Hugging Face's logo

SunSec
/
ds_jiuzhang_model

Safetensors
Model card Files
xet
Community
SunSec commited on
Commit
b4ee6a1
·
verified ·
1 Parent(s): 737573c

Add files using upload-large-folder tool

Browse files
Files changed (46) hide show
  1. .gitattributes +3 -0
  2. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/merges.txt +0 -0
  3. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/special_tokens_map.json +31 -0
  4. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/tokenizer_config.json +207 -0
  5. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/added_tokens.json +24 -0
  6. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/config.json +29 -0
  7. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/generation_config.json +14 -0
  8. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/merges.txt +0 -0
  9. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/model.safetensors.index.json +346 -0
  10. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/special_tokens_map.json +31 -0
  11. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/tokenizer_config.json +207 -0
  12. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/trainer_state.json +579 -0
  13. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/vocab.json +0 -0
  14. sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/config.json +29 -0
  15. sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/generation_config.json +9 -0
  16. sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/model.safetensors.index.json +778 -0
  17. sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/special_tokens_map.json +23 -0
  18. sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/tokenizer_config.json +194 -0
  19. sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/trainer_state.json +320 -0
  20. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/model-00001-of-00004.safetensors +3 -0
  21. sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/trainer_state.json +320 -0
  22. sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/added_tokens.json +28 -0
  23. sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/config.json +29 -0
  24. sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/generation_config.json +13 -0
  25. sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/merges.txt +0 -0
  26. sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/model.safetensors.index.json +778 -0
  27. sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/special_tokens_map.json +31 -0
  28. sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/tokenizer_config.json +239 -0
  29. sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/trainer_state.json +418 -0
  30. sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/vocab.json +0 -0
  31. sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/model-00002-of-00004.safetensors +3 -0
  32. sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/model-00003-of-00004.safetensors +3 -0
  33. sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/model-00004-of-00004.safetensors +3 -0
  34. sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/tokenizer.json +3 -0
  35. sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/training_args.bin +3 -0
  36. sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-55/training_args.bin +3 -0
  37. sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/model-00002-of-00004.safetensors +3 -0
  38. sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/model-00003-of-00004.safetensors +3 -0
  39. sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/model-00004-of-00004.safetensors +3 -0
  40. sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/tokenizer.json +3 -0
  41. sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/training_args.bin +3 -0
  42. sft_search/qwen7b_sft_871_checkpoint-78/model-00001-of-00004.safetensors +3 -0
  43. sft_search/qwen7b_sft_871_checkpoint-78/model-00002-of-00004.safetensors +3 -0
  44. sft_search/qwen7b_sft_871_checkpoint-78/model-00003-of-00004.safetensors +3 -0
  45. sft_search/qwen7b_sft_871_checkpoint-78/model-00004-of-00004.safetensors +3 -0
  46. sft_search/qwen7b_sft_871_checkpoint-78/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  sft_search/JOB:29477\#LR:1e-5\#BASE:Qwen2.5-7B-Instruct\#TOKEN:Qwen2.5-7B-Instruct\#BSZ:2\#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  sft_search/JOB:19929\#LR:1e-5\#BASE:Qwen2.5-7B-Instruct\#TOKEN:Qwen2.5-7B-Instruct\#BSZ:2\#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  sft_search/JOB:19929\#LR:1e-5\#BASE:Qwen2.5-7B-Instruct\#TOKEN:Qwen2.5-7B-Instruct\#BSZ:2\#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
36
  sft_search/JOB:29477\#LR:1e-5\#BASE:Qwen2.5-7B-Instruct\#TOKEN:Qwen2.5-7B-Instruct\#BSZ:2\#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  sft_search/JOB:19929\#LR:1e-5\#BASE:Qwen2.5-7B-Instruct\#TOKEN:Qwen2.5-7B-Instruct\#BSZ:2\#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  sft_search/JOB:19929\#LR:1e-5\#BASE:Qwen2.5-7B-Instruct\#TOKEN:Qwen2.5-7B-Instruct\#BSZ:2\#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ sft_search/qwen7b_sft_871_checkpoint-78/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ sft_search/JOB:28315\#LR:1e-5\#BASE:DeepSeek-R1-Distill-Qwen-7B\#TOKEN:DeepSeek-R1-Distill-Qwen-7B\#BSZ:2\#ACC:4_no_error_data_871/checkpoint-68/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ sft_search/JOB:30936\#LR:1e-5\#BASE:Qwen2.5-7B-Instruct\#TOKEN:Qwen2.5-7B-Instruct\#BSZ:2\#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/tokenizer.json filter=lfs diff=lfs merge=lfs -text
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 30000,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/capacity/userdata/models/Qwen2.5-7B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.0",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.0"
14
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
345
+ }
346
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 30000,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/trainer_state.json ADDED
@@ -0,0 +1,579 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.672727272727273,
5
+ "eval_steps": 500,
6
+ "global_step": 78,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07272727272727272,
13
+ "grad_norm": 12.863605499267578,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 1.6066,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.14545454545454545,
20
+ "grad_norm": 12.792675018310547,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 1.6231,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.21818181818181817,
27
+ "grad_norm": 10.905281066894531,
28
+ "learning_rate": 1e-05,
29
+ "loss": 1.566,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.2909090909090909,
34
+ "grad_norm": 5.113491058349609,
35
+ "learning_rate": 9.995614150494293e-06,
36
+ "loss": 1.3752,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.36363636363636365,
41
+ "grad_norm": 5.1580986976623535,
42
+ "learning_rate": 9.982464296247523e-06,
43
+ "loss": 1.2728,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.43636363636363634,
48
+ "grad_norm": 3.579421043395996,
49
+ "learning_rate": 9.960573506572391e-06,
50
+ "loss": 1.2054,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.509090909090909,
55
+ "grad_norm": 4.449979782104492,
56
+ "learning_rate": 9.929980185352525e-06,
57
+ "loss": 1.1506,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5818181818181818,
62
+ "grad_norm": 3.252600908279419,
63
+ "learning_rate": 9.890738003669029e-06,
64
+ "loss": 1.1002,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.6545454545454545,
69
+ "grad_norm": 2.8043909072875977,
70
+ "learning_rate": 9.842915805643156e-06,
71
+ "loss": 1.0085,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.7272727272727273,
76
+ "grad_norm": 2.5800364017486572,
77
+ "learning_rate": 9.786597487660336e-06,
78
+ "loss": 1.0024,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "grad_norm": 2.2836010456085205,
84
+ "learning_rate": 9.721881851187406e-06,
85
+ "loss": 1.0046,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.8727272727272727,
90
+ "grad_norm": 1.9768003225326538,
91
+ "learning_rate": 9.648882429441258e-06,
92
+ "loss": 0.9928,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.9454545454545454,
97
+ "grad_norm": 1.8235994577407837,
98
+ "learning_rate": 9.567727288213005e-06,
99
+ "loss": 0.9482,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.018181818181818,
104
+ "grad_norm": 2.2026915550231934,
105
+ "learning_rate": 9.478558801197065e-06,
106
+ "loss": 1.185,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.0909090909090908,
111
+ "grad_norm": 1.9497827291488647,
112
+ "learning_rate": 9.381533400219319e-06,
113
+ "loss": 0.8687,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.1636363636363636,
118
+ "grad_norm": 1.5467802286148071,
119
+ "learning_rate": 9.276821300802535e-06,
120
+ "loss": 0.8749,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.2363636363636363,
125
+ "grad_norm": 1.3384064435958862,
126
+ "learning_rate": 9.164606203550498e-06,
127
+ "loss": 0.8268,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.309090909090909,
132
+ "grad_norm": 1.3969143629074097,
133
+ "learning_rate": 9.045084971874738e-06,
134
+ "loss": 0.8037,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.3818181818181818,
139
+ "grad_norm": 1.3535643815994263,
140
+ "learning_rate": 8.9184672866292e-06,
141
+ "loss": 0.7878,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.4545454545454546,
146
+ "grad_norm": 1.332352638244629,
147
+ "learning_rate": 8.784975278258783e-06,
148
+ "loss": 0.695,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 1.5272727272727273,
153
+ "grad_norm": 1.357491135597229,
154
+ "learning_rate": 8.644843137107058e-06,
155
+ "loss": 0.8654,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 1.6,
160
+ "grad_norm": 1.2643765211105347,
161
+ "learning_rate": 8.498316702566828e-06,
162
+ "loss": 0.827,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 1.6727272727272728,
167
+ "grad_norm": 1.2994352579116821,
168
+ "learning_rate": 8.345653031794292e-06,
169
+ "loss": 0.7782,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 1.7454545454545456,
174
+ "grad_norm": 1.3649132251739502,
175
+ "learning_rate": 8.18711994874345e-06,
176
+ "loss": 0.7561,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 1.8181818181818183,
181
+ "grad_norm": 1.3455241918563843,
182
+ "learning_rate": 8.022995574311876e-06,
183
+ "loss": 0.738,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.8909090909090909,
188
+ "grad_norm": 1.2925300598144531,
189
+ "learning_rate": 7.85356783842216e-06,
190
+ "loss": 0.7802,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.9636363636363636,
195
+ "grad_norm": 1.2759337425231934,
196
+ "learning_rate": 7.679133974894984e-06,
197
+ "loss": 0.8125,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.036363636363636,
202
+ "grad_norm": 1.4432379007339478,
203
+ "learning_rate": 7.500000000000001e-06,
204
+ "loss": 0.8592,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.109090909090909,
209
+ "grad_norm": 1.3001188039779663,
210
+ "learning_rate": 7.31648017559931e-06,
211
+ "loss": 0.6461,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.1818181818181817,
216
+ "grad_norm": 1.1495414972305298,
217
+ "learning_rate": 7.128896457825364e-06,
218
+ "loss": 0.602,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.2545454545454544,
223
+ "grad_norm": 1.1932196617126465,
224
+ "learning_rate": 6.9375779322605154e-06,
225
+ "loss": 0.6197,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 2.327272727272727,
230
+ "grad_norm": 1.2582231760025024,
231
+ "learning_rate": 6.7428602366090764e-06,
232
+ "loss": 0.6266,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 2.4,
237
+ "grad_norm": 1.1398663520812988,
238
+ "learning_rate": 6.545084971874738e-06,
239
+ "loss": 0.5696,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 2.4727272727272727,
244
+ "grad_norm": 1.1774870157241821,
245
+ "learning_rate": 6.344599103076329e-06,
246
+ "loss": 0.5542,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 2.5454545454545454,
251
+ "grad_norm": 1.248750925064087,
252
+ "learning_rate": 6.141754350553279e-06,
253
+ "loss": 0.5652,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 2.618181818181818,
258
+ "grad_norm": 1.237967610359192,
259
+ "learning_rate": 5.936906572928625e-06,
260
+ "loss": 0.6002,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 2.690909090909091,
265
+ "grad_norm": 1.1738842725753784,
266
+ "learning_rate": 5.730415142812059e-06,
267
+ "loss": 0.5135,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 2.7636363636363637,
272
+ "grad_norm": 1.1954946517944336,
273
+ "learning_rate": 5.522642316338268e-06,
274
+ "loss": 0.583,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 2.8363636363636364,
279
+ "grad_norm": 1.1883139610290527,
280
+ "learning_rate": 5.3139525976465675e-06,
281
+ "loss": 0.5378,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 2.909090909090909,
286
+ "grad_norm": 1.127272367477417,
287
+ "learning_rate": 5.1047120994167855e-06,
288
+ "loss": 0.5299,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 2.981818181818182,
293
+ "grad_norm": 1.4195200204849243,
294
+ "learning_rate": 4.895287900583216e-06,
295
+ "loss": 0.6672,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 3.0545454545454547,
300
+ "grad_norm": 1.349685549736023,
301
+ "learning_rate": 4.686047402353433e-06,
302
+ "loss": 0.4949,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 3.1272727272727274,
307
+ "grad_norm": 1.1365987062454224,
308
+ "learning_rate": 4.477357683661734e-06,
309
+ "loss": 0.458,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 3.2,
314
+ "grad_norm": 1.1739717721939087,
315
+ "learning_rate": 4.269584857187942e-06,
316
+ "loss": 0.4508,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 3.2727272727272725,
321
+ "grad_norm": 1.134547472000122,
322
+ "learning_rate": 4.063093427071376e-06,
323
+ "loss": 0.4418,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 3.3454545454545457,
328
+ "grad_norm": 1.1062874794006348,
329
+ "learning_rate": 3.8582456494467214e-06,
330
+ "loss": 0.4182,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 3.418181818181818,
335
+ "grad_norm": 1.1738144159317017,
336
+ "learning_rate": 3.655400896923672e-06,
337
+ "loss": 0.4048,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 3.4909090909090907,
342
+ "grad_norm": 1.2603284120559692,
343
+ "learning_rate": 3.4549150281252635e-06,
344
+ "loss": 0.3907,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 3.5636363636363635,
349
+ "grad_norm": 1.3774771690368652,
350
+ "learning_rate": 3.2571397633909252e-06,
351
+ "loss": 0.4155,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 3.6363636363636362,
356
+ "grad_norm": 1.3849499225616455,
357
+ "learning_rate": 3.0624220677394854e-06,
358
+ "loss": 0.4615,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 3.709090909090909,
363
+ "grad_norm": 1.2040380239486694,
364
+ "learning_rate": 2.871103542174637e-06,
365
+ "loss": 0.4282,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 3.7818181818181817,
370
+ "grad_norm": 1.1185059547424316,
371
+ "learning_rate": 2.683519824400693e-06,
372
+ "loss": 0.3728,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 3.8545454545454545,
377
+ "grad_norm": 1.1320322751998901,
378
+ "learning_rate": 2.5000000000000015e-06,
379
+ "loss": 0.4147,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 3.9272727272727272,
384
+ "grad_norm": 1.1219350099563599,
385
+ "learning_rate": 2.320866025105016e-06,
386
+ "loss": 0.4436,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 4.0,
391
+ "grad_norm": 1.3520313501358032,
392
+ "learning_rate": 2.146432161577842e-06,
393
+ "loss": 0.4979,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 4.072727272727272,
398
+ "grad_norm": 1.1228889226913452,
399
+ "learning_rate": 1.977004425688126e-06,
400
+ "loss": 0.3531,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 4.1454545454545455,
405
+ "grad_norm": 1.1075667142868042,
406
+ "learning_rate": 1.8128800512565514e-06,
407
+ "loss": 0.3665,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 4.218181818181818,
412
+ "grad_norm": 1.1154788732528687,
413
+ "learning_rate": 1.6543469682057105e-06,
414
+ "loss": 0.34,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 4.290909090909091,
419
+ "grad_norm": 1.0608782768249512,
420
+ "learning_rate": 1.5016832974331725e-06,
421
+ "loss": 0.3432,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 4.363636363636363,
426
+ "grad_norm": 1.0866858959197998,
427
+ "learning_rate": 1.3551568628929434e-06,
428
+ "loss": 0.3172,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 4.4363636363636365,
433
+ "grad_norm": 1.1228256225585938,
434
+ "learning_rate": 1.2150247217412186e-06,
435
+ "loss": 0.3398,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 4.509090909090909,
440
+ "grad_norm": 0.9872593283653259,
441
+ "learning_rate": 1.0815327133708015e-06,
442
+ "loss": 0.34,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 4.581818181818182,
447
+ "grad_norm": 1.0523958206176758,
448
+ "learning_rate": 9.549150281252633e-07,
449
+ "loss": 0.3362,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 4.654545454545454,
454
+ "grad_norm": 1.1005868911743164,
455
+ "learning_rate": 8.353937964495029e-07,
456
+ "loss": 0.3271,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 4.7272727272727275,
461
+ "grad_norm": 1.120803952217102,
462
+ "learning_rate": 7.23178699197467e-07,
463
+ "loss": 0.351,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 4.8,
468
+ "grad_norm": 1.0729155540466309,
469
+ "learning_rate": 6.184665997806832e-07,
470
+ "loss": 0.3317,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 4.872727272727273,
475
+ "grad_norm": 1.1419527530670166,
476
+ "learning_rate": 5.214411988029355e-07,
477
+ "loss": 0.3292,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 4.945454545454545,
482
+ "grad_norm": 1.0432584285736084,
483
+ "learning_rate": 4.322727117869951e-07,
484
+ "loss": 0.3083,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 5.0181818181818185,
489
+ "grad_norm": 1.242761254310608,
490
+ "learning_rate": 3.511175705587433e-07,
491
+ "loss": 0.3758,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 5.090909090909091,
496
+ "grad_norm": 0.9089120626449585,
497
+ "learning_rate": 2.7811814881259503e-07,
498
+ "loss": 0.3094,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 5.163636363636364,
503
+ "grad_norm": 0.9244056940078735,
504
+ "learning_rate": 2.134025123396638e-07,
505
+ "loss": 0.3104,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 5.236363636363636,
510
+ "grad_norm": 0.9533722400665283,
511
+ "learning_rate": 1.5708419435684463e-07,
512
+ "loss": 0.3038,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 5.309090909090909,
517
+ "grad_norm": 0.9400127530097961,
518
+ "learning_rate": 1.0926199633097156e-07,
519
+ "loss": 0.2922,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 5.381818181818182,
524
+ "grad_norm": 0.9125803709030151,
525
+ "learning_rate": 7.001981464747565e-08,
526
+ "loss": 0.2974,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 5.454545454545454,
531
+ "grad_norm": 0.9389327764511108,
532
+ "learning_rate": 3.9426493427611177e-08,
533
+ "loss": 0.2974,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 5.527272727272727,
538
+ "grad_norm": 0.970079779624939,
539
+ "learning_rate": 1.753570375247815e-08,
540
+ "loss": 0.3322,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 5.6,
545
+ "grad_norm": 0.9173036217689514,
546
+ "learning_rate": 4.385849505708084e-09,
547
+ "loss": 0.2853,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 5.672727272727273,
552
+ "grad_norm": 0.969510018825531,
553
+ "learning_rate": 0.0,
554
+ "loss": 0.3049,
555
+ "step": 78
556
+ }
557
+ ],
558
+ "logging_steps": 1.0,
559
+ "max_steps": 78,
560
+ "num_input_tokens_seen": 0,
561
+ "num_train_epochs": 6,
562
+ "save_steps": 500,
563
+ "stateful_callbacks": {
564
+ "TrainerControl": {
565
+ "args": {
566
+ "should_epoch_stop": false,
567
+ "should_evaluate": false,
568
+ "should_log": false,
569
+ "should_save": true,
570
+ "should_training_stop": true
571
+ },
572
+ "attributes": {}
573
+ }
574
+ },
575
+ "total_flos": 13754527416320.0,
576
+ "train_batch_size": 2,
577
+ "trial_name": null,
578
+ "trial_params": null
579
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-78/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/capacity/userdata/models/DeepSeek-R1-Distill-Qwen-32",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 27648,
13
+ "max_position_embeddings": 131072,
14
+ "max_window_layers": 64,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 64,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.0",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151646,
4
+ "do_sample": true,
5
+ "eos_token_id": 151643,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.46.0"
9
+ }
sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/model.safetensors.index.json ADDED
@@ -0,0 +1,778 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 65527752704
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00014-of-00014.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
524
+ "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
525
+ "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
526
+ "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
527
+ "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
528
+ "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
529
+ "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
530
+ "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
531
+ "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
532
+ "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
533
+ "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
534
+ "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
535
+ "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
536
+ "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
537
+ "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
538
+ "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
539
+ "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
540
+ "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
541
+ "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
542
+ "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
543
+ "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
544
+ "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
545
+ "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
546
+ "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
547
+ "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
548
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
549
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
550
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
551
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
552
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
553
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
554
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
555
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
556
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
557
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
558
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
559
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
560
+ "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
561
+ "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
562
+ "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
563
+ "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
564
+ "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
565
+ "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
566
+ "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
567
+ "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
568
+ "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
569
+ "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
570
+ "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
571
+ "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
572
+ "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
573
+ "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
574
+ "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
575
+ "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
576
+ "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
577
+ "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
578
+ "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
579
+ "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
580
+ "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
581
+ "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
582
+ "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
583
+ "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
584
+ "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
585
+ "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
586
+ "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
587
+ "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
588
+ "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
589
+ "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
590
+ "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
591
+ "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
592
+ "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
593
+ "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
594
+ "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
595
+ "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
596
+ "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
597
+ "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
598
+ "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
599
+ "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
600
+ "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
601
+ "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
602
+ "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
603
+ "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
604
+ "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
605
+ "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
606
+ "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
607
+ "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
608
+ "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
609
+ "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
610
+ "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
611
+ "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
612
+ "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
613
+ "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
614
+ "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
615
+ "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
616
+ "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
617
+ "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
618
+ "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
619
+ "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
620
+ "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
621
+ "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
622
+ "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
623
+ "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
624
+ "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
625
+ "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
626
+ "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
627
+ "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
628
+ "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
629
+ "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
630
+ "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
631
+ "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
632
+ "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
633
+ "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
634
+ "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
635
+ "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
636
+ "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
637
+ "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
638
+ "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
639
+ "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
640
+ "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
641
+ "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
642
+ "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
643
+ "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
644
+ "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
645
+ "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
646
+ "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
647
+ "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
648
+ "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
649
+ "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
650
+ "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
651
+ "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
652
+ "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
653
+ "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
654
+ "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
655
+ "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
656
+ "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
657
+ "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
658
+ "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
659
+ "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
660
+ "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
661
+ "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
662
+ "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
663
+ "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
664
+ "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
665
+ "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
666
+ "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
667
+ "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
668
+ "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
669
+ "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
670
+ "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
671
+ "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
672
+ "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
673
+ "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
674
+ "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
675
+ "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
676
+ "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
677
+ "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
678
+ "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
679
+ "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
680
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
681
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
682
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
683
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
684
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
685
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
686
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
687
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
688
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
689
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
690
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
691
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
692
+ "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
693
+ "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
694
+ "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
695
+ "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
696
+ "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
697
+ "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
698
+ "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
699
+ "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
700
+ "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
701
+ "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
702
+ "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
703
+ "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
704
+ "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
705
+ "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
706
+ "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
707
+ "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
708
+ "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
709
+ "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
710
+ "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
711
+ "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
712
+ "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
713
+ "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
714
+ "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
715
+ "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
716
+ "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
717
+ "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
718
+ "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
719
+ "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
720
+ "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
721
+ "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
722
+ "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
723
+ "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
724
+ "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
725
+ "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
726
+ "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
727
+ "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
728
+ "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
729
+ "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
730
+ "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
731
+ "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
732
+ "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
733
+ "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
734
+ "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
735
+ "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
736
+ "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
737
+ "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
738
+ "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
739
+ "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
740
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
741
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
742
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
743
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
744
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
745
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
746
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
747
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
748
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
749
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
750
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
751
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
752
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
753
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
754
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
755
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
756
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
757
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
758
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
759
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
760
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
761
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
762
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
763
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
764
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
765
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
766
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
767
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
768
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
769
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
770
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
771
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
772
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
773
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
774
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
775
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
776
+ "model.norm.weight": "model-00014-of-00014.safetensors"
777
+ }
778
+ }
sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<｜end▁of▁sentence｜>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜end▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<｜User｜>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<｜Assistant｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<｜begin▁of▁sentence｜>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<｜begin▁of▁sentence｜>",
184
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
185
+ "clean_up_tokenization_spaces": false,
186
+ "eos_token": "<｜end▁of▁sentence｜>",
187
+ "legacy": true,
188
+ "model_max_length": 30000,
189
+ "pad_token": "<｜end▁of▁sentence｜>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizer",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }
sft_search/JOB:17315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-32#TOKEN:DeepSeek-R1-Distill-Qwen-32#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/trainer_state.json ADDED
@@ -0,0 +1,320 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.981818181818182,
5
+ "eval_steps": 500,
6
+ "global_step": 41,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07272727272727272,
13
+ "grad_norm": 4.255582809448242,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 0.6583,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.14545454545454545,
20
+ "grad_norm": 4.0357136726379395,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 0.643,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.21818181818181817,
27
+ "grad_norm": 3.8880791664123535,
28
+ "learning_rate": 1e-05,
29
+ "loss": 0.643,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.2909090909090909,
34
+ "grad_norm": 3.2218215465545654,
35
+ "learning_rate": 9.995614150494293e-06,
36
+ "loss": 0.5897,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.36363636363636365,
41
+ "grad_norm": 2.5902259349823,
42
+ "learning_rate": 9.982464296247523e-06,
43
+ "loss": 0.5662,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.43636363636363634,
48
+ "grad_norm": 2.143651008605957,
49
+ "learning_rate": 9.960573506572391e-06,
50
+ "loss": 0.5204,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.509090909090909,
55
+ "grad_norm": 4.17343807220459,
56
+ "learning_rate": 9.929980185352525e-06,
57
+ "loss": 0.5943,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5818181818181818,
62
+ "grad_norm": 2.9467525482177734,
63
+ "learning_rate": 9.890738003669029e-06,
64
+ "loss": 0.545,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.6545454545454545,
69
+ "grad_norm": 2.349730968475342,
70
+ "learning_rate": 9.842915805643156e-06,
71
+ "loss": 0.5117,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.7272727272727273,
76
+ "grad_norm": 1.6330935955047607,
77
+ "learning_rate": 9.786597487660336e-06,
78
+ "loss": 0.515,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "grad_norm": 1.7604299783706665,
84
+ "learning_rate": 9.721881851187406e-06,
85
+ "loss": 0.4838,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.8727272727272727,
90
+ "grad_norm": 1.7978847026824951,
91
+ "learning_rate": 9.648882429441258e-06,
92
+ "loss": 0.4785,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.9454545454545454,
97
+ "grad_norm": 1.4081897735595703,
98
+ "learning_rate": 9.567727288213005e-06,
99
+ "loss": 0.474,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.018181818181818,
104
+ "grad_norm": 1.4312608242034912,
105
+ "learning_rate": 9.478558801197065e-06,
106
+ "loss": 0.4982,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.0909090909090908,
111
+ "grad_norm": 1.2850415706634521,
112
+ "learning_rate": 9.381533400219319e-06,
113
+ "loss": 0.348,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.1636363636363636,
118
+ "grad_norm": 1.067215919494629,
119
+ "learning_rate": 9.276821300802535e-06,
120
+ "loss": 0.3301,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.2363636363636363,
125
+ "grad_norm": 1.091164469718933,
126
+ "learning_rate": 9.164606203550498e-06,
127
+ "loss": 0.2912,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.309090909090909,
132
+ "grad_norm": 1.1501237154006958,
133
+ "learning_rate": 9.045084971874738e-06,
134
+ "loss": 0.2887,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.3818181818181818,
139
+ "grad_norm": 1.1955480575561523,
140
+ "learning_rate": 8.9184672866292e-06,
141
+ "loss": 0.3054,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.4545454545454546,
146
+ "grad_norm": 1.0156254768371582,
147
+ "learning_rate": 8.784975278258783e-06,
148
+ "loss": 0.2503,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 1.5272727272727273,
153
+ "grad_norm": 0.9238996505737305,
154
+ "learning_rate": 8.644843137107058e-06,
155
+ "loss": 0.2868,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 1.6,
160
+ "grad_norm": 0.8769256472587585,
161
+ "learning_rate": 8.498316702566828e-06,
162
+ "loss": 0.2775,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 1.6727272727272728,
167
+ "grad_norm": 0.9478728175163269,
168
+ "learning_rate": 8.345653031794292e-06,
169
+ "loss": 0.249,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 1.7454545454545456,
174
+ "grad_norm": 1.0192630290985107,
175
+ "learning_rate": 8.18711994874345e-06,
176
+ "loss": 0.2722,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 1.8181818181818183,
181
+ "grad_norm": 0.9386352896690369,
182
+ "learning_rate": 8.022995574311876e-06,
183
+ "loss": 0.2458,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.8909090909090909,
188
+ "grad_norm": 0.8530938029289246,
189
+ "learning_rate": 7.85356783842216e-06,
190
+ "loss": 0.2625,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.9636363636363636,
195
+ "grad_norm": 0.9227771162986755,
196
+ "learning_rate": 7.679133974894984e-06,
197
+ "loss": 0.2696,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.036363636363636,
202
+ "grad_norm": 1.1131892204284668,
203
+ "learning_rate": 7.500000000000001e-06,
204
+ "loss": 0.2573,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.109090909090909,
209
+ "grad_norm": 0.8357598781585693,
210
+ "learning_rate": 7.31648017559931e-06,
211
+ "loss": 0.1477,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.1818181818181817,
216
+ "grad_norm": 0.7426121234893799,
217
+ "learning_rate": 7.128896457825364e-06,
218
+ "loss": 0.1555,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.2545454545454544,
223
+ "grad_norm": 0.761500358581543,
224
+ "learning_rate": 6.9375779322605154e-06,
225
+ "loss": 0.161,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 2.327272727272727,
230
+ "grad_norm": 0.8104410767555237,
231
+ "learning_rate": 6.7428602366090764e-06,
232
+ "loss": 0.1435,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 2.4,
237
+ "grad_norm": 0.8981961011886597,
238
+ "learning_rate": 6.545084971874738e-06,
239
+ "loss": 0.1303,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 2.4727272727272727,
244
+ "grad_norm": 0.8238213062286377,
245
+ "learning_rate": 6.344599103076329e-06,
246
+ "loss": 0.1365,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 2.5454545454545454,
251
+ "grad_norm": 0.7720880508422852,
252
+ "learning_rate": 6.141754350553279e-06,
253
+ "loss": 0.1294,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 2.618181818181818,
258
+ "grad_norm": 0.7719836235046387,
259
+ "learning_rate": 5.936906572928625e-06,
260
+ "loss": 0.1412,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 2.690909090909091,
265
+ "grad_norm": 0.7299773693084717,
266
+ "learning_rate": 5.730415142812059e-06,
267
+ "loss": 0.1251,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 2.7636363636363637,
272
+ "grad_norm": 0.7079101204872131,
273
+ "learning_rate": 5.522642316338268e-06,
274
+ "loss": 0.1419,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 2.8363636363636364,
279
+ "grad_norm": 0.806813657283783,
280
+ "learning_rate": 5.3139525976465675e-06,
281
+ "loss": 0.1397,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 2.909090909090909,
286
+ "grad_norm": 0.7062187790870667,
287
+ "learning_rate": 5.1047120994167855e-06,
288
+ "loss": 0.1242,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 2.981818181818182,
293
+ "grad_norm": 0.9283698201179504,
294
+ "learning_rate": 4.895287900583216e-06,
295
+ "loss": 0.1689,
296
+ "step": 41
297
+ }
298
+ ],
299
+ "logging_steps": 1.0,
300
+ "max_steps": 78,
301
+ "num_input_tokens_seen": 0,
302
+ "num_train_epochs": 6,
303
+ "save_steps": 500,
304
+ "stateful_callbacks": {
305
+ "TrainerControl": {
306
+ "args": {
307
+ "should_epoch_stop": false,
308
+ "should_evaluate": false,
309
+ "should_log": false,
310
+ "should_save": true,
311
+ "should_training_stop": false
312
+ },
313
+ "attributes": {}
314
+ }
315
+ },
316
+ "total_flos": 23948726517760.0,
317
+ "train_batch_size": 2,
318
+ "trial_name": null,
319
+ "trial_params": null
320
+ }
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:316c00e26e372ae5fd06d8cd48d3fc0c088724a4e97bcc5c5b37eb44332b038f
3
+ size 4877660776
sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-41/trainer_state.json ADDED
@@ -0,0 +1,320 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.981818181818182,
5
+ "eval_steps": 500,
6
+ "global_step": 41,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07272727272727272,
13
+ "grad_norm": 3.5163450241088867,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 0.3444,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.14545454545454545,
20
+ "grad_norm": 3.3913087844848633,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 0.3212,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.21818181818181817,
27
+ "grad_norm": 3.0000312328338623,
28
+ "learning_rate": 1e-05,
29
+ "loss": 0.3153,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.2909090909090909,
34
+ "grad_norm": 4.771188259124756,
35
+ "learning_rate": 9.995614150494293e-06,
36
+ "loss": 0.3319,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.36363636363636365,
41
+ "grad_norm": 7.022858142852783,
42
+ "learning_rate": 9.982464296247523e-06,
43
+ "loss": 0.3608,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.43636363636363634,
48
+ "grad_norm": 4.220541954040527,
49
+ "learning_rate": 9.960573506572391e-06,
50
+ "loss": 0.3328,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.509090909090909,
55
+ "grad_norm": 3.3209726810455322,
56
+ "learning_rate": 9.929980185352525e-06,
57
+ "loss": 0.3266,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5818181818181818,
62
+ "grad_norm": 2.4358277320861816,
63
+ "learning_rate": 9.890738003669029e-06,
64
+ "loss": 0.3221,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.6545454545454545,
69
+ "grad_norm": 2.457455635070801,
70
+ "learning_rate": 9.842915805643156e-06,
71
+ "loss": 0.3091,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.7272727272727273,
76
+ "grad_norm": 2.5416903495788574,
77
+ "learning_rate": 9.786597487660336e-06,
78
+ "loss": 0.3244,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "grad_norm": 2.2904388904571533,
84
+ "learning_rate": 9.721881851187406e-06,
85
+ "loss": 0.3066,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.8727272727272727,
90
+ "grad_norm": 2.5365567207336426,
91
+ "learning_rate": 9.648882429441258e-06,
92
+ "loss": 0.3147,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.9454545454545454,
97
+ "grad_norm": 2.294513463973999,
98
+ "learning_rate": 9.567727288213005e-06,
99
+ "loss": 0.3084,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.018181818181818,
104
+ "grad_norm": 2.4129557609558105,
105
+ "learning_rate": 9.478558801197065e-06,
106
+ "loss": 0.3521,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.0909090909090908,
111
+ "grad_norm": 2.2233598232269287,
112
+ "learning_rate": 9.381533400219319e-06,
113
+ "loss": 0.2531,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.1636363636363636,
118
+ "grad_norm": 1.8684265613555908,
119
+ "learning_rate": 9.276821300802535e-06,
120
+ "loss": 0.2376,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.2363636363636363,
125
+ "grad_norm": 1.8931159973144531,
126
+ "learning_rate": 9.164606203550498e-06,
127
+ "loss": 0.2142,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.309090909090909,
132
+ "grad_norm": 1.8524627685546875,
133
+ "learning_rate": 9.045084971874738e-06,
134
+ "loss": 0.2185,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.3818181818181818,
139
+ "grad_norm": 1.9286556243896484,
140
+ "learning_rate": 8.9184672866292e-06,
141
+ "loss": 0.2306,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.4545454545454546,
146
+ "grad_norm": 1.7671759128570557,
147
+ "learning_rate": 8.784975278258783e-06,
148
+ "loss": 0.1948,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 1.5272727272727273,
153
+ "grad_norm": 1.5562022924423218,
154
+ "learning_rate": 8.644843137107058e-06,
155
+ "loss": 0.2143,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 1.6,
160
+ "grad_norm": 1.4897706508636475,
161
+ "learning_rate": 8.498316702566828e-06,
162
+ "loss": 0.2071,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 1.6727272727272728,
167
+ "grad_norm": 1.487337350845337,
168
+ "learning_rate": 8.345653031794292e-06,
169
+ "loss": 0.1913,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 1.7454545454545456,
174
+ "grad_norm": 1.5593852996826172,
175
+ "learning_rate": 8.18711994874345e-06,
176
+ "loss": 0.2086,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 1.8181818181818183,
181
+ "grad_norm": 1.7306010723114014,
182
+ "learning_rate": 8.022995574311876e-06,
183
+ "loss": 0.2032,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.8909090909090909,
188
+ "grad_norm": 1.4432237148284912,
189
+ "learning_rate": 7.85356783842216e-06,
190
+ "loss": 0.2129,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.9636363636363636,
195
+ "grad_norm": 1.470381259918213,
196
+ "learning_rate": 7.679133974894984e-06,
197
+ "loss": 0.2155,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.036363636363636,
202
+ "grad_norm": 1.6842033863067627,
203
+ "learning_rate": 7.500000000000001e-06,
204
+ "loss": 0.2031,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.109090909090909,
209
+ "grad_norm": 1.3305888175964355,
210
+ "learning_rate": 7.31648017559931e-06,
211
+ "loss": 0.1168,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.1818181818181817,
216
+ "grad_norm": 1.1846952438354492,
217
+ "learning_rate": 7.128896457825364e-06,
218
+ "loss": 0.1203,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.2545454545454544,
223
+ "grad_norm": 1.0537058115005493,
224
+ "learning_rate": 6.9375779322605154e-06,
225
+ "loss": 0.1126,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 2.327272727272727,
230
+ "grad_norm": 1.4323068857192993,
231
+ "learning_rate": 6.7428602366090764e-06,
232
+ "loss": 0.1101,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 2.4,
237
+ "grad_norm": 1.2929614782333374,
238
+ "learning_rate": 6.545084971874738e-06,
239
+ "loss": 0.0998,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 2.4727272727272727,
244
+ "grad_norm": 1.4297711849212646,
245
+ "learning_rate": 6.344599103076329e-06,
246
+ "loss": 0.1104,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 2.5454545454545454,
251
+ "grad_norm": 1.297240972518921,
252
+ "learning_rate": 6.141754350553279e-06,
253
+ "loss": 0.1011,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 2.618181818181818,
258
+ "grad_norm": 1.3363728523254395,
259
+ "learning_rate": 5.936906572928625e-06,
260
+ "loss": 0.1121,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 2.690909090909091,
265
+ "grad_norm": 1.2730250358581543,
266
+ "learning_rate": 5.730415142812059e-06,
267
+ "loss": 0.1133,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 2.7636363636363637,
272
+ "grad_norm": 1.338897466659546,
273
+ "learning_rate": 5.522642316338268e-06,
274
+ "loss": 0.1256,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 2.8363636363636364,
279
+ "grad_norm": 1.0859397649765015,
280
+ "learning_rate": 5.3139525976465675e-06,
281
+ "loss": 0.1083,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 2.909090909090909,
286
+ "grad_norm": 1.0852962732315063,
287
+ "learning_rate": 5.1047120994167855e-06,
288
+ "loss": 0.1039,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 2.981818181818182,
293
+ "grad_norm": 1.3069108724594116,
294
+ "learning_rate": 4.895287900583216e-06,
295
+ "loss": 0.133,
296
+ "step": 41
297
+ }
298
+ ],
299
+ "logging_steps": 1.0,
300
+ "max_steps": 78,
301
+ "num_input_tokens_seen": 0,
302
+ "num_train_epochs": 6,
303
+ "save_steps": 500,
304
+ "stateful_callbacks": {
305
+ "TrainerControl": {
306
+ "args": {
307
+ "should_epoch_stop": false,
308
+ "should_evaluate": false,
309
+ "should_log": false,
310
+ "should_save": true,
311
+ "should_training_stop": false
312
+ },
313
+ "attributes": {}
314
+ }
315
+ },
316
+ "total_flos": 24036832526336.0,
317
+ "train_batch_size": 2,
318
+ "trial_name": null,
319
+ "trial_params": null
320
+ }
sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/capacity/userdata/models/QwQ-32B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 27648,
13
+ "max_position_embeddings": 131072,
14
+ "max_window_layers": 64,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 64,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.0",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 40,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.46.0"
13
+ }
sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/model.safetensors.index.json ADDED
@@ -0,0 +1,778 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 65527752704
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00014-of-00014.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
524
+ "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
525
+ "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
526
+ "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
527
+ "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
528
+ "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
529
+ "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
530
+ "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
531
+ "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
532
+ "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
533
+ "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
534
+ "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
535
+ "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
536
+ "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
537
+ "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
538
+ "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
539
+ "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
540
+ "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
541
+ "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
542
+ "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
543
+ "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
544
+ "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
545
+ "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
546
+ "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
547
+ "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
548
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
549
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
550
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
551
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
552
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
553
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
554
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
555
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
556
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
557
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
558
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
559
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
560
+ "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
561
+ "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
562
+ "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
563
+ "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
564
+ "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
565
+ "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
566
+ "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
567
+ "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
568
+ "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
569
+ "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
570
+ "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
571
+ "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
572
+ "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
573
+ "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
574
+ "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
575
+ "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
576
+ "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
577
+ "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
578
+ "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
579
+ "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
580
+ "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
581
+ "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
582
+ "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
583
+ "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
584
+ "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
585
+ "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
586
+ "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
587
+ "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
588
+ "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
589
+ "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
590
+ "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
591
+ "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
592
+ "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
593
+ "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
594
+ "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
595
+ "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
596
+ "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
597
+ "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
598
+ "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
599
+ "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
600
+ "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
601
+ "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
602
+ "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
603
+ "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
604
+ "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
605
+ "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
606
+ "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
607
+ "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
608
+ "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
609
+ "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
610
+ "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
611
+ "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
612
+ "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
613
+ "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
614
+ "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
615
+ "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
616
+ "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
617
+ "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
618
+ "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
619
+ "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
620
+ "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
621
+ "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
622
+ "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
623
+ "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
624
+ "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
625
+ "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
626
+ "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
627
+ "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
628
+ "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
629
+ "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
630
+ "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
631
+ "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
632
+ "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
633
+ "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
634
+ "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
635
+ "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
636
+ "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
637
+ "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
638
+ "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
639
+ "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
640
+ "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
641
+ "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
642
+ "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
643
+ "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
644
+ "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
645
+ "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
646
+ "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
647
+ "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
648
+ "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
649
+ "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
650
+ "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
651
+ "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
652
+ "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
653
+ "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
654
+ "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
655
+ "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
656
+ "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
657
+ "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
658
+ "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
659
+ "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
660
+ "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
661
+ "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
662
+ "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
663
+ "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
664
+ "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
665
+ "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
666
+ "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
667
+ "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
668
+ "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
669
+ "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
670
+ "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
671
+ "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
672
+ "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
673
+ "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
674
+ "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
675
+ "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
676
+ "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
677
+ "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
678
+ "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
679
+ "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
680
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
681
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
682
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
683
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
684
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
685
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
686
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
687
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
688
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
689
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
690
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
691
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
692
+ "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
693
+ "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
694
+ "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
695
+ "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
696
+ "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
697
+ "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
698
+ "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
699
+ "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
700
+ "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
701
+ "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
702
+ "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
703
+ "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
704
+ "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
705
+ "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
706
+ "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
707
+ "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
708
+ "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
709
+ "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
710
+ "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
711
+ "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
712
+ "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
713
+ "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
714
+ "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
715
+ "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
716
+ "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
717
+ "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
718
+ "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
719
+ "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
720
+ "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
721
+ "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
722
+ "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
723
+ "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
724
+ "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
725
+ "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
726
+ "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
727
+ "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
728
+ "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
729
+ "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
730
+ "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
731
+ "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
732
+ "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
733
+ "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
734
+ "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
735
+ "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
736
+ "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
737
+ "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
738
+ "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
739
+ "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
740
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
741
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
742
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
743
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
744
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
745
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
746
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
747
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
748
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
749
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
750
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
751
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
752
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
753
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
754
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
755
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
756
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
757
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
758
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
759
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
760
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
761
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
762
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
763
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
764
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
765
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
766
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
767
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
768
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
769
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
770
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
771
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
772
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
773
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
774
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
775
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
776
+ "model.norm.weight": "model-00014-of-00014.safetensors"
777
+ }
778
+ }
sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- '' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" and not message.tool_calls %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "model_max_length": 30000,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/trainer_state.json ADDED
@@ -0,0 +1,418 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 55,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07272727272727272,
13
+ "grad_norm": 3.5163450241088867,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 0.3444,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.14545454545454545,
20
+ "grad_norm": 3.3913087844848633,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 0.3212,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.21818181818181817,
27
+ "grad_norm": 3.0000312328338623,
28
+ "learning_rate": 1e-05,
29
+ "loss": 0.3153,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.2909090909090909,
34
+ "grad_norm": 4.771188259124756,
35
+ "learning_rate": 9.995614150494293e-06,
36
+ "loss": 0.3319,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.36363636363636365,
41
+ "grad_norm": 7.022858142852783,
42
+ "learning_rate": 9.982464296247523e-06,
43
+ "loss": 0.3608,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.43636363636363634,
48
+ "grad_norm": 4.220541954040527,
49
+ "learning_rate": 9.960573506572391e-06,
50
+ "loss": 0.3328,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.509090909090909,
55
+ "grad_norm": 3.3209726810455322,
56
+ "learning_rate": 9.929980185352525e-06,
57
+ "loss": 0.3266,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5818181818181818,
62
+ "grad_norm": 2.4358277320861816,
63
+ "learning_rate": 9.890738003669029e-06,
64
+ "loss": 0.3221,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.6545454545454545,
69
+ "grad_norm": 2.457455635070801,
70
+ "learning_rate": 9.842915805643156e-06,
71
+ "loss": 0.3091,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.7272727272727273,
76
+ "grad_norm": 2.5416903495788574,
77
+ "learning_rate": 9.786597487660336e-06,
78
+ "loss": 0.3244,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "grad_norm": 2.2904388904571533,
84
+ "learning_rate": 9.721881851187406e-06,
85
+ "loss": 0.3066,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.8727272727272727,
90
+ "grad_norm": 2.5365567207336426,
91
+ "learning_rate": 9.648882429441258e-06,
92
+ "loss": 0.3147,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.9454545454545454,
97
+ "grad_norm": 2.294513463973999,
98
+ "learning_rate": 9.567727288213005e-06,
99
+ "loss": 0.3084,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.018181818181818,
104
+ "grad_norm": 2.4129557609558105,
105
+ "learning_rate": 9.478558801197065e-06,
106
+ "loss": 0.3521,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.0909090909090908,
111
+ "grad_norm": 2.2233598232269287,
112
+ "learning_rate": 9.381533400219319e-06,
113
+ "loss": 0.2531,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.1636363636363636,
118
+ "grad_norm": 1.8684265613555908,
119
+ "learning_rate": 9.276821300802535e-06,
120
+ "loss": 0.2376,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.2363636363636363,
125
+ "grad_norm": 1.8931159973144531,
126
+ "learning_rate": 9.164606203550498e-06,
127
+ "loss": 0.2142,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.309090909090909,
132
+ "grad_norm": 1.8524627685546875,
133
+ "learning_rate": 9.045084971874738e-06,
134
+ "loss": 0.2185,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.3818181818181818,
139
+ "grad_norm": 1.9286556243896484,
140
+ "learning_rate": 8.9184672866292e-06,
141
+ "loss": 0.2306,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.4545454545454546,
146
+ "grad_norm": 1.7671759128570557,
147
+ "learning_rate": 8.784975278258783e-06,
148
+ "loss": 0.1948,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 1.5272727272727273,
153
+ "grad_norm": 1.5562022924423218,
154
+ "learning_rate": 8.644843137107058e-06,
155
+ "loss": 0.2143,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 1.6,
160
+ "grad_norm": 1.4897706508636475,
161
+ "learning_rate": 8.498316702566828e-06,
162
+ "loss": 0.2071,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 1.6727272727272728,
167
+ "grad_norm": 1.487337350845337,
168
+ "learning_rate": 8.345653031794292e-06,
169
+ "loss": 0.1913,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 1.7454545454545456,
174
+ "grad_norm": 1.5593852996826172,
175
+ "learning_rate": 8.18711994874345e-06,
176
+ "loss": 0.2086,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 1.8181818181818183,
181
+ "grad_norm": 1.7306010723114014,
182
+ "learning_rate": 8.022995574311876e-06,
183
+ "loss": 0.2032,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.8909090909090909,
188
+ "grad_norm": 1.4432237148284912,
189
+ "learning_rate": 7.85356783842216e-06,
190
+ "loss": 0.2129,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.9636363636363636,
195
+ "grad_norm": 1.470381259918213,
196
+ "learning_rate": 7.679133974894984e-06,
197
+ "loss": 0.2155,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.036363636363636,
202
+ "grad_norm": 1.6842033863067627,
203
+ "learning_rate": 7.500000000000001e-06,
204
+ "loss": 0.2031,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.109090909090909,
209
+ "grad_norm": 1.3305888175964355,
210
+ "learning_rate": 7.31648017559931e-06,
211
+ "loss": 0.1168,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.1818181818181817,
216
+ "grad_norm": 1.1846952438354492,
217
+ "learning_rate": 7.128896457825364e-06,
218
+ "loss": 0.1203,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.2545454545454544,
223
+ "grad_norm": 1.0537058115005493,
224
+ "learning_rate": 6.9375779322605154e-06,
225
+ "loss": 0.1126,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 2.327272727272727,
230
+ "grad_norm": 1.4323068857192993,
231
+ "learning_rate": 6.7428602366090764e-06,
232
+ "loss": 0.1101,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 2.4,
237
+ "grad_norm": 1.2929614782333374,
238
+ "learning_rate": 6.545084971874738e-06,
239
+ "loss": 0.0998,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 2.4727272727272727,
244
+ "grad_norm": 1.4297711849212646,
245
+ "learning_rate": 6.344599103076329e-06,
246
+ "loss": 0.1104,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 2.5454545454545454,
251
+ "grad_norm": 1.297240972518921,
252
+ "learning_rate": 6.141754350553279e-06,
253
+ "loss": 0.1011,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 2.618181818181818,
258
+ "grad_norm": 1.3363728523254395,
259
+ "learning_rate": 5.936906572928625e-06,
260
+ "loss": 0.1121,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 2.690909090909091,
265
+ "grad_norm": 1.2730250358581543,
266
+ "learning_rate": 5.730415142812059e-06,
267
+ "loss": 0.1133,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 2.7636363636363637,
272
+ "grad_norm": 1.338897466659546,
273
+ "learning_rate": 5.522642316338268e-06,
274
+ "loss": 0.1256,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 2.8363636363636364,
279
+ "grad_norm": 1.0859397649765015,
280
+ "learning_rate": 5.3139525976465675e-06,
281
+ "loss": 0.1083,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 2.909090909090909,
286
+ "grad_norm": 1.0852962732315063,
287
+ "learning_rate": 5.1047120994167855e-06,
288
+ "loss": 0.1039,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 2.981818181818182,
293
+ "grad_norm": 1.3069108724594116,
294
+ "learning_rate": 4.895287900583216e-06,
295
+ "loss": 0.133,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 3.0545454545454547,
300
+ "grad_norm": 1.0186970233917236,
301
+ "learning_rate": 4.686047402353433e-06,
302
+ "loss": 0.0717,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 3.1272727272727274,
307
+ "grad_norm": 0.8754695653915405,
308
+ "learning_rate": 4.477357683661734e-06,
309
+ "loss": 0.0582,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 3.2,
314
+ "grad_norm": 0.9395139217376709,
315
+ "learning_rate": 4.269584857187942e-06,
316
+ "loss": 0.0512,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 3.2727272727272725,
321
+ "grad_norm": 0.8136391639709473,
322
+ "learning_rate": 4.063093427071376e-06,
323
+ "loss": 0.0592,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 3.3454545454545457,
328
+ "grad_norm": 0.7687387466430664,
329
+ "learning_rate": 3.8582456494467214e-06,
330
+ "loss": 0.0429,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 3.418181818181818,
335
+ "grad_norm": 0.8258800506591797,
336
+ "learning_rate": 3.655400896923672e-06,
337
+ "loss": 0.0439,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 3.4909090909090907,
342
+ "grad_norm": 0.863828718662262,
343
+ "learning_rate": 3.4549150281252635e-06,
344
+ "loss": 0.0446,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 3.5636363636363635,
349
+ "grad_norm": 0.8924857974052429,
350
+ "learning_rate": 3.2571397633909252e-06,
351
+ "loss": 0.0463,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 3.6363636363636362,
356
+ "grad_norm": 0.93898606300354,
357
+ "learning_rate": 3.0624220677394854e-06,
358
+ "loss": 0.0475,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 3.709090909090909,
363
+ "grad_norm": 1.0248537063598633,
364
+ "learning_rate": 2.871103542174637e-06,
365
+ "loss": 0.049,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 3.7818181818181817,
370
+ "grad_norm": 0.910682737827301,
371
+ "learning_rate": 2.683519824400693e-06,
372
+ "loss": 0.0434,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 3.8545454545454545,
377
+ "grad_norm": 0.8931945562362671,
378
+ "learning_rate": 2.5000000000000015e-06,
379
+ "loss": 0.0447,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 3.9272727272727272,
384
+ "grad_norm": 0.9278035163879395,
385
+ "learning_rate": 2.320866025105016e-06,
386
+ "loss": 0.0442,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 4.0,
391
+ "grad_norm": 1.0301254987716675,
392
+ "learning_rate": 2.146432161577842e-06,
393
+ "loss": 0.0534,
394
+ "step": 55
395
+ }
396
+ ],
397
+ "logging_steps": 1.0,
398
+ "max_steps": 78,
399
+ "num_input_tokens_seen": 0,
400
+ "num_train_epochs": 6,
401
+ "save_steps": 500,
402
+ "stateful_callbacks": {
403
+ "TrainerControl": {
404
+ "args": {
405
+ "should_epoch_stop": false,
406
+ "should_evaluate": false,
407
+ "should_log": false,
408
+ "should_save": true,
409
+ "should_training_stop": false
410
+ },
411
+ "attributes": {}
412
+ }
413
+ },
414
+ "total_flos": 32129175273472.0,
415
+ "train_batch_size": 2,
416
+ "trial_name": null,
417
+ "trial_params": null
418
+ }
sft_search/JOB:2284#LR:1e-5#BASE:QwQ-32B#TOKEN:QwQ-32B#BSZ:2#ACC:4_no_error_data_871/checkpoint-55/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0fa5aa4139a3090a48766779929ce1281390d8562e4bf46fedb78bd5ccead8
3
+ size 4932751008
sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f755a267c1cbebc3c085e5ac6999761979f422267bef1204e78f0c82a55a20
3
+ size 4330865200
sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9baeaaf60adc56d870d0ca38ea902dd4678fc0b54eccabc1dbf15ae23e468567
3
+ size 1089994880
sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec5656bcf42d45e1203b00951bb1a15cbef63aadee5c25c8b641d6c91b399e6
3
+ size 7544
sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-55/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bb3201b3ced132d6447edb27e9e759a67e20b55937b00af6bffd3ed016c348e
3
+ size 7544
sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a70d64ad53c6db3a08f267381ae34ace4ed5fbf4fc73c8e3609c97da5a3889
3
+ size 4932751008
sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:787fe9ba2c2690befff5937d701d4937f73bb497b864228d49dbfabbe74c7ca0
3
+ size 4330865200
sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7584b85022e3bc1c009170de3826179bde79ea0b4dec2433eef34ab85962f278
3
+ size 1089994880
sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-68/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bb3201b3ced132d6447edb27e9e759a67e20b55937b00af6bffd3ed016c348e
3
+ size 7544
sft_search/qwen7b_sft_871_checkpoint-78/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a3a30a450feedaa898c80aa30ea916da947d7a44ebc49b819e93acfab78a2e
3
+ size 4877660776
sft_search/qwen7b_sft_871_checkpoint-78/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa6fdd01d571e36b031e65a7d68940faadeef093afdbfb53ade0f4854643337c
3
+ size 4932751008
sft_search/qwen7b_sft_871_checkpoint-78/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7700a699891b165665b3d4bc99a49bc11bce9bff3cc0df6833bbd22ca4c635f4
3
+ size 4330865200
sft_search/qwen7b_sft_871_checkpoint-78/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7080686d3001be0066676060efd652336f86252ef0cdbb5c2213035340a65f7b
3
+ size 1089994880
sft_search/qwen7b_sft_871_checkpoint-78/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896