Hugging Face's logo

MgGladys
/
SAS_7B_Classifier

Safetensors
Model card Files
xet
 Community
MgGladys commited on
Commit
07afa9a
·
verified ·
1 Parent(s): 28e8581

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. added_tokens.json +24 -0
  2. chat_template.jinja +7 -0
  3. checkpoint-100/added_tokens.json +24 -0
  4. checkpoint-100/chat_template.jinja +7 -0
  5. checkpoint-100/merges.txt +0 -0
  6. checkpoint-100/preprocessor_config.json +29 -0
  7. checkpoint-100/special_tokens_map.json +31 -0
  8. checkpoint-100/tokenizer_config.json +208 -0
  9. checkpoint-100/trainer_state.json +734 -0
  10. checkpoint-100/vocab.json +0 -0
  11. checkpoint-1000/added_tokens.json +24 -0
  12. checkpoint-1000/chat_template.jinja +7 -0
  13. checkpoint-1000/merges.txt +0 -0
  14. checkpoint-1000/preprocessor_config.json +29 -0
  15. checkpoint-1000/special_tokens_map.json +31 -0
  16. checkpoint-1000/tokenizer_config.json +208 -0
  17. checkpoint-1000/trainer_state.json +0 -0
  18. checkpoint-1000/vocab.json +0 -0
  19. checkpoint-500/added_tokens.json +24 -0
  20. checkpoint-500/chat_template.jinja +7 -0
  21. checkpoint-500/preprocessor_config.json +29 -0
  22. checkpoint-500/special_tokens_map.json +31 -0
  23. checkpoint-500/tokenizer_config.json +208 -0
  24. checkpoint-500/trainer_state.json +3534 -0
  25. checkpoint-700/added_tokens.json +24 -0
  26. checkpoint-700/chat_template.jinja +7 -0
  27. checkpoint-700/merges.txt +0 -0
  28. checkpoint-700/preprocessor_config.json +29 -0
  29. checkpoint-700/special_tokens_map.json +31 -0
  30. checkpoint-700/tokenizer_config.json +208 -0
  31. checkpoint-700/trainer_state.json +0 -0
  32. checkpoint-700/vocab.json +0 -0
  33. checkpoint-900/added_tokens.json +24 -0
  34. checkpoint-900/chat_template.jinja +7 -0
  35. checkpoint-900/merges.txt +0 -0
  36. checkpoint-900/preprocessor_config.json +29 -0
  37. checkpoint-900/special_tokens_map.json +31 -0
  38. checkpoint-900/tokenizer_config.json +208 -0
  39. checkpoint-900/trainer_state.json +0 -0
  40. checkpoint-900/vocab.json +0 -0
  41. merges.txt +0 -0
  42. preprocessor_config.json +29 -0
  43. special_tokens_map.json +31 -0
  44. tokenizer_config.json +208 -0
  45. train_cls.log +0 -0
  46. vocab.json +0 -0
  47. wandb/debug-internal.log +11 -0
  48. wandb/debug.log +24 -0
  49. wandb/run-20260102_193318-igfpea8y/logs/debug-internal.log +11 -0
  50. wandb/run-20260102_193318-igfpea8y/logs/debug.log +24 -0
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
+ }
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
checkpoint-100/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
+ }
checkpoint-100/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
checkpoint-100/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2_5_VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 1003520,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 1003520,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
checkpoint-100/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
+ }
checkpoint-100/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": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.05216484089723526,
6
+ "eval_steps": 500,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0005216484089723526,
14
+ "grad_norm": 3.6680614948272705,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.541,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0010432968179447052,
21
+ "grad_norm": 1.7092307806015015,
22
+ "learning_rate": 5e-06,
23
+ "loss": 0.2639,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.001564945226917058,
28
+ "grad_norm": 1.990319013595581,
29
+ "learning_rate": 1e-05,
30
+ "loss": 0.3118,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0020865936358894104,
35
+ "grad_norm": 3.750917434692383,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 0.4562,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.0026082420448617634,
42
+ "grad_norm": 4.690845966339111,
43
+ "learning_rate": 2e-05,
44
+ "loss": 0.673,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.003129890453834116,
49
+ "grad_norm": 1.4218288660049438,
50
+ "learning_rate": 2.5e-05,
51
+ "loss": 0.2984,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0036515388628064684,
56
+ "grad_norm": 4.896511077880859,
57
+ "learning_rate": 3e-05,
58
+ "loss": 0.7113,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.004173187271778821,
63
+ "grad_norm": 2.5787155628204346,
64
+ "learning_rate": 3.5000000000000004e-05,
65
+ "loss": 0.4226,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.004694835680751174,
70
+ "grad_norm": 1.028937578201294,
71
+ "learning_rate": 4e-05,
72
+ "loss": 0.1873,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.005216484089723527,
77
+ "grad_norm": 3.9262092113494873,
78
+ "learning_rate": 4.4999999999999996e-05,
79
+ "loss": 0.5728,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.005738132498695879,
84
+ "grad_norm": 4.9360198974609375,
85
+ "learning_rate": 5e-05,
86
+ "loss": 0.725,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.006259780907668232,
91
+ "grad_norm": 4.287437915802002,
92
+ "learning_rate": 5.5e-05,
93
+ "loss": 0.6361,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.006781429316640584,
98
+ "grad_norm": 1.3290928602218628,
99
+ "learning_rate": 6e-05,
100
+ "loss": 0.3109,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.007303077725612937,
105
+ "grad_norm": 2.0050501823425293,
106
+ "learning_rate": 6.500000000000001e-05,
107
+ "loss": 0.4099,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.00782472613458529,
112
+ "grad_norm": 4.360481262207031,
113
+ "learning_rate": 7.000000000000001e-05,
114
+ "loss": 0.6363,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.008346374543557642,
119
+ "grad_norm": 3.9680511951446533,
120
+ "learning_rate": 7.5e-05,
121
+ "loss": 0.6124,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.008868022952529996,
126
+ "grad_norm": 1.701784610748291,
127
+ "learning_rate": 8e-05,
128
+ "loss": 0.3439,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.009389671361502348,
133
+ "grad_norm": 4.544748783111572,
134
+ "learning_rate": 8.5e-05,
135
+ "loss": 0.6253,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.0099113197704747,
140
+ "grad_norm": 4.58634090423584,
141
+ "learning_rate": 8.999999999999999e-05,
142
+ "loss": 0.7669,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.010432968179447054,
147
+ "grad_norm": 2.89898419380188,
148
+ "learning_rate": 9.5e-05,
149
+ "loss": 0.512,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.010954616588419406,
154
+ "grad_norm": 2.61112904548645,
155
+ "learning_rate": 0.0001,
156
+ "loss": 0.542,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.011476264997391758,
161
+ "grad_norm": 3.217054843902588,
162
+ "learning_rate": 0.000105,
163
+ "loss": 0.4959,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.011997913406364111,
168
+ "grad_norm": 2.569636821746826,
169
+ "learning_rate": 0.00011,
170
+ "loss": 0.3918,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.012519561815336464,
175
+ "grad_norm": 1.4626373052597046,
176
+ "learning_rate": 0.000115,
177
+ "loss": 0.3316,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.013041210224308816,
182
+ "grad_norm": 1.2480732202529907,
183
+ "learning_rate": 0.00012,
184
+ "loss": 0.3484,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.013562858633281168,
189
+ "grad_norm": 2.5430543422698975,
190
+ "learning_rate": 0.000125,
191
+ "loss": 0.4699,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.014084507042253521,
196
+ "grad_norm": 1.7051862478256226,
197
+ "learning_rate": 0.00013000000000000002,
198
+ "loss": 0.2139,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.014606155451225874,
203
+ "grad_norm": 1.1670981645584106,
204
+ "learning_rate": 0.000135,
205
+ "loss": 0.3883,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.015127803860198226,
210
+ "grad_norm": 1.336538314819336,
211
+ "learning_rate": 0.00014000000000000001,
212
+ "loss": 0.3714,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.01564945226917058,
217
+ "grad_norm": 2.018078565597534,
218
+ "learning_rate": 0.000145,
219
+ "loss": 0.2301,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.01617110067814293,
224
+ "grad_norm": 1.5743223428726196,
225
+ "learning_rate": 0.00015,
226
+ "loss": 0.2935,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.016692749087115284,
231
+ "grad_norm": 1.2724987268447876,
232
+ "learning_rate": 0.000155,
233
+ "loss": 0.3141,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.017214397496087636,
238
+ "grad_norm": 2.2347893714904785,
239
+ "learning_rate": 0.00016,
240
+ "loss": 0.2917,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.01773604590505999,
245
+ "grad_norm": 1.6726069450378418,
246
+ "learning_rate": 0.000165,
247
+ "loss": 0.377,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.018257694314032343,
252
+ "grad_norm": 1.2217071056365967,
253
+ "learning_rate": 0.00017,
254
+ "loss": 0.3027,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.018779342723004695,
259
+ "grad_norm": 1.3436322212219238,
260
+ "learning_rate": 0.000175,
261
+ "loss": 0.2853,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.019300991131977047,
266
+ "grad_norm": 1.2247120141983032,
267
+ "learning_rate": 0.00017999999999999998,
268
+ "loss": 0.2967,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.0198226395409494,
273
+ "grad_norm": 1.0636978149414062,
274
+ "learning_rate": 0.000185,
275
+ "loss": 0.2745,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.02034428794992175,
280
+ "grad_norm": 1.302099347114563,
281
+ "learning_rate": 0.00019,
282
+ "loss": 0.2688,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.020865936358894107,
287
+ "grad_norm": 1.0052679777145386,
288
+ "learning_rate": 0.00019500000000000002,
289
+ "loss": 0.2539,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.02138758476786646,
294
+ "grad_norm": 1.0164084434509277,
295
+ "learning_rate": 0.0002,
296
+ "loss": 0.1978,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.02190923317683881,
301
+ "grad_norm": 1.3891016244888306,
302
+ "learning_rate": 0.000205,
303
+ "loss": 0.3189,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.022430881585811163,
308
+ "grad_norm": 0.960986852645874,
309
+ "learning_rate": 0.00021,
310
+ "loss": 0.2321,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.022952529994783515,
315
+ "grad_norm": 0.9918408393859863,
316
+ "learning_rate": 0.000215,
317
+ "loss": 0.2359,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.023474178403755867,
322
+ "grad_norm": 1.190205693244934,
323
+ "learning_rate": 0.00022,
324
+ "loss": 0.2347,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.023995826812728223,
329
+ "grad_norm": 0.7985232472419739,
330
+ "learning_rate": 0.00022500000000000002,
331
+ "loss": 0.2048,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.024517475221700575,
336
+ "grad_norm": 0.5192842483520508,
337
+ "learning_rate": 0.00023,
338
+ "loss": 0.1116,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.025039123630672927,
343
+ "grad_norm": 1.1033375263214111,
344
+ "learning_rate": 0.000235,
345
+ "loss": 0.2665,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.02556077203964528,
350
+ "grad_norm": 0.7089418172836304,
351
+ "learning_rate": 0.00024,
352
+ "loss": 0.1639,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.02608242044861763,
357
+ "grad_norm": 1.08647882938385,
358
+ "learning_rate": 0.000245,
359
+ "loss": 0.2072,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.026604068857589983,
364
+ "grad_norm": 0.9901174902915955,
365
+ "learning_rate": 0.00025,
366
+ "loss": 0.2035,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.027125717266562335,
371
+ "grad_norm": 0.6938351988792419,
372
+ "learning_rate": 0.000255,
373
+ "loss": 0.1851,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.02764736567553469,
378
+ "grad_norm": 0.8392678499221802,
379
+ "learning_rate": 0.00026000000000000003,
380
+ "loss": 0.1918,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.028169014084507043,
385
+ "grad_norm": 0.5979602932929993,
386
+ "learning_rate": 0.00026500000000000004,
387
+ "loss": 0.1243,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.028690662493479395,
392
+ "grad_norm": 0.7119799852371216,
393
+ "learning_rate": 0.00027,
394
+ "loss": 0.1594,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.029212310902451747,
399
+ "grad_norm": 0.5519995093345642,
400
+ "learning_rate": 0.000275,
401
+ "loss": 0.078,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.0297339593114241,
406
+ "grad_norm": 0.5917723774909973,
407
+ "learning_rate": 0.00028000000000000003,
408
+ "loss": 0.134,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.03025560772039645,
413
+ "grad_norm": 0.6265603303909302,
414
+ "learning_rate": 0.000285,
415
+ "loss": 0.1848,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.030777256129368807,
420
+ "grad_norm": 1.0653454065322876,
421
+ "learning_rate": 0.00029,
422
+ "loss": 0.1831,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.03129890453834116,
427
+ "grad_norm": 0.3466293513774872,
428
+ "learning_rate": 0.000295,
429
+ "loss": 0.0878,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.03182055294731351,
434
+ "grad_norm": 0.5498062372207642,
435
+ "learning_rate": 0.0003,
436
+ "loss": 0.1733,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.03234220135628586,
441
+ "grad_norm": 0.7708966135978699,
442
+ "learning_rate": 0.000305,
443
+ "loss": 0.1975,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.03286384976525822,
448
+ "grad_norm": 0.7717278003692627,
449
+ "learning_rate": 0.00031,
450
+ "loss": 0.1863,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.03338549817423057,
455
+ "grad_norm": 0.8076028823852539,
456
+ "learning_rate": 0.000315,
457
+ "loss": 0.1938,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.03390714658320292,
462
+ "grad_norm": 0.5629755258560181,
463
+ "learning_rate": 0.00032,
464
+ "loss": 0.1471,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.03442879499217527,
469
+ "grad_norm": 0.5237282514572144,
470
+ "learning_rate": 0.00032500000000000004,
471
+ "loss": 0.1244,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.03495044340114763,
476
+ "grad_norm": 0.7248942852020264,
477
+ "learning_rate": 0.00033,
478
+ "loss": 0.1933,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.03547209181011998,
483
+ "grad_norm": 0.49564772844314575,
484
+ "learning_rate": 0.000335,
485
+ "loss": 0.1389,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.03599374021909233,
490
+ "grad_norm": 0.4806594252586365,
491
+ "learning_rate": 0.00034,
492
+ "loss": 0.1295,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.036515388628064686,
497
+ "grad_norm": 0.39995619654655457,
498
+ "learning_rate": 0.000345,
499
+ "loss": 0.1324,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.037037037037037035,
504
+ "grad_norm": 0.6496027708053589,
505
+ "learning_rate": 0.00035,
506
+ "loss": 0.1002,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.03755868544600939,
511
+ "grad_norm": 0.5661569237709045,
512
+ "learning_rate": 0.000355,
513
+ "loss": 0.1277,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.03808033385498174,
518
+ "grad_norm": 0.49875250458717346,
519
+ "learning_rate": 0.00035999999999999997,
520
+ "loss": 0.1322,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.038601982263954095,
525
+ "grad_norm": 0.44551461935043335,
526
+ "learning_rate": 0.000365,
527
+ "loss": 0.1278,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.03912363067292645,
532
+ "grad_norm": 0.3314933478832245,
533
+ "learning_rate": 0.00037,
534
+ "loss": 0.0918,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.0396452790818988,
539
+ "grad_norm": 0.3463922441005707,
540
+ "learning_rate": 0.000375,
541
+ "loss": 0.0948,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.040166927490871154,
546
+ "grad_norm": 0.5401505827903748,
547
+ "learning_rate": 0.00038,
548
+ "loss": 0.1574,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.0406885758998435,
553
+ "grad_norm": 0.39233317971229553,
554
+ "learning_rate": 0.00038500000000000003,
555
+ "loss": 0.1312,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.04121022430881586,
560
+ "grad_norm": 0.4380398988723755,
561
+ "learning_rate": 0.00039000000000000005,
562
+ "loss": 0.0601,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.041731872717788214,
567
+ "grad_norm": 0.3931694030761719,
568
+ "learning_rate": 0.000395,
569
+ "loss": 0.0962,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.04225352112676056,
574
+ "grad_norm": 0.3566243648529053,
575
+ "learning_rate": 0.0004,
576
+ "loss": 0.1137,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.04277516953573292,
581
+ "grad_norm": 0.40159469842910767,
582
+ "learning_rate": 0.00040500000000000003,
583
+ "loss": 0.1128,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.04329681794470527,
588
+ "grad_norm": 0.30474773049354553,
589
+ "learning_rate": 0.00041,
590
+ "loss": 0.0922,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.04381846635367762,
595
+ "grad_norm": 0.31177017092704773,
596
+ "learning_rate": 0.000415,
597
+ "loss": 0.1015,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.04434011476264997,
602
+ "grad_norm": 0.3996855914592743,
603
+ "learning_rate": 0.00042,
604
+ "loss": 0.1266,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.044861763171622326,
609
+ "grad_norm": 0.2281728833913803,
610
+ "learning_rate": 0.000425,
611
+ "loss": 0.0758,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.04538341158059468,
616
+ "grad_norm": 0.5169669985771179,
617
+ "learning_rate": 0.00043,
618
+ "loss": 0.1092,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.04590505998956703,
623
+ "grad_norm": 0.5525585412979126,
624
+ "learning_rate": 0.000435,
625
+ "loss": 0.1226,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.046426708398539386,
630
+ "grad_norm": 0.33093884587287903,
631
+ "learning_rate": 0.00044,
632
+ "loss": 0.0879,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.046948356807511735,
637
+ "grad_norm": 0.3713582158088684,
638
+ "learning_rate": 0.00044500000000000003,
639
+ "loss": 0.1121,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.04747000521648409,
644
+ "grad_norm": 0.565517246723175,
645
+ "learning_rate": 0.00045000000000000004,
646
+ "loss": 0.1469,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.047991653625456446,
651
+ "grad_norm": 0.31801939010620117,
652
+ "learning_rate": 0.000455,
653
+ "loss": 0.0915,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.048513302034428794,
658
+ "grad_norm": 0.42586401104927063,
659
+ "learning_rate": 0.00046,
660
+ "loss": 0.0411,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.04903495044340115,
665
+ "grad_norm": 0.42403289675712585,
666
+ "learning_rate": 0.000465,
667
+ "loss": 0.0589,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.0495565988523735,
672
+ "grad_norm": 0.2604529559612274,
673
+ "learning_rate": 0.00047,
674
+ "loss": 0.0779,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.050078247261345854,
679
+ "grad_norm": 0.32257840037345886,
680
+ "learning_rate": 0.000475,
681
+ "loss": 0.0958,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.0505998956703182,
686
+ "grad_norm": 0.2648946940898895,
687
+ "learning_rate": 0.00048,
688
+ "loss": 0.0591,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.05112154407929056,
693
+ "grad_norm": 0.26664629578590393,
694
+ "learning_rate": 0.00048499999999999997,
695
+ "loss": 0.0607,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.051643192488262914,
700
+ "grad_norm": 0.2891658544540405,
701
+ "learning_rate": 0.00049,
702
+ "loss": 0.0478,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.05216484089723526,
707
+ "grad_norm": 0.35936883091926575,
708
+ "learning_rate": 0.000495,
709
+ "loss": 0.1126,
710
+ "step": 100
711
+ }
712
+ ],
713
+ "logging_steps": 1,
714
+ "max_steps": 1000,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 1,
717
+ "save_steps": 100,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": false
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 0.0,
731
+ "train_batch_size": 512,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
checkpoint-100/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/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
+ }
checkpoint-1000/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
checkpoint-1000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2_5_VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 1003520,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 1003520,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
checkpoint-1000/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
+ }
checkpoint-1000/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": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-1000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/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
+ }
checkpoint-500/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
checkpoint-500/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2_5_VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 1003520,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 1003520,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
checkpoint-500/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
+ }
checkpoint-500/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": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,3534 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.2608242044861763,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0005216484089723526,
14
+ "grad_norm": 3.6680614948272705,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.541,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0010432968179447052,
21
+ "grad_norm": 1.7092307806015015,
22
+ "learning_rate": 5e-06,
23
+ "loss": 0.2639,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.001564945226917058,
28
+ "grad_norm": 1.990319013595581,
29
+ "learning_rate": 1e-05,
30
+ "loss": 0.3118,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0020865936358894104,
35
+ "grad_norm": 3.750917434692383,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 0.4562,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.0026082420448617634,
42
+ "grad_norm": 4.690845966339111,
43
+ "learning_rate": 2e-05,
44
+ "loss": 0.673,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.003129890453834116,
49
+ "grad_norm": 1.4218288660049438,
50
+ "learning_rate": 2.5e-05,
51
+ "loss": 0.2984,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0036515388628064684,
56
+ "grad_norm": 4.896511077880859,
57
+ "learning_rate": 3e-05,
58
+ "loss": 0.7113,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.004173187271778821,
63
+ "grad_norm": 2.5787155628204346,
64
+ "learning_rate": 3.5000000000000004e-05,
65
+ "loss": 0.4226,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.004694835680751174,
70
+ "grad_norm": 1.028937578201294,
71
+ "learning_rate": 4e-05,
72
+ "loss": 0.1873,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.005216484089723527,
77
+ "grad_norm": 3.9262092113494873,
78
+ "learning_rate": 4.4999999999999996e-05,
79
+ "loss": 0.5728,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.005738132498695879,
84
+ "grad_norm": 4.9360198974609375,
85
+ "learning_rate": 5e-05,
86
+ "loss": 0.725,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.006259780907668232,
91
+ "grad_norm": 4.287437915802002,
92
+ "learning_rate": 5.5e-05,
93
+ "loss": 0.6361,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.006781429316640584,
98
+ "grad_norm": 1.3290928602218628,
99
+ "learning_rate": 6e-05,
100
+ "loss": 0.3109,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.007303077725612937,
105
+ "grad_norm": 2.0050501823425293,
106
+ "learning_rate": 6.500000000000001e-05,
107
+ "loss": 0.4099,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.00782472613458529,
112
+ "grad_norm": 4.360481262207031,
113
+ "learning_rate": 7.000000000000001e-05,
114
+ "loss": 0.6363,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.008346374543557642,
119
+ "grad_norm": 3.9680511951446533,
120
+ "learning_rate": 7.5e-05,
121
+ "loss": 0.6124,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.008868022952529996,
126
+ "grad_norm": 1.701784610748291,
127
+ "learning_rate": 8e-05,
128
+ "loss": 0.3439,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.009389671361502348,
133
+ "grad_norm": 4.544748783111572,
134
+ "learning_rate": 8.5e-05,
135
+ "loss": 0.6253,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.0099113197704747,
140
+ "grad_norm": 4.58634090423584,
141
+ "learning_rate": 8.999999999999999e-05,
142
+ "loss": 0.7669,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.010432968179447054,
147
+ "grad_norm": 2.89898419380188,
148
+ "learning_rate": 9.5e-05,
149
+ "loss": 0.512,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.010954616588419406,
154
+ "grad_norm": 2.61112904548645,
155
+ "learning_rate": 0.0001,
156
+ "loss": 0.542,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.011476264997391758,
161
+ "grad_norm": 3.217054843902588,
162
+ "learning_rate": 0.000105,
163
+ "loss": 0.4959,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.011997913406364111,
168
+ "grad_norm": 2.569636821746826,
169
+ "learning_rate": 0.00011,
170
+ "loss": 0.3918,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.012519561815336464,
175
+ "grad_norm": 1.4626373052597046,
176
+ "learning_rate": 0.000115,
177
+ "loss": 0.3316,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.013041210224308816,
182
+ "grad_norm": 1.2480732202529907,
183
+ "learning_rate": 0.00012,
184
+ "loss": 0.3484,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.013562858633281168,
189
+ "grad_norm": 2.5430543422698975,
190
+ "learning_rate": 0.000125,
191
+ "loss": 0.4699,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.014084507042253521,
196
+ "grad_norm": 1.7051862478256226,
197
+ "learning_rate": 0.00013000000000000002,
198
+ "loss": 0.2139,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.014606155451225874,
203
+ "grad_norm": 1.1670981645584106,
204
+ "learning_rate": 0.000135,
205
+ "loss": 0.3883,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.015127803860198226,
210
+ "grad_norm": 1.336538314819336,
211
+ "learning_rate": 0.00014000000000000001,
212
+ "loss": 0.3714,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.01564945226917058,
217
+ "grad_norm": 2.018078565597534,
218
+ "learning_rate": 0.000145,
219
+ "loss": 0.2301,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.01617110067814293,
224
+ "grad_norm": 1.5743223428726196,
225
+ "learning_rate": 0.00015,
226
+ "loss": 0.2935,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.016692749087115284,
231
+ "grad_norm": 1.2724987268447876,
232
+ "learning_rate": 0.000155,
233
+ "loss": 0.3141,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.017214397496087636,
238
+ "grad_norm": 2.2347893714904785,
239
+ "learning_rate": 0.00016,
240
+ "loss": 0.2917,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.01773604590505999,
245
+ "grad_norm": 1.6726069450378418,
246
+ "learning_rate": 0.000165,
247
+ "loss": 0.377,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.018257694314032343,
252
+ "grad_norm": 1.2217071056365967,
253
+ "learning_rate": 0.00017,
254
+ "loss": 0.3027,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.018779342723004695,
259
+ "grad_norm": 1.3436322212219238,
260
+ "learning_rate": 0.000175,
261
+ "loss": 0.2853,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.019300991131977047,
266
+ "grad_norm": 1.2247120141983032,
267
+ "learning_rate": 0.00017999999999999998,
268
+ "loss": 0.2967,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.0198226395409494,
273
+ "grad_norm": 1.0636978149414062,
274
+ "learning_rate": 0.000185,
275
+ "loss": 0.2745,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.02034428794992175,
280
+ "grad_norm": 1.302099347114563,
281
+ "learning_rate": 0.00019,
282
+ "loss": 0.2688,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.020865936358894107,
287
+ "grad_norm": 1.0052679777145386,
288
+ "learning_rate": 0.00019500000000000002,
289
+ "loss": 0.2539,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.02138758476786646,
294
+ "grad_norm": 1.0164084434509277,
295
+ "learning_rate": 0.0002,
296
+ "loss": 0.1978,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.02190923317683881,
301
+ "grad_norm": 1.3891016244888306,
302
+ "learning_rate": 0.000205,
303
+ "loss": 0.3189,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.022430881585811163,
308
+ "grad_norm": 0.960986852645874,
309
+ "learning_rate": 0.00021,
310
+ "loss": 0.2321,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.022952529994783515,
315
+ "grad_norm": 0.9918408393859863,
316
+ "learning_rate": 0.000215,
317
+ "loss": 0.2359,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.023474178403755867,
322
+ "grad_norm": 1.190205693244934,
323
+ "learning_rate": 0.00022,
324
+ "loss": 0.2347,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.023995826812728223,
329
+ "grad_norm": 0.7985232472419739,
330
+ "learning_rate": 0.00022500000000000002,
331
+ "loss": 0.2048,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.024517475221700575,
336
+ "grad_norm": 0.5192842483520508,
337
+ "learning_rate": 0.00023,
338
+ "loss": 0.1116,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.025039123630672927,
343
+ "grad_norm": 1.1033375263214111,
344
+ "learning_rate": 0.000235,
345
+ "loss": 0.2665,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.02556077203964528,
350
+ "grad_norm": 0.7089418172836304,
351
+ "learning_rate": 0.00024,
352
+ "loss": 0.1639,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.02608242044861763,
357
+ "grad_norm": 1.08647882938385,
358
+ "learning_rate": 0.000245,
359
+ "loss": 0.2072,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.026604068857589983,
364
+ "grad_norm": 0.9901174902915955,
365
+ "learning_rate": 0.00025,
366
+ "loss": 0.2035,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.027125717266562335,
371
+ "grad_norm": 0.6938351988792419,
372
+ "learning_rate": 0.000255,
373
+ "loss": 0.1851,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.02764736567553469,
378
+ "grad_norm": 0.8392678499221802,
379
+ "learning_rate": 0.00026000000000000003,
380
+ "loss": 0.1918,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.028169014084507043,
385
+ "grad_norm": 0.5979602932929993,
386
+ "learning_rate": 0.00026500000000000004,
387
+ "loss": 0.1243,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.028690662493479395,
392
+ "grad_norm": 0.7119799852371216,
393
+ "learning_rate": 0.00027,
394
+ "loss": 0.1594,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.029212310902451747,
399
+ "grad_norm": 0.5519995093345642,
400
+ "learning_rate": 0.000275,
401
+ "loss": 0.078,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.0297339593114241,
406
+ "grad_norm": 0.5917723774909973,
407
+ "learning_rate": 0.00028000000000000003,
408
+ "loss": 0.134,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.03025560772039645,
413
+ "grad_norm": 0.6265603303909302,
414
+ "learning_rate": 0.000285,
415
+ "loss": 0.1848,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.030777256129368807,
420
+ "grad_norm": 1.0653454065322876,
421
+ "learning_rate": 0.00029,
422
+ "loss": 0.1831,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.03129890453834116,
427
+ "grad_norm": 0.3466293513774872,
428
+ "learning_rate": 0.000295,
429
+ "loss": 0.0878,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.03182055294731351,
434
+ "grad_norm": 0.5498062372207642,
435
+ "learning_rate": 0.0003,
436
+ "loss": 0.1733,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.03234220135628586,
441
+ "grad_norm": 0.7708966135978699,
442
+ "learning_rate": 0.000305,
443
+ "loss": 0.1975,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.03286384976525822,
448
+ "grad_norm": 0.7717278003692627,
449
+ "learning_rate": 0.00031,
450
+ "loss": 0.1863,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.03338549817423057,
455
+ "grad_norm": 0.8076028823852539,
456
+ "learning_rate": 0.000315,
457
+ "loss": 0.1938,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.03390714658320292,
462
+ "grad_norm": 0.5629755258560181,
463
+ "learning_rate": 0.00032,
464
+ "loss": 0.1471,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.03442879499217527,
469
+ "grad_norm": 0.5237282514572144,
470
+ "learning_rate": 0.00032500000000000004,
471
+ "loss": 0.1244,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.03495044340114763,
476
+ "grad_norm": 0.7248942852020264,
477
+ "learning_rate": 0.00033,
478
+ "loss": 0.1933,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.03547209181011998,
483
+ "grad_norm": 0.49564772844314575,
484
+ "learning_rate": 0.000335,
485
+ "loss": 0.1389,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.03599374021909233,
490
+ "grad_norm": 0.4806594252586365,
491
+ "learning_rate": 0.00034,
492
+ "loss": 0.1295,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.036515388628064686,
497
+ "grad_norm": 0.39995619654655457,
498
+ "learning_rate": 0.000345,
499
+ "loss": 0.1324,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.037037037037037035,
504
+ "grad_norm": 0.6496027708053589,
505
+ "learning_rate": 0.00035,
506
+ "loss": 0.1002,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.03755868544600939,
511
+ "grad_norm": 0.5661569237709045,
512
+ "learning_rate": 0.000355,
513
+ "loss": 0.1277,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.03808033385498174,
518
+ "grad_norm": 0.49875250458717346,
519
+ "learning_rate": 0.00035999999999999997,
520
+ "loss": 0.1322,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.038601982263954095,
525
+ "grad_norm": 0.44551461935043335,
526
+ "learning_rate": 0.000365,
527
+ "loss": 0.1278,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.03912363067292645,
532
+ "grad_norm": 0.3314933478832245,
533
+ "learning_rate": 0.00037,
534
+ "loss": 0.0918,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.0396452790818988,
539
+ "grad_norm": 0.3463922441005707,
540
+ "learning_rate": 0.000375,
541
+ "loss": 0.0948,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.040166927490871154,
546
+ "grad_norm": 0.5401505827903748,
547
+ "learning_rate": 0.00038,
548
+ "loss": 0.1574,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.0406885758998435,
553
+ "grad_norm": 0.39233317971229553,
554
+ "learning_rate": 0.00038500000000000003,
555
+ "loss": 0.1312,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.04121022430881586,
560
+ "grad_norm": 0.4380398988723755,
561
+ "learning_rate": 0.00039000000000000005,
562
+ "loss": 0.0601,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.041731872717788214,
567
+ "grad_norm": 0.3931694030761719,
568
+ "learning_rate": 0.000395,
569
+ "loss": 0.0962,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.04225352112676056,
574
+ "grad_norm": 0.3566243648529053,
575
+ "learning_rate": 0.0004,
576
+ "loss": 0.1137,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.04277516953573292,
581
+ "grad_norm": 0.40159469842910767,
582
+ "learning_rate": 0.00040500000000000003,
583
+ "loss": 0.1128,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.04329681794470527,
588
+ "grad_norm": 0.30474773049354553,
589
+ "learning_rate": 0.00041,
590
+ "loss": 0.0922,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.04381846635367762,
595
+ "grad_norm": 0.31177017092704773,
596
+ "learning_rate": 0.000415,
597
+ "loss": 0.1015,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.04434011476264997,
602
+ "grad_norm": 0.3996855914592743,
603
+ "learning_rate": 0.00042,
604
+ "loss": 0.1266,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.044861763171622326,
609
+ "grad_norm": 0.2281728833913803,
610
+ "learning_rate": 0.000425,
611
+ "loss": 0.0758,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.04538341158059468,
616
+ "grad_norm": 0.5169669985771179,
617
+ "learning_rate": 0.00043,
618
+ "loss": 0.1092,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.04590505998956703,
623
+ "grad_norm": 0.5525585412979126,
624
+ "learning_rate": 0.000435,
625
+ "loss": 0.1226,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.046426708398539386,
630
+ "grad_norm": 0.33093884587287903,
631
+ "learning_rate": 0.00044,
632
+ "loss": 0.0879,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.046948356807511735,
637
+ "grad_norm": 0.3713582158088684,
638
+ "learning_rate": 0.00044500000000000003,
639
+ "loss": 0.1121,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.04747000521648409,
644
+ "grad_norm": 0.565517246723175,
645
+ "learning_rate": 0.00045000000000000004,
646
+ "loss": 0.1469,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.047991653625456446,
651
+ "grad_norm": 0.31801939010620117,
652
+ "learning_rate": 0.000455,
653
+ "loss": 0.0915,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.048513302034428794,
658
+ "grad_norm": 0.42586401104927063,
659
+ "learning_rate": 0.00046,
660
+ "loss": 0.0411,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.04903495044340115,
665
+ "grad_norm": 0.42403289675712585,
666
+ "learning_rate": 0.000465,
667
+ "loss": 0.0589,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.0495565988523735,
672
+ "grad_norm": 0.2604529559612274,
673
+ "learning_rate": 0.00047,
674
+ "loss": 0.0779,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.050078247261345854,
679
+ "grad_norm": 0.32257840037345886,
680
+ "learning_rate": 0.000475,
681
+ "loss": 0.0958,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.0505998956703182,
686
+ "grad_norm": 0.2648946940898895,
687
+ "learning_rate": 0.00048,
688
+ "loss": 0.0591,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.05112154407929056,
693
+ "grad_norm": 0.26664629578590393,
694
+ "learning_rate": 0.00048499999999999997,
695
+ "loss": 0.0607,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.051643192488262914,
700
+ "grad_norm": 0.2891658544540405,
701
+ "learning_rate": 0.00049,
702
+ "loss": 0.0478,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.05216484089723526,
707
+ "grad_norm": 0.35936883091926575,
708
+ "learning_rate": 0.000495,
709
+ "loss": 0.1126,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.05268648930620762,
714
+ "grad_norm": 0.3226841986179352,
715
+ "learning_rate": 0.0005,
716
+ "loss": 0.0995,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.053208137715179966,
721
+ "grad_norm": 0.2140406370162964,
722
+ "learning_rate": 0.0004994444444444445,
723
+ "loss": 0.0636,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.05372978612415232,
728
+ "grad_norm": 0.28297877311706543,
729
+ "learning_rate": 0.0004988888888888889,
730
+ "loss": 0.0674,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.05425143453312467,
735
+ "grad_norm": 0.27131739258766174,
736
+ "learning_rate": 0.0004983333333333334,
737
+ "loss": 0.0657,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.054773082942097026,
742
+ "grad_norm": 0.28402701020240784,
743
+ "learning_rate": 0.0004977777777777778,
744
+ "loss": 0.0894,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.05529473135106938,
749
+ "grad_norm": 0.33924373984336853,
750
+ "learning_rate": 0.0004972222222222222,
751
+ "loss": 0.1264,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.05581637976004173,
756
+ "grad_norm": 0.3655984401702881,
757
+ "learning_rate": 0.0004966666666666666,
758
+ "loss": 0.0828,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.056338028169014086,
763
+ "grad_norm": 0.2262953370809555,
764
+ "learning_rate": 0.0004961111111111111,
765
+ "loss": 0.0662,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.056859676577986434,
770
+ "grad_norm": 0.23988084495067596,
771
+ "learning_rate": 0.0004955555555555556,
772
+ "loss": 0.0672,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.05738132498695879,
777
+ "grad_norm": 0.228820338845253,
778
+ "learning_rate": 0.000495,
779
+ "loss": 0.0615,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.057902973395931145,
784
+ "grad_norm": 0.32484373450279236,
785
+ "learning_rate": 0.0004944444444444445,
786
+ "loss": 0.0833,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.058424621804903494,
791
+ "grad_norm": 0.22520330548286438,
792
+ "learning_rate": 0.0004938888888888889,
793
+ "loss": 0.0767,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.05894627021387585,
798
+ "grad_norm": 0.4783564805984497,
799
+ "learning_rate": 0.0004933333333333334,
800
+ "loss": 0.0999,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.0594679186228482,
805
+ "grad_norm": 0.2565033733844757,
806
+ "learning_rate": 0.0004927777777777777,
807
+ "loss": 0.0819,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.059989567031820554,
812
+ "grad_norm": 0.19332879781723022,
813
+ "learning_rate": 0.0004922222222222222,
814
+ "loss": 0.0702,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.0605112154407929,
819
+ "grad_norm": 0.2507823705673218,
820
+ "learning_rate": 0.0004916666666666666,
821
+ "loss": 0.076,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.06103286384976526,
826
+ "grad_norm": 0.29689472913742065,
827
+ "learning_rate": 0.0004911111111111111,
828
+ "loss": 0.0748,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.06155451225873761,
833
+ "grad_norm": 0.34821203351020813,
834
+ "learning_rate": 0.0004905555555555556,
835
+ "loss": 0.0949,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.06207616066770996,
840
+ "grad_norm": 0.25025618076324463,
841
+ "learning_rate": 0.00049,
842
+ "loss": 0.0813,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.06259780907668232,
847
+ "grad_norm": 0.23138757050037384,
848
+ "learning_rate": 0.0004894444444444445,
849
+ "loss": 0.0806,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.06311945748565467,
854
+ "grad_norm": 0.25655433535575867,
855
+ "learning_rate": 0.0004888888888888889,
856
+ "loss": 0.0864,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.06364110589462701,
861
+ "grad_norm": 0.2863710820674896,
862
+ "learning_rate": 0.0004883333333333333,
863
+ "loss": 0.0659,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.06416275430359937,
868
+ "grad_norm": 0.2628318965435028,
869
+ "learning_rate": 0.0004877777777777778,
870
+ "loss": 0.0746,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.06468440271257173,
875
+ "grad_norm": 0.2095496952533722,
876
+ "learning_rate": 0.0004872222222222222,
877
+ "loss": 0.0746,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.06520605112154408,
882
+ "grad_norm": 0.25687775015830994,
883
+ "learning_rate": 0.0004866666666666667,
884
+ "loss": 0.0867,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.06572769953051644,
889
+ "grad_norm": 0.3623638153076172,
890
+ "learning_rate": 0.0004861111111111111,
891
+ "loss": 0.0859,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.06624934793948878,
896
+ "grad_norm": 0.22254744172096252,
897
+ "learning_rate": 0.0004855555555555556,
898
+ "loss": 0.0956,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.06677099634846113,
903
+ "grad_norm": 0.42705070972442627,
904
+ "learning_rate": 0.00048499999999999997,
905
+ "loss": 0.0885,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.06729264475743349,
910
+ "grad_norm": 0.23360145092010498,
911
+ "learning_rate": 0.00048444444444444446,
912
+ "loss": 0.0521,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.06781429316640585,
917
+ "grad_norm": 0.1959061473608017,
918
+ "learning_rate": 0.0004838888888888889,
919
+ "loss": 0.043,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.0683359415753782,
924
+ "grad_norm": 0.32006219029426575,
925
+ "learning_rate": 0.00048333333333333334,
926
+ "loss": 0.0942,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.06885758998435054,
931
+ "grad_norm": 0.20010985434055328,
932
+ "learning_rate": 0.0004827777777777778,
933
+ "loss": 0.0645,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.0693792383933229,
938
+ "grad_norm": 0.18007700145244598,
939
+ "learning_rate": 0.0004822222222222222,
940
+ "loss": 0.0593,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.06990088680229525,
945
+ "grad_norm": 0.23080182075500488,
946
+ "learning_rate": 0.0004816666666666667,
947
+ "loss": 0.069,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.07042253521126761,
952
+ "grad_norm": 0.16220460832118988,
953
+ "learning_rate": 0.0004811111111111111,
954
+ "loss": 0.0499,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.07094418362023996,
959
+ "grad_norm": 0.19325301051139832,
960
+ "learning_rate": 0.0004805555555555556,
961
+ "loss": 0.0616,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.0714658320292123,
966
+ "grad_norm": 0.16364900767803192,
967
+ "learning_rate": 0.00048,
968
+ "loss": 0.0612,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.07198748043818466,
973
+ "grad_norm": 0.15745937824249268,
974
+ "learning_rate": 0.00047944444444444445,
975
+ "loss": 0.0526,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.07250912884715702,
980
+ "grad_norm": 0.22706539928913116,
981
+ "learning_rate": 0.0004788888888888889,
982
+ "loss": 0.067,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.07303077725612937,
987
+ "grad_norm": 0.22147034108638763,
988
+ "learning_rate": 0.0004783333333333333,
989
+ "loss": 0.0684,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.07355242566510173,
994
+ "grad_norm": 0.2623853385448456,
995
+ "learning_rate": 0.0004777777777777778,
996
+ "loss": 0.0491,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.07407407407407407,
1001
+ "grad_norm": 0.1899435669183731,
1002
+ "learning_rate": 0.00047722222222222225,
1003
+ "loss": 0.029,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.07459572248304643,
1008
+ "grad_norm": 0.2669859826564789,
1009
+ "learning_rate": 0.0004766666666666667,
1010
+ "loss": 0.064,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.07511737089201878,
1015
+ "grad_norm": 0.18063829839229584,
1016
+ "learning_rate": 0.0004761111111111111,
1017
+ "loss": 0.0624,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.07563901930099114,
1022
+ "grad_norm": 0.22147716581821442,
1023
+ "learning_rate": 0.00047555555555555556,
1024
+ "loss": 0.0544,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.07616066770996348,
1029
+ "grad_norm": 0.30522170662879944,
1030
+ "learning_rate": 0.000475,
1031
+ "loss": 0.077,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.07668231611893583,
1036
+ "grad_norm": 0.15942497551441193,
1037
+ "learning_rate": 0.00047444444444444444,
1038
+ "loss": 0.0372,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.07720396452790819,
1043
+ "grad_norm": 0.1456826627254486,
1044
+ "learning_rate": 0.00047388888888888893,
1045
+ "loss": 0.0423,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.07772561293688054,
1050
+ "grad_norm": 0.17793269455432892,
1051
+ "learning_rate": 0.00047333333333333336,
1052
+ "loss": 0.0559,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.0782472613458529,
1057
+ "grad_norm": 0.152329221367836,
1058
+ "learning_rate": 0.0004727777777777778,
1059
+ "loss": 0.0266,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.07876890975482524,
1064
+ "grad_norm": 0.19327858090400696,
1065
+ "learning_rate": 0.00047222222222222224,
1066
+ "loss": 0.0608,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.0792905581637976,
1071
+ "grad_norm": 0.15060095489025116,
1072
+ "learning_rate": 0.0004716666666666667,
1073
+ "loss": 0.0461,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.07981220657276995,
1078
+ "grad_norm": 0.1864742785692215,
1079
+ "learning_rate": 0.0004711111111111111,
1080
+ "loss": 0.0724,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.08033385498174231,
1085
+ "grad_norm": 0.1422508805990219,
1086
+ "learning_rate": 0.00047055555555555555,
1087
+ "loss": 0.0325,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.08085550339071466,
1092
+ "grad_norm": 0.21115481853485107,
1093
+ "learning_rate": 0.00047,
1094
+ "loss": 0.0535,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.081377151799687,
1099
+ "grad_norm": 0.2197350263595581,
1100
+ "learning_rate": 0.0004694444444444445,
1101
+ "loss": 0.0703,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.08189880020865936,
1106
+ "grad_norm": 0.1608528196811676,
1107
+ "learning_rate": 0.0004688888888888889,
1108
+ "loss": 0.0447,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.08242044861763172,
1113
+ "grad_norm": 0.1445985585451126,
1114
+ "learning_rate": 0.00046833333333333335,
1115
+ "loss": 0.0469,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.08294209702660407,
1120
+ "grad_norm": 0.25215667486190796,
1121
+ "learning_rate": 0.0004677777777777778,
1122
+ "loss": 0.0709,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.08346374543557643,
1127
+ "grad_norm": 0.14391636848449707,
1128
+ "learning_rate": 0.0004672222222222222,
1129
+ "loss": 0.0457,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.08398539384454877,
1134
+ "grad_norm": 0.29619306325912476,
1135
+ "learning_rate": 0.00046666666666666666,
1136
+ "loss": 0.0765,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.08450704225352113,
1141
+ "grad_norm": 0.15701289474964142,
1142
+ "learning_rate": 0.0004661111111111111,
1143
+ "loss": 0.0418,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.08502869066249348,
1148
+ "grad_norm": 0.1698683649301529,
1149
+ "learning_rate": 0.0004655555555555556,
1150
+ "loss": 0.0294,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.08555033907146584,
1155
+ "grad_norm": 0.12165573239326477,
1156
+ "learning_rate": 0.000465,
1157
+ "loss": 0.0258,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.08607198748043818,
1162
+ "grad_norm": 0.1611219197511673,
1163
+ "learning_rate": 0.00046444444444444446,
1164
+ "loss": 0.0491,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.08659363588941053,
1169
+ "grad_norm": 0.1486036628484726,
1170
+ "learning_rate": 0.0004638888888888889,
1171
+ "loss": 0.0479,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.08711528429838289,
1176
+ "grad_norm": 0.13054965436458588,
1177
+ "learning_rate": 0.00046333333333333334,
1178
+ "loss": 0.0401,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.08763693270735524,
1183
+ "grad_norm": 0.15433131158351898,
1184
+ "learning_rate": 0.0004627777777777778,
1185
+ "loss": 0.048,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.0881585811163276,
1190
+ "grad_norm": 0.17511604726314545,
1191
+ "learning_rate": 0.0004622222222222222,
1192
+ "loss": 0.0569,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.08868022952529994,
1197
+ "grad_norm": 0.1398395150899887,
1198
+ "learning_rate": 0.0004616666666666667,
1199
+ "loss": 0.034,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.0892018779342723,
1204
+ "grad_norm": 0.15484075248241425,
1205
+ "learning_rate": 0.00046111111111111114,
1206
+ "loss": 0.0514,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.08972352634324465,
1211
+ "grad_norm": 0.17851784825325012,
1212
+ "learning_rate": 0.0004605555555555556,
1213
+ "loss": 0.0571,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.09024517475221701,
1218
+ "grad_norm": 0.18745650351047516,
1219
+ "learning_rate": 0.00046,
1220
+ "loss": 0.0523,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.09076682316118936,
1225
+ "grad_norm": 0.18322691321372986,
1226
+ "learning_rate": 0.00045944444444444445,
1227
+ "loss": 0.0642,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.0912884715701617,
1232
+ "grad_norm": 0.1173708513379097,
1233
+ "learning_rate": 0.0004588888888888889,
1234
+ "loss": 0.0267,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.09181011997913406,
1239
+ "grad_norm": 0.1754874438047409,
1240
+ "learning_rate": 0.0004583333333333333,
1241
+ "loss": 0.0657,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.09233176838810642,
1246
+ "grad_norm": 0.13830502331256866,
1247
+ "learning_rate": 0.0004577777777777778,
1248
+ "loss": 0.0433,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.09285341679707877,
1253
+ "grad_norm": 0.11174938827753067,
1254
+ "learning_rate": 0.0004572222222222222,
1255
+ "loss": 0.04,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.09337506520605113,
1260
+ "grad_norm": 0.1829378753900528,
1261
+ "learning_rate": 0.0004566666666666667,
1262
+ "loss": 0.0453,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.09389671361502347,
1267
+ "grad_norm": 0.10748015344142914,
1268
+ "learning_rate": 0.0004561111111111111,
1269
+ "loss": 0.05,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.09441836202399582,
1274
+ "grad_norm": 0.1160806268453598,
1275
+ "learning_rate": 0.00045555555555555556,
1276
+ "loss": 0.0245,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.09494001043296818,
1281
+ "grad_norm": 0.12387479841709137,
1282
+ "learning_rate": 0.000455,
1283
+ "loss": 0.0259,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.09546165884194054,
1288
+ "grad_norm": 0.1586403250694275,
1289
+ "learning_rate": 0.00045444444444444444,
1290
+ "loss": 0.0378,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.09598330725091289,
1295
+ "grad_norm": 0.18905822932720184,
1296
+ "learning_rate": 0.00045388888888888893,
1297
+ "loss": 0.0484,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.09650495565988523,
1302
+ "grad_norm": 0.17541544139385223,
1303
+ "learning_rate": 0.0004533333333333333,
1304
+ "loss": 0.0503,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.09702660406885759,
1309
+ "grad_norm": 0.1083071306347847,
1310
+ "learning_rate": 0.0004527777777777778,
1311
+ "loss": 0.0439,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.09754825247782994,
1316
+ "grad_norm": 0.10464104264974594,
1317
+ "learning_rate": 0.00045222222222222224,
1318
+ "loss": 0.0271,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.0980699008868023,
1323
+ "grad_norm": 0.18022054433822632,
1324
+ "learning_rate": 0.0004516666666666667,
1325
+ "loss": 0.0589,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.09859154929577464,
1330
+ "grad_norm": 0.18715251982212067,
1331
+ "learning_rate": 0.0004511111111111111,
1332
+ "loss": 0.0489,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.099113197704747,
1337
+ "grad_norm": 0.10440787672996521,
1338
+ "learning_rate": 0.00045055555555555555,
1339
+ "loss": 0.0221,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.09963484611371935,
1344
+ "grad_norm": 0.11525921523571014,
1345
+ "learning_rate": 0.00045000000000000004,
1346
+ "loss": 0.0427,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.10015649452269171,
1351
+ "grad_norm": 0.1573028564453125,
1352
+ "learning_rate": 0.0004494444444444444,
1353
+ "loss": 0.04,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.10067814293166406,
1358
+ "grad_norm": 0.15942253172397614,
1359
+ "learning_rate": 0.0004488888888888889,
1360
+ "loss": 0.045,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.1011997913406364,
1365
+ "grad_norm": 0.2997572422027588,
1366
+ "learning_rate": 0.0004483333333333333,
1367
+ "loss": 0.062,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.10172143974960876,
1372
+ "grad_norm": 0.1859196424484253,
1373
+ "learning_rate": 0.0004477777777777778,
1374
+ "loss": 0.0496,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.10224308815858112,
1379
+ "grad_norm": 0.1265893131494522,
1380
+ "learning_rate": 0.0004472222222222222,
1381
+ "loss": 0.0457,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.10276473656755347,
1386
+ "grad_norm": 0.16036029160022736,
1387
+ "learning_rate": 0.00044666666666666666,
1388
+ "loss": 0.046,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.10328638497652583,
1393
+ "grad_norm": 0.10421448945999146,
1394
+ "learning_rate": 0.00044611111111111115,
1395
+ "loss": 0.033,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.10380803338549817,
1400
+ "grad_norm": 0.12321974337100983,
1401
+ "learning_rate": 0.00044555555555555554,
1402
+ "loss": 0.0458,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.10432968179447052,
1407
+ "grad_norm": 0.13863791525363922,
1408
+ "learning_rate": 0.00044500000000000003,
1409
+ "loss": 0.0221,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.10485133020344288,
1414
+ "grad_norm": 0.11896353214979172,
1415
+ "learning_rate": 0.0004444444444444444,
1416
+ "loss": 0.0477,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.10537297861241524,
1421
+ "grad_norm": 0.1473105251789093,
1422
+ "learning_rate": 0.0004438888888888889,
1423
+ "loss": 0.056,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.10589462702138759,
1428
+ "grad_norm": 0.15058237314224243,
1429
+ "learning_rate": 0.00044333333333333334,
1430
+ "loss": 0.0477,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.10641627543035993,
1435
+ "grad_norm": 0.10770102590322495,
1436
+ "learning_rate": 0.0004427777777777778,
1437
+ "loss": 0.0316,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 0.10693792383933229,
1442
+ "grad_norm": 0.13766999542713165,
1443
+ "learning_rate": 0.00044222222222222227,
1444
+ "loss": 0.041,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 0.10745957224830464,
1449
+ "grad_norm": 0.11786706745624542,
1450
+ "learning_rate": 0.00044166666666666665,
1451
+ "loss": 0.0302,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 0.107981220657277,
1456
+ "grad_norm": 0.10209888964891434,
1457
+ "learning_rate": 0.00044111111111111114,
1458
+ "loss": 0.0396,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 0.10850286906624934,
1463
+ "grad_norm": 0.13609950244426727,
1464
+ "learning_rate": 0.0004405555555555555,
1465
+ "loss": 0.0394,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 0.1090245174752217,
1470
+ "grad_norm": 0.11915361881256104,
1471
+ "learning_rate": 0.00044,
1472
+ "loss": 0.0421,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 0.10954616588419405,
1477
+ "grad_norm": 0.11170439422130585,
1478
+ "learning_rate": 0.0004394444444444445,
1479
+ "loss": 0.0395,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 0.11006781429316641,
1484
+ "grad_norm": 0.12584055960178375,
1485
+ "learning_rate": 0.0004388888888888889,
1486
+ "loss": 0.0534,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 0.11058946270213876,
1491
+ "grad_norm": 0.1454746276140213,
1492
+ "learning_rate": 0.0004383333333333334,
1493
+ "loss": 0.0469,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 0.1111111111111111,
1498
+ "grad_norm": 0.10297106951475143,
1499
+ "learning_rate": 0.00043777777777777776,
1500
+ "loss": 0.0359,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 0.11163275952008346,
1505
+ "grad_norm": 0.10994141548871994,
1506
+ "learning_rate": 0.00043722222222222225,
1507
+ "loss": 0.0404,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 0.11215440792905582,
1512
+ "grad_norm": 0.13165079057216644,
1513
+ "learning_rate": 0.00043666666666666664,
1514
+ "loss": 0.0475,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 0.11267605633802817,
1519
+ "grad_norm": 0.11115416139364243,
1520
+ "learning_rate": 0.00043611111111111113,
1521
+ "loss": 0.0351,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 0.11319770474700053,
1526
+ "grad_norm": 0.15927758812904358,
1527
+ "learning_rate": 0.0004355555555555555,
1528
+ "loss": 0.0468,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 0.11371935315597287,
1533
+ "grad_norm": 0.0941813513636589,
1534
+ "learning_rate": 0.000435,
1535
+ "loss": 0.0337,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 0.11424100156494522,
1540
+ "grad_norm": 0.10850685834884644,
1541
+ "learning_rate": 0.0004344444444444445,
1542
+ "loss": 0.0211,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 0.11476264997391758,
1547
+ "grad_norm": 0.0790611058473587,
1548
+ "learning_rate": 0.0004338888888888889,
1549
+ "loss": 0.0196,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 0.11528429838288994,
1554
+ "grad_norm": 0.10849782079458237,
1555
+ "learning_rate": 0.00043333333333333337,
1556
+ "loss": 0.04,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 0.11580594679186229,
1561
+ "grad_norm": 0.09607880562543869,
1562
+ "learning_rate": 0.00043277777777777775,
1563
+ "loss": 0.0291,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 0.11632759520083463,
1568
+ "grad_norm": 0.17959930002689362,
1569
+ "learning_rate": 0.00043222222222222224,
1570
+ "loss": 0.0426,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 0.11684924360980699,
1575
+ "grad_norm": 0.08865644782781601,
1576
+ "learning_rate": 0.0004316666666666667,
1577
+ "loss": 0.0321,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 0.11737089201877934,
1582
+ "grad_norm": 0.17324934899806976,
1583
+ "learning_rate": 0.0004311111111111111,
1584
+ "loss": 0.0537,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 0.1178925404277517,
1589
+ "grad_norm": 0.10226263850927353,
1590
+ "learning_rate": 0.0004305555555555556,
1591
+ "loss": 0.0342,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 0.11841418883672405,
1596
+ "grad_norm": 0.10456152260303497,
1597
+ "learning_rate": 0.00043,
1598
+ "loss": 0.039,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 0.1189358372456964,
1603
+ "grad_norm": 0.10196290910243988,
1604
+ "learning_rate": 0.0004294444444444445,
1605
+ "loss": 0.0329,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 0.11945748565466875,
1610
+ "grad_norm": 0.12004778534173965,
1611
+ "learning_rate": 0.00042888888888888886,
1612
+ "loss": 0.0434,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 0.11997913406364111,
1617
+ "grad_norm": 0.10152442753314972,
1618
+ "learning_rate": 0.00042833333333333335,
1619
+ "loss": 0.0305,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 0.12050078247261346,
1624
+ "grad_norm": 0.1072554886341095,
1625
+ "learning_rate": 0.0004277777777777778,
1626
+ "loss": 0.0407,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 0.1210224308815858,
1631
+ "grad_norm": 0.08478479087352753,
1632
+ "learning_rate": 0.00042722222222222223,
1633
+ "loss": 0.0375,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 0.12154407929055816,
1638
+ "grad_norm": 0.11901957541704178,
1639
+ "learning_rate": 0.0004266666666666667,
1640
+ "loss": 0.0281,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 0.12206572769953052,
1645
+ "grad_norm": 0.097981758415699,
1646
+ "learning_rate": 0.0004261111111111111,
1647
+ "loss": 0.0365,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 0.12258737610850287,
1652
+ "grad_norm": 0.08464547991752625,
1653
+ "learning_rate": 0.0004255555555555556,
1654
+ "loss": 0.0227,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 0.12310902451747523,
1659
+ "grad_norm": 0.18886807560920715,
1660
+ "learning_rate": 0.000425,
1661
+ "loss": 0.0494,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 0.12363067292644757,
1666
+ "grad_norm": 0.08432997763156891,
1667
+ "learning_rate": 0.00042444444444444447,
1668
+ "loss": 0.031,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 0.12415232133541992,
1673
+ "grad_norm": 0.24738061428070068,
1674
+ "learning_rate": 0.0004238888888888889,
1675
+ "loss": 0.0611,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 0.12467396974439228,
1680
+ "grad_norm": 0.11955960839986801,
1681
+ "learning_rate": 0.00042333333333333334,
1682
+ "loss": 0.0481,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 0.12519561815336464,
1687
+ "grad_norm": 0.132662832736969,
1688
+ "learning_rate": 0.0004227777777777778,
1689
+ "loss": 0.0432,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 0.12571726656233698,
1694
+ "grad_norm": 0.08496639877557755,
1695
+ "learning_rate": 0.0004222222222222222,
1696
+ "loss": 0.0328,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 0.12623891497130935,
1701
+ "grad_norm": 0.13830861449241638,
1702
+ "learning_rate": 0.0004216666666666667,
1703
+ "loss": 0.0336,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 0.1267605633802817,
1708
+ "grad_norm": 0.12200845032930374,
1709
+ "learning_rate": 0.0004211111111111111,
1710
+ "loss": 0.0346,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 0.12728221178925403,
1715
+ "grad_norm": 0.10438041388988495,
1716
+ "learning_rate": 0.0004205555555555556,
1717
+ "loss": 0.039,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 0.1278038601982264,
1722
+ "grad_norm": 0.10238846391439438,
1723
+ "learning_rate": 0.00042,
1724
+ "loss": 0.0442,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 0.12832550860719874,
1729
+ "grad_norm": 0.10930721461772919,
1730
+ "learning_rate": 0.00041944444444444445,
1731
+ "loss": 0.0426,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 0.1288471570161711,
1736
+ "grad_norm": 0.09867265820503235,
1737
+ "learning_rate": 0.0004188888888888889,
1738
+ "loss": 0.0402,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 0.12936880542514345,
1743
+ "grad_norm": 0.1137848049402237,
1744
+ "learning_rate": 0.00041833333333333333,
1745
+ "loss": 0.0278,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 0.1298904538341158,
1750
+ "grad_norm": 0.1364007592201233,
1751
+ "learning_rate": 0.0004177777777777778,
1752
+ "loss": 0.0437,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 0.13041210224308816,
1757
+ "grad_norm": 0.09385659545660019,
1758
+ "learning_rate": 0.0004172222222222222,
1759
+ "loss": 0.0353,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 0.1309337506520605,
1764
+ "grad_norm": 0.1302153617143631,
1765
+ "learning_rate": 0.0004166666666666667,
1766
+ "loss": 0.0287,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 0.13145539906103287,
1771
+ "grad_norm": 0.09976278990507126,
1772
+ "learning_rate": 0.00041611111111111113,
1773
+ "loss": 0.0381,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 0.13197704747000522,
1778
+ "grad_norm": 0.0966271236538887,
1779
+ "learning_rate": 0.00041555555555555557,
1780
+ "loss": 0.0204,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 0.13249869587897756,
1785
+ "grad_norm": 0.0773528590798378,
1786
+ "learning_rate": 0.000415,
1787
+ "loss": 0.0285,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 0.13302034428794993,
1792
+ "grad_norm": 0.2350674420595169,
1793
+ "learning_rate": 0.00041444444444444444,
1794
+ "loss": 0.0511,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 0.13354199269692227,
1799
+ "grad_norm": 0.08375384658575058,
1800
+ "learning_rate": 0.0004138888888888889,
1801
+ "loss": 0.0341,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 0.13406364110589464,
1806
+ "grad_norm": 0.09229125827550888,
1807
+ "learning_rate": 0.0004133333333333333,
1808
+ "loss": 0.0329,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 0.13458528951486698,
1813
+ "grad_norm": 0.08750821650028229,
1814
+ "learning_rate": 0.0004127777777777778,
1815
+ "loss": 0.0283,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 0.13510693792383932,
1820
+ "grad_norm": 0.075618676841259,
1821
+ "learning_rate": 0.00041222222222222224,
1822
+ "loss": 0.0291,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 0.1356285863328117,
1827
+ "grad_norm": 0.16954250633716583,
1828
+ "learning_rate": 0.0004116666666666667,
1829
+ "loss": 0.0441,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 0.13615023474178403,
1834
+ "grad_norm": 0.07529555261135101,
1835
+ "learning_rate": 0.0004111111111111111,
1836
+ "loss": 0.0139,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 0.1366718831507564,
1841
+ "grad_norm": 0.08884407579898834,
1842
+ "learning_rate": 0.00041055555555555555,
1843
+ "loss": 0.0299,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 0.13719353155972874,
1848
+ "grad_norm": 0.09607396274805069,
1849
+ "learning_rate": 0.00041,
1850
+ "loss": 0.0337,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 0.13771517996870108,
1855
+ "grad_norm": 0.08453882485628128,
1856
+ "learning_rate": 0.00040944444444444443,
1857
+ "loss": 0.0315,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 0.13823682837767345,
1862
+ "grad_norm": 0.09629228711128235,
1863
+ "learning_rate": 0.0004088888888888889,
1864
+ "loss": 0.0181,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 0.1387584767866458,
1869
+ "grad_norm": 0.07212290167808533,
1870
+ "learning_rate": 0.00040833333333333336,
1871
+ "loss": 0.0262,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 0.13928012519561817,
1876
+ "grad_norm": 0.09192827343940735,
1877
+ "learning_rate": 0.0004077777777777778,
1878
+ "loss": 0.018,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 0.1398017736045905,
1883
+ "grad_norm": 0.10876122117042542,
1884
+ "learning_rate": 0.00040722222222222223,
1885
+ "loss": 0.0316,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 0.14032342201356285,
1890
+ "grad_norm": 0.10796765238046646,
1891
+ "learning_rate": 0.00040666666666666667,
1892
+ "loss": 0.0323,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 0.14084507042253522,
1897
+ "grad_norm": 0.08297892659902573,
1898
+ "learning_rate": 0.0004061111111111111,
1899
+ "loss": 0.0244,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 0.14136671883150756,
1904
+ "grad_norm": 0.09534858912229538,
1905
+ "learning_rate": 0.00040555555555555554,
1906
+ "loss": 0.0279,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 0.14188836724047993,
1911
+ "grad_norm": 0.07854770123958588,
1912
+ "learning_rate": 0.00040500000000000003,
1913
+ "loss": 0.032,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 0.14241001564945227,
1918
+ "grad_norm": 0.16025401651859283,
1919
+ "learning_rate": 0.00040444444444444447,
1920
+ "loss": 0.0413,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 0.1429316640584246,
1925
+ "grad_norm": 0.07919424772262573,
1926
+ "learning_rate": 0.0004038888888888889,
1927
+ "loss": 0.0277,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 0.14345331246739698,
1932
+ "grad_norm": 0.07335282117128372,
1933
+ "learning_rate": 0.00040333333333333334,
1934
+ "loss": 0.0363,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 0.14397496087636932,
1939
+ "grad_norm": 0.1280767321586609,
1940
+ "learning_rate": 0.0004027777777777778,
1941
+ "loss": 0.0402,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 0.1444966092853417,
1946
+ "grad_norm": 0.11371007561683655,
1947
+ "learning_rate": 0.0004022222222222222,
1948
+ "loss": 0.0312,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 0.14501825769431403,
1953
+ "grad_norm": 0.12229876220226288,
1954
+ "learning_rate": 0.00040166666666666665,
1955
+ "loss": 0.0357,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 0.14553990610328638,
1960
+ "grad_norm": 0.11436333507299423,
1961
+ "learning_rate": 0.0004011111111111111,
1962
+ "loss": 0.0135,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 0.14606155451225875,
1967
+ "grad_norm": 0.08084696531295776,
1968
+ "learning_rate": 0.0004005555555555556,
1969
+ "loss": 0.0302,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 0.1465832029212311,
1974
+ "grad_norm": 0.09421739727258682,
1975
+ "learning_rate": 0.0004,
1976
+ "loss": 0.0376,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 0.14710485133020346,
1981
+ "grad_norm": 0.0744849219918251,
1982
+ "learning_rate": 0.00039944444444444446,
1983
+ "loss": 0.0291,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 0.1476264997391758,
1988
+ "grad_norm": 0.06754301488399506,
1989
+ "learning_rate": 0.0003988888888888889,
1990
+ "loss": 0.0262,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 0.14814814814814814,
1995
+ "grad_norm": 0.06215747445821762,
1996
+ "learning_rate": 0.00039833333333333333,
1997
+ "loss": 0.0223,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 0.1486697965571205,
2002
+ "grad_norm": 0.10289556533098221,
2003
+ "learning_rate": 0.00039777777777777777,
2004
+ "loss": 0.0401,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 0.14919144496609285,
2009
+ "grad_norm": 0.10723885893821716,
2010
+ "learning_rate": 0.0003972222222222222,
2011
+ "loss": 0.018,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 0.1497130933750652,
2016
+ "grad_norm": 0.12683100998401642,
2017
+ "learning_rate": 0.0003966666666666667,
2018
+ "loss": 0.0155,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 0.15023474178403756,
2023
+ "grad_norm": 0.10709403455257416,
2024
+ "learning_rate": 0.00039611111111111113,
2025
+ "loss": 0.0186,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 0.1507563901930099,
2030
+ "grad_norm": 0.09857751429080963,
2031
+ "learning_rate": 0.00039555555555555557,
2032
+ "loss": 0.0311,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 0.15127803860198227,
2037
+ "grad_norm": 0.07990946620702744,
2038
+ "learning_rate": 0.000395,
2039
+ "loss": 0.032,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 0.15179968701095461,
2044
+ "grad_norm": 0.06873098760843277,
2045
+ "learning_rate": 0.00039444444444444444,
2046
+ "loss": 0.0163,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 0.15232133541992696,
2051
+ "grad_norm": 0.0788077712059021,
2052
+ "learning_rate": 0.00039388888888888893,
2053
+ "loss": 0.0319,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 0.15284298382889933,
2058
+ "grad_norm": 0.08789033442735672,
2059
+ "learning_rate": 0.0003933333333333333,
2060
+ "loss": 0.0352,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 0.15336463223787167,
2065
+ "grad_norm": 0.10574653744697571,
2066
+ "learning_rate": 0.0003927777777777778,
2067
+ "loss": 0.0411,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 0.15388628064684404,
2072
+ "grad_norm": 0.08198726177215576,
2073
+ "learning_rate": 0.00039222222222222225,
2074
+ "loss": 0.0286,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 0.15440792905581638,
2079
+ "grad_norm": 0.2811417579650879,
2080
+ "learning_rate": 0.0003916666666666667,
2081
+ "loss": 0.0508,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 0.15492957746478872,
2086
+ "grad_norm": 0.1203279122710228,
2087
+ "learning_rate": 0.0003911111111111111,
2088
+ "loss": 0.0384,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 0.1554512258737611,
2093
+ "grad_norm": 0.08802422881126404,
2094
+ "learning_rate": 0.00039055555555555556,
2095
+ "loss": 0.0305,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 0.15597287428273343,
2100
+ "grad_norm": 0.05368930101394653,
2101
+ "learning_rate": 0.00039000000000000005,
2102
+ "loss": 0.0167,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 0.1564945226917058,
2107
+ "grad_norm": 0.16041633486747742,
2108
+ "learning_rate": 0.00038944444444444443,
2109
+ "loss": 0.047,
2110
+ "step": 300
2111
+ },
2112
+ {
2113
+ "epoch": 0.15701617110067814,
2114
+ "grad_norm": 0.06771723926067352,
2115
+ "learning_rate": 0.0003888888888888889,
2116
+ "loss": 0.0242,
2117
+ "step": 301
2118
+ },
2119
+ {
2120
+ "epoch": 0.15753781950965048,
2121
+ "grad_norm": 0.09745685011148453,
2122
+ "learning_rate": 0.0003883333333333333,
2123
+ "loss": 0.0121,
2124
+ "step": 302
2125
+ },
2126
+ {
2127
+ "epoch": 0.15805946791862285,
2128
+ "grad_norm": 0.1079089567065239,
2129
+ "learning_rate": 0.0003877777777777778,
2130
+ "loss": 0.0331,
2131
+ "step": 303
2132
+ },
2133
+ {
2134
+ "epoch": 0.1585811163275952,
2135
+ "grad_norm": 0.07800073176622391,
2136
+ "learning_rate": 0.00038722222222222223,
2137
+ "loss": 0.0325,
2138
+ "step": 304
2139
+ },
2140
+ {
2141
+ "epoch": 0.15910276473656756,
2142
+ "grad_norm": 0.13546329736709595,
2143
+ "learning_rate": 0.00038666666666666667,
2144
+ "loss": 0.0296,
2145
+ "step": 305
2146
+ },
2147
+ {
2148
+ "epoch": 0.1596244131455399,
2149
+ "grad_norm": 0.0735045000910759,
2150
+ "learning_rate": 0.00038611111111111116,
2151
+ "loss": 0.0275,
2152
+ "step": 306
2153
+ },
2154
+ {
2155
+ "epoch": 0.16014606155451225,
2156
+ "grad_norm": 0.056763097643852234,
2157
+ "learning_rate": 0.00038555555555555554,
2158
+ "loss": 0.025,
2159
+ "step": 307
2160
+ },
2161
+ {
2162
+ "epoch": 0.16066770996348462,
2163
+ "grad_norm": 0.0723307803273201,
2164
+ "learning_rate": 0.00038500000000000003,
2165
+ "loss": 0.0269,
2166
+ "step": 308
2167
+ },
2168
+ {
2169
+ "epoch": 0.16118935837245696,
2170
+ "grad_norm": 0.07295756787061691,
2171
+ "learning_rate": 0.0003844444444444444,
2172
+ "loss": 0.0224,
2173
+ "step": 309
2174
+ },
2175
+ {
2176
+ "epoch": 0.16171100678142933,
2177
+ "grad_norm": 0.1010420173406601,
2178
+ "learning_rate": 0.0003838888888888889,
2179
+ "loss": 0.0154,
2180
+ "step": 310
2181
+ },
2182
+ {
2183
+ "epoch": 0.16223265519040167,
2184
+ "grad_norm": 0.10790162533521652,
2185
+ "learning_rate": 0.00038333333333333334,
2186
+ "loss": 0.0334,
2187
+ "step": 311
2188
+ },
2189
+ {
2190
+ "epoch": 0.162754303599374,
2191
+ "grad_norm": 0.06171411648392677,
2192
+ "learning_rate": 0.0003827777777777778,
2193
+ "loss": 0.026,
2194
+ "step": 312
2195
+ },
2196
+ {
2197
+ "epoch": 0.16327595200834638,
2198
+ "grad_norm": 0.0646505281329155,
2199
+ "learning_rate": 0.0003822222222222223,
2200
+ "loss": 0.0283,
2201
+ "step": 313
2202
+ },
2203
+ {
2204
+ "epoch": 0.16379760041731872,
2205
+ "grad_norm": 0.1241549476981163,
2206
+ "learning_rate": 0.00038166666666666666,
2207
+ "loss": 0.0433,
2208
+ "step": 314
2209
+ },
2210
+ {
2211
+ "epoch": 0.1643192488262911,
2212
+ "grad_norm": 0.08475686609745026,
2213
+ "learning_rate": 0.00038111111111111115,
2214
+ "loss": 0.0264,
2215
+ "step": 315
2216
+ },
2217
+ {
2218
+ "epoch": 0.16484089723526343,
2219
+ "grad_norm": 0.1006927415728569,
2220
+ "learning_rate": 0.00038055555555555553,
2221
+ "loss": 0.0373,
2222
+ "step": 316
2223
+ },
2224
+ {
2225
+ "epoch": 0.16536254564423578,
2226
+ "grad_norm": 0.08395830541849136,
2227
+ "learning_rate": 0.00038,
2228
+ "loss": 0.0151,
2229
+ "step": 317
2230
+ },
2231
+ {
2232
+ "epoch": 0.16588419405320814,
2233
+ "grad_norm": 0.05780460685491562,
2234
+ "learning_rate": 0.0003794444444444444,
2235
+ "loss": 0.018,
2236
+ "step": 318
2237
+ },
2238
+ {
2239
+ "epoch": 0.1664058424621805,
2240
+ "grad_norm": 0.08385057002305984,
2241
+ "learning_rate": 0.0003788888888888889,
2242
+ "loss": 0.0347,
2243
+ "step": 319
2244
+ },
2245
+ {
2246
+ "epoch": 0.16692749087115286,
2247
+ "grad_norm": 0.0629425197839737,
2248
+ "learning_rate": 0.0003783333333333334,
2249
+ "loss": 0.0288,
2250
+ "step": 320
2251
+ },
2252
+ {
2253
+ "epoch": 0.1674491392801252,
2254
+ "grad_norm": 0.07353231310844421,
2255
+ "learning_rate": 0.00037777777777777777,
2256
+ "loss": 0.0318,
2257
+ "step": 321
2258
+ },
2259
+ {
2260
+ "epoch": 0.16797078768909754,
2261
+ "grad_norm": 0.06632209569215775,
2262
+ "learning_rate": 0.00037722222222222226,
2263
+ "loss": 0.0286,
2264
+ "step": 322
2265
+ },
2266
+ {
2267
+ "epoch": 0.1684924360980699,
2268
+ "grad_norm": 0.10224422067403793,
2269
+ "learning_rate": 0.00037666666666666664,
2270
+ "loss": 0.0287,
2271
+ "step": 323
2272
+ },
2273
+ {
2274
+ "epoch": 0.16901408450704225,
2275
+ "grad_norm": 0.07615455985069275,
2276
+ "learning_rate": 0.00037611111111111113,
2277
+ "loss": 0.0245,
2278
+ "step": 324
2279
+ },
2280
+ {
2281
+ "epoch": 0.16953573291601462,
2282
+ "grad_norm": 0.08341842144727707,
2283
+ "learning_rate": 0.0003755555555555555,
2284
+ "loss": 0.0272,
2285
+ "step": 325
2286
+ },
2287
+ {
2288
+ "epoch": 0.17005738132498696,
2289
+ "grad_norm": 0.06340507417917252,
2290
+ "learning_rate": 0.000375,
2291
+ "loss": 0.0251,
2292
+ "step": 326
2293
+ },
2294
+ {
2295
+ "epoch": 0.1705790297339593,
2296
+ "grad_norm": 0.05245117098093033,
2297
+ "learning_rate": 0.0003744444444444445,
2298
+ "loss": 0.016,
2299
+ "step": 327
2300
+ },
2301
+ {
2302
+ "epoch": 0.17110067814293167,
2303
+ "grad_norm": 0.07821597903966904,
2304
+ "learning_rate": 0.0003738888888888889,
2305
+ "loss": 0.0166,
2306
+ "step": 328
2307
+ },
2308
+ {
2309
+ "epoch": 0.17162232655190401,
2310
+ "grad_norm": 0.05091237649321556,
2311
+ "learning_rate": 0.0003733333333333334,
2312
+ "loss": 0.0169,
2313
+ "step": 329
2314
+ },
2315
+ {
2316
+ "epoch": 0.17214397496087636,
2317
+ "grad_norm": 0.11584059149026871,
2318
+ "learning_rate": 0.00037277777777777776,
2319
+ "loss": 0.0424,
2320
+ "step": 330
2321
+ },
2322
+ {
2323
+ "epoch": 0.17266562336984873,
2324
+ "grad_norm": 0.08996029943227768,
2325
+ "learning_rate": 0.00037222222222222225,
2326
+ "loss": 0.0287,
2327
+ "step": 331
2328
+ },
2329
+ {
2330
+ "epoch": 0.17318727177882107,
2331
+ "grad_norm": 0.06258998066186905,
2332
+ "learning_rate": 0.00037166666666666663,
2333
+ "loss": 0.0243,
2334
+ "step": 332
2335
+ },
2336
+ {
2337
+ "epoch": 0.17370892018779344,
2338
+ "grad_norm": 0.06734970957040787,
2339
+ "learning_rate": 0.0003711111111111111,
2340
+ "loss": 0.0294,
2341
+ "step": 333
2342
+ },
2343
+ {
2344
+ "epoch": 0.17423056859676578,
2345
+ "grad_norm": 0.06081216409802437,
2346
+ "learning_rate": 0.0003705555555555556,
2347
+ "loss": 0.0262,
2348
+ "step": 334
2349
+ },
2350
+ {
2351
+ "epoch": 0.17475221700573812,
2352
+ "grad_norm": 0.06397537142038345,
2353
+ "learning_rate": 0.00037,
2354
+ "loss": 0.0161,
2355
+ "step": 335
2356
+ },
2357
+ {
2358
+ "epoch": 0.1752738654147105,
2359
+ "grad_norm": 0.07987434417009354,
2360
+ "learning_rate": 0.0003694444444444445,
2361
+ "loss": 0.0301,
2362
+ "step": 336
2363
+ },
2364
+ {
2365
+ "epoch": 0.17579551382368283,
2366
+ "grad_norm": 0.09395250678062439,
2367
+ "learning_rate": 0.00036888888888888887,
2368
+ "loss": 0.0289,
2369
+ "step": 337
2370
+ },
2371
+ {
2372
+ "epoch": 0.1763171622326552,
2373
+ "grad_norm": 0.05801301822066307,
2374
+ "learning_rate": 0.00036833333333333336,
2375
+ "loss": 0.0326,
2376
+ "step": 338
2377
+ },
2378
+ {
2379
+ "epoch": 0.17683881064162754,
2380
+ "grad_norm": 0.06285756826400757,
2381
+ "learning_rate": 0.00036777777777777774,
2382
+ "loss": 0.0235,
2383
+ "step": 339
2384
+ },
2385
+ {
2386
+ "epoch": 0.17736045905059988,
2387
+ "grad_norm": 0.06429009139537811,
2388
+ "learning_rate": 0.00036722222222222223,
2389
+ "loss": 0.0136,
2390
+ "step": 340
2391
+ },
2392
+ {
2393
+ "epoch": 0.17788210745957225,
2394
+ "grad_norm": 0.05570930242538452,
2395
+ "learning_rate": 0.00036666666666666667,
2396
+ "loss": 0.0205,
2397
+ "step": 341
2398
+ },
2399
+ {
2400
+ "epoch": 0.1784037558685446,
2401
+ "grad_norm": 0.061478108167648315,
2402
+ "learning_rate": 0.0003661111111111111,
2403
+ "loss": 0.026,
2404
+ "step": 342
2405
+ },
2406
+ {
2407
+ "epoch": 0.17892540427751696,
2408
+ "grad_norm": 0.07520420104265213,
2409
+ "learning_rate": 0.0003655555555555556,
2410
+ "loss": 0.0265,
2411
+ "step": 343
2412
+ },
2413
+ {
2414
+ "epoch": 0.1794470526864893,
2415
+ "grad_norm": 0.047426123172044754,
2416
+ "learning_rate": 0.000365,
2417
+ "loss": 0.0144,
2418
+ "step": 344
2419
+ },
2420
+ {
2421
+ "epoch": 0.17996870109546165,
2422
+ "grad_norm": 0.09971431642770767,
2423
+ "learning_rate": 0.00036444444444444447,
2424
+ "loss": 0.0359,
2425
+ "step": 345
2426
+ },
2427
+ {
2428
+ "epoch": 0.18049034950443402,
2429
+ "grad_norm": 0.0507560633122921,
2430
+ "learning_rate": 0.00036388888888888886,
2431
+ "loss": 0.0203,
2432
+ "step": 346
2433
+ },
2434
+ {
2435
+ "epoch": 0.18101199791340636,
2436
+ "grad_norm": 0.09610850363969803,
2437
+ "learning_rate": 0.00036333333333333335,
2438
+ "loss": 0.0352,
2439
+ "step": 347
2440
+ },
2441
+ {
2442
+ "epoch": 0.18153364632237873,
2443
+ "grad_norm": 0.04846423119306564,
2444
+ "learning_rate": 0.0003627777777777778,
2445
+ "loss": 0.0162,
2446
+ "step": 348
2447
+ },
2448
+ {
2449
+ "epoch": 0.18205529473135107,
2450
+ "grad_norm": 0.15771976113319397,
2451
+ "learning_rate": 0.0003622222222222222,
2452
+ "loss": 0.0323,
2453
+ "step": 349
2454
+ },
2455
+ {
2456
+ "epoch": 0.1825769431403234,
2457
+ "grad_norm": 0.07306705415248871,
2458
+ "learning_rate": 0.0003616666666666667,
2459
+ "loss": 0.0217,
2460
+ "step": 350
2461
+ },
2462
+ {
2463
+ "epoch": 0.18309859154929578,
2464
+ "grad_norm": 0.05630479007959366,
2465
+ "learning_rate": 0.0003611111111111111,
2466
+ "loss": 0.0149,
2467
+ "step": 351
2468
+ },
2469
+ {
2470
+ "epoch": 0.18362023995826812,
2471
+ "grad_norm": 0.08934023231267929,
2472
+ "learning_rate": 0.0003605555555555556,
2473
+ "loss": 0.0113,
2474
+ "step": 352
2475
+ },
2476
+ {
2477
+ "epoch": 0.1841418883672405,
2478
+ "grad_norm": 0.1724640429019928,
2479
+ "learning_rate": 0.00035999999999999997,
2480
+ "loss": 0.0435,
2481
+ "step": 353
2482
+ },
2483
+ {
2484
+ "epoch": 0.18466353677621283,
2485
+ "grad_norm": 0.06963273137807846,
2486
+ "learning_rate": 0.00035944444444444446,
2487
+ "loss": 0.0307,
2488
+ "step": 354
2489
+ },
2490
+ {
2491
+ "epoch": 0.18518518518518517,
2492
+ "grad_norm": 0.06084301322698593,
2493
+ "learning_rate": 0.0003588888888888889,
2494
+ "loss": 0.0306,
2495
+ "step": 355
2496
+ },
2497
+ {
2498
+ "epoch": 0.18570683359415754,
2499
+ "grad_norm": 0.07648872584104538,
2500
+ "learning_rate": 0.00035833333333333333,
2501
+ "loss": 0.0271,
2502
+ "step": 356
2503
+ },
2504
+ {
2505
+ "epoch": 0.18622848200312989,
2506
+ "grad_norm": 0.07619331032037735,
2507
+ "learning_rate": 0.00035777777777777777,
2508
+ "loss": 0.0171,
2509
+ "step": 357
2510
+ },
2511
+ {
2512
+ "epoch": 0.18675013041210226,
2513
+ "grad_norm": 0.08520349115133286,
2514
+ "learning_rate": 0.0003572222222222222,
2515
+ "loss": 0.0284,
2516
+ "step": 358
2517
+ },
2518
+ {
2519
+ "epoch": 0.1872717788210746,
2520
+ "grad_norm": 0.057310912758111954,
2521
+ "learning_rate": 0.0003566666666666667,
2522
+ "loss": 0.0223,
2523
+ "step": 359
2524
+ },
2525
+ {
2526
+ "epoch": 0.18779342723004694,
2527
+ "grad_norm": 0.08222941309213638,
2528
+ "learning_rate": 0.0003561111111111111,
2529
+ "loss": 0.0296,
2530
+ "step": 360
2531
+ },
2532
+ {
2533
+ "epoch": 0.1883150756390193,
2534
+ "grad_norm": 0.08427579700946808,
2535
+ "learning_rate": 0.00035555555555555557,
2536
+ "loss": 0.031,
2537
+ "step": 361
2538
+ },
2539
+ {
2540
+ "epoch": 0.18883672404799165,
2541
+ "grad_norm": 0.06189948692917824,
2542
+ "learning_rate": 0.000355,
2543
+ "loss": 0.0273,
2544
+ "step": 362
2545
+ },
2546
+ {
2547
+ "epoch": 0.18935837245696402,
2548
+ "grad_norm": 0.07053495943546295,
2549
+ "learning_rate": 0.00035444444444444445,
2550
+ "loss": 0.0197,
2551
+ "step": 363
2552
+ },
2553
+ {
2554
+ "epoch": 0.18988002086593636,
2555
+ "grad_norm": 0.0913248062133789,
2556
+ "learning_rate": 0.0003538888888888889,
2557
+ "loss": 0.0336,
2558
+ "step": 364
2559
+ },
2560
+ {
2561
+ "epoch": 0.1904016692749087,
2562
+ "grad_norm": 0.062306199222803116,
2563
+ "learning_rate": 0.0003533333333333333,
2564
+ "loss": 0.0291,
2565
+ "step": 365
2566
+ },
2567
+ {
2568
+ "epoch": 0.19092331768388107,
2569
+ "grad_norm": 0.09297792613506317,
2570
+ "learning_rate": 0.0003527777777777778,
2571
+ "loss": 0.0338,
2572
+ "step": 366
2573
+ },
2574
+ {
2575
+ "epoch": 0.1914449660928534,
2576
+ "grad_norm": 0.12690134346485138,
2577
+ "learning_rate": 0.00035222222222222225,
2578
+ "loss": 0.0399,
2579
+ "step": 367
2580
+ },
2581
+ {
2582
+ "epoch": 0.19196661450182578,
2583
+ "grad_norm": 0.07451540231704712,
2584
+ "learning_rate": 0.0003516666666666667,
2585
+ "loss": 0.0364,
2586
+ "step": 368
2587
+ },
2588
+ {
2589
+ "epoch": 0.19248826291079812,
2590
+ "grad_norm": 0.09954366087913513,
2591
+ "learning_rate": 0.0003511111111111111,
2592
+ "loss": 0.036,
2593
+ "step": 369
2594
+ },
2595
+ {
2596
+ "epoch": 0.19300991131977047,
2597
+ "grad_norm": 0.07105272263288498,
2598
+ "learning_rate": 0.00035055555555555556,
2599
+ "loss": 0.0226,
2600
+ "step": 370
2601
+ },
2602
+ {
2603
+ "epoch": 0.19353155972874284,
2604
+ "grad_norm": 0.06857888400554657,
2605
+ "learning_rate": 0.00035,
2606
+ "loss": 0.0305,
2607
+ "step": 371
2608
+ },
2609
+ {
2610
+ "epoch": 0.19405320813771518,
2611
+ "grad_norm": 0.060487356036901474,
2612
+ "learning_rate": 0.00034944444444444443,
2613
+ "loss": 0.0279,
2614
+ "step": 372
2615
+ },
2616
+ {
2617
+ "epoch": 0.19457485654668752,
2618
+ "grad_norm": 0.07935786992311478,
2619
+ "learning_rate": 0.0003488888888888889,
2620
+ "loss": 0.0377,
2621
+ "step": 373
2622
+ },
2623
+ {
2624
+ "epoch": 0.1950965049556599,
2625
+ "grad_norm": 0.10610669106245041,
2626
+ "learning_rate": 0.00034833333333333336,
2627
+ "loss": 0.0198,
2628
+ "step": 374
2629
+ },
2630
+ {
2631
+ "epoch": 0.19561815336463223,
2632
+ "grad_norm": 0.06738949567079544,
2633
+ "learning_rate": 0.0003477777777777778,
2634
+ "loss": 0.0321,
2635
+ "step": 375
2636
+ },
2637
+ {
2638
+ "epoch": 0.1961398017736046,
2639
+ "grad_norm": 0.09995345771312714,
2640
+ "learning_rate": 0.00034722222222222224,
2641
+ "loss": 0.0168,
2642
+ "step": 376
2643
+ },
2644
+ {
2645
+ "epoch": 0.19666145018257694,
2646
+ "grad_norm": 0.07820367068052292,
2647
+ "learning_rate": 0.00034666666666666667,
2648
+ "loss": 0.0192,
2649
+ "step": 377
2650
+ },
2651
+ {
2652
+ "epoch": 0.19718309859154928,
2653
+ "grad_norm": 0.05883244797587395,
2654
+ "learning_rate": 0.0003461111111111111,
2655
+ "loss": 0.0217,
2656
+ "step": 378
2657
+ },
2658
+ {
2659
+ "epoch": 0.19770474700052165,
2660
+ "grad_norm": 0.06929990649223328,
2661
+ "learning_rate": 0.00034555555555555555,
2662
+ "loss": 0.0248,
2663
+ "step": 379
2664
+ },
2665
+ {
2666
+ "epoch": 0.198226395409494,
2667
+ "grad_norm": 0.060583919286727905,
2668
+ "learning_rate": 0.000345,
2669
+ "loss": 0.0204,
2670
+ "step": 380
2671
+ },
2672
+ {
2673
+ "epoch": 0.19874804381846636,
2674
+ "grad_norm": 0.08263508230447769,
2675
+ "learning_rate": 0.0003444444444444445,
2676
+ "loss": 0.0261,
2677
+ "step": 381
2678
+ },
2679
+ {
2680
+ "epoch": 0.1992696922274387,
2681
+ "grad_norm": 0.07354709506034851,
2682
+ "learning_rate": 0.0003438888888888889,
2683
+ "loss": 0.0328,
2684
+ "step": 382
2685
+ },
2686
+ {
2687
+ "epoch": 0.19979134063641105,
2688
+ "grad_norm": 0.09151386469602585,
2689
+ "learning_rate": 0.00034333333333333335,
2690
+ "loss": 0.0315,
2691
+ "step": 383
2692
+ },
2693
+ {
2694
+ "epoch": 0.20031298904538342,
2695
+ "grad_norm": 0.06800325959920883,
2696
+ "learning_rate": 0.0003427777777777778,
2697
+ "loss": 0.0265,
2698
+ "step": 384
2699
+ },
2700
+ {
2701
+ "epoch": 0.20083463745435576,
2702
+ "grad_norm": 0.05672604963183403,
2703
+ "learning_rate": 0.0003422222222222222,
2704
+ "loss": 0.0216,
2705
+ "step": 385
2706
+ },
2707
+ {
2708
+ "epoch": 0.20135628586332813,
2709
+ "grad_norm": 0.07447244226932526,
2710
+ "learning_rate": 0.00034166666666666666,
2711
+ "loss": 0.0253,
2712
+ "step": 386
2713
+ },
2714
+ {
2715
+ "epoch": 0.20187793427230047,
2716
+ "grad_norm": 0.051845699548721313,
2717
+ "learning_rate": 0.0003411111111111111,
2718
+ "loss": 0.0291,
2719
+ "step": 387
2720
+ },
2721
+ {
2722
+ "epoch": 0.2023995826812728,
2723
+ "grad_norm": 0.04311797395348549,
2724
+ "learning_rate": 0.0003405555555555556,
2725
+ "loss": 0.0189,
2726
+ "step": 388
2727
+ },
2728
+ {
2729
+ "epoch": 0.20292123109024518,
2730
+ "grad_norm": 0.08901547640562057,
2731
+ "learning_rate": 0.00034,
2732
+ "loss": 0.0313,
2733
+ "step": 389
2734
+ },
2735
+ {
2736
+ "epoch": 0.20344287949921752,
2737
+ "grad_norm": 0.05055601894855499,
2738
+ "learning_rate": 0.00033944444444444446,
2739
+ "loss": 0.0231,
2740
+ "step": 390
2741
+ },
2742
+ {
2743
+ "epoch": 0.2039645279081899,
2744
+ "grad_norm": 0.04943820461630821,
2745
+ "learning_rate": 0.0003388888888888889,
2746
+ "loss": 0.021,
2747
+ "step": 391
2748
+ },
2749
+ {
2750
+ "epoch": 0.20448617631716223,
2751
+ "grad_norm": 0.0558842197060585,
2752
+ "learning_rate": 0.00033833333333333334,
2753
+ "loss": 0.0251,
2754
+ "step": 392
2755
+ },
2756
+ {
2757
+ "epoch": 0.20500782472613457,
2758
+ "grad_norm": 0.06570509821176529,
2759
+ "learning_rate": 0.00033777777777777777,
2760
+ "loss": 0.012,
2761
+ "step": 393
2762
+ },
2763
+ {
2764
+ "epoch": 0.20552947313510694,
2765
+ "grad_norm": 0.13640566170215607,
2766
+ "learning_rate": 0.0003372222222222222,
2767
+ "loss": 0.0396,
2768
+ "step": 394
2769
+ },
2770
+ {
2771
+ "epoch": 0.20605112154407929,
2772
+ "grad_norm": 0.05271435156464577,
2773
+ "learning_rate": 0.0003366666666666667,
2774
+ "loss": 0.028,
2775
+ "step": 395
2776
+ },
2777
+ {
2778
+ "epoch": 0.20657276995305165,
2779
+ "grad_norm": 0.04778929427266121,
2780
+ "learning_rate": 0.00033611111111111114,
2781
+ "loss": 0.0126,
2782
+ "step": 396
2783
+ },
2784
+ {
2785
+ "epoch": 0.207094418362024,
2786
+ "grad_norm": 0.04178643599152565,
2787
+ "learning_rate": 0.0003355555555555556,
2788
+ "loss": 0.0148,
2789
+ "step": 397
2790
+ },
2791
+ {
2792
+ "epoch": 0.20761606677099634,
2793
+ "grad_norm": 0.05933418869972229,
2794
+ "learning_rate": 0.000335,
2795
+ "loss": 0.0218,
2796
+ "step": 398
2797
+ },
2798
+ {
2799
+ "epoch": 0.2081377151799687,
2800
+ "grad_norm": 0.05561219900846481,
2801
+ "learning_rate": 0.00033444444444444445,
2802
+ "loss": 0.0167,
2803
+ "step": 399
2804
+ },
2805
+ {
2806
+ "epoch": 0.20865936358894105,
2807
+ "grad_norm": 0.0431622713804245,
2808
+ "learning_rate": 0.0003338888888888889,
2809
+ "loss": 0.0263,
2810
+ "step": 400
2811
+ },
2812
+ {
2813
+ "epoch": 0.20918101199791342,
2814
+ "grad_norm": 0.06121833994984627,
2815
+ "learning_rate": 0.0003333333333333333,
2816
+ "loss": 0.0224,
2817
+ "step": 401
2818
+ },
2819
+ {
2820
+ "epoch": 0.20970266040688576,
2821
+ "grad_norm": 0.0923122763633728,
2822
+ "learning_rate": 0.0003327777777777778,
2823
+ "loss": 0.0264,
2824
+ "step": 402
2825
+ },
2826
+ {
2827
+ "epoch": 0.2102243088158581,
2828
+ "grad_norm": 0.045166369527578354,
2829
+ "learning_rate": 0.0003322222222222222,
2830
+ "loss": 0.0135,
2831
+ "step": 403
2832
+ },
2833
+ {
2834
+ "epoch": 0.21074595722483047,
2835
+ "grad_norm": 0.08227386325597763,
2836
+ "learning_rate": 0.0003316666666666667,
2837
+ "loss": 0.0253,
2838
+ "step": 404
2839
+ },
2840
+ {
2841
+ "epoch": 0.2112676056338028,
2842
+ "grad_norm": 0.0516192689538002,
2843
+ "learning_rate": 0.0003311111111111111,
2844
+ "loss": 0.0278,
2845
+ "step": 405
2846
+ },
2847
+ {
2848
+ "epoch": 0.21178925404277518,
2849
+ "grad_norm": 0.11895351111888885,
2850
+ "learning_rate": 0.00033055555555555556,
2851
+ "loss": 0.0333,
2852
+ "step": 406
2853
+ },
2854
+ {
2855
+ "epoch": 0.21231090245174752,
2856
+ "grad_norm": 0.062691330909729,
2857
+ "learning_rate": 0.00033,
2858
+ "loss": 0.0278,
2859
+ "step": 407
2860
+ },
2861
+ {
2862
+ "epoch": 0.21283255086071987,
2863
+ "grad_norm": 0.04849197715520859,
2864
+ "learning_rate": 0.00032944444444444444,
2865
+ "loss": 0.0274,
2866
+ "step": 408
2867
+ },
2868
+ {
2869
+ "epoch": 0.21335419926969224,
2870
+ "grad_norm": 0.12979350984096527,
2871
+ "learning_rate": 0.0003288888888888889,
2872
+ "loss": 0.0311,
2873
+ "step": 409
2874
+ },
2875
+ {
2876
+ "epoch": 0.21387584767866458,
2877
+ "grad_norm": 0.09985975176095963,
2878
+ "learning_rate": 0.0003283333333333333,
2879
+ "loss": 0.0343,
2880
+ "step": 410
2881
+ },
2882
+ {
2883
+ "epoch": 0.21439749608763695,
2884
+ "grad_norm": 0.05388106778264046,
2885
+ "learning_rate": 0.0003277777777777778,
2886
+ "loss": 0.0119,
2887
+ "step": 411
2888
+ },
2889
+ {
2890
+ "epoch": 0.2149191444966093,
2891
+ "grad_norm": 0.061424896121025085,
2892
+ "learning_rate": 0.00032722222222222224,
2893
+ "loss": 0.0258,
2894
+ "step": 412
2895
+ },
2896
+ {
2897
+ "epoch": 0.21544079290558163,
2898
+ "grad_norm": 0.05304243043065071,
2899
+ "learning_rate": 0.0003266666666666667,
2900
+ "loss": 0.0252,
2901
+ "step": 413
2902
+ },
2903
+ {
2904
+ "epoch": 0.215962441314554,
2905
+ "grad_norm": 0.06124117597937584,
2906
+ "learning_rate": 0.0003261111111111111,
2907
+ "loss": 0.0265,
2908
+ "step": 414
2909
+ },
2910
+ {
2911
+ "epoch": 0.21648408972352634,
2912
+ "grad_norm": 0.0462118461728096,
2913
+ "learning_rate": 0.00032555555555555555,
2914
+ "loss": 0.018,
2915
+ "step": 415
2916
+ },
2917
+ {
2918
+ "epoch": 0.21700573813249868,
2919
+ "grad_norm": 0.05339544638991356,
2920
+ "learning_rate": 0.00032500000000000004,
2921
+ "loss": 0.015,
2922
+ "step": 416
2923
+ },
2924
+ {
2925
+ "epoch": 0.21752738654147105,
2926
+ "grad_norm": 0.04562271013855934,
2927
+ "learning_rate": 0.0003244444444444444,
2928
+ "loss": 0.0222,
2929
+ "step": 417
2930
+ },
2931
+ {
2932
+ "epoch": 0.2180490349504434,
2933
+ "grad_norm": 0.06268814951181412,
2934
+ "learning_rate": 0.0003238888888888889,
2935
+ "loss": 0.017,
2936
+ "step": 418
2937
+ },
2938
+ {
2939
+ "epoch": 0.21857068335941576,
2940
+ "grad_norm": 0.07897916436195374,
2941
+ "learning_rate": 0.0003233333333333333,
2942
+ "loss": 0.0362,
2943
+ "step": 419
2944
+ },
2945
+ {
2946
+ "epoch": 0.2190923317683881,
2947
+ "grad_norm": 0.0633966326713562,
2948
+ "learning_rate": 0.0003227777777777778,
2949
+ "loss": 0.016,
2950
+ "step": 420
2951
+ },
2952
+ {
2953
+ "epoch": 0.21961398017736045,
2954
+ "grad_norm": 0.06430386751890182,
2955
+ "learning_rate": 0.0003222222222222222,
2956
+ "loss": 0.029,
2957
+ "step": 421
2958
+ },
2959
+ {
2960
+ "epoch": 0.22013562858633282,
2961
+ "grad_norm": 0.07986673712730408,
2962
+ "learning_rate": 0.00032166666666666666,
2963
+ "loss": 0.0339,
2964
+ "step": 422
2965
+ },
2966
+ {
2967
+ "epoch": 0.22065727699530516,
2968
+ "grad_norm": 0.05497688055038452,
2969
+ "learning_rate": 0.00032111111111111115,
2970
+ "loss": 0.0135,
2971
+ "step": 423
2972
+ },
2973
+ {
2974
+ "epoch": 0.22117892540427753,
2975
+ "grad_norm": 0.07314179837703705,
2976
+ "learning_rate": 0.00032055555555555554,
2977
+ "loss": 0.0274,
2978
+ "step": 424
2979
+ },
2980
+ {
2981
+ "epoch": 0.22170057381324987,
2982
+ "grad_norm": 0.045945893973112106,
2983
+ "learning_rate": 0.00032,
2984
+ "loss": 0.0239,
2985
+ "step": 425
2986
+ },
2987
+ {
2988
+ "epoch": 0.2222222222222222,
2989
+ "grad_norm": 0.11235559731721878,
2990
+ "learning_rate": 0.0003194444444444444,
2991
+ "loss": 0.0302,
2992
+ "step": 426
2993
+ },
2994
+ {
2995
+ "epoch": 0.22274387063119458,
2996
+ "grad_norm": 0.06201227381825447,
2997
+ "learning_rate": 0.0003188888888888889,
2998
+ "loss": 0.0319,
2999
+ "step": 427
3000
+ },
3001
+ {
3002
+ "epoch": 0.22326551904016692,
3003
+ "grad_norm": 0.05009296536445618,
3004
+ "learning_rate": 0.00031833333333333334,
3005
+ "loss": 0.0175,
3006
+ "step": 428
3007
+ },
3008
+ {
3009
+ "epoch": 0.2237871674491393,
3010
+ "grad_norm": 0.06590239703655243,
3011
+ "learning_rate": 0.0003177777777777778,
3012
+ "loss": 0.0275,
3013
+ "step": 429
3014
+ },
3015
+ {
3016
+ "epoch": 0.22430881585811163,
3017
+ "grad_norm": 0.06859228760004044,
3018
+ "learning_rate": 0.00031722222222222227,
3019
+ "loss": 0.0282,
3020
+ "step": 430
3021
+ },
3022
+ {
3023
+ "epoch": 0.22483046426708397,
3024
+ "grad_norm": 0.04625241830945015,
3025
+ "learning_rate": 0.00031666666666666665,
3026
+ "loss": 0.025,
3027
+ "step": 431
3028
+ },
3029
+ {
3030
+ "epoch": 0.22535211267605634,
3031
+ "grad_norm": 0.06035872921347618,
3032
+ "learning_rate": 0.00031611111111111114,
3033
+ "loss": 0.0301,
3034
+ "step": 432
3035
+ },
3036
+ {
3037
+ "epoch": 0.22587376108502868,
3038
+ "grad_norm": 0.09716615080833435,
3039
+ "learning_rate": 0.0003155555555555555,
3040
+ "loss": 0.0135,
3041
+ "step": 433
3042
+ },
3043
+ {
3044
+ "epoch": 0.22639540949400105,
3045
+ "grad_norm": 0.060461174696683884,
3046
+ "learning_rate": 0.000315,
3047
+ "loss": 0.0237,
3048
+ "step": 434
3049
+ },
3050
+ {
3051
+ "epoch": 0.2269170579029734,
3052
+ "grad_norm": 0.0631205216050148,
3053
+ "learning_rate": 0.0003144444444444445,
3054
+ "loss": 0.0136,
3055
+ "step": 435
3056
+ },
3057
+ {
3058
+ "epoch": 0.22743870631194574,
3059
+ "grad_norm": 0.044443339109420776,
3060
+ "learning_rate": 0.0003138888888888889,
3061
+ "loss": 0.0237,
3062
+ "step": 436
3063
+ },
3064
+ {
3065
+ "epoch": 0.2279603547209181,
3066
+ "grad_norm": 0.04617779329419136,
3067
+ "learning_rate": 0.0003133333333333334,
3068
+ "loss": 0.0246,
3069
+ "step": 437
3070
+ },
3071
+ {
3072
+ "epoch": 0.22848200312989045,
3073
+ "grad_norm": 0.040022511035203934,
3074
+ "learning_rate": 0.00031277777777777776,
3075
+ "loss": 0.0291,
3076
+ "step": 438
3077
+ },
3078
+ {
3079
+ "epoch": 0.22900365153886282,
3080
+ "grad_norm": 0.10207943618297577,
3081
+ "learning_rate": 0.00031222222222222225,
3082
+ "loss": 0.0289,
3083
+ "step": 439
3084
+ },
3085
+ {
3086
+ "epoch": 0.22952529994783516,
3087
+ "grad_norm": 0.052271150052547455,
3088
+ "learning_rate": 0.00031166666666666663,
3089
+ "loss": 0.0275,
3090
+ "step": 440
3091
+ },
3092
+ {
3093
+ "epoch": 0.2300469483568075,
3094
+ "grad_norm": 0.05472894012928009,
3095
+ "learning_rate": 0.0003111111111111111,
3096
+ "loss": 0.0237,
3097
+ "step": 441
3098
+ },
3099
+ {
3100
+ "epoch": 0.23056859676577987,
3101
+ "grad_norm": 0.051506489515304565,
3102
+ "learning_rate": 0.0003105555555555555,
3103
+ "loss": 0.0267,
3104
+ "step": 442
3105
+ },
3106
+ {
3107
+ "epoch": 0.2310902451747522,
3108
+ "grad_norm": 0.12625692784786224,
3109
+ "learning_rate": 0.00031,
3110
+ "loss": 0.0295,
3111
+ "step": 443
3112
+ },
3113
+ {
3114
+ "epoch": 0.23161189358372458,
3115
+ "grad_norm": 0.052463430911302567,
3116
+ "learning_rate": 0.0003094444444444445,
3117
+ "loss": 0.0222,
3118
+ "step": 444
3119
+ },
3120
+ {
3121
+ "epoch": 0.23213354199269692,
3122
+ "grad_norm": 0.07140383124351501,
3123
+ "learning_rate": 0.0003088888888888889,
3124
+ "loss": 0.0274,
3125
+ "step": 445
3126
+ },
3127
+ {
3128
+ "epoch": 0.23265519040166927,
3129
+ "grad_norm": 0.04128264635801315,
3130
+ "learning_rate": 0.00030833333333333337,
3131
+ "loss": 0.0195,
3132
+ "step": 446
3133
+ },
3134
+ {
3135
+ "epoch": 0.23317683881064163,
3136
+ "grad_norm": 0.09302657097578049,
3137
+ "learning_rate": 0.00030777777777777775,
3138
+ "loss": 0.0372,
3139
+ "step": 447
3140
+ },
3141
+ {
3142
+ "epoch": 0.23369848721961398,
3143
+ "grad_norm": 0.07428940385580063,
3144
+ "learning_rate": 0.00030722222222222224,
3145
+ "loss": 0.0232,
3146
+ "step": 448
3147
+ },
3148
+ {
3149
+ "epoch": 0.23422013562858635,
3150
+ "grad_norm": 0.08673116564750671,
3151
+ "learning_rate": 0.0003066666666666667,
3152
+ "loss": 0.0292,
3153
+ "step": 449
3154
+ },
3155
+ {
3156
+ "epoch": 0.2347417840375587,
3157
+ "grad_norm": 0.06983821839094162,
3158
+ "learning_rate": 0.0003061111111111111,
3159
+ "loss": 0.0299,
3160
+ "step": 450
3161
+ },
3162
+ {
3163
+ "epoch": 0.23526343244653103,
3164
+ "grad_norm": 0.05890791490674019,
3165
+ "learning_rate": 0.0003055555555555556,
3166
+ "loss": 0.0159,
3167
+ "step": 451
3168
+ },
3169
+ {
3170
+ "epoch": 0.2357850808555034,
3171
+ "grad_norm": 0.05678574740886688,
3172
+ "learning_rate": 0.000305,
3173
+ "loss": 0.0194,
3174
+ "step": 452
3175
+ },
3176
+ {
3177
+ "epoch": 0.23630672926447574,
3178
+ "grad_norm": 0.06532768905162811,
3179
+ "learning_rate": 0.0003044444444444445,
3180
+ "loss": 0.0222,
3181
+ "step": 453
3182
+ },
3183
+ {
3184
+ "epoch": 0.2368283776734481,
3185
+ "grad_norm": 0.04442572221159935,
3186
+ "learning_rate": 0.00030388888888888886,
3187
+ "loss": 0.0204,
3188
+ "step": 454
3189
+ },
3190
+ {
3191
+ "epoch": 0.23735002608242045,
3192
+ "grad_norm": 0.06691122055053711,
3193
+ "learning_rate": 0.00030333333333333335,
3194
+ "loss": 0.0277,
3195
+ "step": 455
3196
+ },
3197
+ {
3198
+ "epoch": 0.2378716744913928,
3199
+ "grad_norm": 0.061397284269332886,
3200
+ "learning_rate": 0.0003027777777777778,
3201
+ "loss": 0.015,
3202
+ "step": 456
3203
+ },
3204
+ {
3205
+ "epoch": 0.23839332290036516,
3206
+ "grad_norm": 0.058687739074230194,
3207
+ "learning_rate": 0.0003022222222222222,
3208
+ "loss": 0.0307,
3209
+ "step": 457
3210
+ },
3211
+ {
3212
+ "epoch": 0.2389149713093375,
3213
+ "grad_norm": 0.07386653125286102,
3214
+ "learning_rate": 0.0003016666666666667,
3215
+ "loss": 0.0291,
3216
+ "step": 458
3217
+ },
3218
+ {
3219
+ "epoch": 0.23943661971830985,
3220
+ "grad_norm": 0.06010840833187103,
3221
+ "learning_rate": 0.0003011111111111111,
3222
+ "loss": 0.02,
3223
+ "step": 459
3224
+ },
3225
+ {
3226
+ "epoch": 0.23995826812728221,
3227
+ "grad_norm": 0.05542018637061119,
3228
+ "learning_rate": 0.0003005555555555556,
3229
+ "loss": 0.0185,
3230
+ "step": 460
3231
+ },
3232
+ {
3233
+ "epoch": 0.24047991653625456,
3234
+ "grad_norm": 0.07411111891269684,
3235
+ "learning_rate": 0.0003,
3236
+ "loss": 0.013,
3237
+ "step": 461
3238
+ },
3239
+ {
3240
+ "epoch": 0.24100156494522693,
3241
+ "grad_norm": 0.05750228837132454,
3242
+ "learning_rate": 0.00029944444444444446,
3243
+ "loss": 0.0157,
3244
+ "step": 462
3245
+ },
3246
+ {
3247
+ "epoch": 0.24152321335419927,
3248
+ "grad_norm": 0.04710470885038376,
3249
+ "learning_rate": 0.0002988888888888889,
3250
+ "loss": 0.0194,
3251
+ "step": 463
3252
+ },
3253
+ {
3254
+ "epoch": 0.2420448617631716,
3255
+ "grad_norm": 0.058672945946455,
3256
+ "learning_rate": 0.00029833333333333334,
3257
+ "loss": 0.0138,
3258
+ "step": 464
3259
+ },
3260
+ {
3261
+ "epoch": 0.24256651017214398,
3262
+ "grad_norm": 0.048859693109989166,
3263
+ "learning_rate": 0.0002977777777777778,
3264
+ "loss": 0.0177,
3265
+ "step": 465
3266
+ },
3267
+ {
3268
+ "epoch": 0.24308815858111632,
3269
+ "grad_norm": 0.0428357794880867,
3270
+ "learning_rate": 0.0002972222222222222,
3271
+ "loss": 0.013,
3272
+ "step": 466
3273
+ },
3274
+ {
3275
+ "epoch": 0.2436098069900887,
3276
+ "grad_norm": 0.053479310125112534,
3277
+ "learning_rate": 0.0002966666666666667,
3278
+ "loss": 0.0238,
3279
+ "step": 467
3280
+ },
3281
+ {
3282
+ "epoch": 0.24413145539906103,
3283
+ "grad_norm": 0.05971763655543327,
3284
+ "learning_rate": 0.0002961111111111111,
3285
+ "loss": 0.0258,
3286
+ "step": 468
3287
+ },
3288
+ {
3289
+ "epoch": 0.24465310380803337,
3290
+ "grad_norm": 0.045527439564466476,
3291
+ "learning_rate": 0.0002955555555555556,
3292
+ "loss": 0.0219,
3293
+ "step": 469
3294
+ },
3295
+ {
3296
+ "epoch": 0.24517475221700574,
3297
+ "grad_norm": 0.04123241826891899,
3298
+ "learning_rate": 0.000295,
3299
+ "loss": 0.0233,
3300
+ "step": 470
3301
+ },
3302
+ {
3303
+ "epoch": 0.24569640062597808,
3304
+ "grad_norm": 0.17581242322921753,
3305
+ "learning_rate": 0.00029444444444444445,
3306
+ "loss": 0.0359,
3307
+ "step": 471
3308
+ },
3309
+ {
3310
+ "epoch": 0.24621804903495045,
3311
+ "grad_norm": 0.09290144592523575,
3312
+ "learning_rate": 0.0002938888888888889,
3313
+ "loss": 0.0256,
3314
+ "step": 472
3315
+ },
3316
+ {
3317
+ "epoch": 0.2467396974439228,
3318
+ "grad_norm": 0.03519435226917267,
3319
+ "learning_rate": 0.0002933333333333333,
3320
+ "loss": 0.0198,
3321
+ "step": 473
3322
+ },
3323
+ {
3324
+ "epoch": 0.24726134585289514,
3325
+ "grad_norm": 0.04338726028800011,
3326
+ "learning_rate": 0.0002927777777777778,
3327
+ "loss": 0.0118,
3328
+ "step": 474
3329
+ },
3330
+ {
3331
+ "epoch": 0.2477829942618675,
3332
+ "grad_norm": 0.1172214224934578,
3333
+ "learning_rate": 0.0002922222222222222,
3334
+ "loss": 0.0324,
3335
+ "step": 475
3336
+ },
3337
+ {
3338
+ "epoch": 0.24830464267083985,
3339
+ "grad_norm": 0.06438913941383362,
3340
+ "learning_rate": 0.0002916666666666667,
3341
+ "loss": 0.0241,
3342
+ "step": 476
3343
+ },
3344
+ {
3345
+ "epoch": 0.24882629107981222,
3346
+ "grad_norm": 0.14249597489833832,
3347
+ "learning_rate": 0.00029111111111111113,
3348
+ "loss": 0.0356,
3349
+ "step": 477
3350
+ },
3351
+ {
3352
+ "epoch": 0.24934793948878456,
3353
+ "grad_norm": 0.045848701149225235,
3354
+ "learning_rate": 0.00029055555555555556,
3355
+ "loss": 0.0155,
3356
+ "step": 478
3357
+ },
3358
+ {
3359
+ "epoch": 0.2498695878977569,
3360
+ "grad_norm": 0.05208711698651314,
3361
+ "learning_rate": 0.00029,
3362
+ "loss": 0.0243,
3363
+ "step": 479
3364
+ },
3365
+ {
3366
+ "epoch": 0.25039123630672927,
3367
+ "grad_norm": 0.05537666380405426,
3368
+ "learning_rate": 0.00028944444444444444,
3369
+ "loss": 0.0308,
3370
+ "step": 480
3371
+ },
3372
+ {
3373
+ "epoch": 0.2509128847157016,
3374
+ "grad_norm": 0.049218740314245224,
3375
+ "learning_rate": 0.0002888888888888889,
3376
+ "loss": 0.0149,
3377
+ "step": 481
3378
+ },
3379
+ {
3380
+ "epoch": 0.25143453312467395,
3381
+ "grad_norm": 0.050829824060201645,
3382
+ "learning_rate": 0.0002883333333333333,
3383
+ "loss": 0.0252,
3384
+ "step": 482
3385
+ },
3386
+ {
3387
+ "epoch": 0.2519561815336463,
3388
+ "grad_norm": 0.047700315713882446,
3389
+ "learning_rate": 0.0002877777777777778,
3390
+ "loss": 0.024,
3391
+ "step": 483
3392
+ },
3393
+ {
3394
+ "epoch": 0.2524778299426187,
3395
+ "grad_norm": 0.07238329201936722,
3396
+ "learning_rate": 0.00028722222222222224,
3397
+ "loss": 0.0214,
3398
+ "step": 484
3399
+ },
3400
+ {
3401
+ "epoch": 0.25299947835159103,
3402
+ "grad_norm": 0.04379934072494507,
3403
+ "learning_rate": 0.0002866666666666667,
3404
+ "loss": 0.0259,
3405
+ "step": 485
3406
+ },
3407
+ {
3408
+ "epoch": 0.2535211267605634,
3409
+ "grad_norm": 0.0694945827126503,
3410
+ "learning_rate": 0.0002861111111111111,
3411
+ "loss": 0.0183,
3412
+ "step": 486
3413
+ },
3414
+ {
3415
+ "epoch": 0.2540427751695357,
3416
+ "grad_norm": 0.056973714381456375,
3417
+ "learning_rate": 0.00028555555555555555,
3418
+ "loss": 0.0272,
3419
+ "step": 487
3420
+ },
3421
+ {
3422
+ "epoch": 0.25456442357850806,
3423
+ "grad_norm": 0.05177774280309677,
3424
+ "learning_rate": 0.000285,
3425
+ "loss": 0.0275,
3426
+ "step": 488
3427
+ },
3428
+ {
3429
+ "epoch": 0.25508607198748046,
3430
+ "grad_norm": 0.08025998622179031,
3431
+ "learning_rate": 0.0002844444444444444,
3432
+ "loss": 0.0275,
3433
+ "step": 489
3434
+ },
3435
+ {
3436
+ "epoch": 0.2556077203964528,
3437
+ "grad_norm": 0.04469485580921173,
3438
+ "learning_rate": 0.0002838888888888889,
3439
+ "loss": 0.0233,
3440
+ "step": 490
3441
+ },
3442
+ {
3443
+ "epoch": 0.25612936880542514,
3444
+ "grad_norm": 0.06418605148792267,
3445
+ "learning_rate": 0.00028333333333333335,
3446
+ "loss": 0.0315,
3447
+ "step": 491
3448
+ },
3449
+ {
3450
+ "epoch": 0.2566510172143975,
3451
+ "grad_norm": 0.09197323769330978,
3452
+ "learning_rate": 0.0002827777777777778,
3453
+ "loss": 0.0252,
3454
+ "step": 492
3455
+ },
3456
+ {
3457
+ "epoch": 0.2571726656233698,
3458
+ "grad_norm": 0.058225080370903015,
3459
+ "learning_rate": 0.00028222222222222223,
3460
+ "loss": 0.0273,
3461
+ "step": 493
3462
+ },
3463
+ {
3464
+ "epoch": 0.2576943140323422,
3465
+ "grad_norm": 0.03813721984624863,
3466
+ "learning_rate": 0.00028166666666666666,
3467
+ "loss": 0.0244,
3468
+ "step": 494
3469
+ },
3470
+ {
3471
+ "epoch": 0.25821596244131456,
3472
+ "grad_norm": 0.07051227241754532,
3473
+ "learning_rate": 0.0002811111111111111,
3474
+ "loss": 0.0243,
3475
+ "step": 495
3476
+ },
3477
+ {
3478
+ "epoch": 0.2587376108502869,
3479
+ "grad_norm": 0.07289328426122665,
3480
+ "learning_rate": 0.00028055555555555554,
3481
+ "loss": 0.0275,
3482
+ "step": 496
3483
+ },
3484
+ {
3485
+ "epoch": 0.25925925925925924,
3486
+ "grad_norm": 0.08466362953186035,
3487
+ "learning_rate": 0.00028000000000000003,
3488
+ "loss": 0.0107,
3489
+ "step": 497
3490
+ },
3491
+ {
3492
+ "epoch": 0.2597809076682316,
3493
+ "grad_norm": 0.06937390565872192,
3494
+ "learning_rate": 0.00027944444444444447,
3495
+ "loss": 0.0277,
3496
+ "step": 498
3497
+ },
3498
+ {
3499
+ "epoch": 0.260302556077204,
3500
+ "grad_norm": 0.07908118516206741,
3501
+ "learning_rate": 0.0002788888888888889,
3502
+ "loss": 0.013,
3503
+ "step": 499
3504
+ },
3505
+ {
3506
+ "epoch": 0.2608242044861763,
3507
+ "grad_norm": 0.05328572168946266,
3508
+ "learning_rate": 0.00027833333333333334,
3509
+ "loss": 0.0241,
3510
+ "step": 500
3511
+ }
3512
+ ],
3513
+ "logging_steps": 1,
3514
+ "max_steps": 1000,
3515
+ "num_input_tokens_seen": 0,
3516
+ "num_train_epochs": 1,
3517
+ "save_steps": 100,
3518
+ "stateful_callbacks": {
3519
+ "TrainerControl": {
3520
+ "args": {
3521
+ "should_epoch_stop": false,
3522
+ "should_evaluate": false,
3523
+ "should_log": false,
3524
+ "should_save": true,
3525
+ "should_training_stop": false
3526
+ },
3527
+ "attributes": {}
3528
+ }
3529
+ },
3530
+ "total_flos": 0.0,
3531
+ "train_batch_size": 512,
3532
+ "trial_name": null,
3533
+ "trial_params": null
3534
+ }
checkpoint-700/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
+ }
checkpoint-700/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
checkpoint-700/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-700/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2_5_VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 1003520,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 1003520,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
checkpoint-700/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
+ }
checkpoint-700/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": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-700/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-700/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-900/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
+ }
checkpoint-900/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
checkpoint-900/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-900/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2_5_VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 1003520,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 1003520,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
checkpoint-900/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
+ }
checkpoint-900/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": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-900/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-900/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2_5_VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 1003520,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 1003520,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
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
+ }
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": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
train_cls.log ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
wandb/debug-internal.log ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-01-02T19:33:18.423985176Z","level":"INFO","msg":"stream: starting","core version":"0.22.2"}
2
+ {"time":"2026-01-02T19:33:18.659423147Z","level":"INFO","msg":"stream: created new stream","id":"igfpea8y"}
3
+ {"time":"2026-01-02T19:33:18.659485089Z","level":"INFO","msg":"handler: started","stream_id":"igfpea8y"}
4
+ {"time":"2026-01-02T19:33:18.659560774Z","level":"INFO","msg":"stream: started","id":"igfpea8y"}
5
+ {"time":"2026-01-02T19:33:18.659606466Z","level":"INFO","msg":"writer: started","stream_id":"igfpea8y"}
6
+ {"time":"2026-01-02T19:33:18.659640905Z","level":"INFO","msg":"sender: started","stream_id":"igfpea8y"}
7
+ {"time":"2026-01-02T23:27:22.881256308Z","level":"INFO","msg":"stream: closing","id":"igfpea8y"}
8
+ {"time":"2026-01-02T23:27:23.385176198Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
9
+ {"time":"2026-01-02T23:27:23.50907896Z","level":"INFO","msg":"handler: closed","stream_id":"igfpea8y"}
10
+ {"time":"2026-01-02T23:27:23.509215985Z","level":"INFO","msg":"sender: closed","stream_id":"igfpea8y"}
11
+ {"time":"2026-01-02T23:27:23.509229009Z","level":"INFO","msg":"stream: closed","id":"igfpea8y"}
wandb/debug.log ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_setup.py:_flush():81] Current SDK version is 0.22.2
2
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_setup.py:_flush():81] Configure stats pid to 4188102
3
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_setup.py:_flush():81] Loading settings from /home/v-menggao/.config/wandb/settings
4
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_setup.py:_flush():81] Loading settings from /home/v-menggao/code/VLM2Vec/wandb/settings
5
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_setup.py:_flush():81] Loading settings from environment variables
6
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_init.py:setup_run_log_directory():705] Logging user logs to /home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_7B_multilayer_distill_aop_10_pooling_i_ret_12_30_h100_2_node_Classifier_L12_i_ret_bsz512/wandb/run-20260102_193318-igfpea8y/logs/debug.log
7
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_init.py:setup_run_log_directory():706] Logging internal logs to /home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_7B_multilayer_distill_aop_10_pooling_i_ret_12_30_h100_2_node_Classifier_L12_i_ret_bsz512/wandb/run-20260102_193318-igfpea8y/logs/debug-internal.log
8
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_init.py:init():832] calling init triggers
9
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_init.py:init():837] wandb.init called with sweep_config: {}
10
+ config: {'_wandb': {}}
11
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_init.py:init():880] starting backend
12
+ 2026-01-02 19:33:18,418 INFO MainThread:4188102 [wandb_init.py:init():883] sending inform_init request
13
+ 2026-01-02 19:33:18,422 INFO MainThread:4188102 [wandb_init.py:init():891] backend started and connected
14
+ 2026-01-02 19:33:18,423 INFO MainThread:4188102 [wandb_init.py:init():961] updated telemetry
15
+ 2026-01-02 19:33:18,429 INFO MainThread:4188102 [wandb_init.py:init():985] communicating run to backend with 90.0 second timeout
16
+ 2026-01-02 19:33:19,022 INFO MainThread:4188102 [wandb_init.py:init():1036] starting run threads in backend
17
+ 2026-01-02 19:33:19,126 INFO MainThread:4188102 [wandb_run.py:_console_start():2509] atexit reg
18
+ 2026-01-02 19:33:19,126 INFO MainThread:4188102 [wandb_run.py:_redirect():2357] redirect: wrap_raw
19
+ 2026-01-02 19:33:19,126 INFO MainThread:4188102 [wandb_run.py:_redirect():2426] Wrapping output streams.
20
+ 2026-01-02 19:33:19,126 INFO MainThread:4188102 [wandb_run.py:_redirect():2449] Redirects installed.
21
+ 2026-01-02 19:33:19,129 INFO MainThread:4188102 [wandb_init.py:init():1076] run started, returning control to user process
22
+ 2026-01-02 19:33:19,130 INFO MainThread:4188102 [wandb_run.py:_config_callback():1392] config_cb None None {'output_dir': '/home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_7B_multilayer_distill_aop_10_pooling_i_ret_12_30_h100_2_node_Classifier_L12_i_ret_bsz512', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 512, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0005, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1, 'max_steps': 1000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 100, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_7B_multilayer_distill_aop_10_pooling_i_ret_12_30_h100_2_node_Classifier_L12_i_ret_bsz512/runs/Jan02_19-23-27_GCRAZGDL1688', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 100, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': True, 'eval_steps': None, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'Qwen2_5vl_7B_multilayer_distill_aop_10_pooling_i_ret_12_30_h100_2_node_Classifier_L12_i_ret_bsz512', 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': True, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'image_encoder_freeze': False, 'resume_from': 'none', 'project_name': None, 'grad_cache': False, 'gc_q_chunk_size': 2, 'gc_p_chunk_size': 2, 'interleave_stopping_strategy': 'all_exhausted', 'interleave_batch_size': 0}
23
+ 2026-01-02 23:27:22,881 INFO wandb-AsyncioManager-main:4188102 [service_client.py:_forward_responses():80] Reached EOF.
24
+ 2026-01-02 23:27:22,881 INFO wandb-AsyncioManager-main:4188102 [mailbox.py:close():137] Closing mailbox, abandoning 1 handles.
wandb/run-20260102_193318-igfpea8y/logs/debug-internal.log ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-01-02T19:33:18.423985176Z","level":"INFO","msg":"stream: starting","core version":"0.22.2"}
2
+ {"time":"2026-01-02T19:33:18.659423147Z","level":"INFO","msg":"stream: created new stream","id":"igfpea8y"}
3
+ {"time":"2026-01-02T19:33:18.659485089Z","level":"INFO","msg":"handler: started","stream_id":"igfpea8y"}
4
+ {"time":"2026-01-02T19:33:18.659560774Z","level":"INFO","msg":"stream: started","id":"igfpea8y"}
5
+ {"time":"2026-01-02T19:33:18.659606466Z","level":"INFO","msg":"writer: started","stream_id":"igfpea8y"}
6
+ {"time":"2026-01-02T19:33:18.659640905Z","level":"INFO","msg":"sender: started","stream_id":"igfpea8y"}
7
+ {"time":"2026-01-02T23:27:22.881256308Z","level":"INFO","msg":"stream: closing","id":"igfpea8y"}
8
+ {"time":"2026-01-02T23:27:23.385176198Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
9
+ {"time":"2026-01-02T23:27:23.50907896Z","level":"INFO","msg":"handler: closed","stream_id":"igfpea8y"}
10
+ {"time":"2026-01-02T23:27:23.509215985Z","level":"INFO","msg":"sender: closed","stream_id":"igfpea8y"}
11
+ {"time":"2026-01-02T23:27:23.509229009Z","level":"INFO","msg":"stream: closed","id":"igfpea8y"}
wandb/run-20260102_193318-igfpea8y/logs/debug.log ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_setup.py:_flush():81] Current SDK version is 0.22.2
2
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_setup.py:_flush():81] Configure stats pid to 4188102
3
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_setup.py:_flush():81] Loading settings from /home/v-menggao/.config/wandb/settings
4
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_setup.py:_flush():81] Loading settings from /home/v-menggao/code/VLM2Vec/wandb/settings
5
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_setup.py:_flush():81] Loading settings from environment variables
6
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_init.py:setup_run_log_directory():705] Logging user logs to /home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_7B_multilayer_distill_aop_10_pooling_i_ret_12_30_h100_2_node_Classifier_L12_i_ret_bsz512/wandb/run-20260102_193318-igfpea8y/logs/debug.log
7
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_init.py:setup_run_log_directory():706] Logging internal logs to /home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_7B_multilayer_distill_aop_10_pooling_i_ret_12_30_h100_2_node_Classifier_L12_i_ret_bsz512/wandb/run-20260102_193318-igfpea8y/logs/debug-internal.log
8
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_init.py:init():832] calling init triggers
9
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_init.py:init():837] wandb.init called with sweep_config: {}
10
+ config: {'_wandb': {}}
11
+ 2026-01-02 19:33:18,211 INFO MainThread:4188102 [wandb_init.py:init():880] starting backend
12
+ 2026-01-02 19:33:18,418 INFO MainThread:4188102 [wandb_init.py:init():883] sending inform_init request
13
+ 2026-01-02 19:33:18,422 INFO MainThread:4188102 [wandb_init.py:init():891] backend started and connected
14
+ 2026-01-02 19:33:18,423 INFO MainThread:4188102 [wandb_init.py:init():961] updated telemetry
15
+ 2026-01-02 19:33:18,429 INFO MainThread:4188102 [wandb_init.py:init():985] communicating run to backend with 90.0 second timeout
16
+ 2026-01-02 19:33:19,022 INFO MainThread:4188102 [wandb_init.py:init():1036] starting run threads in backend
17
+ 2026-01-02 19:33:19,126 INFO MainThread:4188102 [wandb_run.py:_console_start():2509] atexit reg
18
+ 2026-01-02 19:33:19,126 INFO MainThread:4188102 [wandb_run.py:_redirect():2357] redirect: wrap_raw
19
+ 2026-01-02 19:33:19,126 INFO MainThread:4188102 [wandb_run.py:_redirect():2426] Wrapping output streams.
20
+ 2026-01-02 19:33:19,126 INFO MainThread:4188102 [wandb_run.py:_redirect():2449] Redirects installed.
21
+ 2026-01-02 19:33:19,129 INFO MainThread:4188102 [wandb_init.py:init():1076] run started, returning control to user process
22
+ 2026-01-02 19:33:19,130 INFO MainThread:4188102 [wandb_run.py:_config_callback():1392] config_cb None None {'output_dir': '/home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_7B_multilayer_distill_aop_10_pooling_i_ret_12_30_h100_2_node_Classifier_L12_i_ret_bsz512', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 512, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0005, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1, 'max_steps': 1000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 100, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_7B_multilayer_distill_aop_10_pooling_i_ret_12_30_h100_2_node_Classifier_L12_i_ret_bsz512/runs/Jan02_19-23-27_GCRAZGDL1688', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 100, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': True, 'eval_steps': None, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'Qwen2_5vl_7B_multilayer_distill_aop_10_pooling_i_ret_12_30_h100_2_node_Classifier_L12_i_ret_bsz512', 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': True, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'image_encoder_freeze': False, 'resume_from': 'none', 'project_name': None, 'grad_cache': False, 'gc_q_chunk_size': 2, 'gc_p_chunk_size': 2, 'interleave_stopping_strategy': 'all_exhausted', 'interleave_batch_size': 0}
23
+ 2026-01-02 23:27:22,881 INFO wandb-AsyncioManager-main:4188102 [service_client.py:_forward_responses():80] Reached EOF.
24
+ 2026-01-02 23:27:22,881 INFO wandb-AsyncioManager-main:4188102 [mailbox.py:close():137] Closing mailbox, abandoning 1 handles.