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
c85b96c
·
verified ·
1 Parent(s): 8db1af7

Upload continuous evaluation checkpoints, batch 3

Browse files
Files changed (33) hide show
  1. .gitattributes +2 -0
  2. continuous/qwen25/webssl_mae300m_full2b_224/finetune/model.safetensors +3 -0
  3. continuous/qwen25/webssl_mae300m_full2b_224/finetune/special_tokens_map.json +31 -0
  4. continuous/qwen25/webssl_mae300m_full2b_224/finetune/tokenizer.json +3 -0
  5. continuous/qwen25/webssl_mae300m_full2b_224/finetune/tokenizer_config.json +208 -0
  6. continuous/qwen25/webssl_mae300m_full2b_224/finetune/trainer_state.json +1856 -0
  7. continuous/qwen25/webssl_mae300m_full2b_224/finetune/training_args.bin +3 -0
  8. continuous/qwen25/webssl_mae300m_full2b_224/finetune/vocab.json +0 -0
  9. continuous/qwen25/webssl_mae300m_full2b_224/pretrain/config.json +87 -0
  10. continuous/qwen25/webssl_mae300m_full2b_224/pretrain/mm_projector.bin +3 -0
  11. continuous/qwen25/webssl_mae300m_full2b_224/pretrain/trainer_state.json +421 -0
  12. continuous/qwen25/webssl_mae3b_full2b_224/finetune/added_tokens.json +24 -0
  13. continuous/qwen25/webssl_mae3b_full2b_224/finetune/chat_template.jinja +54 -0
  14. continuous/qwen25/webssl_mae3b_full2b_224/finetune/config.json +87 -0
  15. continuous/qwen25/webssl_mae3b_full2b_224/finetune/generation_config.json +13 -0
  16. continuous/qwen25/webssl_mae3b_full2b_224/finetune/merges.txt +0 -0
  17. continuous/qwen25/webssl_mae3b_full2b_224/finetune/model-00001-of-00002.safetensors +3 -0
  18. continuous/qwen25/webssl_mae3b_full2b_224/finetune/model-00002-of-00002.safetensors +3 -0
  19. continuous/qwen25/webssl_mae3b_full2b_224/finetune/model.safetensors.index.json +775 -0
  20. continuous/qwen25/webssl_mae3b_full2b_224/finetune/special_tokens_map.json +31 -0
  21. continuous/qwen25/webssl_mae3b_full2b_224/finetune/tokenizer.json +3 -0
  22. continuous/qwen25/webssl_mae3b_full2b_224/finetune/tokenizer_config.json +208 -0
  23. continuous/qwen25/webssl_mae3b_full2b_224/finetune/trainer_state.json +1856 -0
  24. continuous/qwen25/webssl_mae3b_full2b_224/finetune/training_args.bin +3 -0
  25. continuous/qwen25/webssl_mae3b_full2b_224/finetune/vocab.json +0 -0
  26. continuous/qwen25/webssl_mae3b_full2b_224/pretrain/config.json +87 -0
  27. continuous/qwen25/webssl_mae3b_full2b_224/pretrain/mm_projector.bin +3 -0
  28. continuous/qwen25/webssl_mae3b_full2b_224/pretrain/trainer_state.json +421 -0
  29. continuous/qwen25/webssl_mae700m_full2b_224/finetune/added_tokens.json +24 -0
  30. continuous/qwen25/webssl_mae700m_full2b_224/finetune/chat_template.jinja +54 -0
  31. continuous/qwen25/webssl_mae700m_full2b_224/finetune/config.json +87 -0
  32. continuous/qwen25/webssl_mae700m_full2b_224/finetune/generation_config.json +13 -0
  33. continuous/qwen25/webssl_mae700m_full2b_224/finetune/merges.txt +0 -0
.gitattributes CHANGED
@@ -107,3 +107,5 @@ continuous/qwen25/siglip2_sm16_512/finetune/tokenizer.json filter=lfs diff=lfs m
107
  continuous/qwen25/webssl_dino1b_full2b_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
108
  continuous/qwen25/webssl_mae1b_full2b_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
109
  continuous/qwen25/webssl_mae2b_full2b_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
107
  continuous/qwen25/webssl_dino1b_full2b_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
108
  continuous/qwen25/webssl_mae1b_full2b_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
109
  continuous/qwen25/webssl_mae2b_full2b_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
110
+ continuous/qwen25/webssl_mae300m_full2b_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
111
+ continuous/qwen25/webssl_mae3b_full2b_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
continuous/qwen25/webssl_mae300m_full2b_224/finetune/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5496e18ad79821a1663edc83faa5e2358f1264af458d3a5b7448d79b8c7ce7bd
3
+ size 4178717184
continuous/qwen25/webssl_mae300m_full2b_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/webssl_mae300m_full2b_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/webssl_mae300m_full2b_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/webssl_mae300m_full2b_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": 15.289994239807129,
15
+ "learning_rate": 1.153846153846154e-06,
16
+ "loss": 1.8871,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.007700452401578592,
21
+ "grad_norm": 10.425704956054688,
22
+ "learning_rate": 2.435897435897436e-06,
23
+ "loss": 1.565,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.01155067860236789,
28
+ "grad_norm": 3.7855029106140137,
29
+ "learning_rate": 3.7179487179487184e-06,
30
+ "loss": 1.139,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.015400904803157185,
35
+ "grad_norm": 0.640113115310669,
36
+ "learning_rate": 5e-06,
37
+ "loss": 0.9626,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.019251131003946483,
42
+ "grad_norm": 0.34637245535850525,
43
+ "learning_rate": 6.282051282051282e-06,
44
+ "loss": 0.9344,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.02310135720473578,
49
+ "grad_norm": 0.2681576907634735,
50
+ "learning_rate": 7.564102564102564e-06,
51
+ "loss": 0.8926,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.026951583405525073,
56
+ "grad_norm": 0.2264764904975891,
57
+ "learning_rate": 8.846153846153847e-06,
58
+ "loss": 0.8674,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.03080180960631437,
63
+ "grad_norm": 0.23310117423534393,
64
+ "learning_rate": 9.999996111488723e-06,
65
+ "loss": 0.8768,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.034652035807103666,
70
+ "grad_norm": 0.21713264286518097,
71
+ "learning_rate": 9.999529497453782e-06,
72
+ "loss": 0.8579,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.038502262007892966,
77
+ "grad_norm": 0.2218714952468872,
78
+ "learning_rate": 9.998285264324193e-06,
79
+ "loss": 0.8387,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.04235248820868226,
84
+ "grad_norm": 0.20722094178199768,
85
+ "learning_rate": 9.996263605626052e-06,
86
+ "loss": 0.8282,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.04620271440947156,
91
+ "grad_norm": 0.2249489277601242,
92
+ "learning_rate": 9.99346483580503e-06,
93
+ "loss": 0.8399,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.05005294061026085,
98
+ "grad_norm": 0.2027045637369156,
99
+ "learning_rate": 9.989889390177467e-06,
100
+ "loss": 0.8318,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.053903166811050146,
105
+ "grad_norm": 0.2310321182012558,
106
+ "learning_rate": 9.985537824862647e-06,
107
+ "loss": 0.8324,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.057753393011839446,
112
+ "grad_norm": 0.2341403216123581,
113
+ "learning_rate": 9.980410816696317e-06,
114
+ "loss": 0.8149,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.06160361921262874,
119
+ "grad_norm": 0.2194165736436844,
120
+ "learning_rate": 9.97450916312541e-06,
121
+ "loss": 0.8217,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.06545384541341803,
126
+ "grad_norm": 0.1980160027742386,
127
+ "learning_rate": 9.967833782084004e-06,
128
+ "loss": 0.8233,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.06930407161420733,
133
+ "grad_norm": 0.230560302734375,
134
+ "learning_rate": 9.960385711850554e-06,
135
+ "loss": 0.8502,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.07315429781499663,
140
+ "grad_norm": 0.21881577372550964,
141
+ "learning_rate": 9.952166110886394e-06,
142
+ "loss": 0.8406,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.07700452401578593,
147
+ "grad_norm": 0.24356673657894135,
148
+ "learning_rate": 9.943176257655567e-06,
149
+ "loss": 0.8351,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.08085475021657522,
154
+ "grad_norm": 0.2141706347465515,
155
+ "learning_rate": 9.933417550425952e-06,
156
+ "loss": 0.8237,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.08470497641736452,
161
+ "grad_norm": 0.21844902634620667,
162
+ "learning_rate": 9.9228915070518e-06,
163
+ "loss": 0.8145,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.08855520261815382,
168
+ "grad_norm": 0.21946361660957336,
169
+ "learning_rate": 9.911599764737632e-06,
170
+ "loss": 0.8167,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.09240542881894312,
175
+ "grad_norm": 0.22783713042736053,
176
+ "learning_rate": 9.899544079783606e-06,
177
+ "loss": 0.8103,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.0962556550197324,
182
+ "grad_norm": 0.22610004246234894,
183
+ "learning_rate": 9.886726327312338e-06,
184
+ "loss": 0.8256,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.1001058812205217,
189
+ "grad_norm": 0.21215474605560303,
190
+ "learning_rate": 9.87314850097724e-06,
191
+ "loss": 0.8247,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.103956107421311,
196
+ "grad_norm": 0.21045272052288055,
197
+ "learning_rate": 9.858812712652452e-06,
198
+ "loss": 0.8132,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.10780633362210029,
203
+ "grad_norm": 0.20161877572536469,
204
+ "learning_rate": 9.843721192104341e-06,
205
+ "loss": 0.8146,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.11165655982288959,
210
+ "grad_norm": 0.21491561830043793,
211
+ "learning_rate": 9.827876286644698e-06,
212
+ "loss": 0.8336,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.11550678602367889,
217
+ "grad_norm": 0.19627156853675842,
218
+ "learning_rate": 9.811280460765643e-06,
219
+ "loss": 0.7931,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.11935701222446819,
224
+ "grad_norm": 0.2116481512784958,
225
+ "learning_rate": 9.793936295756292e-06,
226
+ "loss": 0.8045,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.12320723842525748,
231
+ "grad_norm": 0.2153456062078476,
232
+ "learning_rate": 9.775846489301279e-06,
233
+ "loss": 0.8077,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.12705746462604678,
238
+ "grad_norm": 0.22541628777980804,
239
+ "learning_rate": 9.757013855061157e-06,
240
+ "loss": 0.8069,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.13090769082683607,
245
+ "grad_norm": 0.21378028392791748,
246
+ "learning_rate": 9.737441322234758e-06,
247
+ "loss": 0.8187,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.13475791702762538,
252
+ "grad_norm": 0.2281515747308731,
253
+ "learning_rate": 9.717131935103605e-06,
254
+ "loss": 0.8177,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.13860814322841467,
259
+ "grad_norm": 0.2169838547706604,
260
+ "learning_rate": 9.696088852558398e-06,
261
+ "loss": 0.8034,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.14245836942920398,
266
+ "grad_norm": 0.21600009500980377,
267
+ "learning_rate": 9.674315347607686e-06,
268
+ "loss": 0.8294,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.14630859562999327,
273
+ "grad_norm": 0.2154902219772339,
274
+ "learning_rate": 9.651814806868796e-06,
275
+ "loss": 0.7952,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.15015882183078255,
280
+ "grad_norm": 0.22845466434955597,
281
+ "learning_rate": 9.62859073004107e-06,
282
+ "loss": 0.7997,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.15400904803157187,
287
+ "grad_norm": 0.19676846265792847,
288
+ "learning_rate": 9.604646729361547e-06,
289
+ "loss": 0.8057,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.15785927423236115,
294
+ "grad_norm": 0.20854783058166504,
295
+ "learning_rate": 9.579986529043099e-06,
296
+ "loss": 0.7982,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.16170950043315044,
301
+ "grad_norm": 0.2144680917263031,
302
+ "learning_rate": 9.554613964695189e-06,
303
+ "loss": 0.8103,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.16555972663393975,
308
+ "grad_norm": 0.215067058801651,
309
+ "learning_rate": 9.528532982727281e-06,
310
+ "loss": 0.8011,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.16940995283472904,
315
+ "grad_norm": 0.20388004183769226,
316
+ "learning_rate": 9.501747639735018e-06,
317
+ "loss": 0.8012,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.17326017903551832,
322
+ "grad_norm": 0.21219252049922943,
323
+ "learning_rate": 9.474262101869272e-06,
324
+ "loss": 0.789,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.17711040523630764,
329
+ "grad_norm": 0.21704666316509247,
330
+ "learning_rate": 9.446080644188141e-06,
331
+ "loss": 0.7942,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.18096063143709692,
336
+ "grad_norm": 0.20733870565891266,
337
+ "learning_rate": 9.417207649992017e-06,
338
+ "loss": 0.8026,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.18481085763788624,
343
+ "grad_norm": 0.21676281094551086,
344
+ "learning_rate": 9.387647610141816e-06,
345
+ "loss": 0.8017,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.18866108383867553,
350
+ "grad_norm": 0.19876991212368011,
351
+ "learning_rate": 9.35740512236047e-06,
352
+ "loss": 0.7872,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.1925113100394648,
357
+ "grad_norm": 0.19454088807106018,
358
+ "learning_rate": 9.326484890517809e-06,
359
+ "loss": 0.7959,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.19636153624025413,
364
+ "grad_norm": 0.21781767904758453,
365
+ "learning_rate": 9.294891723898926e-06,
366
+ "loss": 0.788,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.2002117624410434,
371
+ "grad_norm": 0.22729846835136414,
372
+ "learning_rate": 9.262630536456153e-06,
373
+ "loss": 0.8177,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.2040619886418327,
378
+ "grad_norm": 0.22545386850833893,
379
+ "learning_rate": 9.229706346044749e-06,
380
+ "loss": 0.7926,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.207912214842622,
385
+ "grad_norm": 0.22628040611743927,
386
+ "learning_rate": 9.196124273642422e-06,
387
+ "loss": 0.8026,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.2117624410434113,
392
+ "grad_norm": 0.20708070695400238,
393
+ "learning_rate": 9.161889542552842e-06,
394
+ "loss": 0.8054,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.21561266724420058,
399
+ "grad_norm": 0.20585712790489197,
400
+ "learning_rate": 9.127007477593193e-06,
401
+ "loss": 0.81,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.2194628934449899,
406
+ "grad_norm": 0.22706079483032227,
407
+ "learning_rate": 9.091483504265974e-06,
408
+ "loss": 0.8209,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.22331311964577918,
413
+ "grad_norm": 0.22458426654338837,
414
+ "learning_rate": 9.055323147915116e-06,
415
+ "loss": 0.7978,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.2271633458465685,
420
+ "grad_norm": 0.21607020497322083,
421
+ "learning_rate": 9.018532032866585e-06,
422
+ "loss": 0.8102,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.23101357204735778,
427
+ "grad_norm": 0.22010226547718048,
428
+ "learning_rate": 8.981115881553579e-06,
429
+ "loss": 0.8017,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.23486379824814707,
434
+ "grad_norm": 0.2265131026506424,
435
+ "learning_rate": 8.943080513626476e-06,
436
+ "loss": 0.8218,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.23871402444893638,
441
+ "grad_norm": 0.20767910778522491,
442
+ "learning_rate": 8.904431845047641e-06,
443
+ "loss": 0.8047,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.24256425064972567,
448
+ "grad_norm": 0.22277358174324036,
449
+ "learning_rate": 8.86517588717128e-06,
450
+ "loss": 0.822,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.24641447685051496,
455
+ "grad_norm": 0.20541071891784668,
456
+ "learning_rate": 8.82531874580844e-06,
457
+ "loss": 0.81,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.25026470305130427,
462
+ "grad_norm": 0.1972970962524414,
463
+ "learning_rate": 8.784866620277314e-06,
464
+ "loss": 0.7688,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.25411492925209356,
469
+ "grad_norm": 0.2394297868013382,
470
+ "learning_rate": 8.743825802439018e-06,
471
+ "loss": 0.8051,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.25796515545288284,
476
+ "grad_norm": 0.2279851734638214,
477
+ "learning_rate": 8.702202675718956e-06,
478
+ "loss": 0.8094,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.26181538165367213,
483
+ "grad_norm": 0.20186138153076172,
484
+ "learning_rate": 8.660003714113959e-06,
485
+ "loss": 0.7809,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.26566560785446147,
490
+ "grad_norm": 0.21112394332885742,
491
+ "learning_rate": 8.617235481185323e-06,
492
+ "loss": 0.8042,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.26951583405525076,
497
+ "grad_norm": 0.21452520787715912,
498
+ "learning_rate": 8.573904629037931e-06,
499
+ "loss": 0.8083,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.27336606025604004,
504
+ "grad_norm": 0.21131016314029694,
505
+ "learning_rate": 8.530017897285585e-06,
506
+ "loss": 0.7891,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.27721628645682933,
511
+ "grad_norm": 0.19949054718017578,
512
+ "learning_rate": 8.485582112002746e-06,
513
+ "loss": 0.7939,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.2810665126576186,
518
+ "grad_norm": 0.21193473041057587,
519
+ "learning_rate": 8.440604184662811e-06,
520
+ "loss": 0.7989,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.28491673885840796,
525
+ "grad_norm": 0.21722348034381866,
526
+ "learning_rate": 8.395091111063118e-06,
527
+ "loss": 0.7894,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.28876696505919724,
532
+ "grad_norm": 0.19853556156158447,
533
+ "learning_rate": 8.349049970236822e-06,
534
+ "loss": 0.787,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.29261719125998653,
539
+ "grad_norm": 0.20901615917682648,
540
+ "learning_rate": 8.302487923351842e-06,
541
+ "loss": 0.7802,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.2964674174607758,
546
+ "grad_norm": 0.20333349704742432,
547
+ "learning_rate": 8.255412212597021e-06,
548
+ "loss": 0.7978,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.3003176436615651,
553
+ "grad_norm": 0.1991925686597824,
554
+ "learning_rate": 8.207830160055688e-06,
555
+ "loss": 0.7937,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.3041678698623544,
560
+ "grad_norm": 0.21822941303253174,
561
+ "learning_rate": 8.159749166566786e-06,
562
+ "loss": 0.7816,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.30801809606314373,
567
+ "grad_norm": 0.20442065596580505,
568
+ "learning_rate": 8.11117671057377e-06,
569
+ "loss": 0.8085,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.311868322263933,
574
+ "grad_norm": 0.2164207100868225,
575
+ "learning_rate": 8.062120346961404e-06,
576
+ "loss": 0.8011,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.3157185484647223,
581
+ "grad_norm": 0.20781736075878143,
582
+ "learning_rate": 8.012587705880705e-06,
583
+ "loss": 0.7957,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.3195687746655116,
588
+ "grad_norm": 0.2082027792930603,
589
+ "learning_rate": 7.962586491562146e-06,
590
+ "loss": 0.7809,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.3234190008663009,
595
+ "grad_norm": 0.23104678094387054,
596
+ "learning_rate": 7.912124481117357e-06,
597
+ "loss": 0.7851,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.3272692270670902,
602
+ "grad_norm": 0.20528103411197662,
603
+ "learning_rate": 7.861209523329494e-06,
604
+ "loss": 0.795,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.3311194532678795,
609
+ "grad_norm": 0.21318012475967407,
610
+ "learning_rate": 7.809849537432432e-06,
611
+ "loss": 0.7826,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.3349696794686688,
616
+ "grad_norm": 0.20590901374816895,
617
+ "learning_rate": 7.758052511879035e-06,
618
+ "loss": 0.7906,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.3388199056694581,
623
+ "grad_norm": 0.2003680020570755,
624
+ "learning_rate": 7.705826503098642e-06,
625
+ "loss": 0.7847,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.34267013187024736,
630
+ "grad_norm": 0.20361952483654022,
631
+ "learning_rate": 7.653179634243979e-06,
632
+ "loss": 0.7849,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.34652035807103665,
637
+ "grad_norm": 0.18971611559391022,
638
+ "learning_rate": 7.600120093927696e-06,
639
+ "loss": 0.7913,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.350370584271826,
644
+ "grad_norm": 0.21570470929145813,
645
+ "learning_rate": 7.546656134948729e-06,
646
+ "loss": 0.7765,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.3542208104726153,
651
+ "grad_norm": 0.21081584692001343,
652
+ "learning_rate": 7.492796073008661e-06,
653
+ "loss": 0.7769,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.35807103667340456,
658
+ "grad_norm": 0.22493471205234528,
659
+ "learning_rate": 7.438548285418326e-06,
660
+ "loss": 0.7659,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.36192126287419385,
665
+ "grad_norm": 0.23478683829307556,
666
+ "learning_rate": 7.3839212097948e-06,
667
+ "loss": 0.798,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.36577148907498314,
672
+ "grad_norm": 0.21508435904979706,
673
+ "learning_rate": 7.328923342749039e-06,
674
+ "loss": 0.8124,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.3696217152757725,
679
+ "grad_norm": 0.21931464970111847,
680
+ "learning_rate": 7.273563238564319e-06,
681
+ "loss": 0.7987,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.37347194147656176,
686
+ "grad_norm": 0.21296416223049164,
687
+ "learning_rate": 7.217849507865724e-06,
688
+ "loss": 0.7799,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.37732216767735105,
693
+ "grad_norm": 0.2104843109846115,
694
+ "learning_rate": 7.161790816280858e-06,
695
+ "loss": 0.7831,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.38117239387814034,
700
+ "grad_norm": 0.2186904102563858,
701
+ "learning_rate": 7.1053958830920125e-06,
702
+ "loss": 0.77,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.3850226200789296,
707
+ "grad_norm": 0.20723237097263336,
708
+ "learning_rate": 7.0486734798799715e-06,
709
+ "loss": 0.7833,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.3888728462797189,
714
+ "grad_norm": 0.20474332571029663,
715
+ "learning_rate": 6.991632429159708e-06,
716
+ "loss": 0.807,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.39272307248050825,
721
+ "grad_norm": 0.22967644035816193,
722
+ "learning_rate": 6.934281603008132e-06,
723
+ "loss": 0.8019,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.39657329868129754,
728
+ "grad_norm": 0.20434841513633728,
729
+ "learning_rate": 6.876629921684143e-06,
730
+ "loss": 0.7986,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.4004235248820868,
735
+ "grad_norm": 0.21328824758529663,
736
+ "learning_rate": 6.818686352241199e-06,
737
+ "loss": 0.7898,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.4042737510828761,
742
+ "grad_norm": 0.19989453256130219,
743
+ "learning_rate": 6.760459907132573e-06,
744
+ "loss": 0.787,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.4081239772836654,
749
+ "grad_norm": 0.1939895898103714,
750
+ "learning_rate": 6.701959642809589e-06,
751
+ "loss": 0.7929,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.41197420348445474,
756
+ "grad_norm": 0.21380171179771423,
757
+ "learning_rate": 6.643194658312987e-06,
758
+ "loss": 0.7823,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.415824429685244,
763
+ "grad_norm": 0.20442096889019012,
764
+ "learning_rate": 6.584174093857676e-06,
765
+ "loss": 0.8071,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.4196746558860333,
770
+ "grad_norm": 0.23313109576702118,
771
+ "learning_rate": 6.5249071294110735e-06,
772
+ "loss": 0.789,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.4235248820868226,
777
+ "grad_norm": 0.2124711126089096,
778
+ "learning_rate": 6.465402983265274e-06,
779
+ "loss": 0.8029,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.4273751082876119,
784
+ "grad_norm": 0.21917474269866943,
785
+ "learning_rate": 6.405670910603243e-06,
786
+ "loss": 0.8006,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.43122533448840117,
791
+ "grad_norm": 0.22951610386371613,
792
+ "learning_rate": 6.345720202059291e-06,
793
+ "loss": 0.7957,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.4350755606891905,
798
+ "grad_norm": 0.2109682410955429,
799
+ "learning_rate": 6.285560182274008e-06,
800
+ "loss": 0.7728,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.4389257868899798,
805
+ "grad_norm": 0.20635755360126495,
806
+ "learning_rate": 6.225200208443936e-06,
807
+ "loss": 0.7943,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.4427760130907691,
812
+ "grad_norm": 0.20726659893989563,
813
+ "learning_rate": 6.16464966886616e-06,
814
+ "loss": 0.7875,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.44662623929155837,
819
+ "grad_norm": 0.24316272139549255,
820
+ "learning_rate": 6.103917981478065e-06,
821
+ "loss": 0.8093,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.45047646549234766,
826
+ "grad_norm": 0.2088736742734909,
827
+ "learning_rate": 6.043014592392489e-06,
828
+ "loss": 0.8219,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.454326691693137,
833
+ "grad_norm": 0.1982356458902359,
834
+ "learning_rate": 5.981948974428485e-06,
835
+ "loss": 0.7928,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.4581769178939263,
840
+ "grad_norm": 0.2135431468486786,
841
+ "learning_rate": 5.920730625637934e-06,
842
+ "loss": 0.7751,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.46202714409471557,
847
+ "grad_norm": 0.22138850390911102,
848
+ "learning_rate": 5.8593690678282355e-06,
849
+ "loss": 0.7855,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.46587737029550486,
854
+ "grad_norm": 0.21944744884967804,
855
+ "learning_rate": 5.797873845081301e-06,
856
+ "loss": 0.7876,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.46972759649629414,
861
+ "grad_norm": 0.21665802597999573,
862
+ "learning_rate": 5.736254522269075e-06,
863
+ "loss": 0.8053,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.47357782269708343,
868
+ "grad_norm": 0.20228910446166992,
869
+ "learning_rate": 5.6745206835658386e-06,
870
+ "loss": 0.8072,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.47742804889787277,
875
+ "grad_norm": 0.20685744285583496,
876
+ "learning_rate": 5.612681930957495e-06,
877
+ "loss": 0.7763,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.48127827509866206,
882
+ "grad_norm": 0.2033269703388214,
883
+ "learning_rate": 5.550747882748095e-06,
884
+ "loss": 0.7761,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.48512850129945134,
889
+ "grad_norm": 0.22223149240016937,
890
+ "learning_rate": 5.4887281720638195e-06,
891
+ "loss": 0.7834,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.48897872750024063,
896
+ "grad_norm": 0.23766174912452698,
897
+ "learning_rate": 5.42663244535466e-06,
898
+ "loss": 0.7689,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.4928289537010299,
903
+ "grad_norm": 0.213004931807518,
904
+ "learning_rate": 5.3644703608940205e-06,
905
+ "loss": 0.776,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.49667917990181926,
910
+ "grad_norm": 0.21234512329101562,
911
+ "learning_rate": 5.302251587276491e-06,
912
+ "loss": 0.787,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.5005294061026085,
917
+ "grad_norm": 0.20418237149715424,
918
+ "learning_rate": 5.2399858019140005e-06,
919
+ "loss": 0.7887,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.5043796323033978,
924
+ "grad_norm": 0.2051668018102646,
925
+ "learning_rate": 5.177682689530615e-06,
926
+ "loss": 0.7991,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.5082298585041871,
931
+ "grad_norm": 0.22009478509426117,
932
+ "learning_rate": 5.11535194065619e-06,
933
+ "loss": 0.772,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.5120800847049765,
938
+ "grad_norm": 0.23292876780033112,
939
+ "learning_rate": 5.053003250119113e-06,
940
+ "loss": 0.7816,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.5159303109057657,
945
+ "grad_norm": 0.21659602224826813,
946
+ "learning_rate": 4.9906463155383925e-06,
947
+ "loss": 0.7861,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.519780537106555,
952
+ "grad_norm": 0.2099297046661377,
953
+ "learning_rate": 4.9282908358153046e-06,
954
+ "loss": 0.7779,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.5236307633073443,
959
+ "grad_norm": 0.2352129966020584,
960
+ "learning_rate": 4.8659465096248345e-06,
961
+ "loss": 0.7974,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.5274809895081336,
966
+ "grad_norm": 0.21425926685333252,
967
+ "learning_rate": 4.803623033907169e-06,
968
+ "loss": 0.7959,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.5313312157089229,
973
+ "grad_norm": 0.19726088643074036,
974
+ "learning_rate": 4.741330102359441e-06,
975
+ "loss": 0.8017,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.5351814419097122,
980
+ "grad_norm": 0.22238197922706604,
981
+ "learning_rate": 4.679077403927996e-06,
982
+ "loss": 0.7817,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.5390316681105015,
987
+ "grad_norm": 0.2080477476119995,
988
+ "learning_rate": 4.616874621301373e-06,
989
+ "loss": 0.7815,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.5428818943112907,
994
+ "grad_norm": 0.21810027956962585,
995
+ "learning_rate": 4.554731429404293e-06,
996
+ "loss": 0.7953,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.5467321205120801,
1001
+ "grad_norm": 0.2276715785264969,
1002
+ "learning_rate": 4.492657493892822e-06,
1003
+ "loss": 0.7822,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.5505823467128694,
1008
+ "grad_norm": 0.22373175621032715,
1009
+ "learning_rate": 4.430662469650999e-06,
1010
+ "loss": 0.7972,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.5544325729136587,
1015
+ "grad_norm": 0.22084490954875946,
1016
+ "learning_rate": 4.368755999289118e-06,
1017
+ "loss": 0.799,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.558282799114448,
1022
+ "grad_norm": 0.22084571421146393,
1023
+ "learning_rate": 4.306947711643949e-06,
1024
+ "loss": 0.782,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.5621330253152372,
1029
+ "grad_norm": 0.2187720537185669,
1030
+ "learning_rate": 4.245247220281068e-06,
1031
+ "loss": 0.7864,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.5659832515160266,
1036
+ "grad_norm": 0.20967915654182434,
1037
+ "learning_rate": 4.183664121999587e-06,
1038
+ "loss": 0.7841,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.5698334777168159,
1043
+ "grad_norm": 0.22110219299793243,
1044
+ "learning_rate": 4.122207995339474e-06,
1045
+ "loss": 0.7782,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.5736837039176051,
1050
+ "grad_norm": 0.21142074465751648,
1051
+ "learning_rate": 4.060888399091734e-06,
1052
+ "loss": 0.7858,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.5775339301183945,
1057
+ "grad_norm": 0.20014244318008423,
1058
+ "learning_rate": 3.999714870811639e-06,
1059
+ "loss": 0.7942,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.5813841563191837,
1064
+ "grad_norm": 0.2166452258825302,
1065
+ "learning_rate": 3.938696925335275e-06,
1066
+ "loss": 0.7883,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.5852343825199731,
1071
+ "grad_norm": 0.2095969021320343,
1072
+ "learning_rate": 3.87784405329962e-06,
1073
+ "loss": 0.7967,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.5890846087207623,
1078
+ "grad_norm": 0.20942175388336182,
1079
+ "learning_rate": 3.817165719666382e-06,
1080
+ "loss": 0.7988,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.5929348349215516,
1085
+ "grad_norm": 0.2041858285665512,
1086
+ "learning_rate": 3.756671362249841e-06,
1087
+ "loss": 0.8023,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.596785061122341,
1092
+ "grad_norm": 0.20753401517868042,
1093
+ "learning_rate": 3.6963703902488907e-06,
1094
+ "loss": 0.7893,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.6006352873231302,
1099
+ "grad_norm": 0.21055012941360474,
1100
+ "learning_rate": 3.6362721827835655e-06,
1101
+ "loss": 0.8065,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.6044855135239195,
1106
+ "grad_norm": 0.21978570520877838,
1107
+ "learning_rate": 3.576386087436212e-06,
1108
+ "loss": 0.8007,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.6083357397247088,
1113
+ "grad_norm": 0.22774620354175568,
1114
+ "learning_rate": 3.5167214187975913e-06,
1115
+ "loss": 0.7899,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.6121859659254981,
1120
+ "grad_norm": 0.18638041615486145,
1121
+ "learning_rate": 3.457287457018086e-06,
1122
+ "loss": 0.7915,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.6160361921262875,
1127
+ "grad_norm": 0.20376603305339813,
1128
+ "learning_rate": 3.3980934463643003e-06,
1129
+ "loss": 0.7806,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.6198864183270767,
1134
+ "grad_norm": 0.20016922056674957,
1135
+ "learning_rate": 3.3391485937812053e-06,
1136
+ "loss": 0.7615,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.623736644527866,
1141
+ "grad_norm": 0.21633805334568024,
1142
+ "learning_rate": 3.280462067460115e-06,
1143
+ "loss": 0.7621,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.6275868707286553,
1148
+ "grad_norm": 0.21101227402687073,
1149
+ "learning_rate": 3.222042995412669e-06,
1150
+ "loss": 0.7933,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.6314370969294446,
1155
+ "grad_norm": 0.18733595311641693,
1156
+ "learning_rate": 3.163900464051089e-06,
1157
+ "loss": 0.7824,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.635287323130234,
1162
+ "grad_norm": 0.2134382277727127,
1163
+ "learning_rate": 3.1060435167748826e-06,
1164
+ "loss": 0.7923,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.6391375493310232,
1169
+ "grad_norm": 0.2086404711008072,
1170
+ "learning_rate": 3.048481152564253e-06,
1171
+ "loss": 0.7723,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.6429877755318125,
1176
+ "grad_norm": 0.22409841418266296,
1177
+ "learning_rate": 2.9912223245804017e-06,
1178
+ "loss": 0.7913,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.6468380017326018,
1183
+ "grad_norm": 0.21579794585704803,
1184
+ "learning_rate": 2.934275938772981e-06,
1185
+ "loss": 0.7895,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.6506882279333911,
1190
+ "grad_norm": 0.2150273621082306,
1191
+ "learning_rate": 2.8776508524948676e-06,
1192
+ "loss": 0.778,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.6545384541341804,
1197
+ "grad_norm": 0.19151686131954193,
1198
+ "learning_rate": 2.821355873124503e-06,
1199
+ "loss": 0.7798,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.6583886803349697,
1204
+ "grad_norm": 0.2160472571849823,
1205
+ "learning_rate": 2.7653997566960144e-06,
1206
+ "loss": 0.7904,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.662238906535759,
1211
+ "grad_norm": 0.22025944292545319,
1212
+ "learning_rate": 2.709791206537309e-06,
1213
+ "loss": 0.7802,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.6660891327365482,
1218
+ "grad_norm": 0.2108069360256195,
1219
+ "learning_rate": 2.6545388719163747e-06,
1220
+ "loss": 0.7876,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.6699393589373376,
1225
+ "grad_norm": 0.2169920802116394,
1226
+ "learning_rate": 2.599651346695979e-06,
1227
+ "loss": 0.7864,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.6737895851381268,
1232
+ "grad_norm": 0.2031964510679245,
1233
+ "learning_rate": 2.545137167997007e-06,
1234
+ "loss": 0.7838,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.6776398113389162,
1239
+ "grad_norm": 0.20046120882034302,
1240
+ "learning_rate": 2.4910048148705972e-06,
1241
+ "loss": 0.7733,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.6814900375397055,
1246
+ "grad_norm": 0.21911999583244324,
1247
+ "learning_rate": 2.4372627069793327e-06,
1248
+ "loss": 0.8147,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.6853402637404947,
1253
+ "grad_norm": 0.22168420255184174,
1254
+ "learning_rate": 2.3839192032876486e-06,
1255
+ "loss": 0.8014,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.6891904899412841,
1260
+ "grad_norm": 0.21177589893341064,
1261
+ "learning_rate": 2.3309826007617047e-06,
1262
+ "loss": 0.8111,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.6930407161420733,
1267
+ "grad_norm": 0.21178041398525238,
1268
+ "learning_rate": 2.278461133078881e-06,
1269
+ "loss": 0.7747,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.6968909423428626,
1274
+ "grad_norm": 0.22362585365772247,
1275
+ "learning_rate": 2.2263629693471258e-06,
1276
+ "loss": 0.7674,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.700741168543652,
1281
+ "grad_norm": 0.2046084851026535,
1282
+ "learning_rate": 2.1746962128343414e-06,
1283
+ "loss": 0.7896,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.7045913947444412,
1288
+ "grad_norm": 0.20281296968460083,
1289
+ "learning_rate": 2.1234688997080183e-06,
1290
+ "loss": 0.7785,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.7084416209452306,
1295
+ "grad_norm": 0.22024181485176086,
1296
+ "learning_rate": 2.0726889977853053e-06,
1297
+ "loss": 0.785,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.7122918471460198,
1302
+ "grad_norm": 0.22684364020824432,
1303
+ "learning_rate": 2.022364405293703e-06,
1304
+ "loss": 0.7942,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.7161420733468091,
1309
+ "grad_norm": 0.21052239835262299,
1310
+ "learning_rate": 1.9725029496425814e-06,
1311
+ "loss": 0.7901,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.7199922995475985,
1316
+ "grad_norm": 0.19522084295749664,
1317
+ "learning_rate": 1.923112386205727e-06,
1318
+ "loss": 0.7857,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.7238425257483877,
1323
+ "grad_norm": 0.20377729833126068,
1324
+ "learning_rate": 1.874200397115079e-06,
1325
+ "loss": 0.7934,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.727692751949177,
1330
+ "grad_norm": 0.22408553957939148,
1331
+ "learning_rate": 1.825774590065857e-06,
1332
+ "loss": 0.7767,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.7315429781499663,
1337
+ "grad_norm": 0.2192942351102829,
1338
+ "learning_rate": 1.7778424971332813e-06,
1339
+ "loss": 0.7865,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.7353932043507556,
1344
+ "grad_norm": 0.20210614800453186,
1345
+ "learning_rate": 1.7304115736010407e-06,
1346
+ "loss": 0.7855,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.739243430551545,
1351
+ "grad_norm": 0.20998318493366241,
1352
+ "learning_rate": 1.6834891968017108e-06,
1353
+ "loss": 0.778,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.7430936567523342,
1358
+ "grad_norm": 0.2170250564813614,
1359
+ "learning_rate": 1.6370826649692884e-06,
1360
+ "loss": 0.7963,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.7469438829531235,
1365
+ "grad_norm": 0.22103233635425568,
1366
+ "learning_rate": 1.5911991961040463e-06,
1367
+ "loss": 0.8005,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.7507941091539128,
1372
+ "grad_norm": 0.2167920172214508,
1373
+ "learning_rate": 1.545845926849851e-06,
1374
+ "loss": 0.7861,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.7546443353547021,
1379
+ "grad_norm": 0.22922120988368988,
1380
+ "learning_rate": 1.5010299113841397e-06,
1381
+ "loss": 0.8065,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.7584945615554913,
1386
+ "grad_norm": 0.21145367622375488,
1387
+ "learning_rate": 1.4567581203207238e-06,
1388
+ "loss": 0.7933,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.7623447877562807,
1393
+ "grad_norm": 0.2232576459646225,
1394
+ "learning_rate": 1.413037439625593e-06,
1395
+ "loss": 0.7958,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.76619501395707,
1400
+ "grad_norm": 0.22100529074668884,
1401
+ "learning_rate": 1.3698746695458847e-06,
1402
+ "loss": 0.7849,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.7700452401578592,
1407
+ "grad_norm": 0.20790348947048187,
1408
+ "learning_rate": 1.3272765235521745e-06,
1409
+ "loss": 0.779,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.7738954663586486,
1414
+ "grad_norm": 0.21758964657783508,
1415
+ "learning_rate": 1.2852496272942877e-06,
1416
+ "loss": 0.7871,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.7777456925594378,
1421
+ "grad_norm": 0.19855712354183197,
1422
+ "learning_rate": 1.2438005175707396e-06,
1423
+ "loss": 0.7742,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.7815959187602272,
1428
+ "grad_norm": 0.20760610699653625,
1429
+ "learning_rate": 1.2029356413120297e-06,
1430
+ "loss": 0.7616,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.7854461449610165,
1435
+ "grad_norm": 0.20898444950580597,
1436
+ "learning_rate": 1.1626613545778786e-06,
1437
+ "loss": 0.778,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.7892963711618057,
1442
+ "grad_norm": 0.20189915597438812,
1443
+ "learning_rate": 1.1229839215686294e-06,
1444
+ "loss": 0.7815,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.7931465973625951,
1449
+ "grad_norm": 0.19242748618125916,
1450
+ "learning_rate": 1.0839095136509188e-06,
1451
+ "loss": 0.7678,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.7969968235633843,
1456
+ "grad_norm": 0.2289295494556427,
1457
+ "learning_rate": 1.045444208397791e-06,
1458
+ "loss": 0.7905,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.8008470497641736,
1463
+ "grad_norm": 0.19410449266433716,
1464
+ "learning_rate": 1.007593988643402e-06,
1465
+ "loss": 0.7719,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.804697275964963,
1470
+ "grad_norm": 0.20379135012626648,
1471
+ "learning_rate": 9.703647415524613e-07,
1472
+ "loss": 0.7928,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.8085475021657522,
1477
+ "grad_norm": 0.20843130350112915,
1478
+ "learning_rate": 9.337622577045485e-07,
1479
+ "loss": 0.782,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.8123977283665416,
1484
+ "grad_norm": 0.21047905087471008,
1485
+ "learning_rate": 8.977922301934588e-07,
1486
+ "loss": 0.7892,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.8162479545673308,
1491
+ "grad_norm": 0.20890088379383087,
1492
+ "learning_rate": 8.624602537417009e-07,
1493
+ "loss": 0.7902,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.8200981807681201,
1498
+ "grad_norm": 0.22864532470703125,
1499
+ "learning_rate": 8.277718238303123e-07,
1500
+ "loss": 0.7772,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.8239484069689095,
1505
+ "grad_norm": 0.21515177190303802,
1506
+ "learning_rate": 7.937323358440935e-07,
1507
+ "loss": 0.7814,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.8277986331696987,
1512
+ "grad_norm": 0.22752045094966888,
1513
+ "learning_rate": 7.603470842324223e-07,
1514
+ "loss": 0.7738,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.831648859370488,
1519
+ "grad_norm": 0.2043709009885788,
1520
+ "learning_rate": 7.276212616857575e-07,
1521
+ "loss": 0.7912,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.8354990855712773,
1526
+ "grad_norm": 0.2100379317998886,
1527
+ "learning_rate": 6.955599583279837e-07,
1528
+ "loss": 0.7933,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.8393493117720666,
1533
+ "grad_norm": 0.20468413829803467,
1534
+ "learning_rate": 6.641681609246981e-07,
1535
+ "loss": 0.7822,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.8431995379728559,
1540
+ "grad_norm": 0.2026038020849228,
1541
+ "learning_rate": 6.334507521075711e-07,
1542
+ "loss": 0.7928,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.8470497641736452,
1547
+ "grad_norm": 0.2247208207845688,
1548
+ "learning_rate": 6.034125096149179e-07,
1549
+ "loss": 0.7852,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.8508999903744345,
1554
+ "grad_norm": 0.21178293228149414,
1555
+ "learning_rate": 5.740581055485722e-07,
1556
+ "loss": 0.7553,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.8547502165752238,
1561
+ "grad_norm": 0.19472260773181915,
1562
+ "learning_rate": 5.453921056471961e-07,
1563
+ "loss": 0.7893,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.8586004427760131,
1568
+ "grad_norm": 0.21213872730731964,
1569
+ "learning_rate": 5.174189685761288e-07,
1570
+ "loss": 0.784,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.8624506689768023,
1575
+ "grad_norm": 0.19713622331619263,
1576
+ "learning_rate": 4.901430452338979e-07,
1577
+ "loss": 0.7944,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.8663008951775917,
1582
+ "grad_norm": 0.20062507688999176,
1583
+ "learning_rate": 4.6356857807548286e-07,
1584
+ "loss": 0.7807,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.870151121378381,
1589
+ "grad_norm": 0.20865771174430847,
1590
+ "learning_rate": 4.376997004524541e-07,
1591
+ "loss": 0.7698,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.8740013475791703,
1596
+ "grad_norm": 0.2096921056509018,
1597
+ "learning_rate": 4.12540435970073e-07,
1598
+ "loss": 0.7789,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.8778515737799596,
1603
+ "grad_norm": 0.20842768251895905,
1604
+ "learning_rate": 3.880946978614703e-07,
1605
+ "loss": 0.7858,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.8817017999807488,
1610
+ "grad_norm": 0.20931476354599,
1611
+ "learning_rate": 3.643662883789878e-07,
1612
+ "loss": 0.7931,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.8855520261815382,
1617
+ "grad_norm": 0.19721974432468414,
1618
+ "learning_rate": 3.41358898202781e-07,
1619
+ "loss": 0.7716,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.8894022523823275,
1624
+ "grad_norm": 0.19501905143260956,
1625
+ "learning_rate": 3.190761058667741e-07,
1626
+ "loss": 0.7846,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.8932524785831167,
1631
+ "grad_norm": 0.2057318538427353,
1632
+ "learning_rate": 2.9752137720206463e-07,
1633
+ "loss": 0.7876,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.8971027047839061,
1638
+ "grad_norm": 0.20295138657093048,
1639
+ "learning_rate": 2.7669806479785067e-07,
1640
+ "loss": 0.7921,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.9009529309846953,
1645
+ "grad_norm": 0.20851290225982666,
1646
+ "learning_rate": 2.566094074799763e-07,
1647
+ "loss": 0.7877,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.9048031571854847,
1652
+ "grad_norm": 0.20773425698280334,
1653
+ "learning_rate": 2.3725852980716557e-07,
1654
+ "loss": 0.7698,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.908653383386274,
1659
+ "grad_norm": 0.20671038329601288,
1660
+ "learning_rate": 2.1864844158503983e-07,
1661
+ "loss": 0.7815,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.9125036095870632,
1666
+ "grad_norm": 0.22589290142059326,
1667
+ "learning_rate": 2.007820373979702e-07,
1668
+ "loss": 0.7741,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.9163538357878526,
1673
+ "grad_norm": 0.2117127925157547,
1674
+ "learning_rate": 1.8366209615886532e-07,
1675
+ "loss": 0.7843,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.9202040619886418,
1680
+ "grad_norm": 0.2086954563856125,
1681
+ "learning_rate": 1.6729128067693613e-07,
1682
+ "loss": 0.792,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.9240542881894311,
1687
+ "grad_norm": 0.22347524762153625,
1688
+ "learning_rate": 1.5167213724353426e-07,
1689
+ "loss": 0.7929,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.9279045143902205,
1694
+ "grad_norm": 0.20665672421455383,
1695
+ "learning_rate": 1.3680709523610058e-07,
1696
+ "loss": 0.773,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.9317547405910097,
1701
+ "grad_norm": 0.20838679373264313,
1702
+ "learning_rate": 1.2269846674030418e-07,
1703
+ "loss": 0.7999,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.935604966791799,
1708
+ "grad_norm": 0.2185722142457962,
1709
+ "learning_rate": 1.0934844619042595e-07,
1710
+ "loss": 0.7927,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.9394551929925883,
1715
+ "grad_norm": 0.21915051341056824,
1716
+ "learning_rate": 9.675911002803961e-08,
1717
+ "loss": 0.7835,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.9433054191933776,
1722
+ "grad_norm": 0.2238607555627823,
1723
+ "learning_rate": 8.493241637904381e-08,
1724
+ "loss": 0.7819,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.9471556453941669,
1729
+ "grad_norm": 0.2091667801141739,
1730
+ "learning_rate": 7.387020474909689e-08,
1731
+ "loss": 0.7995,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.9510058715949562,
1736
+ "grad_norm": 0.22136050462722778,
1737
+ "learning_rate": 6.357419573750856e-08,
1738
+ "loss": 0.7953,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.9548560977957455,
1743
+ "grad_norm": 0.21015149354934692,
1744
+ "learning_rate": 5.4045990769613365e-08,
1745
+ "loss": 0.7768,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.9587063239965348,
1750
+ "grad_norm": 0.2091272920370102,
1751
+ "learning_rate": 4.5287071847694434e-08,
1752
+ "loss": 0.7839,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.9625565501973241,
1757
+ "grad_norm": 0.20674563944339752,
1758
+ "learning_rate": 3.7298801320467817e-08,
1759
+ "loss": 0.7797,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.9664067763981133,
1764
+ "grad_norm": 0.20854413509368896,
1765
+ "learning_rate": 3.0082421671192576e-08,
1766
+ "loss": 0.7714,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.9702570025989027,
1771
+ "grad_norm": 0.20813319087028503,
1772
+ "learning_rate": 2.3639055324410355e-08,
1773
+ "loss": 0.7908,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.974107228799692,
1778
+ "grad_norm": 0.21100874245166779,
1779
+ "learning_rate": 1.7969704471369477e-08,
1780
+ "loss": 0.7785,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.9779574550004813,
1785
+ "grad_norm": 0.20171211659908295,
1786
+ "learning_rate": 1.3075250914142413e-08,
1787
+ "loss": 0.7792,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.9818076812012706,
1792
+ "grad_norm": 0.202281653881073,
1793
+ "learning_rate": 8.956455928476049e-09,
1794
+ "loss": 0.7903,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.9856579074020598,
1799
+ "grad_norm": 0.20218759775161743,
1800
+ "learning_rate": 5.6139601453786275e-09,
1801
+ "loss": 0.7833,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.9895081336028492,
1806
+ "grad_norm": 0.20875690877437592,
1807
+ "learning_rate": 3.0482834514805602e-09,
1808
+ "loss": 0.7722,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.9933583598036385,
1813
+ "grad_norm": 0.20386770367622375,
1814
+ "learning_rate": 1.2598249081713366e-09,
1815
+ "loss": 0.7643,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.9972085860044277,
1820
+ "grad_norm": 0.21388597786426544,
1821
+ "learning_rate": 2.488626895302826e-10,
1822
+ "loss": 0.7948,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.9999037443449803,
1827
+ "step": 2597,
1828
+ "total_flos": 4.0678236759848387e+18,
1829
+ "train_loss": 0.8037232399721259,
1830
+ "train_runtime": 9936.2878,
1831
+ "train_samples_per_second": 66.917,
1832
+ "train_steps_per_second": 0.261
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": 4.0678236759848387e+18,
1853
+ "train_batch_size": 8,
1854
+ "trial_name": null,
1855
+ "trial_params": null
1856
+ }
continuous/qwen25/webssl_mae300m_full2b_224/finetune/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6cc2a051dcd5ffd13c98c89f37561df2a383c7c72ece62b35da238e8a2bf32
3
+ size 6264
continuous/qwen25/webssl_mae300m_full2b_224/finetune/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
continuous/qwen25/webssl_mae300m_full2b_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": 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": "hf:/cache/ckpt/download/tokenizer/continuous/webssl/webssl-mae300m-full2b-224",
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": null,
86
+ "vocab_size": 151936
87
+ }
continuous/qwen25/webssl_mae300m_full2b_224/pretrain/mm_projector.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6a5c8daa357a21d47b8dbdb4047358e0b941ed8a825d53e33b4b869473718d5
3
+ size 15743032
continuous/qwen25/webssl_mae300m_full2b_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": 5.65291166305542,
15
+ "learning_rate": 0.00032142857142857147,
16
+ "loss": 4.6181,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.03669724770642202,
21
+ "grad_norm": 0.6186829209327698,
22
+ "learning_rate": 0.0006785714285714287,
23
+ "loss": 3.5427,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.05504587155963303,
28
+ "grad_norm": 0.39471256732940674,
29
+ "learning_rate": 0.0009999907688176173,
30
+ "loss": 3.2986,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.07339449541284404,
35
+ "grad_norm": 0.2018515169620514,
36
+ "learning_rate": 0.0009988834393115766,
37
+ "loss": 3.2223,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.09174311926605505,
42
+ "grad_norm": 0.443621963262558,
43
+ "learning_rate": 0.0009959345572940772,
44
+ "loss": 3.2017,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.11009174311926606,
49
+ "grad_norm": 0.44934383034706116,
50
+ "learning_rate": 0.0009911550081155983,
51
+ "loss": 3.1796,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.12844036697247707,
56
+ "grad_norm": 0.24101348221302032,
57
+ "learning_rate": 0.0009845624347566433,
58
+ "loss": 3.1587,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.14678899082568808,
63
+ "grad_norm": 0.47819679975509644,
64
+ "learning_rate": 0.0009761811727013547,
65
+ "loss": 3.1463,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1651376146788991,
70
+ "grad_norm": 0.4919668138027191,
71
+ "learning_rate": 0.0009660421601067666,
72
+ "loss": 3.1257,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.1834862385321101,
77
+ "grad_norm": 0.5093356370925903,
78
+ "learning_rate": 0.0009541828235992926,
79
+ "loss": 3.1137,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2018348623853211,
84
+ "grad_norm": 0.36588388681411743,
85
+ "learning_rate": 0.0009406469401200151,
86
+ "loss": 3.0948,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.22018348623853212,
91
+ "grad_norm": 0.3604224622249603,
92
+ "learning_rate": 0.0009254844753287492,
93
+ "loss": 3.0876,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.23853211009174313,
98
+ "grad_norm": 0.30264344811439514,
99
+ "learning_rate": 0.0009087513991633924,
100
+ "loss": 3.0618,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.25688073394495414,
105
+ "grad_norm": 0.5260919332504272,
106
+ "learning_rate": 0.0008905094792353917,
107
+ "loss": 3.0541,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.27522935779816515,
112
+ "grad_norm": 0.6369373202323914,
113
+ "learning_rate": 0.0008708260528239789,
114
+ "loss": 3.0513,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.29357798165137616,
119
+ "grad_norm": 0.5772455334663391,
120
+ "learning_rate": 0.0008497737783108237,
121
+ "loss": 3.0416,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.3119266055045872,
126
+ "grad_norm": 0.4089295268058777,
127
+ "learning_rate": 0.0008274303669726426,
128
+ "loss": 3.0307,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.3302752293577982,
133
+ "grad_norm": 0.5622636079788208,
134
+ "learning_rate": 0.0008038782961218137,
135
+ "loss": 3.019,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.3486238532110092,
140
+ "grad_norm": 0.3858030140399933,
141
+ "learning_rate": 0.000779204504653894,
142
+ "loss": 3.0155,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.3669724770642202,
147
+ "grad_norm": 0.5004948377609253,
148
+ "learning_rate": 0.0007535000721258791,
149
+ "loss": 2.9942,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.3853211009174312,
154
+ "grad_norm": 0.9467535018920898,
155
+ "learning_rate": 0.00072685988254984,
156
+ "loss": 2.9937,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.4036697247706422,
161
+ "grad_norm": 0.784917950630188,
162
+ "learning_rate": 0.0006993822741429906,
163
+ "loss": 3.0034,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.42201834862385323,
168
+ "grad_norm": 0.3911256492137909,
169
+ "learning_rate": 0.0006711686763270818,
170
+ "loss": 2.9975,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.44036697247706424,
175
+ "grad_norm": 0.39426735043525696,
176
+ "learning_rate": 0.0006423232353170831,
177
+ "loss": 2.9858,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.45871559633027525,
182
+ "grad_norm": 0.4313125014305115,
183
+ "learning_rate": 0.0006129524296812335,
184
+ "loss": 2.974,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.47706422018348627,
189
+ "grad_norm": 0.3931993246078491,
190
+ "learning_rate": 0.0005831646772915651,
191
+ "loss": 2.9848,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.4954128440366973,
196
+ "grad_norm": 0.5386514067649841,
197
+ "learning_rate": 0.0005530699351157809,
198
+ "loss": 2.9636,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.5137614678899083,
203
+ "grad_norm": 0.4829685091972351,
204
+ "learning_rate": 0.0005227792933277943,
205
+ "loss": 2.9684,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.5321100917431193,
210
+ "grad_norm": 0.5054261088371277,
211
+ "learning_rate": 0.0004924045652352092,
212
+ "loss": 2.9514,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.5504587155963303,
217
+ "grad_norm": 0.39571037888526917,
218
+ "learning_rate": 0.0004620578745374633,
219
+ "loss": 2.9542,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.5688073394495413,
224
+ "grad_norm": 0.4996972978115082,
225
+ "learning_rate": 0.0004318512414382059,
226
+ "loss": 2.9631,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.5871559633027523,
231
+ "grad_norm": 0.450388640165329,
232
+ "learning_rate": 0.0004018961691397148,
233
+ "loss": 2.957,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.6055045871559633,
238
+ "grad_norm": 0.3984214663505554,
239
+ "learning_rate": 0.0003723032322457458,
240
+ "loss": 2.9425,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.6238532110091743,
245
+ "grad_norm": 0.5362517237663269,
246
+ "learning_rate": 0.0003431816685921625,
247
+ "loss": 2.9452,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.6422018348623854,
252
+ "grad_norm": 0.34061434864997864,
253
+ "learning_rate": 0.0003146389760120416,
254
+ "loss": 2.9533,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.6605504587155964,
259
+ "grad_norm": 0.37805789709091187,
260
+ "learning_rate": 0.00028678051552373485,
261
+ "loss": 2.9516,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.6788990825688074,
266
+ "grad_norm": 0.37703487277030945,
267
+ "learning_rate": 0.0002597091224066581,
268
+ "loss": 2.9386,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.6972477064220184,
273
+ "grad_norm": 0.3886183500289917,
274
+ "learning_rate": 0.0002335247266004629,
275
+ "loss": 2.9525,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.7155963302752294,
280
+ "grad_norm": 0.42785462737083435,
281
+ "learning_rate": 0.000208323983828828,
282
+ "loss": 2.9395,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.7339449541284404,
287
+ "grad_norm": 0.43333348631858826,
288
+ "learning_rate": 0.0001841999188095224,
289
+ "loss": 2.9347,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.7522935779816514,
294
+ "grad_norm": 0.31141379475593567,
295
+ "learning_rate": 0.00016124158186777676,
296
+ "loss": 2.9334,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.7706422018348624,
301
+ "grad_norm": 0.3718603253364563,
302
+ "learning_rate": 0.0001395337202205211,
303
+ "loss": 2.931,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.7889908256880734,
308
+ "grad_norm": 0.358228474855423,
309
+ "learning_rate": 0.00011915646514489292,
310
+ "loss": 2.9353,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.8073394495412844,
315
+ "grad_norm": 0.3305974304676056,
316
+ "learning_rate": 0.00010018503618578818,
317
+ "loss": 2.939,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.8256880733944955,
322
+ "grad_norm": 0.32799428701400757,
323
+ "learning_rate": 8.268946349432583e-05,
324
+ "loss": 2.9377,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.8440366972477065,
329
+ "grad_norm": 0.3345390856266022,
330
+ "learning_rate": 6.673432932217117e-05,
331
+ "loss": 2.9256,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.8623853211009175,
336
+ "grad_norm": 0.30341485142707825,
337
+ "learning_rate": 5.2378529625954684e-05,
338
+ "loss": 2.9155,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.8807339449541285,
343
+ "grad_norm": 0.3133603036403656,
344
+ "learning_rate": 3.9675056661785556e-05,
345
+ "loss": 2.9241,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.8990825688073395,
350
+ "grad_norm": 0.2971453368663788,
351
+ "learning_rate": 2.8670803372379538e-05,
352
+ "loss": 2.9328,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.9174311926605505,
357
+ "grad_norm": 0.2996547222137451,
358
+ "learning_rate": 1.9406390288876586e-05,
359
+ "loss": 2.9389,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.9357798165137615,
364
+ "grad_norm": 0.2756503224372864,
365
+ "learning_rate": 1.191601558631461e-05,
366
+ "loss": 2.9268,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.9541284403669725,
371
+ "grad_norm": 0.23984281718730927,
372
+ "learning_rate": 6.2273288462559305e-06,
373
+ "loss": 2.9198,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.9724770642201835,
378
+ "grad_norm": 0.24871161580085754,
379
+ "learning_rate": 2.361328992552314e-06,
380
+ "loss": 2.924,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.9908256880733946,
385
+ "grad_norm": 0.32040935754776,
386
+ "learning_rate": 3.322867770044202e-07,
387
+ "loss": 2.926,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.0,
392
+ "step": 545,
393
+ "total_flos": 3.3397896333439795e+17,
394
+ "train_loss": 3.0420943933889406,
395
+ "train_runtime": 5286.3333,
396
+ "train_samples_per_second": 105.579,
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": 3.3397896333439795e+17,
418
+ "train_batch_size": 128,
419
+ "trial_name": null,
420
+ "trial_params": null
421
+ }
continuous/qwen25/webssl_mae3b_full2b_224/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/webssl_mae3b_full2b_224/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/webssl_mae3b_full2b_224/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": 3072,
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": "hf:/cache/ckpt/download/tokenizer/continuous/webssl/webssl-mae3b-full2b-224",
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": null,
86
+ "vocab_size": 151936
87
+ }
continuous/qwen25/webssl_mae3b_full2b_224/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/webssl_mae3b_full2b_224/finetune/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
continuous/qwen25/webssl_mae3b_full2b_224/finetune/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09c70bbfe3dd2c872ab13c5b4cfeb9637870df0d1acd809498ac7eb3ea54cf2
3
+ size 4980792424
continuous/qwen25/webssl_mae3b_full2b_224/finetune/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4aa7a18fbfcb26e427340845ebda98e835e5ba81176eeb8319978bdd0b6dcb5
3
+ size 4516786192
continuous/qwen25/webssl_mae3b_full2b_224/finetune/model.safetensors.index.json ADDED
@@ -0,0 +1,775 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4508283392,
4
+ "total_size": 9497476096
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.embeddings.cls_token": "model-00001-of-00002.safetensors",
351
+ "model.vision_tower.vision_tower.embeddings.patch_embeddings.projection.bias": "model-00001-of-00002.safetensors",
352
+ "model.vision_tower.vision_tower.embeddings.patch_embeddings.projection.weight": "model-00001-of-00002.safetensors",
353
+ "model.vision_tower.vision_tower.embeddings.position_embeddings": "model-00001-of-00002.safetensors",
354
+ "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.key.bias": "model-00001-of-00002.safetensors",
355
+ "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.key.weight": "model-00001-of-00002.safetensors",
356
+ "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.query.bias": "model-00001-of-00002.safetensors",
357
+ "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.query.weight": "model-00001-of-00002.safetensors",
358
+ "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.value.bias": "model-00001-of-00002.safetensors",
359
+ "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.value.weight": "model-00001-of-00002.safetensors",
360
+ "model.vision_tower.vision_tower.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
361
+ "model.vision_tower.vision_tower.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
362
+ "model.vision_tower.vision_tower.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00002.safetensors",
363
+ "model.vision_tower.vision_tower.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00002.safetensors",
364
+ "model.vision_tower.vision_tower.encoder.layer.0.layernorm_after.bias": "model-00001-of-00002.safetensors",
365
+ "model.vision_tower.vision_tower.encoder.layer.0.layernorm_after.weight": "model-00001-of-00002.safetensors",
366
+ "model.vision_tower.vision_tower.encoder.layer.0.layernorm_before.bias": "model-00001-of-00002.safetensors",
367
+ "model.vision_tower.vision_tower.encoder.layer.0.layernorm_before.weight": "model-00001-of-00002.safetensors",
368
+ "model.vision_tower.vision_tower.encoder.layer.0.output.dense.bias": "model-00001-of-00002.safetensors",
369
+ "model.vision_tower.vision_tower.encoder.layer.0.output.dense.weight": "model-00001-of-00002.safetensors",
370
+ "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.key.bias": "model-00001-of-00002.safetensors",
371
+ "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.key.weight": "model-00001-of-00002.safetensors",
372
+ "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.query.bias": "model-00001-of-00002.safetensors",
373
+ "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.query.weight": "model-00001-of-00002.safetensors",
374
+ "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.value.bias": "model-00001-of-00002.safetensors",
375
+ "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.value.weight": "model-00001-of-00002.safetensors",
376
+ "model.vision_tower.vision_tower.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors",
377
+ "model.vision_tower.vision_tower.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors",
378
+ "model.vision_tower.vision_tower.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00002.safetensors",
379
+ "model.vision_tower.vision_tower.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00002.safetensors",
380
+ "model.vision_tower.vision_tower.encoder.layer.1.layernorm_after.bias": "model-00001-of-00002.safetensors",
381
+ "model.vision_tower.vision_tower.encoder.layer.1.layernorm_after.weight": "model-00001-of-00002.safetensors",
382
+ "model.vision_tower.vision_tower.encoder.layer.1.layernorm_before.bias": "model-00001-of-00002.safetensors",
383
+ "model.vision_tower.vision_tower.encoder.layer.1.layernorm_before.weight": "model-00001-of-00002.safetensors",
384
+ "model.vision_tower.vision_tower.encoder.layer.1.output.dense.bias": "model-00001-of-00002.safetensors",
385
+ "model.vision_tower.vision_tower.encoder.layer.1.output.dense.weight": "model-00001-of-00002.safetensors",
386
+ "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.key.bias": "model-00002-of-00002.safetensors",
387
+ "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.key.weight": "model-00002-of-00002.safetensors",
388
+ "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.query.bias": "model-00002-of-00002.safetensors",
389
+ "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.query.weight": "model-00002-of-00002.safetensors",
390
+ "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.value.bias": "model-00002-of-00002.safetensors",
391
+ "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.value.weight": "model-00002-of-00002.safetensors",
392
+ "model.vision_tower.vision_tower.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00002.safetensors",
393
+ "model.vision_tower.vision_tower.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00002.safetensors",
394
+ "model.vision_tower.vision_tower.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00002.safetensors",
395
+ "model.vision_tower.vision_tower.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00002.safetensors",
396
+ "model.vision_tower.vision_tower.encoder.layer.10.layernorm_after.bias": "model-00002-of-00002.safetensors",
397
+ "model.vision_tower.vision_tower.encoder.layer.10.layernorm_after.weight": "model-00002-of-00002.safetensors",
398
+ "model.vision_tower.vision_tower.encoder.layer.10.layernorm_before.bias": "model-00002-of-00002.safetensors",
399
+ "model.vision_tower.vision_tower.encoder.layer.10.layernorm_before.weight": "model-00002-of-00002.safetensors",
400
+ "model.vision_tower.vision_tower.encoder.layer.10.output.dense.bias": "model-00002-of-00002.safetensors",
401
+ "model.vision_tower.vision_tower.encoder.layer.10.output.dense.weight": "model-00002-of-00002.safetensors",
402
+ "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.key.bias": "model-00002-of-00002.safetensors",
403
+ "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.key.weight": "model-00002-of-00002.safetensors",
404
+ "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.query.bias": "model-00002-of-00002.safetensors",
405
+ "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.query.weight": "model-00002-of-00002.safetensors",
406
+ "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.value.bias": "model-00002-of-00002.safetensors",
407
+ "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.value.weight": "model-00002-of-00002.safetensors",
408
+ "model.vision_tower.vision_tower.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00002.safetensors",
409
+ "model.vision_tower.vision_tower.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00002.safetensors",
410
+ "model.vision_tower.vision_tower.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00002.safetensors",
411
+ "model.vision_tower.vision_tower.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00002.safetensors",
412
+ "model.vision_tower.vision_tower.encoder.layer.11.layernorm_after.bias": "model-00002-of-00002.safetensors",
413
+ "model.vision_tower.vision_tower.encoder.layer.11.layernorm_after.weight": "model-00002-of-00002.safetensors",
414
+ "model.vision_tower.vision_tower.encoder.layer.11.layernorm_before.bias": "model-00002-of-00002.safetensors",
415
+ "model.vision_tower.vision_tower.encoder.layer.11.layernorm_before.weight": "model-00002-of-00002.safetensors",
416
+ "model.vision_tower.vision_tower.encoder.layer.11.output.dense.bias": "model-00002-of-00002.safetensors",
417
+ "model.vision_tower.vision_tower.encoder.layer.11.output.dense.weight": "model-00002-of-00002.safetensors",
418
+ "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.key.bias": "model-00002-of-00002.safetensors",
419
+ "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.key.weight": "model-00002-of-00002.safetensors",
420
+ "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.query.bias": "model-00002-of-00002.safetensors",
421
+ "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.query.weight": "model-00002-of-00002.safetensors",
422
+ "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.value.bias": "model-00002-of-00002.safetensors",
423
+ "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.value.weight": "model-00002-of-00002.safetensors",
424
+ "model.vision_tower.vision_tower.encoder.layer.12.attention.output.dense.bias": "model-00002-of-00002.safetensors",
425
+ "model.vision_tower.vision_tower.encoder.layer.12.attention.output.dense.weight": "model-00002-of-00002.safetensors",
426
+ "model.vision_tower.vision_tower.encoder.layer.12.intermediate.dense.bias": "model-00002-of-00002.safetensors",
427
+ "model.vision_tower.vision_tower.encoder.layer.12.intermediate.dense.weight": "model-00002-of-00002.safetensors",
428
+ "model.vision_tower.vision_tower.encoder.layer.12.layernorm_after.bias": "model-00002-of-00002.safetensors",
429
+ "model.vision_tower.vision_tower.encoder.layer.12.layernorm_after.weight": "model-00002-of-00002.safetensors",
430
+ "model.vision_tower.vision_tower.encoder.layer.12.layernorm_before.bias": "model-00002-of-00002.safetensors",
431
+ "model.vision_tower.vision_tower.encoder.layer.12.layernorm_before.weight": "model-00002-of-00002.safetensors",
432
+ "model.vision_tower.vision_tower.encoder.layer.12.output.dense.bias": "model-00002-of-00002.safetensors",
433
+ "model.vision_tower.vision_tower.encoder.layer.12.output.dense.weight": "model-00002-of-00002.safetensors",
434
+ "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.key.bias": "model-00002-of-00002.safetensors",
435
+ "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.key.weight": "model-00002-of-00002.safetensors",
436
+ "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.query.bias": "model-00002-of-00002.safetensors",
437
+ "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.query.weight": "model-00002-of-00002.safetensors",
438
+ "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.value.bias": "model-00002-of-00002.safetensors",
439
+ "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.value.weight": "model-00002-of-00002.safetensors",
440
+ "model.vision_tower.vision_tower.encoder.layer.13.attention.output.dense.bias": "model-00002-of-00002.safetensors",
441
+ "model.vision_tower.vision_tower.encoder.layer.13.attention.output.dense.weight": "model-00002-of-00002.safetensors",
442
+ "model.vision_tower.vision_tower.encoder.layer.13.intermediate.dense.bias": "model-00002-of-00002.safetensors",
443
+ "model.vision_tower.vision_tower.encoder.layer.13.intermediate.dense.weight": "model-00002-of-00002.safetensors",
444
+ "model.vision_tower.vision_tower.encoder.layer.13.layernorm_after.bias": "model-00002-of-00002.safetensors",
445
+ "model.vision_tower.vision_tower.encoder.layer.13.layernorm_after.weight": "model-00002-of-00002.safetensors",
446
+ "model.vision_tower.vision_tower.encoder.layer.13.layernorm_before.bias": "model-00002-of-00002.safetensors",
447
+ "model.vision_tower.vision_tower.encoder.layer.13.layernorm_before.weight": "model-00002-of-00002.safetensors",
448
+ "model.vision_tower.vision_tower.encoder.layer.13.output.dense.bias": "model-00002-of-00002.safetensors",
449
+ "model.vision_tower.vision_tower.encoder.layer.13.output.dense.weight": "model-00002-of-00002.safetensors",
450
+ "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.key.bias": "model-00002-of-00002.safetensors",
451
+ "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.key.weight": "model-00002-of-00002.safetensors",
452
+ "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.query.bias": "model-00002-of-00002.safetensors",
453
+ "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.query.weight": "model-00002-of-00002.safetensors",
454
+ "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.value.bias": "model-00002-of-00002.safetensors",
455
+ "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.value.weight": "model-00002-of-00002.safetensors",
456
+ "model.vision_tower.vision_tower.encoder.layer.14.attention.output.dense.bias": "model-00002-of-00002.safetensors",
457
+ "model.vision_tower.vision_tower.encoder.layer.14.attention.output.dense.weight": "model-00002-of-00002.safetensors",
458
+ "model.vision_tower.vision_tower.encoder.layer.14.intermediate.dense.bias": "model-00002-of-00002.safetensors",
459
+ "model.vision_tower.vision_tower.encoder.layer.14.intermediate.dense.weight": "model-00002-of-00002.safetensors",
460
+ "model.vision_tower.vision_tower.encoder.layer.14.layernorm_after.bias": "model-00002-of-00002.safetensors",
461
+ "model.vision_tower.vision_tower.encoder.layer.14.layernorm_after.weight": "model-00002-of-00002.safetensors",
462
+ "model.vision_tower.vision_tower.encoder.layer.14.layernorm_before.bias": "model-00002-of-00002.safetensors",
463
+ "model.vision_tower.vision_tower.encoder.layer.14.layernorm_before.weight": "model-00002-of-00002.safetensors",
464
+ "model.vision_tower.vision_tower.encoder.layer.14.output.dense.bias": "model-00002-of-00002.safetensors",
465
+ "model.vision_tower.vision_tower.encoder.layer.14.output.dense.weight": "model-00002-of-00002.safetensors",
466
+ "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.key.bias": "model-00002-of-00002.safetensors",
467
+ "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.key.weight": "model-00002-of-00002.safetensors",
468
+ "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.query.bias": "model-00002-of-00002.safetensors",
469
+ "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.query.weight": "model-00002-of-00002.safetensors",
470
+ "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.value.bias": "model-00002-of-00002.safetensors",
471
+ "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.value.weight": "model-00002-of-00002.safetensors",
472
+ "model.vision_tower.vision_tower.encoder.layer.15.attention.output.dense.bias": "model-00002-of-00002.safetensors",
473
+ "model.vision_tower.vision_tower.encoder.layer.15.attention.output.dense.weight": "model-00002-of-00002.safetensors",
474
+ "model.vision_tower.vision_tower.encoder.layer.15.intermediate.dense.bias": "model-00002-of-00002.safetensors",
475
+ "model.vision_tower.vision_tower.encoder.layer.15.intermediate.dense.weight": "model-00002-of-00002.safetensors",
476
+ "model.vision_tower.vision_tower.encoder.layer.15.layernorm_after.bias": "model-00002-of-00002.safetensors",
477
+ "model.vision_tower.vision_tower.encoder.layer.15.layernorm_after.weight": "model-00002-of-00002.safetensors",
478
+ "model.vision_tower.vision_tower.encoder.layer.15.layernorm_before.bias": "model-00002-of-00002.safetensors",
479
+ "model.vision_tower.vision_tower.encoder.layer.15.layernorm_before.weight": "model-00002-of-00002.safetensors",
480
+ "model.vision_tower.vision_tower.encoder.layer.15.output.dense.bias": "model-00002-of-00002.safetensors",
481
+ "model.vision_tower.vision_tower.encoder.layer.15.output.dense.weight": "model-00002-of-00002.safetensors",
482
+ "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.key.bias": "model-00002-of-00002.safetensors",
483
+ "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.key.weight": "model-00002-of-00002.safetensors",
484
+ "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.query.bias": "model-00002-of-00002.safetensors",
485
+ "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.query.weight": "model-00002-of-00002.safetensors",
486
+ "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.value.bias": "model-00002-of-00002.safetensors",
487
+ "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.value.weight": "model-00002-of-00002.safetensors",
488
+ "model.vision_tower.vision_tower.encoder.layer.16.attention.output.dense.bias": "model-00002-of-00002.safetensors",
489
+ "model.vision_tower.vision_tower.encoder.layer.16.attention.output.dense.weight": "model-00002-of-00002.safetensors",
490
+ "model.vision_tower.vision_tower.encoder.layer.16.intermediate.dense.bias": "model-00002-of-00002.safetensors",
491
+ "model.vision_tower.vision_tower.encoder.layer.16.intermediate.dense.weight": "model-00002-of-00002.safetensors",
492
+ "model.vision_tower.vision_tower.encoder.layer.16.layernorm_after.bias": "model-00002-of-00002.safetensors",
493
+ "model.vision_tower.vision_tower.encoder.layer.16.layernorm_after.weight": "model-00002-of-00002.safetensors",
494
+ "model.vision_tower.vision_tower.encoder.layer.16.layernorm_before.bias": "model-00002-of-00002.safetensors",
495
+ "model.vision_tower.vision_tower.encoder.layer.16.layernorm_before.weight": "model-00002-of-00002.safetensors",
496
+ "model.vision_tower.vision_tower.encoder.layer.16.output.dense.bias": "model-00002-of-00002.safetensors",
497
+ "model.vision_tower.vision_tower.encoder.layer.16.output.dense.weight": "model-00002-of-00002.safetensors",
498
+ "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.key.bias": "model-00002-of-00002.safetensors",
499
+ "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.key.weight": "model-00002-of-00002.safetensors",
500
+ "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.query.bias": "model-00002-of-00002.safetensors",
501
+ "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.query.weight": "model-00002-of-00002.safetensors",
502
+ "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.value.bias": "model-00002-of-00002.safetensors",
503
+ "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.value.weight": "model-00002-of-00002.safetensors",
504
+ "model.vision_tower.vision_tower.encoder.layer.17.attention.output.dense.bias": "model-00002-of-00002.safetensors",
505
+ "model.vision_tower.vision_tower.encoder.layer.17.attention.output.dense.weight": "model-00002-of-00002.safetensors",
506
+ "model.vision_tower.vision_tower.encoder.layer.17.intermediate.dense.bias": "model-00002-of-00002.safetensors",
507
+ "model.vision_tower.vision_tower.encoder.layer.17.intermediate.dense.weight": "model-00002-of-00002.safetensors",
508
+ "model.vision_tower.vision_tower.encoder.layer.17.layernorm_after.bias": "model-00002-of-00002.safetensors",
509
+ "model.vision_tower.vision_tower.encoder.layer.17.layernorm_after.weight": "model-00002-of-00002.safetensors",
510
+ "model.vision_tower.vision_tower.encoder.layer.17.layernorm_before.bias": "model-00002-of-00002.safetensors",
511
+ "model.vision_tower.vision_tower.encoder.layer.17.layernorm_before.weight": "model-00002-of-00002.safetensors",
512
+ "model.vision_tower.vision_tower.encoder.layer.17.output.dense.bias": "model-00002-of-00002.safetensors",
513
+ "model.vision_tower.vision_tower.encoder.layer.17.output.dense.weight": "model-00002-of-00002.safetensors",
514
+ "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.key.bias": "model-00002-of-00002.safetensors",
515
+ "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.key.weight": "model-00002-of-00002.safetensors",
516
+ "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.query.bias": "model-00002-of-00002.safetensors",
517
+ "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.query.weight": "model-00002-of-00002.safetensors",
518
+ "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.value.bias": "model-00002-of-00002.safetensors",
519
+ "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.value.weight": "model-00002-of-00002.safetensors",
520
+ "model.vision_tower.vision_tower.encoder.layer.18.attention.output.dense.bias": "model-00002-of-00002.safetensors",
521
+ "model.vision_tower.vision_tower.encoder.layer.18.attention.output.dense.weight": "model-00002-of-00002.safetensors",
522
+ "model.vision_tower.vision_tower.encoder.layer.18.intermediate.dense.bias": "model-00002-of-00002.safetensors",
523
+ "model.vision_tower.vision_tower.encoder.layer.18.intermediate.dense.weight": "model-00002-of-00002.safetensors",
524
+ "model.vision_tower.vision_tower.encoder.layer.18.layernorm_after.bias": "model-00002-of-00002.safetensors",
525
+ "model.vision_tower.vision_tower.encoder.layer.18.layernorm_after.weight": "model-00002-of-00002.safetensors",
526
+ "model.vision_tower.vision_tower.encoder.layer.18.layernorm_before.bias": "model-00002-of-00002.safetensors",
527
+ "model.vision_tower.vision_tower.encoder.layer.18.layernorm_before.weight": "model-00002-of-00002.safetensors",
528
+ "model.vision_tower.vision_tower.encoder.layer.18.output.dense.bias": "model-00002-of-00002.safetensors",
529
+ "model.vision_tower.vision_tower.encoder.layer.18.output.dense.weight": "model-00002-of-00002.safetensors",
530
+ "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.key.bias": "model-00002-of-00002.safetensors",
531
+ "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.key.weight": "model-00002-of-00002.safetensors",
532
+ "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.query.bias": "model-00002-of-00002.safetensors",
533
+ "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.query.weight": "model-00002-of-00002.safetensors",
534
+ "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.value.bias": "model-00002-of-00002.safetensors",
535
+ "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.value.weight": "model-00002-of-00002.safetensors",
536
+ "model.vision_tower.vision_tower.encoder.layer.19.attention.output.dense.bias": "model-00002-of-00002.safetensors",
537
+ "model.vision_tower.vision_tower.encoder.layer.19.attention.output.dense.weight": "model-00002-of-00002.safetensors",
538
+ "model.vision_tower.vision_tower.encoder.layer.19.intermediate.dense.bias": "model-00002-of-00002.safetensors",
539
+ "model.vision_tower.vision_tower.encoder.layer.19.intermediate.dense.weight": "model-00002-of-00002.safetensors",
540
+ "model.vision_tower.vision_tower.encoder.layer.19.layernorm_after.bias": "model-00002-of-00002.safetensors",
541
+ "model.vision_tower.vision_tower.encoder.layer.19.layernorm_after.weight": "model-00002-of-00002.safetensors",
542
+ "model.vision_tower.vision_tower.encoder.layer.19.layernorm_before.bias": "model-00002-of-00002.safetensors",
543
+ "model.vision_tower.vision_tower.encoder.layer.19.layernorm_before.weight": "model-00002-of-00002.safetensors",
544
+ "model.vision_tower.vision_tower.encoder.layer.19.output.dense.bias": "model-00002-of-00002.safetensors",
545
+ "model.vision_tower.vision_tower.encoder.layer.19.output.dense.weight": "model-00002-of-00002.safetensors",
546
+ "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.key.bias": "model-00001-of-00002.safetensors",
547
+ "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.key.weight": "model-00001-of-00002.safetensors",
548
+ "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.query.bias": "model-00001-of-00002.safetensors",
549
+ "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.query.weight": "model-00001-of-00002.safetensors",
550
+ "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.value.bias": "model-00001-of-00002.safetensors",
551
+ "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.value.weight": "model-00001-of-00002.safetensors",
552
+ "model.vision_tower.vision_tower.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors",
553
+ "model.vision_tower.vision_tower.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors",
554
+ "model.vision_tower.vision_tower.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00002.safetensors",
555
+ "model.vision_tower.vision_tower.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00002.safetensors",
556
+ "model.vision_tower.vision_tower.encoder.layer.2.layernorm_after.bias": "model-00001-of-00002.safetensors",
557
+ "model.vision_tower.vision_tower.encoder.layer.2.layernorm_after.weight": "model-00001-of-00002.safetensors",
558
+ "model.vision_tower.vision_tower.encoder.layer.2.layernorm_before.bias": "model-00001-of-00002.safetensors",
559
+ "model.vision_tower.vision_tower.encoder.layer.2.layernorm_before.weight": "model-00001-of-00002.safetensors",
560
+ "model.vision_tower.vision_tower.encoder.layer.2.output.dense.bias": "model-00001-of-00002.safetensors",
561
+ "model.vision_tower.vision_tower.encoder.layer.2.output.dense.weight": "model-00001-of-00002.safetensors",
562
+ "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.key.bias": "model-00002-of-00002.safetensors",
563
+ "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.key.weight": "model-00002-of-00002.safetensors",
564
+ "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.query.bias": "model-00002-of-00002.safetensors",
565
+ "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.query.weight": "model-00002-of-00002.safetensors",
566
+ "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.value.bias": "model-00002-of-00002.safetensors",
567
+ "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.value.weight": "model-00002-of-00002.safetensors",
568
+ "model.vision_tower.vision_tower.encoder.layer.20.attention.output.dense.bias": "model-00002-of-00002.safetensors",
569
+ "model.vision_tower.vision_tower.encoder.layer.20.attention.output.dense.weight": "model-00002-of-00002.safetensors",
570
+ "model.vision_tower.vision_tower.encoder.layer.20.intermediate.dense.bias": "model-00002-of-00002.safetensors",
571
+ "model.vision_tower.vision_tower.encoder.layer.20.intermediate.dense.weight": "model-00002-of-00002.safetensors",
572
+ "model.vision_tower.vision_tower.encoder.layer.20.layernorm_after.bias": "model-00002-of-00002.safetensors",
573
+ "model.vision_tower.vision_tower.encoder.layer.20.layernorm_after.weight": "model-00002-of-00002.safetensors",
574
+ "model.vision_tower.vision_tower.encoder.layer.20.layernorm_before.bias": "model-00002-of-00002.safetensors",
575
+ "model.vision_tower.vision_tower.encoder.layer.20.layernorm_before.weight": "model-00002-of-00002.safetensors",
576
+ "model.vision_tower.vision_tower.encoder.layer.20.output.dense.bias": "model-00002-of-00002.safetensors",
577
+ "model.vision_tower.vision_tower.encoder.layer.20.output.dense.weight": "model-00002-of-00002.safetensors",
578
+ "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.key.bias": "model-00002-of-00002.safetensors",
579
+ "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.key.weight": "model-00002-of-00002.safetensors",
580
+ "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.query.bias": "model-00002-of-00002.safetensors",
581
+ "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.query.weight": "model-00002-of-00002.safetensors",
582
+ "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.value.bias": "model-00002-of-00002.safetensors",
583
+ "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.value.weight": "model-00002-of-00002.safetensors",
584
+ "model.vision_tower.vision_tower.encoder.layer.21.attention.output.dense.bias": "model-00002-of-00002.safetensors",
585
+ "model.vision_tower.vision_tower.encoder.layer.21.attention.output.dense.weight": "model-00002-of-00002.safetensors",
586
+ "model.vision_tower.vision_tower.encoder.layer.21.intermediate.dense.bias": "model-00002-of-00002.safetensors",
587
+ "model.vision_tower.vision_tower.encoder.layer.21.intermediate.dense.weight": "model-00002-of-00002.safetensors",
588
+ "model.vision_tower.vision_tower.encoder.layer.21.layernorm_after.bias": "model-00002-of-00002.safetensors",
589
+ "model.vision_tower.vision_tower.encoder.layer.21.layernorm_after.weight": "model-00002-of-00002.safetensors",
590
+ "model.vision_tower.vision_tower.encoder.layer.21.layernorm_before.bias": "model-00002-of-00002.safetensors",
591
+ "model.vision_tower.vision_tower.encoder.layer.21.layernorm_before.weight": "model-00002-of-00002.safetensors",
592
+ "model.vision_tower.vision_tower.encoder.layer.21.output.dense.bias": "model-00002-of-00002.safetensors",
593
+ "model.vision_tower.vision_tower.encoder.layer.21.output.dense.weight": "model-00002-of-00002.safetensors",
594
+ "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.key.bias": "model-00002-of-00002.safetensors",
595
+ "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.key.weight": "model-00002-of-00002.safetensors",
596
+ "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.query.bias": "model-00002-of-00002.safetensors",
597
+ "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.query.weight": "model-00002-of-00002.safetensors",
598
+ "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.value.bias": "model-00002-of-00002.safetensors",
599
+ "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.value.weight": "model-00002-of-00002.safetensors",
600
+ "model.vision_tower.vision_tower.encoder.layer.22.attention.output.dense.bias": "model-00002-of-00002.safetensors",
601
+ "model.vision_tower.vision_tower.encoder.layer.22.attention.output.dense.weight": "model-00002-of-00002.safetensors",
602
+ "model.vision_tower.vision_tower.encoder.layer.22.intermediate.dense.bias": "model-00002-of-00002.safetensors",
603
+ "model.vision_tower.vision_tower.encoder.layer.22.intermediate.dense.weight": "model-00002-of-00002.safetensors",
604
+ "model.vision_tower.vision_tower.encoder.layer.22.layernorm_after.bias": "model-00002-of-00002.safetensors",
605
+ "model.vision_tower.vision_tower.encoder.layer.22.layernorm_after.weight": "model-00002-of-00002.safetensors",
606
+ "model.vision_tower.vision_tower.encoder.layer.22.layernorm_before.bias": "model-00002-of-00002.safetensors",
607
+ "model.vision_tower.vision_tower.encoder.layer.22.layernorm_before.weight": "model-00002-of-00002.safetensors",
608
+ "model.vision_tower.vision_tower.encoder.layer.22.output.dense.bias": "model-00002-of-00002.safetensors",
609
+ "model.vision_tower.vision_tower.encoder.layer.22.output.dense.weight": "model-00002-of-00002.safetensors",
610
+ "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.key.bias": "model-00002-of-00002.safetensors",
611
+ "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.key.weight": "model-00002-of-00002.safetensors",
612
+ "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.query.bias": "model-00002-of-00002.safetensors",
613
+ "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.query.weight": "model-00002-of-00002.safetensors",
614
+ "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.value.bias": "model-00002-of-00002.safetensors",
615
+ "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.value.weight": "model-00002-of-00002.safetensors",
616
+ "model.vision_tower.vision_tower.encoder.layer.23.attention.output.dense.bias": "model-00002-of-00002.safetensors",
617
+ "model.vision_tower.vision_tower.encoder.layer.23.attention.output.dense.weight": "model-00002-of-00002.safetensors",
618
+ "model.vision_tower.vision_tower.encoder.layer.23.intermediate.dense.bias": "model-00002-of-00002.safetensors",
619
+ "model.vision_tower.vision_tower.encoder.layer.23.intermediate.dense.weight": "model-00002-of-00002.safetensors",
620
+ "model.vision_tower.vision_tower.encoder.layer.23.layernorm_after.bias": "model-00002-of-00002.safetensors",
621
+ "model.vision_tower.vision_tower.encoder.layer.23.layernorm_after.weight": "model-00002-of-00002.safetensors",
622
+ "model.vision_tower.vision_tower.encoder.layer.23.layernorm_before.bias": "model-00002-of-00002.safetensors",
623
+ "model.vision_tower.vision_tower.encoder.layer.23.layernorm_before.weight": "model-00002-of-00002.safetensors",
624
+ "model.vision_tower.vision_tower.encoder.layer.23.output.dense.bias": "model-00002-of-00002.safetensors",
625
+ "model.vision_tower.vision_tower.encoder.layer.23.output.dense.weight": "model-00002-of-00002.safetensors",
626
+ "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.key.bias": "model-00002-of-00002.safetensors",
627
+ "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.key.weight": "model-00002-of-00002.safetensors",
628
+ "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.query.bias": "model-00002-of-00002.safetensors",
629
+ "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.query.weight": "model-00002-of-00002.safetensors",
630
+ "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.value.bias": "model-00002-of-00002.safetensors",
631
+ "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.value.weight": "model-00002-of-00002.safetensors",
632
+ "model.vision_tower.vision_tower.encoder.layer.24.attention.output.dense.bias": "model-00002-of-00002.safetensors",
633
+ "model.vision_tower.vision_tower.encoder.layer.24.attention.output.dense.weight": "model-00002-of-00002.safetensors",
634
+ "model.vision_tower.vision_tower.encoder.layer.24.intermediate.dense.bias": "model-00002-of-00002.safetensors",
635
+ "model.vision_tower.vision_tower.encoder.layer.24.intermediate.dense.weight": "model-00002-of-00002.safetensors",
636
+ "model.vision_tower.vision_tower.encoder.layer.24.layernorm_after.bias": "model-00002-of-00002.safetensors",
637
+ "model.vision_tower.vision_tower.encoder.layer.24.layernorm_after.weight": "model-00002-of-00002.safetensors",
638
+ "model.vision_tower.vision_tower.encoder.layer.24.layernorm_before.bias": "model-00002-of-00002.safetensors",
639
+ "model.vision_tower.vision_tower.encoder.layer.24.layernorm_before.weight": "model-00002-of-00002.safetensors",
640
+ "model.vision_tower.vision_tower.encoder.layer.24.output.dense.bias": "model-00002-of-00002.safetensors",
641
+ "model.vision_tower.vision_tower.encoder.layer.24.output.dense.weight": "model-00002-of-00002.safetensors",
642
+ "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.key.bias": "model-00002-of-00002.safetensors",
643
+ "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.key.weight": "model-00002-of-00002.safetensors",
644
+ "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.query.bias": "model-00002-of-00002.safetensors",
645
+ "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.query.weight": "model-00002-of-00002.safetensors",
646
+ "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.value.bias": "model-00002-of-00002.safetensors",
647
+ "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.value.weight": "model-00002-of-00002.safetensors",
648
+ "model.vision_tower.vision_tower.encoder.layer.25.attention.output.dense.bias": "model-00002-of-00002.safetensors",
649
+ "model.vision_tower.vision_tower.encoder.layer.25.attention.output.dense.weight": "model-00002-of-00002.safetensors",
650
+ "model.vision_tower.vision_tower.encoder.layer.25.intermediate.dense.bias": "model-00002-of-00002.safetensors",
651
+ "model.vision_tower.vision_tower.encoder.layer.25.intermediate.dense.weight": "model-00002-of-00002.safetensors",
652
+ "model.vision_tower.vision_tower.encoder.layer.25.layernorm_after.bias": "model-00002-of-00002.safetensors",
653
+ "model.vision_tower.vision_tower.encoder.layer.25.layernorm_after.weight": "model-00002-of-00002.safetensors",
654
+ "model.vision_tower.vision_tower.encoder.layer.25.layernorm_before.bias": "model-00002-of-00002.safetensors",
655
+ "model.vision_tower.vision_tower.encoder.layer.25.layernorm_before.weight": "model-00002-of-00002.safetensors",
656
+ "model.vision_tower.vision_tower.encoder.layer.25.output.dense.bias": "model-00002-of-00002.safetensors",
657
+ "model.vision_tower.vision_tower.encoder.layer.25.output.dense.weight": "model-00002-of-00002.safetensors",
658
+ "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.key.bias": "model-00001-of-00002.safetensors",
659
+ "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.key.weight": "model-00001-of-00002.safetensors",
660
+ "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.query.bias": "model-00001-of-00002.safetensors",
661
+ "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.query.weight": "model-00001-of-00002.safetensors",
662
+ "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.value.bias": "model-00001-of-00002.safetensors",
663
+ "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.value.weight": "model-00001-of-00002.safetensors",
664
+ "model.vision_tower.vision_tower.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00002.safetensors",
665
+ "model.vision_tower.vision_tower.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00002.safetensors",
666
+ "model.vision_tower.vision_tower.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00002.safetensors",
667
+ "model.vision_tower.vision_tower.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00002.safetensors",
668
+ "model.vision_tower.vision_tower.encoder.layer.3.layernorm_after.bias": "model-00001-of-00002.safetensors",
669
+ "model.vision_tower.vision_tower.encoder.layer.3.layernorm_after.weight": "model-00001-of-00002.safetensors",
670
+ "model.vision_tower.vision_tower.encoder.layer.3.layernorm_before.bias": "model-00001-of-00002.safetensors",
671
+ "model.vision_tower.vision_tower.encoder.layer.3.layernorm_before.weight": "model-00001-of-00002.safetensors",
672
+ "model.vision_tower.vision_tower.encoder.layer.3.output.dense.bias": "model-00001-of-00002.safetensors",
673
+ "model.vision_tower.vision_tower.encoder.layer.3.output.dense.weight": "model-00001-of-00002.safetensors",
674
+ "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.key.bias": "model-00001-of-00002.safetensors",
675
+ "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.key.weight": "model-00001-of-00002.safetensors",
676
+ "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.query.bias": "model-00001-of-00002.safetensors",
677
+ "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.query.weight": "model-00001-of-00002.safetensors",
678
+ "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.value.bias": "model-00001-of-00002.safetensors",
679
+ "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.value.weight": "model-00001-of-00002.safetensors",
680
+ "model.vision_tower.vision_tower.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00002.safetensors",
681
+ "model.vision_tower.vision_tower.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00002.safetensors",
682
+ "model.vision_tower.vision_tower.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00002.safetensors",
683
+ "model.vision_tower.vision_tower.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00002.safetensors",
684
+ "model.vision_tower.vision_tower.encoder.layer.4.layernorm_after.bias": "model-00001-of-00002.safetensors",
685
+ "model.vision_tower.vision_tower.encoder.layer.4.layernorm_after.weight": "model-00001-of-00002.safetensors",
686
+ "model.vision_tower.vision_tower.encoder.layer.4.layernorm_before.bias": "model-00001-of-00002.safetensors",
687
+ "model.vision_tower.vision_tower.encoder.layer.4.layernorm_before.weight": "model-00001-of-00002.safetensors",
688
+ "model.vision_tower.vision_tower.encoder.layer.4.output.dense.bias": "model-00001-of-00002.safetensors",
689
+ "model.vision_tower.vision_tower.encoder.layer.4.output.dense.weight": "model-00001-of-00002.safetensors",
690
+ "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.key.bias": "model-00001-of-00002.safetensors",
691
+ "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.key.weight": "model-00001-of-00002.safetensors",
692
+ "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.query.bias": "model-00001-of-00002.safetensors",
693
+ "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.query.weight": "model-00001-of-00002.safetensors",
694
+ "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.value.bias": "model-00001-of-00002.safetensors",
695
+ "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.value.weight": "model-00001-of-00002.safetensors",
696
+ "model.vision_tower.vision_tower.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00002.safetensors",
697
+ "model.vision_tower.vision_tower.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00002.safetensors",
698
+ "model.vision_tower.vision_tower.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00002.safetensors",
699
+ "model.vision_tower.vision_tower.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00002.safetensors",
700
+ "model.vision_tower.vision_tower.encoder.layer.5.layernorm_after.bias": "model-00001-of-00002.safetensors",
701
+ "model.vision_tower.vision_tower.encoder.layer.5.layernorm_after.weight": "model-00001-of-00002.safetensors",
702
+ "model.vision_tower.vision_tower.encoder.layer.5.layernorm_before.bias": "model-00001-of-00002.safetensors",
703
+ "model.vision_tower.vision_tower.encoder.layer.5.layernorm_before.weight": "model-00001-of-00002.safetensors",
704
+ "model.vision_tower.vision_tower.encoder.layer.5.output.dense.bias": "model-00001-of-00002.safetensors",
705
+ "model.vision_tower.vision_tower.encoder.layer.5.output.dense.weight": "model-00001-of-00002.safetensors",
706
+ "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.key.bias": "model-00001-of-00002.safetensors",
707
+ "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.key.weight": "model-00001-of-00002.safetensors",
708
+ "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.query.bias": "model-00001-of-00002.safetensors",
709
+ "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.query.weight": "model-00001-of-00002.safetensors",
710
+ "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.value.bias": "model-00001-of-00002.safetensors",
711
+ "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.value.weight": "model-00001-of-00002.safetensors",
712
+ "model.vision_tower.vision_tower.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00002.safetensors",
713
+ "model.vision_tower.vision_tower.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00002.safetensors",
714
+ "model.vision_tower.vision_tower.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00002.safetensors",
715
+ "model.vision_tower.vision_tower.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00002.safetensors",
716
+ "model.vision_tower.vision_tower.encoder.layer.6.layernorm_after.bias": "model-00001-of-00002.safetensors",
717
+ "model.vision_tower.vision_tower.encoder.layer.6.layernorm_after.weight": "model-00001-of-00002.safetensors",
718
+ "model.vision_tower.vision_tower.encoder.layer.6.layernorm_before.bias": "model-00001-of-00002.safetensors",
719
+ "model.vision_tower.vision_tower.encoder.layer.6.layernorm_before.weight": "model-00001-of-00002.safetensors",
720
+ "model.vision_tower.vision_tower.encoder.layer.6.output.dense.bias": "model-00001-of-00002.safetensors",
721
+ "model.vision_tower.vision_tower.encoder.layer.6.output.dense.weight": "model-00001-of-00002.safetensors",
722
+ "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.key.bias": "model-00001-of-00002.safetensors",
723
+ "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.key.weight": "model-00001-of-00002.safetensors",
724
+ "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.query.bias": "model-00001-of-00002.safetensors",
725
+ "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.query.weight": "model-00001-of-00002.safetensors",
726
+ "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.value.bias": "model-00001-of-00002.safetensors",
727
+ "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.value.weight": "model-00001-of-00002.safetensors",
728
+ "model.vision_tower.vision_tower.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00002.safetensors",
729
+ "model.vision_tower.vision_tower.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00002.safetensors",
730
+ "model.vision_tower.vision_tower.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00002.safetensors",
731
+ "model.vision_tower.vision_tower.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00002.safetensors",
732
+ "model.vision_tower.vision_tower.encoder.layer.7.layernorm_after.bias": "model-00001-of-00002.safetensors",
733
+ "model.vision_tower.vision_tower.encoder.layer.7.layernorm_after.weight": "model-00001-of-00002.safetensors",
734
+ "model.vision_tower.vision_tower.encoder.layer.7.layernorm_before.bias": "model-00001-of-00002.safetensors",
735
+ "model.vision_tower.vision_tower.encoder.layer.7.layernorm_before.weight": "model-00001-of-00002.safetensors",
736
+ "model.vision_tower.vision_tower.encoder.layer.7.output.dense.bias": "model-00001-of-00002.safetensors",
737
+ "model.vision_tower.vision_tower.encoder.layer.7.output.dense.weight": "model-00001-of-00002.safetensors",
738
+ "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.key.bias": "model-00001-of-00002.safetensors",
739
+ "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.key.weight": "model-00001-of-00002.safetensors",
740
+ "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.query.bias": "model-00001-of-00002.safetensors",
741
+ "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.query.weight": "model-00001-of-00002.safetensors",
742
+ "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.value.bias": "model-00001-of-00002.safetensors",
743
+ "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.value.weight": "model-00001-of-00002.safetensors",
744
+ "model.vision_tower.vision_tower.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00002.safetensors",
745
+ "model.vision_tower.vision_tower.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00002.safetensors",
746
+ "model.vision_tower.vision_tower.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00002.safetensors",
747
+ "model.vision_tower.vision_tower.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00002.safetensors",
748
+ "model.vision_tower.vision_tower.encoder.layer.8.layernorm_after.bias": "model-00002-of-00002.safetensors",
749
+ "model.vision_tower.vision_tower.encoder.layer.8.layernorm_after.weight": "model-00002-of-00002.safetensors",
750
+ "model.vision_tower.vision_tower.encoder.layer.8.layernorm_before.bias": "model-00002-of-00002.safetensors",
751
+ "model.vision_tower.vision_tower.encoder.layer.8.layernorm_before.weight": "model-00002-of-00002.safetensors",
752
+ "model.vision_tower.vision_tower.encoder.layer.8.output.dense.bias": "model-00002-of-00002.safetensors",
753
+ "model.vision_tower.vision_tower.encoder.layer.8.output.dense.weight": "model-00002-of-00002.safetensors",
754
+ "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.key.bias": "model-00002-of-00002.safetensors",
755
+ "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.key.weight": "model-00002-of-00002.safetensors",
756
+ "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.query.bias": "model-00002-of-00002.safetensors",
757
+ "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.query.weight": "model-00002-of-00002.safetensors",
758
+ "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.value.bias": "model-00002-of-00002.safetensors",
759
+ "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.value.weight": "model-00002-of-00002.safetensors",
760
+ "model.vision_tower.vision_tower.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00002.safetensors",
761
+ "model.vision_tower.vision_tower.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00002.safetensors",
762
+ "model.vision_tower.vision_tower.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00002.safetensors",
763
+ "model.vision_tower.vision_tower.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00002.safetensors",
764
+ "model.vision_tower.vision_tower.encoder.layer.9.layernorm_after.bias": "model-00002-of-00002.safetensors",
765
+ "model.vision_tower.vision_tower.encoder.layer.9.layernorm_after.weight": "model-00002-of-00002.safetensors",
766
+ "model.vision_tower.vision_tower.encoder.layer.9.layernorm_before.bias": "model-00002-of-00002.safetensors",
767
+ "model.vision_tower.vision_tower.encoder.layer.9.layernorm_before.weight": "model-00002-of-00002.safetensors",
768
+ "model.vision_tower.vision_tower.encoder.layer.9.output.dense.bias": "model-00002-of-00002.safetensors",
769
+ "model.vision_tower.vision_tower.encoder.layer.9.output.dense.weight": "model-00002-of-00002.safetensors",
770
+ "model.vision_tower.vision_tower.layernorm.bias": "model-00002-of-00002.safetensors",
771
+ "model.vision_tower.vision_tower.layernorm.weight": "model-00002-of-00002.safetensors",
772
+ "model.vision_tower.vision_tower.pooler.dense.bias": "model-00002-of-00002.safetensors",
773
+ "model.vision_tower.vision_tower.pooler.dense.weight": "model-00002-of-00002.safetensors"
774
+ }
775
+ }
continuous/qwen25/webssl_mae3b_full2b_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/webssl_mae3b_full2b_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/webssl_mae3b_full2b_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/webssl_mae3b_full2b_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": 14.740432739257812,
15
+ "learning_rate": 1.153846153846154e-06,
16
+ "loss": 2.0018,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.007700452401578592,
21
+ "grad_norm": 7.5593342781066895,
22
+ "learning_rate": 2.435897435897436e-06,
23
+ "loss": 1.6632,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.01155067860236789,
28
+ "grad_norm": 3.710819959640503,
29
+ "learning_rate": 3.7179487179487184e-06,
30
+ "loss": 1.2096,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.015400904803157185,
35
+ "grad_norm": 0.6263419389724731,
36
+ "learning_rate": 5e-06,
37
+ "loss": 0.9826,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.019251131003946483,
42
+ "grad_norm": 0.3889085650444031,
43
+ "learning_rate": 6.282051282051282e-06,
44
+ "loss": 0.9406,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.02310135720473578,
49
+ "grad_norm": 0.28540635108947754,
50
+ "learning_rate": 7.564102564102564e-06,
51
+ "loss": 0.8946,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.026951583405525073,
56
+ "grad_norm": 0.22711798548698425,
57
+ "learning_rate": 8.846153846153847e-06,
58
+ "loss": 0.8668,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.03080180960631437,
63
+ "grad_norm": 0.2380182445049286,
64
+ "learning_rate": 9.999996111488723e-06,
65
+ "loss": 0.8742,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.034652035807103666,
70
+ "grad_norm": 0.21203289926052094,
71
+ "learning_rate": 9.999529497453782e-06,
72
+ "loss": 0.8537,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.038502262007892966,
77
+ "grad_norm": 0.21856829524040222,
78
+ "learning_rate": 9.998285264324193e-06,
79
+ "loss": 0.8344,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.04235248820868226,
84
+ "grad_norm": 0.2122943252325058,
85
+ "learning_rate": 9.996263605626052e-06,
86
+ "loss": 0.8231,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.04620271440947156,
91
+ "grad_norm": 0.2231542468070984,
92
+ "learning_rate": 9.99346483580503e-06,
93
+ "loss": 0.8355,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.05005294061026085,
98
+ "grad_norm": 0.20169459283351898,
99
+ "learning_rate": 9.989889390177467e-06,
100
+ "loss": 0.8272,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.053903166811050146,
105
+ "grad_norm": 0.2308754175901413,
106
+ "learning_rate": 9.985537824862647e-06,
107
+ "loss": 0.8267,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.057753393011839446,
112
+ "grad_norm": 0.23377133905887604,
113
+ "learning_rate": 9.980410816696317e-06,
114
+ "loss": 0.8103,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.06160361921262874,
119
+ "grad_norm": 0.21733610332012177,
120
+ "learning_rate": 9.97450916312541e-06,
121
+ "loss": 0.8172,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.06545384541341803,
126
+ "grad_norm": 0.19193190336227417,
127
+ "learning_rate": 9.967833782084004e-06,
128
+ "loss": 0.818,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.06930407161420733,
133
+ "grad_norm": 0.22831909358501434,
134
+ "learning_rate": 9.960385711850554e-06,
135
+ "loss": 0.8456,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.07315429781499663,
140
+ "grad_norm": 0.22033141553401947,
141
+ "learning_rate": 9.952166110886394e-06,
142
+ "loss": 0.8352,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.07700452401578593,
147
+ "grad_norm": 0.24567261338233948,
148
+ "learning_rate": 9.943176257655567e-06,
149
+ "loss": 0.8296,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.08085475021657522,
154
+ "grad_norm": 0.21381895244121552,
155
+ "learning_rate": 9.933417550425952e-06,
156
+ "loss": 0.819,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.08470497641736452,
161
+ "grad_norm": 0.2189001739025116,
162
+ "learning_rate": 9.9228915070518e-06,
163
+ "loss": 0.8087,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.08855520261815382,
168
+ "grad_norm": 0.21770042181015015,
169
+ "learning_rate": 9.911599764737632e-06,
170
+ "loss": 0.8115,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.09240542881894312,
175
+ "grad_norm": 0.23099291324615479,
176
+ "learning_rate": 9.899544079783606e-06,
177
+ "loss": 0.8048,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.0962556550197324,
182
+ "grad_norm": 0.2200271636247635,
183
+ "learning_rate": 9.886726327312338e-06,
184
+ "loss": 0.8198,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.1001058812205217,
189
+ "grad_norm": 0.21309828758239746,
190
+ "learning_rate": 9.87314850097724e-06,
191
+ "loss": 0.8195,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.103956107421311,
196
+ "grad_norm": 0.20982636511325836,
197
+ "learning_rate": 9.858812712652452e-06,
198
+ "loss": 0.8068,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.10780633362210029,
203
+ "grad_norm": 0.20000089704990387,
204
+ "learning_rate": 9.843721192104341e-06,
205
+ "loss": 0.8083,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.11165655982288959,
210
+ "grad_norm": 0.21890954673290253,
211
+ "learning_rate": 9.827876286644698e-06,
212
+ "loss": 0.828,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.11550678602367889,
217
+ "grad_norm": 0.19791266322135925,
218
+ "learning_rate": 9.811280460765643e-06,
219
+ "loss": 0.7875,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.11935701222446819,
224
+ "grad_norm": 0.2149326503276825,
225
+ "learning_rate": 9.793936295756292e-06,
226
+ "loss": 0.7984,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.12320723842525748,
231
+ "grad_norm": 0.22006359696388245,
232
+ "learning_rate": 9.775846489301279e-06,
233
+ "loss": 0.8018,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.12705746462604678,
238
+ "grad_norm": 0.22024904191493988,
239
+ "learning_rate": 9.757013855061157e-06,
240
+ "loss": 0.8006,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.13090769082683607,
245
+ "grad_norm": 0.2165515124797821,
246
+ "learning_rate": 9.737441322234758e-06,
247
+ "loss": 0.8136,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.13475791702762538,
252
+ "grad_norm": 0.2206028699874878,
253
+ "learning_rate": 9.717131935103605e-06,
254
+ "loss": 0.8118,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.13860814322841467,
259
+ "grad_norm": 0.21436938643455505,
260
+ "learning_rate": 9.696088852558398e-06,
261
+ "loss": 0.7983,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.14245836942920398,
266
+ "grad_norm": 0.21059143543243408,
267
+ "learning_rate": 9.674315347607686e-06,
268
+ "loss": 0.8233,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.14630859562999327,
273
+ "grad_norm": 0.21528297662734985,
274
+ "learning_rate": 9.651814806868796e-06,
275
+ "loss": 0.7886,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.15015882183078255,
280
+ "grad_norm": 0.22042393684387207,
281
+ "learning_rate": 9.62859073004107e-06,
282
+ "loss": 0.7936,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.15400904803157187,
287
+ "grad_norm": 0.19345125555992126,
288
+ "learning_rate": 9.604646729361547e-06,
289
+ "loss": 0.8006,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.15785927423236115,
294
+ "grad_norm": 0.2058127075433731,
295
+ "learning_rate": 9.579986529043099e-06,
296
+ "loss": 0.7924,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.16170950043315044,
301
+ "grad_norm": 0.2160652130842209,
302
+ "learning_rate": 9.554613964695189e-06,
303
+ "loss": 0.8044,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.16555972663393975,
308
+ "grad_norm": 0.21569734811782837,
309
+ "learning_rate": 9.528532982727281e-06,
310
+ "loss": 0.7951,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.16940995283472904,
315
+ "grad_norm": 0.2004237323999405,
316
+ "learning_rate": 9.501747639735018e-06,
317
+ "loss": 0.7946,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.17326017903551832,
322
+ "grad_norm": 0.21148496866226196,
323
+ "learning_rate": 9.474262101869272e-06,
324
+ "loss": 0.7827,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.17711040523630764,
329
+ "grad_norm": 0.21656860411167145,
330
+ "learning_rate": 9.446080644188141e-06,
331
+ "loss": 0.7878,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.18096063143709692,
336
+ "grad_norm": 0.20531369745731354,
337
+ "learning_rate": 9.417207649992017e-06,
338
+ "loss": 0.7964,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.18481085763788624,
343
+ "grad_norm": 0.2129681259393692,
344
+ "learning_rate": 9.387647610141816e-06,
345
+ "loss": 0.7959,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.18866108383867553,
350
+ "grad_norm": 0.19442333281040192,
351
+ "learning_rate": 9.35740512236047e-06,
352
+ "loss": 0.7812,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.1925113100394648,
357
+ "grad_norm": 0.19342488050460815,
358
+ "learning_rate": 9.326484890517809e-06,
359
+ "loss": 0.7901,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.19636153624025413,
364
+ "grad_norm": 0.21883556246757507,
365
+ "learning_rate": 9.294891723898926e-06,
366
+ "loss": 0.7819,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.2002117624410434,
371
+ "grad_norm": 0.22579477727413177,
372
+ "learning_rate": 9.262630536456153e-06,
373
+ "loss": 0.8109,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.2040619886418327,
378
+ "grad_norm": 0.22520811855793,
379
+ "learning_rate": 9.229706346044749e-06,
380
+ "loss": 0.7863,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.207912214842622,
385
+ "grad_norm": 0.22569149732589722,
386
+ "learning_rate": 9.196124273642422e-06,
387
+ "loss": 0.7969,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.2117624410434113,
392
+ "grad_norm": 0.21038641035556793,
393
+ "learning_rate": 9.161889542552842e-06,
394
+ "loss": 0.799,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.21561266724420058,
399
+ "grad_norm": 0.2024410516023636,
400
+ "learning_rate": 9.127007477593193e-06,
401
+ "loss": 0.8038,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.2194628934449899,
406
+ "grad_norm": 0.2258559614419937,
407
+ "learning_rate": 9.091483504265974e-06,
408
+ "loss": 0.815,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.22331311964577918,
413
+ "grad_norm": 0.21699675917625427,
414
+ "learning_rate": 9.055323147915116e-06,
415
+ "loss": 0.7918,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.2271633458465685,
420
+ "grad_norm": 0.21330538392066956,
421
+ "learning_rate": 9.018532032866585e-06,
422
+ "loss": 0.8036,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.23101357204735778,
427
+ "grad_norm": 0.212269589304924,
428
+ "learning_rate": 8.981115881553579e-06,
429
+ "loss": 0.7952,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.23486379824814707,
434
+ "grad_norm": 0.22286619246006012,
435
+ "learning_rate": 8.943080513626476e-06,
436
+ "loss": 0.815,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.23871402444893638,
441
+ "grad_norm": 0.20794133841991425,
442
+ "learning_rate": 8.904431845047641e-06,
443
+ "loss": 0.7988,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.24256425064972567,
448
+ "grad_norm": 0.223821222782135,
449
+ "learning_rate": 8.86517588717128e-06,
450
+ "loss": 0.8154,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.24641447685051496,
455
+ "grad_norm": 0.20798133313655853,
456
+ "learning_rate": 8.82531874580844e-06,
457
+ "loss": 0.8041,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.25026470305130427,
462
+ "grad_norm": 0.1938098520040512,
463
+ "learning_rate": 8.784866620277314e-06,
464
+ "loss": 0.7621,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.25411492925209356,
469
+ "grad_norm": 0.22643618285655975,
470
+ "learning_rate": 8.743825802439018e-06,
471
+ "loss": 0.7984,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.25796515545288284,
476
+ "grad_norm": 0.226744145154953,
477
+ "learning_rate": 8.702202675718956e-06,
478
+ "loss": 0.8031,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.26181538165367213,
483
+ "grad_norm": 0.20160621404647827,
484
+ "learning_rate": 8.660003714113959e-06,
485
+ "loss": 0.7741,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.26566560785446147,
490
+ "grad_norm": 0.21288016438484192,
491
+ "learning_rate": 8.617235481185323e-06,
492
+ "loss": 0.7978,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.26951583405525076,
497
+ "grad_norm": 0.2147081345319748,
498
+ "learning_rate": 8.573904629037931e-06,
499
+ "loss": 0.8016,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.27336606025604004,
504
+ "grad_norm": 0.20993798971176147,
505
+ "learning_rate": 8.530017897285585e-06,
506
+ "loss": 0.783,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.27721628645682933,
511
+ "grad_norm": 0.19782884418964386,
512
+ "learning_rate": 8.485582112002746e-06,
513
+ "loss": 0.7878,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.2810665126576186,
518
+ "grad_norm": 0.21022723615169525,
519
+ "learning_rate": 8.440604184662811e-06,
520
+ "loss": 0.7925,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.28491673885840796,
525
+ "grad_norm": 0.21525394916534424,
526
+ "learning_rate": 8.395091111063118e-06,
527
+ "loss": 0.7828,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.28876696505919724,
532
+ "grad_norm": 0.19822882115840912,
533
+ "learning_rate": 8.349049970236822e-06,
534
+ "loss": 0.7811,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.29261719125998653,
539
+ "grad_norm": 0.20763720571994781,
540
+ "learning_rate": 8.302487923351842e-06,
541
+ "loss": 0.774,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.2964674174607758,
546
+ "grad_norm": 0.20552876591682434,
547
+ "learning_rate": 8.255412212597021e-06,
548
+ "loss": 0.7909,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.3003176436615651,
553
+ "grad_norm": 0.1976495087146759,
554
+ "learning_rate": 8.207830160055688e-06,
555
+ "loss": 0.7869,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.3041678698623544,
560
+ "grad_norm": 0.21309000253677368,
561
+ "learning_rate": 8.159749166566786e-06,
562
+ "loss": 0.7744,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.30801809606314373,
567
+ "grad_norm": 0.20668265223503113,
568
+ "learning_rate": 8.11117671057377e-06,
569
+ "loss": 0.8013,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.311868322263933,
574
+ "grad_norm": 0.2201952487230301,
575
+ "learning_rate": 8.062120346961404e-06,
576
+ "loss": 0.7938,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.3157185484647223,
581
+ "grad_norm": 0.20316627621650696,
582
+ "learning_rate": 8.012587705880705e-06,
583
+ "loss": 0.7888,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.3195687746655116,
588
+ "grad_norm": 0.20644305646419525,
589
+ "learning_rate": 7.962586491562146e-06,
590
+ "loss": 0.7736,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.3234190008663009,
595
+ "grad_norm": 0.2256862074136734,
596
+ "learning_rate": 7.912124481117357e-06,
597
+ "loss": 0.7784,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.3272692270670902,
602
+ "grad_norm": 0.20445044338703156,
603
+ "learning_rate": 7.861209523329494e-06,
604
+ "loss": 0.7883,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.3311194532678795,
609
+ "grad_norm": 0.21300341188907623,
610
+ "learning_rate": 7.809849537432432e-06,
611
+ "loss": 0.7754,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.3349696794686688,
616
+ "grad_norm": 0.20653606951236725,
617
+ "learning_rate": 7.758052511879035e-06,
618
+ "loss": 0.7835,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.3388199056694581,
623
+ "grad_norm": 0.2003398835659027,
624
+ "learning_rate": 7.705826503098642e-06,
625
+ "loss": 0.7788,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.34267013187024736,
630
+ "grad_norm": 0.20268110930919647,
631
+ "learning_rate": 7.653179634243979e-06,
632
+ "loss": 0.7781,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.34652035807103665,
637
+ "grad_norm": 0.1914311796426773,
638
+ "learning_rate": 7.600120093927696e-06,
639
+ "loss": 0.7842,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.350370584271826,
644
+ "grad_norm": 0.2198861837387085,
645
+ "learning_rate": 7.546656134948729e-06,
646
+ "loss": 0.7696,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.3542208104726153,
651
+ "grad_norm": 0.2170405387878418,
652
+ "learning_rate": 7.492796073008661e-06,
653
+ "loss": 0.7699,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.35807103667340456,
658
+ "grad_norm": 0.223048597574234,
659
+ "learning_rate": 7.438548285418326e-06,
660
+ "loss": 0.7591,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.36192126287419385,
665
+ "grad_norm": 0.2335508167743683,
666
+ "learning_rate": 7.3839212097948e-06,
667
+ "loss": 0.7913,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.36577148907498314,
672
+ "grad_norm": 0.21385671198368073,
673
+ "learning_rate": 7.328923342749039e-06,
674
+ "loss": 0.8054,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.3696217152757725,
679
+ "grad_norm": 0.2216998189687729,
680
+ "learning_rate": 7.273563238564319e-06,
681
+ "loss": 0.7913,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.37347194147656176,
686
+ "grad_norm": 0.2124149352312088,
687
+ "learning_rate": 7.217849507865724e-06,
688
+ "loss": 0.7724,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.37732216767735105,
693
+ "grad_norm": 0.2089921087026596,
694
+ "learning_rate": 7.161790816280858e-06,
695
+ "loss": 0.7766,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.38117239387814034,
700
+ "grad_norm": 0.22030803561210632,
701
+ "learning_rate": 7.1053958830920125e-06,
702
+ "loss": 0.7629,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.3850226200789296,
707
+ "grad_norm": 0.2092115581035614,
708
+ "learning_rate": 7.0486734798799715e-06,
709
+ "loss": 0.7762,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.3888728462797189,
714
+ "grad_norm": 0.20596954226493835,
715
+ "learning_rate": 6.991632429159708e-06,
716
+ "loss": 0.8007,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.39272307248050825,
721
+ "grad_norm": 0.22748009860515594,
722
+ "learning_rate": 6.934281603008132e-06,
723
+ "loss": 0.7943,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.39657329868129754,
728
+ "grad_norm": 0.20389117300510406,
729
+ "learning_rate": 6.876629921684143e-06,
730
+ "loss": 0.7911,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.4004235248820868,
735
+ "grad_norm": 0.21205660700798035,
736
+ "learning_rate": 6.818686352241199e-06,
737
+ "loss": 0.7815,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.4042737510828761,
742
+ "grad_norm": 0.19480517506599426,
743
+ "learning_rate": 6.760459907132573e-06,
744
+ "loss": 0.7795,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.4081239772836654,
749
+ "grad_norm": 0.19423940777778625,
750
+ "learning_rate": 6.701959642809589e-06,
751
+ "loss": 0.7851,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.41197420348445474,
756
+ "grad_norm": 0.21241061389446259,
757
+ "learning_rate": 6.643194658312987e-06,
758
+ "loss": 0.7746,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.415824429685244,
763
+ "grad_norm": 0.20408867299556732,
764
+ "learning_rate": 6.584174093857676e-06,
765
+ "loss": 0.7996,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.4196746558860333,
770
+ "grad_norm": 0.2339077591896057,
771
+ "learning_rate": 6.5249071294110735e-06,
772
+ "loss": 0.7816,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.4235248820868226,
777
+ "grad_norm": 0.21220777928829193,
778
+ "learning_rate": 6.465402983265274e-06,
779
+ "loss": 0.796,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.4273751082876119,
784
+ "grad_norm": 0.21588359773159027,
785
+ "learning_rate": 6.405670910603243e-06,
786
+ "loss": 0.7928,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.43122533448840117,
791
+ "grad_norm": 0.22561486065387726,
792
+ "learning_rate": 6.345720202059291e-06,
793
+ "loss": 0.7881,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.4350755606891905,
798
+ "grad_norm": 0.20983414351940155,
799
+ "learning_rate": 6.285560182274008e-06,
800
+ "loss": 0.7657,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.4389257868899798,
805
+ "grad_norm": 0.20635223388671875,
806
+ "learning_rate": 6.225200208443936e-06,
807
+ "loss": 0.7866,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.4427760130907691,
812
+ "grad_norm": 0.21180471777915955,
813
+ "learning_rate": 6.16464966886616e-06,
814
+ "loss": 0.7795,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.44662623929155837,
819
+ "grad_norm": 0.2414553165435791,
820
+ "learning_rate": 6.103917981478065e-06,
821
+ "loss": 0.8018,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.45047646549234766,
826
+ "grad_norm": 0.20977549254894257,
827
+ "learning_rate": 6.043014592392489e-06,
828
+ "loss": 0.814,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.454326691693137,
833
+ "grad_norm": 0.19705963134765625,
834
+ "learning_rate": 5.981948974428485e-06,
835
+ "loss": 0.7861,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.4581769178939263,
840
+ "grad_norm": 0.21779416501522064,
841
+ "learning_rate": 5.920730625637934e-06,
842
+ "loss": 0.7676,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.46202714409471557,
847
+ "grad_norm": 0.218234121799469,
848
+ "learning_rate": 5.8593690678282355e-06,
849
+ "loss": 0.778,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.46587737029550486,
854
+ "grad_norm": 0.2173709273338318,
855
+ "learning_rate": 5.797873845081301e-06,
856
+ "loss": 0.7802,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.46972759649629414,
861
+ "grad_norm": 0.21555374562740326,
862
+ "learning_rate": 5.736254522269075e-06,
863
+ "loss": 0.7975,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.47357782269708343,
868
+ "grad_norm": 0.20465444028377533,
869
+ "learning_rate": 5.6745206835658386e-06,
870
+ "loss": 0.8002,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.47742804889787277,
875
+ "grad_norm": 0.20293821394443512,
876
+ "learning_rate": 5.612681930957495e-06,
877
+ "loss": 0.7693,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.48127827509866206,
882
+ "grad_norm": 0.20461735129356384,
883
+ "learning_rate": 5.550747882748095e-06,
884
+ "loss": 0.7683,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.48512850129945134,
889
+ "grad_norm": 0.22078260779380798,
890
+ "learning_rate": 5.4887281720638195e-06,
891
+ "loss": 0.7757,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.48897872750024063,
896
+ "grad_norm": 0.23799549043178558,
897
+ "learning_rate": 5.42663244535466e-06,
898
+ "loss": 0.7613,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.4928289537010299,
903
+ "grad_norm": 0.22281384468078613,
904
+ "learning_rate": 5.3644703608940205e-06,
905
+ "loss": 0.7683,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.49667917990181926,
910
+ "grad_norm": 0.21330107748508453,
911
+ "learning_rate": 5.302251587276491e-06,
912
+ "loss": 0.7796,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.5005294061026085,
917
+ "grad_norm": 0.2029404640197754,
918
+ "learning_rate": 5.2399858019140005e-06,
919
+ "loss": 0.7813,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.5043796323033978,
924
+ "grad_norm": 0.20473673939704895,
925
+ "learning_rate": 5.177682689530615e-06,
926
+ "loss": 0.7916,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.5082298585041871,
931
+ "grad_norm": 0.2164319008588791,
932
+ "learning_rate": 5.11535194065619e-06,
933
+ "loss": 0.7645,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.5120800847049765,
938
+ "grad_norm": 0.23752082884311676,
939
+ "learning_rate": 5.053003250119113e-06,
940
+ "loss": 0.774,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.5159303109057657,
945
+ "grad_norm": 0.21805062890052795,
946
+ "learning_rate": 4.9906463155383925e-06,
947
+ "loss": 0.7783,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.519780537106555,
952
+ "grad_norm": 0.2122947871685028,
953
+ "learning_rate": 4.9282908358153046e-06,
954
+ "loss": 0.7702,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.5236307633073443,
959
+ "grad_norm": 0.24198898673057556,
960
+ "learning_rate": 4.8659465096248345e-06,
961
+ "loss": 0.7903,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.5274809895081336,
966
+ "grad_norm": 0.2186824381351471,
967
+ "learning_rate": 4.803623033907169e-06,
968
+ "loss": 0.7887,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.5313312157089229,
973
+ "grad_norm": 0.20149856805801392,
974
+ "learning_rate": 4.741330102359441e-06,
975
+ "loss": 0.7938,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.5351814419097122,
980
+ "grad_norm": 0.22498708963394165,
981
+ "learning_rate": 4.679077403927996e-06,
982
+ "loss": 0.774,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.5390316681105015,
987
+ "grad_norm": 0.2108890563249588,
988
+ "learning_rate": 4.616874621301373e-06,
989
+ "loss": 0.7735,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.5428818943112907,
994
+ "grad_norm": 0.21827872097492218,
995
+ "learning_rate": 4.554731429404293e-06,
996
+ "loss": 0.787,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.5467321205120801,
1001
+ "grad_norm": 0.2239445298910141,
1002
+ "learning_rate": 4.492657493892822e-06,
1003
+ "loss": 0.7741,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.5505823467128694,
1008
+ "grad_norm": 0.22541218996047974,
1009
+ "learning_rate": 4.430662469650999e-06,
1010
+ "loss": 0.7891,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.5544325729136587,
1015
+ "grad_norm": 0.22202137112617493,
1016
+ "learning_rate": 4.368755999289118e-06,
1017
+ "loss": 0.7919,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.558282799114448,
1022
+ "grad_norm": 0.22219301760196686,
1023
+ "learning_rate": 4.306947711643949e-06,
1024
+ "loss": 0.774,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.5621330253152372,
1029
+ "grad_norm": 0.21781539916992188,
1030
+ "learning_rate": 4.245247220281068e-06,
1031
+ "loss": 0.7784,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.5659832515160266,
1036
+ "grad_norm": 0.20739150047302246,
1037
+ "learning_rate": 4.183664121999587e-06,
1038
+ "loss": 0.7759,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.5698334777168159,
1043
+ "grad_norm": 0.21361471712589264,
1044
+ "learning_rate": 4.122207995339474e-06,
1045
+ "loss": 0.7711,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.5736837039176051,
1050
+ "grad_norm": 0.20360085368156433,
1051
+ "learning_rate": 4.060888399091734e-06,
1052
+ "loss": 0.7782,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.5775339301183945,
1057
+ "grad_norm": 0.20177637040615082,
1058
+ "learning_rate": 3.999714870811639e-06,
1059
+ "loss": 0.7865,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.5813841563191837,
1064
+ "grad_norm": 0.21254485845565796,
1065
+ "learning_rate": 3.938696925335275e-06,
1066
+ "loss": 0.7803,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.5852343825199731,
1071
+ "grad_norm": 0.2065831869840622,
1072
+ "learning_rate": 3.87784405329962e-06,
1073
+ "loss": 0.7886,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.5890846087207623,
1078
+ "grad_norm": 0.20945949852466583,
1079
+ "learning_rate": 3.817165719666382e-06,
1080
+ "loss": 0.7907,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.5929348349215516,
1085
+ "grad_norm": 0.20793063938617706,
1086
+ "learning_rate": 3.756671362249841e-06,
1087
+ "loss": 0.7943,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.596785061122341,
1092
+ "grad_norm": 0.2080674171447754,
1093
+ "learning_rate": 3.6963703902488907e-06,
1094
+ "loss": 0.7814,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.6006352873231302,
1099
+ "grad_norm": 0.21349214017391205,
1100
+ "learning_rate": 3.6362721827835655e-06,
1101
+ "loss": 0.7979,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.6044855135239195,
1106
+ "grad_norm": 0.21987390518188477,
1107
+ "learning_rate": 3.576386087436212e-06,
1108
+ "loss": 0.7933,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.6083357397247088,
1113
+ "grad_norm": 0.22680547833442688,
1114
+ "learning_rate": 3.5167214187975913e-06,
1115
+ "loss": 0.7823,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.6121859659254981,
1120
+ "grad_norm": 0.19044801592826843,
1121
+ "learning_rate": 3.457287457018086e-06,
1122
+ "loss": 0.7837,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.6160361921262875,
1127
+ "grad_norm": 0.20380637049674988,
1128
+ "learning_rate": 3.3980934463643003e-06,
1129
+ "loss": 0.7725,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.6198864183270767,
1134
+ "grad_norm": 0.19651706516742706,
1135
+ "learning_rate": 3.3391485937812053e-06,
1136
+ "loss": 0.7538,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.623736644527866,
1141
+ "grad_norm": 0.20963917672634125,
1142
+ "learning_rate": 3.280462067460115e-06,
1143
+ "loss": 0.7538,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.6275868707286553,
1148
+ "grad_norm": 0.21058477461338043,
1149
+ "learning_rate": 3.222042995412669e-06,
1150
+ "loss": 0.7854,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.6314370969294446,
1155
+ "grad_norm": 0.1908433735370636,
1156
+ "learning_rate": 3.163900464051089e-06,
1157
+ "loss": 0.7741,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.635287323130234,
1162
+ "grad_norm": 0.2127835899591446,
1163
+ "learning_rate": 3.1060435167748826e-06,
1164
+ "loss": 0.7839,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.6391375493310232,
1169
+ "grad_norm": 0.20902498066425323,
1170
+ "learning_rate": 3.048481152564253e-06,
1171
+ "loss": 0.7639,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.6429877755318125,
1176
+ "grad_norm": 0.22223131358623505,
1177
+ "learning_rate": 2.9912223245804017e-06,
1178
+ "loss": 0.7833,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.6468380017326018,
1183
+ "grad_norm": 0.22115196287631989,
1184
+ "learning_rate": 2.934275938772981e-06,
1185
+ "loss": 0.7813,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.6506882279333911,
1190
+ "grad_norm": 0.2206103801727295,
1191
+ "learning_rate": 2.8776508524948676e-06,
1192
+ "loss": 0.77,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.6545384541341804,
1197
+ "grad_norm": 0.19261068105697632,
1198
+ "learning_rate": 2.821355873124503e-06,
1199
+ "loss": 0.7719,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.6583886803349697,
1204
+ "grad_norm": 0.2154761403799057,
1205
+ "learning_rate": 2.7653997566960144e-06,
1206
+ "loss": 0.7824,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.662238906535759,
1211
+ "grad_norm": 0.21660096943378448,
1212
+ "learning_rate": 2.709791206537309e-06,
1213
+ "loss": 0.772,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.6660891327365482,
1218
+ "grad_norm": 0.2148159146308899,
1219
+ "learning_rate": 2.6545388719163747e-06,
1220
+ "loss": 0.7792,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.6699393589373376,
1225
+ "grad_norm": 0.21491363644599915,
1226
+ "learning_rate": 2.599651346695979e-06,
1227
+ "loss": 0.7781,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.6737895851381268,
1232
+ "grad_norm": 0.20274674892425537,
1233
+ "learning_rate": 2.545137167997007e-06,
1234
+ "loss": 0.7759,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.6776398113389162,
1239
+ "grad_norm": 0.20303402841091156,
1240
+ "learning_rate": 2.4910048148705972e-06,
1241
+ "loss": 0.7651,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.6814900375397055,
1246
+ "grad_norm": 0.22246386110782623,
1247
+ "learning_rate": 2.4372627069793327e-06,
1248
+ "loss": 0.8068,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.6853402637404947,
1253
+ "grad_norm": 0.21829211711883545,
1254
+ "learning_rate": 2.3839192032876486e-06,
1255
+ "loss": 0.793,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.6891904899412841,
1260
+ "grad_norm": 0.20908202230930328,
1261
+ "learning_rate": 2.3309826007617047e-06,
1262
+ "loss": 0.8031,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.6930407161420733,
1267
+ "grad_norm": 0.2083471268415451,
1268
+ "learning_rate": 2.278461133078881e-06,
1269
+ "loss": 0.7666,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.6968909423428626,
1274
+ "grad_norm": 0.22239188849925995,
1275
+ "learning_rate": 2.2263629693471258e-06,
1276
+ "loss": 0.7593,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.700741168543652,
1281
+ "grad_norm": 0.2009306699037552,
1282
+ "learning_rate": 2.1746962128343414e-06,
1283
+ "loss": 0.7811,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.7045913947444412,
1288
+ "grad_norm": 0.2068733274936676,
1289
+ "learning_rate": 2.1234688997080183e-06,
1290
+ "loss": 0.7704,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.7084416209452306,
1295
+ "grad_norm": 0.22389362752437592,
1296
+ "learning_rate": 2.0726889977853053e-06,
1297
+ "loss": 0.7769,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.7122918471460198,
1302
+ "grad_norm": 0.22473621368408203,
1303
+ "learning_rate": 2.022364405293703e-06,
1304
+ "loss": 0.7865,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.7161420733468091,
1309
+ "grad_norm": 0.21032844483852386,
1310
+ "learning_rate": 1.9725029496425814e-06,
1311
+ "loss": 0.7815,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.7199922995475985,
1316
+ "grad_norm": 0.19500789046287537,
1317
+ "learning_rate": 1.923112386205727e-06,
1318
+ "loss": 0.7776,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.7238425257483877,
1323
+ "grad_norm": 0.20170867443084717,
1324
+ "learning_rate": 1.874200397115079e-06,
1325
+ "loss": 0.7852,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.727692751949177,
1330
+ "grad_norm": 0.22819548845291138,
1331
+ "learning_rate": 1.825774590065857e-06,
1332
+ "loss": 0.7683,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.7315429781499663,
1337
+ "grad_norm": 0.21575115621089935,
1338
+ "learning_rate": 1.7778424971332813e-06,
1339
+ "loss": 0.7779,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.7353932043507556,
1344
+ "grad_norm": 0.2013723999261856,
1345
+ "learning_rate": 1.7304115736010407e-06,
1346
+ "loss": 0.7768,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.739243430551545,
1351
+ "grad_norm": 0.21244390308856964,
1352
+ "learning_rate": 1.6834891968017108e-06,
1353
+ "loss": 0.7692,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.7430936567523342,
1358
+ "grad_norm": 0.2166135013103485,
1359
+ "learning_rate": 1.6370826649692884e-06,
1360
+ "loss": 0.7876,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.7469438829531235,
1365
+ "grad_norm": 0.2226439267396927,
1366
+ "learning_rate": 1.5911991961040463e-06,
1367
+ "loss": 0.7929,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.7507941091539128,
1372
+ "grad_norm": 0.2141723483800888,
1373
+ "learning_rate": 1.545845926849851e-06,
1374
+ "loss": 0.7784,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.7546443353547021,
1379
+ "grad_norm": 0.22685964405536652,
1380
+ "learning_rate": 1.5010299113841397e-06,
1381
+ "loss": 0.7984,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.7584945615554913,
1386
+ "grad_norm": 0.2094143033027649,
1387
+ "learning_rate": 1.4567581203207238e-06,
1388
+ "loss": 0.7851,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.7623447877562807,
1393
+ "grad_norm": 0.2234186828136444,
1394
+ "learning_rate": 1.413037439625593e-06,
1395
+ "loss": 0.7883,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.76619501395707,
1400
+ "grad_norm": 0.22383403778076172,
1401
+ "learning_rate": 1.3698746695458847e-06,
1402
+ "loss": 0.7779,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.7700452401578592,
1407
+ "grad_norm": 0.208175927400589,
1408
+ "learning_rate": 1.3272765235521745e-06,
1409
+ "loss": 0.7706,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.7738954663586486,
1414
+ "grad_norm": 0.21302570402622223,
1415
+ "learning_rate": 1.2852496272942877e-06,
1416
+ "loss": 0.7793,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.7777456925594378,
1421
+ "grad_norm": 0.19982188940048218,
1422
+ "learning_rate": 1.2438005175707396e-06,
1423
+ "loss": 0.7659,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.7815959187602272,
1428
+ "grad_norm": 0.2070276290178299,
1429
+ "learning_rate": 1.2029356413120297e-06,
1430
+ "loss": 0.7536,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.7854461449610165,
1435
+ "grad_norm": 0.21053263545036316,
1436
+ "learning_rate": 1.1626613545778786e-06,
1437
+ "loss": 0.7695,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.7892963711618057,
1442
+ "grad_norm": 0.2022554576396942,
1443
+ "learning_rate": 1.1229839215686294e-06,
1444
+ "loss": 0.7733,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.7931465973625951,
1449
+ "grad_norm": 0.19224557280540466,
1450
+ "learning_rate": 1.0839095136509188e-06,
1451
+ "loss": 0.7594,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.7969968235633843,
1456
+ "grad_norm": 0.2274632751941681,
1457
+ "learning_rate": 1.045444208397791e-06,
1458
+ "loss": 0.7821,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.8008470497641736,
1463
+ "grad_norm": 0.19657747447490692,
1464
+ "learning_rate": 1.007593988643402e-06,
1465
+ "loss": 0.7632,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.804697275964963,
1470
+ "grad_norm": 0.20633268356323242,
1471
+ "learning_rate": 9.703647415524613e-07,
1472
+ "loss": 0.7845,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.8085475021657522,
1477
+ "grad_norm": 0.2080032229423523,
1478
+ "learning_rate": 9.337622577045485e-07,
1479
+ "loss": 0.7733,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.8123977283665416,
1484
+ "grad_norm": 0.21002790331840515,
1485
+ "learning_rate": 8.977922301934588e-07,
1486
+ "loss": 0.7814,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.8162479545673308,
1491
+ "grad_norm": 0.2124558836221695,
1492
+ "learning_rate": 8.624602537417009e-07,
1493
+ "loss": 0.7828,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.8200981807681201,
1498
+ "grad_norm": 0.22640317678451538,
1499
+ "learning_rate": 8.277718238303123e-07,
1500
+ "loss": 0.7685,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.8239484069689095,
1505
+ "grad_norm": 0.21114447712898254,
1506
+ "learning_rate": 7.937323358440935e-07,
1507
+ "loss": 0.7736,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.8277986331696987,
1512
+ "grad_norm": 0.2270970195531845,
1513
+ "learning_rate": 7.603470842324223e-07,
1514
+ "loss": 0.7655,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.831648859370488,
1519
+ "grad_norm": 0.20568488538265228,
1520
+ "learning_rate": 7.276212616857575e-07,
1521
+ "loss": 0.7831,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.8354990855712773,
1526
+ "grad_norm": 0.20750771462917328,
1527
+ "learning_rate": 6.955599583279837e-07,
1528
+ "loss": 0.7851,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.8393493117720666,
1533
+ "grad_norm": 0.20571944117546082,
1534
+ "learning_rate": 6.641681609246981e-07,
1535
+ "loss": 0.7744,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.8431995379728559,
1540
+ "grad_norm": 0.19998811185359955,
1541
+ "learning_rate": 6.334507521075711e-07,
1542
+ "loss": 0.7842,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.8470497641736452,
1547
+ "grad_norm": 0.22232890129089355,
1548
+ "learning_rate": 6.034125096149179e-07,
1549
+ "loss": 0.7771,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.8508999903744345,
1554
+ "grad_norm": 0.21345071494579315,
1555
+ "learning_rate": 5.740581055485722e-07,
1556
+ "loss": 0.7473,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.8547502165752238,
1561
+ "grad_norm": 0.192673921585083,
1562
+ "learning_rate": 5.453921056471961e-07,
1563
+ "loss": 0.7809,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.8586004427760131,
1568
+ "grad_norm": 0.21327252686023712,
1569
+ "learning_rate": 5.174189685761288e-07,
1570
+ "loss": 0.7758,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.8624506689768023,
1575
+ "grad_norm": 0.19729246199131012,
1576
+ "learning_rate": 4.901430452338979e-07,
1577
+ "loss": 0.7865,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.8663008951775917,
1582
+ "grad_norm": 0.20290955901145935,
1583
+ "learning_rate": 4.6356857807548286e-07,
1584
+ "loss": 0.772,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.870151121378381,
1589
+ "grad_norm": 0.20993776619434357,
1590
+ "learning_rate": 4.376997004524541e-07,
1591
+ "loss": 0.7618,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.8740013475791703,
1596
+ "grad_norm": 0.21237675845623016,
1597
+ "learning_rate": 4.12540435970073e-07,
1598
+ "loss": 0.7703,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.8778515737799596,
1603
+ "grad_norm": 0.20923922955989838,
1604
+ "learning_rate": 3.880946978614703e-07,
1605
+ "loss": 0.7774,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.8817017999807488,
1610
+ "grad_norm": 0.21122848987579346,
1611
+ "learning_rate": 3.643662883789878e-07,
1612
+ "loss": 0.7849,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.8855520261815382,
1617
+ "grad_norm": 0.19561360776424408,
1618
+ "learning_rate": 3.41358898202781e-07,
1619
+ "loss": 0.7633,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.8894022523823275,
1624
+ "grad_norm": 0.1980663537979126,
1625
+ "learning_rate": 3.190761058667741e-07,
1626
+ "loss": 0.7764,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.8932524785831167,
1631
+ "grad_norm": 0.2075805813074112,
1632
+ "learning_rate": 2.9752137720206463e-07,
1633
+ "loss": 0.7796,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.8971027047839061,
1638
+ "grad_norm": 0.20497144758701324,
1639
+ "learning_rate": 2.7669806479785067e-07,
1640
+ "loss": 0.7841,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.9009529309846953,
1645
+ "grad_norm": 0.20873452723026276,
1646
+ "learning_rate": 2.566094074799763e-07,
1647
+ "loss": 0.7797,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.9048031571854847,
1652
+ "grad_norm": 0.204280287027359,
1653
+ "learning_rate": 2.3725852980716557e-07,
1654
+ "loss": 0.7614,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.908653383386274,
1659
+ "grad_norm": 0.20380885899066925,
1660
+ "learning_rate": 2.1864844158503983e-07,
1661
+ "loss": 0.773,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.9125036095870632,
1666
+ "grad_norm": 0.22461214661598206,
1667
+ "learning_rate": 2.007820373979702e-07,
1668
+ "loss": 0.7656,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.9163538357878526,
1673
+ "grad_norm": 0.20846429467201233,
1674
+ "learning_rate": 1.8366209615886532e-07,
1675
+ "loss": 0.7757,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.9202040619886418,
1680
+ "grad_norm": 0.20569050312042236,
1681
+ "learning_rate": 1.6729128067693613e-07,
1682
+ "loss": 0.7838,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.9240542881894311,
1687
+ "grad_norm": 0.22572170197963715,
1688
+ "learning_rate": 1.5167213724353426e-07,
1689
+ "loss": 0.7848,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.9279045143902205,
1694
+ "grad_norm": 0.2065679132938385,
1695
+ "learning_rate": 1.3680709523610058e-07,
1696
+ "loss": 0.7647,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.9317547405910097,
1701
+ "grad_norm": 0.208219975233078,
1702
+ "learning_rate": 1.2269846674030418e-07,
1703
+ "loss": 0.791,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.935604966791799,
1708
+ "grad_norm": 0.21968205273151398,
1709
+ "learning_rate": 1.0934844619042595e-07,
1710
+ "loss": 0.7844,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.9394551929925883,
1715
+ "grad_norm": 0.21992537379264832,
1716
+ "learning_rate": 9.675911002803961e-08,
1717
+ "loss": 0.7748,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.9433054191933776,
1722
+ "grad_norm": 0.2247823029756546,
1723
+ "learning_rate": 8.493241637904381e-08,
1724
+ "loss": 0.7738,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.9471556453941669,
1729
+ "grad_norm": 0.2084953635931015,
1730
+ "learning_rate": 7.387020474909689e-08,
1731
+ "loss": 0.791,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.9510058715949562,
1736
+ "grad_norm": 0.22294579446315765,
1737
+ "learning_rate": 6.357419573750856e-08,
1738
+ "loss": 0.7876,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.9548560977957455,
1743
+ "grad_norm": 0.20887179672718048,
1744
+ "learning_rate": 5.4045990769613365e-08,
1745
+ "loss": 0.7686,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.9587063239965348,
1750
+ "grad_norm": 0.20837971568107605,
1751
+ "learning_rate": 4.5287071847694434e-08,
1752
+ "loss": 0.7756,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.9625565501973241,
1757
+ "grad_norm": 0.20914310216903687,
1758
+ "learning_rate": 3.7298801320467817e-08,
1759
+ "loss": 0.7713,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.9664067763981133,
1764
+ "grad_norm": 0.2080354541540146,
1765
+ "learning_rate": 3.0082421671192576e-08,
1766
+ "loss": 0.7634,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.9702570025989027,
1771
+ "grad_norm": 0.20737680792808533,
1772
+ "learning_rate": 2.3639055324410355e-08,
1773
+ "loss": 0.782,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.974107228799692,
1778
+ "grad_norm": 0.2141965627670288,
1779
+ "learning_rate": 1.7969704471369477e-08,
1780
+ "loss": 0.77,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.9779574550004813,
1785
+ "grad_norm": 0.20162968337535858,
1786
+ "learning_rate": 1.3075250914142413e-08,
1787
+ "loss": 0.7715,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.9818076812012706,
1792
+ "grad_norm": 0.20147916674613953,
1793
+ "learning_rate": 8.956455928476049e-09,
1794
+ "loss": 0.7815,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.9856579074020598,
1799
+ "grad_norm": 0.20226159691810608,
1800
+ "learning_rate": 5.6139601453786275e-09,
1801
+ "loss": 0.7745,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.9895081336028492,
1806
+ "grad_norm": 0.20819644629955292,
1807
+ "learning_rate": 3.0482834514805602e-09,
1808
+ "loss": 0.7636,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.9933583598036385,
1813
+ "grad_norm": 0.20282794535160065,
1814
+ "learning_rate": 1.2598249081713366e-09,
1815
+ "loss": 0.7567,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.9972085860044277,
1820
+ "grad_norm": 0.21885094046592712,
1821
+ "learning_rate": 2.488626895302826e-10,
1822
+ "loss": 0.7865,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.9999037443449803,
1827
+ "step": 2597,
1828
+ "total_flos": 1.0743412796721988e+19,
1829
+ "train_loss": 0.7978170120950199,
1830
+ "train_runtime": 10621.3859,
1831
+ "train_samples_per_second": 62.6,
1832
+ "train_steps_per_second": 0.245
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": 1.0743412796721988e+19,
1853
+ "train_batch_size": 8,
1854
+ "trial_name": null,
1855
+ "trial_params": null
1856
+ }
continuous/qwen25/webssl_mae3b_full2b_224/finetune/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406d6b886a576f740057fe98af24237d96309860af2467053be39df5cc2df354
3
+ size 6264
continuous/qwen25/webssl_mae3b_full2b_224/finetune/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
continuous/qwen25/webssl_mae3b_full2b_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": 3072,
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": "hf:/cache/ckpt/download/tokenizer/continuous/webssl/webssl-mae3b-full2b-224",
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": null,
86
+ "vocab_size": 151936
87
+ }
continuous/qwen25/webssl_mae3b_full2b_224/pretrain/mm_projector.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa3ec2eb139d81d323bc1e8cf3ff4e9dd7e55302947e8a913394537f5ff9412
3
+ size 28325944
continuous/qwen25/webssl_mae3b_full2b_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": 4.825870037078857,
15
+ "learning_rate": 0.00032142857142857147,
16
+ "loss": 5.8907,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.03669724770642202,
21
+ "grad_norm": 0.4508224129676819,
22
+ "learning_rate": 0.0006785714285714287,
23
+ "loss": 3.6928,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.05504587155963303,
28
+ "grad_norm": 0.3006614148616791,
29
+ "learning_rate": 0.0009999907688176173,
30
+ "loss": 3.3488,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.07339449541284404,
35
+ "grad_norm": 0.29393959045410156,
36
+ "learning_rate": 0.0009988834393115766,
37
+ "loss": 3.258,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.09174311926605505,
42
+ "grad_norm": 0.1604757159948349,
43
+ "learning_rate": 0.0009959345572940772,
44
+ "loss": 3.2187,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.11009174311926606,
49
+ "grad_norm": 0.1573365032672882,
50
+ "learning_rate": 0.0009911550081155983,
51
+ "loss": 3.1827,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.12844036697247707,
56
+ "grad_norm": 0.11798259615898132,
57
+ "learning_rate": 0.0009845624347566433,
58
+ "loss": 3.1537,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.14678899082568808,
63
+ "grad_norm": 0.1722407042980194,
64
+ "learning_rate": 0.0009761811727013547,
65
+ "loss": 3.1326,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1651376146788991,
70
+ "grad_norm": 0.14153969287872314,
71
+ "learning_rate": 0.0009660421601067666,
72
+ "loss": 3.1027,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.1834862385321101,
77
+ "grad_norm": 0.15883448719978333,
78
+ "learning_rate": 0.0009541828235992926,
79
+ "loss": 3.0888,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2018348623853211,
84
+ "grad_norm": 0.1774405837059021,
85
+ "learning_rate": 0.0009406469401200151,
86
+ "loss": 3.0669,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.22018348623853212,
91
+ "grad_norm": 0.20551803708076477,
92
+ "learning_rate": 0.0009254844753287492,
93
+ "loss": 3.0553,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.23853211009174313,
98
+ "grad_norm": 0.28293806314468384,
99
+ "learning_rate": 0.0009087513991633924,
100
+ "loss": 3.0285,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.25688073394495414,
105
+ "grad_norm": 0.2632162868976593,
106
+ "learning_rate": 0.0008905094792353917,
107
+ "loss": 3.0157,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.27522935779816515,
112
+ "grad_norm": 0.41172370314598083,
113
+ "learning_rate": 0.0008708260528239789,
114
+ "loss": 3.0111,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.29357798165137616,
119
+ "grad_norm": 0.35458168387413025,
120
+ "learning_rate": 0.0008497737783108237,
121
+ "loss": 2.9971,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.3119266055045872,
126
+ "grad_norm": 0.19063077867031097,
127
+ "learning_rate": 0.0008274303669726426,
128
+ "loss": 2.9826,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.3302752293577982,
133
+ "grad_norm": 0.20337118208408356,
134
+ "learning_rate": 0.0008038782961218137,
135
+ "loss": 2.9687,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.3486238532110092,
140
+ "grad_norm": 0.2896587550640106,
141
+ "learning_rate": 0.000779204504653894,
142
+ "loss": 2.9638,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.3669724770642202,
147
+ "grad_norm": 0.26309940218925476,
148
+ "learning_rate": 0.0007535000721258791,
149
+ "loss": 2.94,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.3853211009174312,
154
+ "grad_norm": 0.39689332246780396,
155
+ "learning_rate": 0.00072685988254984,
156
+ "loss": 2.9392,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.4036697247706422,
161
+ "grad_norm": 0.35606658458709717,
162
+ "learning_rate": 0.0006993822741429906,
163
+ "loss": 2.946,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.42201834862385323,
168
+ "grad_norm": 0.23820513486862183,
169
+ "learning_rate": 0.0006711686763270818,
170
+ "loss": 2.941,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.44036697247706424,
175
+ "grad_norm": 0.26427021622657776,
176
+ "learning_rate": 0.0006423232353170831,
177
+ "loss": 2.9294,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.45871559633027525,
182
+ "grad_norm": 0.24811160564422607,
183
+ "learning_rate": 0.0006129524296812335,
184
+ "loss": 2.9138,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.47706422018348627,
189
+ "grad_norm": 0.32672226428985596,
190
+ "learning_rate": 0.0005831646772915651,
191
+ "loss": 2.9243,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.4954128440366973,
196
+ "grad_norm": 0.3311411738395691,
197
+ "learning_rate": 0.0005530699351157809,
198
+ "loss": 2.9026,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.5137614678899083,
203
+ "grad_norm": 0.2016647756099701,
204
+ "learning_rate": 0.0005227792933277943,
205
+ "loss": 2.9069,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.5321100917431193,
210
+ "grad_norm": 0.2825239300727844,
211
+ "learning_rate": 0.0004924045652352092,
212
+ "loss": 2.8851,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.5504587155963303,
217
+ "grad_norm": 0.26197418570518494,
218
+ "learning_rate": 0.0004620578745374633,
219
+ "loss": 2.8877,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.5688073394495413,
224
+ "grad_norm": 0.3415624499320984,
225
+ "learning_rate": 0.0004318512414382059,
226
+ "loss": 2.8963,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.5871559633027523,
231
+ "grad_norm": 0.37081378698349,
232
+ "learning_rate": 0.0004018961691397148,
233
+ "loss": 2.8872,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.6055045871559633,
238
+ "grad_norm": 0.3518434166908264,
239
+ "learning_rate": 0.0003723032322457458,
240
+ "loss": 2.8732,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.6238532110091743,
245
+ "grad_norm": 0.2624620497226715,
246
+ "learning_rate": 0.0003431816685921625,
247
+ "loss": 2.876,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.6422018348623854,
252
+ "grad_norm": 0.3188704252243042,
253
+ "learning_rate": 0.0003146389760120416,
254
+ "loss": 2.8788,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.6605504587155964,
259
+ "grad_norm": 0.35431674122810364,
260
+ "learning_rate": 0.00028678051552373485,
261
+ "loss": 2.8804,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.6788990825688074,
266
+ "grad_norm": 0.2790682911872864,
267
+ "learning_rate": 0.0002597091224066581,
268
+ "loss": 2.8691,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.6972477064220184,
273
+ "grad_norm": 0.26000988483428955,
274
+ "learning_rate": 0.0002335247266004629,
275
+ "loss": 2.8784,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.7155963302752294,
280
+ "grad_norm": 0.23517853021621704,
281
+ "learning_rate": 0.000208323983828828,
282
+ "loss": 2.8642,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.7339449541284404,
287
+ "grad_norm": 0.2827903628349304,
288
+ "learning_rate": 0.0001841999188095224,
289
+ "loss": 2.8627,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.7522935779816514,
294
+ "grad_norm": 0.2117435783147812,
295
+ "learning_rate": 0.00016124158186777676,
296
+ "loss": 2.8617,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.7706422018348624,
301
+ "grad_norm": 0.3064662516117096,
302
+ "learning_rate": 0.0001395337202205211,
303
+ "loss": 2.8562,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.7889908256880734,
308
+ "grad_norm": 0.23737068474292755,
309
+ "learning_rate": 0.00011915646514489292,
310
+ "loss": 2.8593,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.8073394495412844,
315
+ "grad_norm": 0.2548057734966278,
316
+ "learning_rate": 0.00010018503618578818,
317
+ "loss": 2.8641,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.8256880733944955,
322
+ "grad_norm": 0.20560236275196075,
323
+ "learning_rate": 8.268946349432583e-05,
324
+ "loss": 2.8621,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.8440366972477065,
329
+ "grad_norm": 0.21767565608024597,
330
+ "learning_rate": 6.673432932217117e-05,
331
+ "loss": 2.8506,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.8623853211009175,
336
+ "grad_norm": 0.20354464650154114,
337
+ "learning_rate": 5.2378529625954684e-05,
338
+ "loss": 2.8404,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.8807339449541285,
343
+ "grad_norm": 0.21537426114082336,
344
+ "learning_rate": 3.9675056661785556e-05,
345
+ "loss": 2.848,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.8990825688073395,
350
+ "grad_norm": 0.20284520089626312,
351
+ "learning_rate": 2.8670803372379538e-05,
352
+ "loss": 2.8552,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.9174311926605505,
357
+ "grad_norm": 0.19604842364788055,
358
+ "learning_rate": 1.9406390288876586e-05,
359
+ "loss": 2.8613,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.9357798165137615,
364
+ "grad_norm": 0.18617893755435944,
365
+ "learning_rate": 1.191601558631461e-05,
366
+ "loss": 2.8503,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.9541284403669725,
371
+ "grad_norm": 0.183115154504776,
372
+ "learning_rate": 6.2273288462559305e-06,
373
+ "loss": 2.8421,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.9724770642201835,
378
+ "grad_norm": 0.17621935904026031,
379
+ "learning_rate": 2.361328992552314e-06,
380
+ "loss": 2.8473,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.9908256880733946,
385
+ "grad_norm": 0.22285357117652893,
386
+ "learning_rate": 3.322867770044202e-07,
387
+ "loss": 2.8508,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.0,
392
+ "step": 545,
393
+ "total_flos": 8.500977358214267e+17,
394
+ "train_loss": 3.017227598067817,
395
+ "train_runtime": 5252.487,
396
+ "train_samples_per_second": 106.26,
397
+ "train_steps_per_second": 0.104
398
+ }
399
+ ],
400
+ "logging_steps": 10,
401
+ "max_steps": 545,
402
+ "num_input_tokens_seen": 33142912,
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": 8.500977358214267e+17,
418
+ "train_batch_size": 64,
419
+ "trial_name": null,
420
+ "trial_params": null
421
+ }
continuous/qwen25/webssl_mae700m_full2b_224/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/webssl_mae700m_full2b_224/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/webssl_mae700m_full2b_224/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": 1280,
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": "hf:/cache/ckpt/download/tokenizer/continuous/webssl/webssl-mae700m-full2b-224",
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": null,
86
+ "vocab_size": 151936
87
+ }
continuous/qwen25/webssl_mae700m_full2b_224/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/webssl_mae700m_full2b_224/finetune/merges.txt ADDED
The diff for this file is too large to render. See raw diff