Hugging Face's logo

336labs
/
VisionEncoder-to-MLLM-ModelZoo

Safetensors
vision-encoder-evaluation
multimodal
visual-tokenizer-benchmark
checkpoints
Model card Files
xet
 Community
lyunee commited on
Commit
ab5c40b
·
verified ·
1 Parent(s): 80ee85c

Upload continuous evaluation checkpoints, batch 9

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. continuous/qwen25/pe_core_b16_224/finetune/special_tokens_map.json +31 -0
  3. continuous/qwen25/pe_core_b16_224/finetune/tokenizer.json +3 -0
  4. continuous/qwen25/pe_core_b16_224/finetune/tokenizer_config.json +208 -0
  5. continuous/qwen25/pe_core_b16_224/finetune/trainer_state.json +1856 -0
  6. continuous/qwen25/pe_core_b16_224/finetune/training_args.bin +3 -0
  7. continuous/qwen25/pe_core_b16_224/finetune/vocab.json +0 -0
  8. continuous/qwen25/pe_core_b16_224/pretrain/config.json +87 -0
  9. continuous/qwen25/pe_core_b16_224/pretrain/mm_projector.bin +3 -0
  10. continuous/qwen25/pe_core_b16_224/pretrain/trainer_state.json +421 -0
  11. continuous/qwen25/pe_core_g14_448/finetune/added_tokens.json +24 -0
  12. continuous/qwen25/pe_core_g14_448/finetune/chat_template.jinja +54 -0
  13. continuous/qwen25/pe_core_g14_448/finetune/config.json +87 -0
  14. continuous/qwen25/pe_core_g14_448/finetune/generation_config.json +13 -0
  15. continuous/qwen25/pe_core_g14_448/finetune/merges.txt +0 -0
  16. continuous/qwen25/pe_core_g14_448/finetune/model-00001-of-00002.safetensors +3 -0
  17. continuous/qwen25/pe_core_g14_448/finetune/model-00002-of-00002.safetensors +3 -0
  18. continuous/qwen25/pe_core_g14_448/finetune/model.safetensors.index.json +969 -0
  19. continuous/qwen25/pe_core_g14_448/finetune/special_tokens_map.json +31 -0
  20. continuous/qwen25/pe_core_g14_448/finetune/tokenizer.json +3 -0
  21. continuous/qwen25/pe_core_g14_448/finetune/tokenizer_config.json +208 -0
  22. continuous/qwen25/pe_core_g14_448/finetune/trainer_state.json +1856 -0
  23. continuous/qwen25/pe_core_g14_448/finetune/training_args.bin +3 -0
  24. continuous/qwen25/pe_core_g14_448/finetune/vocab.json +0 -0
  25. continuous/qwen25/pe_core_g14_448/pretrain/config.json +87 -0
  26. continuous/qwen25/pe_core_g14_448/pretrain/mm_projector.bin +3 -0
  27. continuous/qwen25/pe_core_g14_448/pretrain/trainer_state.json +421 -0
  28. continuous/qwen25/pe_core_l14_336/finetune/added_tokens.json +24 -0
  29. continuous/qwen25/pe_core_l14_336/finetune/chat_template.jinja +54 -0
  30. continuous/qwen25/pe_core_l14_336/finetune/config.json +87 -0
  31. continuous/qwen25/pe_core_l14_336/finetune/generation_config.json +13 -0
  32. continuous/qwen25/pe_core_l14_336/finetune/merges.txt +0 -0
  33. continuous/qwen25/pe_core_l14_336/finetune/model.safetensors +3 -0
  34. continuous/qwen25/pe_core_l14_336/finetune/special_tokens_map.json +31 -0
  35. continuous/qwen25/pe_core_l14_336/finetune/tokenizer.json +3 -0
  36. continuous/qwen25/pe_core_l14_336/finetune/tokenizer_config.json +208 -0
  37. continuous/qwen25/pe_core_l14_336/finetune/trainer_state.json +1856 -0
  38. continuous/qwen25/pe_core_l14_336/finetune/training_args.bin +3 -0
  39. continuous/qwen25/pe_core_l14_336/finetune/vocab.json +0 -0
  40. continuous/qwen25/pe_core_l14_336/pretrain/config.json +87 -0
  41. continuous/qwen25/pe_core_l14_336/pretrain/mm_projector.bin +3 -0
  42. continuous/qwen25/pe_core_l14_336/pretrain/trainer_state.json +421 -0
  43. continuous/qwen25/pe_core_s16_384/finetune/added_tokens.json +24 -0
  44. continuous/qwen25/pe_core_s16_384/finetune/chat_template.jinja +54 -0
  45. continuous/qwen25/pe_core_s16_384/finetune/config.json +87 -0
  46. continuous/qwen25/pe_core_s16_384/finetune/generation_config.json +13 -0
  47. continuous/qwen25/pe_core_s16_384/finetune/merges.txt +0 -0
  48. continuous/qwen25/pe_core_s16_384/finetune/model.safetensors +3 -0
  49. continuous/qwen25/pe_core_s16_384/finetune/special_tokens_map.json +31 -0
  50. continuous/qwen25/pe_core_s16_384/finetune/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -75,3 +75,7 @@ continuous/qwen25/mc2_m16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=
75
  continuous/qwen25/mc2_s16_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
  continuous/qwen25/mc2_s16_224_mt5/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
  continuous/qwen25/mc2_s16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
75
  continuous/qwen25/mc2_s16_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
  continuous/qwen25/mc2_s16_224_mt5/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
  continuous/qwen25/mc2_s16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
+ continuous/qwen25/pe_core_b16_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
79
+ continuous/qwen25/pe_core_g14_448/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
80
+ continuous/qwen25/pe_core_l14_336/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
81
+ continuous/qwen25/pe_core_s16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
continuous/qwen25/pe_core_b16_224/finetune/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
+ }
continuous/qwen25/pe_core_b16_224/finetune/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
continuous/qwen25/pe_core_b16_224/finetune/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 8192,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
continuous/qwen25/pe_core_b16_224/finetune/trainer_state.json ADDED
@@ -0,0 +1,1856 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9999037443449803,
6
+ "eval_steps": 500,
7
+ "global_step": 2597,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.003850226200789296,
14
+ "grad_norm": 15.932648658752441,
15
+ "learning_rate": 1.153846153846154e-06,
16
+ "loss": 1.721,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.007700452401578592,
21
+ "grad_norm": 5.445934772491455,
22
+ "learning_rate": 2.435897435897436e-06,
23
+ "loss": 1.3569,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.01155067860236789,
28
+ "grad_norm": 3.56986927986145,
29
+ "learning_rate": 3.7179487179487184e-06,
30
+ "loss": 1.071,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.015400904803157185,
35
+ "grad_norm": 0.6619648933410645,
36
+ "learning_rate": 5e-06,
37
+ "loss": 0.934,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.019251131003946483,
42
+ "grad_norm": 0.386212021112442,
43
+ "learning_rate": 6.282051282051282e-06,
44
+ "loss": 0.9097,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.02310135720473578,
49
+ "grad_norm": 0.2914702296257019,
50
+ "learning_rate": 7.564102564102564e-06,
51
+ "loss": 0.865,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.026951583405525073,
56
+ "grad_norm": 0.2368481308221817,
57
+ "learning_rate": 8.846153846153847e-06,
58
+ "loss": 0.8408,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.03080180960631437,
63
+ "grad_norm": 0.2527359426021576,
64
+ "learning_rate": 9.999996111488723e-06,
65
+ "loss": 0.8482,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.034652035807103666,
70
+ "grad_norm": 0.22266840934753418,
71
+ "learning_rate": 9.999529497453782e-06,
72
+ "loss": 0.8285,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.038502262007892966,
77
+ "grad_norm": 0.24463927745819092,
78
+ "learning_rate": 9.998285264324193e-06,
79
+ "loss": 0.806,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.04235248820868226,
84
+ "grad_norm": 0.21206887066364288,
85
+ "learning_rate": 9.996263605626052e-06,
86
+ "loss": 0.7957,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.04620271440947156,
91
+ "grad_norm": 0.23455841839313507,
92
+ "learning_rate": 9.99346483580503e-06,
93
+ "loss": 0.8087,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.05005294061026085,
98
+ "grad_norm": 0.21884392201900482,
99
+ "learning_rate": 9.989889390177467e-06,
100
+ "loss": 0.7971,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.053903166811050146,
105
+ "grad_norm": 0.24236023426055908,
106
+ "learning_rate": 9.985537824862647e-06,
107
+ "loss": 0.7985,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.057753393011839446,
112
+ "grad_norm": 0.24751783907413483,
113
+ "learning_rate": 9.980410816696317e-06,
114
+ "loss": 0.7785,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.06160361921262874,
119
+ "grad_norm": 0.23768383264541626,
120
+ "learning_rate": 9.97450916312541e-06,
121
+ "loss": 0.7876,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.06545384541341803,
126
+ "grad_norm": 0.20772039890289307,
127
+ "learning_rate": 9.967833782084004e-06,
128
+ "loss": 0.7887,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.06930407161420733,
133
+ "grad_norm": 0.24322466552257538,
134
+ "learning_rate": 9.960385711850554e-06,
135
+ "loss": 0.8133,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.07315429781499663,
140
+ "grad_norm": 0.23069967329502106,
141
+ "learning_rate": 9.952166110886394e-06,
142
+ "loss": 0.8057,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.07700452401578593,
147
+ "grad_norm": 0.25517401099205017,
148
+ "learning_rate": 9.943176257655567e-06,
149
+ "loss": 0.7972,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.08085475021657522,
154
+ "grad_norm": 0.2196679562330246,
155
+ "learning_rate": 9.933417550425952e-06,
156
+ "loss": 0.7897,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.08470497641736452,
161
+ "grad_norm": 0.22724390029907227,
162
+ "learning_rate": 9.9228915070518e-06,
163
+ "loss": 0.7741,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.08855520261815382,
168
+ "grad_norm": 0.22490595281124115,
169
+ "learning_rate": 9.911599764737632e-06,
170
+ "loss": 0.7775,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.09240542881894312,
175
+ "grad_norm": 0.2303687185049057,
176
+ "learning_rate": 9.899544079783606e-06,
177
+ "loss": 0.771,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.0962556550197324,
182
+ "grad_norm": 0.23437826335430145,
183
+ "learning_rate": 9.886726327312338e-06,
184
+ "loss": 0.7866,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.1001058812205217,
189
+ "grad_norm": 0.2194032520055771,
190
+ "learning_rate": 9.87314850097724e-06,
191
+ "loss": 0.785,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.103956107421311,
196
+ "grad_norm": 0.22213797271251678,
197
+ "learning_rate": 9.858812712652452e-06,
198
+ "loss": 0.7737,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.10780633362210029,
203
+ "grad_norm": 0.21684154868125916,
204
+ "learning_rate": 9.843721192104341e-06,
205
+ "loss": 0.7725,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.11165655982288959,
210
+ "grad_norm": 0.22000086307525635,
211
+ "learning_rate": 9.827876286644698e-06,
212
+ "loss": 0.7925,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.11550678602367889,
217
+ "grad_norm": 0.21316953003406525,
218
+ "learning_rate": 9.811280460765643e-06,
219
+ "loss": 0.7548,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.11935701222446819,
224
+ "grad_norm": 0.22485332190990448,
225
+ "learning_rate": 9.793936295756292e-06,
226
+ "loss": 0.7616,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.12320723842525748,
231
+ "grad_norm": 0.22272515296936035,
232
+ "learning_rate": 9.775846489301279e-06,
233
+ "loss": 0.7695,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.12705746462604678,
238
+ "grad_norm": 0.22629159688949585,
239
+ "learning_rate": 9.757013855061157e-06,
240
+ "loss": 0.7658,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.13090769082683607,
245
+ "grad_norm": 0.22487622499465942,
246
+ "learning_rate": 9.737441322234758e-06,
247
+ "loss": 0.7783,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.13475791702762538,
252
+ "grad_norm": 0.23078761994838715,
253
+ "learning_rate": 9.717131935103605e-06,
254
+ "loss": 0.7791,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.13860814322841467,
259
+ "grad_norm": 0.22894033789634705,
260
+ "learning_rate": 9.696088852558398e-06,
261
+ "loss": 0.764,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.14245836942920398,
266
+ "grad_norm": 0.22055217623710632,
267
+ "learning_rate": 9.674315347607686e-06,
268
+ "loss": 0.7907,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.14630859562999327,
273
+ "grad_norm": 0.2210051566362381,
274
+ "learning_rate": 9.651814806868796e-06,
275
+ "loss": 0.7561,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.15015882183078255,
280
+ "grad_norm": 0.23582284152507782,
281
+ "learning_rate": 9.62859073004107e-06,
282
+ "loss": 0.7569,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.15400904803157187,
287
+ "grad_norm": 0.20009511709213257,
288
+ "learning_rate": 9.604646729361547e-06,
289
+ "loss": 0.7605,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.15785927423236115,
294
+ "grad_norm": 0.2152101993560791,
295
+ "learning_rate": 9.579986529043099e-06,
296
+ "loss": 0.7521,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.16170950043315044,
301
+ "grad_norm": 0.2165537029504776,
302
+ "learning_rate": 9.554613964695189e-06,
303
+ "loss": 0.7686,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.16555972663393975,
308
+ "grad_norm": 0.22070623934268951,
309
+ "learning_rate": 9.528532982727281e-06,
310
+ "loss": 0.7622,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.16940995283472904,
315
+ "grad_norm": 0.20777498185634613,
316
+ "learning_rate": 9.501747639735018e-06,
317
+ "loss": 0.7578,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.17326017903551832,
322
+ "grad_norm": 0.22221443057060242,
323
+ "learning_rate": 9.474262101869272e-06,
324
+ "loss": 0.7473,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.17711040523630764,
329
+ "grad_norm": 0.2218913584947586,
330
+ "learning_rate": 9.446080644188141e-06,
331
+ "loss": 0.7527,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.18096063143709692,
336
+ "grad_norm": 0.20985344052314758,
337
+ "learning_rate": 9.417207649992017e-06,
338
+ "loss": 0.7579,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.18481085763788624,
343
+ "grad_norm": 0.21729516983032227,
344
+ "learning_rate": 9.387647610141816e-06,
345
+ "loss": 0.7569,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.18866108383867553,
350
+ "grad_norm": 0.20086634159088135,
351
+ "learning_rate": 9.35740512236047e-06,
352
+ "loss": 0.7461,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.1925113100394648,
357
+ "grad_norm": 0.20299090445041656,
358
+ "learning_rate": 9.326484890517809e-06,
359
+ "loss": 0.7558,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.19636153624025413,
364
+ "grad_norm": 0.21984419226646423,
365
+ "learning_rate": 9.294891723898926e-06,
366
+ "loss": 0.7453,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.2002117624410434,
371
+ "grad_norm": 0.2308613657951355,
372
+ "learning_rate": 9.262630536456153e-06,
373
+ "loss": 0.7756,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.2040619886418327,
378
+ "grad_norm": 0.22640790045261383,
379
+ "learning_rate": 9.229706346044749e-06,
380
+ "loss": 0.7506,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.207912214842622,
385
+ "grad_norm": 0.2315797656774521,
386
+ "learning_rate": 9.196124273642422e-06,
387
+ "loss": 0.7598,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.2117624410434113,
392
+ "grad_norm": 0.21840378642082214,
393
+ "learning_rate": 9.161889542552842e-06,
394
+ "loss": 0.7666,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.21561266724420058,
399
+ "grad_norm": 0.2080698013305664,
400
+ "learning_rate": 9.127007477593193e-06,
401
+ "loss": 0.7657,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.2194628934449899,
406
+ "grad_norm": 0.23232385516166687,
407
+ "learning_rate": 9.091483504265974e-06,
408
+ "loss": 0.7744,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.22331311964577918,
413
+ "grad_norm": 0.22780568897724152,
414
+ "learning_rate": 9.055323147915116e-06,
415
+ "loss": 0.7539,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.2271633458465685,
420
+ "grad_norm": 0.22133058309555054,
421
+ "learning_rate": 9.018532032866585e-06,
422
+ "loss": 0.7634,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.23101357204735778,
427
+ "grad_norm": 0.21444444358348846,
428
+ "learning_rate": 8.981115881553579e-06,
429
+ "loss": 0.757,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.23486379824814707,
434
+ "grad_norm": 0.22593992948532104,
435
+ "learning_rate": 8.943080513626476e-06,
436
+ "loss": 0.7762,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.23871402444893638,
441
+ "grad_norm": 0.21888867020606995,
442
+ "learning_rate": 8.904431845047641e-06,
443
+ "loss": 0.7618,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.24256425064972567,
448
+ "grad_norm": 0.2261175662279129,
449
+ "learning_rate": 8.86517588717128e-06,
450
+ "loss": 0.7774,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.24641447685051496,
455
+ "grad_norm": 0.21065379679203033,
456
+ "learning_rate": 8.82531874580844e-06,
457
+ "loss": 0.7706,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.25026470305130427,
462
+ "grad_norm": 0.19750933349132538,
463
+ "learning_rate": 8.784866620277314e-06,
464
+ "loss": 0.7274,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.25411492925209356,
469
+ "grad_norm": 0.23169691860675812,
470
+ "learning_rate": 8.743825802439018e-06,
471
+ "loss": 0.7579,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.25796515545288284,
476
+ "grad_norm": 0.23364432156085968,
477
+ "learning_rate": 8.702202675718956e-06,
478
+ "loss": 0.7681,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.26181538165367213,
483
+ "grad_norm": 0.20905442535877228,
484
+ "learning_rate": 8.660003714113959e-06,
485
+ "loss": 0.7347,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.26566560785446147,
490
+ "grad_norm": 0.21464502811431885,
491
+ "learning_rate": 8.617235481185323e-06,
492
+ "loss": 0.7566,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.26951583405525076,
497
+ "grad_norm": 0.22347243130207062,
498
+ "learning_rate": 8.573904629037931e-06,
499
+ "loss": 0.7637,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.27336606025604004,
504
+ "grad_norm": 0.21247273683547974,
505
+ "learning_rate": 8.530017897285585e-06,
506
+ "loss": 0.7471,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.27721628645682933,
511
+ "grad_norm": 0.19698558747768402,
512
+ "learning_rate": 8.485582112002746e-06,
513
+ "loss": 0.7538,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.2810665126576186,
518
+ "grad_norm": 0.2150079607963562,
519
+ "learning_rate": 8.440604184662811e-06,
520
+ "loss": 0.7536,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.28491673885840796,
525
+ "grad_norm": 0.22130756080150604,
526
+ "learning_rate": 8.395091111063118e-06,
527
+ "loss": 0.7448,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.28876696505919724,
532
+ "grad_norm": 0.20307685434818268,
533
+ "learning_rate": 8.349049970236822e-06,
534
+ "loss": 0.7432,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.29261719125998653,
539
+ "grad_norm": 0.21923643350601196,
540
+ "learning_rate": 8.302487923351842e-06,
541
+ "loss": 0.7345,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.2964674174607758,
546
+ "grad_norm": 0.21253342926502228,
547
+ "learning_rate": 8.255412212597021e-06,
548
+ "loss": 0.7547,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.3003176436615651,
553
+ "grad_norm": 0.21030797064304352,
554
+ "learning_rate": 8.207830160055688e-06,
555
+ "loss": 0.751,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.3041678698623544,
560
+ "grad_norm": 0.2187235802412033,
561
+ "learning_rate": 8.159749166566786e-06,
562
+ "loss": 0.7367,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.30801809606314373,
567
+ "grad_norm": 0.20887960493564606,
568
+ "learning_rate": 8.11117671057377e-06,
569
+ "loss": 0.7618,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.311868322263933,
574
+ "grad_norm": 0.22646799683570862,
575
+ "learning_rate": 8.062120346961404e-06,
576
+ "loss": 0.7526,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.3157185484647223,
581
+ "grad_norm": 0.20481322705745697,
582
+ "learning_rate": 8.012587705880705e-06,
583
+ "loss": 0.7491,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.3195687746655116,
588
+ "grad_norm": 0.2116325944662094,
589
+ "learning_rate": 7.962586491562146e-06,
590
+ "loss": 0.735,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.3234190008663009,
595
+ "grad_norm": 0.22848431766033173,
596
+ "learning_rate": 7.912124481117357e-06,
597
+ "loss": 0.7389,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.3272692270670902,
602
+ "grad_norm": 0.21664942800998688,
603
+ "learning_rate": 7.861209523329494e-06,
604
+ "loss": 0.7547,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.3311194532678795,
609
+ "grad_norm": 0.2150033861398697,
610
+ "learning_rate": 7.809849537432432e-06,
611
+ "loss": 0.7357,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.3349696794686688,
616
+ "grad_norm": 0.2142949253320694,
617
+ "learning_rate": 7.758052511879035e-06,
618
+ "loss": 0.7465,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.3388199056694581,
623
+ "grad_norm": 0.20102286338806152,
624
+ "learning_rate": 7.705826503098642e-06,
625
+ "loss": 0.74,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.34267013187024736,
630
+ "grad_norm": 0.20870764553546906,
631
+ "learning_rate": 7.653179634243979e-06,
632
+ "loss": 0.7426,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.34652035807103665,
637
+ "grad_norm": 0.20469748973846436,
638
+ "learning_rate": 7.600120093927696e-06,
639
+ "loss": 0.7437,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.350370584271826,
644
+ "grad_norm": 0.22269542515277863,
645
+ "learning_rate": 7.546656134948729e-06,
646
+ "loss": 0.7286,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.3542208104726153,
651
+ "grad_norm": 0.2120954394340515,
652
+ "learning_rate": 7.492796073008661e-06,
653
+ "loss": 0.733,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.35807103667340456,
658
+ "grad_norm": 0.22881487011909485,
659
+ "learning_rate": 7.438548285418326e-06,
660
+ "loss": 0.722,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.36192126287419385,
665
+ "grad_norm": 0.24415983259677887,
666
+ "learning_rate": 7.3839212097948e-06,
667
+ "loss": 0.7542,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.36577148907498314,
672
+ "grad_norm": 0.2219870388507843,
673
+ "learning_rate": 7.328923342749039e-06,
674
+ "loss": 0.7709,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.3696217152757725,
679
+ "grad_norm": 0.22693270444869995,
680
+ "learning_rate": 7.273563238564319e-06,
681
+ "loss": 0.7566,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.37347194147656176,
686
+ "grad_norm": 0.21512608230113983,
687
+ "learning_rate": 7.217849507865724e-06,
688
+ "loss": 0.7326,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.37732216767735105,
693
+ "grad_norm": 0.21215364336967468,
694
+ "learning_rate": 7.161790816280858e-06,
695
+ "loss": 0.7414,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.38117239387814034,
700
+ "grad_norm": 0.22566629946231842,
701
+ "learning_rate": 7.1053958830920125e-06,
702
+ "loss": 0.7208,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.3850226200789296,
707
+ "grad_norm": 0.21276669204235077,
708
+ "learning_rate": 7.0486734798799715e-06,
709
+ "loss": 0.7411,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.3888728462797189,
714
+ "grad_norm": 0.20882049202919006,
715
+ "learning_rate": 6.991632429159708e-06,
716
+ "loss": 0.7651,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.39272307248050825,
721
+ "grad_norm": 0.23090042173862457,
722
+ "learning_rate": 6.934281603008132e-06,
723
+ "loss": 0.7552,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.39657329868129754,
728
+ "grad_norm": 0.20838959515094757,
729
+ "learning_rate": 6.876629921684143e-06,
730
+ "loss": 0.7537,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.4004235248820868,
735
+ "grad_norm": 0.21868503093719482,
736
+ "learning_rate": 6.818686352241199e-06,
737
+ "loss": 0.7433,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.4042737510828761,
742
+ "grad_norm": 0.19816556572914124,
743
+ "learning_rate": 6.760459907132573e-06,
744
+ "loss": 0.7408,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.4081239772836654,
749
+ "grad_norm": 0.1963321566581726,
750
+ "learning_rate": 6.701959642809589e-06,
751
+ "loss": 0.7445,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.41197420348445474,
756
+ "grad_norm": 0.21453474462032318,
757
+ "learning_rate": 6.643194658312987e-06,
758
+ "loss": 0.7332,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.415824429685244,
763
+ "grad_norm": 0.21382677555084229,
764
+ "learning_rate": 6.584174093857676e-06,
765
+ "loss": 0.7599,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.4196746558860333,
770
+ "grad_norm": 0.23023217916488647,
771
+ "learning_rate": 6.5249071294110735e-06,
772
+ "loss": 0.7435,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.4235248820868226,
777
+ "grad_norm": 0.215740367770195,
778
+ "learning_rate": 6.465402983265274e-06,
779
+ "loss": 0.7581,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.4273751082876119,
784
+ "grad_norm": 0.21848347783088684,
785
+ "learning_rate": 6.405670910603243e-06,
786
+ "loss": 0.7531,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.43122533448840117,
791
+ "grad_norm": 0.2294517457485199,
792
+ "learning_rate": 6.345720202059291e-06,
793
+ "loss": 0.7494,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.4350755606891905,
798
+ "grad_norm": 0.2156561017036438,
799
+ "learning_rate": 6.285560182274008e-06,
800
+ "loss": 0.7263,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.4389257868899798,
805
+ "grad_norm": 0.20885002613067627,
806
+ "learning_rate": 6.225200208443936e-06,
807
+ "loss": 0.7501,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.4427760130907691,
812
+ "grad_norm": 0.20687836408615112,
813
+ "learning_rate": 6.16464966886616e-06,
814
+ "loss": 0.7387,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.44662623929155837,
819
+ "grad_norm": 0.25087615847587585,
820
+ "learning_rate": 6.103917981478065e-06,
821
+ "loss": 0.7642,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.45047646549234766,
826
+ "grad_norm": 0.21338105201721191,
827
+ "learning_rate": 6.043014592392489e-06,
828
+ "loss": 0.7738,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.454326691693137,
833
+ "grad_norm": 0.20158855617046356,
834
+ "learning_rate": 5.981948974428485e-06,
835
+ "loss": 0.7473,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.4581769178939263,
840
+ "grad_norm": 0.2190813571214676,
841
+ "learning_rate": 5.920730625637934e-06,
842
+ "loss": 0.7255,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.46202714409471557,
847
+ "grad_norm": 0.22716295719146729,
848
+ "learning_rate": 5.8593690678282355e-06,
849
+ "loss": 0.7403,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.46587737029550486,
854
+ "grad_norm": 0.22628115117549896,
855
+ "learning_rate": 5.797873845081301e-06,
856
+ "loss": 0.7427,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.46972759649629414,
861
+ "grad_norm": 0.21491706371307373,
862
+ "learning_rate": 5.736254522269075e-06,
863
+ "loss": 0.7581,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.47357782269708343,
868
+ "grad_norm": 0.2106267660856247,
869
+ "learning_rate": 5.6745206835658386e-06,
870
+ "loss": 0.7624,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.47742804889787277,
875
+ "grad_norm": 0.2036954164505005,
876
+ "learning_rate": 5.612681930957495e-06,
877
+ "loss": 0.7308,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.48127827509866206,
882
+ "grad_norm": 0.20300213992595673,
883
+ "learning_rate": 5.550747882748095e-06,
884
+ "loss": 0.7274,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.48512850129945134,
889
+ "grad_norm": 0.23043978214263916,
890
+ "learning_rate": 5.4887281720638195e-06,
891
+ "loss": 0.7405,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.48897872750024063,
896
+ "grad_norm": 0.23930388689041138,
897
+ "learning_rate": 5.42663244535466e-06,
898
+ "loss": 0.7204,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.4928289537010299,
903
+ "grad_norm": 0.21923625469207764,
904
+ "learning_rate": 5.3644703608940205e-06,
905
+ "loss": 0.7312,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.49667917990181926,
910
+ "grad_norm": 0.22051626443862915,
911
+ "learning_rate": 5.302251587276491e-06,
912
+ "loss": 0.7403,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.5005294061026085,
917
+ "grad_norm": 0.2076631337404251,
918
+ "learning_rate": 5.2399858019140005e-06,
919
+ "loss": 0.7425,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.5043796323033978,
924
+ "grad_norm": 0.20484495162963867,
925
+ "learning_rate": 5.177682689530615e-06,
926
+ "loss": 0.7555,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.5082298585041871,
931
+ "grad_norm": 0.2195906788110733,
932
+ "learning_rate": 5.11535194065619e-06,
933
+ "loss": 0.7241,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.5120800847049765,
938
+ "grad_norm": 0.23852989077568054,
939
+ "learning_rate": 5.053003250119113e-06,
940
+ "loss": 0.7319,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.5159303109057657,
945
+ "grad_norm": 0.22056062519550323,
946
+ "learning_rate": 4.9906463155383925e-06,
947
+ "loss": 0.741,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.519780537106555,
952
+ "grad_norm": 0.21421228349208832,
953
+ "learning_rate": 4.9282908358153046e-06,
954
+ "loss": 0.736,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.5236307633073443,
959
+ "grad_norm": 0.2394324094057083,
960
+ "learning_rate": 4.8659465096248345e-06,
961
+ "loss": 0.7507,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.5274809895081336,
966
+ "grad_norm": 0.22187286615371704,
967
+ "learning_rate": 4.803623033907169e-06,
968
+ "loss": 0.7458,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.5313312157089229,
973
+ "grad_norm": 0.20707815885543823,
974
+ "learning_rate": 4.741330102359441e-06,
975
+ "loss": 0.7558,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.5351814419097122,
980
+ "grad_norm": 0.23025839030742645,
981
+ "learning_rate": 4.679077403927996e-06,
982
+ "loss": 0.7341,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.5390316681105015,
987
+ "grad_norm": 0.2094666063785553,
988
+ "learning_rate": 4.616874621301373e-06,
989
+ "loss": 0.735,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.5428818943112907,
994
+ "grad_norm": 0.2274055927991867,
995
+ "learning_rate": 4.554731429404293e-06,
996
+ "loss": 0.751,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.5467321205120801,
1001
+ "grad_norm": 0.22626498341560364,
1002
+ "learning_rate": 4.492657493892822e-06,
1003
+ "loss": 0.7323,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.5505823467128694,
1008
+ "grad_norm": 0.2288290411233902,
1009
+ "learning_rate": 4.430662469650999e-06,
1010
+ "loss": 0.7491,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.5544325729136587,
1015
+ "grad_norm": 0.22458694875240326,
1016
+ "learning_rate": 4.368755999289118e-06,
1017
+ "loss": 0.7552,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.558282799114448,
1022
+ "grad_norm": 0.22694316506385803,
1023
+ "learning_rate": 4.306947711643949e-06,
1024
+ "loss": 0.733,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.5621330253152372,
1029
+ "grad_norm": 0.22429995238780975,
1030
+ "learning_rate": 4.245247220281068e-06,
1031
+ "loss": 0.7406,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.5659832515160266,
1036
+ "grad_norm": 0.20867669582366943,
1037
+ "learning_rate": 4.183664121999587e-06,
1038
+ "loss": 0.7348,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.5698334777168159,
1043
+ "grad_norm": 0.2284485101699829,
1044
+ "learning_rate": 4.122207995339474e-06,
1045
+ "loss": 0.7324,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.5736837039176051,
1050
+ "grad_norm": 0.2093874216079712,
1051
+ "learning_rate": 4.060888399091734e-06,
1052
+ "loss": 0.7389,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.5775339301183945,
1057
+ "grad_norm": 0.20862643420696259,
1058
+ "learning_rate": 3.999714870811639e-06,
1059
+ "loss": 0.7507,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.5813841563191837,
1064
+ "grad_norm": 0.21143025159835815,
1065
+ "learning_rate": 3.938696925335275e-06,
1066
+ "loss": 0.7418,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.5852343825199731,
1071
+ "grad_norm": 0.21554864943027496,
1072
+ "learning_rate": 3.87784405329962e-06,
1073
+ "loss": 0.7503,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.5890846087207623,
1078
+ "grad_norm": 0.21345093846321106,
1079
+ "learning_rate": 3.817165719666382e-06,
1080
+ "loss": 0.75,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.5929348349215516,
1085
+ "grad_norm": 0.21044158935546875,
1086
+ "learning_rate": 3.756671362249841e-06,
1087
+ "loss": 0.7572,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.596785061122341,
1092
+ "grad_norm": 0.21203948557376862,
1093
+ "learning_rate": 3.6963703902488907e-06,
1094
+ "loss": 0.7418,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.6006352873231302,
1099
+ "grad_norm": 0.20670557022094727,
1100
+ "learning_rate": 3.6362721827835655e-06,
1101
+ "loss": 0.7543,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.6044855135239195,
1106
+ "grad_norm": 0.22738444805145264,
1107
+ "learning_rate": 3.576386087436212e-06,
1108
+ "loss": 0.7533,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.6083357397247088,
1113
+ "grad_norm": 0.22929948568344116,
1114
+ "learning_rate": 3.5167214187975913e-06,
1115
+ "loss": 0.7448,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.6121859659254981,
1120
+ "grad_norm": 0.18887080252170563,
1121
+ "learning_rate": 3.457287457018086e-06,
1122
+ "loss": 0.7452,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.6160361921262875,
1127
+ "grad_norm": 0.2057100087404251,
1128
+ "learning_rate": 3.3980934463643003e-06,
1129
+ "loss": 0.736,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.6198864183270767,
1134
+ "grad_norm": 0.20391926169395447,
1135
+ "learning_rate": 3.3391485937812053e-06,
1136
+ "loss": 0.7159,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.623736644527866,
1141
+ "grad_norm": 0.21577982604503632,
1142
+ "learning_rate": 3.280462067460115e-06,
1143
+ "loss": 0.7156,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.6275868707286553,
1148
+ "grad_norm": 0.21281744539737701,
1149
+ "learning_rate": 3.222042995412669e-06,
1150
+ "loss": 0.7469,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.6314370969294446,
1155
+ "grad_norm": 0.19039955735206604,
1156
+ "learning_rate": 3.163900464051089e-06,
1157
+ "loss": 0.7342,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.635287323130234,
1162
+ "grad_norm": 0.21983614563941956,
1163
+ "learning_rate": 3.1060435167748826e-06,
1164
+ "loss": 0.7467,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.6391375493310232,
1169
+ "grad_norm": 0.21256189048290253,
1170
+ "learning_rate": 3.048481152564253e-06,
1171
+ "loss": 0.7268,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.6429877755318125,
1176
+ "grad_norm": 0.22715967893600464,
1177
+ "learning_rate": 2.9912223245804017e-06,
1178
+ "loss": 0.7493,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.6468380017326018,
1183
+ "grad_norm": 0.22424647212028503,
1184
+ "learning_rate": 2.934275938772981e-06,
1185
+ "loss": 0.742,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.6506882279333911,
1190
+ "grad_norm": 0.22474314272403717,
1191
+ "learning_rate": 2.8776508524948676e-06,
1192
+ "loss": 0.7328,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.6545384541341804,
1197
+ "grad_norm": 0.19397254288196564,
1198
+ "learning_rate": 2.821355873124503e-06,
1199
+ "loss": 0.7305,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.6583886803349697,
1204
+ "grad_norm": 0.2161148339509964,
1205
+ "learning_rate": 2.7653997566960144e-06,
1206
+ "loss": 0.7445,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.662238906535759,
1211
+ "grad_norm": 0.21926622092723846,
1212
+ "learning_rate": 2.709791206537309e-06,
1213
+ "loss": 0.7353,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.6660891327365482,
1218
+ "grad_norm": 0.21705017983913422,
1219
+ "learning_rate": 2.6545388719163747e-06,
1220
+ "loss": 0.7366,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.6699393589373376,
1225
+ "grad_norm": 0.21734753251075745,
1226
+ "learning_rate": 2.599651346695979e-06,
1227
+ "loss": 0.7383,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.6737895851381268,
1232
+ "grad_norm": 0.20460210740566254,
1233
+ "learning_rate": 2.545137167997007e-06,
1234
+ "loss": 0.7378,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.6776398113389162,
1239
+ "grad_norm": 0.20735082030296326,
1240
+ "learning_rate": 2.4910048148705972e-06,
1241
+ "loss": 0.7262,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.6814900375397055,
1246
+ "grad_norm": 0.22607006132602692,
1247
+ "learning_rate": 2.4372627069793327e-06,
1248
+ "loss": 0.77,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.6853402637404947,
1253
+ "grad_norm": 0.22636766731739044,
1254
+ "learning_rate": 2.3839192032876486e-06,
1255
+ "loss": 0.755,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.6891904899412841,
1260
+ "grad_norm": 0.21230876445770264,
1261
+ "learning_rate": 2.3309826007617047e-06,
1262
+ "loss": 0.7638,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.6930407161420733,
1267
+ "grad_norm": 0.21172498166561127,
1268
+ "learning_rate": 2.278461133078881e-06,
1269
+ "loss": 0.7269,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.6968909423428626,
1274
+ "grad_norm": 0.2245231419801712,
1275
+ "learning_rate": 2.2263629693471258e-06,
1276
+ "loss": 0.7205,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.700741168543652,
1281
+ "grad_norm": 0.2050289660692215,
1282
+ "learning_rate": 2.1746962128343414e-06,
1283
+ "loss": 0.7407,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.7045913947444412,
1288
+ "grad_norm": 0.21453888714313507,
1289
+ "learning_rate": 2.1234688997080183e-06,
1290
+ "loss": 0.7333,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.7084416209452306,
1295
+ "grad_norm": 0.22607402503490448,
1296
+ "learning_rate": 2.0726889977853053e-06,
1297
+ "loss": 0.7383,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.7122918471460198,
1302
+ "grad_norm": 0.2317328006029129,
1303
+ "learning_rate": 2.022364405293703e-06,
1304
+ "loss": 0.7496,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.7161420733468091,
1309
+ "grad_norm": 0.21129962801933289,
1310
+ "learning_rate": 1.9725029496425814e-06,
1311
+ "loss": 0.744,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.7199922995475985,
1316
+ "grad_norm": 0.1963067352771759,
1317
+ "learning_rate": 1.923112386205727e-06,
1318
+ "loss": 0.7378,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.7238425257483877,
1323
+ "grad_norm": 0.20696192979812622,
1324
+ "learning_rate": 1.874200397115079e-06,
1325
+ "loss": 0.7478,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.727692751949177,
1330
+ "grad_norm": 0.22158849239349365,
1331
+ "learning_rate": 1.825774590065857e-06,
1332
+ "loss": 0.7304,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.7315429781499663,
1337
+ "grad_norm": 0.22376036643981934,
1338
+ "learning_rate": 1.7778424971332813e-06,
1339
+ "loss": 0.7411,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.7353932043507556,
1344
+ "grad_norm": 0.20761944353580475,
1345
+ "learning_rate": 1.7304115736010407e-06,
1346
+ "loss": 0.7368,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.739243430551545,
1351
+ "grad_norm": 0.21293635666370392,
1352
+ "learning_rate": 1.6834891968017108e-06,
1353
+ "loss": 0.7336,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.7430936567523342,
1358
+ "grad_norm": 0.22416706383228302,
1359
+ "learning_rate": 1.6370826649692884e-06,
1360
+ "loss": 0.7458,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.7469438829531235,
1365
+ "grad_norm": 0.22242772579193115,
1366
+ "learning_rate": 1.5911991961040463e-06,
1367
+ "loss": 0.7546,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.7507941091539128,
1372
+ "grad_norm": 0.21888771653175354,
1373
+ "learning_rate": 1.545845926849851e-06,
1374
+ "loss": 0.7421,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.7546443353547021,
1379
+ "grad_norm": 0.22848762571811676,
1380
+ "learning_rate": 1.5010299113841397e-06,
1381
+ "loss": 0.7587,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.7584945615554913,
1386
+ "grad_norm": 0.21025928854942322,
1387
+ "learning_rate": 1.4567581203207238e-06,
1388
+ "loss": 0.7486,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.7623447877562807,
1393
+ "grad_norm": 0.22542546689510345,
1394
+ "learning_rate": 1.413037439625593e-06,
1395
+ "loss": 0.7475,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.76619501395707,
1400
+ "grad_norm": 0.2274562120437622,
1401
+ "learning_rate": 1.3698746695458847e-06,
1402
+ "loss": 0.7416,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.7700452401578592,
1407
+ "grad_norm": 0.21304059028625488,
1408
+ "learning_rate": 1.3272765235521745e-06,
1409
+ "loss": 0.7345,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.7738954663586486,
1414
+ "grad_norm": 0.21864274144172668,
1415
+ "learning_rate": 1.2852496272942877e-06,
1416
+ "loss": 0.7437,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.7777456925594378,
1421
+ "grad_norm": 0.20177558064460754,
1422
+ "learning_rate": 1.2438005175707396e-06,
1423
+ "loss": 0.7287,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.7815959187602272,
1428
+ "grad_norm": 0.2104826718568802,
1429
+ "learning_rate": 1.2029356413120297e-06,
1430
+ "loss": 0.7147,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.7854461449610165,
1435
+ "grad_norm": 0.21124134957790375,
1436
+ "learning_rate": 1.1626613545778786e-06,
1437
+ "loss": 0.7309,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.7892963711618057,
1442
+ "grad_norm": 0.20302768051624298,
1443
+ "learning_rate": 1.1229839215686294e-06,
1444
+ "loss": 0.7353,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.7931465973625951,
1449
+ "grad_norm": 0.19965875148773193,
1450
+ "learning_rate": 1.0839095136509188e-06,
1451
+ "loss": 0.7185,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.7969968235633843,
1456
+ "grad_norm": 0.2340506613254547,
1457
+ "learning_rate": 1.045444208397791e-06,
1458
+ "loss": 0.7398,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.8008470497641736,
1463
+ "grad_norm": 0.19919805228710175,
1464
+ "learning_rate": 1.007593988643402e-06,
1465
+ "loss": 0.7255,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.804697275964963,
1470
+ "grad_norm": 0.20575954020023346,
1471
+ "learning_rate": 9.703647415524613e-07,
1472
+ "loss": 0.7477,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.8085475021657522,
1477
+ "grad_norm": 0.21213339269161224,
1478
+ "learning_rate": 9.337622577045485e-07,
1479
+ "loss": 0.7341,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.8123977283665416,
1484
+ "grad_norm": 0.21631906926631927,
1485
+ "learning_rate": 8.977922301934588e-07,
1486
+ "loss": 0.7463,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.8162479545673308,
1491
+ "grad_norm": 0.21357570588588715,
1492
+ "learning_rate": 8.624602537417009e-07,
1493
+ "loss": 0.7472,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.8200981807681201,
1498
+ "grad_norm": 0.2297028750181198,
1499
+ "learning_rate": 8.277718238303123e-07,
1500
+ "loss": 0.7324,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.8239484069689095,
1505
+ "grad_norm": 0.21392296254634857,
1506
+ "learning_rate": 7.937323358440935e-07,
1507
+ "loss": 0.736,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.8277986331696987,
1512
+ "grad_norm": 0.23125675320625305,
1513
+ "learning_rate": 7.603470842324223e-07,
1514
+ "loss": 0.7259,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.831648859370488,
1519
+ "grad_norm": 0.2106177657842636,
1520
+ "learning_rate": 7.276212616857575e-07,
1521
+ "loss": 0.7459,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.8354990855712773,
1526
+ "grad_norm": 0.21089111268520355,
1527
+ "learning_rate": 6.955599583279837e-07,
1528
+ "loss": 0.7442,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.8393493117720666,
1533
+ "grad_norm": 0.20791761577129364,
1534
+ "learning_rate": 6.641681609246981e-07,
1535
+ "loss": 0.7377,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.8431995379728559,
1540
+ "grad_norm": 0.21828563511371613,
1541
+ "learning_rate": 6.334507521075711e-07,
1542
+ "loss": 0.7432,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.8470497641736452,
1547
+ "grad_norm": 0.22199754416942596,
1548
+ "learning_rate": 6.034125096149179e-07,
1549
+ "loss": 0.7398,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.8508999903744345,
1554
+ "grad_norm": 0.2126222401857376,
1555
+ "learning_rate": 5.740581055485722e-07,
1556
+ "loss": 0.7083,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.8547502165752238,
1561
+ "grad_norm": 0.20007187128067017,
1562
+ "learning_rate": 5.453921056471961e-07,
1563
+ "loss": 0.7427,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.8586004427760131,
1568
+ "grad_norm": 0.21432650089263916,
1569
+ "learning_rate": 5.174189685761288e-07,
1570
+ "loss": 0.7395,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.8624506689768023,
1575
+ "grad_norm": 0.20391327142715454,
1576
+ "learning_rate": 4.901430452338979e-07,
1577
+ "loss": 0.75,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.8663008951775917,
1582
+ "grad_norm": 0.20440144836902618,
1583
+ "learning_rate": 4.6356857807548286e-07,
1584
+ "loss": 0.7334,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.870151121378381,
1589
+ "grad_norm": 0.21394142508506775,
1590
+ "learning_rate": 4.376997004524541e-07,
1591
+ "loss": 0.7229,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.8740013475791703,
1596
+ "grad_norm": 0.21321547031402588,
1597
+ "learning_rate": 4.12540435970073e-07,
1598
+ "loss": 0.73,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.8778515737799596,
1603
+ "grad_norm": 0.21159252524375916,
1604
+ "learning_rate": 3.880946978614703e-07,
1605
+ "loss": 0.7441,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.8817017999807488,
1610
+ "grad_norm": 0.2123544067144394,
1611
+ "learning_rate": 3.643662883789878e-07,
1612
+ "loss": 0.7429,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.8855520261815382,
1617
+ "grad_norm": 0.19925038516521454,
1618
+ "learning_rate": 3.41358898202781e-07,
1619
+ "loss": 0.7245,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.8894022523823275,
1624
+ "grad_norm": 0.19873680174350739,
1625
+ "learning_rate": 3.190761058667741e-07,
1626
+ "loss": 0.7353,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.8932524785831167,
1631
+ "grad_norm": 0.208774134516716,
1632
+ "learning_rate": 2.9752137720206463e-07,
1633
+ "loss": 0.7395,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.8971027047839061,
1638
+ "grad_norm": 0.20910587906837463,
1639
+ "learning_rate": 2.7669806479785067e-07,
1640
+ "loss": 0.745,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.9009529309846953,
1645
+ "grad_norm": 0.21283988654613495,
1646
+ "learning_rate": 2.566094074799763e-07,
1647
+ "loss": 0.736,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.9048031571854847,
1652
+ "grad_norm": 0.2097628116607666,
1653
+ "learning_rate": 2.3725852980716557e-07,
1654
+ "loss": 0.7259,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.908653383386274,
1659
+ "grad_norm": 0.20725542306900024,
1660
+ "learning_rate": 2.1864844158503983e-07,
1661
+ "loss": 0.7325,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.9125036095870632,
1666
+ "grad_norm": 0.23242177069187164,
1667
+ "learning_rate": 2.007820373979702e-07,
1668
+ "loss": 0.7277,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.9163538357878526,
1673
+ "grad_norm": 0.21491439640522003,
1674
+ "learning_rate": 1.8366209615886532e-07,
1675
+ "loss": 0.7374,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.9202040619886418,
1680
+ "grad_norm": 0.21491259336471558,
1681
+ "learning_rate": 1.6729128067693613e-07,
1682
+ "loss": 0.7517,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.9240542881894311,
1687
+ "grad_norm": 0.22935597598552704,
1688
+ "learning_rate": 1.5167213724353426e-07,
1689
+ "loss": 0.7487,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.9279045143902205,
1694
+ "grad_norm": 0.20915105938911438,
1695
+ "learning_rate": 1.3680709523610058e-07,
1696
+ "loss": 0.7269,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.9317547405910097,
1701
+ "grad_norm": 0.21069851517677307,
1702
+ "learning_rate": 1.2269846674030418e-07,
1703
+ "loss": 0.7532,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.935604966791799,
1708
+ "grad_norm": 0.22361114621162415,
1709
+ "learning_rate": 1.0934844619042595e-07,
1710
+ "loss": 0.7483,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.9394551929925883,
1715
+ "grad_norm": 0.2213500440120697,
1716
+ "learning_rate": 9.675911002803961e-08,
1717
+ "loss": 0.7356,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.9433054191933776,
1722
+ "grad_norm": 0.2372669279575348,
1723
+ "learning_rate": 8.493241637904381e-08,
1724
+ "loss": 0.7331,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.9471556453941669,
1729
+ "grad_norm": 0.2121705710887909,
1730
+ "learning_rate": 7.387020474909689e-08,
1731
+ "loss": 0.7553,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.9510058715949562,
1736
+ "grad_norm": 0.23965048789978027,
1737
+ "learning_rate": 6.357419573750856e-08,
1738
+ "loss": 0.7492,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.9548560977957455,
1743
+ "grad_norm": 0.2116674929857254,
1744
+ "learning_rate": 5.4045990769613365e-08,
1745
+ "loss": 0.7295,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.9587063239965348,
1750
+ "grad_norm": 0.21433815360069275,
1751
+ "learning_rate": 4.5287071847694434e-08,
1752
+ "loss": 0.7354,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.9625565501973241,
1757
+ "grad_norm": 0.21182873845100403,
1758
+ "learning_rate": 3.7298801320467817e-08,
1759
+ "loss": 0.7355,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.9664067763981133,
1764
+ "grad_norm": 0.21423117816448212,
1765
+ "learning_rate": 3.0082421671192576e-08,
1766
+ "loss": 0.7272,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.9702570025989027,
1771
+ "grad_norm": 0.21191883087158203,
1772
+ "learning_rate": 2.3639055324410355e-08,
1773
+ "loss": 0.7483,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.974107228799692,
1778
+ "grad_norm": 0.21606358885765076,
1779
+ "learning_rate": 1.7969704471369477e-08,
1780
+ "loss": 0.7334,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.9779574550004813,
1785
+ "grad_norm": 0.2051563858985901,
1786
+ "learning_rate": 1.3075250914142413e-08,
1787
+ "loss": 0.7356,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.9818076812012706,
1792
+ "grad_norm": 0.20528455078601837,
1793
+ "learning_rate": 8.956455928476049e-09,
1794
+ "loss": 0.7437,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.9856579074020598,
1799
+ "grad_norm": 0.20655429363250732,
1800
+ "learning_rate": 5.6139601453786275e-09,
1801
+ "loss": 0.7349,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.9895081336028492,
1806
+ "grad_norm": 0.21022355556488037,
1807
+ "learning_rate": 3.0482834514805602e-09,
1808
+ "loss": 0.7259,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.9933583598036385,
1813
+ "grad_norm": 0.20769844949245453,
1814
+ "learning_rate": 1.2598249081713366e-09,
1815
+ "loss": 0.7149,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.9972085860044277,
1820
+ "grad_norm": 0.216297909617424,
1821
+ "learning_rate": 2.488626895302826e-10,
1822
+ "loss": 0.75,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.9999037443449803,
1827
+ "step": 2597,
1828
+ "total_flos": 3.537373145239388e+18,
1829
+ "train_loss": 0.7581706979800794,
1830
+ "train_runtime": 9882.1233,
1831
+ "train_samples_per_second": 67.283,
1832
+ "train_steps_per_second": 0.263
1833
+ }
1834
+ ],
1835
+ "logging_steps": 10,
1836
+ "max_steps": 2597,
1837
+ "num_input_tokens_seen": 418855352,
1838
+ "num_train_epochs": 1,
1839
+ "save_steps": 500,
1840
+ "stateful_callbacks": {
1841
+ "TrainerControl": {
1842
+ "args": {
1843
+ "should_epoch_stop": false,
1844
+ "should_evaluate": false,
1845
+ "should_log": false,
1846
+ "should_save": true,
1847
+ "should_training_stop": true
1848
+ },
1849
+ "attributes": {}
1850
+ }
1851
+ },
1852
+ "total_flos": 3.537373145239388e+18,
1853
+ "train_batch_size": 8,
1854
+ "trial_name": null,
1855
+ "trial_params": null
1856
+ }
continuous/qwen25/pe_core_b16_224/finetune/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff8611f0c9a89d904608556558c491c7ce817370f1cf7b1c30b9fa355ee376e
3
+ size 6264
continuous/qwen25/pe_core_b16_224/finetune/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
continuous/qwen25/pe_core_b16_224/pretrain/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_faster_video": false,
3
+ "add_time_instruction": false,
4
+ "architectures": [
5
+ "Qwen2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "faster_token_stride": 10,
11
+ "force_sample": false,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "image_aspect_ratio": "square",
15
+ "image_crop_resolution": null,
16
+ "image_grid_pinpoints": null,
17
+ "image_split_resolution": null,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8960,
20
+ "layer_types": [
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention"
49
+ ],
50
+ "max_position_embeddings": 32768,
51
+ "max_window_layers": 21,
52
+ "mm_hidden_size": 768,
53
+ "mm_newline_position": "grid",
54
+ "mm_patch_merge_type": "flat",
55
+ "mm_projector_lr": null,
56
+ "mm_projector_type": "mlp2x_gelu",
57
+ "mm_resampler_type": null,
58
+ "mm_spatial_pool_mode": "bilinear",
59
+ "mm_spatial_pool_stride": null,
60
+ "mm_tunable_parts": "mm_mlp_adapter",
61
+ "mm_use_im_patch_token": false,
62
+ "mm_use_im_start_end": false,
63
+ "mm_vision_select_feature": "patch",
64
+ "mm_vision_select_layer": -1,
65
+ "mm_vision_tower": "vtb_ssl:pe",
66
+ "mm_vision_tower_lr": null,
67
+ "model_type": "qwen2",
68
+ "num_attention_heads": 12,
69
+ "num_hidden_layers": 28,
70
+ "num_key_value_heads": 2,
71
+ "pad_token_id": 151643,
72
+ "pos_skipping_range": 4096,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": null,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_model_max_length": 8192,
79
+ "tokenizer_padding_side": "right",
80
+ "transformers_version": "4.57.6",
81
+ "use_cache": true,
82
+ "use_mm_proj": true,
83
+ "use_pos_skipping": false,
84
+ "use_sliding_window": false,
85
+ "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Core-B16-224/PE-Core-B16-224.pt",
86
+ "vocab_size": 151936
87
+ }
continuous/qwen25/pe_core_b16_224/pretrain/mm_projector.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743d1bdc940641f9a0f971859a8792c53927c46a939c6193a50dfef832f658a1
3
+ size 14170168
continuous/qwen25/pe_core_b16_224/pretrain/trainer_state.json ADDED
@@ -0,0 +1,421 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 545,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01834862385321101,
14
+ "grad_norm": 1.3910655975341797,
15
+ "learning_rate": 0.00032142857142857147,
16
+ "loss": 4.6749,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.03669724770642202,
21
+ "grad_norm": 0.7117429971694946,
22
+ "learning_rate": 0.0006785714285714287,
23
+ "loss": 3.7328,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.05504587155963303,
28
+ "grad_norm": 0.24122880399227142,
29
+ "learning_rate": 0.0009999907688176173,
30
+ "loss": 3.354,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.07339449541284404,
35
+ "grad_norm": 0.24885347485542297,
36
+ "learning_rate": 0.0009988834393115766,
37
+ "loss": 3.2585,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.09174311926605505,
42
+ "grad_norm": 0.1792614609003067,
43
+ "learning_rate": 0.0009959345572940772,
44
+ "loss": 3.2247,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.11009174311926606,
49
+ "grad_norm": 0.24738812446594238,
50
+ "learning_rate": 0.0009911550081155983,
51
+ "loss": 3.1888,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.12844036697247707,
56
+ "grad_norm": 0.25249892473220825,
57
+ "learning_rate": 0.0009845624347566433,
58
+ "loss": 3.1513,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.14678899082568808,
63
+ "grad_norm": 0.2237100601196289,
64
+ "learning_rate": 0.0009761811727013547,
65
+ "loss": 3.1225,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1651376146788991,
70
+ "grad_norm": 0.22574253380298615,
71
+ "learning_rate": 0.0009660421601067666,
72
+ "loss": 3.087,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.1834862385321101,
77
+ "grad_norm": 0.23696982860565186,
78
+ "learning_rate": 0.0009541828235992926,
79
+ "loss": 3.0655,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2018348623853211,
84
+ "grad_norm": 0.25150543451309204,
85
+ "learning_rate": 0.0009406469401200151,
86
+ "loss": 3.0333,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.22018348623853212,
91
+ "grad_norm": 0.2303459495306015,
92
+ "learning_rate": 0.0009254844753287492,
93
+ "loss": 3.0171,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.23853211009174313,
98
+ "grad_norm": 0.28809797763824463,
99
+ "learning_rate": 0.0009087513991633924,
100
+ "loss": 2.982,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.25688073394495414,
105
+ "grad_norm": 0.24291226267814636,
106
+ "learning_rate": 0.0008905094792353917,
107
+ "loss": 2.9642,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.27522935779816515,
112
+ "grad_norm": 0.3188406825065613,
113
+ "learning_rate": 0.0008708260528239789,
114
+ "loss": 2.9475,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.29357798165137616,
119
+ "grad_norm": 0.21053360402584076,
120
+ "learning_rate": 0.0008497737783108237,
121
+ "loss": 2.9243,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.3119266055045872,
126
+ "grad_norm": 0.21759405732154846,
127
+ "learning_rate": 0.0008274303669726426,
128
+ "loss": 2.9073,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.3302752293577982,
133
+ "grad_norm": 0.2321425974369049,
134
+ "learning_rate": 0.0008038782961218137,
135
+ "loss": 2.8826,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.3486238532110092,
140
+ "grad_norm": 0.24034686386585236,
141
+ "learning_rate": 0.000779204504653894,
142
+ "loss": 2.8705,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.3669724770642202,
147
+ "grad_norm": 0.2517447769641876,
148
+ "learning_rate": 0.0007535000721258791,
149
+ "loss": 2.8418,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.3853211009174312,
154
+ "grad_norm": 0.2415682077407837,
155
+ "learning_rate": 0.00072685988254984,
156
+ "loss": 2.8295,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.4036697247706422,
161
+ "grad_norm": 0.2795529067516327,
162
+ "learning_rate": 0.0006993822741429906,
163
+ "loss": 2.8338,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.42201834862385323,
168
+ "grad_norm": 0.20474667847156525,
169
+ "learning_rate": 0.0006711686763270818,
170
+ "loss": 2.8217,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.44036697247706424,
175
+ "grad_norm": 0.21257485449314117,
176
+ "learning_rate": 0.0006423232353170831,
177
+ "loss": 2.8059,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.45871559633027525,
182
+ "grad_norm": 0.21883709728717804,
183
+ "learning_rate": 0.0006129524296812335,
184
+ "loss": 2.7902,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.47706422018348627,
189
+ "grad_norm": 0.2371562272310257,
190
+ "learning_rate": 0.0005831646772915651,
191
+ "loss": 2.7958,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.4954128440366973,
196
+ "grad_norm": 0.22247716784477234,
197
+ "learning_rate": 0.0005530699351157809,
198
+ "loss": 2.7735,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.5137614678899083,
203
+ "grad_norm": 0.23495396971702576,
204
+ "learning_rate": 0.0005227792933277943,
205
+ "loss": 2.773,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.5321100917431193,
210
+ "grad_norm": 0.21318231523036957,
211
+ "learning_rate": 0.0004924045652352092,
212
+ "loss": 2.7533,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.5504587155963303,
217
+ "grad_norm": 0.2162557691335678,
218
+ "learning_rate": 0.0004620578745374633,
219
+ "loss": 2.7497,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.5688073394495413,
224
+ "grad_norm": 0.21728795766830444,
225
+ "learning_rate": 0.0004318512414382059,
226
+ "loss": 2.7564,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.5871559633027523,
231
+ "grad_norm": 0.21438634395599365,
232
+ "learning_rate": 0.0004018961691397148,
233
+ "loss": 2.7481,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.6055045871559633,
238
+ "grad_norm": 0.24966682493686676,
239
+ "learning_rate": 0.0003723032322457458,
240
+ "loss": 2.7267,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.6238532110091743,
245
+ "grad_norm": 0.25063520669937134,
246
+ "learning_rate": 0.0003431816685921625,
247
+ "loss": 2.7309,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.6422018348623854,
252
+ "grad_norm": 0.22486066818237305,
253
+ "learning_rate": 0.0003146389760120416,
254
+ "loss": 2.7294,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.6605504587155964,
259
+ "grad_norm": 0.245912566781044,
260
+ "learning_rate": 0.00028678051552373485,
261
+ "loss": 2.7283,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.6788990825688074,
266
+ "grad_norm": 0.22440475225448608,
267
+ "learning_rate": 0.0002597091224066581,
268
+ "loss": 2.7082,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.6972477064220184,
273
+ "grad_norm": 0.22488869726657867,
274
+ "learning_rate": 0.0002335247266004629,
275
+ "loss": 2.712,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.7155963302752294,
280
+ "grad_norm": 0.22090168297290802,
281
+ "learning_rate": 0.000208323983828828,
282
+ "loss": 2.6961,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.7339449541284404,
287
+ "grad_norm": 0.21457040309906006,
288
+ "learning_rate": 0.0001841999188095224,
289
+ "loss": 2.6845,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.7522935779816514,
294
+ "grad_norm": 0.21548748016357422,
295
+ "learning_rate": 0.00016124158186777676,
296
+ "loss": 2.6823,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.7706422018348624,
301
+ "grad_norm": 0.23832756280899048,
302
+ "learning_rate": 0.0001395337202205211,
303
+ "loss": 2.6745,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.7889908256880734,
308
+ "grad_norm": 0.22298657894134521,
309
+ "learning_rate": 0.00011915646514489292,
310
+ "loss": 2.6668,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.8073394495412844,
315
+ "grad_norm": 0.22177371382713318,
316
+ "learning_rate": 0.00010018503618578818,
317
+ "loss": 2.6747,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.8256880733944955,
322
+ "grad_norm": 0.22339899837970734,
323
+ "learning_rate": 8.268946349432583e-05,
324
+ "loss": 2.6675,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.8440366972477065,
329
+ "grad_norm": 0.22562147676944733,
330
+ "learning_rate": 6.673432932217117e-05,
331
+ "loss": 2.6545,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.8623853211009175,
336
+ "grad_norm": 0.22914426028728485,
337
+ "learning_rate": 5.2378529625954684e-05,
338
+ "loss": 2.6452,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.8807339449541285,
343
+ "grad_norm": 0.24230438470840454,
344
+ "learning_rate": 3.9675056661785556e-05,
345
+ "loss": 2.6507,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.8990825688073395,
350
+ "grad_norm": 0.2223258763551712,
351
+ "learning_rate": 2.8670803372379538e-05,
352
+ "loss": 2.656,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.9174311926605505,
357
+ "grad_norm": 0.22369270026683807,
358
+ "learning_rate": 1.9406390288876586e-05,
359
+ "loss": 2.6635,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.9357798165137615,
364
+ "grad_norm": 0.22927208244800568,
365
+ "learning_rate": 1.191601558631461e-05,
366
+ "loss": 2.6476,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.9541284403669725,
371
+ "grad_norm": 0.22284965217113495,
372
+ "learning_rate": 6.2273288462559305e-06,
373
+ "loss": 2.6458,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.9724770642201835,
378
+ "grad_norm": 0.21139664947986603,
379
+ "learning_rate": 2.361328992552314e-06,
380
+ "loss": 2.6466,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.9908256880733946,
385
+ "grad_norm": 0.22436881065368652,
386
+ "learning_rate": 3.322867770044202e-07,
387
+ "loss": 2.6467,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.0,
392
+ "step": 545,
393
+ "total_flos": 2.9042758800480666e+17,
394
+ "train_loss": 2.8794037407691326,
395
+ "train_runtime": 5280.8861,
396
+ "train_samples_per_second": 105.688,
397
+ "train_steps_per_second": 0.103
398
+ }
399
+ ],
400
+ "logging_steps": 10,
401
+ "max_steps": 545,
402
+ "num_input_tokens_seen": 34389120,
403
+ "num_train_epochs": 1,
404
+ "save_steps": 500,
405
+ "stateful_callbacks": {
406
+ "TrainerControl": {
407
+ "args": {
408
+ "should_epoch_stop": false,
409
+ "should_evaluate": false,
410
+ "should_log": false,
411
+ "should_save": false,
412
+ "should_training_stop": false
413
+ },
414
+ "attributes": {}
415
+ }
416
+ },
417
+ "total_flos": 2.9042758800480666e+17,
418
+ "train_batch_size": 128,
419
+ "trial_name": null,
420
+ "trial_params": null
421
+ }
continuous/qwen25/pe_core_g14_448/finetune/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
+ }
continuous/qwen25/pe_core_g14_448/finetune/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
continuous/qwen25/pe_core_g14_448/finetune/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_faster_video": false,
3
+ "add_time_instruction": false,
4
+ "architectures": [
5
+ "LlavaQwenForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "faster_token_stride": 10,
11
+ "force_sample": false,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "image_aspect_ratio": "square",
15
+ "image_crop_resolution": null,
16
+ "image_grid_pinpoints": null,
17
+ "image_split_resolution": null,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8960,
20
+ "layer_types": [
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention"
49
+ ],
50
+ "max_position_embeddings": 32768,
51
+ "max_window_layers": 21,
52
+ "mm_hidden_size": 1536,
53
+ "mm_newline_position": "grid",
54
+ "mm_patch_merge_type": "flat",
55
+ "mm_projector_lr": 0.0001,
56
+ "mm_projector_type": "mlp2x_gelu",
57
+ "mm_resampler_type": null,
58
+ "mm_spatial_pool_mode": "bilinear",
59
+ "mm_spatial_pool_stride": null,
60
+ "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
61
+ "mm_use_im_patch_token": false,
62
+ "mm_use_im_start_end": false,
63
+ "mm_vision_select_feature": "patch",
64
+ "mm_vision_select_layer": -1,
65
+ "mm_vision_tower": "vtb_ssl:pe",
66
+ "mm_vision_tower_lr": null,
67
+ "model_type": "qwen2",
68
+ "num_attention_heads": 12,
69
+ "num_hidden_layers": 28,
70
+ "num_key_value_heads": 2,
71
+ "pad_token_id": 151643,
72
+ "pos_skipping_range": 4096,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": null,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_model_max_length": 8192,
79
+ "tokenizer_padding_side": "right",
80
+ "transformers_version": "4.57.6",
81
+ "use_cache": true,
82
+ "use_mm_proj": true,
83
+ "use_pos_skipping": false,
84
+ "use_sliding_window": false,
85
+ "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Core-G14-448/PE-Core-G14-448.pt",
86
+ "vocab_size": 151936
87
+ }
continuous/qwen25/pe_core_g14_448/finetune/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.1,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.6"
13
+ }
continuous/qwen25/pe_core_g14_448/finetune/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
continuous/qwen25/pe_core_g14_448/finetune/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a15461f9597c8a762863c894ae5e4f6aa73917954c4f2845c4dd754f0cab7d
3
+ size 4992106384
continuous/qwen25/pe_core_g14_448/finetune/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed452abbb02ab81fe423e2255cec1141d0f73dbcb8ba471c6e25e087568c72ba
3
+ size 2345150920
continuous/qwen25/pe_core_g14_448/finetune/model.safetensors.index.json ADDED
@@ -0,0 +1,969 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 3430468608,
4
+ "total_size": 7337127936
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00002-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
346
+ "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
347
+ "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
348
+ "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
349
+ "model.norm.weight": "model-00001-of-00002.safetensors",
350
+ "model.vision_tower.vision_tower.attn_pool.attn.in_proj_bias": "model-00002-of-00002.safetensors",
351
+ "model.vision_tower.vision_tower.attn_pool.attn.in_proj_weight": "model-00002-of-00002.safetensors",
352
+ "model.vision_tower.vision_tower.attn_pool.attn.out_proj.bias": "model-00002-of-00002.safetensors",
353
+ "model.vision_tower.vision_tower.attn_pool.attn.out_proj.weight": "model-00002-of-00002.safetensors",
354
+ "model.vision_tower.vision_tower.attn_pool.layernorm.bias": "model-00002-of-00002.safetensors",
355
+ "model.vision_tower.vision_tower.attn_pool.layernorm.weight": "model-00002-of-00002.safetensors",
356
+ "model.vision_tower.vision_tower.attn_pool.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
357
+ "model.vision_tower.vision_tower.attn_pool.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
358
+ "model.vision_tower.vision_tower.attn_pool.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
359
+ "model.vision_tower.vision_tower.attn_pool.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.vision_tower.vision_tower.attn_pool.probe": "model-00002-of-00002.safetensors",
361
+ "model.vision_tower.vision_tower.conv1.weight": "model-00001-of-00002.safetensors",
362
+ "model.vision_tower.vision_tower.ln_post.bias": "model-00001-of-00002.safetensors",
363
+ "model.vision_tower.vision_tower.ln_post.weight": "model-00001-of-00002.safetensors",
364
+ "model.vision_tower.vision_tower.ln_pre.bias": "model-00001-of-00002.safetensors",
365
+ "model.vision_tower.vision_tower.ln_pre.weight": "model-00001-of-00002.safetensors",
366
+ "model.vision_tower.vision_tower.positional_embedding": "model-00001-of-00002.safetensors",
367
+ "model.vision_tower.vision_tower.proj": "model-00001-of-00002.safetensors",
368
+ "model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_bias": "model-00001-of-00002.safetensors",
369
+ "model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_weight": "model-00001-of-00002.safetensors",
370
+ "model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.bias": "model-00001-of-00002.safetensors",
371
+ "model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.bias": "model-00001-of-00002.safetensors",
373
+ "model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.weight": "model-00001-of-00002.safetensors",
374
+ "model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.bias": "model-00001-of-00002.safetensors",
375
+ "model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.weight": "model-00001-of-00002.safetensors",
376
+ "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
377
+ "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
378
+ "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
379
+ "model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_bias": "model-00001-of-00002.safetensors",
381
+ "model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_weight": "model-00001-of-00002.safetensors",
382
+ "model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.bias": "model-00001-of-00002.safetensors",
383
+ "model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.bias": "model-00001-of-00002.safetensors",
385
+ "model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.weight": "model-00001-of-00002.safetensors",
386
+ "model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.bias": "model-00001-of-00002.safetensors",
387
+ "model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.weight": "model-00001-of-00002.safetensors",
388
+ "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
389
+ "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
390
+ "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
391
+ "model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_bias": "model-00001-of-00002.safetensors",
393
+ "model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_weight": "model-00001-of-00002.safetensors",
394
+ "model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.bias": "model-00001-of-00002.safetensors",
395
+ "model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.bias": "model-00001-of-00002.safetensors",
397
+ "model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.weight": "model-00001-of-00002.safetensors",
398
+ "model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.bias": "model-00001-of-00002.safetensors",
399
+ "model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.weight": "model-00001-of-00002.safetensors",
400
+ "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
401
+ "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
402
+ "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
403
+ "model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_bias": "model-00001-of-00002.safetensors",
405
+ "model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_weight": "model-00001-of-00002.safetensors",
406
+ "model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.bias": "model-00001-of-00002.safetensors",
407
+ "model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.bias": "model-00001-of-00002.safetensors",
409
+ "model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.weight": "model-00001-of-00002.safetensors",
410
+ "model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.bias": "model-00001-of-00002.safetensors",
411
+ "model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.weight": "model-00001-of-00002.safetensors",
412
+ "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
413
+ "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
414
+ "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
415
+ "model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
416
+ "model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_bias": "model-00001-of-00002.safetensors",
417
+ "model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_weight": "model-00001-of-00002.safetensors",
418
+ "model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.bias": "model-00001-of-00002.safetensors",
419
+ "model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.bias": "model-00001-of-00002.safetensors",
421
+ "model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.weight": "model-00001-of-00002.safetensors",
422
+ "model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.bias": "model-00001-of-00002.safetensors",
423
+ "model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.weight": "model-00001-of-00002.safetensors",
424
+ "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
425
+ "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
426
+ "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
427
+ "model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
428
+ "model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_bias": "model-00001-of-00002.safetensors",
429
+ "model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_weight": "model-00001-of-00002.safetensors",
430
+ "model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.bias": "model-00001-of-00002.safetensors",
431
+ "model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.bias": "model-00001-of-00002.safetensors",
433
+ "model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.weight": "model-00001-of-00002.safetensors",
434
+ "model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.bias": "model-00001-of-00002.safetensors",
435
+ "model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.weight": "model-00001-of-00002.safetensors",
436
+ "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
437
+ "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
438
+ "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
439
+ "model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_bias": "model-00001-of-00002.safetensors",
441
+ "model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_weight": "model-00001-of-00002.safetensors",
442
+ "model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.bias": "model-00001-of-00002.safetensors",
443
+ "model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.bias": "model-00001-of-00002.safetensors",
445
+ "model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.weight": "model-00001-of-00002.safetensors",
446
+ "model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.bias": "model-00001-of-00002.safetensors",
447
+ "model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.weight": "model-00001-of-00002.safetensors",
448
+ "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
449
+ "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
450
+ "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
451
+ "model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
452
+ "model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_bias": "model-00001-of-00002.safetensors",
453
+ "model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_weight": "model-00001-of-00002.safetensors",
454
+ "model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.bias": "model-00001-of-00002.safetensors",
455
+ "model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
456
+ "model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.bias": "model-00001-of-00002.safetensors",
457
+ "model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.weight": "model-00001-of-00002.safetensors",
458
+ "model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.bias": "model-00001-of-00002.safetensors",
459
+ "model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.weight": "model-00001-of-00002.safetensors",
460
+ "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
461
+ "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
462
+ "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
463
+ "model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
464
+ "model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_bias": "model-00001-of-00002.safetensors",
465
+ "model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_weight": "model-00001-of-00002.safetensors",
466
+ "model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.bias": "model-00001-of-00002.safetensors",
467
+ "model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
468
+ "model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.bias": "model-00001-of-00002.safetensors",
469
+ "model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.weight": "model-00001-of-00002.safetensors",
470
+ "model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.bias": "model-00001-of-00002.safetensors",
471
+ "model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.weight": "model-00001-of-00002.safetensors",
472
+ "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
473
+ "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
474
+ "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
475
+ "model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
476
+ "model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_bias": "model-00001-of-00002.safetensors",
477
+ "model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_weight": "model-00001-of-00002.safetensors",
478
+ "model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.bias": "model-00001-of-00002.safetensors",
479
+ "model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
480
+ "model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.bias": "model-00001-of-00002.safetensors",
481
+ "model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.weight": "model-00001-of-00002.safetensors",
482
+ "model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.bias": "model-00001-of-00002.safetensors",
483
+ "model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.weight": "model-00001-of-00002.safetensors",
484
+ "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
485
+ "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
486
+ "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
487
+ "model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
488
+ "model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_bias": "model-00001-of-00002.safetensors",
489
+ "model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_weight": "model-00001-of-00002.safetensors",
490
+ "model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.bias": "model-00001-of-00002.safetensors",
491
+ "model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.weight": "model-00001-of-00002.safetensors",
492
+ "model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.bias": "model-00001-of-00002.safetensors",
493
+ "model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.weight": "model-00001-of-00002.safetensors",
494
+ "model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.bias": "model-00001-of-00002.safetensors",
495
+ "model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.weight": "model-00001-of-00002.safetensors",
496
+ "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
497
+ "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
498
+ "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
499
+ "model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
500
+ "model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_bias": "model-00001-of-00002.safetensors",
501
+ "model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_weight": "model-00001-of-00002.safetensors",
502
+ "model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.bias": "model-00001-of-00002.safetensors",
503
+ "model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.weight": "model-00001-of-00002.safetensors",
504
+ "model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.bias": "model-00001-of-00002.safetensors",
505
+ "model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.weight": "model-00001-of-00002.safetensors",
506
+ "model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.bias": "model-00001-of-00002.safetensors",
507
+ "model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.weight": "model-00001-of-00002.safetensors",
508
+ "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
509
+ "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
510
+ "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
511
+ "model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
512
+ "model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_bias": "model-00001-of-00002.safetensors",
513
+ "model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_weight": "model-00001-of-00002.safetensors",
514
+ "model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.bias": "model-00001-of-00002.safetensors",
515
+ "model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
516
+ "model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.bias": "model-00001-of-00002.safetensors",
517
+ "model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.weight": "model-00001-of-00002.safetensors",
518
+ "model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.bias": "model-00001-of-00002.safetensors",
519
+ "model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.weight": "model-00001-of-00002.safetensors",
520
+ "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
521
+ "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
522
+ "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
523
+ "model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
524
+ "model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_bias": "model-00001-of-00002.safetensors",
525
+ "model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_weight": "model-00001-of-00002.safetensors",
526
+ "model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.bias": "model-00001-of-00002.safetensors",
527
+ "model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.weight": "model-00001-of-00002.safetensors",
528
+ "model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.bias": "model-00001-of-00002.safetensors",
529
+ "model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.weight": "model-00001-of-00002.safetensors",
530
+ "model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.bias": "model-00001-of-00002.safetensors",
531
+ "model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.weight": "model-00001-of-00002.safetensors",
532
+ "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
533
+ "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
534
+ "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
535
+ "model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
536
+ "model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_bias": "model-00001-of-00002.safetensors",
537
+ "model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_weight": "model-00001-of-00002.safetensors",
538
+ "model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.bias": "model-00001-of-00002.safetensors",
539
+ "model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.weight": "model-00001-of-00002.safetensors",
540
+ "model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.bias": "model-00001-of-00002.safetensors",
541
+ "model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.weight": "model-00001-of-00002.safetensors",
542
+ "model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.bias": "model-00001-of-00002.safetensors",
543
+ "model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.weight": "model-00001-of-00002.safetensors",
544
+ "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
545
+ "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
546
+ "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
547
+ "model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
548
+ "model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_bias": "model-00001-of-00002.safetensors",
549
+ "model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_weight": "model-00001-of-00002.safetensors",
550
+ "model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.bias": "model-00001-of-00002.safetensors",
551
+ "model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.weight": "model-00001-of-00002.safetensors",
552
+ "model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.bias": "model-00001-of-00002.safetensors",
553
+ "model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.weight": "model-00001-of-00002.safetensors",
554
+ "model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.bias": "model-00001-of-00002.safetensors",
555
+ "model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.weight": "model-00001-of-00002.safetensors",
556
+ "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
557
+ "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
558
+ "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
559
+ "model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
560
+ "model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_bias": "model-00001-of-00002.safetensors",
561
+ "model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_weight": "model-00001-of-00002.safetensors",
562
+ "model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.bias": "model-00001-of-00002.safetensors",
563
+ "model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.weight": "model-00001-of-00002.safetensors",
564
+ "model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.bias": "model-00001-of-00002.safetensors",
565
+ "model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.weight": "model-00001-of-00002.safetensors",
566
+ "model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.bias": "model-00001-of-00002.safetensors",
567
+ "model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.weight": "model-00001-of-00002.safetensors",
568
+ "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
569
+ "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
570
+ "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
571
+ "model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
572
+ "model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_bias": "model-00001-of-00002.safetensors",
573
+ "model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_weight": "model-00001-of-00002.safetensors",
574
+ "model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.bias": "model-00001-of-00002.safetensors",
575
+ "model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.weight": "model-00001-of-00002.safetensors",
576
+ "model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.bias": "model-00001-of-00002.safetensors",
577
+ "model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.weight": "model-00001-of-00002.safetensors",
578
+ "model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.bias": "model-00001-of-00002.safetensors",
579
+ "model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.weight": "model-00001-of-00002.safetensors",
580
+ "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
581
+ "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
582
+ "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
583
+ "model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
584
+ "model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_bias": "model-00001-of-00002.safetensors",
585
+ "model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_weight": "model-00001-of-00002.safetensors",
586
+ "model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.bias": "model-00001-of-00002.safetensors",
587
+ "model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.weight": "model-00001-of-00002.safetensors",
588
+ "model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.bias": "model-00001-of-00002.safetensors",
589
+ "model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.weight": "model-00001-of-00002.safetensors",
590
+ "model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.bias": "model-00001-of-00002.safetensors",
591
+ "model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.weight": "model-00001-of-00002.safetensors",
592
+ "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
593
+ "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
594
+ "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
595
+ "model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
596
+ "model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_bias": "model-00002-of-00002.safetensors",
597
+ "model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_weight": "model-00002-of-00002.safetensors",
598
+ "model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.bias": "model-00002-of-00002.safetensors",
599
+ "model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.weight": "model-00002-of-00002.safetensors",
600
+ "model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.bias": "model-00002-of-00002.safetensors",
601
+ "model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.weight": "model-00002-of-00002.safetensors",
602
+ "model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.bias": "model-00002-of-00002.safetensors",
603
+ "model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.weight": "model-00002-of-00002.safetensors",
604
+ "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
605
+ "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
606
+ "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
607
+ "model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
608
+ "model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_bias": "model-00002-of-00002.safetensors",
609
+ "model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_weight": "model-00002-of-00002.safetensors",
610
+ "model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.bias": "model-00002-of-00002.safetensors",
611
+ "model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.weight": "model-00002-of-00002.safetensors",
612
+ "model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.bias": "model-00002-of-00002.safetensors",
613
+ "model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.weight": "model-00002-of-00002.safetensors",
614
+ "model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.bias": "model-00002-of-00002.safetensors",
615
+ "model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.weight": "model-00002-of-00002.safetensors",
616
+ "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
617
+ "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
618
+ "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
619
+ "model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
620
+ "model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_bias": "model-00002-of-00002.safetensors",
621
+ "model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_weight": "model-00002-of-00002.safetensors",
622
+ "model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.bias": "model-00002-of-00002.safetensors",
623
+ "model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.weight": "model-00002-of-00002.safetensors",
624
+ "model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.bias": "model-00002-of-00002.safetensors",
625
+ "model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.weight": "model-00002-of-00002.safetensors",
626
+ "model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.bias": "model-00002-of-00002.safetensors",
627
+ "model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.weight": "model-00002-of-00002.safetensors",
628
+ "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
629
+ "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
630
+ "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
631
+ "model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
632
+ "model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_bias": "model-00002-of-00002.safetensors",
633
+ "model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_weight": "model-00002-of-00002.safetensors",
634
+ "model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.bias": "model-00002-of-00002.safetensors",
635
+ "model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.weight": "model-00002-of-00002.safetensors",
636
+ "model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.bias": "model-00002-of-00002.safetensors",
637
+ "model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.weight": "model-00002-of-00002.safetensors",
638
+ "model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.bias": "model-00002-of-00002.safetensors",
639
+ "model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.weight": "model-00002-of-00002.safetensors",
640
+ "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
641
+ "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
642
+ "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
643
+ "model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
644
+ "model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_bias": "model-00001-of-00002.safetensors",
645
+ "model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_weight": "model-00001-of-00002.safetensors",
646
+ "model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.bias": "model-00001-of-00002.safetensors",
647
+ "model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
648
+ "model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.bias": "model-00001-of-00002.safetensors",
649
+ "model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.weight": "model-00001-of-00002.safetensors",
650
+ "model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.bias": "model-00001-of-00002.safetensors",
651
+ "model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.weight": "model-00001-of-00002.safetensors",
652
+ "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
653
+ "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
654
+ "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
655
+ "model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
656
+ "model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_bias": "model-00002-of-00002.safetensors",
657
+ "model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_weight": "model-00002-of-00002.safetensors",
658
+ "model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.bias": "model-00002-of-00002.safetensors",
659
+ "model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.weight": "model-00002-of-00002.safetensors",
660
+ "model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.bias": "model-00002-of-00002.safetensors",
661
+ "model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.weight": "model-00002-of-00002.safetensors",
662
+ "model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.bias": "model-00002-of-00002.safetensors",
663
+ "model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.weight": "model-00002-of-00002.safetensors",
664
+ "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
665
+ "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
666
+ "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
667
+ "model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
668
+ "model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_bias": "model-00002-of-00002.safetensors",
669
+ "model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_weight": "model-00002-of-00002.safetensors",
670
+ "model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.bias": "model-00002-of-00002.safetensors",
671
+ "model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.weight": "model-00002-of-00002.safetensors",
672
+ "model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.bias": "model-00002-of-00002.safetensors",
673
+ "model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.weight": "model-00002-of-00002.safetensors",
674
+ "model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.bias": "model-00002-of-00002.safetensors",
675
+ "model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.weight": "model-00002-of-00002.safetensors",
676
+ "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
677
+ "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
678
+ "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
679
+ "model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
680
+ "model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_bias": "model-00002-of-00002.safetensors",
681
+ "model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_weight": "model-00002-of-00002.safetensors",
682
+ "model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.bias": "model-00002-of-00002.safetensors",
683
+ "model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.weight": "model-00002-of-00002.safetensors",
684
+ "model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.bias": "model-00002-of-00002.safetensors",
685
+ "model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.weight": "model-00002-of-00002.safetensors",
686
+ "model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.bias": "model-00002-of-00002.safetensors",
687
+ "model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.weight": "model-00002-of-00002.safetensors",
688
+ "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
689
+ "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
690
+ "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
691
+ "model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
692
+ "model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_bias": "model-00002-of-00002.safetensors",
693
+ "model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_weight": "model-00002-of-00002.safetensors",
694
+ "model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.bias": "model-00002-of-00002.safetensors",
695
+ "model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.weight": "model-00002-of-00002.safetensors",
696
+ "model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.bias": "model-00002-of-00002.safetensors",
697
+ "model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.weight": "model-00002-of-00002.safetensors",
698
+ "model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.bias": "model-00002-of-00002.safetensors",
699
+ "model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.weight": "model-00002-of-00002.safetensors",
700
+ "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
701
+ "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
702
+ "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
703
+ "model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
704
+ "model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_bias": "model-00002-of-00002.safetensors",
705
+ "model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_weight": "model-00002-of-00002.safetensors",
706
+ "model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.bias": "model-00002-of-00002.safetensors",
707
+ "model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.weight": "model-00002-of-00002.safetensors",
708
+ "model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.bias": "model-00002-of-00002.safetensors",
709
+ "model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.weight": "model-00002-of-00002.safetensors",
710
+ "model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.bias": "model-00002-of-00002.safetensors",
711
+ "model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.weight": "model-00002-of-00002.safetensors",
712
+ "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
713
+ "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
714
+ "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
715
+ "model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
716
+ "model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_bias": "model-00002-of-00002.safetensors",
717
+ "model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_weight": "model-00002-of-00002.safetensors",
718
+ "model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.bias": "model-00002-of-00002.safetensors",
719
+ "model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.weight": "model-00002-of-00002.safetensors",
720
+ "model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.bias": "model-00002-of-00002.safetensors",
721
+ "model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.weight": "model-00002-of-00002.safetensors",
722
+ "model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.bias": "model-00002-of-00002.safetensors",
723
+ "model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.weight": "model-00002-of-00002.safetensors",
724
+ "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
725
+ "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
726
+ "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
727
+ "model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
728
+ "model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_bias": "model-00002-of-00002.safetensors",
729
+ "model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_weight": "model-00002-of-00002.safetensors",
730
+ "model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.bias": "model-00002-of-00002.safetensors",
731
+ "model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.weight": "model-00002-of-00002.safetensors",
732
+ "model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.bias": "model-00002-of-00002.safetensors",
733
+ "model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.weight": "model-00002-of-00002.safetensors",
734
+ "model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.bias": "model-00002-of-00002.safetensors",
735
+ "model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.weight": "model-00002-of-00002.safetensors",
736
+ "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
737
+ "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
738
+ "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
739
+ "model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
740
+ "model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_bias": "model-00002-of-00002.safetensors",
741
+ "model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_weight": "model-00002-of-00002.safetensors",
742
+ "model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.bias": "model-00002-of-00002.safetensors",
743
+ "model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.weight": "model-00002-of-00002.safetensors",
744
+ "model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.bias": "model-00002-of-00002.safetensors",
745
+ "model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.weight": "model-00002-of-00002.safetensors",
746
+ "model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.bias": "model-00002-of-00002.safetensors",
747
+ "model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.weight": "model-00002-of-00002.safetensors",
748
+ "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
749
+ "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
750
+ "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
751
+ "model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
752
+ "model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_bias": "model-00002-of-00002.safetensors",
753
+ "model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_weight": "model-00002-of-00002.safetensors",
754
+ "model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.bias": "model-00002-of-00002.safetensors",
755
+ "model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.weight": "model-00002-of-00002.safetensors",
756
+ "model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.bias": "model-00002-of-00002.safetensors",
757
+ "model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.weight": "model-00002-of-00002.safetensors",
758
+ "model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.bias": "model-00002-of-00002.safetensors",
759
+ "model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.weight": "model-00002-of-00002.safetensors",
760
+ "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
761
+ "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
762
+ "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
763
+ "model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
764
+ "model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_bias": "model-00002-of-00002.safetensors",
765
+ "model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_weight": "model-00002-of-00002.safetensors",
766
+ "model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.bias": "model-00002-of-00002.safetensors",
767
+ "model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.weight": "model-00002-of-00002.safetensors",
768
+ "model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.bias": "model-00002-of-00002.safetensors",
769
+ "model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.weight": "model-00002-of-00002.safetensors",
770
+ "model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.bias": "model-00002-of-00002.safetensors",
771
+ "model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.weight": "model-00002-of-00002.safetensors",
772
+ "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
773
+ "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
774
+ "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
775
+ "model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
776
+ "model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_bias": "model-00001-of-00002.safetensors",
777
+ "model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_weight": "model-00001-of-00002.safetensors",
778
+ "model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.bias": "model-00001-of-00002.safetensors",
779
+ "model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
780
+ "model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.bias": "model-00001-of-00002.safetensors",
781
+ "model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.weight": "model-00001-of-00002.safetensors",
782
+ "model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.bias": "model-00001-of-00002.safetensors",
783
+ "model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.weight": "model-00001-of-00002.safetensors",
784
+ "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
785
+ "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
786
+ "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
787
+ "model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
788
+ "model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_bias": "model-00002-of-00002.safetensors",
789
+ "model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_weight": "model-00002-of-00002.safetensors",
790
+ "model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.bias": "model-00002-of-00002.safetensors",
791
+ "model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.weight": "model-00002-of-00002.safetensors",
792
+ "model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.bias": "model-00002-of-00002.safetensors",
793
+ "model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.weight": "model-00002-of-00002.safetensors",
794
+ "model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.bias": "model-00002-of-00002.safetensors",
795
+ "model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.weight": "model-00002-of-00002.safetensors",
796
+ "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
797
+ "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
798
+ "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
799
+ "model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
800
+ "model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_bias": "model-00002-of-00002.safetensors",
801
+ "model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_weight": "model-00002-of-00002.safetensors",
802
+ "model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.bias": "model-00002-of-00002.safetensors",
803
+ "model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.weight": "model-00002-of-00002.safetensors",
804
+ "model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.bias": "model-00002-of-00002.safetensors",
805
+ "model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.weight": "model-00002-of-00002.safetensors",
806
+ "model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.bias": "model-00002-of-00002.safetensors",
807
+ "model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.weight": "model-00002-of-00002.safetensors",
808
+ "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
809
+ "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
810
+ "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
811
+ "model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
812
+ "model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_bias": "model-00002-of-00002.safetensors",
813
+ "model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_weight": "model-00002-of-00002.safetensors",
814
+ "model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.bias": "model-00002-of-00002.safetensors",
815
+ "model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.weight": "model-00002-of-00002.safetensors",
816
+ "model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.bias": "model-00002-of-00002.safetensors",
817
+ "model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.weight": "model-00002-of-00002.safetensors",
818
+ "model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.bias": "model-00002-of-00002.safetensors",
819
+ "model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.weight": "model-00002-of-00002.safetensors",
820
+ "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
821
+ "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
822
+ "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
823
+ "model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
824
+ "model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_bias": "model-00002-of-00002.safetensors",
825
+ "model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_weight": "model-00002-of-00002.safetensors",
826
+ "model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.bias": "model-00002-of-00002.safetensors",
827
+ "model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.weight": "model-00002-of-00002.safetensors",
828
+ "model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.bias": "model-00002-of-00002.safetensors",
829
+ "model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.weight": "model-00002-of-00002.safetensors",
830
+ "model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.bias": "model-00002-of-00002.safetensors",
831
+ "model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.weight": "model-00002-of-00002.safetensors",
832
+ "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
833
+ "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
834
+ "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
835
+ "model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
836
+ "model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_bias": "model-00002-of-00002.safetensors",
837
+ "model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_weight": "model-00002-of-00002.safetensors",
838
+ "model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.bias": "model-00002-of-00002.safetensors",
839
+ "model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.weight": "model-00002-of-00002.safetensors",
840
+ "model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.bias": "model-00002-of-00002.safetensors",
841
+ "model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.weight": "model-00002-of-00002.safetensors",
842
+ "model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.bias": "model-00002-of-00002.safetensors",
843
+ "model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.weight": "model-00002-of-00002.safetensors",
844
+ "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
845
+ "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
846
+ "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
847
+ "model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
848
+ "model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_bias": "model-00002-of-00002.safetensors",
849
+ "model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_weight": "model-00002-of-00002.safetensors",
850
+ "model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.bias": "model-00002-of-00002.safetensors",
851
+ "model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.weight": "model-00002-of-00002.safetensors",
852
+ "model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.bias": "model-00002-of-00002.safetensors",
853
+ "model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.weight": "model-00002-of-00002.safetensors",
854
+ "model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.bias": "model-00002-of-00002.safetensors",
855
+ "model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.weight": "model-00002-of-00002.safetensors",
856
+ "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
857
+ "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
858
+ "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
859
+ "model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
860
+ "model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_bias": "model-00002-of-00002.safetensors",
861
+ "model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_weight": "model-00002-of-00002.safetensors",
862
+ "model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.bias": "model-00002-of-00002.safetensors",
863
+ "model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.weight": "model-00002-of-00002.safetensors",
864
+ "model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.bias": "model-00002-of-00002.safetensors",
865
+ "model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.weight": "model-00002-of-00002.safetensors",
866
+ "model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.bias": "model-00002-of-00002.safetensors",
867
+ "model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.weight": "model-00002-of-00002.safetensors",
868
+ "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
869
+ "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
870
+ "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
871
+ "model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
872
+ "model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_bias": "model-00002-of-00002.safetensors",
873
+ "model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_weight": "model-00002-of-00002.safetensors",
874
+ "model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.bias": "model-00002-of-00002.safetensors",
875
+ "model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.weight": "model-00002-of-00002.safetensors",
876
+ "model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.bias": "model-00002-of-00002.safetensors",
877
+ "model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.weight": "model-00002-of-00002.safetensors",
878
+ "model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.bias": "model-00002-of-00002.safetensors",
879
+ "model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.weight": "model-00002-of-00002.safetensors",
880
+ "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
881
+ "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
882
+ "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
883
+ "model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
884
+ "model.vision_tower.vision_tower.transformer.resblocks.48.attn.in_proj_bias": "model-00002-of-00002.safetensors",
885
+ "model.vision_tower.vision_tower.transformer.resblocks.48.attn.in_proj_weight": "model-00002-of-00002.safetensors",
886
+ "model.vision_tower.vision_tower.transformer.resblocks.48.attn.out_proj.bias": "model-00002-of-00002.safetensors",
887
+ "model.vision_tower.vision_tower.transformer.resblocks.48.attn.out_proj.weight": "model-00002-of-00002.safetensors",
888
+ "model.vision_tower.vision_tower.transformer.resblocks.48.ln_1.bias": "model-00002-of-00002.safetensors",
889
+ "model.vision_tower.vision_tower.transformer.resblocks.48.ln_1.weight": "model-00002-of-00002.safetensors",
890
+ "model.vision_tower.vision_tower.transformer.resblocks.48.ln_2.bias": "model-00002-of-00002.safetensors",
891
+ "model.vision_tower.vision_tower.transformer.resblocks.48.ln_2.weight": "model-00002-of-00002.safetensors",
892
+ "model.vision_tower.vision_tower.transformer.resblocks.48.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
893
+ "model.vision_tower.vision_tower.transformer.resblocks.48.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
894
+ "model.vision_tower.vision_tower.transformer.resblocks.48.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
895
+ "model.vision_tower.vision_tower.transformer.resblocks.48.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
896
+ "model.vision_tower.vision_tower.transformer.resblocks.49.attn.in_proj_bias": "model-00002-of-00002.safetensors",
897
+ "model.vision_tower.vision_tower.transformer.resblocks.49.attn.in_proj_weight": "model-00002-of-00002.safetensors",
898
+ "model.vision_tower.vision_tower.transformer.resblocks.49.attn.out_proj.bias": "model-00002-of-00002.safetensors",
899
+ "model.vision_tower.vision_tower.transformer.resblocks.49.attn.out_proj.weight": "model-00002-of-00002.safetensors",
900
+ "model.vision_tower.vision_tower.transformer.resblocks.49.ln_1.bias": "model-00002-of-00002.safetensors",
901
+ "model.vision_tower.vision_tower.transformer.resblocks.49.ln_1.weight": "model-00002-of-00002.safetensors",
902
+ "model.vision_tower.vision_tower.transformer.resblocks.49.ln_2.bias": "model-00002-of-00002.safetensors",
903
+ "model.vision_tower.vision_tower.transformer.resblocks.49.ln_2.weight": "model-00002-of-00002.safetensors",
904
+ "model.vision_tower.vision_tower.transformer.resblocks.49.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
905
+ "model.vision_tower.vision_tower.transformer.resblocks.49.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
906
+ "model.vision_tower.vision_tower.transformer.resblocks.49.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
907
+ "model.vision_tower.vision_tower.transformer.resblocks.49.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
908
+ "model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_bias": "model-00001-of-00002.safetensors",
909
+ "model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_weight": "model-00001-of-00002.safetensors",
910
+ "model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.bias": "model-00001-of-00002.safetensors",
911
+ "model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
912
+ "model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.bias": "model-00001-of-00002.safetensors",
913
+ "model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.weight": "model-00001-of-00002.safetensors",
914
+ "model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.bias": "model-00001-of-00002.safetensors",
915
+ "model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.weight": "model-00001-of-00002.safetensors",
916
+ "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
917
+ "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
918
+ "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
919
+ "model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
920
+ "model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_bias": "model-00001-of-00002.safetensors",
921
+ "model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_weight": "model-00001-of-00002.safetensors",
922
+ "model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.bias": "model-00001-of-00002.safetensors",
923
+ "model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
924
+ "model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.bias": "model-00001-of-00002.safetensors",
925
+ "model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.weight": "model-00001-of-00002.safetensors",
926
+ "model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.bias": "model-00001-of-00002.safetensors",
927
+ "model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.weight": "model-00001-of-00002.safetensors",
928
+ "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
929
+ "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
930
+ "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
931
+ "model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
932
+ "model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_bias": "model-00001-of-00002.safetensors",
933
+ "model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_weight": "model-00001-of-00002.safetensors",
934
+ "model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.bias": "model-00001-of-00002.safetensors",
935
+ "model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
936
+ "model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.bias": "model-00001-of-00002.safetensors",
937
+ "model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.weight": "model-00001-of-00002.safetensors",
938
+ "model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.bias": "model-00001-of-00002.safetensors",
939
+ "model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.weight": "model-00001-of-00002.safetensors",
940
+ "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
941
+ "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
942
+ "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
943
+ "model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
944
+ "model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_bias": "model-00001-of-00002.safetensors",
945
+ "model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_weight": "model-00001-of-00002.safetensors",
946
+ "model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.bias": "model-00001-of-00002.safetensors",
947
+ "model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
948
+ "model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.bias": "model-00001-of-00002.safetensors",
949
+ "model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.weight": "model-00001-of-00002.safetensors",
950
+ "model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.bias": "model-00001-of-00002.safetensors",
951
+ "model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.weight": "model-00001-of-00002.safetensors",
952
+ "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
953
+ "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
954
+ "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
955
+ "model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
956
+ "model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_bias": "model-00001-of-00002.safetensors",
957
+ "model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_weight": "model-00001-of-00002.safetensors",
958
+ "model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.bias": "model-00001-of-00002.safetensors",
959
+ "model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
960
+ "model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.bias": "model-00001-of-00002.safetensors",
961
+ "model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.weight": "model-00001-of-00002.safetensors",
962
+ "model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.bias": "model-00001-of-00002.safetensors",
963
+ "model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.weight": "model-00001-of-00002.safetensors",
964
+ "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
965
+ "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
966
+ "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
967
+ "model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors"
968
+ }
969
+ }
continuous/qwen25/pe_core_g14_448/finetune/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
+ }
continuous/qwen25/pe_core_g14_448/finetune/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
continuous/qwen25/pe_core_g14_448/finetune/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 8192,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
continuous/qwen25/pe_core_g14_448/finetune/trainer_state.json ADDED
@@ -0,0 +1,1856 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9999037443449803,
6
+ "eval_steps": 500,
7
+ "global_step": 2597,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.003850226200789296,
14
+ "grad_norm": 7.271701812744141,
15
+ "learning_rate": 1.153846153846154e-06,
16
+ "loss": 2.072,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.007700452401578592,
21
+ "grad_norm": 3.920562267303467,
22
+ "learning_rate": 2.435897435897436e-06,
23
+ "loss": 1.6732,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.01155067860236789,
28
+ "grad_norm": 2.1630008220672607,
29
+ "learning_rate": 3.7179487179487184e-06,
30
+ "loss": 1.1674,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.015400904803157185,
35
+ "grad_norm": 0.4189048111438751,
36
+ "learning_rate": 5e-06,
37
+ "loss": 0.9499,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.019251131003946483,
42
+ "grad_norm": 0.24676254391670227,
43
+ "learning_rate": 6.282051282051282e-06,
44
+ "loss": 0.9166,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.02310135720473578,
49
+ "grad_norm": 0.17406035959720612,
50
+ "learning_rate": 7.564102564102564e-06,
51
+ "loss": 0.8674,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.026951583405525073,
56
+ "grad_norm": 0.13212697207927704,
57
+ "learning_rate": 8.846153846153847e-06,
58
+ "loss": 0.8425,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.03080180960631437,
63
+ "grad_norm": 0.14277400076389313,
64
+ "learning_rate": 9.999996111488723e-06,
65
+ "loss": 0.85,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.034652035807103666,
70
+ "grad_norm": 0.14026287198066711,
71
+ "learning_rate": 9.999529497453782e-06,
72
+ "loss": 0.8352,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.038502262007892966,
77
+ "grad_norm": 0.13334979116916656,
78
+ "learning_rate": 9.998285264324193e-06,
79
+ "loss": 0.8083,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.04235248820868226,
84
+ "grad_norm": 0.12197940051555634,
85
+ "learning_rate": 9.996263605626052e-06,
86
+ "loss": 0.7961,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.04620271440947156,
91
+ "grad_norm": 0.1290683001279831,
92
+ "learning_rate": 9.99346483580503e-06,
93
+ "loss": 0.8055,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.05005294061026085,
98
+ "grad_norm": 0.11824268847703934,
99
+ "learning_rate": 9.989889390177467e-06,
100
+ "loss": 0.7895,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.053903166811050146,
105
+ "grad_norm": 0.12944895029067993,
106
+ "learning_rate": 9.985537824862647e-06,
107
+ "loss": 0.7945,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.057753393011839446,
112
+ "grad_norm": 0.14592581987380981,
113
+ "learning_rate": 9.980410816696317e-06,
114
+ "loss": 0.7847,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.06160361921262874,
119
+ "grad_norm": 0.1339201033115387,
120
+ "learning_rate": 9.97450916312541e-06,
121
+ "loss": 0.7828,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.06545384541341803,
126
+ "grad_norm": 0.11574842780828476,
127
+ "learning_rate": 9.967833782084004e-06,
128
+ "loss": 0.7815,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.06930407161420733,
133
+ "grad_norm": 0.129705548286438,
134
+ "learning_rate": 9.960385711850554e-06,
135
+ "loss": 0.8032,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.07315429781499663,
140
+ "grad_norm": 0.12688224017620087,
141
+ "learning_rate": 9.952166110886394e-06,
142
+ "loss": 0.8044,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.07700452401578593,
147
+ "grad_norm": 0.13631966710090637,
148
+ "learning_rate": 9.943176257655567e-06,
149
+ "loss": 0.7861,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.08085475021657522,
154
+ "grad_norm": 0.12541745603084564,
155
+ "learning_rate": 9.933417550425952e-06,
156
+ "loss": 0.7891,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.08470497641736452,
161
+ "grad_norm": 0.1452760547399521,
162
+ "learning_rate": 9.9228915070518e-06,
163
+ "loss": 0.7644,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.08855520261815382,
168
+ "grad_norm": 0.13237255811691284,
169
+ "learning_rate": 9.911599764737632e-06,
170
+ "loss": 0.7721,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.09240542881894312,
175
+ "grad_norm": 0.13091683387756348,
176
+ "learning_rate": 9.899544079783606e-06,
177
+ "loss": 0.7569,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.0962556550197324,
182
+ "grad_norm": 0.12932968139648438,
183
+ "learning_rate": 9.886726327312338e-06,
184
+ "loss": 0.7737,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.1001058812205217,
189
+ "grad_norm": 0.12747564911842346,
190
+ "learning_rate": 9.87314850097724e-06,
191
+ "loss": 0.7772,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.103956107421311,
196
+ "grad_norm": 0.121647909283638,
197
+ "learning_rate": 9.858812712652452e-06,
198
+ "loss": 0.7634,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.10780633362210029,
203
+ "grad_norm": 0.11865510791540146,
204
+ "learning_rate": 9.843721192104341e-06,
205
+ "loss": 0.7642,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.11165655982288959,
210
+ "grad_norm": 0.12457911670207977,
211
+ "learning_rate": 9.827876286644698e-06,
212
+ "loss": 0.779,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.11550678602367889,
217
+ "grad_norm": 0.12371369451284409,
218
+ "learning_rate": 9.811280460765643e-06,
219
+ "loss": 0.741,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.11935701222446819,
224
+ "grad_norm": 0.1325763612985611,
225
+ "learning_rate": 9.793936295756292e-06,
226
+ "loss": 0.7524,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.12320723842525748,
231
+ "grad_norm": 0.12374066561460495,
232
+ "learning_rate": 9.775846489301279e-06,
233
+ "loss": 0.7564,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.12705746462604678,
238
+ "grad_norm": 0.1256614625453949,
239
+ "learning_rate": 9.757013855061157e-06,
240
+ "loss": 0.7554,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.13090769082683607,
245
+ "grad_norm": 0.12491127103567123,
246
+ "learning_rate": 9.737441322234758e-06,
247
+ "loss": 0.7629,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.13475791702762538,
252
+ "grad_norm": 0.1297522634267807,
253
+ "learning_rate": 9.717131935103605e-06,
254
+ "loss": 0.7691,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.13860814322841467,
259
+ "grad_norm": 0.12176083028316498,
260
+ "learning_rate": 9.696088852558398e-06,
261
+ "loss": 0.7498,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.14245836942920398,
266
+ "grad_norm": 0.13084673881530762,
267
+ "learning_rate": 9.674315347607686e-06,
268
+ "loss": 0.7745,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.14630859562999327,
273
+ "grad_norm": 0.11910505592823029,
274
+ "learning_rate": 9.651814806868796e-06,
275
+ "loss": 0.7488,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.15015882183078255,
280
+ "grad_norm": 0.136897012591362,
281
+ "learning_rate": 9.62859073004107e-06,
282
+ "loss": 0.7468,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.15400904803157187,
287
+ "grad_norm": 0.11842416971921921,
288
+ "learning_rate": 9.604646729361547e-06,
289
+ "loss": 0.7502,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.15785927423236115,
294
+ "grad_norm": 0.11979175359010696,
295
+ "learning_rate": 9.579986529043099e-06,
296
+ "loss": 0.7335,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.16170950043315044,
301
+ "grad_norm": 0.12339454889297485,
302
+ "learning_rate": 9.554613964695189e-06,
303
+ "loss": 0.7485,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.16555972663393975,
308
+ "grad_norm": 0.12649649381637573,
309
+ "learning_rate": 9.528532982727281e-06,
310
+ "loss": 0.7439,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.16940995283472904,
315
+ "grad_norm": 0.1298736184835434,
316
+ "learning_rate": 9.501747639735018e-06,
317
+ "loss": 0.74,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.17326017903551832,
322
+ "grad_norm": 0.12532320618629456,
323
+ "learning_rate": 9.474262101869272e-06,
324
+ "loss": 0.7266,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.17711040523630764,
329
+ "grad_norm": 0.12363260239362717,
330
+ "learning_rate": 9.446080644188141e-06,
331
+ "loss": 0.7415,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.18096063143709692,
336
+ "grad_norm": 0.13096825778484344,
337
+ "learning_rate": 9.417207649992017e-06,
338
+ "loss": 0.742,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.18481085763788624,
343
+ "grad_norm": 0.12339988350868225,
344
+ "learning_rate": 9.387647610141816e-06,
345
+ "loss": 0.7362,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.18866108383867553,
350
+ "grad_norm": 0.12184390425682068,
351
+ "learning_rate": 9.35740512236047e-06,
352
+ "loss": 0.7288,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.1925113100394648,
357
+ "grad_norm": 0.10983569175004959,
358
+ "learning_rate": 9.326484890517809e-06,
359
+ "loss": 0.7371,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.19636153624025413,
364
+ "grad_norm": 0.12503112852573395,
365
+ "learning_rate": 9.294891723898926e-06,
366
+ "loss": 0.7176,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.2002117624410434,
371
+ "grad_norm": 0.12650518119335175,
372
+ "learning_rate": 9.262630536456153e-06,
373
+ "loss": 0.757,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.2040619886418327,
378
+ "grad_norm": 0.12755414843559265,
379
+ "learning_rate": 9.229706346044749e-06,
380
+ "loss": 0.7292,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.207912214842622,
385
+ "grad_norm": 0.1285887062549591,
386
+ "learning_rate": 9.196124273642422e-06,
387
+ "loss": 0.7443,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.2117624410434113,
392
+ "grad_norm": 0.11489944159984589,
393
+ "learning_rate": 9.161889542552842e-06,
394
+ "loss": 0.7514,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.21561266724420058,
399
+ "grad_norm": 0.12155210226774216,
400
+ "learning_rate": 9.127007477593193e-06,
401
+ "loss": 0.7447,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.2194628934449899,
406
+ "grad_norm": 0.1296476274728775,
407
+ "learning_rate": 9.091483504265974e-06,
408
+ "loss": 0.7563,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.22331311964577918,
413
+ "grad_norm": 0.12011411041021347,
414
+ "learning_rate": 9.055323147915116e-06,
415
+ "loss": 0.7301,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.2271633458465685,
420
+ "grad_norm": 0.12914824485778809,
421
+ "learning_rate": 9.018532032866585e-06,
422
+ "loss": 0.7481,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.23101357204735778,
427
+ "grad_norm": 0.12422823905944824,
428
+ "learning_rate": 8.981115881553579e-06,
429
+ "loss": 0.7445,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.23486379824814707,
434
+ "grad_norm": 0.128742516040802,
435
+ "learning_rate": 8.943080513626476e-06,
436
+ "loss": 0.7551,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.23871402444893638,
441
+ "grad_norm": 0.12873631715774536,
442
+ "learning_rate": 8.904431845047641e-06,
443
+ "loss": 0.7465,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.24256425064972567,
448
+ "grad_norm": 0.13429811596870422,
449
+ "learning_rate": 8.86517588717128e-06,
450
+ "loss": 0.7522,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.24641447685051496,
455
+ "grad_norm": 0.10990362614393234,
456
+ "learning_rate": 8.82531874580844e-06,
457
+ "loss": 0.7512,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.25026470305130427,
462
+ "grad_norm": 0.10815179347991943,
463
+ "learning_rate": 8.784866620277314e-06,
464
+ "loss": 0.7092,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.25411492925209356,
469
+ "grad_norm": 0.1301898956298828,
470
+ "learning_rate": 8.743825802439018e-06,
471
+ "loss": 0.7242,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.25796515545288284,
476
+ "grad_norm": 0.1292671263217926,
477
+ "learning_rate": 8.702202675718956e-06,
478
+ "loss": 0.7478,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.26181538165367213,
483
+ "grad_norm": 0.12113941460847855,
484
+ "learning_rate": 8.660003714113959e-06,
485
+ "loss": 0.7213,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.26566560785446147,
490
+ "grad_norm": 0.11549089103937149,
491
+ "learning_rate": 8.617235481185323e-06,
492
+ "loss": 0.7326,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.26951583405525076,
497
+ "grad_norm": 0.13744913041591644,
498
+ "learning_rate": 8.573904629037931e-06,
499
+ "loss": 0.7397,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.27336606025604004,
504
+ "grad_norm": 0.11705910414457321,
505
+ "learning_rate": 8.530017897285585e-06,
506
+ "loss": 0.7247,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.27721628645682933,
511
+ "grad_norm": 0.10770375281572342,
512
+ "learning_rate": 8.485582112002746e-06,
513
+ "loss": 0.7353,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.2810665126576186,
518
+ "grad_norm": 0.1238565668463707,
519
+ "learning_rate": 8.440604184662811e-06,
520
+ "loss": 0.7356,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.28491673885840796,
525
+ "grad_norm": 0.12637142837047577,
526
+ "learning_rate": 8.395091111063118e-06,
527
+ "loss": 0.722,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.28876696505919724,
532
+ "grad_norm": 0.11565504968166351,
533
+ "learning_rate": 8.349049970236822e-06,
534
+ "loss": 0.7229,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.29261719125998653,
539
+ "grad_norm": 0.1210106834769249,
540
+ "learning_rate": 8.302487923351842e-06,
541
+ "loss": 0.7122,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.2964674174607758,
546
+ "grad_norm": 0.12096888571977615,
547
+ "learning_rate": 8.255412212597021e-06,
548
+ "loss": 0.7327,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.3003176436615651,
553
+ "grad_norm": 0.12444206327199936,
554
+ "learning_rate": 8.207830160055688e-06,
555
+ "loss": 0.7279,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.3041678698623544,
560
+ "grad_norm": 0.11940550059080124,
561
+ "learning_rate": 8.159749166566786e-06,
562
+ "loss": 0.7158,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.30801809606314373,
567
+ "grad_norm": 0.12265162169933319,
568
+ "learning_rate": 8.11117671057377e-06,
569
+ "loss": 0.7393,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.311868322263933,
574
+ "grad_norm": 0.11982421576976776,
575
+ "learning_rate": 8.062120346961404e-06,
576
+ "loss": 0.7249,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.3157185484647223,
581
+ "grad_norm": 0.10751131176948547,
582
+ "learning_rate": 8.012587705880705e-06,
583
+ "loss": 0.7319,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.3195687746655116,
588
+ "grad_norm": 0.11841066181659698,
589
+ "learning_rate": 7.962586491562146e-06,
590
+ "loss": 0.7187,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.3234190008663009,
595
+ "grad_norm": 0.12668372690677643,
596
+ "learning_rate": 7.912124481117357e-06,
597
+ "loss": 0.7186,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.3272692270670902,
602
+ "grad_norm": 0.10963724553585052,
603
+ "learning_rate": 7.861209523329494e-06,
604
+ "loss": 0.7259,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.3311194532678795,
609
+ "grad_norm": 0.11449850350618362,
610
+ "learning_rate": 7.809849537432432e-06,
611
+ "loss": 0.7178,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.3349696794686688,
616
+ "grad_norm": 0.11857673525810242,
617
+ "learning_rate": 7.758052511879035e-06,
618
+ "loss": 0.7144,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.3388199056694581,
623
+ "grad_norm": 0.10904961824417114,
624
+ "learning_rate": 7.705826503098642e-06,
625
+ "loss": 0.7217,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.34267013187024736,
630
+ "grad_norm": 0.11249038577079773,
631
+ "learning_rate": 7.653179634243979e-06,
632
+ "loss": 0.7158,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.34652035807103665,
637
+ "grad_norm": 0.10601029545068741,
638
+ "learning_rate": 7.600120093927696e-06,
639
+ "loss": 0.7107,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.350370584271826,
644
+ "grad_norm": 0.1209498718380928,
645
+ "learning_rate": 7.546656134948729e-06,
646
+ "loss": 0.7075,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.3542208104726153,
651
+ "grad_norm": 0.10915538668632507,
652
+ "learning_rate": 7.492796073008661e-06,
653
+ "loss": 0.7043,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.35807103667340456,
658
+ "grad_norm": 0.12891606986522675,
659
+ "learning_rate": 7.438548285418326e-06,
660
+ "loss": 0.7009,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.36192126287419385,
665
+ "grad_norm": 0.1264500468969345,
666
+ "learning_rate": 7.3839212097948e-06,
667
+ "loss": 0.7361,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.36577148907498314,
672
+ "grad_norm": 0.11222334206104279,
673
+ "learning_rate": 7.328923342749039e-06,
674
+ "loss": 0.7485,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.3696217152757725,
679
+ "grad_norm": 0.12560343742370605,
680
+ "learning_rate": 7.273563238564319e-06,
681
+ "loss": 0.7263,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.37347194147656176,
686
+ "grad_norm": 0.11586467921733856,
687
+ "learning_rate": 7.217849507865724e-06,
688
+ "loss": 0.7036,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.37732216767735105,
693
+ "grad_norm": 0.10970785468816757,
694
+ "learning_rate": 7.161790816280858e-06,
695
+ "loss": 0.7194,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.38117239387814034,
700
+ "grad_norm": 0.12697751820087433,
701
+ "learning_rate": 7.1053958830920125e-06,
702
+ "loss": 0.6932,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.3850226200789296,
707
+ "grad_norm": 0.1210712194442749,
708
+ "learning_rate": 7.0486734798799715e-06,
709
+ "loss": 0.7224,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.3888728462797189,
714
+ "grad_norm": 0.11826971918344498,
715
+ "learning_rate": 6.991632429159708e-06,
716
+ "loss": 0.7437,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.39272307248050825,
721
+ "grad_norm": 0.12368576228618622,
722
+ "learning_rate": 6.934281603008132e-06,
723
+ "loss": 0.7196,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.39657329868129754,
728
+ "grad_norm": 0.11281894147396088,
729
+ "learning_rate": 6.876629921684143e-06,
730
+ "loss": 0.732,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.4004235248820868,
735
+ "grad_norm": 0.1129785105586052,
736
+ "learning_rate": 6.818686352241199e-06,
737
+ "loss": 0.7284,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.4042737510828761,
742
+ "grad_norm": 0.11076430231332779,
743
+ "learning_rate": 6.760459907132573e-06,
744
+ "loss": 0.7186,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.4081239772836654,
749
+ "grad_norm": 0.11337845027446747,
750
+ "learning_rate": 6.701959642809589e-06,
751
+ "loss": 0.7222,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.41197420348445474,
756
+ "grad_norm": 0.1172068789601326,
757
+ "learning_rate": 6.643194658312987e-06,
758
+ "loss": 0.7035,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.415824429685244,
763
+ "grad_norm": 0.11210376024246216,
764
+ "learning_rate": 6.584174093857676e-06,
765
+ "loss": 0.7396,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.4196746558860333,
770
+ "grad_norm": 0.1272713840007782,
771
+ "learning_rate": 6.5249071294110735e-06,
772
+ "loss": 0.7142,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.4235248820868226,
777
+ "grad_norm": 0.12908822298049927,
778
+ "learning_rate": 6.465402983265274e-06,
779
+ "loss": 0.7342,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.4273751082876119,
784
+ "grad_norm": 0.11804359406232834,
785
+ "learning_rate": 6.405670910603243e-06,
786
+ "loss": 0.7296,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.43122533448840117,
791
+ "grad_norm": 0.12638284265995026,
792
+ "learning_rate": 6.345720202059291e-06,
793
+ "loss": 0.7214,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.4350755606891905,
798
+ "grad_norm": 0.12153468281030655,
799
+ "learning_rate": 6.285560182274008e-06,
800
+ "loss": 0.708,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.4389257868899798,
805
+ "grad_norm": 0.11103112250566483,
806
+ "learning_rate": 6.225200208443936e-06,
807
+ "loss": 0.716,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.4427760130907691,
812
+ "grad_norm": 0.10911386460065842,
813
+ "learning_rate": 6.16464966886616e-06,
814
+ "loss": 0.7114,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.44662623929155837,
819
+ "grad_norm": 0.13298162817955017,
820
+ "learning_rate": 6.103917981478065e-06,
821
+ "loss": 0.7403,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.45047646549234766,
826
+ "grad_norm": 0.11514422297477722,
827
+ "learning_rate": 6.043014592392489e-06,
828
+ "loss": 0.7459,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.454326691693137,
833
+ "grad_norm": 0.10379037261009216,
834
+ "learning_rate": 5.981948974428485e-06,
835
+ "loss": 0.719,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.4581769178939263,
840
+ "grad_norm": 0.1126343160867691,
841
+ "learning_rate": 5.920730625637934e-06,
842
+ "loss": 0.6979,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.46202714409471557,
847
+ "grad_norm": 0.1197405606508255,
848
+ "learning_rate": 5.8593690678282355e-06,
849
+ "loss": 0.7113,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.46587737029550486,
854
+ "grad_norm": 0.12259652465581894,
855
+ "learning_rate": 5.797873845081301e-06,
856
+ "loss": 0.7139,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.46972759649629414,
861
+ "grad_norm": 0.11717702448368073,
862
+ "learning_rate": 5.736254522269075e-06,
863
+ "loss": 0.7258,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.47357782269708343,
868
+ "grad_norm": 0.11370323598384857,
869
+ "learning_rate": 5.6745206835658386e-06,
870
+ "loss": 0.7338,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.47742804889787277,
875
+ "grad_norm": 0.10765629261732101,
876
+ "learning_rate": 5.612681930957495e-06,
877
+ "loss": 0.7089,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.48127827509866206,
882
+ "grad_norm": 0.10655038058757782,
883
+ "learning_rate": 5.550747882748095e-06,
884
+ "loss": 0.7029,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.48512850129945134,
889
+ "grad_norm": 0.12222810834646225,
890
+ "learning_rate": 5.4887281720638195e-06,
891
+ "loss": 0.7136,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.48897872750024063,
896
+ "grad_norm": 0.13150262832641602,
897
+ "learning_rate": 5.42663244535466e-06,
898
+ "loss": 0.6975,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.4928289537010299,
903
+ "grad_norm": 0.11520398408174515,
904
+ "learning_rate": 5.3644703608940205e-06,
905
+ "loss": 0.7043,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.49667917990181926,
910
+ "grad_norm": 0.12035271525382996,
911
+ "learning_rate": 5.302251587276491e-06,
912
+ "loss": 0.7231,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.5005294061026085,
917
+ "grad_norm": 0.11771697551012039,
918
+ "learning_rate": 5.2399858019140005e-06,
919
+ "loss": 0.7191,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.5043796323033978,
924
+ "grad_norm": 0.11294110119342804,
925
+ "learning_rate": 5.177682689530615e-06,
926
+ "loss": 0.7322,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.5082298585041871,
931
+ "grad_norm": 0.12597905099391937,
932
+ "learning_rate": 5.11535194065619e-06,
933
+ "loss": 0.7048,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.5120800847049765,
938
+ "grad_norm": 0.13572901487350464,
939
+ "learning_rate": 5.053003250119113e-06,
940
+ "loss": 0.7072,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.5159303109057657,
945
+ "grad_norm": 0.12123768776655197,
946
+ "learning_rate": 4.9906463155383925e-06,
947
+ "loss": 0.7174,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.519780537106555,
952
+ "grad_norm": 0.1172645166516304,
953
+ "learning_rate": 4.9282908358153046e-06,
954
+ "loss": 0.7116,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.5236307633073443,
959
+ "grad_norm": 0.13858285546302795,
960
+ "learning_rate": 4.8659465096248345e-06,
961
+ "loss": 0.7178,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.5274809895081336,
966
+ "grad_norm": 0.11528172343969345,
967
+ "learning_rate": 4.803623033907169e-06,
968
+ "loss": 0.7192,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.5313312157089229,
973
+ "grad_norm": 0.10680907219648361,
974
+ "learning_rate": 4.741330102359441e-06,
975
+ "loss": 0.7307,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.5351814419097122,
980
+ "grad_norm": 0.12694528698921204,
981
+ "learning_rate": 4.679077403927996e-06,
982
+ "loss": 0.7035,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.5390316681105015,
987
+ "grad_norm": 0.11780314892530441,
988
+ "learning_rate": 4.616874621301373e-06,
989
+ "loss": 0.7129,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.5428818943112907,
994
+ "grad_norm": 0.1174406036734581,
995
+ "learning_rate": 4.554731429404293e-06,
996
+ "loss": 0.7284,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.5467321205120801,
1001
+ "grad_norm": 0.12295341491699219,
1002
+ "learning_rate": 4.492657493892822e-06,
1003
+ "loss": 0.7084,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.5505823467128694,
1008
+ "grad_norm": 0.1205807626247406,
1009
+ "learning_rate": 4.430662469650999e-06,
1010
+ "loss": 0.7223,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.5544325729136587,
1015
+ "grad_norm": 0.11425131559371948,
1016
+ "learning_rate": 4.368755999289118e-06,
1017
+ "loss": 0.726,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.558282799114448,
1022
+ "grad_norm": 0.1263428032398224,
1023
+ "learning_rate": 4.306947711643949e-06,
1024
+ "loss": 0.7036,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.5621330253152372,
1029
+ "grad_norm": 0.12008614093065262,
1030
+ "learning_rate": 4.245247220281068e-06,
1031
+ "loss": 0.7142,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.5659832515160266,
1036
+ "grad_norm": 0.11184190213680267,
1037
+ "learning_rate": 4.183664121999587e-06,
1038
+ "loss": 0.7076,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.5698334777168159,
1043
+ "grad_norm": 0.1263689547777176,
1044
+ "learning_rate": 4.122207995339474e-06,
1045
+ "loss": 0.7052,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.5736837039176051,
1050
+ "grad_norm": 0.11744481325149536,
1051
+ "learning_rate": 4.060888399091734e-06,
1052
+ "loss": 0.7128,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.5775339301183945,
1057
+ "grad_norm": 0.11308754235506058,
1058
+ "learning_rate": 3.999714870811639e-06,
1059
+ "loss": 0.7279,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.5813841563191837,
1064
+ "grad_norm": 0.11350201070308685,
1065
+ "learning_rate": 3.938696925335275e-06,
1066
+ "loss": 0.7157,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.5852343825199731,
1071
+ "grad_norm": 0.12316755205392838,
1072
+ "learning_rate": 3.87784405329962e-06,
1073
+ "loss": 0.722,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.5890846087207623,
1078
+ "grad_norm": 0.122797392308712,
1079
+ "learning_rate": 3.817165719666382e-06,
1080
+ "loss": 0.7186,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.5929348349215516,
1085
+ "grad_norm": 0.1104922890663147,
1086
+ "learning_rate": 3.756671362249841e-06,
1087
+ "loss": 0.7326,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.596785061122341,
1092
+ "grad_norm": 0.11939578503370285,
1093
+ "learning_rate": 3.6963703902488907e-06,
1094
+ "loss": 0.7206,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.6006352873231302,
1099
+ "grad_norm": 0.12079333513975143,
1100
+ "learning_rate": 3.6362721827835655e-06,
1101
+ "loss": 0.7284,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.6044855135239195,
1106
+ "grad_norm": 0.12233269214630127,
1107
+ "learning_rate": 3.576386087436212e-06,
1108
+ "loss": 0.7205,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.6083357397247088,
1113
+ "grad_norm": 0.12012306600809097,
1114
+ "learning_rate": 3.5167214187975913e-06,
1115
+ "loss": 0.7244,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.6121859659254981,
1120
+ "grad_norm": 0.10458192229270935,
1121
+ "learning_rate": 3.457287457018086e-06,
1122
+ "loss": 0.7195,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.6160361921262875,
1127
+ "grad_norm": 0.10855144262313843,
1128
+ "learning_rate": 3.3980934463643003e-06,
1129
+ "loss": 0.7079,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.6198864183270767,
1134
+ "grad_norm": 0.10491714626550674,
1135
+ "learning_rate": 3.3391485937812053e-06,
1136
+ "loss": 0.686,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.623736644527866,
1141
+ "grad_norm": 0.11575963348150253,
1142
+ "learning_rate": 3.280462067460115e-06,
1143
+ "loss": 0.6894,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.6275868707286553,
1148
+ "grad_norm": 0.11118635535240173,
1149
+ "learning_rate": 3.222042995412669e-06,
1150
+ "loss": 0.7273,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.6314370969294446,
1155
+ "grad_norm": 0.1033163070678711,
1156
+ "learning_rate": 3.163900464051089e-06,
1157
+ "loss": 0.7061,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.635287323130234,
1162
+ "grad_norm": 0.11656031757593155,
1163
+ "learning_rate": 3.1060435167748826e-06,
1164
+ "loss": 0.719,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.6391375493310232,
1169
+ "grad_norm": 0.11664772778749466,
1170
+ "learning_rate": 3.048481152564253e-06,
1171
+ "loss": 0.708,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.6429877755318125,
1176
+ "grad_norm": 0.12624825537204742,
1177
+ "learning_rate": 2.9912223245804017e-06,
1178
+ "loss": 0.7294,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.6468380017326018,
1183
+ "grad_norm": 0.1185910776257515,
1184
+ "learning_rate": 2.934275938772981e-06,
1185
+ "loss": 0.7075,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.6506882279333911,
1190
+ "grad_norm": 0.11135411262512207,
1191
+ "learning_rate": 2.8776508524948676e-06,
1192
+ "loss": 0.6983,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.6545384541341804,
1197
+ "grad_norm": 0.10499187558889389,
1198
+ "learning_rate": 2.821355873124503e-06,
1199
+ "loss": 0.6986,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.6583886803349697,
1204
+ "grad_norm": 0.11346419900655746,
1205
+ "learning_rate": 2.7653997566960144e-06,
1206
+ "loss": 0.7173,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.662238906535759,
1211
+ "grad_norm": 0.1145080029964447,
1212
+ "learning_rate": 2.709791206537309e-06,
1213
+ "loss": 0.7075,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.6660891327365482,
1218
+ "grad_norm": 0.11577607691287994,
1219
+ "learning_rate": 2.6545388719163747e-06,
1220
+ "loss": 0.7038,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.6699393589373376,
1225
+ "grad_norm": 0.11655327677726746,
1226
+ "learning_rate": 2.599651346695979e-06,
1227
+ "loss": 0.7162,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.6737895851381268,
1232
+ "grad_norm": 0.113648422062397,
1233
+ "learning_rate": 2.545137167997007e-06,
1234
+ "loss": 0.7122,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.6776398113389162,
1239
+ "grad_norm": 0.10828101634979248,
1240
+ "learning_rate": 2.4910048148705972e-06,
1241
+ "loss": 0.6979,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.6814900375397055,
1246
+ "grad_norm": 0.12208633869886398,
1247
+ "learning_rate": 2.4372627069793327e-06,
1248
+ "loss": 0.7416,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.6853402637404947,
1253
+ "grad_norm": 0.12413984537124634,
1254
+ "learning_rate": 2.3839192032876486e-06,
1255
+ "loss": 0.7242,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.6891904899412841,
1260
+ "grad_norm": 0.11547788977622986,
1261
+ "learning_rate": 2.3309826007617047e-06,
1262
+ "loss": 0.7343,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.6930407161420733,
1267
+ "grad_norm": 0.11034944653511047,
1268
+ "learning_rate": 2.278461133078881e-06,
1269
+ "loss": 0.6971,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.6968909423428626,
1274
+ "grad_norm": 0.11712385714054108,
1275
+ "learning_rate": 2.2263629693471258e-06,
1276
+ "loss": 0.6952,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.700741168543652,
1281
+ "grad_norm": 0.1133355051279068,
1282
+ "learning_rate": 2.1746962128343414e-06,
1283
+ "loss": 0.7158,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.7045913947444412,
1288
+ "grad_norm": 0.11103581637144089,
1289
+ "learning_rate": 2.1234688997080183e-06,
1290
+ "loss": 0.7146,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.7084416209452306,
1295
+ "grad_norm": 0.12818586826324463,
1296
+ "learning_rate": 2.0726889977853053e-06,
1297
+ "loss": 0.7121,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.7122918471460198,
1302
+ "grad_norm": 0.12617170810699463,
1303
+ "learning_rate": 2.022364405293703e-06,
1304
+ "loss": 0.7232,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.7161420733468091,
1309
+ "grad_norm": 0.1156310886144638,
1310
+ "learning_rate": 1.9725029496425814e-06,
1311
+ "loss": 0.721,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.7199922995475985,
1316
+ "grad_norm": 0.10481128096580505,
1317
+ "learning_rate": 1.923112386205727e-06,
1318
+ "loss": 0.715,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.7238425257483877,
1323
+ "grad_norm": 0.11546818166971207,
1324
+ "learning_rate": 1.874200397115079e-06,
1325
+ "loss": 0.7218,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.727692751949177,
1330
+ "grad_norm": 0.12174128741025925,
1331
+ "learning_rate": 1.825774590065857e-06,
1332
+ "loss": 0.707,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.7315429781499663,
1337
+ "grad_norm": 0.1233733743429184,
1338
+ "learning_rate": 1.7778424971332813e-06,
1339
+ "loss": 0.7168,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.7353932043507556,
1344
+ "grad_norm": 0.10865708440542221,
1345
+ "learning_rate": 1.7304115736010407e-06,
1346
+ "loss": 0.7175,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.739243430551545,
1351
+ "grad_norm": 0.11152032017707825,
1352
+ "learning_rate": 1.6834891968017108e-06,
1353
+ "loss": 0.7115,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.7430936567523342,
1358
+ "grad_norm": 0.1144336611032486,
1359
+ "learning_rate": 1.6370826649692884e-06,
1360
+ "loss": 0.7182,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.7469438829531235,
1365
+ "grad_norm": 0.11825168132781982,
1366
+ "learning_rate": 1.5911991961040463e-06,
1367
+ "loss": 0.7315,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.7507941091539128,
1372
+ "grad_norm": 0.11788872629404068,
1373
+ "learning_rate": 1.545845926849851e-06,
1374
+ "loss": 0.7184,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.7546443353547021,
1379
+ "grad_norm": 0.11926126480102539,
1380
+ "learning_rate": 1.5010299113841397e-06,
1381
+ "loss": 0.7329,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.7584945615554913,
1386
+ "grad_norm": 0.11559195816516876,
1387
+ "learning_rate": 1.4567581203207238e-06,
1388
+ "loss": 0.7303,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.7623447877562807,
1393
+ "grad_norm": 0.11328424513339996,
1394
+ "learning_rate": 1.413037439625593e-06,
1395
+ "loss": 0.7136,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.76619501395707,
1400
+ "grad_norm": 0.12627574801445007,
1401
+ "learning_rate": 1.3698746695458847e-06,
1402
+ "loss": 0.7141,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.7700452401578592,
1407
+ "grad_norm": 0.11168164759874344,
1408
+ "learning_rate": 1.3272765235521745e-06,
1409
+ "loss": 0.7168,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.7738954663586486,
1414
+ "grad_norm": 0.11451941728591919,
1415
+ "learning_rate": 1.2852496272942877e-06,
1416
+ "loss": 0.7173,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.7777456925594378,
1421
+ "grad_norm": 0.10970424860715866,
1422
+ "learning_rate": 1.2438005175707396e-06,
1423
+ "loss": 0.7013,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.7815959187602272,
1428
+ "grad_norm": 0.11347179114818573,
1429
+ "learning_rate": 1.2029356413120297e-06,
1430
+ "loss": 0.6877,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.7854461449610165,
1435
+ "grad_norm": 0.1153201013803482,
1436
+ "learning_rate": 1.1626613545778786e-06,
1437
+ "loss": 0.7056,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.7892963711618057,
1442
+ "grad_norm": 0.11276719719171524,
1443
+ "learning_rate": 1.1229839215686294e-06,
1444
+ "loss": 0.7142,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.7931465973625951,
1449
+ "grad_norm": 0.11720067262649536,
1450
+ "learning_rate": 1.0839095136509188e-06,
1451
+ "loss": 0.692,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.7969968235633843,
1456
+ "grad_norm": 0.12660808861255646,
1457
+ "learning_rate": 1.045444208397791e-06,
1458
+ "loss": 0.7045,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.8008470497641736,
1463
+ "grad_norm": 0.10960297286510468,
1464
+ "learning_rate": 1.007593988643402e-06,
1465
+ "loss": 0.6943,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.804697275964963,
1470
+ "grad_norm": 0.1093006506562233,
1471
+ "learning_rate": 9.703647415524613e-07,
1472
+ "loss": 0.7176,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.8085475021657522,
1477
+ "grad_norm": 0.11444323509931564,
1478
+ "learning_rate": 9.337622577045485e-07,
1479
+ "loss": 0.7118,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.8123977283665416,
1484
+ "grad_norm": 0.11392248421907425,
1485
+ "learning_rate": 8.977922301934588e-07,
1486
+ "loss": 0.7252,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.8162479545673308,
1491
+ "grad_norm": 0.11507934331893921,
1492
+ "learning_rate": 8.624602537417009e-07,
1493
+ "loss": 0.7218,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.8200981807681201,
1498
+ "grad_norm": 0.12052169442176819,
1499
+ "learning_rate": 8.277718238303123e-07,
1500
+ "loss": 0.7046,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.8239484069689095,
1505
+ "grad_norm": 0.11853440850973129,
1506
+ "learning_rate": 7.937323358440935e-07,
1507
+ "loss": 0.7169,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.8277986331696987,
1512
+ "grad_norm": 0.13546203076839447,
1513
+ "learning_rate": 7.603470842324223e-07,
1514
+ "loss": 0.6988,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.831648859370488,
1519
+ "grad_norm": 0.11157195270061493,
1520
+ "learning_rate": 7.276212616857575e-07,
1521
+ "loss": 0.7188,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.8354990855712773,
1526
+ "grad_norm": 0.1148800253868103,
1527
+ "learning_rate": 6.955599583279837e-07,
1528
+ "loss": 0.7194,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.8393493117720666,
1533
+ "grad_norm": 0.11038414388895035,
1534
+ "learning_rate": 6.641681609246981e-07,
1535
+ "loss": 0.7101,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.8431995379728559,
1540
+ "grad_norm": 0.11509692668914795,
1541
+ "learning_rate": 6.334507521075711e-07,
1542
+ "loss": 0.7197,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.8470497641736452,
1547
+ "grad_norm": 0.11786804348230362,
1548
+ "learning_rate": 6.034125096149179e-07,
1549
+ "loss": 0.7062,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.8508999903744345,
1554
+ "grad_norm": 0.14596542716026306,
1555
+ "learning_rate": 5.740581055485722e-07,
1556
+ "loss": 0.6911,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.8547502165752238,
1561
+ "grad_norm": 0.1030445471405983,
1562
+ "learning_rate": 5.453921056471961e-07,
1563
+ "loss": 0.7134,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.8586004427760131,
1568
+ "grad_norm": 0.12131880968809128,
1569
+ "learning_rate": 5.174189685761288e-07,
1570
+ "loss": 0.7085,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.8624506689768023,
1575
+ "grad_norm": 0.11107596009969711,
1576
+ "learning_rate": 4.901430452338979e-07,
1577
+ "loss": 0.7258,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.8663008951775917,
1582
+ "grad_norm": 0.11548212915658951,
1583
+ "learning_rate": 4.6356857807548286e-07,
1584
+ "loss": 0.7081,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.870151121378381,
1589
+ "grad_norm": 0.11594735831022263,
1590
+ "learning_rate": 4.376997004524541e-07,
1591
+ "loss": 0.6973,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.8740013475791703,
1596
+ "grad_norm": 0.10689855366945267,
1597
+ "learning_rate": 4.12540435970073e-07,
1598
+ "loss": 0.6971,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.8778515737799596,
1603
+ "grad_norm": 0.11263618618249893,
1604
+ "learning_rate": 3.880946978614703e-07,
1605
+ "loss": 0.7192,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.8817017999807488,
1610
+ "grad_norm": 0.1101706475019455,
1611
+ "learning_rate": 3.643662883789878e-07,
1612
+ "loss": 0.716,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.8855520261815382,
1617
+ "grad_norm": 0.1105148121714592,
1618
+ "learning_rate": 3.41358898202781e-07,
1619
+ "loss": 0.7014,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.8894022523823275,
1624
+ "grad_norm": 0.10414297878742218,
1625
+ "learning_rate": 3.190761058667741e-07,
1626
+ "loss": 0.7034,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.8932524785831167,
1631
+ "grad_norm": 0.11108338087797165,
1632
+ "learning_rate": 2.9752137720206463e-07,
1633
+ "loss": 0.7115,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.8971027047839061,
1638
+ "grad_norm": 0.11659479886293411,
1639
+ "learning_rate": 2.7669806479785067e-07,
1640
+ "loss": 0.7218,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.9009529309846953,
1645
+ "grad_norm": 0.11061543971300125,
1646
+ "learning_rate": 2.566094074799763e-07,
1647
+ "loss": 0.7106,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.9048031571854847,
1652
+ "grad_norm": 0.1117371916770935,
1653
+ "learning_rate": 2.3725852980716557e-07,
1654
+ "loss": 0.7011,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.908653383386274,
1659
+ "grad_norm": 0.11453350633382797,
1660
+ "learning_rate": 2.1864844158503983e-07,
1661
+ "loss": 0.7119,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.9125036095870632,
1666
+ "grad_norm": 0.11889798194169998,
1667
+ "learning_rate": 2.007820373979702e-07,
1668
+ "loss": 0.7013,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.9163538357878526,
1673
+ "grad_norm": 0.11521857976913452,
1674
+ "learning_rate": 1.8366209615886532e-07,
1675
+ "loss": 0.7069,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.9202040619886418,
1680
+ "grad_norm": 0.11163676530122757,
1681
+ "learning_rate": 1.6729128067693613e-07,
1682
+ "loss": 0.7289,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.9240542881894311,
1687
+ "grad_norm": 0.11653687059879303,
1688
+ "learning_rate": 1.5167213724353426e-07,
1689
+ "loss": 0.7172,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.9279045143902205,
1694
+ "grad_norm": 0.11493801325559616,
1695
+ "learning_rate": 1.3680709523610058e-07,
1696
+ "loss": 0.6993,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.9317547405910097,
1701
+ "grad_norm": 0.1104951798915863,
1702
+ "learning_rate": 1.2269846674030418e-07,
1703
+ "loss": 0.7286,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.935604966791799,
1708
+ "grad_norm": 0.12190693616867065,
1709
+ "learning_rate": 1.0934844619042595e-07,
1710
+ "loss": 0.7208,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.9394551929925883,
1715
+ "grad_norm": 0.1198669895529747,
1716
+ "learning_rate": 9.675911002803961e-08,
1717
+ "loss": 0.7082,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.9433054191933776,
1722
+ "grad_norm": 0.12435677647590637,
1723
+ "learning_rate": 8.493241637904381e-08,
1724
+ "loss": 0.7061,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.9471556453941669,
1729
+ "grad_norm": 0.11743120849132538,
1730
+ "learning_rate": 7.387020474909689e-08,
1731
+ "loss": 0.7274,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.9510058715949562,
1736
+ "grad_norm": 0.1221618503332138,
1737
+ "learning_rate": 6.357419573750856e-08,
1738
+ "loss": 0.715,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.9548560977957455,
1743
+ "grad_norm": 0.11310809850692749,
1744
+ "learning_rate": 5.4045990769613365e-08,
1745
+ "loss": 0.7057,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.9587063239965348,
1750
+ "grad_norm": 0.11679426580667496,
1751
+ "learning_rate": 4.5287071847694434e-08,
1752
+ "loss": 0.7065,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.9625565501973241,
1757
+ "grad_norm": 0.11453266441822052,
1758
+ "learning_rate": 3.7298801320467817e-08,
1759
+ "loss": 0.7086,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.9664067763981133,
1764
+ "grad_norm": 0.11639870703220367,
1765
+ "learning_rate": 3.0082421671192576e-08,
1766
+ "loss": 0.7017,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.9702570025989027,
1771
+ "grad_norm": 0.11039458960294724,
1772
+ "learning_rate": 2.3639055324410355e-08,
1773
+ "loss": 0.7196,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.974107228799692,
1778
+ "grad_norm": 0.11280366033315659,
1779
+ "learning_rate": 1.7969704471369477e-08,
1780
+ "loss": 0.7056,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.9779574550004813,
1785
+ "grad_norm": 0.10807891190052032,
1786
+ "learning_rate": 1.3075250914142413e-08,
1787
+ "loss": 0.7104,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.9818076812012706,
1792
+ "grad_norm": 0.10861364752054214,
1793
+ "learning_rate": 8.956455928476049e-09,
1794
+ "loss": 0.7217,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.9856579074020598,
1799
+ "grad_norm": 0.1007571741938591,
1800
+ "learning_rate": 5.6139601453786275e-09,
1801
+ "loss": 0.6998,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.9895081336028492,
1806
+ "grad_norm": 0.11708196997642517,
1807
+ "learning_rate": 3.0482834514805602e-09,
1808
+ "loss": 0.7046,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.9933583598036385,
1813
+ "grad_norm": 0.11324185132980347,
1814
+ "learning_rate": 1.2598249081713366e-09,
1815
+ "loss": 0.687,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.9972085860044277,
1820
+ "grad_norm": 0.11148441582918167,
1821
+ "learning_rate": 2.488626895302826e-10,
1822
+ "loss": 0.7212,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.9999037443449803,
1827
+ "step": 2597,
1828
+ "total_flos": 6.371953972499972e+18,
1829
+ "train_loss": 0.7395372456846946,
1830
+ "train_runtime": 17952.6919,
1831
+ "train_samples_per_second": 37.036,
1832
+ "train_steps_per_second": 0.145
1833
+ }
1834
+ ],
1835
+ "logging_steps": 10,
1836
+ "max_steps": 2597,
1837
+ "num_input_tokens_seen": 332174164,
1838
+ "num_train_epochs": 1,
1839
+ "save_steps": 500,
1840
+ "stateful_callbacks": {
1841
+ "TrainerControl": {
1842
+ "args": {
1843
+ "should_epoch_stop": false,
1844
+ "should_evaluate": false,
1845
+ "should_log": false,
1846
+ "should_save": true,
1847
+ "should_training_stop": true
1848
+ },
1849
+ "attributes": {}
1850
+ }
1851
+ },
1852
+ "total_flos": 6.371953972499972e+18,
1853
+ "train_batch_size": 4,
1854
+ "trial_name": null,
1855
+ "trial_params": null
1856
+ }
continuous/qwen25/pe_core_g14_448/finetune/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ddddce269b3e96ea66e7479d7e90d58d0ca91440f91b4721ef81fd24d15471a
3
+ size 6264
continuous/qwen25/pe_core_g14_448/finetune/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
continuous/qwen25/pe_core_g14_448/pretrain/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_faster_video": false,
3
+ "add_time_instruction": false,
4
+ "architectures": [
5
+ "Qwen2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "faster_token_stride": 10,
11
+ "force_sample": false,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "image_aspect_ratio": "square",
15
+ "image_crop_resolution": null,
16
+ "image_grid_pinpoints": null,
17
+ "image_split_resolution": null,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8960,
20
+ "layer_types": [
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention"
49
+ ],
50
+ "max_position_embeddings": 32768,
51
+ "max_window_layers": 21,
52
+ "mm_hidden_size": 1536,
53
+ "mm_newline_position": "grid",
54
+ "mm_patch_merge_type": "flat",
55
+ "mm_projector_lr": null,
56
+ "mm_projector_type": "mlp2x_gelu",
57
+ "mm_resampler_type": null,
58
+ "mm_spatial_pool_mode": "bilinear",
59
+ "mm_spatial_pool_stride": null,
60
+ "mm_tunable_parts": "mm_mlp_adapter",
61
+ "mm_use_im_patch_token": false,
62
+ "mm_use_im_start_end": false,
63
+ "mm_vision_select_feature": "patch",
64
+ "mm_vision_select_layer": -1,
65
+ "mm_vision_tower": "vtb_ssl:pe",
66
+ "mm_vision_tower_lr": null,
67
+ "model_type": "qwen2",
68
+ "num_attention_heads": 12,
69
+ "num_hidden_layers": 28,
70
+ "num_key_value_heads": 2,
71
+ "pad_token_id": 151643,
72
+ "pos_skipping_range": 4096,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": null,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_model_max_length": 8192,
79
+ "tokenizer_padding_side": "right",
80
+ "transformers_version": "4.57.6",
81
+ "use_cache": true,
82
+ "use_mm_proj": true,
83
+ "use_pos_skipping": false,
84
+ "use_sliding_window": false,
85
+ "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Core-G14-448/PE-Core-G14-448.pt",
86
+ "vocab_size": 151936
87
+ }
continuous/qwen25/pe_core_g14_448/pretrain/mm_projector.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def8703d2981d3049c7a099257923b9c3ca0fb5361f77fe949888fc3ba164a57
3
+ size 18888760
continuous/qwen25/pe_core_g14_448/pretrain/trainer_state.json ADDED
@@ -0,0 +1,421 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 545,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01834862385321101,
14
+ "grad_norm": 0.39481446146965027,
15
+ "learning_rate": 0.00032142857142857147,
16
+ "loss": 4.8408,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.03669724770642202,
21
+ "grad_norm": 0.19814623892307281,
22
+ "learning_rate": 0.0006785714285714287,
23
+ "loss": 3.8273,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.05504587155963303,
28
+ "grad_norm": 0.08985866606235504,
29
+ "learning_rate": 0.0009999907688176173,
30
+ "loss": 3.4194,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.07339449541284404,
35
+ "grad_norm": 0.04323100298643112,
36
+ "learning_rate": 0.0009988834393115766,
37
+ "loss": 3.3041,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.09174311926605505,
42
+ "grad_norm": 0.03598347306251526,
43
+ "learning_rate": 0.0009959345572940772,
44
+ "loss": 3.2624,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.11009174311926606,
49
+ "grad_norm": 0.03775301203131676,
50
+ "learning_rate": 0.0009911550081155983,
51
+ "loss": 3.2256,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.12844036697247707,
56
+ "grad_norm": 0.04388684034347534,
57
+ "learning_rate": 0.0009845624347566433,
58
+ "loss": 3.1883,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.14678899082568808,
63
+ "grad_norm": 0.060684382915496826,
64
+ "learning_rate": 0.0009761811727013547,
65
+ "loss": 3.1563,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1651376146788991,
70
+ "grad_norm": 0.048251211643218994,
71
+ "learning_rate": 0.0009660421601067666,
72
+ "loss": 3.1211,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.1834862385321101,
77
+ "grad_norm": 0.061564672738313675,
78
+ "learning_rate": 0.0009541828235992926,
79
+ "loss": 3.0905,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2018348623853211,
84
+ "grad_norm": 0.05936511978507042,
85
+ "learning_rate": 0.0009406469401200151,
86
+ "loss": 3.0467,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.22018348623853212,
91
+ "grad_norm": 0.07949792593717575,
92
+ "learning_rate": 0.0009254844753287492,
93
+ "loss": 3.0177,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.23853211009174313,
98
+ "grad_norm": 0.07717183232307434,
99
+ "learning_rate": 0.0009087513991633924,
100
+ "loss": 2.9673,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.25688073394495414,
105
+ "grad_norm": 0.08451516926288605,
106
+ "learning_rate": 0.0008905094792353917,
107
+ "loss": 2.937,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.27522935779816515,
112
+ "grad_norm": 0.08765852451324463,
113
+ "learning_rate": 0.0008708260528239789,
114
+ "loss": 2.911,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.29357798165137616,
119
+ "grad_norm": 0.09549334645271301,
120
+ "learning_rate": 0.0008497737783108237,
121
+ "loss": 2.8778,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.3119266055045872,
126
+ "grad_norm": 0.08404996991157532,
127
+ "learning_rate": 0.0008274303669726426,
128
+ "loss": 2.861,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.3302752293577982,
133
+ "grad_norm": 0.0880809798836708,
134
+ "learning_rate": 0.0008038782961218137,
135
+ "loss": 2.833,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.3486238532110092,
140
+ "grad_norm": 0.08382479846477509,
141
+ "learning_rate": 0.000779204504653894,
142
+ "loss": 2.8196,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.3669724770642202,
147
+ "grad_norm": 0.08560793846845627,
148
+ "learning_rate": 0.0007535000721258791,
149
+ "loss": 2.7886,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.3853211009174312,
154
+ "grad_norm": 0.08857789635658264,
155
+ "learning_rate": 0.00072685988254984,
156
+ "loss": 2.7767,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.4036697247706422,
161
+ "grad_norm": 0.09514912217855453,
162
+ "learning_rate": 0.0006993822741429906,
163
+ "loss": 2.7824,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.42201834862385323,
168
+ "grad_norm": 0.09922544658184052,
169
+ "learning_rate": 0.0006711686763270818,
170
+ "loss": 2.7667,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.44036697247706424,
175
+ "grad_norm": 0.09181252866983414,
176
+ "learning_rate": 0.0006423232353170831,
177
+ "loss": 2.7528,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.45871559633027525,
182
+ "grad_norm": 0.09831017255783081,
183
+ "learning_rate": 0.0006129524296812335,
184
+ "loss": 2.7369,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.47706422018348627,
189
+ "grad_norm": 0.09956222027540207,
190
+ "learning_rate": 0.0005831646772915651,
191
+ "loss": 2.7386,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.4954128440366973,
196
+ "grad_norm": 0.09485175460577011,
197
+ "learning_rate": 0.0005530699351157809,
198
+ "loss": 2.716,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.5137614678899083,
203
+ "grad_norm": 0.08592832833528519,
204
+ "learning_rate": 0.0005227792933277943,
205
+ "loss": 2.7129,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.5321100917431193,
210
+ "grad_norm": 0.09075655043125153,
211
+ "learning_rate": 0.0004924045652352092,
212
+ "loss": 2.6967,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.5504587155963303,
217
+ "grad_norm": 0.09596816450357437,
218
+ "learning_rate": 0.0004620578745374633,
219
+ "loss": 2.6947,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.5688073394495413,
224
+ "grad_norm": 0.10986959934234619,
225
+ "learning_rate": 0.0004318512414382059,
226
+ "loss": 2.699,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.5871559633027523,
231
+ "grad_norm": 0.09286665171384811,
232
+ "learning_rate": 0.0004018961691397148,
233
+ "loss": 2.6934,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.6055045871559633,
238
+ "grad_norm": 0.10134488344192505,
239
+ "learning_rate": 0.0003723032322457458,
240
+ "loss": 2.6728,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.6238532110091743,
245
+ "grad_norm": 0.1129816472530365,
246
+ "learning_rate": 0.0003431816685921625,
247
+ "loss": 2.6744,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.6422018348623854,
252
+ "grad_norm": 0.09781069308519363,
253
+ "learning_rate": 0.0003146389760120416,
254
+ "loss": 2.6734,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.6605504587155964,
259
+ "grad_norm": 0.0898892730474472,
260
+ "learning_rate": 0.00028678051552373485,
261
+ "loss": 2.6734,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.6788990825688074,
266
+ "grad_norm": 0.09403355419635773,
267
+ "learning_rate": 0.0002597091224066581,
268
+ "loss": 2.6623,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.6972477064220184,
273
+ "grad_norm": 0.08949156105518341,
274
+ "learning_rate": 0.0002335247266004629,
275
+ "loss": 2.6671,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.7155963302752294,
280
+ "grad_norm": 0.09519299119710922,
281
+ "learning_rate": 0.000208323983828828,
282
+ "loss": 2.6554,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.7339449541284404,
287
+ "grad_norm": 0.08692976087331772,
288
+ "learning_rate": 0.0001841999188095224,
289
+ "loss": 2.6458,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.7522935779816514,
294
+ "grad_norm": 0.08561374992132187,
295
+ "learning_rate": 0.00016124158186777676,
296
+ "loss": 2.6478,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.7706422018348624,
301
+ "grad_norm": 0.08929994702339172,
302
+ "learning_rate": 0.0001395337202205211,
303
+ "loss": 2.6404,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.7889908256880734,
308
+ "grad_norm": 0.09562073647975922,
309
+ "learning_rate": 0.00011915646514489292,
310
+ "loss": 2.6358,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.8073394495412844,
315
+ "grad_norm": 0.08905952423810959,
316
+ "learning_rate": 0.00010018503618578818,
317
+ "loss": 2.6456,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.8256880733944955,
322
+ "grad_norm": 0.09201698750257492,
323
+ "learning_rate": 8.268946349432583e-05,
324
+ "loss": 2.6373,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.8440366972477065,
329
+ "grad_norm": 0.0910116583108902,
330
+ "learning_rate": 6.673432932217117e-05,
331
+ "loss": 2.6258,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.8623853211009175,
336
+ "grad_norm": 0.08695732057094574,
337
+ "learning_rate": 5.2378529625954684e-05,
338
+ "loss": 2.6175,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.8807339449541285,
343
+ "grad_norm": 0.08875082433223724,
344
+ "learning_rate": 3.9675056661785556e-05,
345
+ "loss": 2.6233,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.8990825688073395,
350
+ "grad_norm": 0.08607099950313568,
351
+ "learning_rate": 2.8670803372379538e-05,
352
+ "loss": 2.6309,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.9174311926605505,
357
+ "grad_norm": 0.08690930902957916,
358
+ "learning_rate": 1.9406390288876586e-05,
359
+ "loss": 2.6362,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.9357798165137615,
364
+ "grad_norm": 0.08564309775829315,
365
+ "learning_rate": 1.191601558631461e-05,
366
+ "loss": 2.623,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.9541284403669725,
371
+ "grad_norm": 0.08585304766893387,
372
+ "learning_rate": 6.2273288462559305e-06,
373
+ "loss": 2.6187,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.9724770642201835,
378
+ "grad_norm": 0.08487770706415176,
379
+ "learning_rate": 2.361328992552314e-06,
380
+ "loss": 2.6191,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.9908256880733946,
385
+ "grad_norm": 0.08831780403852463,
386
+ "learning_rate": 3.322867770044202e-07,
387
+ "loss": 2.6221,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.0,
392
+ "step": 545,
393
+ "total_flos": 6.11857667291349e+17,
394
+ "train_loss": 2.8573217916926112,
395
+ "train_runtime": 7827.101,
396
+ "train_samples_per_second": 71.307,
397
+ "train_steps_per_second": 0.07
398
+ }
399
+ ],
400
+ "logging_steps": 10,
401
+ "max_steps": 545,
402
+ "num_input_tokens_seen": 31896544,
403
+ "num_train_epochs": 1,
404
+ "save_steps": 500,
405
+ "stateful_callbacks": {
406
+ "TrainerControl": {
407
+ "args": {
408
+ "should_epoch_stop": false,
409
+ "should_evaluate": false,
410
+ "should_log": false,
411
+ "should_save": false,
412
+ "should_training_stop": false
413
+ },
414
+ "attributes": {}
415
+ }
416
+ },
417
+ "total_flos": 6.11857667291349e+17,
418
+ "train_batch_size": 32,
419
+ "trial_name": null,
420
+ "trial_params": null
421
+ }
continuous/qwen25/pe_core_l14_336/finetune/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
+ }
continuous/qwen25/pe_core_l14_336/finetune/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
continuous/qwen25/pe_core_l14_336/finetune/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_faster_video": false,
3
+ "add_time_instruction": false,
4
+ "architectures": [
5
+ "LlavaQwenForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "faster_token_stride": 10,
11
+ "force_sample": false,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "image_aspect_ratio": "square",
15
+ "image_crop_resolution": null,
16
+ "image_grid_pinpoints": null,
17
+ "image_split_resolution": null,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8960,
20
+ "layer_types": [
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention"
49
+ ],
50
+ "max_position_embeddings": 32768,
51
+ "max_window_layers": 21,
52
+ "mm_hidden_size": 1024,
53
+ "mm_newline_position": "grid",
54
+ "mm_patch_merge_type": "flat",
55
+ "mm_projector_lr": 0.0001,
56
+ "mm_projector_type": "mlp2x_gelu",
57
+ "mm_resampler_type": null,
58
+ "mm_spatial_pool_mode": "bilinear",
59
+ "mm_spatial_pool_stride": null,
60
+ "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
61
+ "mm_use_im_patch_token": false,
62
+ "mm_use_im_start_end": false,
63
+ "mm_vision_select_feature": "patch",
64
+ "mm_vision_select_layer": -1,
65
+ "mm_vision_tower": "vtb_ssl:pe",
66
+ "mm_vision_tower_lr": null,
67
+ "model_type": "qwen2",
68
+ "num_attention_heads": 12,
69
+ "num_hidden_layers": 28,
70
+ "num_key_value_heads": 2,
71
+ "pad_token_id": 151643,
72
+ "pos_skipping_range": 4096,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": null,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_model_max_length": 8192,
79
+ "tokenizer_padding_side": "right",
80
+ "transformers_version": "4.57.6",
81
+ "use_cache": true,
82
+ "use_mm_proj": true,
83
+ "use_pos_skipping": false,
84
+ "use_sliding_window": false,
85
+ "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Core-L14-336/PE-Core-L14-336.pt",
86
+ "vocab_size": 151936
87
+ }
continuous/qwen25/pe_core_l14_336/finetune/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.1,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.6"
13
+ }
continuous/qwen25/pe_core_l14_336/finetune/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
continuous/qwen25/pe_core_l14_336/finetune/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d6daed1b6286d502fd1127d680a80a6e95f199ef34f34ab74350c0ea79cae55
3
+ size 4204303224
continuous/qwen25/pe_core_l14_336/finetune/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
+ }
continuous/qwen25/pe_core_l14_336/finetune/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
continuous/qwen25/pe_core_l14_336/finetune/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 8192,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
continuous/qwen25/pe_core_l14_336/finetune/trainer_state.json ADDED
@@ -0,0 +1,1856 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9999037443449803,
6
+ "eval_steps": 500,
7
+ "global_step": 2597,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.003850226200789296,
14
+ "grad_norm": 16.84551429748535,
15
+ "learning_rate": 1.153846153846154e-06,
16
+ "loss": 1.7892,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.007700452401578592,
21
+ "grad_norm": 8.263071060180664,
22
+ "learning_rate": 2.435897435897436e-06,
23
+ "loss": 1.4545,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.01155067860236789,
28
+ "grad_norm": 3.5514397621154785,
29
+ "learning_rate": 3.7179487179487184e-06,
30
+ "loss": 1.0725,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.015400904803157185,
35
+ "grad_norm": 0.712310791015625,
36
+ "learning_rate": 5e-06,
37
+ "loss": 0.9286,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.019251131003946483,
42
+ "grad_norm": 0.36908745765686035,
43
+ "learning_rate": 6.282051282051282e-06,
44
+ "loss": 0.8974,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.02310135720473578,
49
+ "grad_norm": 0.3151516020298004,
50
+ "learning_rate": 7.564102564102564e-06,
51
+ "loss": 0.853,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.026951583405525073,
56
+ "grad_norm": 0.2740204930305481,
57
+ "learning_rate": 8.846153846153847e-06,
58
+ "loss": 0.8293,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.03080180960631437,
63
+ "grad_norm": 0.2886011302471161,
64
+ "learning_rate": 9.999996111488723e-06,
65
+ "loss": 0.8362,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.034652035807103666,
70
+ "grad_norm": 0.2680872976779938,
71
+ "learning_rate": 9.999529497453782e-06,
72
+ "loss": 0.8174,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.038502262007892966,
77
+ "grad_norm": 0.2560257017612457,
78
+ "learning_rate": 9.998285264324193e-06,
79
+ "loss": 0.7938,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.04235248820868226,
84
+ "grad_norm": 0.23932288587093353,
85
+ "learning_rate": 9.996263605626052e-06,
86
+ "loss": 0.7849,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.04620271440947156,
91
+ "grad_norm": 0.2551158368587494,
92
+ "learning_rate": 9.99346483580503e-06,
93
+ "loss": 0.797,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.05005294061026085,
98
+ "grad_norm": 0.2440168708562851,
99
+ "learning_rate": 9.989889390177467e-06,
100
+ "loss": 0.7845,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.053903166811050146,
105
+ "grad_norm": 0.26039016246795654,
106
+ "learning_rate": 9.985537824862647e-06,
107
+ "loss": 0.7867,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.057753393011839446,
112
+ "grad_norm": 0.27778303623199463,
113
+ "learning_rate": 9.980410816696317e-06,
114
+ "loss": 0.7654,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.06160361921262874,
119
+ "grad_norm": 0.25828075408935547,
120
+ "learning_rate": 9.97450916312541e-06,
121
+ "loss": 0.7754,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.06545384541341803,
126
+ "grad_norm": 0.2177531123161316,
127
+ "learning_rate": 9.967833782084004e-06,
128
+ "loss": 0.777,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.06930407161420733,
133
+ "grad_norm": 0.2655026316642761,
134
+ "learning_rate": 9.960385711850554e-06,
135
+ "loss": 0.7999,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.07315429781499663,
140
+ "grad_norm": 0.2557540237903595,
141
+ "learning_rate": 9.952166110886394e-06,
142
+ "loss": 0.7914,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.07700452401578593,
147
+ "grad_norm": 0.2918579876422882,
148
+ "learning_rate": 9.943176257655567e-06,
149
+ "loss": 0.7822,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.08085475021657522,
154
+ "grad_norm": 0.24181726574897766,
155
+ "learning_rate": 9.933417550425952e-06,
156
+ "loss": 0.7773,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.08470497641736452,
161
+ "grad_norm": 0.25412923097610474,
162
+ "learning_rate": 9.9228915070518e-06,
163
+ "loss": 0.7601,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.08855520261815382,
168
+ "grad_norm": 0.25493207573890686,
169
+ "learning_rate": 9.911599764737632e-06,
170
+ "loss": 0.7644,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.09240542881894312,
175
+ "grad_norm": 0.24505974352359772,
176
+ "learning_rate": 9.899544079783606e-06,
177
+ "loss": 0.7573,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.0962556550197324,
182
+ "grad_norm": 0.24733063578605652,
183
+ "learning_rate": 9.886726327312338e-06,
184
+ "loss": 0.7741,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.1001058812205217,
189
+ "grad_norm": 0.23546834290027618,
190
+ "learning_rate": 9.87314850097724e-06,
191
+ "loss": 0.7709,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.103956107421311,
196
+ "grad_norm": 0.25040510296821594,
197
+ "learning_rate": 9.858812712652452e-06,
198
+ "loss": 0.7588,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.10780633362210029,
203
+ "grad_norm": 0.2366444319486618,
204
+ "learning_rate": 9.843721192104341e-06,
205
+ "loss": 0.7576,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.11165655982288959,
210
+ "grad_norm": 0.23723086714744568,
211
+ "learning_rate": 9.827876286644698e-06,
212
+ "loss": 0.7784,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.11550678602367889,
217
+ "grad_norm": 0.22453834116458893,
218
+ "learning_rate": 9.811280460765643e-06,
219
+ "loss": 0.7411,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.11935701222446819,
224
+ "grad_norm": 0.24234910309314728,
225
+ "learning_rate": 9.793936295756292e-06,
226
+ "loss": 0.7479,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.12320723842525748,
231
+ "grad_norm": 0.24358582496643066,
232
+ "learning_rate": 9.775846489301279e-06,
233
+ "loss": 0.7562,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.12705746462604678,
238
+ "grad_norm": 0.246526837348938,
239
+ "learning_rate": 9.757013855061157e-06,
240
+ "loss": 0.7529,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.13090769082683607,
245
+ "grad_norm": 0.24150966107845306,
246
+ "learning_rate": 9.737441322234758e-06,
247
+ "loss": 0.7646,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.13475791702762538,
252
+ "grad_norm": 0.24096515774726868,
253
+ "learning_rate": 9.717131935103605e-06,
254
+ "loss": 0.7648,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.13860814322841467,
259
+ "grad_norm": 0.23921038210391998,
260
+ "learning_rate": 9.696088852558398e-06,
261
+ "loss": 0.7502,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.14245836942920398,
266
+ "grad_norm": 0.24209699034690857,
267
+ "learning_rate": 9.674315347607686e-06,
268
+ "loss": 0.7779,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.14630859562999327,
273
+ "grad_norm": 0.22919267416000366,
274
+ "learning_rate": 9.651814806868796e-06,
275
+ "loss": 0.7429,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.15015882183078255,
280
+ "grad_norm": 0.24360312521457672,
281
+ "learning_rate": 9.62859073004107e-06,
282
+ "loss": 0.7425,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.15400904803157187,
287
+ "grad_norm": 0.22040630877017975,
288
+ "learning_rate": 9.604646729361547e-06,
289
+ "loss": 0.7464,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.15785927423236115,
294
+ "grad_norm": 0.23609554767608643,
295
+ "learning_rate": 9.579986529043099e-06,
296
+ "loss": 0.738,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.16170950043315044,
301
+ "grad_norm": 0.2331172525882721,
302
+ "learning_rate": 9.554613964695189e-06,
303
+ "loss": 0.7555,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.16555972663393975,
308
+ "grad_norm": 0.23904968798160553,
309
+ "learning_rate": 9.528532982727281e-06,
310
+ "loss": 0.7493,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.16940995283472904,
315
+ "grad_norm": 0.22223885357379913,
316
+ "learning_rate": 9.501747639735018e-06,
317
+ "loss": 0.7431,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.17326017903551832,
322
+ "grad_norm": 0.23074287176132202,
323
+ "learning_rate": 9.474262101869272e-06,
324
+ "loss": 0.7344,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.17711040523630764,
329
+ "grad_norm": 0.23723791539669037,
330
+ "learning_rate": 9.446080644188141e-06,
331
+ "loss": 0.7401,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.18096063143709692,
336
+ "grad_norm": 0.22065789997577667,
337
+ "learning_rate": 9.417207649992017e-06,
338
+ "loss": 0.7441,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.18481085763788624,
343
+ "grad_norm": 0.23571328818798065,
344
+ "learning_rate": 9.387647610141816e-06,
345
+ "loss": 0.7423,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.18866108383867553,
350
+ "grad_norm": 0.2138325273990631,
351
+ "learning_rate": 9.35740512236047e-06,
352
+ "loss": 0.7314,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.1925113100394648,
357
+ "grad_norm": 0.22418254613876343,
358
+ "learning_rate": 9.326484890517809e-06,
359
+ "loss": 0.7435,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.19636153624025413,
364
+ "grad_norm": 0.23921112716197968,
365
+ "learning_rate": 9.294891723898926e-06,
366
+ "loss": 0.7316,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.2002117624410434,
371
+ "grad_norm": 0.25048619508743286,
372
+ "learning_rate": 9.262630536456153e-06,
373
+ "loss": 0.7615,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.2040619886418327,
378
+ "grad_norm": 0.24124373495578766,
379
+ "learning_rate": 9.229706346044749e-06,
380
+ "loss": 0.7371,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.207912214842622,
385
+ "grad_norm": 0.2478654831647873,
386
+ "learning_rate": 9.196124273642422e-06,
387
+ "loss": 0.7458,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.2117624410434113,
392
+ "grad_norm": 0.23326949775218964,
393
+ "learning_rate": 9.161889542552842e-06,
394
+ "loss": 0.7532,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.21561266724420058,
399
+ "grad_norm": 0.22033269703388214,
400
+ "learning_rate": 9.127007477593193e-06,
401
+ "loss": 0.7518,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.2194628934449899,
406
+ "grad_norm": 0.25935474038124084,
407
+ "learning_rate": 9.091483504265974e-06,
408
+ "loss": 0.759,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.22331311964577918,
413
+ "grad_norm": 0.24067433178424835,
414
+ "learning_rate": 9.055323147915116e-06,
415
+ "loss": 0.7401,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.2271633458465685,
420
+ "grad_norm": 0.2392929047346115,
421
+ "learning_rate": 9.018532032866585e-06,
422
+ "loss": 0.7481,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.23101357204735778,
427
+ "grad_norm": 0.2222733348608017,
428
+ "learning_rate": 8.981115881553579e-06,
429
+ "loss": 0.7422,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.23486379824814707,
434
+ "grad_norm": 0.2578257918357849,
435
+ "learning_rate": 8.943080513626476e-06,
436
+ "loss": 0.7611,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.23871402444893638,
441
+ "grad_norm": 0.23604415357112885,
442
+ "learning_rate": 8.904431845047641e-06,
443
+ "loss": 0.747,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.24256425064972567,
448
+ "grad_norm": 0.24020303785800934,
449
+ "learning_rate": 8.86517588717128e-06,
450
+ "loss": 0.7631,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.24641447685051496,
455
+ "grad_norm": 0.220405712723732,
456
+ "learning_rate": 8.82531874580844e-06,
457
+ "loss": 0.7587,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.25026470305130427,
462
+ "grad_norm": 0.21404320001602173,
463
+ "learning_rate": 8.784866620277314e-06,
464
+ "loss": 0.7146,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.25411492925209356,
469
+ "grad_norm": 0.2435895949602127,
470
+ "learning_rate": 8.743825802439018e-06,
471
+ "loss": 0.7422,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.25796515545288284,
476
+ "grad_norm": 0.26877251267433167,
477
+ "learning_rate": 8.702202675718956e-06,
478
+ "loss": 0.7543,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.26181538165367213,
483
+ "grad_norm": 0.21779081225395203,
484
+ "learning_rate": 8.660003714113959e-06,
485
+ "loss": 0.7211,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.26566560785446147,
490
+ "grad_norm": 0.2264346182346344,
491
+ "learning_rate": 8.617235481185323e-06,
492
+ "loss": 0.7421,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.26951583405525076,
497
+ "grad_norm": 0.2521556615829468,
498
+ "learning_rate": 8.573904629037931e-06,
499
+ "loss": 0.75,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.27336606025604004,
504
+ "grad_norm": 0.22575032711029053,
505
+ "learning_rate": 8.530017897285585e-06,
506
+ "loss": 0.733,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.27721628645682933,
511
+ "grad_norm": 0.20724047720432281,
512
+ "learning_rate": 8.485582112002746e-06,
513
+ "loss": 0.7406,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.2810665126576186,
518
+ "grad_norm": 0.22396576404571533,
519
+ "learning_rate": 8.440604184662811e-06,
520
+ "loss": 0.7385,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.28491673885840796,
525
+ "grad_norm": 0.22596168518066406,
526
+ "learning_rate": 8.395091111063118e-06,
527
+ "loss": 0.7302,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.28876696505919724,
532
+ "grad_norm": 0.2072855532169342,
533
+ "learning_rate": 8.349049970236822e-06,
534
+ "loss": 0.7307,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.29261719125998653,
539
+ "grad_norm": 0.22827614843845367,
540
+ "learning_rate": 8.302487923351842e-06,
541
+ "loss": 0.7205,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.2964674174607758,
546
+ "grad_norm": 0.22411444783210754,
547
+ "learning_rate": 8.255412212597021e-06,
548
+ "loss": 0.7403,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.3003176436615651,
553
+ "grad_norm": 0.2177380621433258,
554
+ "learning_rate": 8.207830160055688e-06,
555
+ "loss": 0.7368,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.3041678698623544,
560
+ "grad_norm": 0.22460579872131348,
561
+ "learning_rate": 8.159749166566786e-06,
562
+ "loss": 0.7227,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.30801809606314373,
567
+ "grad_norm": 0.21953478455543518,
568
+ "learning_rate": 8.11117671057377e-06,
569
+ "loss": 0.7471,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.311868322263933,
574
+ "grad_norm": 0.24367427825927734,
575
+ "learning_rate": 8.062120346961404e-06,
576
+ "loss": 0.7377,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.3157185484647223,
581
+ "grad_norm": 0.2138199359178543,
582
+ "learning_rate": 8.012587705880705e-06,
583
+ "loss": 0.7342,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.3195687746655116,
588
+ "grad_norm": 0.21690304577350616,
589
+ "learning_rate": 7.962586491562146e-06,
590
+ "loss": 0.7198,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.3234190008663009,
595
+ "grad_norm": 0.2438443899154663,
596
+ "learning_rate": 7.912124481117357e-06,
597
+ "loss": 0.7245,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.3272692270670902,
602
+ "grad_norm": 0.22192181646823883,
603
+ "learning_rate": 7.861209523329494e-06,
604
+ "loss": 0.7407,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.3311194532678795,
609
+ "grad_norm": 0.22695297002792358,
610
+ "learning_rate": 7.809849537432432e-06,
611
+ "loss": 0.7218,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.3349696794686688,
616
+ "grad_norm": 0.22569270431995392,
617
+ "learning_rate": 7.758052511879035e-06,
618
+ "loss": 0.7325,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.3388199056694581,
623
+ "grad_norm": 0.21625623106956482,
624
+ "learning_rate": 7.705826503098642e-06,
625
+ "loss": 0.7256,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.34267013187024736,
630
+ "grad_norm": 0.21995940804481506,
631
+ "learning_rate": 7.653179634243979e-06,
632
+ "loss": 0.7286,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.34652035807103665,
637
+ "grad_norm": 0.20020437240600586,
638
+ "learning_rate": 7.600120093927696e-06,
639
+ "loss": 0.7285,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.350370584271826,
644
+ "grad_norm": 0.23818418383598328,
645
+ "learning_rate": 7.546656134948729e-06,
646
+ "loss": 0.7134,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.3542208104726153,
651
+ "grad_norm": 0.2268024981021881,
652
+ "learning_rate": 7.492796073008661e-06,
653
+ "loss": 0.7184,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.35807103667340456,
658
+ "grad_norm": 0.2423514574766159,
659
+ "learning_rate": 7.438548285418326e-06,
660
+ "loss": 0.7077,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.36192126287419385,
665
+ "grad_norm": 0.24127864837646484,
666
+ "learning_rate": 7.3839212097948e-06,
667
+ "loss": 0.7407,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.36577148907498314,
672
+ "grad_norm": 0.22991707921028137,
673
+ "learning_rate": 7.328923342749039e-06,
674
+ "loss": 0.7577,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.3696217152757725,
679
+ "grad_norm": 0.2373737096786499,
680
+ "learning_rate": 7.273563238564319e-06,
681
+ "loss": 0.7416,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.37347194147656176,
686
+ "grad_norm": 0.2252638041973114,
687
+ "learning_rate": 7.217849507865724e-06,
688
+ "loss": 0.717,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.37732216767735105,
693
+ "grad_norm": 0.21792437136173248,
694
+ "learning_rate": 7.161790816280858e-06,
695
+ "loss": 0.7285,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.38117239387814034,
700
+ "grad_norm": 0.23382404446601868,
701
+ "learning_rate": 7.1053958830920125e-06,
702
+ "loss": 0.7052,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.3850226200789296,
707
+ "grad_norm": 0.2222089320421219,
708
+ "learning_rate": 7.0486734798799715e-06,
709
+ "loss": 0.7268,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.3888728462797189,
714
+ "grad_norm": 0.2213781476020813,
715
+ "learning_rate": 6.991632429159708e-06,
716
+ "loss": 0.751,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.39272307248050825,
721
+ "grad_norm": 0.24251770973205566,
722
+ "learning_rate": 6.934281603008132e-06,
723
+ "loss": 0.7398,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.39657329868129754,
728
+ "grad_norm": 0.22661496698856354,
729
+ "learning_rate": 6.876629921684143e-06,
730
+ "loss": 0.739,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.4004235248820868,
735
+ "grad_norm": 0.229758158326149,
736
+ "learning_rate": 6.818686352241199e-06,
737
+ "loss": 0.7281,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.4042737510828761,
742
+ "grad_norm": 0.20646047592163086,
743
+ "learning_rate": 6.760459907132573e-06,
744
+ "loss": 0.7257,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.4081239772836654,
749
+ "grad_norm": 0.20980824530124664,
750
+ "learning_rate": 6.701959642809589e-06,
751
+ "loss": 0.7296,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.41197420348445474,
756
+ "grad_norm": 0.22794947028160095,
757
+ "learning_rate": 6.643194658312987e-06,
758
+ "loss": 0.7184,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.415824429685244,
763
+ "grad_norm": 0.21621042490005493,
764
+ "learning_rate": 6.584174093857676e-06,
765
+ "loss": 0.7455,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.4196746558860333,
770
+ "grad_norm": 0.24947792291641235,
771
+ "learning_rate": 6.5249071294110735e-06,
772
+ "loss": 0.7288,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.4235248820868226,
777
+ "grad_norm": 0.22646251320838928,
778
+ "learning_rate": 6.465402983265274e-06,
779
+ "loss": 0.743,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.4273751082876119,
784
+ "grad_norm": 0.23079213500022888,
785
+ "learning_rate": 6.405670910603243e-06,
786
+ "loss": 0.737,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.43122533448840117,
791
+ "grad_norm": 0.24848900735378265,
792
+ "learning_rate": 6.345720202059291e-06,
793
+ "loss": 0.7338,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.4350755606891905,
798
+ "grad_norm": 0.23059658706188202,
799
+ "learning_rate": 6.285560182274008e-06,
800
+ "loss": 0.7113,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.4389257868899798,
805
+ "grad_norm": 0.22721830010414124,
806
+ "learning_rate": 6.225200208443936e-06,
807
+ "loss": 0.7352,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.4427760130907691,
812
+ "grad_norm": 0.22049985826015472,
813
+ "learning_rate": 6.16464966886616e-06,
814
+ "loss": 0.7236,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.44662623929155837,
819
+ "grad_norm": 0.2618195414543152,
820
+ "learning_rate": 6.103917981478065e-06,
821
+ "loss": 0.7497,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.45047646549234766,
826
+ "grad_norm": 0.22171983122825623,
827
+ "learning_rate": 6.043014592392489e-06,
828
+ "loss": 0.7584,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.454326691693137,
833
+ "grad_norm": 0.2122264951467514,
834
+ "learning_rate": 5.981948974428485e-06,
835
+ "loss": 0.7329,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.4581769178939263,
840
+ "grad_norm": 0.21923209726810455,
841
+ "learning_rate": 5.920730625637934e-06,
842
+ "loss": 0.7097,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.46202714409471557,
847
+ "grad_norm": 0.23183771967887878,
848
+ "learning_rate": 5.8593690678282355e-06,
849
+ "loss": 0.7261,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.46587737029550486,
854
+ "grad_norm": 0.23105807602405548,
855
+ "learning_rate": 5.797873845081301e-06,
856
+ "loss": 0.7292,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.46972759649629414,
861
+ "grad_norm": 0.23266646265983582,
862
+ "learning_rate": 5.736254522269075e-06,
863
+ "loss": 0.7429,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.47357782269708343,
868
+ "grad_norm": 0.22191940248012543,
869
+ "learning_rate": 5.6745206835658386e-06,
870
+ "loss": 0.7487,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.47742804889787277,
875
+ "grad_norm": 0.21146529912948608,
876
+ "learning_rate": 5.612681930957495e-06,
877
+ "loss": 0.7169,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.48127827509866206,
882
+ "grad_norm": 0.21221579611301422,
883
+ "learning_rate": 5.550747882748095e-06,
884
+ "loss": 0.7118,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.48512850129945134,
889
+ "grad_norm": 0.24004513025283813,
890
+ "learning_rate": 5.4887281720638195e-06,
891
+ "loss": 0.7259,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.48897872750024063,
896
+ "grad_norm": 0.25321313738822937,
897
+ "learning_rate": 5.42663244535466e-06,
898
+ "loss": 0.7058,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.4928289537010299,
903
+ "grad_norm": 0.23067393898963928,
904
+ "learning_rate": 5.3644703608940205e-06,
905
+ "loss": 0.7171,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.49667917990181926,
910
+ "grad_norm": 0.23892945051193237,
911
+ "learning_rate": 5.302251587276491e-06,
912
+ "loss": 0.7258,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.5005294061026085,
917
+ "grad_norm": 0.21814614534378052,
918
+ "learning_rate": 5.2399858019140005e-06,
919
+ "loss": 0.7269,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.5043796323033978,
924
+ "grad_norm": 0.21333502233028412,
925
+ "learning_rate": 5.177682689530615e-06,
926
+ "loss": 0.7421,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.5082298585041871,
931
+ "grad_norm": 0.23456589877605438,
932
+ "learning_rate": 5.11535194065619e-06,
933
+ "loss": 0.7094,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.5120800847049765,
938
+ "grad_norm": 0.24140198528766632,
939
+ "learning_rate": 5.053003250119113e-06,
940
+ "loss": 0.7165,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.5159303109057657,
945
+ "grad_norm": 0.24183183908462524,
946
+ "learning_rate": 4.9906463155383925e-06,
947
+ "loss": 0.7263,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.519780537106555,
952
+ "grad_norm": 0.22483964264392853,
953
+ "learning_rate": 4.9282908358153046e-06,
954
+ "loss": 0.7229,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.5236307633073443,
959
+ "grad_norm": 0.25656479597091675,
960
+ "learning_rate": 4.8659465096248345e-06,
961
+ "loss": 0.7356,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.5274809895081336,
966
+ "grad_norm": 0.22551442682743073,
967
+ "learning_rate": 4.803623033907169e-06,
968
+ "loss": 0.7301,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.5313312157089229,
973
+ "grad_norm": 0.21404632925987244,
974
+ "learning_rate": 4.741330102359441e-06,
975
+ "loss": 0.7417,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.5351814419097122,
980
+ "grad_norm": 0.24177585542201996,
981
+ "learning_rate": 4.679077403927996e-06,
982
+ "loss": 0.7177,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.5390316681105015,
987
+ "grad_norm": 0.22157888114452362,
988
+ "learning_rate": 4.616874621301373e-06,
989
+ "loss": 0.7216,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.5428818943112907,
994
+ "grad_norm": 0.23018169403076172,
995
+ "learning_rate": 4.554731429404293e-06,
996
+ "loss": 0.7357,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.5467321205120801,
1001
+ "grad_norm": 0.23788028955459595,
1002
+ "learning_rate": 4.492657493892822e-06,
1003
+ "loss": 0.7171,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.5505823467128694,
1008
+ "grad_norm": 0.23634755611419678,
1009
+ "learning_rate": 4.430662469650999e-06,
1010
+ "loss": 0.7342,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.5544325729136587,
1015
+ "grad_norm": 0.22768938541412354,
1016
+ "learning_rate": 4.368755999289118e-06,
1017
+ "loss": 0.7409,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.558282799114448,
1022
+ "grad_norm": 0.2411932796239853,
1023
+ "learning_rate": 4.306947711643949e-06,
1024
+ "loss": 0.7178,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.5621330253152372,
1029
+ "grad_norm": 0.23645783960819244,
1030
+ "learning_rate": 4.245247220281068e-06,
1031
+ "loss": 0.7253,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.5659832515160266,
1036
+ "grad_norm": 0.21812684834003448,
1037
+ "learning_rate": 4.183664121999587e-06,
1038
+ "loss": 0.7197,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.5698334777168159,
1043
+ "grad_norm": 0.2457520216703415,
1044
+ "learning_rate": 4.122207995339474e-06,
1045
+ "loss": 0.7186,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.5736837039176051,
1050
+ "grad_norm": 0.21957319974899292,
1051
+ "learning_rate": 4.060888399091734e-06,
1052
+ "loss": 0.7236,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.5775339301183945,
1057
+ "grad_norm": 0.2135009765625,
1058
+ "learning_rate": 3.999714870811639e-06,
1059
+ "loss": 0.7368,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.5813841563191837,
1064
+ "grad_norm": 0.2205502688884735,
1065
+ "learning_rate": 3.938696925335275e-06,
1066
+ "loss": 0.7282,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.5852343825199731,
1071
+ "grad_norm": 0.2280818223953247,
1072
+ "learning_rate": 3.87784405329962e-06,
1073
+ "loss": 0.735,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.5890846087207623,
1078
+ "grad_norm": 0.22201301157474518,
1079
+ "learning_rate": 3.817165719666382e-06,
1080
+ "loss": 0.7348,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.5929348349215516,
1085
+ "grad_norm": 0.22352463006973267,
1086
+ "learning_rate": 3.756671362249841e-06,
1087
+ "loss": 0.744,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.596785061122341,
1092
+ "grad_norm": 0.22531256079673767,
1093
+ "learning_rate": 3.6963703902488907e-06,
1094
+ "loss": 0.7275,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.6006352873231302,
1099
+ "grad_norm": 0.2235032021999359,
1100
+ "learning_rate": 3.6362721827835655e-06,
1101
+ "loss": 0.738,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.6044855135239195,
1106
+ "grad_norm": 0.23060625791549683,
1107
+ "learning_rate": 3.576386087436212e-06,
1108
+ "loss": 0.7385,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.6083357397247088,
1113
+ "grad_norm": 0.24664254486560822,
1114
+ "learning_rate": 3.5167214187975913e-06,
1115
+ "loss": 0.7286,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.6121859659254981,
1120
+ "grad_norm": 0.19943630695343018,
1121
+ "learning_rate": 3.457287457018086e-06,
1122
+ "loss": 0.7296,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.6160361921262875,
1127
+ "grad_norm": 0.21321284770965576,
1128
+ "learning_rate": 3.3980934463643003e-06,
1129
+ "loss": 0.7213,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.6198864183270767,
1134
+ "grad_norm": 0.21150624752044678,
1135
+ "learning_rate": 3.3391485937812053e-06,
1136
+ "loss": 0.7016,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.623736644527866,
1141
+ "grad_norm": 0.22218354046344757,
1142
+ "learning_rate": 3.280462067460115e-06,
1143
+ "loss": 0.7013,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.6275868707286553,
1148
+ "grad_norm": 0.22030869126319885,
1149
+ "learning_rate": 3.222042995412669e-06,
1150
+ "loss": 0.7322,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.6314370969294446,
1155
+ "grad_norm": 0.20098574459552765,
1156
+ "learning_rate": 3.163900464051089e-06,
1157
+ "loss": 0.7193,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.635287323130234,
1162
+ "grad_norm": 0.22929607331752777,
1163
+ "learning_rate": 3.1060435167748826e-06,
1164
+ "loss": 0.732,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.6391375493310232,
1169
+ "grad_norm": 0.22449444234371185,
1170
+ "learning_rate": 3.048481152564253e-06,
1171
+ "loss": 0.7136,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.6429877755318125,
1176
+ "grad_norm": 0.23324370384216309,
1177
+ "learning_rate": 2.9912223245804017e-06,
1178
+ "loss": 0.7355,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.6468380017326018,
1183
+ "grad_norm": 0.23257479071617126,
1184
+ "learning_rate": 2.934275938772981e-06,
1185
+ "loss": 0.7256,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.6506882279333911,
1190
+ "grad_norm": 0.22665172815322876,
1191
+ "learning_rate": 2.8776508524948676e-06,
1192
+ "loss": 0.7174,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.6545384541341804,
1197
+ "grad_norm": 0.2026968002319336,
1198
+ "learning_rate": 2.821355873124503e-06,
1199
+ "loss": 0.7152,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.6583886803349697,
1204
+ "grad_norm": 0.2277691513299942,
1205
+ "learning_rate": 2.7653997566960144e-06,
1206
+ "loss": 0.7303,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.662238906535759,
1211
+ "grad_norm": 0.2301967442035675,
1212
+ "learning_rate": 2.709791206537309e-06,
1213
+ "loss": 0.7211,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.6660891327365482,
1218
+ "grad_norm": 0.23111602663993835,
1219
+ "learning_rate": 2.6545388719163747e-06,
1220
+ "loss": 0.7192,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.6699393589373376,
1225
+ "grad_norm": 0.2265385091304779,
1226
+ "learning_rate": 2.599651346695979e-06,
1227
+ "loss": 0.7237,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.6737895851381268,
1232
+ "grad_norm": 0.21590180695056915,
1233
+ "learning_rate": 2.545137167997007e-06,
1234
+ "loss": 0.7233,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.6776398113389162,
1239
+ "grad_norm": 0.21903018653392792,
1240
+ "learning_rate": 2.4910048148705972e-06,
1241
+ "loss": 0.7102,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.6814900375397055,
1246
+ "grad_norm": 0.2358357161283493,
1247
+ "learning_rate": 2.4372627069793327e-06,
1248
+ "loss": 0.7558,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.6853402637404947,
1253
+ "grad_norm": 0.23804980516433716,
1254
+ "learning_rate": 2.3839192032876486e-06,
1255
+ "loss": 0.7392,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.6891904899412841,
1260
+ "grad_norm": 0.22769561409950256,
1261
+ "learning_rate": 2.3309826007617047e-06,
1262
+ "loss": 0.7496,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.6930407161420733,
1267
+ "grad_norm": 0.22375677525997162,
1268
+ "learning_rate": 2.278461133078881e-06,
1269
+ "loss": 0.713,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.6968909423428626,
1274
+ "grad_norm": 0.23237738013267517,
1275
+ "learning_rate": 2.2263629693471258e-06,
1276
+ "loss": 0.7052,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.700741168543652,
1281
+ "grad_norm": 0.21869096159934998,
1282
+ "learning_rate": 2.1746962128343414e-06,
1283
+ "loss": 0.7256,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.7045913947444412,
1288
+ "grad_norm": 0.2167786955833435,
1289
+ "learning_rate": 2.1234688997080183e-06,
1290
+ "loss": 0.7175,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.7084416209452306,
1295
+ "grad_norm": 0.23672528564929962,
1296
+ "learning_rate": 2.0726889977853053e-06,
1297
+ "loss": 0.7225,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.7122918471460198,
1302
+ "grad_norm": 0.23498331010341644,
1303
+ "learning_rate": 2.022364405293703e-06,
1304
+ "loss": 0.7354,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.7161420733468091,
1309
+ "grad_norm": 0.21953538060188293,
1310
+ "learning_rate": 1.9725029496425814e-06,
1311
+ "loss": 0.7294,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.7199922995475985,
1316
+ "grad_norm": 0.20463386178016663,
1317
+ "learning_rate": 1.923112386205727e-06,
1318
+ "loss": 0.7241,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.7238425257483877,
1323
+ "grad_norm": 0.21449820697307587,
1324
+ "learning_rate": 1.874200397115079e-06,
1325
+ "loss": 0.7331,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.727692751949177,
1330
+ "grad_norm": 0.23526880145072937,
1331
+ "learning_rate": 1.825774590065857e-06,
1332
+ "loss": 0.7153,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.7315429781499663,
1337
+ "grad_norm": 0.23917131125926971,
1338
+ "learning_rate": 1.7778424971332813e-06,
1339
+ "loss": 0.7263,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.7353932043507556,
1344
+ "grad_norm": 0.21619004011154175,
1345
+ "learning_rate": 1.7304115736010407e-06,
1346
+ "loss": 0.7227,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.739243430551545,
1351
+ "grad_norm": 0.2217293530702591,
1352
+ "learning_rate": 1.6834891968017108e-06,
1353
+ "loss": 0.7195,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.7430936567523342,
1358
+ "grad_norm": 0.23821181058883667,
1359
+ "learning_rate": 1.6370826649692884e-06,
1360
+ "loss": 0.7291,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.7469438829531235,
1365
+ "grad_norm": 0.234721377491951,
1366
+ "learning_rate": 1.5911991961040463e-06,
1367
+ "loss": 0.7415,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.7507941091539128,
1372
+ "grad_norm": 0.23024974763393402,
1373
+ "learning_rate": 1.545845926849851e-06,
1374
+ "loss": 0.7298,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.7546443353547021,
1379
+ "grad_norm": 0.23769573867321014,
1380
+ "learning_rate": 1.5010299113841397e-06,
1381
+ "loss": 0.7445,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.7584945615554913,
1386
+ "grad_norm": 0.22599360346794128,
1387
+ "learning_rate": 1.4567581203207238e-06,
1388
+ "loss": 0.7347,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.7623447877562807,
1393
+ "grad_norm": 0.23509778082370758,
1394
+ "learning_rate": 1.413037439625593e-06,
1395
+ "loss": 0.7327,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.76619501395707,
1400
+ "grad_norm": 0.23773007094860077,
1401
+ "learning_rate": 1.3698746695458847e-06,
1402
+ "loss": 0.7267,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.7700452401578592,
1407
+ "grad_norm": 0.22155648469924927,
1408
+ "learning_rate": 1.3272765235521745e-06,
1409
+ "loss": 0.7187,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.7738954663586486,
1414
+ "grad_norm": 0.21843701601028442,
1415
+ "learning_rate": 1.2852496272942877e-06,
1416
+ "loss": 0.7306,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.7777456925594378,
1421
+ "grad_norm": 0.20898380875587463,
1422
+ "learning_rate": 1.2438005175707396e-06,
1423
+ "loss": 0.7139,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.7815959187602272,
1428
+ "grad_norm": 0.2171592265367508,
1429
+ "learning_rate": 1.2029356413120297e-06,
1430
+ "loss": 0.6991,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.7854461449610165,
1435
+ "grad_norm": 0.21643193066120148,
1436
+ "learning_rate": 1.1626613545778786e-06,
1437
+ "loss": 0.7159,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.7892963711618057,
1442
+ "grad_norm": 0.21493452787399292,
1443
+ "learning_rate": 1.1229839215686294e-06,
1444
+ "loss": 0.7205,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.7931465973625951,
1449
+ "grad_norm": 0.22198839485645294,
1450
+ "learning_rate": 1.0839095136509188e-06,
1451
+ "loss": 0.7025,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.7969968235633843,
1456
+ "grad_norm": 0.24037325382232666,
1457
+ "learning_rate": 1.045444208397791e-06,
1458
+ "loss": 0.7252,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.8008470497641736,
1463
+ "grad_norm": 0.21233801543712616,
1464
+ "learning_rate": 1.007593988643402e-06,
1465
+ "loss": 0.7106,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.804697275964963,
1470
+ "grad_norm": 0.2110198587179184,
1471
+ "learning_rate": 9.703647415524613e-07,
1472
+ "loss": 0.7322,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.8085475021657522,
1477
+ "grad_norm": 0.22095899283885956,
1478
+ "learning_rate": 9.337622577045485e-07,
1479
+ "loss": 0.7189,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.8123977283665416,
1484
+ "grad_norm": 0.2323921024799347,
1485
+ "learning_rate": 8.977922301934588e-07,
1486
+ "loss": 0.7325,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.8162479545673308,
1491
+ "grad_norm": 0.22580565512180328,
1492
+ "learning_rate": 8.624602537417009e-07,
1493
+ "loss": 0.733,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.8200981807681201,
1498
+ "grad_norm": 0.23235096037387848,
1499
+ "learning_rate": 8.277718238303123e-07,
1500
+ "loss": 0.7161,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.8239484069689095,
1505
+ "grad_norm": 0.22165675461292267,
1506
+ "learning_rate": 7.937323358440935e-07,
1507
+ "loss": 0.7209,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.8277986331696987,
1512
+ "grad_norm": 0.2462707906961441,
1513
+ "learning_rate": 7.603470842324223e-07,
1514
+ "loss": 0.7113,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.831648859370488,
1519
+ "grad_norm": 0.22120234370231628,
1520
+ "learning_rate": 7.276212616857575e-07,
1521
+ "loss": 0.7317,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.8354990855712773,
1526
+ "grad_norm": 0.2249097228050232,
1527
+ "learning_rate": 6.955599583279837e-07,
1528
+ "loss": 0.7289,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.8393493117720666,
1533
+ "grad_norm": 0.21910323202610016,
1534
+ "learning_rate": 6.641681609246981e-07,
1535
+ "loss": 0.7237,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.8431995379728559,
1540
+ "grad_norm": 0.21550127863883972,
1541
+ "learning_rate": 6.334507521075711e-07,
1542
+ "loss": 0.7274,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.8470497641736452,
1547
+ "grad_norm": 0.2327413558959961,
1548
+ "learning_rate": 6.034125096149179e-07,
1549
+ "loss": 0.7264,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.8508999903744345,
1554
+ "grad_norm": 0.23068974912166595,
1555
+ "learning_rate": 5.740581055485722e-07,
1556
+ "loss": 0.6944,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.8547502165752238,
1561
+ "grad_norm": 0.20995543897151947,
1562
+ "learning_rate": 5.453921056471961e-07,
1563
+ "loss": 0.7272,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.8586004427760131,
1568
+ "grad_norm": 0.22604350745677948,
1569
+ "learning_rate": 5.174189685761288e-07,
1570
+ "loss": 0.7254,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.8624506689768023,
1575
+ "grad_norm": 0.20793288946151733,
1576
+ "learning_rate": 4.901430452338979e-07,
1577
+ "loss": 0.7349,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.8663008951775917,
1582
+ "grad_norm": 0.21462103724479675,
1583
+ "learning_rate": 4.6356857807548286e-07,
1584
+ "loss": 0.7182,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.870151121378381,
1589
+ "grad_norm": 0.22026042640209198,
1590
+ "learning_rate": 4.376997004524541e-07,
1591
+ "loss": 0.7086,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.8740013475791703,
1596
+ "grad_norm": 0.21678486466407776,
1597
+ "learning_rate": 4.12540435970073e-07,
1598
+ "loss": 0.7135,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.8778515737799596,
1603
+ "grad_norm": 0.22299028933048248,
1604
+ "learning_rate": 3.880946978614703e-07,
1605
+ "loss": 0.7298,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.8817017999807488,
1610
+ "grad_norm": 0.22146910429000854,
1611
+ "learning_rate": 3.643662883789878e-07,
1612
+ "loss": 0.7277,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.8855520261815382,
1617
+ "grad_norm": 0.20632033050060272,
1618
+ "learning_rate": 3.41358898202781e-07,
1619
+ "loss": 0.7096,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.8894022523823275,
1624
+ "grad_norm": 0.20563673973083496,
1625
+ "learning_rate": 3.190761058667741e-07,
1626
+ "loss": 0.7198,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.8932524785831167,
1631
+ "grad_norm": 0.22028161585330963,
1632
+ "learning_rate": 2.9752137720206463e-07,
1633
+ "loss": 0.724,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.8971027047839061,
1638
+ "grad_norm": 0.21885104477405548,
1639
+ "learning_rate": 2.7669806479785067e-07,
1640
+ "loss": 0.7296,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.9009529309846953,
1645
+ "grad_norm": 0.21906128525733948,
1646
+ "learning_rate": 2.566094074799763e-07,
1647
+ "loss": 0.7213,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.9048031571854847,
1652
+ "grad_norm": 0.22169512510299683,
1653
+ "learning_rate": 2.3725852980716557e-07,
1654
+ "loss": 0.711,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.908653383386274,
1659
+ "grad_norm": 0.21961405873298645,
1660
+ "learning_rate": 2.1864844158503983e-07,
1661
+ "loss": 0.7175,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.9125036095870632,
1666
+ "grad_norm": 0.23875993490219116,
1667
+ "learning_rate": 2.007820373979702e-07,
1668
+ "loss": 0.7117,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.9163538357878526,
1673
+ "grad_norm": 0.22534888982772827,
1674
+ "learning_rate": 1.8366209615886532e-07,
1675
+ "loss": 0.7236,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.9202040619886418,
1680
+ "grad_norm": 0.2170930653810501,
1681
+ "learning_rate": 1.6729128067693613e-07,
1682
+ "loss": 0.7372,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.9240542881894311,
1687
+ "grad_norm": 0.23884405195713043,
1688
+ "learning_rate": 1.5167213724353426e-07,
1689
+ "loss": 0.7347,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.9279045143902205,
1694
+ "grad_norm": 0.2203165739774704,
1695
+ "learning_rate": 1.3680709523610058e-07,
1696
+ "loss": 0.7134,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.9317547405910097,
1701
+ "grad_norm": 0.22331523895263672,
1702
+ "learning_rate": 1.2269846674030418e-07,
1703
+ "loss": 0.7376,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.935604966791799,
1708
+ "grad_norm": 0.23456981778144836,
1709
+ "learning_rate": 1.0934844619042595e-07,
1710
+ "loss": 0.7338,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.9394551929925883,
1715
+ "grad_norm": 0.23450526595115662,
1716
+ "learning_rate": 9.675911002803961e-08,
1717
+ "loss": 0.7212,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.9433054191933776,
1722
+ "grad_norm": 0.24414415657520294,
1723
+ "learning_rate": 8.493241637904381e-08,
1724
+ "loss": 0.7166,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.9471556453941669,
1729
+ "grad_norm": 0.22395433485507965,
1730
+ "learning_rate": 7.387020474909689e-08,
1731
+ "loss": 0.7391,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.9510058715949562,
1736
+ "grad_norm": 0.25715962052345276,
1737
+ "learning_rate": 6.357419573750856e-08,
1738
+ "loss": 0.7345,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.9548560977957455,
1743
+ "grad_norm": 0.22143277525901794,
1744
+ "learning_rate": 5.4045990769613365e-08,
1745
+ "loss": 0.7147,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.9587063239965348,
1750
+ "grad_norm": 0.22280800342559814,
1751
+ "learning_rate": 4.5287071847694434e-08,
1752
+ "loss": 0.7207,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.9625565501973241,
1757
+ "grad_norm": 0.21950890123844147,
1758
+ "learning_rate": 3.7298801320467817e-08,
1759
+ "loss": 0.7204,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.9664067763981133,
1764
+ "grad_norm": 0.21739082038402557,
1765
+ "learning_rate": 3.0082421671192576e-08,
1766
+ "loss": 0.7126,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.9702570025989027,
1771
+ "grad_norm": 0.2193877100944519,
1772
+ "learning_rate": 2.3639055324410355e-08,
1773
+ "loss": 0.735,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.974107228799692,
1778
+ "grad_norm": 0.2254035770893097,
1779
+ "learning_rate": 1.7969704471369477e-08,
1780
+ "loss": 0.7174,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.9779574550004813,
1785
+ "grad_norm": 0.21143938601016998,
1786
+ "learning_rate": 1.3075250914142413e-08,
1787
+ "loss": 0.7203,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.9818076812012706,
1792
+ "grad_norm": 0.21119479835033417,
1793
+ "learning_rate": 8.956455928476049e-09,
1794
+ "loss": 0.7291,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.9856579074020598,
1799
+ "grad_norm": 0.21750783920288086,
1800
+ "learning_rate": 5.6139601453786275e-09,
1801
+ "loss": 0.7198,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.9895081336028492,
1806
+ "grad_norm": 0.22089140117168427,
1807
+ "learning_rate": 3.0482834514805602e-09,
1808
+ "loss": 0.7113,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.9933583598036385,
1813
+ "grad_norm": 0.21553485095500946,
1814
+ "learning_rate": 1.2598249081713366e-09,
1815
+ "loss": 0.6996,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.9972085860044277,
1820
+ "grad_norm": 0.22459015250205994,
1821
+ "learning_rate": 2.488626895302826e-10,
1822
+ "loss": 0.7366,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.9999037443449803,
1827
+ "step": 2597,
1828
+ "total_flos": 4.099991765556134e+18,
1829
+ "train_loss": 0.7446105143268337,
1830
+ "train_runtime": 11783.0252,
1831
+ "train_samples_per_second": 56.429,
1832
+ "train_steps_per_second": 0.22
1833
+ }
1834
+ ],
1835
+ "logging_steps": 10,
1836
+ "max_steps": 2597,
1837
+ "num_input_tokens_seen": 418855352,
1838
+ "num_train_epochs": 1,
1839
+ "save_steps": 500,
1840
+ "stateful_callbacks": {
1841
+ "TrainerControl": {
1842
+ "args": {
1843
+ "should_epoch_stop": false,
1844
+ "should_evaluate": false,
1845
+ "should_log": false,
1846
+ "should_save": true,
1847
+ "should_training_stop": true
1848
+ },
1849
+ "attributes": {}
1850
+ }
1851
+ },
1852
+ "total_flos": 4.099991765556134e+18,
1853
+ "train_batch_size": 8,
1854
+ "trial_name": null,
1855
+ "trial_params": null
1856
+ }
continuous/qwen25/pe_core_l14_336/finetune/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3485c7a3ccd268a1fcf29cdeb8dc74891fd3fa13c28d63fd59a3c4398a399a
3
+ size 6264
continuous/qwen25/pe_core_l14_336/finetune/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
continuous/qwen25/pe_core_l14_336/pretrain/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_faster_video": false,
3
+ "add_time_instruction": false,
4
+ "architectures": [
5
+ "Qwen2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "faster_token_stride": 10,
11
+ "force_sample": false,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "image_aspect_ratio": "square",
15
+ "image_crop_resolution": null,
16
+ "image_grid_pinpoints": null,
17
+ "image_split_resolution": null,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8960,
20
+ "layer_types": [
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention"
49
+ ],
50
+ "max_position_embeddings": 32768,
51
+ "max_window_layers": 21,
52
+ "mm_hidden_size": 1024,
53
+ "mm_newline_position": "grid",
54
+ "mm_patch_merge_type": "flat",
55
+ "mm_projector_lr": null,
56
+ "mm_projector_type": "mlp2x_gelu",
57
+ "mm_resampler_type": null,
58
+ "mm_spatial_pool_mode": "bilinear",
59
+ "mm_spatial_pool_stride": null,
60
+ "mm_tunable_parts": "mm_mlp_adapter",
61
+ "mm_use_im_patch_token": false,
62
+ "mm_use_im_start_end": false,
63
+ "mm_vision_select_feature": "patch",
64
+ "mm_vision_select_layer": -1,
65
+ "mm_vision_tower": "vtb_ssl:pe",
66
+ "mm_vision_tower_lr": null,
67
+ "model_type": "qwen2",
68
+ "num_attention_heads": 12,
69
+ "num_hidden_layers": 28,
70
+ "num_key_value_heads": 2,
71
+ "pad_token_id": 151643,
72
+ "pos_skipping_range": 4096,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": null,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_model_max_length": 8192,
79
+ "tokenizer_padding_side": "right",
80
+ "transformers_version": "4.57.6",
81
+ "use_cache": true,
82
+ "use_mm_proj": true,
83
+ "use_pos_skipping": false,
84
+ "use_sliding_window": false,
85
+ "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Core-L14-336/PE-Core-L14-336.pt",
86
+ "vocab_size": 151936
87
+ }
continuous/qwen25/pe_core_l14_336/pretrain/mm_projector.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b0c7baab18675ea7f14e335743b7eeaf43567e566e239a18f77dac5a85fe6b
3
+ size 15743032
continuous/qwen25/pe_core_l14_336/pretrain/trainer_state.json ADDED
@@ -0,0 +1,421 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 545,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01834862385321101,
14
+ "grad_norm": 0.3522736430168152,
15
+ "learning_rate": 0.00032142857142857147,
16
+ "loss": 4.7858,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.03669724770642202,
21
+ "grad_norm": 0.1990043967962265,
22
+ "learning_rate": 0.0006785714285714287,
23
+ "loss": 4.0264,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.05504587155963303,
28
+ "grad_norm": 0.1593051701784134,
29
+ "learning_rate": 0.0009999907688176173,
30
+ "loss": 3.7009,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.07339449541284404,
35
+ "grad_norm": 0.27292051911354065,
36
+ "learning_rate": 0.0009988834393115766,
37
+ "loss": 3.4599,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.09174311926605505,
42
+ "grad_norm": 0.07681471109390259,
43
+ "learning_rate": 0.0009959345572940772,
44
+ "loss": 3.3342,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.11009174311926606,
49
+ "grad_norm": 0.06186879426240921,
50
+ "learning_rate": 0.0009911550081155983,
51
+ "loss": 3.2746,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.12844036697247707,
56
+ "grad_norm": 0.04571845754981041,
57
+ "learning_rate": 0.0009845624347566433,
58
+ "loss": 3.2319,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.14678899082568808,
63
+ "grad_norm": 0.0633586049079895,
64
+ "learning_rate": 0.0009761811727013547,
65
+ "loss": 3.1958,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1651376146788991,
70
+ "grad_norm": 0.06398757547140121,
71
+ "learning_rate": 0.0009660421601067666,
72
+ "loss": 3.1503,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.1834862385321101,
77
+ "grad_norm": 0.0820324718952179,
78
+ "learning_rate": 0.0009541828235992926,
79
+ "loss": 3.1166,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2018348623853211,
84
+ "grad_norm": 0.07360020279884338,
85
+ "learning_rate": 0.0009406469401200151,
86
+ "loss": 3.0752,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.22018348623853212,
91
+ "grad_norm": 0.08991989493370056,
92
+ "learning_rate": 0.0009254844753287492,
93
+ "loss": 3.0476,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.23853211009174313,
98
+ "grad_norm": 0.08779213577508926,
99
+ "learning_rate": 0.0009087513991633924,
100
+ "loss": 2.9991,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.25688073394495414,
105
+ "grad_norm": 0.10224965959787369,
106
+ "learning_rate": 0.0008905094792353917,
107
+ "loss": 2.9709,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.27522935779816515,
112
+ "grad_norm": 0.08120649307966232,
113
+ "learning_rate": 0.0008708260528239789,
114
+ "loss": 2.9481,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.29357798165137616,
119
+ "grad_norm": 0.0983848124742508,
120
+ "learning_rate": 0.0008497737783108237,
121
+ "loss": 2.9153,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.3119266055045872,
126
+ "grad_norm": 0.0861283540725708,
127
+ "learning_rate": 0.0008274303669726426,
128
+ "loss": 2.8993,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.3302752293577982,
133
+ "grad_norm": 0.16006560623645782,
134
+ "learning_rate": 0.0008038782961218137,
135
+ "loss": 2.8717,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.3486238532110092,
140
+ "grad_norm": 0.09529836475849152,
141
+ "learning_rate": 0.000779204504653894,
142
+ "loss": 2.8599,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.3669724770642202,
147
+ "grad_norm": 0.0877712070941925,
148
+ "learning_rate": 0.0007535000721258791,
149
+ "loss": 2.8302,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.3853211009174312,
154
+ "grad_norm": 0.08622035384178162,
155
+ "learning_rate": 0.00072685988254984,
156
+ "loss": 2.8135,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.4036697247706422,
161
+ "grad_norm": 0.11132845282554626,
162
+ "learning_rate": 0.0006993822741429906,
163
+ "loss": 2.8178,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.42201834862385323,
168
+ "grad_norm": 0.1004701554775238,
169
+ "learning_rate": 0.0006711686763270818,
170
+ "loss": 2.8073,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.44036697247706424,
175
+ "grad_norm": 0.08382391929626465,
176
+ "learning_rate": 0.0006423232353170831,
177
+ "loss": 2.7886,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.45871559633027525,
182
+ "grad_norm": 0.09838276356458664,
183
+ "learning_rate": 0.0006129524296812335,
184
+ "loss": 2.7707,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.47706422018348627,
189
+ "grad_norm": 0.08573777973651886,
190
+ "learning_rate": 0.0005831646772915651,
191
+ "loss": 2.7753,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.4954128440366973,
196
+ "grad_norm": 0.089602991938591,
197
+ "learning_rate": 0.0005530699351157809,
198
+ "loss": 2.7504,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.5137614678899083,
203
+ "grad_norm": 0.09272128343582153,
204
+ "learning_rate": 0.0005227792933277943,
205
+ "loss": 2.7496,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.5321100917431193,
210
+ "grad_norm": 0.09663499146699905,
211
+ "learning_rate": 0.0004924045652352092,
212
+ "loss": 2.7295,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.5504587155963303,
217
+ "grad_norm": 0.0914536863565445,
218
+ "learning_rate": 0.0004620578745374633,
219
+ "loss": 2.7262,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.5688073394495413,
224
+ "grad_norm": 0.09122458845376968,
225
+ "learning_rate": 0.0004318512414382059,
226
+ "loss": 2.7305,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.5871559633027523,
231
+ "grad_norm": 0.08700031042098999,
232
+ "learning_rate": 0.0004018961691397148,
233
+ "loss": 2.7216,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.6055045871559633,
238
+ "grad_norm": 0.09416543692350388,
239
+ "learning_rate": 0.0003723032322457458,
240
+ "loss": 2.6984,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.6238532110091743,
245
+ "grad_norm": 0.07727879285812378,
246
+ "learning_rate": 0.0003431816685921625,
247
+ "loss": 2.6983,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.6422018348623854,
252
+ "grad_norm": 0.10560670495033264,
253
+ "learning_rate": 0.0003146389760120416,
254
+ "loss": 2.6958,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.6605504587155964,
259
+ "grad_norm": 0.09738922864198685,
260
+ "learning_rate": 0.00028678051552373485,
261
+ "loss": 2.6904,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.6788990825688074,
266
+ "grad_norm": 0.08088542520999908,
267
+ "learning_rate": 0.0002597091224066581,
268
+ "loss": 2.6763,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.6972477064220184,
273
+ "grad_norm": 0.08453583717346191,
274
+ "learning_rate": 0.0002335247266004629,
275
+ "loss": 2.6793,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.7155963302752294,
280
+ "grad_norm": 0.08616087585687637,
281
+ "learning_rate": 0.000208323983828828,
282
+ "loss": 2.6637,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.7339449541284404,
287
+ "grad_norm": 0.0800304263830185,
288
+ "learning_rate": 0.0001841999188095224,
289
+ "loss": 2.6489,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.7522935779816514,
294
+ "grad_norm": 0.08353264629840851,
295
+ "learning_rate": 0.00016124158186777676,
296
+ "loss": 2.6502,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.7706422018348624,
301
+ "grad_norm": 0.07594425231218338,
302
+ "learning_rate": 0.0001395337202205211,
303
+ "loss": 2.6436,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.7889908256880734,
308
+ "grad_norm": 0.07930558919906616,
309
+ "learning_rate": 0.00011915646514489292,
310
+ "loss": 2.6353,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.8073394495412844,
315
+ "grad_norm": 0.08239097893238068,
316
+ "learning_rate": 0.00010018503618578818,
317
+ "loss": 2.6437,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.8256880733944955,
322
+ "grad_norm": 0.07650898396968842,
323
+ "learning_rate": 8.268946349432583e-05,
324
+ "loss": 2.6339,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.8440366972477065,
329
+ "grad_norm": 0.07879605889320374,
330
+ "learning_rate": 6.673432932217117e-05,
331
+ "loss": 2.6221,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.8623853211009175,
336
+ "grad_norm": 0.07641169428825378,
337
+ "learning_rate": 5.2378529625954684e-05,
338
+ "loss": 2.6167,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.8807339449541285,
343
+ "grad_norm": 0.07793845981359482,
344
+ "learning_rate": 3.9675056661785556e-05,
345
+ "loss": 2.6211,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.8990825688073395,
350
+ "grad_norm": 0.08019229024648666,
351
+ "learning_rate": 2.8670803372379538e-05,
352
+ "loss": 2.6274,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.9174311926605505,
357
+ "grad_norm": 0.0721561536192894,
358
+ "learning_rate": 1.9406390288876586e-05,
359
+ "loss": 2.632,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.9357798165137615,
364
+ "grad_norm": 0.07494896650314331,
365
+ "learning_rate": 1.191601558631461e-05,
366
+ "loss": 2.617,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.9541284403669725,
371
+ "grad_norm": 0.07354287058115005,
372
+ "learning_rate": 6.2273288462559305e-06,
373
+ "loss": 2.6171,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.9724770642201835,
378
+ "grad_norm": 0.07668881863355637,
379
+ "learning_rate": 2.361328992552314e-06,
380
+ "loss": 2.619,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.9908256880733946,
385
+ "grad_norm": 0.07785826176404953,
386
+ "learning_rate": 3.322867770044202e-07,
387
+ "loss": 2.6154,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.0,
392
+ "step": 545,
393
+ "total_flos": 3.122213121163264e+17,
394
+ "train_loss": 2.888605697001886,
395
+ "train_runtime": 5309.9876,
396
+ "train_samples_per_second": 105.109,
397
+ "train_steps_per_second": 0.103
398
+ }
399
+ ],
400
+ "logging_steps": 10,
401
+ "max_steps": 545,
402
+ "num_input_tokens_seen": 31896544,
403
+ "num_train_epochs": 1,
404
+ "save_steps": 500,
405
+ "stateful_callbacks": {
406
+ "TrainerControl": {
407
+ "args": {
408
+ "should_epoch_stop": false,
409
+ "should_evaluate": false,
410
+ "should_log": false,
411
+ "should_save": false,
412
+ "should_training_stop": false
413
+ },
414
+ "attributes": {}
415
+ }
416
+ },
417
+ "total_flos": 3.122213121163264e+17,
418
+ "train_batch_size": 32,
419
+ "trial_name": null,
420
+ "trial_params": null
421
+ }
continuous/qwen25/pe_core_s16_384/finetune/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
+ }
continuous/qwen25/pe_core_s16_384/finetune/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
continuous/qwen25/pe_core_s16_384/finetune/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_faster_video": false,
3
+ "add_time_instruction": false,
4
+ "architectures": [
5
+ "LlavaQwenForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "faster_token_stride": 10,
11
+ "force_sample": false,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "image_aspect_ratio": "square",
15
+ "image_crop_resolution": null,
16
+ "image_grid_pinpoints": null,
17
+ "image_split_resolution": null,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8960,
20
+ "layer_types": [
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention"
49
+ ],
50
+ "max_position_embeddings": 32768,
51
+ "max_window_layers": 21,
52
+ "mm_hidden_size": 384,
53
+ "mm_newline_position": "grid",
54
+ "mm_patch_merge_type": "flat",
55
+ "mm_projector_lr": 0.0001,
56
+ "mm_projector_type": "mlp2x_gelu",
57
+ "mm_resampler_type": null,
58
+ "mm_spatial_pool_mode": "bilinear",
59
+ "mm_spatial_pool_stride": null,
60
+ "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
61
+ "mm_use_im_patch_token": false,
62
+ "mm_use_im_start_end": false,
63
+ "mm_vision_select_feature": "patch",
64
+ "mm_vision_select_layer": -1,
65
+ "mm_vision_tower": "vtb_ssl:pe",
66
+ "mm_vision_tower_lr": null,
67
+ "model_type": "qwen2",
68
+ "num_attention_heads": 12,
69
+ "num_hidden_layers": 28,
70
+ "num_key_value_heads": 2,
71
+ "pad_token_id": 151643,
72
+ "pos_skipping_range": 4096,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": null,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_model_max_length": 8192,
79
+ "tokenizer_padding_side": "right",
80
+ "transformers_version": "4.57.6",
81
+ "use_cache": true,
82
+ "use_mm_proj": true,
83
+ "use_pos_skipping": false,
84
+ "use_sliding_window": false,
85
+ "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Core-S16-384/PE-Core-S16-384.pt",
86
+ "vocab_size": 151936
87
+ }
continuous/qwen25/pe_core_s16_384/finetune/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.1,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.6"
13
+ }
continuous/qwen25/pe_core_s16_384/finetune/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
continuous/qwen25/pe_core_s16_384/finetune/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1045df0cb8cd8adb8fab96d1fdf5439e1a3446c1c9aa23afaafab0bfc746c714
3
+ size 3613612568
continuous/qwen25/pe_core_s16_384/finetune/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
+ }
continuous/qwen25/pe_core_s16_384/finetune/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896