375,
3370
+ "learning_rate": 1.3768710104121628e-05,
3371
+ "loss": 0.458,
3372
+ "step": 477
3373
+ },
3374
+ {
3375
+ "epoch": 0.8683015440508629,
3376
+ "grad_norm": 1.1640625,
3377
+ "learning_rate": 1.3739592057378005e-05,
3378
+ "loss": 0.4561,
3379
+ "step": 478
3380
+ },
3381
+ {
3382
+ "epoch": 0.8701180744777475,
3383
+ "grad_norm": 1.0234375,
3384
+ "learning_rate": 1.3710437102370511e-05,
3385
+ "loss": 0.4539,
3386
+ "step": 479
3387
+ },
3388
+ {
3389
+ "epoch": 0.8719346049046321,
3390
+ "grad_norm": 0.9609375,
3391
+ "learning_rate": 1.3681245526846782e-05,
3392
+ "loss": 0.4428,
3393
+ "step": 480
3394
+ },
3395
+ {
3396
+ "epoch": 0.8737511353315168,
3397
+ "grad_norm": 0.95703125,
3398
+ "learning_rate": 1.365201761891588e-05,
3399
+ "loss": 0.4426,
3400
+ "step": 481
3401
+ },
3402
+ {
3403
+ "epoch": 0.8755676657584015,
3404
+ "grad_norm": 1.09375,
3405
+ "learning_rate": 1.3622753667045459e-05,
3406
+ "loss": 0.4518,
3407
+ "step": 482
3408
+ },
3409
+ {
3410
+ "epoch": 0.8773841961852861,
3411
+ "grad_norm": 0.984375,
3412
+ "learning_rate": 1.3593453960058909e-05,
3413
+ "loss": 0.4453,
3414
+ "step": 483
3415
+ },
3416
+ {
3417
+ "epoch": 0.8792007266121707,
3418
+ "grad_norm": 1.0234375,
3419
+ "learning_rate": 1.3564118787132507e-05,
3420
+ "loss": 0.4581,
3421
+ "step": 484
3422
+ },
3423
+ {
3424
+ "epoch": 0.8810172570390554,
3425
+ "grad_norm": 1.0390625,
3426
+ "learning_rate": 1.3534748437792573e-05,
3427
+ "loss": 0.4543,
3428
+ "step": 485
3429
+ },
3430
+ {
3431
+ "epoch": 0.8828337874659401,
3432
+ "grad_norm": 0.921875,
3433
+ "learning_rate": 1.350534320191259e-05,
3434
+ "loss": 0.4446,
3435
+ "step": 486
3436
+ },
3437
+ {
3438
+ "epoch": 0.8846503178928247,
3439
+ "grad_norm": 1.0625,
3440
+ "learning_rate": 1.347590336971037e-05,
3441
+ "loss": 0.4394,
3442
+ "step": 487
3443
+ },
3444
+ {
3445
+ "epoch": 0.8864668483197093,
3446
+ "grad_norm": 0.96875,
3447
+ "learning_rate": 1.344642923174517e-05,
3448
+ "loss": 0.4523,
3449
+ "step": 488
3450
+ },
3451
+ {
3452
+ "epoch": 0.888283378746594,
3453
+ "grad_norm": 1.046875,
3454
+ "learning_rate": 1.3416921078914835e-05,
3455
+ "loss": 0.4602,
3456
+ "step": 489
3457
+ },
3458
+ {
3459
+ "epoch": 0.8900999091734787,
3460
+ "grad_norm": 1.015625,
3461
+ "learning_rate": 1.3387379202452917e-05,
3462
+ "loss": 0.4418,
3463
+ "step": 490
3464
+ },
3465
+ {
3466
+ "epoch": 0.8919164396003633,
3467
+ "grad_norm": 0.9609375,
3468
+ "learning_rate": 1.3357803893925807e-05,
3469
+ "loss": 0.4399,
3470
+ "step": 491
3471
+ },
3472
+ {
3473
+ "epoch": 0.8937329700272479,
3474
+ "grad_norm": 1.046875,
3475
+ "learning_rate": 1.3328195445229869e-05,
3476
+ "loss": 0.4492,
3477
+ "step": 492
3478
+ },
3479
+ {
3480
+ "epoch": 0.8955495004541326,
3481
+ "grad_norm": 1.0078125,
3482
+ "learning_rate": 1.329855414858853e-05,
3483
+ "loss": 0.4605,
3484
+ "step": 493
3485
+ },
3486
+ {
3487
+ "epoch": 0.8973660308810173,
3488
+ "grad_norm": 0.9453125,
3489
+ "learning_rate": 1.3268880296549424e-05,
3490
+ "loss": 0.4497,
3491
+ "step": 494
3492
+ },
3493
+ {
3494
+ "epoch": 0.8991825613079019,
3495
+ "grad_norm": 0.96875,
3496
+ "learning_rate": 1.3239174181981496e-05,
3497
+ "loss": 0.4604,
3498
+ "step": 495
3499
+ },
3500
+ {
3501
+ "epoch": 0.9009990917347865,
3502
+ "grad_norm": 1.0234375,
3503
+ "learning_rate": 1.3209436098072095e-05,
3504
+ "loss": 0.4542,
3505
+ "step": 496
3506
+ },
3507
+ {
3508
+ "epoch": 0.9028156221616712,
3509
+ "grad_norm": 0.94140625,
3510
+ "learning_rate": 1.317966633832411e-05,
3511
+ "loss": 0.4468,
3512
+ "step": 497
3513
+ },
3514
+ {
3515
+ "epoch": 0.9046321525885559,
3516
+ "grad_norm": 0.98046875,
3517
+ "learning_rate": 1.3149865196553049e-05,
3518
+ "loss": 0.4623,
3519
+ "step": 498
3520
+ },
3521
+ {
3522
+ "epoch": 0.9064486830154405,
3523
+ "grad_norm": 0.97265625,
3524
+ "learning_rate": 1.3120032966884151e-05,
3525
+ "loss": 0.4479,
3526
+ "step": 499
3527
+ },
3528
+ {
3529
+ "epoch": 0.9082652134423251,
3530
+ "grad_norm": 0.9375,
3531
+ "learning_rate": 1.3090169943749475e-05,
3532
+ "loss": 0.456,
3533
+ "step": 500
3534
+ },
3535
+ {
3536
+ "epoch": 0.9100817438692098,
3537
+ "grad_norm": 1.078125,
3538
+ "learning_rate": 1.306027642188501e-05,
3539
+ "loss": 0.4532,
3540
+ "step": 501
3541
+ },
3542
+ {
3543
+ "epoch": 0.9118982742960945,
3544
+ "grad_norm": 0.953125,
3545
+ "learning_rate": 1.3030352696327741e-05,
3546
+ "loss": 0.4517,
3547
+ "step": 502
3548
+ },
3549
+ {
3550
+ "epoch": 0.9137148047229791,
3551
+ "grad_norm": 1.0703125,
3552
+ "learning_rate": 1.3000399062412763e-05,
3553
+ "loss": 0.4304,
3554
+ "step": 503
3555
+ },
3556
+ {
3557
+ "epoch": 0.9155313351498637,
3558
+ "grad_norm": 1.0,
3559
+ "learning_rate": 1.297041581577035e-05,
3560
+ "loss": 0.4352,
3561
+ "step": 504
3562
+ },
3563
+ {
3564
+ "epoch": 0.9173478655767484,
3565
+ "grad_norm": 1.09375,
3566
+ "learning_rate": 1.294040325232304e-05,
3567
+ "loss": 0.4319,
3568
+ "step": 505
3569
+ },
3570
+ {
3571
+ "epoch": 0.9191643960036331,
3572
+ "grad_norm": 0.93359375,
3573
+ "learning_rate": 1.2910361668282718e-05,
3574
+ "loss": 0.451,
3575
+ "step": 506
3576
+ },
3577
+ {
3578
+ "epoch": 0.9209809264305178,
3579
+ "grad_norm": 0.95703125,
3580
+ "learning_rate": 1.2880291360147694e-05,
3581
+ "loss": 0.4431,
3582
+ "step": 507
3583
+ },
3584
+ {
3585
+ "epoch": 0.9227974568574023,
3586
+ "grad_norm": 0.93359375,
3587
+ "learning_rate": 1.2850192624699762e-05,
3588
+ "loss": 0.4596,
3589
+ "step": 508
3590
+ },
3591
+ {
3592
+ "epoch": 0.924613987284287,
3593
+ "grad_norm": 0.96875,
3594
+ "learning_rate": 1.2820065759001295e-05,
3595
+ "loss": 0.4516,
3596
+ "step": 509
3597
+ },
3598
+ {
3599
+ "epoch": 0.9264305177111717,
3600
+ "grad_norm": 0.97265625,
3601
+ "learning_rate": 1.2789911060392295e-05,
3602
+ "loss": 0.4492,
3603
+ "step": 510
3604
+ },
3605
+ {
3606
+ "epoch": 0.9282470481380564,
3607
+ "grad_norm": 0.9765625,
3608
+ "learning_rate": 1.2759728826487461e-05,
3609
+ "loss": 0.4476,
3610
+ "step": 511
3611
+ },
3612
+ {
3613
+ "epoch": 0.9300635785649409,
3614
+ "grad_norm": 0.94921875,
3615
+ "learning_rate": 1.2729519355173254e-05,
3616
+ "loss": 0.4468,
3617
+ "step": 512
3618
+ },
3619
+ {
3620
+ "epoch": 0.9318801089918256,
3621
+ "grad_norm": 1.015625,
3622
+ "learning_rate": 1.2699282944604968e-05,
3623
+ "loss": 0.4413,
3624
+ "step": 513
3625
+ },
3626
+ {
3627
+ "epoch": 0.9336966394187103,
3628
+ "grad_norm": 0.9296875,
3629
+ "learning_rate": 1.2669019893203758e-05,
3630
+ "loss": 0.4409,
3631
+ "step": 514
3632
+ },
3633
+ {
3634
+ "epoch": 0.935513169845595,
3635
+ "grad_norm": 0.96875,
3636
+ "learning_rate": 1.2638730499653731e-05,
3637
+ "loss": 0.4381,
3638
+ "step": 515
3639
+ },
3640
+ {
3641
+ "epoch": 0.9373297002724795,
3642
+ "grad_norm": 0.98046875,
3643
+ "learning_rate": 1.2608415062898971e-05,
3644
+ "loss": 0.4573,
3645
+ "step": 516
3646
+ },
3647
+ {
3648
+ "epoch": 0.9391462306993642,
3649
+ "grad_norm": 0.90625,
3650
+ "learning_rate": 1.25780738821406e-05,
3651
+ "loss": 0.4509,
3652
+ "step": 517
3653
+ },
3654
+ {
3655
+ "epoch": 0.9409627611262489,
3656
+ "grad_norm": 1.078125,
3657
+ "learning_rate": 1.2547707256833823e-05,
3658
+ "loss": 0.4566,
3659
+ "step": 518
3660
+ },
3661
+ {
3662
+ "epoch": 0.9427792915531336,
3663
+ "grad_norm": 0.93359375,
3664
+ "learning_rate": 1.2517315486684973e-05,
3665
+ "loss": 0.4379,
3666
+ "step": 519
3667
+ },
3668
+ {
3669
+ "epoch": 0.9445958219800181,
3670
+ "grad_norm": 1.1171875,
3671
+ "learning_rate": 1.2486898871648552e-05,
3672
+ "loss": 0.439,
3673
+ "step": 520
3674
+ },
3675
+ {
3676
+ "epoch": 0.9464123524069028,
3677
+ "grad_norm": 1.046875,
3678
+ "learning_rate": 1.2456457711924266e-05,
3679
+ "loss": 0.4341,
3680
+ "step": 521
3681
+ },
3682
+ {
3683
+ "epoch": 0.9482288828337875,
3684
+ "grad_norm": 0.91015625,
3685
+ "learning_rate": 1.2425992307954075e-05,
3686
+ "loss": 0.4375,
3687
+ "step": 522
3688
+ },
3689
+ {
3690
+ "epoch": 0.9500454132606722,
3691
+ "grad_norm": 1.0703125,
3692
+ "learning_rate": 1.2395502960419221e-05,
3693
+ "loss": 0.4627,
3694
+ "step": 523
3695
+ },
3696
+ {
3697
+ "epoch": 0.9518619436875567,
3698
+ "grad_norm": 1.03125,
3699
+ "learning_rate": 1.236498997023725e-05,
3700
+ "loss": 0.445,
3701
+ "step": 524
3702
+ },
3703
+ {
3704
+ "epoch": 0.9536784741144414,
3705
+ "grad_norm": 0.8671875,
3706
+ "learning_rate": 1.2334453638559057e-05,
3707
+ "loss": 0.4422,
3708
+ "step": 525
3709
+ },
3710
+ {
3711
+ "epoch": 0.9554950045413261,
3712
+ "grad_norm": 1.0234375,
3713
+ "learning_rate": 1.2303894266765908e-05,
3714
+ "loss": 0.4506,
3715
+ "step": 526
3716
+ },
3717
+ {
3718
+ "epoch": 0.9573115349682108,
3719
+ "grad_norm": 0.859375,
3720
+ "learning_rate": 1.2273312156466466e-05,
3721
+ "loss": 0.4475,
3722
+ "step": 527
3723
+ },
3724
+ {
3725
+ "epoch": 0.9591280653950953,
3726
+ "grad_norm": 0.91015625,
3727
+ "learning_rate": 1.2242707609493814e-05,
3728
+ "loss": 0.436,
3729
+ "step": 528
3730
+ },
3731
+ {
3732
+ "epoch": 0.96094459582198,
3733
+ "grad_norm": 0.9765625,
3734
+ "learning_rate": 1.2212080927902474e-05,
3735
+ "loss": 0.4527,
3736
+ "step": 529
3737
+ },
3738
+ {
3739
+ "epoch": 0.9627611262488647,
3740
+ "grad_norm": 0.8671875,
3741
+ "learning_rate": 1.2181432413965428e-05,
3742
+ "loss": 0.445,
3743
+ "step": 530
3744
+ },
3745
+ {
3746
+ "epoch": 0.9645776566757494,
3747
+ "grad_norm": 1.0625,
3748
+ "learning_rate": 1.2150762370171137e-05,
3749
+ "loss": 0.4447,
3750
+ "step": 531
3751
+ },
3752
+ {
3753
+ "epoch": 0.9663941871026339,
3754
+ "grad_norm": 1.0546875,
3755
+ "learning_rate": 1.212007109922055e-05,
3756
+ "loss": 0.4446,
3757
+ "step": 532
3758
+ },
3759
+ {
3760
+ "epoch": 0.9682107175295186,
3761
+ "grad_norm": 0.86328125,
3762
+ "learning_rate": 1.2089358904024117e-05,
3763
+ "loss": 0.4394,
3764
+ "step": 533
3765
+ },
3766
+ {
3767
+ "epoch": 0.9700272479564033,
3768
+ "grad_norm": 0.98828125,
3769
+ "learning_rate": 1.2058626087698814e-05,
3770
+ "loss": 0.4407,
3771
+ "step": 534
3772
+ },
3773
+ {
3774
+ "epoch": 0.971843778383288,
3775
+ "grad_norm": 0.9609375,
3776
+ "learning_rate": 1.2027872953565125e-05,
3777
+ "loss": 0.4396,
3778
+ "step": 535
3779
+ },
3780
+ {
3781
+ "epoch": 0.9736603088101726,
3782
+ "grad_norm": 0.94140625,
3783
+ "learning_rate": 1.1997099805144071e-05,
3784
+ "loss": 0.4557,
3785
+ "step": 536
3786
+ },
3787
+ {
3788
+ "epoch": 0.9754768392370572,
3789
+ "grad_norm": 0.90625,
3790
+ "learning_rate": 1.19663069461542e-05,
3791
+ "loss": 0.4415,
3792
+ "step": 537
3793
+ },
3794
+ {
3795
+ "epoch": 0.9772933696639419,
3796
+ "grad_norm": 0.98046875,
3797
+ "learning_rate": 1.1935494680508606e-05,
3798
+ "loss": 0.4474,
3799
+ "step": 538
3800
+ },
3801
+ {
3802
+ "epoch": 0.9791099000908265,
3803
+ "grad_norm": 0.8828125,
3804
+ "learning_rate": 1.1904663312311902e-05,
3805
+ "loss": 0.4546,
3806
+ "step": 539
3807
+ },
3808
+ {
3809
+ "epoch": 0.9809264305177112,
3810
+ "grad_norm": 1.046875,
3811
+ "learning_rate": 1.187381314585725e-05,
3812
+ "loss": 0.4402,
3813
+ "step": 540
3814
+ },
3815
+ {
3816
+ "epoch": 0.9827429609445958,
3817
+ "grad_norm": 0.90234375,
3818
+ "learning_rate": 1.1842944485623335e-05,
3819
+ "loss": 0.4257,
3820
+ "step": 541
3821
+ },
3822
+ {
3823
+ "epoch": 0.9845594913714805,
3824
+ "grad_norm": 0.87109375,
3825
+ "learning_rate": 1.1812057636271374e-05,
3826
+ "loss": 0.4409,
3827
+ "step": 542
3828
+ },
3829
+ {
3830
+ "epoch": 0.9863760217983651,
3831
+ "grad_norm": 0.99609375,
3832
+ "learning_rate": 1.17811529026421e-05,
3833
+ "loss": 0.4522,
3834
+ "step": 543
3835
+ },
3836
+ {
3837
+ "epoch": 0.9881925522252498,
3838
+ "grad_norm": 0.953125,
3839
+ "learning_rate": 1.1750230589752763e-05,
3840
+ "loss": 0.4594,
3841
+ "step": 544
3842
+ },
3843
+ {
3844
+ "epoch": 0.9900090826521344,
3845
+ "grad_norm": 1.0234375,
3846
+ "learning_rate": 1.1719291002794096e-05,
3847
+ "loss": 0.437,
3848
+ "step": 545
3849
+ },
3850
+ {
3851
+ "epoch": 0.9918256130790191,
3852
+ "grad_norm": 1.0234375,
3853
+ "learning_rate": 1.1688334447127338e-05,
3854
+ "loss": 0.4266,
3855
+ "step": 546
3856
+ },
3857
+ {
3858
+ "epoch": 0.9936421435059037,
3859
+ "grad_norm": 0.90234375,
3860
+ "learning_rate": 1.1657361228281198e-05,
3861
+ "loss": 0.4377,
3862
+ "step": 547
3863
+ },
3864
+ {
3865
+ "epoch": 0.9954586739327884,
3866
+ "grad_norm": 0.9140625,
3867
+ "learning_rate": 1.1626371651948839e-05,
3868
+ "loss": 0.4373,
3869
+ "step": 548
3870
+ },
3871
+ {
3872
+ "epoch": 0.997275204359673,
3873
+ "grad_norm": 1.046875,
3874
+ "learning_rate": 1.1595366023984864e-05,
3875
+ "loss": 0.4395,
3876
+ "step": 549
3877
+ },
3878
+ {
3879
+ "epoch": 0.9990917347865577,
3880
+ "grad_norm": 0.92578125,
3881
+ "learning_rate": 1.156434465040231e-05,
3882
+ "loss": 0.4454,
3883
+ "step": 550
3884
+ }
3885
+ ],
3886
+ "logging_steps": 1,
3887
+ "max_steps": 1100,
3888
+ "num_input_tokens_seen": 0,
3889
+ "num_train_epochs": 2,
3890
+ "save_steps": 550,
3891
+ "total_flos": 6.492324211615334e+18,
3892
+ "train_batch_size": 1,
3893
+ "trial_name": null,
3894
+ "trial_params": null
3895
+ }
checkpoint-550/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acfdd936d2ba45f8c9b9b7cbbc505a6f7b90e583f2d68f5ad65a25f1ea2d340d
3
+ size 6008