Hugging Face's logo

FuseAI
/
FuseChat-Llama-3.2-1B-Instruct

Safetensors
llama
Model card Files Community
AALF commited on
Commit
12d0245
•
1 Parent(s): 613d906

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. all_results.json +9 -0
  2. checkpoint-404/config.json +40 -0
  3. checkpoint-404/generation_config.json +12 -0
  4. checkpoint-404/model.safetensors +3 -0
  5. checkpoint-404/special_tokens_map.json +23 -0
  6. checkpoint-404/tokenizer.json +0 -0
  7. checkpoint-404/tokenizer_config.json +2065 -0
  8. checkpoint-404/trainer_state.json +1248 -0
  9. checkpoint-404/training_args.bin +3 -0
  10. config.json +40 -0
  11. generation_config.json +12 -0
  12. model.safetensors +3 -0
  13. special_tokens_map.json +23 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +2065 -0
  16. train_results.json +9 -0
  17. trainer_state.json +1557 -0
  18. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.559710203114146,
5
+ "train_runtime": 2572.2381,
6
+ "train_samples": 64128,
7
+ "train_samples_per_second": 24.931,
8
+ "train_steps_per_second": 0.195
9
+ }
checkpoint-404/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/GLOBALFS/gznwp_3/qxj/lgzhong/LLaMA-Factory/saves/llama31/Llama-3.2-1B-Instruct-SFT-v1.5-lr5e-6-packing",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.43.4",
38
+ "use_cache": false,
39
+ "vocab_size": 128256
40
+ }
checkpoint-404/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.43.4"
12
+ }
checkpoint-404/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a83d6f62cd17fd7fd442732c002638b6ee8adddc6bc4f8ffe63a60f9e6aa54ef
3
+ size 2471645608
checkpoint-404/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-404/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-404/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 2048,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
checkpoint-404/trainer_state.json ADDED
@@ -0,0 +1,1248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8063872255489022,
5
+ "eval_steps": 500,
6
+ "global_step": 404,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.001996007984031936,
13
+ "grad_norm": 16.492788975984936,
14
+ "learning_rate": 1.9607843137254902e-08,
15
+ "logits/chosen": 1.3011724948883057,
16
+ "logits/rejected": 1.3879833221435547,
17
+ "logps/chosen": -0.9583934545516968,
18
+ "logps/rejected": -0.908146858215332,
19
+ "loss": 0.6931,
20
+ "rewards/accuracies": 0.0,
21
+ "rewards/chosen": 0.0,
22
+ "rewards/margins": 0.0,
23
+ "rewards/rejected": 0.0,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.00998003992015968,
28
+ "grad_norm": 18.616408754077472,
29
+ "learning_rate": 9.80392156862745e-08,
30
+ "logits/chosen": 1.230096697807312,
31
+ "logits/rejected": 1.2526068687438965,
32
+ "logps/chosen": -0.8566818833351135,
33
+ "logps/rejected": -0.9451415538787842,
34
+ "loss": 0.6931,
35
+ "rewards/accuracies": 0.34375,
36
+ "rewards/chosen": -0.00325668603181839,
37
+ "rewards/margins": -0.0027664820663630962,
38
+ "rewards/rejected": -0.0004902039654552937,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01996007984031936,
43
+ "grad_norm": 19.72943287901331,
44
+ "learning_rate": 1.96078431372549e-07,
45
+ "logits/chosen": 1.1732714176177979,
46
+ "logits/rejected": 1.2325665950775146,
47
+ "logps/chosen": -0.8571804165840149,
48
+ "logps/rejected": -0.9293950200080872,
49
+ "loss": 0.6935,
50
+ "rewards/accuracies": 0.5249999761581421,
51
+ "rewards/chosen": -0.0004458148032426834,
52
+ "rewards/margins": 0.00015245657414197922,
53
+ "rewards/rejected": -0.0005982713773846626,
54
+ "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.029940119760479042,
58
+ "grad_norm": 15.989882260008397,
59
+ "learning_rate": 2.941176470588235e-07,
60
+ "logits/chosen": 1.1804090738296509,
61
+ "logits/rejected": 1.227670669555664,
62
+ "logps/chosen": -0.8887054324150085,
63
+ "logps/rejected": -0.9415630102157593,
64
+ "loss": 0.6942,
65
+ "rewards/accuracies": 0.4124999940395355,
66
+ "rewards/chosen": -0.005856434814631939,
67
+ "rewards/margins": -0.004528886638581753,
68
+ "rewards/rejected": -0.0013275481760501862,
69
+ "step": 15
70
+ },
71
+ {
72
+ "epoch": 0.03992015968063872,
73
+ "grad_norm": 21.617808491664096,
74
+ "learning_rate": 3.92156862745098e-07,
75
+ "logits/chosen": 1.2326724529266357,
76
+ "logits/rejected": 1.239334225654602,
77
+ "logps/chosen": -1.025779366493225,
78
+ "logps/rejected": -0.9815893173217773,
79
+ "loss": 0.6924,
80
+ "rewards/accuracies": 0.5249999761581421,
81
+ "rewards/chosen": -0.011453075334429741,
82
+ "rewards/margins": -0.006528028752654791,
83
+ "rewards/rejected": -0.004925046116113663,
84
+ "step": 20
85
+ },
86
+ {
87
+ "epoch": 0.0499001996007984,
88
+ "grad_norm": 14.85293949325317,
89
+ "learning_rate": 4.901960784313725e-07,
90
+ "logits/chosen": 1.1621646881103516,
91
+ "logits/rejected": 1.2202112674713135,
92
+ "logps/chosen": -0.9435383081436157,
93
+ "logps/rejected": -1.0095245838165283,
94
+ "loss": 0.6926,
95
+ "rewards/accuracies": 0.4749999940395355,
96
+ "rewards/chosen": -0.008930020034313202,
97
+ "rewards/margins": 0.011791445314884186,
98
+ "rewards/rejected": -0.020721465349197388,
99
+ "step": 25
100
+ },
101
+ {
102
+ "epoch": 0.059880239520958084,
103
+ "grad_norm": 18.28049213488445,
104
+ "learning_rate": 5.88235294117647e-07,
105
+ "logits/chosen": 1.2528660297393799,
106
+ "logits/rejected": 1.3036034107208252,
107
+ "logps/chosen": -0.9394888877868652,
108
+ "logps/rejected": -0.9887625575065613,
109
+ "loss": 0.6928,
110
+ "rewards/accuracies": 0.5,
111
+ "rewards/chosen": -0.020373398438096046,
112
+ "rewards/margins": -0.0037106983363628387,
113
+ "rewards/rejected": -0.016662701964378357,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.06986027944111776,
118
+ "grad_norm": 15.999817261895291,
119
+ "learning_rate": 6.862745098039216e-07,
120
+ "logits/chosen": 1.1911170482635498,
121
+ "logits/rejected": 1.2343870401382446,
122
+ "logps/chosen": -0.9691197276115417,
123
+ "logps/rejected": -0.9998400807380676,
124
+ "loss": 0.6912,
125
+ "rewards/accuracies": 0.48750001192092896,
126
+ "rewards/chosen": -0.01592147909104824,
127
+ "rewards/margins": 0.0014309640973806381,
128
+ "rewards/rejected": -0.01735244318842888,
129
+ "step": 35
130
+ },
131
+ {
132
+ "epoch": 0.07984031936127745,
133
+ "grad_norm": 14.867532956796651,
134
+ "learning_rate": 7.84313725490196e-07,
135
+ "logits/chosen": 1.2250399589538574,
136
+ "logits/rejected": 1.2877371311187744,
137
+ "logps/chosen": -0.9882305860519409,
138
+ "logps/rejected": -1.013457179069519,
139
+ "loss": 0.6866,
140
+ "rewards/accuracies": 0.625,
141
+ "rewards/chosen": -0.014133378863334656,
142
+ "rewards/margins": 0.023214522749185562,
143
+ "rewards/rejected": -0.03734790161252022,
144
+ "step": 40
145
+ },
146
+ {
147
+ "epoch": 0.08982035928143713,
148
+ "grad_norm": 19.324457876267314,
149
+ "learning_rate": 8.823529411764705e-07,
150
+ "logits/chosen": 1.2738926410675049,
151
+ "logits/rejected": 1.2850474119186401,
152
+ "logps/chosen": -0.9675604701042175,
153
+ "logps/rejected": -1.0223758220672607,
154
+ "loss": 0.6804,
155
+ "rewards/accuracies": 0.6499999761581421,
156
+ "rewards/chosen": -0.010748568922281265,
157
+ "rewards/margins": 0.0401780791580677,
158
+ "rewards/rejected": -0.05092664435505867,
159
+ "step": 45
160
+ },
161
+ {
162
+ "epoch": 0.0998003992015968,
163
+ "grad_norm": 18.41965619240879,
164
+ "learning_rate": 9.80392156862745e-07,
165
+ "logits/chosen": 1.2459691762924194,
166
+ "logits/rejected": 1.3021132946014404,
167
+ "logps/chosen": -0.9164802432060242,
168
+ "logps/rejected": -1.013667345046997,
169
+ "loss": 0.6739,
170
+ "rewards/accuracies": 0.637499988079071,
171
+ "rewards/chosen": -0.026862669736146927,
172
+ "rewards/margins": 0.07785479724407196,
173
+ "rewards/rejected": -0.10471747070550919,
174
+ "step": 50
175
+ },
176
+ {
177
+ "epoch": 0.10978043912175649,
178
+ "grad_norm": 16.897558680765105,
179
+ "learning_rate": 9.99805057520177e-07,
180
+ "logits/chosen": 1.1725871562957764,
181
+ "logits/rejected": 1.173532247543335,
182
+ "logps/chosen": -0.9711742401123047,
183
+ "logps/rejected": -0.9595904350280762,
184
+ "loss": 0.6738,
185
+ "rewards/accuracies": 0.737500011920929,
186
+ "rewards/chosen": -0.03100317157804966,
187
+ "rewards/margins": 0.11643954366445541,
188
+ "rewards/rejected": -0.14744271337985992,
189
+ "step": 55
190
+ },
191
+ {
192
+ "epoch": 0.11976047904191617,
193
+ "grad_norm": 14.265898399249132,
194
+ "learning_rate": 9.990133642141357e-07,
195
+ "logits/chosen": 1.1897612810134888,
196
+ "logits/rejected": 1.2000809907913208,
197
+ "logps/chosen": -0.9207404255867004,
198
+ "logps/rejected": -0.9565631747245789,
199
+ "loss": 0.6693,
200
+ "rewards/accuracies": 0.6000000238418579,
201
+ "rewards/chosen": -0.06663166731595993,
202
+ "rewards/margins": 0.18790733814239502,
203
+ "rewards/rejected": -0.25453901290893555,
204
+ "step": 60
205
+ },
206
+ {
207
+ "epoch": 0.12974051896207583,
208
+ "grad_norm": 19.11690615448299,
209
+ "learning_rate": 9.976136999909155e-07,
210
+ "logits/chosen": 1.261150598526001,
211
+ "logits/rejected": 1.2706950902938843,
212
+ "logps/chosen": -0.9832024574279785,
213
+ "logps/rejected": -0.9762998819351196,
214
+ "loss": 0.6736,
215
+ "rewards/accuracies": 0.675000011920929,
216
+ "rewards/chosen": -0.08731752634048462,
217
+ "rewards/margins": 0.037145014852285385,
218
+ "rewards/rejected": -0.1244625449180603,
219
+ "step": 65
220
+ },
221
+ {
222
+ "epoch": 0.13972055888223553,
223
+ "grad_norm": 16.308947856088572,
224
+ "learning_rate": 9.956077701257707e-07,
225
+ "logits/chosen": 1.1949059963226318,
226
+ "logits/rejected": 1.2373930215835571,
227
+ "logps/chosen": -0.923254132270813,
228
+ "logps/rejected": -0.9537776708602905,
229
+ "loss": 0.6588,
230
+ "rewards/accuracies": 0.800000011920929,
231
+ "rewards/chosen": -0.0689881294965744,
232
+ "rewards/margins": 0.0771615132689476,
233
+ "rewards/rejected": -0.1461496502161026,
234
+ "step": 70
235
+ },
236
+ {
237
+ "epoch": 0.1497005988023952,
238
+ "grad_norm": 18.31597399561215,
239
+ "learning_rate": 9.929980185352525e-07,
240
+ "logits/chosen": 1.1303855180740356,
241
+ "logits/rejected": 1.166472315788269,
242
+ "logps/chosen": -1.0079195499420166,
243
+ "logps/rejected": -1.0075769424438477,
244
+ "loss": 0.6486,
245
+ "rewards/accuracies": 0.7124999761581421,
246
+ "rewards/chosen": -0.026683980599045753,
247
+ "rewards/margins": 0.0837903693318367,
248
+ "rewards/rejected": -0.1104743480682373,
249
+ "step": 75
250
+ },
251
+ {
252
+ "epoch": 0.1596806387225549,
253
+ "grad_norm": 16.142069213484454,
254
+ "learning_rate": 9.89787624799672e-07,
255
+ "logits/chosen": 1.1199300289154053,
256
+ "logits/rejected": 1.1778942346572876,
257
+ "logps/chosen": -0.9652664065361023,
258
+ "logps/rejected": -1.0307899713516235,
259
+ "loss": 0.6496,
260
+ "rewards/accuracies": 0.737500011920929,
261
+ "rewards/chosen": -0.0005544237792491913,
262
+ "rewards/margins": 0.10419625043869019,
263
+ "rewards/rejected": -0.10475067049264908,
264
+ "step": 80
265
+ },
266
+ {
267
+ "epoch": 0.16966067864271456,
268
+ "grad_norm": 15.306215682029483,
269
+ "learning_rate": 9.859805002892731e-07,
270
+ "logits/chosen": 1.1645634174346924,
271
+ "logits/rejected": 1.1519969701766968,
272
+ "logps/chosen": -0.9917243719100952,
273
+ "logps/rejected": -1.060416340827942,
274
+ "loss": 0.661,
275
+ "rewards/accuracies": 0.675000011920929,
276
+ "rewards/chosen": -0.09171438962221146,
277
+ "rewards/margins": 0.20642364025115967,
278
+ "rewards/rejected": -0.2981380820274353,
279
+ "step": 85
280
+ },
281
+ {
282
+ "epoch": 0.17964071856287425,
283
+ "grad_norm": 15.254186655042064,
284
+ "learning_rate": 9.81581283398829e-07,
285
+ "logits/chosen": 1.103563904762268,
286
+ "logits/rejected": 1.1300289630889893,
287
+ "logps/chosen": -0.969647228717804,
288
+ "logps/rejected": -0.9916777610778809,
289
+ "loss": 0.6337,
290
+ "rewards/accuracies": 0.7250000238418579,
291
+ "rewards/chosen": 0.013281228020787239,
292
+ "rewards/margins": 0.1793346405029297,
293
+ "rewards/rejected": -0.1660534292459488,
294
+ "step": 90
295
+ },
296
+ {
297
+ "epoch": 0.18962075848303392,
298
+ "grad_norm": 15.282160453652757,
299
+ "learning_rate": 9.765953338964734e-07,
300
+ "logits/chosen": 1.0921884775161743,
301
+ "logits/rejected": 1.1226933002471924,
302
+ "logps/chosen": -1.0730102062225342,
303
+ "logps/rejected": -1.1024601459503174,
304
+ "loss": 0.6385,
305
+ "rewards/accuracies": 0.7749999761581421,
306
+ "rewards/chosen": 0.0058188484981656075,
307
+ "rewards/margins": 0.21344614028930664,
308
+ "rewards/rejected": -0.2076272964477539,
309
+ "step": 95
310
+ },
311
+ {
312
+ "epoch": 0.1996007984031936,
313
+ "grad_norm": 21.61748232589367,
314
+ "learning_rate": 9.710287263936483e-07,
315
+ "logits/chosen": 1.0795061588287354,
316
+ "logits/rejected": 1.0822367668151855,
317
+ "logps/chosen": -1.0821864604949951,
318
+ "logps/rejected": -1.1186153888702393,
319
+ "loss": 0.621,
320
+ "rewards/accuracies": 0.6875,
321
+ "rewards/chosen": 0.07217474281787872,
322
+ "rewards/margins": 0.3310089707374573,
323
+ "rewards/rejected": -0.25883427262306213,
324
+ "step": 100
325
+ },
326
+ {
327
+ "epoch": 0.20958083832335328,
328
+ "grad_norm": 23.129340339628143,
329
+ "learning_rate": 9.648882429441256e-07,
330
+ "logits/chosen": 1.0758105516433716,
331
+ "logits/rejected": 1.0959206819534302,
332
+ "logps/chosen": -0.9559111595153809,
333
+ "logps/rejected": -0.9702944755554199,
334
+ "loss": 0.6278,
335
+ "rewards/accuracies": 0.7124999761581421,
336
+ "rewards/chosen": -0.027358528226614,
337
+ "rewards/margins": 0.17237558960914612,
338
+ "rewards/rejected": -0.1997341364622116,
339
+ "step": 105
340
+ },
341
+ {
342
+ "epoch": 0.21956087824351297,
343
+ "grad_norm": 15.179993551058994,
344
+ "learning_rate": 9.581813647811197e-07,
345
+ "logits/chosen": 1.094158411026001,
346
+ "logits/rejected": 1.114650011062622,
347
+ "logps/chosen": -0.9534612894058228,
348
+ "logps/rejected": -0.9674752354621887,
349
+ "loss": 0.6124,
350
+ "rewards/accuracies": 0.75,
351
+ "rewards/chosen": 0.058080364018678665,
352
+ "rewards/margins": 0.30136996507644653,
353
+ "rewards/rejected": -0.24328958988189697,
354
+ "step": 110
355
+ },
356
+ {
357
+ "epoch": 0.22954091816367264,
358
+ "grad_norm": 13.705886523650493,
359
+ "learning_rate": 9.509162632025569e-07,
360
+ "logits/chosen": 1.0607202053070068,
361
+ "logits/rejected": 1.045424461364746,
362
+ "logps/chosen": -1.1245949268341064,
363
+ "logps/rejected": -1.1509120464324951,
364
+ "loss": 0.6167,
365
+ "rewards/accuracies": 0.675000011920929,
366
+ "rewards/chosen": -0.07293939590454102,
367
+ "rewards/margins": 0.17659255862236023,
368
+ "rewards/rejected": -0.24953195452690125,
369
+ "step": 115
370
+ },
371
+ {
372
+ "epoch": 0.23952095808383234,
373
+ "grad_norm": 27.63745397695,
374
+ "learning_rate": 9.431017896156073e-07,
375
+ "logits/chosen": 1.0884307622909546,
376
+ "logits/rejected": 1.101423978805542,
377
+ "logps/chosen": -0.9731513857841492,
378
+ "logps/rejected": -1.023944616317749,
379
+ "loss": 0.6061,
380
+ "rewards/accuracies": 0.6625000238418579,
381
+ "rewards/chosen": 0.055571239441633224,
382
+ "rewards/margins": 0.36377543210983276,
383
+ "rewards/rejected": -0.3082042336463928,
384
+ "step": 120
385
+ },
386
+ {
387
+ "epoch": 0.249500998003992,
388
+ "grad_norm": 14.89222449165367,
389
+ "learning_rate": 9.347474647526095e-07,
390
+ "logits/chosen": 1.0270758867263794,
391
+ "logits/rejected": 1.061629056930542,
392
+ "logps/chosen": -0.9520384073257446,
393
+ "logps/rejected": -0.9609392285346985,
394
+ "loss": 0.5982,
395
+ "rewards/accuracies": 0.75,
396
+ "rewards/chosen": -0.03607760742306709,
397
+ "rewards/margins": 0.205668643116951,
398
+ "rewards/rejected": -0.24174626171588898,
399
+ "step": 125
400
+ },
401
+ {
402
+ "epoch": 0.25948103792415167,
403
+ "grad_norm": 16.598481366896863,
404
+ "learning_rate": 9.258634670715237e-07,
405
+ "logits/chosen": 0.9625661969184875,
406
+ "logits/rejected": 0.9923114776611328,
407
+ "logps/chosen": -0.9781230092048645,
408
+ "logps/rejected": -1.0380465984344482,
409
+ "loss": 0.6033,
410
+ "rewards/accuracies": 0.8374999761581421,
411
+ "rewards/chosen": -0.08731977641582489,
412
+ "rewards/margins": 0.32325008511543274,
413
+ "rewards/rejected": -0.41056984663009644,
414
+ "step": 130
415
+ },
416
+ {
417
+ "epoch": 0.2694610778443114,
418
+ "grad_norm": 17.332548482467526,
419
+ "learning_rate": 9.164606203550497e-07,
420
+ "logits/chosen": 1.0289146900177002,
421
+ "logits/rejected": 1.0656378269195557,
422
+ "logps/chosen": -0.898147463798523,
423
+ "logps/rejected": -0.949881911277771,
424
+ "loss": 0.602,
425
+ "rewards/accuracies": 0.7749999761581421,
426
+ "rewards/chosen": -0.01896672695875168,
427
+ "rewards/margins": 0.33230799436569214,
428
+ "rewards/rejected": -0.351274698972702,
429
+ "step": 135
430
+ },
431
+ {
432
+ "epoch": 0.27944111776447106,
433
+ "grad_norm": 16.198930205544908,
434
+ "learning_rate": 9.065503805235137e-07,
435
+ "logits/chosen": 1.0169068574905396,
436
+ "logits/rejected": 1.0443648099899292,
437
+ "logps/chosen": -0.9837234616279602,
438
+ "logps/rejected": -1.015891432762146,
439
+ "loss": 0.5962,
440
+ "rewards/accuracies": 0.7749999761581421,
441
+ "rewards/chosen": -0.11362324655056,
442
+ "rewards/margins": 0.29118040204048157,
443
+ "rewards/rejected": -0.40480366349220276,
444
+ "step": 140
445
+ },
446
+ {
447
+ "epoch": 0.2894211576846307,
448
+ "grad_norm": 14.26896893631501,
449
+ "learning_rate": 8.961448216775953e-07,
450
+ "logits/chosen": 0.9983326196670532,
451
+ "logits/rejected": 0.984410285949707,
452
+ "logps/chosen": -1.0478496551513672,
453
+ "logps/rejected": -1.0458667278289795,
454
+ "loss": 0.6106,
455
+ "rewards/accuracies": 0.6625000238418579,
456
+ "rewards/chosen": -0.384859174489975,
457
+ "rewards/margins": 0.23550406098365784,
458
+ "rewards/rejected": -0.6203632354736328,
459
+ "step": 145
460
+ },
461
+ {
462
+ "epoch": 0.2994011976047904,
463
+ "grad_norm": 17.114721290662626,
464
+ "learning_rate": 8.852566213878946e-07,
465
+ "logits/chosen": 0.9434808492660522,
466
+ "logits/rejected": 0.9709761738777161,
467
+ "logps/chosen": -0.946380615234375,
468
+ "logps/rejected": -1.011891484260559,
469
+ "loss": 0.6051,
470
+ "rewards/accuracies": 0.8125,
471
+ "rewards/chosen": -0.10636933147907257,
472
+ "rewards/margins": 0.38454684615135193,
473
+ "rewards/rejected": -0.4909161627292633,
474
+ "step": 150
475
+ },
476
+ {
477
+ "epoch": 0.3093812375249501,
478
+ "grad_norm": 12.532368784046184,
479
+ "learning_rate": 8.73899045249266e-07,
480
+ "logits/chosen": 0.9879257082939148,
481
+ "logits/rejected": 1.0284427404403687,
482
+ "logps/chosen": -0.9887377619743347,
483
+ "logps/rejected": -1.0425301790237427,
484
+ "loss": 0.5785,
485
+ "rewards/accuracies": 0.7124999761581421,
486
+ "rewards/chosen": -0.18314163386821747,
487
+ "rewards/margins": 0.3873257339000702,
488
+ "rewards/rejected": -0.5704673528671265,
489
+ "step": 155
490
+ },
491
+ {
492
+ "epoch": 0.3193612774451098,
493
+ "grad_norm": 20.653306879612042,
494
+ "learning_rate": 8.620859307187338e-07,
495
+ "logits/chosen": 0.9365812540054321,
496
+ "logits/rejected": 0.9702633619308472,
497
+ "logps/chosen": -0.9792872667312622,
498
+ "logps/rejected": -1.0119134187698364,
499
+ "loss": 0.5915,
500
+ "rewards/accuracies": 0.7124999761581421,
501
+ "rewards/chosen": -0.28814950585365295,
502
+ "rewards/margins": 0.3159632086753845,
503
+ "rewards/rejected": -0.6041126847267151,
504
+ "step": 160
505
+ },
506
+ {
507
+ "epoch": 0.32934131736526945,
508
+ "grad_norm": 46.72961396087624,
509
+ "learning_rate": 8.498316702566826e-07,
510
+ "logits/chosen": 1.0088741779327393,
511
+ "logits/rejected": 1.0628801584243774,
512
+ "logps/chosen": -1.0191477537155151,
513
+ "logps/rejected": -1.0589340925216675,
514
+ "loss": 0.5784,
515
+ "rewards/accuracies": 0.7749999761581421,
516
+ "rewards/chosen": -0.43470463156700134,
517
+ "rewards/margins": 0.3699150085449219,
518
+ "rewards/rejected": -0.8046196103096008,
519
+ "step": 165
520
+ },
521
+ {
522
+ "epoch": 0.3393213572854291,
523
+ "grad_norm": 17.875828780004216,
524
+ "learning_rate": 8.371511937918617e-07,
525
+ "logits/chosen": 0.8878538012504578,
526
+ "logits/rejected": 0.9223688840866089,
527
+ "logps/chosen": -0.9879400134086609,
528
+ "logps/rejected": -1.029184103012085,
529
+ "loss": 0.6033,
530
+ "rewards/accuracies": 0.7749999761581421,
531
+ "rewards/chosen": -0.3266729712486267,
532
+ "rewards/margins": 0.5894866585731506,
533
+ "rewards/rejected": -0.9161597490310669,
534
+ "step": 170
535
+ },
536
+ {
537
+ "epoch": 0.34930139720558884,
538
+ "grad_norm": 16.753564996079323,
539
+ "learning_rate": 8.240599505315654e-07,
540
+ "logits/chosen": 0.8993169665336609,
541
+ "logits/rejected": 0.931827187538147,
542
+ "logps/chosen": -1.0300993919372559,
543
+ "logps/rejected": -1.104100227355957,
544
+ "loss": 0.5719,
545
+ "rewards/accuracies": 0.762499988079071,
546
+ "rewards/chosen": -0.26795631647109985,
547
+ "rewards/margins": 0.4897838234901428,
548
+ "rewards/rejected": -0.7577401399612427,
549
+ "step": 175
550
+ },
551
+ {
552
+ "epoch": 0.3592814371257485,
553
+ "grad_norm": 37.583807172799176,
554
+ "learning_rate": 8.105738901391551e-07,
555
+ "logits/chosen": 0.9503185153007507,
556
+ "logits/rejected": 0.9612258076667786,
557
+ "logps/chosen": -0.9984599947929382,
558
+ "logps/rejected": -1.0410314798355103,
559
+ "loss": 0.5749,
560
+ "rewards/accuracies": 0.800000011920929,
561
+ "rewards/chosen": -0.3058738708496094,
562
+ "rewards/margins": 0.4171958565711975,
563
+ "rewards/rejected": -0.7230697274208069,
564
+ "step": 180
565
+ },
566
+ {
567
+ "epoch": 0.36926147704590817,
568
+ "grad_norm": 31.25023262450056,
569
+ "learning_rate": 7.967094433018508e-07,
570
+ "logits/chosen": 0.8538301587104797,
571
+ "logits/rejected": 0.8765438199043274,
572
+ "logps/chosen": -1.0639922618865967,
573
+ "logps/rejected": -1.1690170764923096,
574
+ "loss": 0.5628,
575
+ "rewards/accuracies": 0.75,
576
+ "rewards/chosen": -0.31266123056411743,
577
+ "rewards/margins": 0.6013716459274292,
578
+ "rewards/rejected": -0.9140329360961914,
579
+ "step": 185
580
+ },
581
+ {
582
+ "epoch": 0.37924151696606784,
583
+ "grad_norm": 21.697159728289254,
584
+ "learning_rate": 7.82483501712469e-07,
585
+ "logits/chosen": 0.8337196111679077,
586
+ "logits/rejected": 0.8647937774658203,
587
+ "logps/chosen": -1.0461093187332153,
588
+ "logps/rejected": -1.0427898168563843,
589
+ "loss": 0.5701,
590
+ "rewards/accuracies": 0.737500011920929,
591
+ "rewards/chosen": -0.48062148690223694,
592
+ "rewards/margins": 0.4651462435722351,
593
+ "rewards/rejected": -0.9457677602767944,
594
+ "step": 190
595
+ },
596
+ {
597
+ "epoch": 0.38922155688622756,
598
+ "grad_norm": 13.452601846054984,
599
+ "learning_rate": 7.679133974894982e-07,
600
+ "logits/chosen": 0.8574188351631165,
601
+ "logits/rejected": 0.8771845102310181,
602
+ "logps/chosen": -1.0106494426727295,
603
+ "logps/rejected": -1.1300721168518066,
604
+ "loss": 0.5649,
605
+ "rewards/accuracies": 0.7875000238418579,
606
+ "rewards/chosen": -0.5489331483840942,
607
+ "rewards/margins": 0.6363680958747864,
608
+ "rewards/rejected": -1.1853011846542358,
609
+ "step": 195
610
+ },
611
+ {
612
+ "epoch": 0.3992015968063872,
613
+ "grad_norm": 14.045999687736995,
614
+ "learning_rate": 7.530168820605818e-07,
615
+ "logits/chosen": 0.8429155349731445,
616
+ "logits/rejected": 0.8586641550064087,
617
+ "logps/chosen": -1.1243480443954468,
618
+ "logps/rejected": -1.126988172531128,
619
+ "loss": 0.5556,
620
+ "rewards/accuracies": 0.699999988079071,
621
+ "rewards/chosen": -0.611405074596405,
622
+ "rewards/margins": 0.5212133526802063,
623
+ "rewards/rejected": -1.1326184272766113,
624
+ "step": 200
625
+ },
626
+ {
627
+ "epoch": 0.4091816367265469,
628
+ "grad_norm": 11.17840118621038,
629
+ "learning_rate": 7.378121045351377e-07,
630
+ "logits/chosen": 0.8805230855941772,
631
+ "logits/rejected": 0.8616092801094055,
632
+ "logps/chosen": -1.025155782699585,
633
+ "logps/rejected": -1.1043505668640137,
634
+ "loss": 0.5274,
635
+ "rewards/accuracies": 0.75,
636
+ "rewards/chosen": -0.5864971280097961,
637
+ "rewards/margins": 0.6259642839431763,
638
+ "rewards/rejected": -1.2124613523483276,
639
+ "step": 205
640
+ },
641
+ {
642
+ "epoch": 0.41916167664670656,
643
+ "grad_norm": 17.02714464481709,
644
+ "learning_rate": 7.223175895924637e-07,
645
+ "logits/chosen": 0.8006958961486816,
646
+ "logits/rejected": 0.8346986770629883,
647
+ "logps/chosen": -1.0029652118682861,
648
+ "logps/rejected": -1.0653495788574219,
649
+ "loss": 0.5437,
650
+ "rewards/accuracies": 0.800000011920929,
651
+ "rewards/chosen": -0.5938572287559509,
652
+ "rewards/margins": 0.5961542725563049,
653
+ "rewards/rejected": -1.1900113821029663,
654
+ "step": 210
655
+ },
656
+ {
657
+ "epoch": 0.4291417165668663,
658
+ "grad_norm": 12.708513730083673,
659
+ "learning_rate": 7.065522149122709e-07,
660
+ "logits/chosen": 0.7250524759292603,
661
+ "logits/rejected": 0.7448651790618896,
662
+ "logps/chosen": -1.0977203845977783,
663
+ "logps/rejected": -1.1671373844146729,
664
+ "loss": 0.5296,
665
+ "rewards/accuracies": 0.8374999761581421,
666
+ "rewards/chosen": -0.8822553753852844,
667
+ "rewards/margins": 0.5623547434806824,
668
+ "rewards/rejected": -1.4446099996566772,
669
+ "step": 215
670
+ },
671
+ {
672
+ "epoch": 0.43912175648702595,
673
+ "grad_norm": 23.02316300872982,
674
+ "learning_rate": 6.905351881751371e-07,
675
+ "logits/chosen": 0.7448990345001221,
676
+ "logits/rejected": 0.759792685508728,
677
+ "logps/chosen": -1.0590717792510986,
678
+ "logps/rejected": -1.1264311075210571,
679
+ "loss": 0.5411,
680
+ "rewards/accuracies": 0.7250000238418579,
681
+ "rewards/chosen": -0.7196047306060791,
682
+ "rewards/margins": 0.6396269798278809,
683
+ "rewards/rejected": -1.35923171043396,
684
+ "step": 220
685
+ },
686
+ {
687
+ "epoch": 0.4491017964071856,
688
+ "grad_norm": 15.317013674505024,
689
+ "learning_rate": 6.742860236609076e-07,
690
+ "logits/chosen": 0.7387903928756714,
691
+ "logits/rejected": 0.7482835054397583,
692
+ "logps/chosen": -1.0746328830718994,
693
+ "logps/rejected": -1.0935697555541992,
694
+ "loss": 0.5362,
695
+ "rewards/accuracies": 0.75,
696
+ "rewards/chosen": -0.91168612241745,
697
+ "rewards/margins": 0.43347805738449097,
698
+ "rewards/rejected": -1.3451642990112305,
699
+ "step": 225
700
+ },
701
+ {
702
+ "epoch": 0.4590818363273453,
703
+ "grad_norm": 20.979897267224555,
704
+ "learning_rate": 6.578245184735512e-07,
705
+ "logits/chosen": 0.7530170679092407,
706
+ "logits/rejected": 0.7971817851066589,
707
+ "logps/chosen": -1.0877180099487305,
708
+ "logps/rejected": -1.1133688688278198,
709
+ "loss": 0.5297,
710
+ "rewards/accuracies": 0.762499988079071,
711
+ "rewards/chosen": -0.7731893062591553,
712
+ "rewards/margins": 0.6359795331954956,
713
+ "rewards/rejected": -1.4091689586639404,
714
+ "step": 230
715
+ },
716
+ {
717
+ "epoch": 0.469061876247505,
718
+ "grad_norm": 23.654443057551042,
719
+ "learning_rate": 6.411707284214383e-07,
720
+ "logits/chosen": 0.7936985492706299,
721
+ "logits/rejected": 0.8071283102035522,
722
+ "logps/chosen": -1.1007978916168213,
723
+ "logps/rejected": -1.175083041191101,
724
+ "loss": 0.5189,
725
+ "rewards/accuracies": 0.75,
726
+ "rewards/chosen": -0.8833421468734741,
727
+ "rewards/margins": 0.6522087454795837,
728
+ "rewards/rejected": -1.535550832748413,
729
+ "step": 235
730
+ },
731
+ {
732
+ "epoch": 0.47904191616766467,
733
+ "grad_norm": 17.617163550183303,
734
+ "learning_rate": 6.243449435824276e-07,
735
+ "logits/chosen": 0.7208539247512817,
736
+ "logits/rejected": 0.7419721484184265,
737
+ "logps/chosen": -0.9637038111686707,
738
+ "logps/rejected": -1.0924652814865112,
739
+ "loss": 0.5239,
740
+ "rewards/accuracies": 0.75,
741
+ "rewards/chosen": -0.823961079120636,
742
+ "rewards/margins": 0.9264790415763855,
743
+ "rewards/rejected": -1.750440239906311,
744
+ "step": 240
745
+ },
746
+ {
747
+ "epoch": 0.48902195608782434,
748
+ "grad_norm": 23.429183199427385,
749
+ "learning_rate": 6.073676635835316e-07,
750
+ "logits/chosen": 0.7787541747093201,
751
+ "logits/rejected": 0.8052628636360168,
752
+ "logps/chosen": -1.0102448463439941,
753
+ "logps/rejected": -1.2205474376678467,
754
+ "loss": 0.5087,
755
+ "rewards/accuracies": 0.8125,
756
+ "rewards/chosen": -0.7600202560424805,
757
+ "rewards/margins": 1.2399606704711914,
758
+ "rewards/rejected": -1.9999806880950928,
759
+ "step": 245
760
+ },
761
+ {
762
+ "epoch": 0.499001996007984,
763
+ "grad_norm": 15.897882119964894,
764
+ "learning_rate": 5.9025957262528e-07,
765
+ "logits/chosen": 0.674079179763794,
766
+ "logits/rejected": 0.6560205221176147,
767
+ "logps/chosen": -1.0422561168670654,
768
+ "logps/rejected": -1.15647292137146,
769
+ "loss": 0.5129,
770
+ "rewards/accuracies": 0.8374999761581421,
771
+ "rewards/chosen": -0.9762313961982727,
772
+ "rewards/margins": 0.9589719772338867,
773
+ "rewards/rejected": -1.9352035522460938,
774
+ "step": 250
775
+ },
776
+ {
777
+ "epoch": 0.5089820359281437,
778
+ "grad_norm": 23.926407573258526,
779
+ "learning_rate": 5.730415142812058e-07,
780
+ "logits/chosen": 0.6435045003890991,
781
+ "logits/rejected": 0.6540420055389404,
782
+ "logps/chosen": -1.1076724529266357,
783
+ "logps/rejected": -1.2272051572799683,
784
+ "loss": 0.5207,
785
+ "rewards/accuracies": 0.824999988079071,
786
+ "rewards/chosen": -1.1593824625015259,
787
+ "rewards/margins": 0.9408347010612488,
788
+ "rewards/rejected": -2.10021710395813,
789
+ "step": 255
790
+ },
791
+ {
792
+ "epoch": 0.5189620758483033,
793
+ "grad_norm": 25.873872774153636,
794
+ "learning_rate": 5.557344661031627e-07,
795
+ "logits/chosen": 0.6078227758407593,
796
+ "logits/rejected": 0.6234728097915649,
797
+ "logps/chosen": -1.1247365474700928,
798
+ "logps/rejected": -1.1961596012115479,
799
+ "loss": 0.5558,
800
+ "rewards/accuracies": 0.7124999761581421,
801
+ "rewards/chosen": -1.4092304706573486,
802
+ "rewards/margins": 0.7921189665794373,
803
+ "rewards/rejected": -2.2013492584228516,
804
+ "step": 260
805
+ },
806
+ {
807
+ "epoch": 0.5289421157684631,
808
+ "grad_norm": 14.32961070454234,
809
+ "learning_rate": 5.383595140634093e-07,
810
+ "logits/chosen": 0.634459912776947,
811
+ "logits/rejected": 0.6405037641525269,
812
+ "logps/chosen": -1.054018259048462,
813
+ "logps/rejected": -1.1594079732894897,
814
+ "loss": 0.5108,
815
+ "rewards/accuracies": 0.699999988079071,
816
+ "rewards/chosen": -1.3187201023101807,
817
+ "rewards/margins": 0.7670294046401978,
818
+ "rewards/rejected": -2.085749626159668,
819
+ "step": 265
820
+ },
821
+ {
822
+ "epoch": 0.5389221556886228,
823
+ "grad_norm": 12.765239103380393,
824
+ "learning_rate": 5.209378268645997e-07,
825
+ "logits/chosen": 0.6027650237083435,
826
+ "logits/rejected": 0.6287568211555481,
827
+ "logps/chosen": -1.008739948272705,
828
+ "logps/rejected": -1.1450139284133911,
829
+ "loss": 0.5318,
830
+ "rewards/accuracies": 0.75,
831
+ "rewards/chosen": -1.2432196140289307,
832
+ "rewards/margins": 0.6896325349807739,
833
+ "rewards/rejected": -1.932852029800415,
834
+ "step": 270
835
+ },
836
+ {
837
+ "epoch": 0.5489021956087824,
838
+ "grad_norm": 17.632252940280708,
839
+ "learning_rate": 5.034906301489807e-07,
840
+ "logits/chosen": 0.6728609204292297,
841
+ "logits/rejected": 0.6657983064651489,
842
+ "logps/chosen": -1.1084893941879272,
843
+ "logps/rejected": -1.182081937789917,
844
+ "loss": 0.5413,
845
+ "rewards/accuracies": 0.762499988079071,
846
+ "rewards/chosen": -1.4515244960784912,
847
+ "rewards/margins": 0.8624111413955688,
848
+ "rewards/rejected": -2.3139355182647705,
849
+ "step": 275
850
+ },
851
+ {
852
+ "epoch": 0.5588822355289421,
853
+ "grad_norm": 22.324779245169193,
854
+ "learning_rate": 4.860391806382156e-07,
855
+ "logits/chosen": 0.6076717972755432,
856
+ "logits/rejected": 0.6105688810348511,
857
+ "logps/chosen": -1.0900273323059082,
858
+ "logps/rejected": -1.1191543340682983,
859
+ "loss": 0.512,
860
+ "rewards/accuracies": 0.862500011920929,
861
+ "rewards/chosen": -1.21976900100708,
862
+ "rewards/margins": 0.7310382723808289,
863
+ "rewards/rejected": -1.9508073329925537,
864
+ "step": 280
865
+ },
866
+ {
867
+ "epoch": 0.5688622754491018,
868
+ "grad_norm": 18.31410229389494,
869
+ "learning_rate": 4.686047402353433e-07,
870
+ "logits/chosen": 0.6535500288009644,
871
+ "logits/rejected": 0.6188856959342957,
872
+ "logps/chosen": -1.0886776447296143,
873
+ "logps/rejected": -1.1758826971054077,
874
+ "loss": 0.4871,
875
+ "rewards/accuracies": 0.8125,
876
+ "rewards/chosen": -1.381490707397461,
877
+ "rewards/margins": 0.8018454313278198,
878
+ "rewards/rejected": -2.1833362579345703,
879
+ "step": 285
880
+ },
881
+ {
882
+ "epoch": 0.5788423153692615,
883
+ "grad_norm": 28.66415855277427,
884
+ "learning_rate": 4.512085501204253e-07,
885
+ "logits/chosen": 0.7206050157546997,
886
+ "logits/rejected": 0.7634114623069763,
887
+ "logps/chosen": -1.116304636001587,
888
+ "logps/rejected": -1.1659752130508423,
889
+ "loss": 0.553,
890
+ "rewards/accuracies": 0.7250000238418579,
891
+ "rewards/chosen": -1.4132583141326904,
892
+ "rewards/margins": 0.657631516456604,
893
+ "rewards/rejected": -2.070889711380005,
894
+ "step": 290
895
+ },
896
+ {
897
+ "epoch": 0.5888223552894212,
898
+ "grad_norm": 17.845472804681062,
899
+ "learning_rate": 4.338718048714387e-07,
900
+ "logits/chosen": 0.6159842610359192,
901
+ "logits/rejected": 0.6279784440994263,
902
+ "logps/chosen": -1.0876820087432861,
903
+ "logps/rejected": -1.1220331192016602,
904
+ "loss": 0.5134,
905
+ "rewards/accuracies": 0.8374999761581421,
906
+ "rewards/chosen": -1.233598232269287,
907
+ "rewards/margins": 0.5510263442993164,
908
+ "rewards/rejected": -1.784624695777893,
909
+ "step": 295
910
+ },
911
+ {
912
+ "epoch": 0.5988023952095808,
913
+ "grad_norm": 22.693877555997958,
914
+ "learning_rate": 4.166156266419489e-07,
915
+ "logits/chosen": 0.6069675087928772,
916
+ "logits/rejected": 0.6444044709205627,
917
+ "logps/chosen": -1.0315536260604858,
918
+ "logps/rejected": -1.1916632652282715,
919
+ "loss": 0.5015,
920
+ "rewards/accuracies": 0.7749999761581421,
921
+ "rewards/chosen": -1.4063842296600342,
922
+ "rewards/margins": 0.8028200268745422,
923
+ "rewards/rejected": -2.2092041969299316,
924
+ "step": 300
925
+ },
926
+ {
927
+ "epoch": 0.6087824351297405,
928
+ "grad_norm": 29.176362707547757,
929
+ "learning_rate": 3.9946103942701775e-07,
930
+ "logits/chosen": 0.6731375455856323,
931
+ "logits/rejected": 0.6558948755264282,
932
+ "logps/chosen": -1.0202916860580444,
933
+ "logps/rejected": -1.1923191547393799,
934
+ "loss": 0.4922,
935
+ "rewards/accuracies": 0.7875000238418579,
936
+ "rewards/chosen": -1.134216547012329,
937
+ "rewards/margins": 0.8526105880737305,
938
+ "rewards/rejected": -1.9868271350860596,
939
+ "step": 305
940
+ },
941
+ {
942
+ "epoch": 0.6187624750499002,
943
+ "grad_norm": 16.68482157863775,
944
+ "learning_rate": 3.8242894344870495e-07,
945
+ "logits/chosen": 0.6814749836921692,
946
+ "logits/rejected": 0.6544811129570007,
947
+ "logps/chosen": -1.1450976133346558,
948
+ "logps/rejected": -1.2438080310821533,
949
+ "loss": 0.518,
950
+ "rewards/accuracies": 0.875,
951
+ "rewards/chosen": -1.6444076299667358,
952
+ "rewards/margins": 0.7449675798416138,
953
+ "rewards/rejected": -2.3893752098083496,
954
+ "step": 310
955
+ },
956
+ {
957
+ "epoch": 0.6287425149700598,
958
+ "grad_norm": 24.235832517472502,
959
+ "learning_rate": 3.6554008969236715e-07,
960
+ "logits/chosen": 0.6473463773727417,
961
+ "logits/rejected": 0.6526838541030884,
962
+ "logps/chosen": -1.1155353784561157,
963
+ "logps/rejected": -1.2412601709365845,
964
+ "loss": 0.5036,
965
+ "rewards/accuracies": 0.7749999761581421,
966
+ "rewards/chosen": -1.5284216403961182,
967
+ "rewards/margins": 0.7738613486289978,
968
+ "rewards/rejected": -2.3022828102111816,
969
+ "step": 315
970
+ },
971
+ {
972
+ "epoch": 0.6387225548902196,
973
+ "grad_norm": 14.637858980431309,
974
+ "learning_rate": 3.488150546247778e-07,
975
+ "logits/chosen": 0.641592264175415,
976
+ "logits/rejected": 0.6488014459609985,
977
+ "logps/chosen": -1.0486619472503662,
978
+ "logps/rejected": -1.117785930633545,
979
+ "loss": 0.5076,
980
+ "rewards/accuracies": 0.800000011920929,
981
+ "rewards/chosen": -1.3681632280349731,
982
+ "rewards/margins": 0.7144045829772949,
983
+ "rewards/rejected": -2.0825679302215576,
984
+ "step": 320
985
+ },
986
+ {
987
+ "epoch": 0.6487025948103793,
988
+ "grad_norm": 14.611695255214977,
989
+ "learning_rate": 3.3227421512487255e-07,
990
+ "logits/chosen": 0.6020836234092712,
991
+ "logits/rejected": 0.5903235673904419,
992
+ "logps/chosen": -1.0694186687469482,
993
+ "logps/rejected": -1.1450960636138916,
994
+ "loss": 0.4988,
995
+ "rewards/accuracies": 0.75,
996
+ "rewards/chosen": -1.495102047920227,
997
+ "rewards/margins": 0.6063732504844666,
998
+ "rewards/rejected": -2.101475238800049,
999
+ "step": 325
1000
+ },
1001
+ {
1002
+ "epoch": 0.6586826347305389,
1003
+ "grad_norm": 53.83501877641933,
1004
+ "learning_rate": 3.15937723657661e-07,
1005
+ "logits/chosen": 0.5937372446060181,
1006
+ "logits/rejected": 0.5983537435531616,
1007
+ "logps/chosen": -1.0911985635757446,
1008
+ "logps/rejected": -1.1970782279968262,
1009
+ "loss": 0.5292,
1010
+ "rewards/accuracies": 0.7875000238418579,
1011
+ "rewards/chosen": -1.5829055309295654,
1012
+ "rewards/margins": 0.6139482259750366,
1013
+ "rewards/rejected": -2.1968536376953125,
1014
+ "step": 330
1015
+ },
1016
+ {
1017
+ "epoch": 0.6686626746506986,
1018
+ "grad_norm": 22.263382020354737,
1019
+ "learning_rate": 2.9982548372155256e-07,
1020
+ "logits/chosen": 0.5615344047546387,
1021
+ "logits/rejected": 0.5818489789962769,
1022
+ "logps/chosen": -1.0336883068084717,
1023
+ "logps/rejected": -1.1681592464447021,
1024
+ "loss": 0.5036,
1025
+ "rewards/accuracies": 0.824999988079071,
1026
+ "rewards/chosen": -1.2369213104248047,
1027
+ "rewards/margins": 1.0152759552001953,
1028
+ "rewards/rejected": -2.252197265625,
1029
+ "step": 335
1030
+ },
1031
+ {
1032
+ "epoch": 0.6786427145708582,
1033
+ "grad_norm": 28.648845585620847,
1034
+ "learning_rate": 2.8395712559900874e-07,
1035
+ "logits/chosen": 0.5865073204040527,
1036
+ "logits/rejected": 0.5887445211410522,
1037
+ "logps/chosen": -1.2165284156799316,
1038
+ "logps/rejected": -1.285627007484436,
1039
+ "loss": 0.5287,
1040
+ "rewards/accuracies": 0.7250000238418579,
1041
+ "rewards/chosen": -1.876123070716858,
1042
+ "rewards/margins": 0.8445480465888977,
1043
+ "rewards/rejected": -2.7206711769104004,
1044
+ "step": 340
1045
+ },
1046
+ {
1047
+ "epoch": 0.688622754491018,
1048
+ "grad_norm": 27.7967265314739,
1049
+ "learning_rate": 2.683519824400692e-07,
1050
+ "logits/chosen": 0.6274746656417847,
1051
+ "logits/rejected": 0.6499799489974976,
1052
+ "logps/chosen": -1.1229360103607178,
1053
+ "logps/rejected": -1.2630244493484497,
1054
+ "loss": 0.5228,
1055
+ "rewards/accuracies": 0.7250000238418579,
1056
+ "rewards/chosen": -1.6735212802886963,
1057
+ "rewards/margins": 0.8694586753845215,
1058
+ "rewards/rejected": -2.5429797172546387,
1059
+ "step": 345
1060
+ },
1061
+ {
1062
+ "epoch": 0.6986027944111777,
1063
+ "grad_norm": 22.50466227883414,
1064
+ "learning_rate": 2.530290667078846e-07,
1065
+ "logits/chosen": 0.620844841003418,
1066
+ "logits/rejected": 0.6195460557937622,
1067
+ "logps/chosen": -1.1165497303009033,
1068
+ "logps/rejected": -1.1850183010101318,
1069
+ "loss": 0.5019,
1070
+ "rewards/accuracies": 0.824999988079071,
1071
+ "rewards/chosen": -1.5181663036346436,
1072
+ "rewards/margins": 0.7825000286102295,
1073
+ "rewards/rejected": -2.300666332244873,
1074
+ "step": 350
1075
+ },
1076
+ {
1077
+ "epoch": 0.7085828343313373,
1078
+ "grad_norm": 21.26239260918309,
1079
+ "learning_rate": 2.380070470149605e-07,
1080
+ "logits/chosen": 0.6597515940666199,
1081
+ "logits/rejected": 0.6680246591567993,
1082
+ "logps/chosen": -1.1044973134994507,
1083
+ "logps/rejected": -1.2354698181152344,
1084
+ "loss": 0.4914,
1085
+ "rewards/accuracies": 0.7749999761581421,
1086
+ "rewards/chosen": -1.4524997472763062,
1087
+ "rewards/margins": 1.0394423007965088,
1088
+ "rewards/rejected": -2.4919424057006836,
1089
+ "step": 355
1090
+ },
1091
+ {
1092
+ "epoch": 0.718562874251497,
1093
+ "grad_norm": 30.986440285036473,
1094
+ "learning_rate": 2.23304225378328e-07,
1095
+ "logits/chosen": 0.5663326978683472,
1096
+ "logits/rejected": 0.5595775842666626,
1097
+ "logps/chosen": -1.2192121744155884,
1098
+ "logps/rejected": -1.2986266613006592,
1099
+ "loss": 0.4991,
1100
+ "rewards/accuracies": 0.7875000238418579,
1101
+ "rewards/chosen": -1.6858431100845337,
1102
+ "rewards/margins": 1.0494027137756348,
1103
+ "rewards/rejected": -2.735245704650879,
1104
+ "step": 360
1105
+ },
1106
+ {
1107
+ "epoch": 0.7285429141716567,
1108
+ "grad_norm": 31.154865644231116,
1109
+ "learning_rate": 2.0893851492135532e-07,
1110
+ "logits/chosen": 0.5782791376113892,
1111
+ "logits/rejected": 0.5733534097671509,
1112
+ "logps/chosen": -1.108449935913086,
1113
+ "logps/rejected": -1.2320600748062134,
1114
+ "loss": 0.4969,
1115
+ "rewards/accuracies": 0.7749999761581421,
1116
+ "rewards/chosen": -1.4567809104919434,
1117
+ "rewards/margins": 1.0569483041763306,
1118
+ "rewards/rejected": -2.5137288570404053,
1119
+ "step": 365
1120
+ },
1121
+ {
1122
+ "epoch": 0.7385229540918163,
1123
+ "grad_norm": 25.665361579684205,
1124
+ "learning_rate": 1.9492741804936618e-07,
1125
+ "logits/chosen": 0.5590307116508484,
1126
+ "logits/rejected": 0.5289372205734253,
1127
+ "logps/chosen": -1.135460615158081,
1128
+ "logps/rejected": -1.1982572078704834,
1129
+ "loss": 0.5123,
1130
+ "rewards/accuracies": 0.7749999761581421,
1131
+ "rewards/chosen": -1.5751354694366455,
1132
+ "rewards/margins": 0.7708719968795776,
1133
+ "rewards/rejected": -2.346007823944092,
1134
+ "step": 370
1135
+ },
1136
+ {
1137
+ "epoch": 0.7485029940119761,
1138
+ "grad_norm": 13.466456049238714,
1139
+ "learning_rate": 1.812880051256551e-07,
1140
+ "logits/chosen": 0.5437551736831665,
1141
+ "logits/rejected": 0.540005087852478,
1142
+ "logps/chosen": -1.1057159900665283,
1143
+ "logps/rejected": -1.1711170673370361,
1144
+ "loss": 0.4956,
1145
+ "rewards/accuracies": 0.6875,
1146
+ "rewards/chosen": -1.607832670211792,
1147
+ "rewards/margins": 0.5974467396736145,
1148
+ "rewards/rejected": -2.205279588699341,
1149
+ "step": 375
1150
+ },
1151
+ {
1152
+ "epoch": 0.7584830339321357,
1153
+ "grad_norm": 22.830693166932168,
1154
+ "learning_rate": 1.6803689367387918e-07,
1155
+ "logits/chosen": 0.5521084666252136,
1156
+ "logits/rejected": 0.563881516456604,
1157
+ "logps/chosen": -1.0188974142074585,
1158
+ "logps/rejected": -1.0934759378433228,
1159
+ "loss": 0.5364,
1160
+ "rewards/accuracies": 0.6625000238418579,
1161
+ "rewards/chosen": -1.6915432214736938,
1162
+ "rewards/margins": 0.41655927896499634,
1163
+ "rewards/rejected": -2.108102560043335,
1164
+ "step": 380
1165
+ },
1166
+ {
1167
+ "epoch": 0.7684630738522954,
1168
+ "grad_norm": 16.717527209109356,
1169
+ "learning_rate": 1.551902281321651e-07,
1170
+ "logits/chosen": 0.6741904020309448,
1171
+ "logits/rejected": 0.6558393836021423,
1172
+ "logps/chosen": -1.153136134147644,
1173
+ "logps/rejected": -1.2626793384552002,
1174
+ "loss": 0.4885,
1175
+ "rewards/accuracies": 0.8374999761581421,
1176
+ "rewards/chosen": -1.4042468070983887,
1177
+ "rewards/margins": 1.1682214736938477,
1178
+ "rewards/rejected": -2.5724682807922363,
1179
+ "step": 385
1180
+ },
1181
+ {
1182
+ "epoch": 0.7784431137724551,
1183
+ "grad_norm": 21.35977175588003,
1184
+ "learning_rate": 1.4276366018359842e-07,
1185
+ "logits/chosen": 0.5667208433151245,
1186
+ "logits/rejected": 0.5196897387504578,
1187
+ "logps/chosen": -1.1266697645187378,
1188
+ "logps/rejected": -1.2171615362167358,
1189
+ "loss": 0.5164,
1190
+ "rewards/accuracies": 0.7875000238418579,
1191
+ "rewards/chosen": -1.5344607830047607,
1192
+ "rewards/margins": 0.9302822947502136,
1193
+ "rewards/rejected": -2.464743137359619,
1194
+ "step": 390
1195
+ },
1196
+ {
1197
+ "epoch": 0.7884231536926147,
1198
+ "grad_norm": 21.011004494402407,
1199
+ "learning_rate": 1.3077232968705805e-07,
1200
+ "logits/chosen": 0.581541121006012,
1201
+ "logits/rejected": 0.5735315084457397,
1202
+ "logps/chosen": -1.1142101287841797,
1203
+ "logps/rejected": -1.204474687576294,
1204
+ "loss": 0.4938,
1205
+ "rewards/accuracies": 0.8125,
1206
+ "rewards/chosen": -1.4655622243881226,
1207
+ "rewards/margins": 0.7967506647109985,
1208
+ "rewards/rejected": -2.262312650680542,
1209
+ "step": 395
1210
+ },
1211
+ {
1212
+ "epoch": 0.7984031936127745,
1213
+ "grad_norm": 21.73473549415687,
1214
+ "learning_rate": 1.192308462316317e-07,
1215
+ "logits/chosen": 0.49174603819847107,
1216
+ "logits/rejected": 0.5455900430679321,
1217
+ "logps/chosen": -1.1133276224136353,
1218
+ "logps/rejected": -1.2326544523239136,
1219
+ "loss": 0.5169,
1220
+ "rewards/accuracies": 0.862500011920929,
1221
+ "rewards/chosen": -1.5614674091339111,
1222
+ "rewards/margins": 0.7484425902366638,
1223
+ "rewards/rejected": -2.309910297393799,
1224
+ "step": 400
1225
+ }
1226
+ ],
1227
+ "logging_steps": 5,
1228
+ "max_steps": 501,
1229
+ "num_input_tokens_seen": 0,
1230
+ "num_train_epochs": 1,
1231
+ "save_steps": 101,
1232
+ "stateful_callbacks": {
1233
+ "TrainerControl": {
1234
+ "args": {
1235
+ "should_epoch_stop": false,
1236
+ "should_evaluate": false,
1237
+ "should_log": false,
1238
+ "should_save": true,
1239
+ "should_training_stop": false
1240
+ },
1241
+ "attributes": {}
1242
+ }
1243
+ },
1244
+ "total_flos": 0.0,
1245
+ "train_batch_size": 4,
1246
+ "trial_name": null,
1247
+ "trial_params": null
1248
+ }
checkpoint-404/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed4b600e94a28f3fe41cf5d5ef5d0ac61fe15cfd65a7a4a0057ca329ad8e12cc
3
+ size 7544
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/GLOBALFS/gznwp_3/qxj/lgzhong/LLaMA-Factory/saves/llama31/Llama-3.2-1B-Instruct-SFT-v1.5-lr5e-6-packing",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.43.4",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.43.4"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7adf17cf93658f72201f6a8689612b5210f335e780eb1fa0ac23ea2c4cf0d43f
3
+ size 2471645608
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 2048,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.559710203114146,
5
+ "train_runtime": 2572.2381,
6
+ "train_samples": 64128,
7
+ "train_samples_per_second": 24.931,
8
+ "train_steps_per_second": 0.195
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1557 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 501,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.001996007984031936,
13
+ "grad_norm": 16.492788975984936,
14
+ "learning_rate": 1.9607843137254902e-08,
15
+ "logits/chosen": 1.3011724948883057,
16
+ "logits/rejected": 1.3879833221435547,
17
+ "logps/chosen": -0.9583934545516968,
18
+ "logps/rejected": -0.908146858215332,
19
+ "loss": 0.6931,
20
+ "rewards/accuracies": 0.0,
21
+ "rewards/chosen": 0.0,
22
+ "rewards/margins": 0.0,
23
+ "rewards/rejected": 0.0,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.00998003992015968,
28
+ "grad_norm": 18.616408754077472,
29
+ "learning_rate": 9.80392156862745e-08,
30
+ "logits/chosen": 1.230096697807312,
31
+ "logits/rejected": 1.2526068687438965,
32
+ "logps/chosen": -0.8566818833351135,
33
+ "logps/rejected": -0.9451415538787842,
34
+ "loss": 0.6931,
35
+ "rewards/accuracies": 0.34375,
36
+ "rewards/chosen": -0.00325668603181839,
37
+ "rewards/margins": -0.0027664820663630962,
38
+ "rewards/rejected": -0.0004902039654552937,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01996007984031936,
43
+ "grad_norm": 19.72943287901331,
44
+ "learning_rate": 1.96078431372549e-07,
45
+ "logits/chosen": 1.1732714176177979,
46
+ "logits/rejected": 1.2325665950775146,
47
+ "logps/chosen": -0.8571804165840149,
48
+ "logps/rejected": -0.9293950200080872,
49
+ "loss": 0.6935,
50
+ "rewards/accuracies": 0.5249999761581421,
51
+ "rewards/chosen": -0.0004458148032426834,
52
+ "rewards/margins": 0.00015245657414197922,
53
+ "rewards/rejected": -0.0005982713773846626,
54
+ "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.029940119760479042,
58
+ "grad_norm": 15.989882260008397,
59
+ "learning_rate": 2.941176470588235e-07,
60
+ "logits/chosen": 1.1804090738296509,
61
+ "logits/rejected": 1.227670669555664,
62
+ "logps/chosen": -0.8887054324150085,
63
+ "logps/rejected": -0.9415630102157593,
64
+ "loss": 0.6942,
65
+ "rewards/accuracies": 0.4124999940395355,
66
+ "rewards/chosen": -0.005856434814631939,
67
+ "rewards/margins": -0.004528886638581753,
68
+ "rewards/rejected": -0.0013275481760501862,
69
+ "step": 15
70
+ },
71
+ {
72
+ "epoch": 0.03992015968063872,
73
+ "grad_norm": 21.617808491664096,
74
+ "learning_rate": 3.92156862745098e-07,
75
+ "logits/chosen": 1.2326724529266357,
76
+ "logits/rejected": 1.239334225654602,
77
+ "logps/chosen": -1.025779366493225,
78
+ "logps/rejected": -0.9815893173217773,
79
+ "loss": 0.6924,
80
+ "rewards/accuracies": 0.5249999761581421,
81
+ "rewards/chosen": -0.011453075334429741,
82
+ "rewards/margins": -0.006528028752654791,
83
+ "rewards/rejected": -0.004925046116113663,
84
+ "step": 20
85
+ },
86
+ {
87
+ "epoch": 0.0499001996007984,
88
+ "grad_norm": 14.85293949325317,
89
+ "learning_rate": 4.901960784313725e-07,
90
+ "logits/chosen": 1.1621646881103516,
91
+ "logits/rejected": 1.2202112674713135,
92
+ "logps/chosen": -0.9435383081436157,
93
+ "logps/rejected": -1.0095245838165283,
94
+ "loss": 0.6926,
95
+ "rewards/accuracies": 0.4749999940395355,
96
+ "rewards/chosen": -0.008930020034313202,
97
+ "rewards/margins": 0.011791445314884186,
98
+ "rewards/rejected": -0.020721465349197388,
99
+ "step": 25
100
+ },
101
+ {
102
+ "epoch": 0.059880239520958084,
103
+ "grad_norm": 18.28049213488445,
104
+ "learning_rate": 5.88235294117647e-07,
105
+ "logits/chosen": 1.2528660297393799,
106
+ "logits/rejected": 1.3036034107208252,
107
+ "logps/chosen": -0.9394888877868652,
108
+ "logps/rejected": -0.9887625575065613,
109
+ "loss": 0.6928,
110
+ "rewards/accuracies": 0.5,
111
+ "rewards/chosen": -0.020373398438096046,
112
+ "rewards/margins": -0.0037106983363628387,
113
+ "rewards/rejected": -0.016662701964378357,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.06986027944111776,
118
+ "grad_norm": 15.999817261895291,
119
+ "learning_rate": 6.862745098039216e-07,
120
+ "logits/chosen": 1.1911170482635498,
121
+ "logits/rejected": 1.2343870401382446,
122
+ "logps/chosen": -0.9691197276115417,
123
+ "logps/rejected": -0.9998400807380676,
124
+ "loss": 0.6912,
125
+ "rewards/accuracies": 0.48750001192092896,
126
+ "rewards/chosen": -0.01592147909104824,
127
+ "rewards/margins": 0.0014309640973806381,
128
+ "rewards/rejected": -0.01735244318842888,
129
+ "step": 35
130
+ },
131
+ {
132
+ "epoch": 0.07984031936127745,
133
+ "grad_norm": 14.867532956796651,
134
+ "learning_rate": 7.84313725490196e-07,
135
+ "logits/chosen": 1.2250399589538574,
136
+ "logits/rejected": 1.2877371311187744,
137
+ "logps/chosen": -0.9882305860519409,
138
+ "logps/rejected": -1.013457179069519,
139
+ "loss": 0.6866,
140
+ "rewards/accuracies": 0.625,
141
+ "rewards/chosen": -0.014133378863334656,
142
+ "rewards/margins": 0.023214522749185562,
143
+ "rewards/rejected": -0.03734790161252022,
144
+ "step": 40
145
+ },
146
+ {
147
+ "epoch": 0.08982035928143713,
148
+ "grad_norm": 19.324457876267314,
149
+ "learning_rate": 8.823529411764705e-07,
150
+ "logits/chosen": 1.2738926410675049,
151
+ "logits/rejected": 1.2850474119186401,
152
+ "logps/chosen": -0.9675604701042175,
153
+ "logps/rejected": -1.0223758220672607,
154
+ "loss": 0.6804,
155
+ "rewards/accuracies": 0.6499999761581421,
156
+ "rewards/chosen": -0.010748568922281265,
157
+ "rewards/margins": 0.0401780791580677,
158
+ "rewards/rejected": -0.05092664435505867,
159
+ "step": 45
160
+ },
161
+ {
162
+ "epoch": 0.0998003992015968,
163
+ "grad_norm": 18.41965619240879,
164
+ "learning_rate": 9.80392156862745e-07,
165
+ "logits/chosen": 1.2459691762924194,
166
+ "logits/rejected": 1.3021132946014404,
167
+ "logps/chosen": -0.9164802432060242,
168
+ "logps/rejected": -1.013667345046997,
169
+ "loss": 0.6739,
170
+ "rewards/accuracies": 0.637499988079071,
171
+ "rewards/chosen": -0.026862669736146927,
172
+ "rewards/margins": 0.07785479724407196,
173
+ "rewards/rejected": -0.10471747070550919,
174
+ "step": 50
175
+ },
176
+ {
177
+ "epoch": 0.10978043912175649,
178
+ "grad_norm": 16.897558680765105,
179
+ "learning_rate": 9.99805057520177e-07,
180
+ "logits/chosen": 1.1725871562957764,
181
+ "logits/rejected": 1.173532247543335,
182
+ "logps/chosen": -0.9711742401123047,
183
+ "logps/rejected": -0.9595904350280762,
184
+ "loss": 0.6738,
185
+ "rewards/accuracies": 0.737500011920929,
186
+ "rewards/chosen": -0.03100317157804966,
187
+ "rewards/margins": 0.11643954366445541,
188
+ "rewards/rejected": -0.14744271337985992,
189
+ "step": 55
190
+ },
191
+ {
192
+ "epoch": 0.11976047904191617,
193
+ "grad_norm": 14.265898399249132,
194
+ "learning_rate": 9.990133642141357e-07,
195
+ "logits/chosen": 1.1897612810134888,
196
+ "logits/rejected": 1.2000809907913208,
197
+ "logps/chosen": -0.9207404255867004,
198
+ "logps/rejected": -0.9565631747245789,
199
+ "loss": 0.6693,
200
+ "rewards/accuracies": 0.6000000238418579,
201
+ "rewards/chosen": -0.06663166731595993,
202
+ "rewards/margins": 0.18790733814239502,
203
+ "rewards/rejected": -0.25453901290893555,
204
+ "step": 60
205
+ },
206
+ {
207
+ "epoch": 0.12974051896207583,
208
+ "grad_norm": 19.11690615448299,
209
+ "learning_rate": 9.976136999909155e-07,
210
+ "logits/chosen": 1.261150598526001,
211
+ "logits/rejected": 1.2706950902938843,
212
+ "logps/chosen": -0.9832024574279785,
213
+ "logps/rejected": -0.9762998819351196,
214
+ "loss": 0.6736,
215
+ "rewards/accuracies": 0.675000011920929,
216
+ "rewards/chosen": -0.08731752634048462,
217
+ "rewards/margins": 0.037145014852285385,
218
+ "rewards/rejected": -0.1244625449180603,
219
+ "step": 65
220
+ },
221
+ {
222
+ "epoch": 0.13972055888223553,
223
+ "grad_norm": 16.308947856088572,
224
+ "learning_rate": 9.956077701257707e-07,
225
+ "logits/chosen": 1.1949059963226318,
226
+ "logits/rejected": 1.2373930215835571,
227
+ "logps/chosen": -0.923254132270813,
228
+ "logps/rejected": -0.9537776708602905,
229
+ "loss": 0.6588,
230
+ "rewards/accuracies": 0.800000011920929,
231
+ "rewards/chosen": -0.0689881294965744,
232
+ "rewards/margins": 0.0771615132689476,
233
+ "rewards/rejected": -0.1461496502161026,
234
+ "step": 70
235
+ },
236
+ {
237
+ "epoch": 0.1497005988023952,
238
+ "grad_norm": 18.31597399561215,
239
+ "learning_rate": 9.929980185352525e-07,
240
+ "logits/chosen": 1.1303855180740356,
241
+ "logits/rejected": 1.166472315788269,
242
+ "logps/chosen": -1.0079195499420166,
243
+ "logps/rejected": -1.0075769424438477,
244
+ "loss": 0.6486,
245
+ "rewards/accuracies": 0.7124999761581421,
246
+ "rewards/chosen": -0.026683980599045753,
247
+ "rewards/margins": 0.0837903693318367,
248
+ "rewards/rejected": -0.1104743480682373,
249
+ "step": 75
250
+ },
251
+ {
252
+ "epoch": 0.1596806387225549,
253
+ "grad_norm": 16.142069213484454,
254
+ "learning_rate": 9.89787624799672e-07,
255
+ "logits/chosen": 1.1199300289154053,
256
+ "logits/rejected": 1.1778942346572876,
257
+ "logps/chosen": -0.9652664065361023,
258
+ "logps/rejected": -1.0307899713516235,
259
+ "loss": 0.6496,
260
+ "rewards/accuracies": 0.737500011920929,
261
+ "rewards/chosen": -0.0005544237792491913,
262
+ "rewards/margins": 0.10419625043869019,
263
+ "rewards/rejected": -0.10475067049264908,
264
+ "step": 80
265
+ },
266
+ {
267
+ "epoch": 0.16966067864271456,
268
+ "grad_norm": 15.306215682029483,
269
+ "learning_rate": 9.859805002892731e-07,
270
+ "logits/chosen": 1.1645634174346924,
271
+ "logits/rejected": 1.1519969701766968,
272
+ "logps/chosen": -0.9917243719100952,
273
+ "logps/rejected": -1.060416340827942,
274
+ "loss": 0.661,
275
+ "rewards/accuracies": 0.675000011920929,
276
+ "rewards/chosen": -0.09171438962221146,
277
+ "rewards/margins": 0.20642364025115967,
278
+ "rewards/rejected": -0.2981380820274353,
279
+ "step": 85
280
+ },
281
+ {
282
+ "epoch": 0.17964071856287425,
283
+ "grad_norm": 15.254186655042064,
284
+ "learning_rate": 9.81581283398829e-07,
285
+ "logits/chosen": 1.103563904762268,
286
+ "logits/rejected": 1.1300289630889893,
287
+ "logps/chosen": -0.969647228717804,
288
+ "logps/rejected": -0.9916777610778809,
289
+ "loss": 0.6337,
290
+ "rewards/accuracies": 0.7250000238418579,
291
+ "rewards/chosen": 0.013281228020787239,
292
+ "rewards/margins": 0.1793346405029297,
293
+ "rewards/rejected": -0.1660534292459488,
294
+ "step": 90
295
+ },
296
+ {
297
+ "epoch": 0.18962075848303392,
298
+ "grad_norm": 15.282160453652757,
299
+ "learning_rate": 9.765953338964734e-07,
300
+ "logits/chosen": 1.0921884775161743,
301
+ "logits/rejected": 1.1226933002471924,
302
+ "logps/chosen": -1.0730102062225342,
303
+ "logps/rejected": -1.1024601459503174,
304
+ "loss": 0.6385,
305
+ "rewards/accuracies": 0.7749999761581421,
306
+ "rewards/chosen": 0.0058188484981656075,
307
+ "rewards/margins": 0.21344614028930664,
308
+ "rewards/rejected": -0.2076272964477539,
309
+ "step": 95
310
+ },
311
+ {
312
+ "epoch": 0.1996007984031936,
313
+ "grad_norm": 21.61748232589367,
314
+ "learning_rate": 9.710287263936483e-07,
315
+ "logits/chosen": 1.0795061588287354,
316
+ "logits/rejected": 1.0822367668151855,
317
+ "logps/chosen": -1.0821864604949951,
318
+ "logps/rejected": -1.1186153888702393,
319
+ "loss": 0.621,
320
+ "rewards/accuracies": 0.6875,
321
+ "rewards/chosen": 0.07217474281787872,
322
+ "rewards/margins": 0.3310089707374573,
323
+ "rewards/rejected": -0.25883427262306213,
324
+ "step": 100
325
+ },
326
+ {
327
+ "epoch": 0.20958083832335328,
328
+ "grad_norm": 23.129340339628143,
329
+ "learning_rate": 9.648882429441256e-07,
330
+ "logits/chosen": 1.0758105516433716,
331
+ "logits/rejected": 1.0959206819534302,
332
+ "logps/chosen": -0.9559111595153809,
333
+ "logps/rejected": -0.9702944755554199,
334
+ "loss": 0.6278,
335
+ "rewards/accuracies": 0.7124999761581421,
336
+ "rewards/chosen": -0.027358528226614,
337
+ "rewards/margins": 0.17237558960914612,
338
+ "rewards/rejected": -0.1997341364622116,
339
+ "step": 105
340
+ },
341
+ {
342
+ "epoch": 0.21956087824351297,
343
+ "grad_norm": 15.179993551058994,
344
+ "learning_rate": 9.581813647811197e-07,
345
+ "logits/chosen": 1.094158411026001,
346
+ "logits/rejected": 1.114650011062622,
347
+ "logps/chosen": -0.9534612894058228,
348
+ "logps/rejected": -0.9674752354621887,
349
+ "loss": 0.6124,
350
+ "rewards/accuracies": 0.75,
351
+ "rewards/chosen": 0.058080364018678665,
352
+ "rewards/margins": 0.30136996507644653,
353
+ "rewards/rejected": -0.24328958988189697,
354
+ "step": 110
355
+ },
356
+ {
357
+ "epoch": 0.22954091816367264,
358
+ "grad_norm": 13.705886523650493,
359
+ "learning_rate": 9.509162632025569e-07,
360
+ "logits/chosen": 1.0607202053070068,
361
+ "logits/rejected": 1.045424461364746,
362
+ "logps/chosen": -1.1245949268341064,
363
+ "logps/rejected": -1.1509120464324951,
364
+ "loss": 0.6167,
365
+ "rewards/accuracies": 0.675000011920929,
366
+ "rewards/chosen": -0.07293939590454102,
367
+ "rewards/margins": 0.17659255862236023,
368
+ "rewards/rejected": -0.24953195452690125,
369
+ "step": 115
370
+ },
371
+ {
372
+ "epoch": 0.23952095808383234,
373
+ "grad_norm": 27.63745397695,
374
+ "learning_rate": 9.431017896156073e-07,
375
+ "logits/chosen": 1.0884307622909546,
376
+ "logits/rejected": 1.101423978805542,
377
+ "logps/chosen": -0.9731513857841492,
378
+ "logps/rejected": -1.023944616317749,
379
+ "loss": 0.6061,
380
+ "rewards/accuracies": 0.6625000238418579,
381
+ "rewards/chosen": 0.055571239441633224,
382
+ "rewards/margins": 0.36377543210983276,
383
+ "rewards/rejected": -0.3082042336463928,
384
+ "step": 120
385
+ },
386
+ {
387
+ "epoch": 0.249500998003992,
388
+ "grad_norm": 14.89222449165367,
389
+ "learning_rate": 9.347474647526095e-07,
390
+ "logits/chosen": 1.0270758867263794,
391
+ "logits/rejected": 1.061629056930542,
392
+ "logps/chosen": -0.9520384073257446,
393
+ "logps/rejected": -0.9609392285346985,
394
+ "loss": 0.5982,
395
+ "rewards/accuracies": 0.75,
396
+ "rewards/chosen": -0.03607760742306709,
397
+ "rewards/margins": 0.205668643116951,
398
+ "rewards/rejected": -0.24174626171588898,
399
+ "step": 125
400
+ },
401
+ {
402
+ "epoch": 0.25948103792415167,
403
+ "grad_norm": 16.598481366896863,
404
+ "learning_rate": 9.258634670715237e-07,
405
+ "logits/chosen": 0.9625661969184875,
406
+ "logits/rejected": 0.9923114776611328,
407
+ "logps/chosen": -0.9781230092048645,
408
+ "logps/rejected": -1.0380465984344482,
409
+ "loss": 0.6033,
410
+ "rewards/accuracies": 0.8374999761581421,
411
+ "rewards/chosen": -0.08731977641582489,
412
+ "rewards/margins": 0.32325008511543274,
413
+ "rewards/rejected": -0.41056984663009644,
414
+ "step": 130
415
+ },
416
+ {
417
+ "epoch": 0.2694610778443114,
418
+ "grad_norm": 17.332548482467526,
419
+ "learning_rate": 9.164606203550497e-07,
420
+ "logits/chosen": 1.0289146900177002,
421
+ "logits/rejected": 1.0656378269195557,
422
+ "logps/chosen": -0.898147463798523,
423
+ "logps/rejected": -0.949881911277771,
424
+ "loss": 0.602,
425
+ "rewards/accuracies": 0.7749999761581421,
426
+ "rewards/chosen": -0.01896672695875168,
427
+ "rewards/margins": 0.33230799436569214,
428
+ "rewards/rejected": -0.351274698972702,
429
+ "step": 135
430
+ },
431
+ {
432
+ "epoch": 0.27944111776447106,
433
+ "grad_norm": 16.198930205544908,
434
+ "learning_rate": 9.065503805235137e-07,
435
+ "logits/chosen": 1.0169068574905396,
436
+ "logits/rejected": 1.0443648099899292,
437
+ "logps/chosen": -0.9837234616279602,
438
+ "logps/rejected": -1.015891432762146,
439
+ "loss": 0.5962,
440
+ "rewards/accuracies": 0.7749999761581421,
441
+ "rewards/chosen": -0.11362324655056,
442
+ "rewards/margins": 0.29118040204048157,
443
+ "rewards/rejected": -0.40480366349220276,
444
+ "step": 140
445
+ },
446
+ {
447
+ "epoch": 0.2894211576846307,
448
+ "grad_norm": 14.26896893631501,
449
+ "learning_rate": 8.961448216775953e-07,
450
+ "logits/chosen": 0.9983326196670532,
451
+ "logits/rejected": 0.984410285949707,
452
+ "logps/chosen": -1.0478496551513672,
453
+ "logps/rejected": -1.0458667278289795,
454
+ "loss": 0.6106,
455
+ "rewards/accuracies": 0.6625000238418579,
456
+ "rewards/chosen": -0.384859174489975,
457
+ "rewards/margins": 0.23550406098365784,
458
+ "rewards/rejected": -0.6203632354736328,
459
+ "step": 145
460
+ },
461
+ {
462
+ "epoch": 0.2994011976047904,
463
+ "grad_norm": 17.114721290662626,
464
+ "learning_rate": 8.852566213878946e-07,
465
+ "logits/chosen": 0.9434808492660522,
466
+ "logits/rejected": 0.9709761738777161,
467
+ "logps/chosen": -0.946380615234375,
468
+ "logps/rejected": -1.011891484260559,
469
+ "loss": 0.6051,
470
+ "rewards/accuracies": 0.8125,
471
+ "rewards/chosen": -0.10636933147907257,
472
+ "rewards/margins": 0.38454684615135193,
473
+ "rewards/rejected": -0.4909161627292633,
474
+ "step": 150
475
+ },
476
+ {
477
+ "epoch": 0.3093812375249501,
478
+ "grad_norm": 12.532368784046184,
479
+ "learning_rate": 8.73899045249266e-07,
480
+ "logits/chosen": 0.9879257082939148,
481
+ "logits/rejected": 1.0284427404403687,
482
+ "logps/chosen": -0.9887377619743347,
483
+ "logps/rejected": -1.0425301790237427,
484
+ "loss": 0.5785,
485
+ "rewards/accuracies": 0.7124999761581421,
486
+ "rewards/chosen": -0.18314163386821747,
487
+ "rewards/margins": 0.3873257339000702,
488
+ "rewards/rejected": -0.5704673528671265,
489
+ "step": 155
490
+ },
491
+ {
492
+ "epoch": 0.3193612774451098,
493
+ "grad_norm": 20.653306879612042,
494
+ "learning_rate": 8.620859307187338e-07,
495
+ "logits/chosen": 0.9365812540054321,
496
+ "logits/rejected": 0.9702633619308472,
497
+ "logps/chosen": -0.9792872667312622,
498
+ "logps/rejected": -1.0119134187698364,
499
+ "loss": 0.5915,
500
+ "rewards/accuracies": 0.7124999761581421,
501
+ "rewards/chosen": -0.28814950585365295,
502
+ "rewards/margins": 0.3159632086753845,
503
+ "rewards/rejected": -0.6041126847267151,
504
+ "step": 160
505
+ },
506
+ {
507
+ "epoch": 0.32934131736526945,
508
+ "grad_norm": 46.72961396087624,
509
+ "learning_rate": 8.498316702566826e-07,
510
+ "logits/chosen": 1.0088741779327393,
511
+ "logits/rejected": 1.0628801584243774,
512
+ "logps/chosen": -1.0191477537155151,
513
+ "logps/rejected": -1.0589340925216675,
514
+ "loss": 0.5784,
515
+ "rewards/accuracies": 0.7749999761581421,
516
+ "rewards/chosen": -0.43470463156700134,
517
+ "rewards/margins": 0.3699150085449219,
518
+ "rewards/rejected": -0.8046196103096008,
519
+ "step": 165
520
+ },
521
+ {
522
+ "epoch": 0.3393213572854291,
523
+ "grad_norm": 17.875828780004216,
524
+ "learning_rate": 8.371511937918617e-07,
525
+ "logits/chosen": 0.8878538012504578,
526
+ "logits/rejected": 0.9223688840866089,
527
+ "logps/chosen": -0.9879400134086609,
528
+ "logps/rejected": -1.029184103012085,
529
+ "loss": 0.6033,
530
+ "rewards/accuracies": 0.7749999761581421,
531
+ "rewards/chosen": -0.3266729712486267,
532
+ "rewards/margins": 0.5894866585731506,
533
+ "rewards/rejected": -0.9161597490310669,
534
+ "step": 170
535
+ },
536
+ {
537
+ "epoch": 0.34930139720558884,
538
+ "grad_norm": 16.753564996079323,
539
+ "learning_rate": 8.240599505315654e-07,
540
+ "logits/chosen": 0.8993169665336609,
541
+ "logits/rejected": 0.931827187538147,
542
+ "logps/chosen": -1.0300993919372559,
543
+ "logps/rejected": -1.104100227355957,
544
+ "loss": 0.5719,
545
+ "rewards/accuracies": 0.762499988079071,
546
+ "rewards/chosen": -0.26795631647109985,
547
+ "rewards/margins": 0.4897838234901428,
548
+ "rewards/rejected": -0.7577401399612427,
549
+ "step": 175
550
+ },
551
+ {
552
+ "epoch": 0.3592814371257485,
553
+ "grad_norm": 37.583807172799176,
554
+ "learning_rate": 8.105738901391551e-07,
555
+ "logits/chosen": 0.9503185153007507,
556
+ "logits/rejected": 0.9612258076667786,
557
+ "logps/chosen": -0.9984599947929382,
558
+ "logps/rejected": -1.0410314798355103,
559
+ "loss": 0.5749,
560
+ "rewards/accuracies": 0.800000011920929,
561
+ "rewards/chosen": -0.3058738708496094,
562
+ "rewards/margins": 0.4171958565711975,
563
+ "rewards/rejected": -0.7230697274208069,
564
+ "step": 180
565
+ },
566
+ {
567
+ "epoch": 0.36926147704590817,
568
+ "grad_norm": 31.25023262450056,
569
+ "learning_rate": 7.967094433018508e-07,
570
+ "logits/chosen": 0.8538301587104797,
571
+ "logits/rejected": 0.8765438199043274,
572
+ "logps/chosen": -1.0639922618865967,
573
+ "logps/rejected": -1.1690170764923096,
574
+ "loss": 0.5628,
575
+ "rewards/accuracies": 0.75,
576
+ "rewards/chosen": -0.31266123056411743,
577
+ "rewards/margins": 0.6013716459274292,
578
+ "rewards/rejected": -0.9140329360961914,
579
+ "step": 185
580
+ },
581
+ {
582
+ "epoch": 0.37924151696606784,
583
+ "grad_norm": 21.697159728289254,
584
+ "learning_rate": 7.82483501712469e-07,
585
+ "logits/chosen": 0.8337196111679077,
586
+ "logits/rejected": 0.8647937774658203,
587
+ "logps/chosen": -1.0461093187332153,
588
+ "logps/rejected": -1.0427898168563843,
589
+ "loss": 0.5701,
590
+ "rewards/accuracies": 0.737500011920929,
591
+ "rewards/chosen": -0.48062148690223694,
592
+ "rewards/margins": 0.4651462435722351,
593
+ "rewards/rejected": -0.9457677602767944,
594
+ "step": 190
595
+ },
596
+ {
597
+ "epoch": 0.38922155688622756,
598
+ "grad_norm": 13.452601846054984,
599
+ "learning_rate": 7.679133974894982e-07,
600
+ "logits/chosen": 0.8574188351631165,
601
+ "logits/rejected": 0.8771845102310181,
602
+ "logps/chosen": -1.0106494426727295,
603
+ "logps/rejected": -1.1300721168518066,
604
+ "loss": 0.5649,
605
+ "rewards/accuracies": 0.7875000238418579,
606
+ "rewards/chosen": -0.5489331483840942,
607
+ "rewards/margins": 0.6363680958747864,
608
+ "rewards/rejected": -1.1853011846542358,
609
+ "step": 195
610
+ },
611
+ {
612
+ "epoch": 0.3992015968063872,
613
+ "grad_norm": 14.045999687736995,
614
+ "learning_rate": 7.530168820605818e-07,
615
+ "logits/chosen": 0.8429155349731445,
616
+ "logits/rejected": 0.8586641550064087,
617
+ "logps/chosen": -1.1243480443954468,
618
+ "logps/rejected": -1.126988172531128,
619
+ "loss": 0.5556,
620
+ "rewards/accuracies": 0.699999988079071,
621
+ "rewards/chosen": -0.611405074596405,
622
+ "rewards/margins": 0.5212133526802063,
623
+ "rewards/rejected": -1.1326184272766113,
624
+ "step": 200
625
+ },
626
+ {
627
+ "epoch": 0.4091816367265469,
628
+ "grad_norm": 11.17840118621038,
629
+ "learning_rate": 7.378121045351377e-07,
630
+ "logits/chosen": 0.8805230855941772,
631
+ "logits/rejected": 0.8616092801094055,
632
+ "logps/chosen": -1.025155782699585,
633
+ "logps/rejected": -1.1043505668640137,
634
+ "loss": 0.5274,
635
+ "rewards/accuracies": 0.75,
636
+ "rewards/chosen": -0.5864971280097961,
637
+ "rewards/margins": 0.6259642839431763,
638
+ "rewards/rejected": -1.2124613523483276,
639
+ "step": 205
640
+ },
641
+ {
642
+ "epoch": 0.41916167664670656,
643
+ "grad_norm": 17.02714464481709,
644
+ "learning_rate": 7.223175895924637e-07,
645
+ "logits/chosen": 0.8006958961486816,
646
+ "logits/rejected": 0.8346986770629883,
647
+ "logps/chosen": -1.0029652118682861,
648
+ "logps/rejected": -1.0653495788574219,
649
+ "loss": 0.5437,
650
+ "rewards/accuracies": 0.800000011920929,
651
+ "rewards/chosen": -0.5938572287559509,
652
+ "rewards/margins": 0.5961542725563049,
653
+ "rewards/rejected": -1.1900113821029663,
654
+ "step": 210
655
+ },
656
+ {
657
+ "epoch": 0.4291417165668663,
658
+ "grad_norm": 12.708513730083673,
659
+ "learning_rate": 7.065522149122709e-07,
660
+ "logits/chosen": 0.7250524759292603,
661
+ "logits/rejected": 0.7448651790618896,
662
+ "logps/chosen": -1.0977203845977783,
663
+ "logps/rejected": -1.1671373844146729,
664
+ "loss": 0.5296,
665
+ "rewards/accuracies": 0.8374999761581421,
666
+ "rewards/chosen": -0.8822553753852844,
667
+ "rewards/margins": 0.5623547434806824,
668
+ "rewards/rejected": -1.4446099996566772,
669
+ "step": 215
670
+ },
671
+ {
672
+ "epoch": 0.43912175648702595,
673
+ "grad_norm": 23.02316300872982,
674
+ "learning_rate": 6.905351881751371e-07,
675
+ "logits/chosen": 0.7448990345001221,
676
+ "logits/rejected": 0.759792685508728,
677
+ "logps/chosen": -1.0590717792510986,
678
+ "logps/rejected": -1.1264311075210571,
679
+ "loss": 0.5411,
680
+ "rewards/accuracies": 0.7250000238418579,
681
+ "rewards/chosen": -0.7196047306060791,
682
+ "rewards/margins": 0.6396269798278809,
683
+ "rewards/rejected": -1.35923171043396,
684
+ "step": 220
685
+ },
686
+ {
687
+ "epoch": 0.4491017964071856,
688
+ "grad_norm": 15.317013674505024,
689
+ "learning_rate": 6.742860236609076e-07,
690
+ "logits/chosen": 0.7387903928756714,
691
+ "logits/rejected": 0.7482835054397583,
692
+ "logps/chosen": -1.0746328830718994,
693
+ "logps/rejected": -1.0935697555541992,
694
+ "loss": 0.5362,
695
+ "rewards/accuracies": 0.75,
696
+ "rewards/chosen": -0.91168612241745,
697
+ "rewards/margins": 0.43347805738449097,
698
+ "rewards/rejected": -1.3451642990112305,
699
+ "step": 225
700
+ },
701
+ {
702
+ "epoch": 0.4590818363273453,
703
+ "grad_norm": 20.979897267224555,
704
+ "learning_rate": 6.578245184735512e-07,
705
+ "logits/chosen": 0.7530170679092407,
706
+ "logits/rejected": 0.7971817851066589,
707
+ "logps/chosen": -1.0877180099487305,
708
+ "logps/rejected": -1.1133688688278198,
709
+ "loss": 0.5297,
710
+ "rewards/accuracies": 0.762499988079071,
711
+ "rewards/chosen": -0.7731893062591553,
712
+ "rewards/margins": 0.6359795331954956,
713
+ "rewards/rejected": -1.4091689586639404,
714
+ "step": 230
715
+ },
716
+ {
717
+ "epoch": 0.469061876247505,
718
+ "grad_norm": 23.654443057551042,
719
+ "learning_rate": 6.411707284214383e-07,
720
+ "logits/chosen": 0.7936985492706299,
721
+ "logits/rejected": 0.8071283102035522,
722
+ "logps/chosen": -1.1007978916168213,
723
+ "logps/rejected": -1.175083041191101,
724
+ "loss": 0.5189,
725
+ "rewards/accuracies": 0.75,
726
+ "rewards/chosen": -0.8833421468734741,
727
+ "rewards/margins": 0.6522087454795837,
728
+ "rewards/rejected": -1.535550832748413,
729
+ "step": 235
730
+ },
731
+ {
732
+ "epoch": 0.47904191616766467,
733
+ "grad_norm": 17.617163550183303,
734
+ "learning_rate": 6.243449435824276e-07,
735
+ "logits/chosen": 0.7208539247512817,
736
+ "logits/rejected": 0.7419721484184265,
737
+ "logps/chosen": -0.9637038111686707,
738
+ "logps/rejected": -1.0924652814865112,
739
+ "loss": 0.5239,
740
+ "rewards/accuracies": 0.75,
741
+ "rewards/chosen": -0.823961079120636,
742
+ "rewards/margins": 0.9264790415763855,
743
+ "rewards/rejected": -1.750440239906311,
744
+ "step": 240
745
+ },
746
+ {
747
+ "epoch": 0.48902195608782434,
748
+ "grad_norm": 23.429183199427385,
749
+ "learning_rate": 6.073676635835316e-07,
750
+ "logits/chosen": 0.7787541747093201,
751
+ "logits/rejected": 0.8052628636360168,
752
+ "logps/chosen": -1.0102448463439941,
753
+ "logps/rejected": -1.2205474376678467,
754
+ "loss": 0.5087,
755
+ "rewards/accuracies": 0.8125,
756
+ "rewards/chosen": -0.7600202560424805,
757
+ "rewards/margins": 1.2399606704711914,
758
+ "rewards/rejected": -1.9999806880950928,
759
+ "step": 245
760
+ },
761
+ {
762
+ "epoch": 0.499001996007984,
763
+ "grad_norm": 15.897882119964894,
764
+ "learning_rate": 5.9025957262528e-07,
765
+ "logits/chosen": 0.674079179763794,
766
+ "logits/rejected": 0.6560205221176147,
767
+ "logps/chosen": -1.0422561168670654,
768
+ "logps/rejected": -1.15647292137146,
769
+ "loss": 0.5129,
770
+ "rewards/accuracies": 0.8374999761581421,
771
+ "rewards/chosen": -0.9762313961982727,
772
+ "rewards/margins": 0.9589719772338867,
773
+ "rewards/rejected": -1.9352035522460938,
774
+ "step": 250
775
+ },
776
+ {
777
+ "epoch": 0.5089820359281437,
778
+ "grad_norm": 23.926407573258526,
779
+ "learning_rate": 5.730415142812058e-07,
780
+ "logits/chosen": 0.6435045003890991,
781
+ "logits/rejected": 0.6540420055389404,
782
+ "logps/chosen": -1.1076724529266357,
783
+ "logps/rejected": -1.2272051572799683,
784
+ "loss": 0.5207,
785
+ "rewards/accuracies": 0.824999988079071,
786
+ "rewards/chosen": -1.1593824625015259,
787
+ "rewards/margins": 0.9408347010612488,
788
+ "rewards/rejected": -2.10021710395813,
789
+ "step": 255
790
+ },
791
+ {
792
+ "epoch": 0.5189620758483033,
793
+ "grad_norm": 25.873872774153636,
794
+ "learning_rate": 5.557344661031627e-07,
795
+ "logits/chosen": 0.6078227758407593,
796
+ "logits/rejected": 0.6234728097915649,
797
+ "logps/chosen": -1.1247365474700928,
798
+ "logps/rejected": -1.1961596012115479,
799
+ "loss": 0.5558,
800
+ "rewards/accuracies": 0.7124999761581421,
801
+ "rewards/chosen": -1.4092304706573486,
802
+ "rewards/margins": 0.7921189665794373,
803
+ "rewards/rejected": -2.2013492584228516,
804
+ "step": 260
805
+ },
806
+ {
807
+ "epoch": 0.5289421157684631,
808
+ "grad_norm": 14.32961070454234,
809
+ "learning_rate": 5.383595140634093e-07,
810
+ "logits/chosen": 0.634459912776947,
811
+ "logits/rejected": 0.6405037641525269,
812
+ "logps/chosen": -1.054018259048462,
813
+ "logps/rejected": -1.1594079732894897,
814
+ "loss": 0.5108,
815
+ "rewards/accuracies": 0.699999988079071,
816
+ "rewards/chosen": -1.3187201023101807,
817
+ "rewards/margins": 0.7670294046401978,
818
+ "rewards/rejected": -2.085749626159668,
819
+ "step": 265
820
+ },
821
+ {
822
+ "epoch": 0.5389221556886228,
823
+ "grad_norm": 12.765239103380393,
824
+ "learning_rate": 5.209378268645997e-07,
825
+ "logits/chosen": 0.6027650237083435,
826
+ "logits/rejected": 0.6287568211555481,
827
+ "logps/chosen": -1.008739948272705,
828
+ "logps/rejected": -1.1450139284133911,
829
+ "loss": 0.5318,
830
+ "rewards/accuracies": 0.75,
831
+ "rewards/chosen": -1.2432196140289307,
832
+ "rewards/margins": 0.6896325349807739,
833
+ "rewards/rejected": -1.932852029800415,
834
+ "step": 270
835
+ },
836
+ {
837
+ "epoch": 0.5489021956087824,
838
+ "grad_norm": 17.632252940280708,
839
+ "learning_rate": 5.034906301489807e-07,
840
+ "logits/chosen": 0.6728609204292297,
841
+ "logits/rejected": 0.6657983064651489,
842
+ "logps/chosen": -1.1084893941879272,
843
+ "logps/rejected": -1.182081937789917,
844
+ "loss": 0.5413,
845
+ "rewards/accuracies": 0.762499988079071,
846
+ "rewards/chosen": -1.4515244960784912,
847
+ "rewards/margins": 0.8624111413955688,
848
+ "rewards/rejected": -2.3139355182647705,
849
+ "step": 275
850
+ },
851
+ {
852
+ "epoch": 0.5588822355289421,
853
+ "grad_norm": 22.324779245169193,
854
+ "learning_rate": 4.860391806382156e-07,
855
+ "logits/chosen": 0.6076717972755432,
856
+ "logits/rejected": 0.6105688810348511,
857
+ "logps/chosen": -1.0900273323059082,
858
+ "logps/rejected": -1.1191543340682983,
859
+ "loss": 0.512,
860
+ "rewards/accuracies": 0.862500011920929,
861
+ "rewards/chosen": -1.21976900100708,
862
+ "rewards/margins": 0.7310382723808289,
863
+ "rewards/rejected": -1.9508073329925537,
864
+ "step": 280
865
+ },
866
+ {
867
+ "epoch": 0.5688622754491018,
868
+ "grad_norm": 18.31410229389494,
869
+ "learning_rate": 4.686047402353433e-07,
870
+ "logits/chosen": 0.6535500288009644,
871
+ "logits/rejected": 0.6188856959342957,
872
+ "logps/chosen": -1.0886776447296143,
873
+ "logps/rejected": -1.1758826971054077,
874
+ "loss": 0.4871,
875
+ "rewards/accuracies": 0.8125,
876
+ "rewards/chosen": -1.381490707397461,
877
+ "rewards/margins": 0.8018454313278198,
878
+ "rewards/rejected": -2.1833362579345703,
879
+ "step": 285
880
+ },
881
+ {
882
+ "epoch": 0.5788423153692615,
883
+ "grad_norm": 28.66415855277427,
884
+ "learning_rate": 4.512085501204253e-07,
885
+ "logits/chosen": 0.7206050157546997,
886
+ "logits/rejected": 0.7634114623069763,
887
+ "logps/chosen": -1.116304636001587,
888
+ "logps/rejected": -1.1659752130508423,
889
+ "loss": 0.553,
890
+ "rewards/accuracies": 0.7250000238418579,
891
+ "rewards/chosen": -1.4132583141326904,
892
+ "rewards/margins": 0.657631516456604,
893
+ "rewards/rejected": -2.070889711380005,
894
+ "step": 290
895
+ },
896
+ {
897
+ "epoch": 0.5888223552894212,
898
+ "grad_norm": 17.845472804681062,
899
+ "learning_rate": 4.338718048714387e-07,
900
+ "logits/chosen": 0.6159842610359192,
901
+ "logits/rejected": 0.6279784440994263,
902
+ "logps/chosen": -1.0876820087432861,
903
+ "logps/rejected": -1.1220331192016602,
904
+ "loss": 0.5134,
905
+ "rewards/accuracies": 0.8374999761581421,
906
+ "rewards/chosen": -1.233598232269287,
907
+ "rewards/margins": 0.5510263442993164,
908
+ "rewards/rejected": -1.784624695777893,
909
+ "step": 295
910
+ },
911
+ {
912
+ "epoch": 0.5988023952095808,
913
+ "grad_norm": 22.693877555997958,
914
+ "learning_rate": 4.166156266419489e-07,
915
+ "logits/chosen": 0.6069675087928772,
916
+ "logits/rejected": 0.6444044709205627,
917
+ "logps/chosen": -1.0315536260604858,
918
+ "logps/rejected": -1.1916632652282715,
919
+ "loss": 0.5015,
920
+ "rewards/accuracies": 0.7749999761581421,
921
+ "rewards/chosen": -1.4063842296600342,
922
+ "rewards/margins": 0.8028200268745422,
923
+ "rewards/rejected": -2.2092041969299316,
924
+ "step": 300
925
+ },
926
+ {
927
+ "epoch": 0.6087824351297405,
928
+ "grad_norm": 29.176362707547757,
929
+ "learning_rate": 3.9946103942701775e-07,
930
+ "logits/chosen": 0.6731375455856323,
931
+ "logits/rejected": 0.6558948755264282,
932
+ "logps/chosen": -1.0202916860580444,
933
+ "logps/rejected": -1.1923191547393799,
934
+ "loss": 0.4922,
935
+ "rewards/accuracies": 0.7875000238418579,
936
+ "rewards/chosen": -1.134216547012329,
937
+ "rewards/margins": 0.8526105880737305,
938
+ "rewards/rejected": -1.9868271350860596,
939
+ "step": 305
940
+ },
941
+ {
942
+ "epoch": 0.6187624750499002,
943
+ "grad_norm": 16.68482157863775,
944
+ "learning_rate": 3.8242894344870495e-07,
945
+ "logits/chosen": 0.6814749836921692,
946
+ "logits/rejected": 0.6544811129570007,
947
+ "logps/chosen": -1.1450976133346558,
948
+ "logps/rejected": -1.2438080310821533,
949
+ "loss": 0.518,
950
+ "rewards/accuracies": 0.875,
951
+ "rewards/chosen": -1.6444076299667358,
952
+ "rewards/margins": 0.7449675798416138,
953
+ "rewards/rejected": -2.3893752098083496,
954
+ "step": 310
955
+ },
956
+ {
957
+ "epoch": 0.6287425149700598,
958
+ "grad_norm": 24.235832517472502,
959
+ "learning_rate": 3.6554008969236715e-07,
960
+ "logits/chosen": 0.6473463773727417,
961
+ "logits/rejected": 0.6526838541030884,
962
+ "logps/chosen": -1.1155353784561157,
963
+ "logps/rejected": -1.2412601709365845,
964
+ "loss": 0.5036,
965
+ "rewards/accuracies": 0.7749999761581421,
966
+ "rewards/chosen": -1.5284216403961182,
967
+ "rewards/margins": 0.7738613486289978,
968
+ "rewards/rejected": -2.3022828102111816,
969
+ "step": 315
970
+ },
971
+ {
972
+ "epoch": 0.6387225548902196,
973
+ "grad_norm": 14.637858980431309,
974
+ "learning_rate": 3.488150546247778e-07,
975
+ "logits/chosen": 0.641592264175415,
976
+ "logits/rejected": 0.6488014459609985,
977
+ "logps/chosen": -1.0486619472503662,
978
+ "logps/rejected": -1.117785930633545,
979
+ "loss": 0.5076,
980
+ "rewards/accuracies": 0.800000011920929,
981
+ "rewards/chosen": -1.3681632280349731,
982
+ "rewards/margins": 0.7144045829772949,
983
+ "rewards/rejected": -2.0825679302215576,
984
+ "step": 320
985
+ },
986
+ {
987
+ "epoch": 0.6487025948103793,
988
+ "grad_norm": 14.611695255214977,
989
+ "learning_rate": 3.3227421512487255e-07,
990
+ "logits/chosen": 0.6020836234092712,
991
+ "logits/rejected": 0.5903235673904419,
992
+ "logps/chosen": -1.0694186687469482,
993
+ "logps/rejected": -1.1450960636138916,
994
+ "loss": 0.4988,
995
+ "rewards/accuracies": 0.75,
996
+ "rewards/chosen": -1.495102047920227,
997
+ "rewards/margins": 0.6063732504844666,
998
+ "rewards/rejected": -2.101475238800049,
999
+ "step": 325
1000
+ },
1001
+ {
1002
+ "epoch": 0.6586826347305389,
1003
+ "grad_norm": 53.83501877641933,
1004
+ "learning_rate": 3.15937723657661e-07,
1005
+ "logits/chosen": 0.5937372446060181,
1006
+ "logits/rejected": 0.5983537435531616,
1007
+ "logps/chosen": -1.0911985635757446,
1008
+ "logps/rejected": -1.1970782279968262,
1009
+ "loss": 0.5292,
1010
+ "rewards/accuracies": 0.7875000238418579,
1011
+ "rewards/chosen": -1.5829055309295654,
1012
+ "rewards/margins": 0.6139482259750366,
1013
+ "rewards/rejected": -2.1968536376953125,
1014
+ "step": 330
1015
+ },
1016
+ {
1017
+ "epoch": 0.6686626746506986,
1018
+ "grad_norm": 22.263382020354737,
1019
+ "learning_rate": 2.9982548372155256e-07,
1020
+ "logits/chosen": 0.5615344047546387,
1021
+ "logits/rejected": 0.5818489789962769,
1022
+ "logps/chosen": -1.0336883068084717,
1023
+ "logps/rejected": -1.1681592464447021,
1024
+ "loss": 0.5036,
1025
+ "rewards/accuracies": 0.824999988079071,
1026
+ "rewards/chosen": -1.2369213104248047,
1027
+ "rewards/margins": 1.0152759552001953,
1028
+ "rewards/rejected": -2.252197265625,
1029
+ "step": 335
1030
+ },
1031
+ {
1032
+ "epoch": 0.6786427145708582,
1033
+ "grad_norm": 28.648845585620847,
1034
+ "learning_rate": 2.8395712559900874e-07,
1035
+ "logits/chosen": 0.5865073204040527,
1036
+ "logits/rejected": 0.5887445211410522,
1037
+ "logps/chosen": -1.2165284156799316,
1038
+ "logps/rejected": -1.285627007484436,
1039
+ "loss": 0.5287,
1040
+ "rewards/accuracies": 0.7250000238418579,
1041
+ "rewards/chosen": -1.876123070716858,
1042
+ "rewards/margins": 0.8445480465888977,
1043
+ "rewards/rejected": -2.7206711769104004,
1044
+ "step": 340
1045
+ },
1046
+ {
1047
+ "epoch": 0.688622754491018,
1048
+ "grad_norm": 27.7967265314739,
1049
+ "learning_rate": 2.683519824400692e-07,
1050
+ "logits/chosen": 0.6274746656417847,
1051
+ "logits/rejected": 0.6499799489974976,
1052
+ "logps/chosen": -1.1229360103607178,
1053
+ "logps/rejected": -1.2630244493484497,
1054
+ "loss": 0.5228,
1055
+ "rewards/accuracies": 0.7250000238418579,
1056
+ "rewards/chosen": -1.6735212802886963,
1057
+ "rewards/margins": 0.8694586753845215,
1058
+ "rewards/rejected": -2.5429797172546387,
1059
+ "step": 345
1060
+ },
1061
+ {
1062
+ "epoch": 0.6986027944111777,
1063
+ "grad_norm": 22.50466227883414,
1064
+ "learning_rate": 2.530290667078846e-07,
1065
+ "logits/chosen": 0.620844841003418,
1066
+ "logits/rejected": 0.6195460557937622,
1067
+ "logps/chosen": -1.1165497303009033,
1068
+ "logps/rejected": -1.1850183010101318,
1069
+ "loss": 0.5019,
1070
+ "rewards/accuracies": 0.824999988079071,
1071
+ "rewards/chosen": -1.5181663036346436,
1072
+ "rewards/margins": 0.7825000286102295,
1073
+ "rewards/rejected": -2.300666332244873,
1074
+ "step": 350
1075
+ },
1076
+ {
1077
+ "epoch": 0.7085828343313373,
1078
+ "grad_norm": 21.26239260918309,
1079
+ "learning_rate": 2.380070470149605e-07,
1080
+ "logits/chosen": 0.6597515940666199,
1081
+ "logits/rejected": 0.6680246591567993,
1082
+ "logps/chosen": -1.1044973134994507,
1083
+ "logps/rejected": -1.2354698181152344,
1084
+ "loss": 0.4914,
1085
+ "rewards/accuracies": 0.7749999761581421,
1086
+ "rewards/chosen": -1.4524997472763062,
1087
+ "rewards/margins": 1.0394423007965088,
1088
+ "rewards/rejected": -2.4919424057006836,
1089
+ "step": 355
1090
+ },
1091
+ {
1092
+ "epoch": 0.718562874251497,
1093
+ "grad_norm": 30.986440285036473,
1094
+ "learning_rate": 2.23304225378328e-07,
1095
+ "logits/chosen": 0.5663326978683472,
1096
+ "logits/rejected": 0.5595775842666626,
1097
+ "logps/chosen": -1.2192121744155884,
1098
+ "logps/rejected": -1.2986266613006592,
1099
+ "loss": 0.4991,
1100
+ "rewards/accuracies": 0.7875000238418579,
1101
+ "rewards/chosen": -1.6858431100845337,
1102
+ "rewards/margins": 1.0494027137756348,
1103
+ "rewards/rejected": -2.735245704650879,
1104
+ "step": 360
1105
+ },
1106
+ {
1107
+ "epoch": 0.7285429141716567,
1108
+ "grad_norm": 31.154865644231116,
1109
+ "learning_rate": 2.0893851492135532e-07,
1110
+ "logits/chosen": 0.5782791376113892,
1111
+ "logits/rejected": 0.5733534097671509,
1112
+ "logps/chosen": -1.108449935913086,
1113
+ "logps/rejected": -1.2320600748062134,
1114
+ "loss": 0.4969,
1115
+ "rewards/accuracies": 0.7749999761581421,
1116
+ "rewards/chosen": -1.4567809104919434,
1117
+ "rewards/margins": 1.0569483041763306,
1118
+ "rewards/rejected": -2.5137288570404053,
1119
+ "step": 365
1120
+ },
1121
+ {
1122
+ "epoch": 0.7385229540918163,
1123
+ "grad_norm": 25.665361579684205,
1124
+ "learning_rate": 1.9492741804936618e-07,
1125
+ "logits/chosen": 0.5590307116508484,
1126
+ "logits/rejected": 0.5289372205734253,
1127
+ "logps/chosen": -1.135460615158081,
1128
+ "logps/rejected": -1.1982572078704834,
1129
+ "loss": 0.5123,
1130
+ "rewards/accuracies": 0.7749999761581421,
1131
+ "rewards/chosen": -1.5751354694366455,
1132
+ "rewards/margins": 0.7708719968795776,
1133
+ "rewards/rejected": -2.346007823944092,
1134
+ "step": 370
1135
+ },
1136
+ {
1137
+ "epoch": 0.7485029940119761,
1138
+ "grad_norm": 13.466456049238714,
1139
+ "learning_rate": 1.812880051256551e-07,
1140
+ "logits/chosen": 0.5437551736831665,
1141
+ "logits/rejected": 0.540005087852478,
1142
+ "logps/chosen": -1.1057159900665283,
1143
+ "logps/rejected": -1.1711170673370361,
1144
+ "loss": 0.4956,
1145
+ "rewards/accuracies": 0.6875,
1146
+ "rewards/chosen": -1.607832670211792,
1147
+ "rewards/margins": 0.5974467396736145,
1148
+ "rewards/rejected": -2.205279588699341,
1149
+ "step": 375
1150
+ },
1151
+ {
1152
+ "epoch": 0.7584830339321357,
1153
+ "grad_norm": 22.830693166932168,
1154
+ "learning_rate": 1.6803689367387918e-07,
1155
+ "logits/chosen": 0.5521084666252136,
1156
+ "logits/rejected": 0.563881516456604,
1157
+ "logps/chosen": -1.0188974142074585,
1158
+ "logps/rejected": -1.0934759378433228,
1159
+ "loss": 0.5364,
1160
+ "rewards/accuracies": 0.6625000238418579,
1161
+ "rewards/chosen": -1.6915432214736938,
1162
+ "rewards/margins": 0.41655927896499634,
1163
+ "rewards/rejected": -2.108102560043335,
1164
+ "step": 380
1165
+ },
1166
+ {
1167
+ "epoch": 0.7684630738522954,
1168
+ "grad_norm": 16.717527209109356,
1169
+ "learning_rate": 1.551902281321651e-07,
1170
+ "logits/chosen": 0.6741904020309448,
1171
+ "logits/rejected": 0.6558393836021423,
1172
+ "logps/chosen": -1.153136134147644,
1173
+ "logps/rejected": -1.2626793384552002,
1174
+ "loss": 0.4885,
1175
+ "rewards/accuracies": 0.8374999761581421,
1176
+ "rewards/chosen": -1.4042468070983887,
1177
+ "rewards/margins": 1.1682214736938477,
1178
+ "rewards/rejected": -2.5724682807922363,
1179
+ "step": 385
1180
+ },
1181
+ {
1182
+ "epoch": 0.7784431137724551,
1183
+ "grad_norm": 21.35977175588003,
1184
+ "learning_rate": 1.4276366018359842e-07,
1185
+ "logits/chosen": 0.5667208433151245,
1186
+ "logits/rejected": 0.5196897387504578,
1187
+ "logps/chosen": -1.1266697645187378,
1188
+ "logps/rejected": -1.2171615362167358,
1189
+ "loss": 0.5164,
1190
+ "rewards/accuracies": 0.7875000238418579,
1191
+ "rewards/chosen": -1.5344607830047607,
1192
+ "rewards/margins": 0.9302822947502136,
1193
+ "rewards/rejected": -2.464743137359619,
1194
+ "step": 390
1195
+ },
1196
+ {
1197
+ "epoch": 0.7884231536926147,
1198
+ "grad_norm": 21.011004494402407,
1199
+ "learning_rate": 1.3077232968705805e-07,
1200
+ "logits/chosen": 0.581541121006012,
1201
+ "logits/rejected": 0.5735315084457397,
1202
+ "logps/chosen": -1.1142101287841797,
1203
+ "logps/rejected": -1.204474687576294,
1204
+ "loss": 0.4938,
1205
+ "rewards/accuracies": 0.8125,
1206
+ "rewards/chosen": -1.4655622243881226,
1207
+ "rewards/margins": 0.7967506647109985,
1208
+ "rewards/rejected": -2.262312650680542,
1209
+ "step": 395
1210
+ },
1211
+ {
1212
+ "epoch": 0.7984031936127745,
1213
+ "grad_norm": 21.73473549415687,
1214
+ "learning_rate": 1.192308462316317e-07,
1215
+ "logits/chosen": 0.49174603819847107,
1216
+ "logits/rejected": 0.5455900430679321,
1217
+ "logps/chosen": -1.1133276224136353,
1218
+ "logps/rejected": -1.2326544523239136,
1219
+ "loss": 0.5169,
1220
+ "rewards/accuracies": 0.862500011920929,
1221
+ "rewards/chosen": -1.5614674091339111,
1222
+ "rewards/margins": 0.7484425902366638,
1223
+ "rewards/rejected": -2.309910297393799,
1224
+ "step": 400
1225
+ },
1226
+ {
1227
+ "epoch": 0.8083832335329342,
1228
+ "grad_norm": 18.213898305037567,
1229
+ "learning_rate": 1.0815327133708013e-07,
1230
+ "logits/chosen": 0.5780737400054932,
1231
+ "logits/rejected": 0.6099402904510498,
1232
+ "logps/chosen": -1.0353389978408813,
1233
+ "logps/rejected": -1.1462222337722778,
1234
+ "loss": 0.5117,
1235
+ "rewards/accuracies": 0.800000011920929,
1236
+ "rewards/chosen": -1.678412675857544,
1237
+ "rewards/margins": 0.7521916031837463,
1238
+ "rewards/rejected": -2.4306042194366455,
1239
+ "step": 405
1240
+ },
1241
+ {
1242
+ "epoch": 0.8183632734530938,
1243
+ "grad_norm": 14.585406444054382,
1244
+ "learning_rate": 9.755310132204297e-08,
1245
+ "logits/chosen": 0.5654971599578857,
1246
+ "logits/rejected": 0.5592461824417114,
1247
+ "logps/chosen": -1.0622889995574951,
1248
+ "logps/rejected": -1.2071908712387085,
1249
+ "loss": 0.5324,
1250
+ "rewards/accuracies": 0.75,
1251
+ "rewards/chosen": -1.5269814729690552,
1252
+ "rewards/margins": 1.1922402381896973,
1253
+ "rewards/rejected": -2.719221591949463,
1254
+ "step": 410
1255
+ },
1256
+ {
1257
+ "epoch": 0.8283433133732535,
1258
+ "grad_norm": 23.842758561266724,
1259
+ "learning_rate": 8.744325086085247e-08,
1260
+ "logits/chosen": 0.5762808322906494,
1261
+ "logits/rejected": 0.5668230652809143,
1262
+ "logps/chosen": -1.1735143661499023,
1263
+ "logps/rejected": -1.2483824491500854,
1264
+ "loss": 0.504,
1265
+ "rewards/accuracies": 0.800000011920929,
1266
+ "rewards/chosen": -1.7859411239624023,
1267
+ "rewards/margins": 0.8882120847702026,
1268
+ "rewards/rejected": -2.6741533279418945,
1269
+ "step": 415
1270
+ },
1271
+ {
1272
+ "epoch": 0.8383233532934131,
1273
+ "grad_norm": 41.62435891120011,
1274
+ "learning_rate": 7.783603724899257e-08,
1275
+ "logits/chosen": 0.5172094106674194,
1276
+ "logits/rejected": 0.5516868829727173,
1277
+ "logps/chosen": -1.145578145980835,
1278
+ "logps/rejected": -1.248124599456787,
1279
+ "loss": 0.5313,
1280
+ "rewards/accuracies": 0.737500011920929,
1281
+ "rewards/chosen": -1.742923378944397,
1282
+ "rewards/margins": 0.8347417712211609,
1283
+ "rewards/rejected": -2.577665090560913,
1284
+ "step": 420
1285
+ },
1286
+ {
1287
+ "epoch": 0.8483033932135728,
1288
+ "grad_norm": 26.49206528554136,
1289
+ "learning_rate": 6.874316539637126e-08,
1290
+ "logits/chosen": 0.5917887091636658,
1291
+ "logits/rejected": 0.6128644943237305,
1292
+ "logps/chosen": -1.0141854286193848,
1293
+ "logps/rejected": -1.1528804302215576,
1294
+ "loss": 0.4854,
1295
+ "rewards/accuracies": 0.824999988079071,
1296
+ "rewards/chosen": -1.2433063983917236,
1297
+ "rewards/margins": 0.826849639415741,
1298
+ "rewards/rejected": -2.0701558589935303,
1299
+ "step": 425
1300
+ },
1301
+ {
1302
+ "epoch": 0.8582834331337326,
1303
+ "grad_norm": 14.052261790037898,
1304
+ "learning_rate": 6.017571356669182e-08,
1305
+ "logits/chosen": 0.5848813652992249,
1306
+ "logits/rejected": 0.5729445219039917,
1307
+ "logps/chosen": -1.1584407091140747,
1308
+ "logps/rejected": -1.304329752922058,
1309
+ "loss": 0.5097,
1310
+ "rewards/accuracies": 0.7749999761581421,
1311
+ "rewards/chosen": -1.7920862436294556,
1312
+ "rewards/margins": 0.670229971408844,
1313
+ "rewards/rejected": -2.4623162746429443,
1314
+ "step": 430
1315
+ },
1316
+ {
1317
+ "epoch": 0.8682634730538922,
1318
+ "grad_norm": 18.538952507210343,
1319
+ "learning_rate": 5.2144119880293544e-08,
1320
+ "logits/chosen": 0.5895706415176392,
1321
+ "logits/rejected": 0.5678045749664307,
1322
+ "logps/chosen": -1.075687050819397,
1323
+ "logps/rejected": -1.2755447626113892,
1324
+ "loss": 0.5187,
1325
+ "rewards/accuracies": 0.824999988079071,
1326
+ "rewards/chosen": -1.3742207288742065,
1327
+ "rewards/margins": 1.1585171222686768,
1328
+ "rewards/rejected": -2.532737970352173,
1329
+ "step": 435
1330
+ },
1331
+ {
1332
+ "epoch": 0.8782435129740519,
1333
+ "grad_norm": 17.852951128940067,
1334
+ "learning_rate": 4.465816959691149e-08,
1335
+ "logits/chosen": 0.5652838945388794,
1336
+ "logits/rejected": 0.6052907705307007,
1337
+ "logps/chosen": -1.2037353515625,
1338
+ "logps/rejected": -1.3117984533309937,
1339
+ "loss": 0.5009,
1340
+ "rewards/accuracies": 0.887499988079071,
1341
+ "rewards/chosen": -1.7123981714248657,
1342
+ "rewards/margins": 1.019058108329773,
1343
+ "rewards/rejected": -2.7314560413360596,
1344
+ "step": 440
1345
+ },
1346
+ {
1347
+ "epoch": 0.8882235528942116,
1348
+ "grad_norm": 14.249216111089481,
1349
+ "learning_rate": 3.7726983193843485e-08,
1350
+ "logits/chosen": 0.517819344997406,
1351
+ "logits/rejected": 0.5205559730529785,
1352
+ "logps/chosen": -1.0231516361236572,
1353
+ "logps/rejected": -1.148457646369934,
1354
+ "loss": 0.5199,
1355
+ "rewards/accuracies": 0.699999988079071,
1356
+ "rewards/chosen": -1.4192359447479248,
1357
+ "rewards/margins": 0.889240562915802,
1358
+ "rewards/rejected": -2.308476448059082,
1359
+ "step": 445
1360
+ },
1361
+ {
1362
+ "epoch": 0.8982035928143712,
1363
+ "grad_norm": 17.926055468482602,
1364
+ "learning_rate": 3.135900525405427e-08,
1365
+ "logits/chosen": 0.5483254194259644,
1366
+ "logits/rejected": 0.5569725036621094,
1367
+ "logps/chosen": -1.160649299621582,
1368
+ "logps/rejected": -1.2841194868087769,
1369
+ "loss": 0.5171,
1370
+ "rewards/accuracies": 0.762499988079071,
1371
+ "rewards/chosen": -1.7122529745101929,
1372
+ "rewards/margins": 0.9245160222053528,
1373
+ "rewards/rejected": -2.6367690563201904,
1374
+ "step": 450
1375
+ },
1376
+ {
1377
+ "epoch": 0.908183632734531,
1378
+ "grad_norm": 15.183540302368447,
1379
+ "learning_rate": 2.5561994177751732e-08,
1380
+ "logits/chosen": 0.6299312114715576,
1381
+ "logits/rejected": 0.6476989984512329,
1382
+ "logps/chosen": -1.0939618349075317,
1383
+ "logps/rejected": -1.187743902206421,
1384
+ "loss": 0.4643,
1385
+ "rewards/accuracies": 0.75,
1386
+ "rewards/chosen": -1.5630865097045898,
1387
+ "rewards/margins": 0.8125492334365845,
1388
+ "rewards/rejected": -2.3756356239318848,
1389
+ "step": 455
1390
+ },
1391
+ {
1392
+ "epoch": 0.9181636726546906,
1393
+ "grad_norm": 15.769731536967763,
1394
+ "learning_rate": 2.0343012729971243e-08,
1395
+ "logits/chosen": 0.5560911893844604,
1396
+ "logits/rejected": 0.563130259513855,
1397
+ "logps/chosen": -1.1199856996536255,
1398
+ "logps/rejected": -1.2025185823440552,
1399
+ "loss": 0.4948,
1400
+ "rewards/accuracies": 0.7250000238418579,
1401
+ "rewards/chosen": -1.6438310146331787,
1402
+ "rewards/margins": 0.8590097427368164,
1403
+ "rewards/rejected": -2.502840518951416,
1404
+ "step": 460
1405
+ },
1406
+ {
1407
+ "epoch": 0.9281437125748503,
1408
+ "grad_norm": 21.7191545301948,
1409
+ "learning_rate": 1.570841943568446e-08,
1410
+ "logits/chosen": 0.6068538427352905,
1411
+ "logits/rejected": 0.6409121751785278,
1412
+ "logps/chosen": -1.211014747619629,
1413
+ "logps/rejected": -1.3489148616790771,
1414
+ "loss": 0.4823,
1415
+ "rewards/accuracies": 0.8999999761581421,
1416
+ "rewards/chosen": -1.6730806827545166,
1417
+ "rewards/margins": 1.099481463432312,
1418
+ "rewards/rejected": -2.772562026977539,
1419
+ "step": 465
1420
+ },
1421
+ {
1422
+ "epoch": 0.93812375249501,
1423
+ "grad_norm": 23.87949640105234,
1424
+ "learning_rate": 1.166386083291604e-08,
1425
+ "logits/chosen": 0.5642676949501038,
1426
+ "logits/rejected": 0.5937134027481079,
1427
+ "logps/chosen": -1.0865347385406494,
1428
+ "logps/rejected": -1.2261168956756592,
1429
+ "loss": 0.5012,
1430
+ "rewards/accuracies": 0.7875000238418579,
1431
+ "rewards/chosen": -1.5355206727981567,
1432
+ "rewards/margins": 0.9762239456176758,
1433
+ "rewards/rejected": -2.511744260787964,
1434
+ "step": 470
1435
+ },
1436
+ {
1437
+ "epoch": 0.9481037924151696,
1438
+ "grad_norm": 11.821044673852356,
1439
+ "learning_rate": 8.214264593307096e-09,
1440
+ "logits/chosen": 0.5303646922111511,
1441
+ "logits/rejected": 0.550706684589386,
1442
+ "logps/chosen": -1.212477207183838,
1443
+ "logps/rejected": -1.27964186668396,
1444
+ "loss": 0.4881,
1445
+ "rewards/accuracies": 0.762499988079071,
1446
+ "rewards/chosen": -1.8850059509277344,
1447
+ "rewards/margins": 0.7182316780090332,
1448
+ "rewards/rejected": -2.603238105773926,
1449
+ "step": 475
1450
+ },
1451
+ {
1452
+ "epoch": 0.9580838323353293,
1453
+ "grad_norm": 18.686466292842862,
1454
+ "learning_rate": 5.3638335185058335e-09,
1455
+ "logits/chosen": 0.5736523866653442,
1456
+ "logits/rejected": 0.625065267086029,
1457
+ "logps/chosen": -1.2084397077560425,
1458
+ "logps/rejected": -1.3002406358718872,
1459
+ "loss": 0.5266,
1460
+ "rewards/accuracies": 0.8125,
1461
+ "rewards/chosen": -1.7023632526397705,
1462
+ "rewards/margins": 0.9809869527816772,
1463
+ "rewards/rejected": -2.6833503246307373,
1464
+ "step": 480
1465
+ },
1466
+ {
1467
+ "epoch": 0.9680638722554891,
1468
+ "grad_norm": 26.284460492309865,
1469
+ "learning_rate": 3.116040419701815e-09,
1470
+ "logits/chosen": 0.5889401435852051,
1471
+ "logits/rejected": 0.5715131759643555,
1472
+ "logps/chosen": -1.1137585639953613,
1473
+ "logps/rejected": -1.2124450206756592,
1474
+ "loss": 0.5171,
1475
+ "rewards/accuracies": 0.7875000238418579,
1476
+ "rewards/chosen": -1.5402872562408447,
1477
+ "rewards/margins": 0.7413524389266968,
1478
+ "rewards/rejected": -2.281639575958252,
1479
+ "step": 485
1480
+ },
1481
+ {
1482
+ "epoch": 0.9780439121756487,
1483
+ "grad_norm": 30.03419204450396,
1484
+ "learning_rate": 1.4736238865398765e-09,
1485
+ "logits/chosen": 0.6326584815979004,
1486
+ "logits/rejected": 0.6649195551872253,
1487
+ "logps/chosen": -1.1648736000061035,
1488
+ "logps/rejected": -1.2586228847503662,
1489
+ "loss": 0.519,
1490
+ "rewards/accuracies": 0.762499988079071,
1491
+ "rewards/chosen": -1.403749942779541,
1492
+ "rewards/margins": 1.0453355312347412,
1493
+ "rewards/rejected": -2.4490854740142822,
1494
+ "step": 490
1495
+ },
1496
+ {
1497
+ "epoch": 0.9880239520958084,
1498
+ "grad_norm": 33.25313115299262,
1499
+ "learning_rate": 4.3858495057080836e-10,
1500
+ "logits/chosen": 0.5985925197601318,
1501
+ "logits/rejected": 0.5628663301467896,
1502
+ "logps/chosen": -1.2969096899032593,
1503
+ "logps/rejected": -1.4230639934539795,
1504
+ "loss": 0.4764,
1505
+ "rewards/accuracies": 0.8125,
1506
+ "rewards/chosen": -1.819708228111267,
1507
+ "rewards/margins": 1.287508487701416,
1508
+ "rewards/rejected": -3.1072165966033936,
1509
+ "step": 495
1510
+ },
1511
+ {
1512
+ "epoch": 0.998003992015968,
1513
+ "grad_norm": 30.55644687750284,
1514
+ "learning_rate": 1.2184647302626582e-11,
1515
+ "logits/chosen": 0.5701574087142944,
1516
+ "logits/rejected": 0.5943929553031921,
1517
+ "logps/chosen": -1.1318881511688232,
1518
+ "logps/rejected": -1.2142232656478882,
1519
+ "loss": 0.4976,
1520
+ "rewards/accuracies": 0.762499988079071,
1521
+ "rewards/chosen": -1.6143200397491455,
1522
+ "rewards/margins": 0.6937130093574524,
1523
+ "rewards/rejected": -2.3080332279205322,
1524
+ "step": 500
1525
+ },
1526
+ {
1527
+ "epoch": 1.0,
1528
+ "step": 501,
1529
+ "total_flos": 0.0,
1530
+ "train_loss": 0.559710203114146,
1531
+ "train_runtime": 2572.2381,
1532
+ "train_samples_per_second": 24.931,
1533
+ "train_steps_per_second": 0.195
1534
+ }
1535
+ ],
1536
+ "logging_steps": 5,
1537
+ "max_steps": 501,
1538
+ "num_input_tokens_seen": 0,
1539
+ "num_train_epochs": 1,
1540
+ "save_steps": 101,
1541
+ "stateful_callbacks": {
1542
+ "TrainerControl": {
1543
+ "args": {
1544
+ "should_epoch_stop": false,
1545
+ "should_evaluate": false,
1546
+ "should_log": false,
1547
+ "should_save": true,
1548
+ "should_training_stop": true
1549
+ },
1550
+ "attributes": {}
1551
+ }
1552
+ },
1553
+ "total_flos": 0.0,
1554
+ "train_batch_size": 4,
1555
+ "trial_name": null,
1556
+ "trial_params": null
1557
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed4b600e94a28f3fe41cf5d5ef5d0ac61fe15cfd65a7a4a0057ca329ad8e12cc
3
+ size 7544