Hugging Face's logo

MgGladys
/
SAS_3B_Classifier

Safetensors
Model card Files
xet
 Community
MgGladys commited on
Commit
3136cda
·
verified ·
1 Parent(s): 85033ff

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-20251231_205711-onkf9agw/files/wandb-summary.json +1 -0
  50. wandb/run-20251231_205711-onkf9agw/logs/debug-internal.log +11 -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": 0.026048450117218024,
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": 0.00026048450117218026,
14
+ "grad_norm": 6.6370320320129395,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.5389,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0005209690023443605,
21
+ "grad_norm": 7.1702704429626465,
22
+ "learning_rate": 5e-06,
23
+ "loss": 1.3234,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0007814535035165407,
28
+ "grad_norm": 8.348443984985352,
29
+ "learning_rate": 1e-05,
30
+ "loss": 1.2501,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.001041938004688721,
35
+ "grad_norm": 7.599966526031494,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 1.4676,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.0013024225058609013,
42
+ "grad_norm": 5.925275802612305,
43
+ "learning_rate": 2e-05,
44
+ "loss": 1.1892,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.0015629070070330815,
49
+ "grad_norm": 7.288003921508789,
50
+ "learning_rate": 2.5e-05,
51
+ "loss": 1.492,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0018233915082052619,
56
+ "grad_norm": 7.2629218101501465,
57
+ "learning_rate": 3e-05,
58
+ "loss": 1.3525,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.002083876009377442,
63
+ "grad_norm": 9.106829643249512,
64
+ "learning_rate": 3.5000000000000004e-05,
65
+ "loss": 1.6033,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0023443605105496223,
70
+ "grad_norm": 8.875594139099121,
71
+ "learning_rate": 4e-05,
72
+ "loss": 1.5238,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.0026048450117218025,
77
+ "grad_norm": 7.383709907531738,
78
+ "learning_rate": 4.4999999999999996e-05,
79
+ "loss": 1.4859,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.0028653295128939827,
84
+ "grad_norm": 7.463179111480713,
85
+ "learning_rate": 5e-05,
86
+ "loss": 1.3504,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.003125814014066163,
91
+ "grad_norm": 7.137135028839111,
92
+ "learning_rate": 5.5e-05,
93
+ "loss": 1.358,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.003386298515238343,
98
+ "grad_norm": 5.68809175491333,
99
+ "learning_rate": 6e-05,
100
+ "loss": 1.2017,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.0036467830164105238,
105
+ "grad_norm": 6.024169921875,
106
+ "learning_rate": 6.500000000000001e-05,
107
+ "loss": 1.1491,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.003907267517582704,
112
+ "grad_norm": 5.510103225708008,
113
+ "learning_rate": 7.000000000000001e-05,
114
+ "loss": 1.1809,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.004167752018754884,
119
+ "grad_norm": 6.086293697357178,
120
+ "learning_rate": 7.5e-05,
121
+ "loss": 1.2069,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.004428236519927064,
126
+ "grad_norm": 5.8847551345825195,
127
+ "learning_rate": 8e-05,
128
+ "loss": 1.2933,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.004688721021099245,
133
+ "grad_norm": 5.263647079467773,
134
+ "learning_rate": 8.5e-05,
135
+ "loss": 1.0476,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.004949205522271425,
140
+ "grad_norm": 5.684865951538086,
141
+ "learning_rate": 8.999999999999999e-05,
142
+ "loss": 1.1442,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.005209690023443605,
147
+ "grad_norm": 4.671970844268799,
148
+ "learning_rate": 9.5e-05,
149
+ "loss": 1.0422,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.005470174524615785,
154
+ "grad_norm": 7.935784816741943,
155
+ "learning_rate": 0.0001,
156
+ "loss": 1.1025,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.0057306590257879654,
161
+ "grad_norm": 4.634947299957275,
162
+ "learning_rate": 0.000105,
163
+ "loss": 0.9849,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.005991143526960146,
168
+ "grad_norm": 4.8161516189575195,
169
+ "learning_rate": 0.00011,
170
+ "loss": 0.9843,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.006251628028132326,
175
+ "grad_norm": 4.3339762687683105,
176
+ "learning_rate": 0.000115,
177
+ "loss": 0.8714,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.006512112529304506,
182
+ "grad_norm": 3.4047181606292725,
183
+ "learning_rate": 0.00012,
184
+ "loss": 0.8898,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.006772597030476686,
189
+ "grad_norm": 4.15224552154541,
190
+ "learning_rate": 0.000125,
191
+ "loss": 1.0079,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.0070330815316488665,
196
+ "grad_norm": 3.5006914138793945,
197
+ "learning_rate": 0.00013000000000000002,
198
+ "loss": 0.8013,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.0072935660328210476,
203
+ "grad_norm": 2.773101806640625,
204
+ "learning_rate": 0.000135,
205
+ "loss": 0.7086,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.007554050533993228,
210
+ "grad_norm": 2.4410135746002197,
211
+ "learning_rate": 0.00014000000000000001,
212
+ "loss": 0.7198,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.007814535035165408,
217
+ "grad_norm": 2.5674309730529785,
218
+ "learning_rate": 0.000145,
219
+ "loss": 0.6359,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.008075019536337588,
224
+ "grad_norm": 2.310837984085083,
225
+ "learning_rate": 0.00015,
226
+ "loss": 0.6039,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.008335504037509768,
231
+ "grad_norm": 2.4884161949157715,
232
+ "learning_rate": 0.000155,
233
+ "loss": 0.8962,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.008595988538681949,
238
+ "grad_norm": 5.428861141204834,
239
+ "learning_rate": 0.00016,
240
+ "loss": 0.5576,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.008856473039854129,
245
+ "grad_norm": 2.035452127456665,
246
+ "learning_rate": 0.000165,
247
+ "loss": 0.5866,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.009116957541026309,
252
+ "grad_norm": 4.757160663604736,
253
+ "learning_rate": 0.00017,
254
+ "loss": 0.4413,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.00937744204219849,
259
+ "grad_norm": 2.8071913719177246,
260
+ "learning_rate": 0.000175,
261
+ "loss": 0.7013,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.00963792654337067,
266
+ "grad_norm": 3.3390369415283203,
267
+ "learning_rate": 0.00017999999999999998,
268
+ "loss": 0.348,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.00989841104454285,
273
+ "grad_norm": 2.469451665878296,
274
+ "learning_rate": 0.000185,
275
+ "loss": 0.72,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.01015889554571503,
280
+ "grad_norm": 2.7830817699432373,
281
+ "learning_rate": 0.00019,
282
+ "loss": 0.671,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.01041938004688721,
287
+ "grad_norm": 3.005566358566284,
288
+ "learning_rate": 0.00019500000000000002,
289
+ "loss": 0.5808,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.01067986454805939,
294
+ "grad_norm": 2.8901026248931885,
295
+ "learning_rate": 0.0002,
296
+ "loss": 0.6022,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.01094034904923157,
301
+ "grad_norm": 2.004911422729492,
302
+ "learning_rate": 0.000205,
303
+ "loss": 0.525,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.01120083355040375,
308
+ "grad_norm": 2.9986109733581543,
309
+ "learning_rate": 0.00021,
310
+ "loss": 0.6073,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.011461318051575931,
315
+ "grad_norm": 3.4304168224334717,
316
+ "learning_rate": 0.000215,
317
+ "loss": 0.5203,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.011721802552748111,
322
+ "grad_norm": 2.295295000076294,
323
+ "learning_rate": 0.00022,
324
+ "loss": 0.3148,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.011982287053920291,
329
+ "grad_norm": 3.9490885734558105,
330
+ "learning_rate": 0.00022500000000000002,
331
+ "loss": 0.5378,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.012242771555092472,
336
+ "grad_norm": 2.3454151153564453,
337
+ "learning_rate": 0.00023,
338
+ "loss": 0.3085,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.012503256056264652,
343
+ "grad_norm": 2.9150779247283936,
344
+ "learning_rate": 0.000235,
345
+ "loss": 0.432,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.012763740557436832,
350
+ "grad_norm": 2.1253578662872314,
351
+ "learning_rate": 0.00024,
352
+ "loss": 0.1773,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.013024225058609012,
357
+ "grad_norm": 3.5161190032958984,
358
+ "learning_rate": 0.000245,
359
+ "loss": 0.581,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.013284709559781192,
364
+ "grad_norm": 1.8895039558410645,
365
+ "learning_rate": 0.00025,
366
+ "loss": 0.4554,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.013545194060953373,
371
+ "grad_norm": 1.1252281665802002,
372
+ "learning_rate": 0.000255,
373
+ "loss": 0.3409,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.013805678562125553,
378
+ "grad_norm": 2.6543619632720947,
379
+ "learning_rate": 0.00026000000000000003,
380
+ "loss": 0.594,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.014066163063297733,
385
+ "grad_norm": 3.3003315925598145,
386
+ "learning_rate": 0.00026500000000000004,
387
+ "loss": 0.5753,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.014326647564469915,
392
+ "grad_norm": 2.486830234527588,
393
+ "learning_rate": 0.00027,
394
+ "loss": 0.2907,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.014587132065642095,
399
+ "grad_norm": 1.5953302383422852,
400
+ "learning_rate": 0.000275,
401
+ "loss": 0.4006,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.014847616566814275,
406
+ "grad_norm": 1.8115977048873901,
407
+ "learning_rate": 0.00028000000000000003,
408
+ "loss": 0.2677,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.015108101067986456,
413
+ "grad_norm": 2.282597780227661,
414
+ "learning_rate": 0.000285,
415
+ "loss": 0.6526,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.015368585569158636,
420
+ "grad_norm": 1.4348944425582886,
421
+ "learning_rate": 0.00029,
422
+ "loss": 0.4291,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.015629070070330816,
427
+ "grad_norm": 2.0866997241973877,
428
+ "learning_rate": 0.000295,
429
+ "loss": 0.1811,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.015889554571502994,
434
+ "grad_norm": 1.6576564311981201,
435
+ "learning_rate": 0.0003,
436
+ "loss": 0.4088,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.016150039072675176,
441
+ "grad_norm": 1.635674238204956,
442
+ "learning_rate": 0.000305,
443
+ "loss": 0.4438,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.016410523573847355,
448
+ "grad_norm": 1.140415072441101,
449
+ "learning_rate": 0.00031,
450
+ "loss": 0.3589,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.016671008075019537,
455
+ "grad_norm": 1.7953686714172363,
456
+ "learning_rate": 0.000315,
457
+ "loss": 0.2778,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.016931492576191715,
462
+ "grad_norm": 2.2324233055114746,
463
+ "learning_rate": 0.00032,
464
+ "loss": 0.5049,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.017191977077363897,
469
+ "grad_norm": 2.036297559738159,
470
+ "learning_rate": 0.00032500000000000004,
471
+ "loss": 0.2636,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.017452461578536076,
476
+ "grad_norm": 2.2596747875213623,
477
+ "learning_rate": 0.00033,
478
+ "loss": 0.3743,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.017712946079708258,
483
+ "grad_norm": 1.6777313947677612,
484
+ "learning_rate": 0.000335,
485
+ "loss": 0.3978,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.017973430580880436,
490
+ "grad_norm": 1.6452847719192505,
491
+ "learning_rate": 0.00034,
492
+ "loss": 0.1836,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.018233915082052618,
497
+ "grad_norm": 1.7216978073120117,
498
+ "learning_rate": 0.000345,
499
+ "loss": 0.4191,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.018494399583224796,
504
+ "grad_norm": 1.7111387252807617,
505
+ "learning_rate": 0.00035,
506
+ "loss": 0.1812,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.01875488408439698,
511
+ "grad_norm": 1.6676584482192993,
512
+ "learning_rate": 0.000355,
513
+ "loss": 0.4526,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.019015368585569157,
518
+ "grad_norm": 0.9286651611328125,
519
+ "learning_rate": 0.00035999999999999997,
520
+ "loss": 0.2746,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.01927585308674134,
525
+ "grad_norm": 3.234783411026001,
526
+ "learning_rate": 0.000365,
527
+ "loss": 0.5224,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.01953633758791352,
532
+ "grad_norm": 1.3695653676986694,
533
+ "learning_rate": 0.00037,
534
+ "loss": 0.3308,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.0197968220890857,
539
+ "grad_norm": 2.9995968341827393,
540
+ "learning_rate": 0.000375,
541
+ "loss": 0.4817,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.02005730659025788,
546
+ "grad_norm": 1.8912553787231445,
547
+ "learning_rate": 0.00038,
548
+ "loss": 0.2722,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.02031779109143006,
553
+ "grad_norm": 1.3702706098556519,
554
+ "learning_rate": 0.00038500000000000003,
555
+ "loss": 0.1064,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.02057827559260224,
560
+ "grad_norm": 0.9273198246955872,
561
+ "learning_rate": 0.00039000000000000005,
562
+ "loss": 0.1233,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.02083876009377442,
567
+ "grad_norm": 0.8209530711174011,
568
+ "learning_rate": 0.000395,
569
+ "loss": 0.2622,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.021099244594946602,
574
+ "grad_norm": 1.4749599695205688,
575
+ "learning_rate": 0.0004,
576
+ "loss": 0.2999,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.02135972909611878,
581
+ "grad_norm": 1.1133017539978027,
582
+ "learning_rate": 0.00040500000000000003,
583
+ "loss": 0.2929,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.021620213597290962,
588
+ "grad_norm": 1.235826015472412,
589
+ "learning_rate": 0.00041,
590
+ "loss": 0.3106,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.02188069809846314,
595
+ "grad_norm": 0.9904353022575378,
596
+ "learning_rate": 0.000415,
597
+ "loss": 0.2101,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.022141182599635323,
602
+ "grad_norm": 1.2953742742538452,
603
+ "learning_rate": 0.00042,
604
+ "loss": 0.1131,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.0224016671008075,
609
+ "grad_norm": 1.10429048538208,
610
+ "learning_rate": 0.000425,
611
+ "loss": 0.2727,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.022662151601979683,
616
+ "grad_norm": 1.048660159111023,
617
+ "learning_rate": 0.00043,
618
+ "loss": 0.1082,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.022922636103151862,
623
+ "grad_norm": 0.857686460018158,
624
+ "learning_rate": 0.000435,
625
+ "loss": 0.1475,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.023183120604324044,
630
+ "grad_norm": 0.9353561401367188,
631
+ "learning_rate": 0.00044,
632
+ "loss": 0.2123,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.023443605105496222,
637
+ "grad_norm": 1.4590015411376953,
638
+ "learning_rate": 0.00044500000000000003,
639
+ "loss": 0.2988,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.023704089606668404,
644
+ "grad_norm": 0.9181132316589355,
645
+ "learning_rate": 0.00045000000000000004,
646
+ "loss": 0.2321,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.023964574107840583,
651
+ "grad_norm": 0.7688923478126526,
652
+ "learning_rate": 0.000455,
653
+ "loss": 0.16,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.024225058609012765,
658
+ "grad_norm": 1.0974979400634766,
659
+ "learning_rate": 0.00046,
660
+ "loss": 0.2135,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.024485543110184943,
665
+ "grad_norm": 1.083938717842102,
666
+ "learning_rate": 0.000465,
667
+ "loss": 0.1931,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.024746027611357125,
672
+ "grad_norm": 0.5162568688392639,
673
+ "learning_rate": 0.00047,
674
+ "loss": 0.0853,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.025006512112529303,
679
+ "grad_norm": 0.8454329967498779,
680
+ "learning_rate": 0.000475,
681
+ "loss": 0.1723,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.025266996613701485,
686
+ "grad_norm": 0.9237842559814453,
687
+ "learning_rate": 0.00048,
688
+ "loss": 0.1858,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.025527481114873664,
693
+ "grad_norm": 0.8391311168670654,
694
+ "learning_rate": 0.00048499999999999997,
695
+ "loss": 0.1558,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.025787965616045846,
700
+ "grad_norm": 0.7986068725585938,
701
+ "learning_rate": 0.00049,
702
+ "loss": 0.2043,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.026048450117218024,
707
+ "grad_norm": 0.3467917740345001,
708
+ "learning_rate": 0.000495,
709
+ "loss": 0.0386,
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": 256,
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": 0.13024225058609012,
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": 0.00026048450117218026,
14
+ "grad_norm": 6.6370320320129395,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.5389,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0005209690023443605,
21
+ "grad_norm": 7.1702704429626465,
22
+ "learning_rate": 5e-06,
23
+ "loss": 1.3234,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0007814535035165407,
28
+ "grad_norm": 8.348443984985352,
29
+ "learning_rate": 1e-05,
30
+ "loss": 1.2501,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.001041938004688721,
35
+ "grad_norm": 7.599966526031494,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 1.4676,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.0013024225058609013,
42
+ "grad_norm": 5.925275802612305,
43
+ "learning_rate": 2e-05,
44
+ "loss": 1.1892,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.0015629070070330815,
49
+ "grad_norm": 7.288003921508789,
50
+ "learning_rate": 2.5e-05,
51
+ "loss": 1.492,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0018233915082052619,
56
+ "grad_norm": 7.2629218101501465,
57
+ "learning_rate": 3e-05,
58
+ "loss": 1.3525,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.002083876009377442,
63
+ "grad_norm": 9.106829643249512,
64
+ "learning_rate": 3.5000000000000004e-05,
65
+ "loss": 1.6033,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0023443605105496223,
70
+ "grad_norm": 8.875594139099121,
71
+ "learning_rate": 4e-05,
72
+ "loss": 1.5238,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.0026048450117218025,
77
+ "grad_norm": 7.383709907531738,
78
+ "learning_rate": 4.4999999999999996e-05,
79
+ "loss": 1.4859,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.0028653295128939827,
84
+ "grad_norm": 7.463179111480713,
85
+ "learning_rate": 5e-05,
86
+ "loss": 1.3504,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.003125814014066163,
91
+ "grad_norm": 7.137135028839111,
92
+ "learning_rate": 5.5e-05,
93
+ "loss": 1.358,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.003386298515238343,
98
+ "grad_norm": 5.68809175491333,
99
+ "learning_rate": 6e-05,
100
+ "loss": 1.2017,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.0036467830164105238,
105
+ "grad_norm": 6.024169921875,
106
+ "learning_rate": 6.500000000000001e-05,
107
+ "loss": 1.1491,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.003907267517582704,
112
+ "grad_norm": 5.510103225708008,
113
+ "learning_rate": 7.000000000000001e-05,
114
+ "loss": 1.1809,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.004167752018754884,
119
+ "grad_norm": 6.086293697357178,
120
+ "learning_rate": 7.5e-05,
121
+ "loss": 1.2069,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.004428236519927064,
126
+ "grad_norm": 5.8847551345825195,
127
+ "learning_rate": 8e-05,
128
+ "loss": 1.2933,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.004688721021099245,
133
+ "grad_norm": 5.263647079467773,
134
+ "learning_rate": 8.5e-05,
135
+ "loss": 1.0476,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.004949205522271425,
140
+ "grad_norm": 5.684865951538086,
141
+ "learning_rate": 8.999999999999999e-05,
142
+ "loss": 1.1442,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.005209690023443605,
147
+ "grad_norm": 4.671970844268799,
148
+ "learning_rate": 9.5e-05,
149
+ "loss": 1.0422,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.005470174524615785,
154
+ "grad_norm": 7.935784816741943,
155
+ "learning_rate": 0.0001,
156
+ "loss": 1.1025,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.0057306590257879654,
161
+ "grad_norm": 4.634947299957275,
162
+ "learning_rate": 0.000105,
163
+ "loss": 0.9849,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.005991143526960146,
168
+ "grad_norm": 4.8161516189575195,
169
+ "learning_rate": 0.00011,
170
+ "loss": 0.9843,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.006251628028132326,
175
+ "grad_norm": 4.3339762687683105,
176
+ "learning_rate": 0.000115,
177
+ "loss": 0.8714,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.006512112529304506,
182
+ "grad_norm": 3.4047181606292725,
183
+ "learning_rate": 0.00012,
184
+ "loss": 0.8898,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.006772597030476686,
189
+ "grad_norm": 4.15224552154541,
190
+ "learning_rate": 0.000125,
191
+ "loss": 1.0079,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.0070330815316488665,
196
+ "grad_norm": 3.5006914138793945,
197
+ "learning_rate": 0.00013000000000000002,
198
+ "loss": 0.8013,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.0072935660328210476,
203
+ "grad_norm": 2.773101806640625,
204
+ "learning_rate": 0.000135,
205
+ "loss": 0.7086,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.007554050533993228,
210
+ "grad_norm": 2.4410135746002197,
211
+ "learning_rate": 0.00014000000000000001,
212
+ "loss": 0.7198,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.007814535035165408,
217
+ "grad_norm": 2.5674309730529785,
218
+ "learning_rate": 0.000145,
219
+ "loss": 0.6359,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.008075019536337588,
224
+ "grad_norm": 2.310837984085083,
225
+ "learning_rate": 0.00015,
226
+ "loss": 0.6039,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.008335504037509768,
231
+ "grad_norm": 2.4884161949157715,
232
+ "learning_rate": 0.000155,
233
+ "loss": 0.8962,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.008595988538681949,
238
+ "grad_norm": 5.428861141204834,
239
+ "learning_rate": 0.00016,
240
+ "loss": 0.5576,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.008856473039854129,
245
+ "grad_norm": 2.035452127456665,
246
+ "learning_rate": 0.000165,
247
+ "loss": 0.5866,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.009116957541026309,
252
+ "grad_norm": 4.757160663604736,
253
+ "learning_rate": 0.00017,
254
+ "loss": 0.4413,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.00937744204219849,
259
+ "grad_norm": 2.8071913719177246,
260
+ "learning_rate": 0.000175,
261
+ "loss": 0.7013,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.00963792654337067,
266
+ "grad_norm": 3.3390369415283203,
267
+ "learning_rate": 0.00017999999999999998,
268
+ "loss": 0.348,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.00989841104454285,
273
+ "grad_norm": 2.469451665878296,
274
+ "learning_rate": 0.000185,
275
+ "loss": 0.72,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.01015889554571503,
280
+ "grad_norm": 2.7830817699432373,
281
+ "learning_rate": 0.00019,
282
+ "loss": 0.671,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.01041938004688721,
287
+ "grad_norm": 3.005566358566284,
288
+ "learning_rate": 0.00019500000000000002,
289
+ "loss": 0.5808,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.01067986454805939,
294
+ "grad_norm": 2.8901026248931885,
295
+ "learning_rate": 0.0002,
296
+ "loss": 0.6022,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.01094034904923157,
301
+ "grad_norm": 2.004911422729492,
302
+ "learning_rate": 0.000205,
303
+ "loss": 0.525,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.01120083355040375,
308
+ "grad_norm": 2.9986109733581543,
309
+ "learning_rate": 0.00021,
310
+ "loss": 0.6073,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.011461318051575931,
315
+ "grad_norm": 3.4304168224334717,
316
+ "learning_rate": 0.000215,
317
+ "loss": 0.5203,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.011721802552748111,
322
+ "grad_norm": 2.295295000076294,
323
+ "learning_rate": 0.00022,
324
+ "loss": 0.3148,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.011982287053920291,
329
+ "grad_norm": 3.9490885734558105,
330
+ "learning_rate": 0.00022500000000000002,
331
+ "loss": 0.5378,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.012242771555092472,
336
+ "grad_norm": 2.3454151153564453,
337
+ "learning_rate": 0.00023,
338
+ "loss": 0.3085,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.012503256056264652,
343
+ "grad_norm": 2.9150779247283936,
344
+ "learning_rate": 0.000235,
345
+ "loss": 0.432,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.012763740557436832,
350
+ "grad_norm": 2.1253578662872314,
351
+ "learning_rate": 0.00024,
352
+ "loss": 0.1773,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.013024225058609012,
357
+ "grad_norm": 3.5161190032958984,
358
+ "learning_rate": 0.000245,
359
+ "loss": 0.581,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.013284709559781192,
364
+ "grad_norm": 1.8895039558410645,
365
+ "learning_rate": 0.00025,
366
+ "loss": 0.4554,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.013545194060953373,
371
+ "grad_norm": 1.1252281665802002,
372
+ "learning_rate": 0.000255,
373
+ "loss": 0.3409,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.013805678562125553,
378
+ "grad_norm": 2.6543619632720947,
379
+ "learning_rate": 0.00026000000000000003,
380
+ "loss": 0.594,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.014066163063297733,
385
+ "grad_norm": 3.3003315925598145,
386
+ "learning_rate": 0.00026500000000000004,
387
+ "loss": 0.5753,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.014326647564469915,
392
+ "grad_norm": 2.486830234527588,
393
+ "learning_rate": 0.00027,
394
+ "loss": 0.2907,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.014587132065642095,
399
+ "grad_norm": 1.5953302383422852,
400
+ "learning_rate": 0.000275,
401
+ "loss": 0.4006,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.014847616566814275,
406
+ "grad_norm": 1.8115977048873901,
407
+ "learning_rate": 0.00028000000000000003,
408
+ "loss": 0.2677,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.015108101067986456,
413
+ "grad_norm": 2.282597780227661,
414
+ "learning_rate": 0.000285,
415
+ "loss": 0.6526,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.015368585569158636,
420
+ "grad_norm": 1.4348944425582886,
421
+ "learning_rate": 0.00029,
422
+ "loss": 0.4291,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.015629070070330816,
427
+ "grad_norm": 2.0866997241973877,
428
+ "learning_rate": 0.000295,
429
+ "loss": 0.1811,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.015889554571502994,
434
+ "grad_norm": 1.6576564311981201,
435
+ "learning_rate": 0.0003,
436
+ "loss": 0.4088,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.016150039072675176,
441
+ "grad_norm": 1.635674238204956,
442
+ "learning_rate": 0.000305,
443
+ "loss": 0.4438,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.016410523573847355,
448
+ "grad_norm": 1.140415072441101,
449
+ "learning_rate": 0.00031,
450
+ "loss": 0.3589,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.016671008075019537,
455
+ "grad_norm": 1.7953686714172363,
456
+ "learning_rate": 0.000315,
457
+ "loss": 0.2778,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.016931492576191715,
462
+ "grad_norm": 2.2324233055114746,
463
+ "learning_rate": 0.00032,
464
+ "loss": 0.5049,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.017191977077363897,
469
+ "grad_norm": 2.036297559738159,
470
+ "learning_rate": 0.00032500000000000004,
471
+ "loss": 0.2636,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.017452461578536076,
476
+ "grad_norm": 2.2596747875213623,
477
+ "learning_rate": 0.00033,
478
+ "loss": 0.3743,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.017712946079708258,
483
+ "grad_norm": 1.6777313947677612,
484
+ "learning_rate": 0.000335,
485
+ "loss": 0.3978,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.017973430580880436,
490
+ "grad_norm": 1.6452847719192505,
491
+ "learning_rate": 0.00034,
492
+ "loss": 0.1836,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.018233915082052618,
497
+ "grad_norm": 1.7216978073120117,
498
+ "learning_rate": 0.000345,
499
+ "loss": 0.4191,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.018494399583224796,
504
+ "grad_norm": 1.7111387252807617,
505
+ "learning_rate": 0.00035,
506
+ "loss": 0.1812,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.01875488408439698,
511
+ "grad_norm": 1.6676584482192993,
512
+ "learning_rate": 0.000355,
513
+ "loss": 0.4526,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.019015368585569157,
518
+ "grad_norm": 0.9286651611328125,
519
+ "learning_rate": 0.00035999999999999997,
520
+ "loss": 0.2746,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.01927585308674134,
525
+ "grad_norm": 3.234783411026001,
526
+ "learning_rate": 0.000365,
527
+ "loss": 0.5224,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.01953633758791352,
532
+ "grad_norm": 1.3695653676986694,
533
+ "learning_rate": 0.00037,
534
+ "loss": 0.3308,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.0197968220890857,
539
+ "grad_norm": 2.9995968341827393,
540
+ "learning_rate": 0.000375,
541
+ "loss": 0.4817,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.02005730659025788,
546
+ "grad_norm": 1.8912553787231445,
547
+ "learning_rate": 0.00038,
548
+ "loss": 0.2722,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.02031779109143006,
553
+ "grad_norm": 1.3702706098556519,
554
+ "learning_rate": 0.00038500000000000003,
555
+ "loss": 0.1064,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.02057827559260224,
560
+ "grad_norm": 0.9273198246955872,
561
+ "learning_rate": 0.00039000000000000005,
562
+ "loss": 0.1233,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.02083876009377442,
567
+ "grad_norm": 0.8209530711174011,
568
+ "learning_rate": 0.000395,
569
+ "loss": 0.2622,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.021099244594946602,
574
+ "grad_norm": 1.4749599695205688,
575
+ "learning_rate": 0.0004,
576
+ "loss": 0.2999,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.02135972909611878,
581
+ "grad_norm": 1.1133017539978027,
582
+ "learning_rate": 0.00040500000000000003,
583
+ "loss": 0.2929,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.021620213597290962,
588
+ "grad_norm": 1.235826015472412,
589
+ "learning_rate": 0.00041,
590
+ "loss": 0.3106,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.02188069809846314,
595
+ "grad_norm": 0.9904353022575378,
596
+ "learning_rate": 0.000415,
597
+ "loss": 0.2101,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.022141182599635323,
602
+ "grad_norm": 1.2953742742538452,
603
+ "learning_rate": 0.00042,
604
+ "loss": 0.1131,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.0224016671008075,
609
+ "grad_norm": 1.10429048538208,
610
+ "learning_rate": 0.000425,
611
+ "loss": 0.2727,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.022662151601979683,
616
+ "grad_norm": 1.048660159111023,
617
+ "learning_rate": 0.00043,
618
+ "loss": 0.1082,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.022922636103151862,
623
+ "grad_norm": 0.857686460018158,
624
+ "learning_rate": 0.000435,
625
+ "loss": 0.1475,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.023183120604324044,
630
+ "grad_norm": 0.9353561401367188,
631
+ "learning_rate": 0.00044,
632
+ "loss": 0.2123,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.023443605105496222,
637
+ "grad_norm": 1.4590015411376953,
638
+ "learning_rate": 0.00044500000000000003,
639
+ "loss": 0.2988,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.023704089606668404,
644
+ "grad_norm": 0.9181132316589355,
645
+ "learning_rate": 0.00045000000000000004,
646
+ "loss": 0.2321,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.023964574107840583,
651
+ "grad_norm": 0.7688923478126526,
652
+ "learning_rate": 0.000455,
653
+ "loss": 0.16,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.024225058609012765,
658
+ "grad_norm": 1.0974979400634766,
659
+ "learning_rate": 0.00046,
660
+ "loss": 0.2135,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.024485543110184943,
665
+ "grad_norm": 1.083938717842102,
666
+ "learning_rate": 0.000465,
667
+ "loss": 0.1931,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.024746027611357125,
672
+ "grad_norm": 0.5162568688392639,
673
+ "learning_rate": 0.00047,
674
+ "loss": 0.0853,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.025006512112529303,
679
+ "grad_norm": 0.8454329967498779,
680
+ "learning_rate": 0.000475,
681
+ "loss": 0.1723,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.025266996613701485,
686
+ "grad_norm": 0.9237842559814453,
687
+ "learning_rate": 0.00048,
688
+ "loss": 0.1858,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.025527481114873664,
693
+ "grad_norm": 0.8391311168670654,
694
+ "learning_rate": 0.00048499999999999997,
695
+ "loss": 0.1558,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.025787965616045846,
700
+ "grad_norm": 0.7986068725585938,
701
+ "learning_rate": 0.00049,
702
+ "loss": 0.2043,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.026048450117218024,
707
+ "grad_norm": 0.3467917740345001,
708
+ "learning_rate": 0.000495,
709
+ "loss": 0.0386,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.026308934618390206,
714
+ "grad_norm": 1.4537785053253174,
715
+ "learning_rate": 0.0005,
716
+ "loss": 0.2298,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.026569419119562385,
721
+ "grad_norm": 0.5565273761749268,
722
+ "learning_rate": 0.0004994444444444445,
723
+ "loss": 0.0893,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.026829903620734567,
728
+ "grad_norm": 0.5200175642967224,
729
+ "learning_rate": 0.0004988888888888889,
730
+ "loss": 0.1191,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.027090388121906745,
735
+ "grad_norm": 0.8346852660179138,
736
+ "learning_rate": 0.0004983333333333334,
737
+ "loss": 0.1709,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.027350872623078927,
742
+ "grad_norm": 0.6015453934669495,
743
+ "learning_rate": 0.0004977777777777778,
744
+ "loss": 0.1095,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.027611357124251105,
749
+ "grad_norm": 0.5995053052902222,
750
+ "learning_rate": 0.0004972222222222222,
751
+ "loss": 0.1382,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.027871841625423287,
756
+ "grad_norm": 0.857565701007843,
757
+ "learning_rate": 0.0004966666666666666,
758
+ "loss": 0.1751,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.028132326126595466,
763
+ "grad_norm": 0.561795175075531,
764
+ "learning_rate": 0.0004961111111111111,
765
+ "loss": 0.1364,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.028392810627767648,
770
+ "grad_norm": 0.6582000851631165,
771
+ "learning_rate": 0.0004955555555555556,
772
+ "loss": 0.1348,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.02865329512893983,
777
+ "grad_norm": 0.5225309729576111,
778
+ "learning_rate": 0.000495,
779
+ "loss": 0.0939,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.02891377963011201,
784
+ "grad_norm": 0.6684510707855225,
785
+ "learning_rate": 0.0004944444444444445,
786
+ "loss": 0.1658,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.02917426413128419,
791
+ "grad_norm": 0.6758474111557007,
792
+ "learning_rate": 0.0004938888888888889,
793
+ "loss": 0.0703,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.02943474863245637,
798
+ "grad_norm": 0.7549937963485718,
799
+ "learning_rate": 0.0004933333333333334,
800
+ "loss": 0.0794,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.02969523313362855,
805
+ "grad_norm": 0.4596688747406006,
806
+ "learning_rate": 0.0004927777777777777,
807
+ "loss": 0.1018,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.02995571763480073,
812
+ "grad_norm": 0.48921626806259155,
813
+ "learning_rate": 0.0004922222222222222,
814
+ "loss": 0.1206,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.03021620213597291,
819
+ "grad_norm": 0.5874961614608765,
820
+ "learning_rate": 0.0004916666666666666,
821
+ "loss": 0.1024,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.03047668663714509,
826
+ "grad_norm": 0.4092181921005249,
827
+ "learning_rate": 0.0004911111111111111,
828
+ "loss": 0.1152,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.03073717113831727,
833
+ "grad_norm": 0.731638491153717,
834
+ "learning_rate": 0.0004905555555555556,
835
+ "loss": 0.1052,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.03099765563948945,
840
+ "grad_norm": 0.5791296362876892,
841
+ "learning_rate": 0.00049,
842
+ "loss": 0.1155,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.03125814014066163,
847
+ "grad_norm": 0.524922788143158,
848
+ "learning_rate": 0.0004894444444444445,
849
+ "loss": 0.1225,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.03151862464183381,
854
+ "grad_norm": 0.43153440952301025,
855
+ "learning_rate": 0.0004888888888888889,
856
+ "loss": 0.1042,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.03177910914300599,
861
+ "grad_norm": 0.5489442348480225,
862
+ "learning_rate": 0.0004883333333333333,
863
+ "loss": 0.0436,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.032039593644178174,
868
+ "grad_norm": 0.47173041105270386,
869
+ "learning_rate": 0.0004877777777777778,
870
+ "loss": 0.0986,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.03230007814535035,
875
+ "grad_norm": 0.6360733509063721,
876
+ "learning_rate": 0.0004872222222222222,
877
+ "loss": 0.1181,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.03256056264652253,
882
+ "grad_norm": 0.294552743434906,
883
+ "learning_rate": 0.0004866666666666667,
884
+ "loss": 0.0407,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.03282104714769471,
889
+ "grad_norm": 0.44740888476371765,
890
+ "learning_rate": 0.0004861111111111111,
891
+ "loss": 0.0477,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.033081531648866895,
896
+ "grad_norm": 0.8320237398147583,
897
+ "learning_rate": 0.0004855555555555556,
898
+ "loss": 0.1399,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.033342016150039074,
903
+ "grad_norm": 0.4137701392173767,
904
+ "learning_rate": 0.00048499999999999997,
905
+ "loss": 0.1035,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.03360250065121125,
910
+ "grad_norm": 0.6063897609710693,
911
+ "learning_rate": 0.00048444444444444446,
912
+ "loss": 0.1225,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.03386298515238343,
917
+ "grad_norm": 0.3804122507572174,
918
+ "learning_rate": 0.0004838888888888889,
919
+ "loss": 0.0626,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.034123469653555616,
924
+ "grad_norm": 0.370593398809433,
925
+ "learning_rate": 0.00048333333333333334,
926
+ "loss": 0.0533,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.034383954154727794,
931
+ "grad_norm": 0.5119293928146362,
932
+ "learning_rate": 0.0004827777777777778,
933
+ "loss": 0.1296,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.03464443865589997,
938
+ "grad_norm": 0.3838193118572235,
939
+ "learning_rate": 0.0004822222222222222,
940
+ "loss": 0.0839,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.03490492315707215,
945
+ "grad_norm": 0.36693644523620605,
946
+ "learning_rate": 0.0004816666666666667,
947
+ "loss": 0.0754,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.03516540765824434,
952
+ "grad_norm": 0.3589820861816406,
953
+ "learning_rate": 0.0004811111111111111,
954
+ "loss": 0.0829,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.035425892159416515,
959
+ "grad_norm": 0.5229784250259399,
960
+ "learning_rate": 0.0004805555555555556,
961
+ "loss": 0.0547,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.035686376660588694,
966
+ "grad_norm": 0.4046158194541931,
967
+ "learning_rate": 0.00048,
968
+ "loss": 0.1089,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.03594686116176087,
973
+ "grad_norm": 0.3599977195262909,
974
+ "learning_rate": 0.00047944444444444445,
975
+ "loss": 0.0847,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.03620734566293306,
980
+ "grad_norm": 0.4707350730895996,
981
+ "learning_rate": 0.0004788888888888889,
982
+ "loss": 0.0469,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.036467830164105236,
987
+ "grad_norm": 0.43708017468452454,
988
+ "learning_rate": 0.0004783333333333333,
989
+ "loss": 0.1026,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.036728314665277415,
994
+ "grad_norm": 0.38362443447113037,
995
+ "learning_rate": 0.0004777777777777778,
996
+ "loss": 0.081,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.03698879916644959,
1001
+ "grad_norm": 0.3944476842880249,
1002
+ "learning_rate": 0.00047722222222222225,
1003
+ "loss": 0.0975,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.03724928366762178,
1008
+ "grad_norm": 0.3799622356891632,
1009
+ "learning_rate": 0.0004766666666666667,
1010
+ "loss": 0.0762,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.03750976816879396,
1015
+ "grad_norm": 0.26444610953330994,
1016
+ "learning_rate": 0.0004761111111111111,
1017
+ "loss": 0.0391,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.037770252669966135,
1022
+ "grad_norm": 0.2609337866306305,
1023
+ "learning_rate": 0.00047555555555555556,
1024
+ "loss": 0.0339,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.038030737171138314,
1029
+ "grad_norm": 0.31581151485443115,
1030
+ "learning_rate": 0.000475,
1031
+ "loss": 0.0478,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.0382912216723105,
1036
+ "grad_norm": 0.24990220367908478,
1037
+ "learning_rate": 0.00047444444444444444,
1038
+ "loss": 0.0547,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.03855170617348268,
1043
+ "grad_norm": 0.25984567403793335,
1044
+ "learning_rate": 0.00047388888888888893,
1045
+ "loss": 0.0292,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.038812190674654856,
1050
+ "grad_norm": 0.2555845379829407,
1051
+ "learning_rate": 0.00047333333333333336,
1052
+ "loss": 0.0603,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.03907267517582704,
1057
+ "grad_norm": 0.2423526793718338,
1058
+ "learning_rate": 0.0004727777777777778,
1059
+ "loss": 0.0433,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.03933315967699922,
1064
+ "grad_norm": 0.3917102813720703,
1065
+ "learning_rate": 0.00047222222222222224,
1066
+ "loss": 0.0856,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.0395936441781714,
1071
+ "grad_norm": 0.25814005732536316,
1072
+ "learning_rate": 0.0004716666666666667,
1073
+ "loss": 0.03,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.03985412867934358,
1078
+ "grad_norm": 0.5332754254341125,
1079
+ "learning_rate": 0.0004711111111111111,
1080
+ "loss": 0.0926,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.04011461318051576,
1085
+ "grad_norm": 0.41863763332366943,
1086
+ "learning_rate": 0.00047055555555555555,
1087
+ "loss": 0.0781,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.04037509768168794,
1092
+ "grad_norm": 0.18758471310138702,
1093
+ "learning_rate": 0.00047,
1094
+ "loss": 0.02,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.04063558218286012,
1099
+ "grad_norm": 0.4820327162742615,
1100
+ "learning_rate": 0.0004694444444444445,
1101
+ "loss": 0.0925,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.0408960666840323,
1106
+ "grad_norm": 0.35083940625190735,
1107
+ "learning_rate": 0.0004688888888888889,
1108
+ "loss": 0.0765,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.04115655118520448,
1113
+ "grad_norm": 0.17448937892913818,
1114
+ "learning_rate": 0.00046833333333333335,
1115
+ "loss": 0.0336,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.04141703568637666,
1120
+ "grad_norm": 0.2029111683368683,
1121
+ "learning_rate": 0.0004677777777777778,
1122
+ "loss": 0.0254,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.04167752018754884,
1127
+ "grad_norm": 0.362997442483902,
1128
+ "learning_rate": 0.0004672222222222222,
1129
+ "loss": 0.065,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.04193800468872102,
1134
+ "grad_norm": 0.17652612924575806,
1135
+ "learning_rate": 0.00046666666666666666,
1136
+ "loss": 0.0459,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.042198489189893204,
1141
+ "grad_norm": 0.3325017988681793,
1142
+ "learning_rate": 0.0004661111111111111,
1143
+ "loss": 0.0725,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.04245897369106538,
1148
+ "grad_norm": 0.2500215172767639,
1149
+ "learning_rate": 0.0004655555555555556,
1150
+ "loss": 0.0643,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.04271945819223756,
1155
+ "grad_norm": 0.2853871285915375,
1156
+ "learning_rate": 0.000465,
1157
+ "loss": 0.0267,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.04297994269340974,
1162
+ "grad_norm": 0.19212019443511963,
1163
+ "learning_rate": 0.00046444444444444446,
1164
+ "loss": 0.0423,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.043240427194581925,
1169
+ "grad_norm": 0.5235925316810608,
1170
+ "learning_rate": 0.0004638888888888889,
1171
+ "loss": 0.1148,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.0435009116957541,
1176
+ "grad_norm": 0.27955177426338196,
1177
+ "learning_rate": 0.00046333333333333334,
1178
+ "loss": 0.0639,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.04376139619692628,
1183
+ "grad_norm": 0.21516919136047363,
1184
+ "learning_rate": 0.0004627777777777778,
1185
+ "loss": 0.0604,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.04402188069809846,
1190
+ "grad_norm": 0.23670804500579834,
1191
+ "learning_rate": 0.0004622222222222222,
1192
+ "loss": 0.0622,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.044282365199270646,
1197
+ "grad_norm": 0.2706695795059204,
1198
+ "learning_rate": 0.0004616666666666667,
1199
+ "loss": 0.0689,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.044542849700442824,
1204
+ "grad_norm": 0.29786598682403564,
1205
+ "learning_rate": 0.00046111111111111114,
1206
+ "loss": 0.0594,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.044803334201615,
1211
+ "grad_norm": 0.24643343687057495,
1212
+ "learning_rate": 0.0004605555555555556,
1213
+ "loss": 0.0708,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.04506381870278718,
1218
+ "grad_norm": 0.299601286649704,
1219
+ "learning_rate": 0.00046,
1220
+ "loss": 0.0747,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.04532430320395937,
1225
+ "grad_norm": 0.3954971432685852,
1226
+ "learning_rate": 0.00045944444444444445,
1227
+ "loss": 0.0777,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.045584787705131545,
1232
+ "grad_norm": 0.21053896844387054,
1233
+ "learning_rate": 0.0004588888888888889,
1234
+ "loss": 0.0515,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.045845272206303724,
1239
+ "grad_norm": 0.2881135642528534,
1240
+ "learning_rate": 0.0004583333333333333,
1241
+ "loss": 0.0686,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.0461057567074759,
1246
+ "grad_norm": 0.283166766166687,
1247
+ "learning_rate": 0.0004577777777777778,
1248
+ "loss": 0.0365,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.04636624120864809,
1253
+ "grad_norm": 0.24174754321575165,
1254
+ "learning_rate": 0.0004572222222222222,
1255
+ "loss": 0.0647,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.046626725709820266,
1260
+ "grad_norm": 0.24825502932071686,
1261
+ "learning_rate": 0.0004566666666666667,
1262
+ "loss": 0.0673,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.046887210210992444,
1267
+ "grad_norm": 0.2801763117313385,
1268
+ "learning_rate": 0.0004561111111111111,
1269
+ "loss": 0.0284,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.04714769471216462,
1274
+ "grad_norm": 0.3177853226661682,
1275
+ "learning_rate": 0.00045555555555555556,
1276
+ "loss": 0.0751,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.04740817921333681,
1281
+ "grad_norm": 0.2763389050960541,
1282
+ "learning_rate": 0.000455,
1283
+ "loss": 0.0491,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.04766866371450899,
1288
+ "grad_norm": 0.2378890961408615,
1289
+ "learning_rate": 0.00045444444444444444,
1290
+ "loss": 0.0527,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.047929148215681165,
1295
+ "grad_norm": 0.24222926795482635,
1296
+ "learning_rate": 0.00045388888888888893,
1297
+ "loss": 0.0664,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.04818963271685335,
1302
+ "grad_norm": 0.23114658892154694,
1303
+ "learning_rate": 0.0004533333333333333,
1304
+ "loss": 0.0494,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.04845011721802553,
1309
+ "grad_norm": 0.22762534022331238,
1310
+ "learning_rate": 0.0004527777777777778,
1311
+ "loss": 0.071,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.04871060171919771,
1316
+ "grad_norm": 0.2370385229587555,
1317
+ "learning_rate": 0.00045222222222222224,
1318
+ "loss": 0.0387,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.048971086220369886,
1323
+ "grad_norm": 0.22486446797847748,
1324
+ "learning_rate": 0.0004516666666666667,
1325
+ "loss": 0.0547,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.04923157072154207,
1330
+ "grad_norm": 0.20467261970043182,
1331
+ "learning_rate": 0.0004511111111111111,
1332
+ "loss": 0.0623,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.04949205522271425,
1337
+ "grad_norm": 0.1958482414484024,
1338
+ "learning_rate": 0.00045055555555555555,
1339
+ "loss": 0.038,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.04975253972388643,
1344
+ "grad_norm": 0.2064603567123413,
1345
+ "learning_rate": 0.00045000000000000004,
1346
+ "loss": 0.0485,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.05001302422505861,
1351
+ "grad_norm": 0.21092765033245087,
1352
+ "learning_rate": 0.0004494444444444444,
1353
+ "loss": 0.0401,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.05027350872623079,
1358
+ "grad_norm": 0.19756095111370087,
1359
+ "learning_rate": 0.0004488888888888889,
1360
+ "loss": 0.0498,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.05053399322740297,
1365
+ "grad_norm": 0.21518975496292114,
1366
+ "learning_rate": 0.0004483333333333333,
1367
+ "loss": 0.0166,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.05079447772857515,
1372
+ "grad_norm": 0.2586614489555359,
1373
+ "learning_rate": 0.0004477777777777778,
1374
+ "loss": 0.0551,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.05105496222974733,
1379
+ "grad_norm": 0.2525339126586914,
1380
+ "learning_rate": 0.0004472222222222222,
1381
+ "loss": 0.0576,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.05131544673091951,
1386
+ "grad_norm": 0.26852843165397644,
1387
+ "learning_rate": 0.00044666666666666666,
1388
+ "loss": 0.0457,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.05157593123209169,
1393
+ "grad_norm": 0.2254427671432495,
1394
+ "learning_rate": 0.00044611111111111115,
1395
+ "loss": 0.0414,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.05183641573326387,
1400
+ "grad_norm": 0.14540040493011475,
1401
+ "learning_rate": 0.00044555555555555554,
1402
+ "loss": 0.0223,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.05209690023443605,
1407
+ "grad_norm": 0.21755613386631012,
1408
+ "learning_rate": 0.00044500000000000003,
1409
+ "loss": 0.0495,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.052357384735608234,
1414
+ "grad_norm": 0.33412784337997437,
1415
+ "learning_rate": 0.0004444444444444444,
1416
+ "loss": 0.063,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.05261786923678041,
1421
+ "grad_norm": 0.30330124497413635,
1422
+ "learning_rate": 0.0004438888888888889,
1423
+ "loss": 0.0639,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.05287835373795259,
1428
+ "grad_norm": 0.3984980583190918,
1429
+ "learning_rate": 0.00044333333333333334,
1430
+ "loss": 0.0699,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.05313883823912477,
1435
+ "grad_norm": 0.22607579827308655,
1436
+ "learning_rate": 0.0004427777777777778,
1437
+ "loss": 0.0498,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 0.053399322740296955,
1442
+ "grad_norm": 0.20679153501987457,
1443
+ "learning_rate": 0.00044222222222222227,
1444
+ "loss": 0.0608,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 0.05365980724146913,
1449
+ "grad_norm": 0.2578828036785126,
1450
+ "learning_rate": 0.00044166666666666665,
1451
+ "loss": 0.0686,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 0.05392029174264131,
1456
+ "grad_norm": 0.20136725902557373,
1457
+ "learning_rate": 0.00044111111111111114,
1458
+ "loss": 0.0314,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 0.05418077624381349,
1463
+ "grad_norm": 0.2162970006465912,
1464
+ "learning_rate": 0.0004405555555555555,
1465
+ "loss": 0.0275,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 0.054441260744985676,
1470
+ "grad_norm": 0.22596463561058044,
1471
+ "learning_rate": 0.00044,
1472
+ "loss": 0.05,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 0.054701745246157854,
1477
+ "grad_norm": 0.21236006915569305,
1478
+ "learning_rate": 0.0004394444444444445,
1479
+ "loss": 0.0634,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 0.05496222974733003,
1484
+ "grad_norm": 0.22657150030136108,
1485
+ "learning_rate": 0.0004388888888888889,
1486
+ "loss": 0.0194,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 0.05522271424850221,
1491
+ "grad_norm": 0.2614911198616028,
1492
+ "learning_rate": 0.0004383333333333334,
1493
+ "loss": 0.0223,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 0.055483198749674396,
1498
+ "grad_norm": 0.19223269820213318,
1499
+ "learning_rate": 0.00043777777777777776,
1500
+ "loss": 0.0342,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 0.055743683250846575,
1505
+ "grad_norm": 0.16092517971992493,
1506
+ "learning_rate": 0.00043722222222222225,
1507
+ "loss": 0.0264,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 0.05600416775201875,
1512
+ "grad_norm": 0.17417079210281372,
1513
+ "learning_rate": 0.00043666666666666664,
1514
+ "loss": 0.0235,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 0.05626465225319093,
1519
+ "grad_norm": 0.22072814404964447,
1520
+ "learning_rate": 0.00043611111111111113,
1521
+ "loss": 0.0431,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 0.05652513675436312,
1526
+ "grad_norm": 0.27902325987815857,
1527
+ "learning_rate": 0.0004355555555555555,
1528
+ "loss": 0.0578,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 0.056785621255535296,
1533
+ "grad_norm": 0.14471304416656494,
1534
+ "learning_rate": 0.000435,
1535
+ "loss": 0.0272,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 0.057046105756707474,
1540
+ "grad_norm": 0.19169339537620544,
1541
+ "learning_rate": 0.0004344444444444445,
1542
+ "loss": 0.0516,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 0.05730659025787966,
1547
+ "grad_norm": 0.2244272381067276,
1548
+ "learning_rate": 0.0004338888888888889,
1549
+ "loss": 0.046,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 0.05756707475905184,
1554
+ "grad_norm": 0.12852348387241364,
1555
+ "learning_rate": 0.00043333333333333337,
1556
+ "loss": 0.0373,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 0.05782755926022402,
1561
+ "grad_norm": 0.2068084180355072,
1562
+ "learning_rate": 0.00043277777777777775,
1563
+ "loss": 0.0597,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 0.058088043761396195,
1568
+ "grad_norm": 0.2222401201725006,
1569
+ "learning_rate": 0.00043222222222222224,
1570
+ "loss": 0.0412,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 0.05834852826256838,
1575
+ "grad_norm": 0.22024814784526825,
1576
+ "learning_rate": 0.0004316666666666667,
1577
+ "loss": 0.045,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 0.05860901276374056,
1582
+ "grad_norm": 0.1876782774925232,
1583
+ "learning_rate": 0.0004311111111111111,
1584
+ "loss": 0.0433,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 0.05886949726491274,
1589
+ "grad_norm": 0.3719448149204254,
1590
+ "learning_rate": 0.0004305555555555556,
1591
+ "loss": 0.0645,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 0.059129981766084916,
1596
+ "grad_norm": 0.18171130120754242,
1597
+ "learning_rate": 0.00043,
1598
+ "loss": 0.0452,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 0.0593904662672571,
1603
+ "grad_norm": 0.178982675075531,
1604
+ "learning_rate": 0.0004294444444444445,
1605
+ "loss": 0.0497,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 0.05965095076842928,
1610
+ "grad_norm": 0.1660393476486206,
1611
+ "learning_rate": 0.00042888888888888886,
1612
+ "loss": 0.0478,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 0.05991143526960146,
1617
+ "grad_norm": 0.1843854784965515,
1618
+ "learning_rate": 0.00042833333333333335,
1619
+ "loss": 0.0522,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 0.06017191977077364,
1624
+ "grad_norm": 0.12932512164115906,
1625
+ "learning_rate": 0.0004277777777777778,
1626
+ "loss": 0.0233,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 0.06043240427194582,
1631
+ "grad_norm": 0.2272115796804428,
1632
+ "learning_rate": 0.00042722222222222223,
1633
+ "loss": 0.044,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 0.060692888773118,
1638
+ "grad_norm": 0.15523988008499146,
1639
+ "learning_rate": 0.0004266666666666667,
1640
+ "loss": 0.0275,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 0.06095337327429018,
1645
+ "grad_norm": 0.1535874903202057,
1646
+ "learning_rate": 0.0004261111111111111,
1647
+ "loss": 0.0316,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 0.06121385777546236,
1652
+ "grad_norm": 0.23498567938804626,
1653
+ "learning_rate": 0.0004255555555555556,
1654
+ "loss": 0.054,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 0.06147434227663454,
1659
+ "grad_norm": 0.1743401437997818,
1660
+ "learning_rate": 0.000425,
1661
+ "loss": 0.051,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 0.06173482677780672,
1666
+ "grad_norm": 0.1762365847826004,
1667
+ "learning_rate": 0.00042444444444444447,
1668
+ "loss": 0.0464,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 0.0619953112789789,
1673
+ "grad_norm": 0.18202027678489685,
1674
+ "learning_rate": 0.0004238888888888889,
1675
+ "loss": 0.0197,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 0.06225579578015108,
1680
+ "grad_norm": 0.20636488497257233,
1681
+ "learning_rate": 0.00042333333333333334,
1682
+ "loss": 0.054,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 0.06251628028132326,
1687
+ "grad_norm": 0.12590542435646057,
1688
+ "learning_rate": 0.0004227777777777778,
1689
+ "loss": 0.023,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 0.06277676478249544,
1694
+ "grad_norm": 0.19617991149425507,
1695
+ "learning_rate": 0.0004222222222222222,
1696
+ "loss": 0.0166,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 0.06303724928366762,
1701
+ "grad_norm": 0.20318199694156647,
1702
+ "learning_rate": 0.0004216666666666667,
1703
+ "loss": 0.0567,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 0.0632977337848398,
1708
+ "grad_norm": 0.14517085254192352,
1709
+ "learning_rate": 0.0004211111111111111,
1710
+ "loss": 0.0196,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 0.06355821828601198,
1715
+ "grad_norm": 0.15447178483009338,
1716
+ "learning_rate": 0.0004205555555555556,
1717
+ "loss": 0.0387,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 0.06381870278718416,
1722
+ "grad_norm": 0.17070916295051575,
1723
+ "learning_rate": 0.00042,
1724
+ "loss": 0.0461,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 0.06407918728835635,
1729
+ "grad_norm": 0.15433409810066223,
1730
+ "learning_rate": 0.00041944444444444445,
1731
+ "loss": 0.019,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 0.06433967178952853,
1736
+ "grad_norm": 0.183025062084198,
1737
+ "learning_rate": 0.0004188888888888889,
1738
+ "loss": 0.0444,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 0.0646001562907007,
1743
+ "grad_norm": 0.385356068611145,
1744
+ "learning_rate": 0.00041833333333333333,
1745
+ "loss": 0.0547,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 0.06486064079187288,
1750
+ "grad_norm": 0.21771393716335297,
1751
+ "learning_rate": 0.0004177777777777778,
1752
+ "loss": 0.0509,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 0.06512112529304506,
1757
+ "grad_norm": 0.21005302667617798,
1758
+ "learning_rate": 0.0004172222222222222,
1759
+ "loss": 0.0433,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 0.06538160979421724,
1764
+ "grad_norm": 0.13587549328804016,
1765
+ "learning_rate": 0.0004166666666666667,
1766
+ "loss": 0.038,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 0.06564209429538942,
1771
+ "grad_norm": 0.17643588781356812,
1772
+ "learning_rate": 0.00041611111111111113,
1773
+ "loss": 0.0468,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 0.0659025787965616,
1778
+ "grad_norm": 0.1694176346063614,
1779
+ "learning_rate": 0.00041555555555555557,
1780
+ "loss": 0.0372,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 0.06616306329773379,
1785
+ "grad_norm": 0.20141932368278503,
1786
+ "learning_rate": 0.000415,
1787
+ "loss": 0.0529,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 0.06642354779890597,
1792
+ "grad_norm": 0.22460468113422394,
1793
+ "learning_rate": 0.00041444444444444444,
1794
+ "loss": 0.0441,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 0.06668403230007815,
1799
+ "grad_norm": 0.16733771562576294,
1800
+ "learning_rate": 0.0004138888888888889,
1801
+ "loss": 0.0475,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 0.06694451680125033,
1806
+ "grad_norm": 0.1671062558889389,
1807
+ "learning_rate": 0.0004133333333333333,
1808
+ "loss": 0.0357,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 0.0672050013024225,
1813
+ "grad_norm": 0.16501788794994354,
1814
+ "learning_rate": 0.0004127777777777778,
1815
+ "loss": 0.0477,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 0.06746548580359468,
1820
+ "grad_norm": 0.23321153223514557,
1821
+ "learning_rate": 0.00041222222222222224,
1822
+ "loss": 0.0233,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 0.06772597030476686,
1827
+ "grad_norm": 0.21765446662902832,
1828
+ "learning_rate": 0.0004116666666666667,
1829
+ "loss": 0.0379,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 0.06798645480593905,
1834
+ "grad_norm": 0.15531405806541443,
1835
+ "learning_rate": 0.0004111111111111111,
1836
+ "loss": 0.036,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 0.06824693930711123,
1841
+ "grad_norm": 0.2108466476202011,
1842
+ "learning_rate": 0.00041055555555555555,
1843
+ "loss": 0.0232,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 0.06850742380828341,
1848
+ "grad_norm": 0.1868615299463272,
1849
+ "learning_rate": 0.00041,
1850
+ "loss": 0.0524,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 0.06876790830945559,
1855
+ "grad_norm": 0.2014734148979187,
1856
+ "learning_rate": 0.00040944444444444443,
1857
+ "loss": 0.0513,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 0.06902839281062777,
1862
+ "grad_norm": 0.1071903333067894,
1863
+ "learning_rate": 0.0004088888888888889,
1864
+ "loss": 0.0344,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 0.06928887731179995,
1869
+ "grad_norm": 0.11115298420190811,
1870
+ "learning_rate": 0.00040833333333333336,
1871
+ "loss": 0.038,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 0.06954936181297212,
1876
+ "grad_norm": 0.2003505676984787,
1877
+ "learning_rate": 0.0004077777777777778,
1878
+ "loss": 0.049,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 0.0698098463141443,
1883
+ "grad_norm": 0.1403959095478058,
1884
+ "learning_rate": 0.00040722222222222223,
1885
+ "loss": 0.0324,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 0.0700703308153165,
1890
+ "grad_norm": 0.16135309636592865,
1891
+ "learning_rate": 0.00040666666666666667,
1892
+ "loss": 0.0367,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 0.07033081531648867,
1897
+ "grad_norm": 0.14055243134498596,
1898
+ "learning_rate": 0.0004061111111111111,
1899
+ "loss": 0.0387,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 0.07059129981766085,
1904
+ "grad_norm": 0.2191935032606125,
1905
+ "learning_rate": 0.00040555555555555554,
1906
+ "loss": 0.0469,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 0.07085178431883303,
1911
+ "grad_norm": 0.1192723885178566,
1912
+ "learning_rate": 0.00040500000000000003,
1913
+ "loss": 0.0198,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 0.07111226882000521,
1918
+ "grad_norm": 0.12160241603851318,
1919
+ "learning_rate": 0.00040444444444444447,
1920
+ "loss": 0.0291,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 0.07137275332117739,
1925
+ "grad_norm": 0.11681188642978668,
1926
+ "learning_rate": 0.0004038888888888889,
1927
+ "loss": 0.0214,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 0.07163323782234957,
1932
+ "grad_norm": 0.16357356309890747,
1933
+ "learning_rate": 0.00040333333333333334,
1934
+ "loss": 0.0386,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 0.07189372232352174,
1939
+ "grad_norm": 0.21038782596588135,
1940
+ "learning_rate": 0.0004027777777777778,
1941
+ "loss": 0.0487,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 0.07215420682469394,
1946
+ "grad_norm": 0.16823112964630127,
1947
+ "learning_rate": 0.0004022222222222222,
1948
+ "loss": 0.0398,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 0.07241469132586612,
1953
+ "grad_norm": 0.11350996047258377,
1954
+ "learning_rate": 0.00040166666666666665,
1955
+ "loss": 0.023,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 0.0726751758270383,
1960
+ "grad_norm": 0.12088004499673843,
1961
+ "learning_rate": 0.0004011111111111111,
1962
+ "loss": 0.0367,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 0.07293566032821047,
1967
+ "grad_norm": 0.20815615355968475,
1968
+ "learning_rate": 0.0004005555555555556,
1969
+ "loss": 0.0339,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 0.07319614482938265,
1974
+ "grad_norm": 0.20457801222801208,
1975
+ "learning_rate": 0.0004,
1976
+ "loss": 0.0462,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 0.07345662933055483,
1981
+ "grad_norm": 0.2844444811344147,
1982
+ "learning_rate": 0.00039944444444444446,
1983
+ "loss": 0.0542,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 0.07371711383172701,
1988
+ "grad_norm": 0.19987139105796814,
1989
+ "learning_rate": 0.0003988888888888889,
1990
+ "loss": 0.0179,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 0.07397759833289919,
1995
+ "grad_norm": 0.14339959621429443,
1996
+ "learning_rate": 0.00039833333333333333,
1997
+ "loss": 0.0449,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 0.07423808283407138,
2002
+ "grad_norm": 0.15933018922805786,
2003
+ "learning_rate": 0.00039777777777777777,
2004
+ "loss": 0.027,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 0.07449856733524356,
2009
+ "grad_norm": 0.207759290933609,
2010
+ "learning_rate": 0.0003972222222222222,
2011
+ "loss": 0.0461,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 0.07475905183641574,
2016
+ "grad_norm": 0.13354656100273132,
2017
+ "learning_rate": 0.0003966666666666667,
2018
+ "loss": 0.0415,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 0.07501953633758791,
2023
+ "grad_norm": 0.1208604946732521,
2024
+ "learning_rate": 0.00039611111111111113,
2025
+ "loss": 0.0393,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 0.07528002083876009,
2030
+ "grad_norm": 0.1399313062429428,
2031
+ "learning_rate": 0.00039555555555555557,
2032
+ "loss": 0.043,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 0.07554050533993227,
2037
+ "grad_norm": 0.1408071219921112,
2038
+ "learning_rate": 0.000395,
2039
+ "loss": 0.015,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 0.07580098984110445,
2044
+ "grad_norm": 0.11537426710128784,
2045
+ "learning_rate": 0.00039444444444444444,
2046
+ "loss": 0.0345,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 0.07606147434227663,
2051
+ "grad_norm": 0.12704655528068542,
2052
+ "learning_rate": 0.00039388888888888893,
2053
+ "loss": 0.0399,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 0.07632195884344882,
2058
+ "grad_norm": 0.09692219644784927,
2059
+ "learning_rate": 0.0003933333333333333,
2060
+ "loss": 0.0328,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 0.076582443344621,
2065
+ "grad_norm": 0.12996357679367065,
2066
+ "learning_rate": 0.0003927777777777778,
2067
+ "loss": 0.0151,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 0.07684292784579318,
2072
+ "grad_norm": 0.0913880318403244,
2073
+ "learning_rate": 0.00039222222222222225,
2074
+ "loss": 0.0328,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 0.07710341234696536,
2079
+ "grad_norm": 0.10965622216463089,
2080
+ "learning_rate": 0.0003916666666666667,
2081
+ "loss": 0.0296,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 0.07736389684813753,
2086
+ "grad_norm": 0.1479872316122055,
2087
+ "learning_rate": 0.0003911111111111111,
2088
+ "loss": 0.0421,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 0.07762438134930971,
2093
+ "grad_norm": 0.10420911759138107,
2094
+ "learning_rate": 0.00039055555555555556,
2095
+ "loss": 0.0227,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 0.07788486585048189,
2100
+ "grad_norm": 0.13351784646511078,
2101
+ "learning_rate": 0.00039000000000000005,
2102
+ "loss": 0.0341,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 0.07814535035165408,
2107
+ "grad_norm": 0.11381152272224426,
2108
+ "learning_rate": 0.00038944444444444443,
2109
+ "loss": 0.0381,
2110
+ "step": 300
2111
+ },
2112
+ {
2113
+ "epoch": 0.07840583485282626,
2114
+ "grad_norm": 0.1092122346162796,
2115
+ "learning_rate": 0.0003888888888888889,
2116
+ "loss": 0.0247,
2117
+ "step": 301
2118
+ },
2119
+ {
2120
+ "epoch": 0.07866631935399844,
2121
+ "grad_norm": 0.11427556723356247,
2122
+ "learning_rate": 0.0003883333333333333,
2123
+ "loss": 0.0396,
2124
+ "step": 302
2125
+ },
2126
+ {
2127
+ "epoch": 0.07892680385517062,
2128
+ "grad_norm": 0.25716203451156616,
2129
+ "learning_rate": 0.0003877777777777778,
2130
+ "loss": 0.0503,
2131
+ "step": 303
2132
+ },
2133
+ {
2134
+ "epoch": 0.0791872883563428,
2135
+ "grad_norm": 0.10936491191387177,
2136
+ "learning_rate": 0.00038722222222222223,
2137
+ "loss": 0.0345,
2138
+ "step": 304
2139
+ },
2140
+ {
2141
+ "epoch": 0.07944777285751498,
2142
+ "grad_norm": 0.10200309008359909,
2143
+ "learning_rate": 0.00038666666666666667,
2144
+ "loss": 0.0307,
2145
+ "step": 305
2146
+ },
2147
+ {
2148
+ "epoch": 0.07970825735868715,
2149
+ "grad_norm": 0.15819424390792847,
2150
+ "learning_rate": 0.00038611111111111116,
2151
+ "loss": 0.0375,
2152
+ "step": 306
2153
+ },
2154
+ {
2155
+ "epoch": 0.07996874185985933,
2156
+ "grad_norm": 0.14317704737186432,
2157
+ "learning_rate": 0.00038555555555555554,
2158
+ "loss": 0.0374,
2159
+ "step": 307
2160
+ },
2161
+ {
2162
+ "epoch": 0.08022922636103152,
2163
+ "grad_norm": 0.14639945328235626,
2164
+ "learning_rate": 0.00038500000000000003,
2165
+ "loss": 0.0306,
2166
+ "step": 308
2167
+ },
2168
+ {
2169
+ "epoch": 0.0804897108622037,
2170
+ "grad_norm": 0.1522209346294403,
2171
+ "learning_rate": 0.0003844444444444444,
2172
+ "loss": 0.0158,
2173
+ "step": 309
2174
+ },
2175
+ {
2176
+ "epoch": 0.08075019536337588,
2177
+ "grad_norm": 0.1352933645248413,
2178
+ "learning_rate": 0.0003838888888888889,
2179
+ "loss": 0.0191,
2180
+ "step": 310
2181
+ },
2182
+ {
2183
+ "epoch": 0.08101067986454806,
2184
+ "grad_norm": 0.30525916814804077,
2185
+ "learning_rate": 0.00038333333333333334,
2186
+ "loss": 0.0529,
2187
+ "step": 311
2188
+ },
2189
+ {
2190
+ "epoch": 0.08127116436572024,
2191
+ "grad_norm": 0.2127600610256195,
2192
+ "learning_rate": 0.0003827777777777778,
2193
+ "loss": 0.0545,
2194
+ "step": 312
2195
+ },
2196
+ {
2197
+ "epoch": 0.08153164886689242,
2198
+ "grad_norm": 0.12473171949386597,
2199
+ "learning_rate": 0.0003822222222222223,
2200
+ "loss": 0.0174,
2201
+ "step": 313
2202
+ },
2203
+ {
2204
+ "epoch": 0.0817921333680646,
2205
+ "grad_norm": 0.13822594285011292,
2206
+ "learning_rate": 0.00038166666666666666,
2207
+ "loss": 0.0129,
2208
+ "step": 314
2209
+ },
2210
+ {
2211
+ "epoch": 0.08205261786923677,
2212
+ "grad_norm": 0.1683114618062973,
2213
+ "learning_rate": 0.00038111111111111115,
2214
+ "loss": 0.0214,
2215
+ "step": 315
2216
+ },
2217
+ {
2218
+ "epoch": 0.08231310237040897,
2219
+ "grad_norm": 0.09103227406740189,
2220
+ "learning_rate": 0.00038055555555555553,
2221
+ "loss": 0.0307,
2222
+ "step": 316
2223
+ },
2224
+ {
2225
+ "epoch": 0.08257358687158114,
2226
+ "grad_norm": 0.10524292290210724,
2227
+ "learning_rate": 0.00038,
2228
+ "loss": 0.0205,
2229
+ "step": 317
2230
+ },
2231
+ {
2232
+ "epoch": 0.08283407137275332,
2233
+ "grad_norm": 0.15706130862236023,
2234
+ "learning_rate": 0.0003794444444444444,
2235
+ "loss": 0.037,
2236
+ "step": 318
2237
+ },
2238
+ {
2239
+ "epoch": 0.0830945558739255,
2240
+ "grad_norm": 0.14827808737754822,
2241
+ "learning_rate": 0.0003788888888888889,
2242
+ "loss": 0.0332,
2243
+ "step": 319
2244
+ },
2245
+ {
2246
+ "epoch": 0.08335504037509768,
2247
+ "grad_norm": 0.09460010379552841,
2248
+ "learning_rate": 0.0003783333333333334,
2249
+ "loss": 0.032,
2250
+ "step": 320
2251
+ },
2252
+ {
2253
+ "epoch": 0.08361552487626986,
2254
+ "grad_norm": 0.16332273185253143,
2255
+ "learning_rate": 0.00037777777777777777,
2256
+ "loss": 0.0176,
2257
+ "step": 321
2258
+ },
2259
+ {
2260
+ "epoch": 0.08387600937744204,
2261
+ "grad_norm": 0.2653479278087616,
2262
+ "learning_rate": 0.00037722222222222226,
2263
+ "loss": 0.046,
2264
+ "step": 322
2265
+ },
2266
+ {
2267
+ "epoch": 0.08413649387861422,
2268
+ "grad_norm": 0.22567397356033325,
2269
+ "learning_rate": 0.00037666666666666664,
2270
+ "loss": 0.0397,
2271
+ "step": 323
2272
+ },
2273
+ {
2274
+ "epoch": 0.08439697837978641,
2275
+ "grad_norm": 0.09909996390342712,
2276
+ "learning_rate": 0.00037611111111111113,
2277
+ "loss": 0.0347,
2278
+ "step": 324
2279
+ },
2280
+ {
2281
+ "epoch": 0.08465746288095859,
2282
+ "grad_norm": 0.14052069187164307,
2283
+ "learning_rate": 0.0003755555555555555,
2284
+ "loss": 0.0426,
2285
+ "step": 325
2286
+ },
2287
+ {
2288
+ "epoch": 0.08491794738213077,
2289
+ "grad_norm": 0.10061012208461761,
2290
+ "learning_rate": 0.000375,
2291
+ "loss": 0.0339,
2292
+ "step": 326
2293
+ },
2294
+ {
2295
+ "epoch": 0.08517843188330294,
2296
+ "grad_norm": 0.07894690334796906,
2297
+ "learning_rate": 0.0003744444444444445,
2298
+ "loss": 0.0251,
2299
+ "step": 327
2300
+ },
2301
+ {
2302
+ "epoch": 0.08543891638447512,
2303
+ "grad_norm": 0.09962338209152222,
2304
+ "learning_rate": 0.0003738888888888889,
2305
+ "loss": 0.0349,
2306
+ "step": 328
2307
+ },
2308
+ {
2309
+ "epoch": 0.0856994008856473,
2310
+ "grad_norm": 0.18012109398841858,
2311
+ "learning_rate": 0.0003733333333333334,
2312
+ "loss": 0.0151,
2313
+ "step": 329
2314
+ },
2315
+ {
2316
+ "epoch": 0.08595988538681948,
2317
+ "grad_norm": 0.11095000058412552,
2318
+ "learning_rate": 0.00037277777777777776,
2319
+ "loss": 0.0377,
2320
+ "step": 330
2321
+ },
2322
+ {
2323
+ "epoch": 0.08622036988799167,
2324
+ "grad_norm": 0.06870577484369278,
2325
+ "learning_rate": 0.00037222222222222225,
2326
+ "loss": 0.0188,
2327
+ "step": 331
2328
+ },
2329
+ {
2330
+ "epoch": 0.08648085438916385,
2331
+ "grad_norm": 0.24816635251045227,
2332
+ "learning_rate": 0.00037166666666666663,
2333
+ "loss": 0.0391,
2334
+ "step": 332
2335
+ },
2336
+ {
2337
+ "epoch": 0.08674133889033603,
2338
+ "grad_norm": 0.10784301161766052,
2339
+ "learning_rate": 0.0003711111111111111,
2340
+ "loss": 0.0187,
2341
+ "step": 333
2342
+ },
2343
+ {
2344
+ "epoch": 0.0870018233915082,
2345
+ "grad_norm": 0.11542753875255585,
2346
+ "learning_rate": 0.0003705555555555556,
2347
+ "loss": 0.0393,
2348
+ "step": 334
2349
+ },
2350
+ {
2351
+ "epoch": 0.08726230789268039,
2352
+ "grad_norm": 0.1449226289987564,
2353
+ "learning_rate": 0.00037,
2354
+ "loss": 0.0379,
2355
+ "step": 335
2356
+ },
2357
+ {
2358
+ "epoch": 0.08752279239385256,
2359
+ "grad_norm": 0.165171280503273,
2360
+ "learning_rate": 0.0003694444444444445,
2361
+ "loss": 0.0475,
2362
+ "step": 336
2363
+ },
2364
+ {
2365
+ "epoch": 0.08778327689502474,
2366
+ "grad_norm": 0.16520822048187256,
2367
+ "learning_rate": 0.00036888888888888887,
2368
+ "loss": 0.0392,
2369
+ "step": 337
2370
+ },
2371
+ {
2372
+ "epoch": 0.08804376139619692,
2373
+ "grad_norm": 0.10801101475954056,
2374
+ "learning_rate": 0.00036833333333333336,
2375
+ "loss": 0.0374,
2376
+ "step": 338
2377
+ },
2378
+ {
2379
+ "epoch": 0.08830424589736911,
2380
+ "grad_norm": 0.13719044625759125,
2381
+ "learning_rate": 0.00036777777777777774,
2382
+ "loss": 0.0293,
2383
+ "step": 339
2384
+ },
2385
+ {
2386
+ "epoch": 0.08856473039854129,
2387
+ "grad_norm": 0.13164854049682617,
2388
+ "learning_rate": 0.00036722222222222223,
2389
+ "loss": 0.0159,
2390
+ "step": 340
2391
+ },
2392
+ {
2393
+ "epoch": 0.08882521489971347,
2394
+ "grad_norm": 0.16117313504219055,
2395
+ "learning_rate": 0.00036666666666666667,
2396
+ "loss": 0.0238,
2397
+ "step": 341
2398
+ },
2399
+ {
2400
+ "epoch": 0.08908569940088565,
2401
+ "grad_norm": 0.11216874420642853,
2402
+ "learning_rate": 0.0003661111111111111,
2403
+ "loss": 0.034,
2404
+ "step": 342
2405
+ },
2406
+ {
2407
+ "epoch": 0.08934618390205783,
2408
+ "grad_norm": 0.10498247295618057,
2409
+ "learning_rate": 0.0003655555555555556,
2410
+ "loss": 0.0335,
2411
+ "step": 343
2412
+ },
2413
+ {
2414
+ "epoch": 0.08960666840323,
2415
+ "grad_norm": 0.083678238093853,
2416
+ "learning_rate": 0.000365,
2417
+ "loss": 0.0318,
2418
+ "step": 344
2419
+ },
2420
+ {
2421
+ "epoch": 0.08986715290440218,
2422
+ "grad_norm": 0.09851270914077759,
2423
+ "learning_rate": 0.00036444444444444447,
2424
+ "loss": 0.032,
2425
+ "step": 345
2426
+ },
2427
+ {
2428
+ "epoch": 0.09012763740557436,
2429
+ "grad_norm": 0.15901733934879303,
2430
+ "learning_rate": 0.00036388888888888886,
2431
+ "loss": 0.0369,
2432
+ "step": 346
2433
+ },
2434
+ {
2435
+ "epoch": 0.09038812190674655,
2436
+ "grad_norm": 0.1602892279624939,
2437
+ "learning_rate": 0.00036333333333333335,
2438
+ "loss": 0.0144,
2439
+ "step": 347
2440
+ },
2441
+ {
2442
+ "epoch": 0.09064860640791873,
2443
+ "grad_norm": 0.0990363284945488,
2444
+ "learning_rate": 0.0003627777777777778,
2445
+ "loss": 0.0307,
2446
+ "step": 348
2447
+ },
2448
+ {
2449
+ "epoch": 0.09090909090909091,
2450
+ "grad_norm": 0.09152241796255112,
2451
+ "learning_rate": 0.0003622222222222222,
2452
+ "loss": 0.0174,
2453
+ "step": 349
2454
+ },
2455
+ {
2456
+ "epoch": 0.09116957541026309,
2457
+ "grad_norm": 0.11197351664304733,
2458
+ "learning_rate": 0.0003616666666666667,
2459
+ "loss": 0.0291,
2460
+ "step": 350
2461
+ },
2462
+ {
2463
+ "epoch": 0.09143005991143527,
2464
+ "grad_norm": 0.11259925365447998,
2465
+ "learning_rate": 0.0003611111111111111,
2466
+ "loss": 0.0118,
2467
+ "step": 351
2468
+ },
2469
+ {
2470
+ "epoch": 0.09169054441260745,
2471
+ "grad_norm": 0.07788604497909546,
2472
+ "learning_rate": 0.0003605555555555556,
2473
+ "loss": 0.0289,
2474
+ "step": 352
2475
+ },
2476
+ {
2477
+ "epoch": 0.09195102891377963,
2478
+ "grad_norm": 0.06775746494531631,
2479
+ "learning_rate": 0.00035999999999999997,
2480
+ "loss": 0.0253,
2481
+ "step": 353
2482
+ },
2483
+ {
2484
+ "epoch": 0.0922115134149518,
2485
+ "grad_norm": 0.13518136739730835,
2486
+ "learning_rate": 0.00035944444444444446,
2487
+ "loss": 0.0404,
2488
+ "step": 354
2489
+ },
2490
+ {
2491
+ "epoch": 0.092471997916124,
2492
+ "grad_norm": 0.1233261302113533,
2493
+ "learning_rate": 0.0003588888888888889,
2494
+ "loss": 0.0331,
2495
+ "step": 355
2496
+ },
2497
+ {
2498
+ "epoch": 0.09273248241729617,
2499
+ "grad_norm": 0.1096162497997284,
2500
+ "learning_rate": 0.00035833333333333333,
2501
+ "loss": 0.0423,
2502
+ "step": 356
2503
+ },
2504
+ {
2505
+ "epoch": 0.09299296691846835,
2506
+ "grad_norm": 0.1044531762599945,
2507
+ "learning_rate": 0.00035777777777777777,
2508
+ "loss": 0.0159,
2509
+ "step": 357
2510
+ },
2511
+ {
2512
+ "epoch": 0.09325345141964053,
2513
+ "grad_norm": 0.09880375862121582,
2514
+ "learning_rate": 0.0003572222222222222,
2515
+ "loss": 0.0315,
2516
+ "step": 358
2517
+ },
2518
+ {
2519
+ "epoch": 0.09351393592081271,
2520
+ "grad_norm": 0.16216698288917542,
2521
+ "learning_rate": 0.0003566666666666667,
2522
+ "loss": 0.038,
2523
+ "step": 359
2524
+ },
2525
+ {
2526
+ "epoch": 0.09377442042198489,
2527
+ "grad_norm": 0.10374052822589874,
2528
+ "learning_rate": 0.0003561111111111111,
2529
+ "loss": 0.017,
2530
+ "step": 360
2531
+ },
2532
+ {
2533
+ "epoch": 0.09403490492315707,
2534
+ "grad_norm": 0.09040326625108719,
2535
+ "learning_rate": 0.00035555555555555557,
2536
+ "loss": 0.0306,
2537
+ "step": 361
2538
+ },
2539
+ {
2540
+ "epoch": 0.09429538942432925,
2541
+ "grad_norm": 0.088216632604599,
2542
+ "learning_rate": 0.000355,
2543
+ "loss": 0.025,
2544
+ "step": 362
2545
+ },
2546
+ {
2547
+ "epoch": 0.09455587392550144,
2548
+ "grad_norm": 0.13739970326423645,
2549
+ "learning_rate": 0.00035444444444444445,
2550
+ "loss": 0.0315,
2551
+ "step": 363
2552
+ },
2553
+ {
2554
+ "epoch": 0.09481635842667362,
2555
+ "grad_norm": 0.0974138155579567,
2556
+ "learning_rate": 0.0003538888888888889,
2557
+ "loss": 0.0284,
2558
+ "step": 364
2559
+ },
2560
+ {
2561
+ "epoch": 0.0950768429278458,
2562
+ "grad_norm": 0.08695337176322937,
2563
+ "learning_rate": 0.0003533333333333333,
2564
+ "loss": 0.0228,
2565
+ "step": 365
2566
+ },
2567
+ {
2568
+ "epoch": 0.09533732742901797,
2569
+ "grad_norm": 0.1133357360959053,
2570
+ "learning_rate": 0.0003527777777777778,
2571
+ "loss": 0.0247,
2572
+ "step": 366
2573
+ },
2574
+ {
2575
+ "epoch": 0.09559781193019015,
2576
+ "grad_norm": 0.11041553318500519,
2577
+ "learning_rate": 0.00035222222222222225,
2578
+ "loss": 0.0196,
2579
+ "step": 367
2580
+ },
2581
+ {
2582
+ "epoch": 0.09585829643136233,
2583
+ "grad_norm": 0.08988118171691895,
2584
+ "learning_rate": 0.0003516666666666667,
2585
+ "loss": 0.018,
2586
+ "step": 368
2587
+ },
2588
+ {
2589
+ "epoch": 0.09611878093253451,
2590
+ "grad_norm": 0.08557140082120895,
2591
+ "learning_rate": 0.0003511111111111111,
2592
+ "loss": 0.0189,
2593
+ "step": 369
2594
+ },
2595
+ {
2596
+ "epoch": 0.0963792654337067,
2597
+ "grad_norm": 0.08144374936819077,
2598
+ "learning_rate": 0.00035055555555555556,
2599
+ "loss": 0.0195,
2600
+ "step": 370
2601
+ },
2602
+ {
2603
+ "epoch": 0.09663974993487888,
2604
+ "grad_norm": 0.18180625140666962,
2605
+ "learning_rate": 0.00035,
2606
+ "loss": 0.0412,
2607
+ "step": 371
2608
+ },
2609
+ {
2610
+ "epoch": 0.09690023443605106,
2611
+ "grad_norm": 0.1168271005153656,
2612
+ "learning_rate": 0.00034944444444444443,
2613
+ "loss": 0.015,
2614
+ "step": 372
2615
+ },
2616
+ {
2617
+ "epoch": 0.09716071893722324,
2618
+ "grad_norm": 0.08017319440841675,
2619
+ "learning_rate": 0.0003488888888888889,
2620
+ "loss": 0.0309,
2621
+ "step": 373
2622
+ },
2623
+ {
2624
+ "epoch": 0.09742120343839542,
2625
+ "grad_norm": 0.16148969531059265,
2626
+ "learning_rate": 0.00034833333333333336,
2627
+ "loss": 0.0344,
2628
+ "step": 374
2629
+ },
2630
+ {
2631
+ "epoch": 0.0976816879395676,
2632
+ "grad_norm": 0.07820136100053787,
2633
+ "learning_rate": 0.0003477777777777778,
2634
+ "loss": 0.0154,
2635
+ "step": 375
2636
+ },
2637
+ {
2638
+ "epoch": 0.09794217244073977,
2639
+ "grad_norm": 0.1732979118824005,
2640
+ "learning_rate": 0.00034722222222222224,
2641
+ "loss": 0.0362,
2642
+ "step": 376
2643
+ },
2644
+ {
2645
+ "epoch": 0.09820265694191195,
2646
+ "grad_norm": 0.16460788249969482,
2647
+ "learning_rate": 0.00034666666666666667,
2648
+ "loss": 0.0399,
2649
+ "step": 377
2650
+ },
2651
+ {
2652
+ "epoch": 0.09846314144308414,
2653
+ "grad_norm": 0.17509953677654266,
2654
+ "learning_rate": 0.0003461111111111111,
2655
+ "loss": 0.0384,
2656
+ "step": 378
2657
+ },
2658
+ {
2659
+ "epoch": 0.09872362594425632,
2660
+ "grad_norm": 0.09137140214443207,
2661
+ "learning_rate": 0.00034555555555555555,
2662
+ "loss": 0.0124,
2663
+ "step": 379
2664
+ },
2665
+ {
2666
+ "epoch": 0.0989841104454285,
2667
+ "grad_norm": 0.0854978933930397,
2668
+ "learning_rate": 0.000345,
2669
+ "loss": 0.028,
2670
+ "step": 380
2671
+ },
2672
+ {
2673
+ "epoch": 0.09924459494660068,
2674
+ "grad_norm": 0.09197288006544113,
2675
+ "learning_rate": 0.0003444444444444445,
2676
+ "loss": 0.0147,
2677
+ "step": 381
2678
+ },
2679
+ {
2680
+ "epoch": 0.09950507944777286,
2681
+ "grad_norm": 0.15859054028987885,
2682
+ "learning_rate": 0.0003438888888888889,
2683
+ "loss": 0.0423,
2684
+ "step": 382
2685
+ },
2686
+ {
2687
+ "epoch": 0.09976556394894504,
2688
+ "grad_norm": 0.09122268110513687,
2689
+ "learning_rate": 0.00034333333333333335,
2690
+ "loss": 0.0288,
2691
+ "step": 383
2692
+ },
2693
+ {
2694
+ "epoch": 0.10002604845011721,
2695
+ "grad_norm": 0.1572301834821701,
2696
+ "learning_rate": 0.0003427777777777778,
2697
+ "loss": 0.0392,
2698
+ "step": 384
2699
+ },
2700
+ {
2701
+ "epoch": 0.10028653295128939,
2702
+ "grad_norm": 0.1745997965335846,
2703
+ "learning_rate": 0.0003422222222222222,
2704
+ "loss": 0.0401,
2705
+ "step": 385
2706
+ },
2707
+ {
2708
+ "epoch": 0.10054701745246158,
2709
+ "grad_norm": 0.12563872337341309,
2710
+ "learning_rate": 0.00034166666666666666,
2711
+ "loss": 0.0359,
2712
+ "step": 386
2713
+ },
2714
+ {
2715
+ "epoch": 0.10080750195363376,
2716
+ "grad_norm": 0.14481599628925323,
2717
+ "learning_rate": 0.0003411111111111111,
2718
+ "loss": 0.0458,
2719
+ "step": 387
2720
+ },
2721
+ {
2722
+ "epoch": 0.10106798645480594,
2723
+ "grad_norm": 0.10502296686172485,
2724
+ "learning_rate": 0.0003405555555555556,
2725
+ "loss": 0.03,
2726
+ "step": 388
2727
+ },
2728
+ {
2729
+ "epoch": 0.10132847095597812,
2730
+ "grad_norm": 0.12301287800073624,
2731
+ "learning_rate": 0.00034,
2732
+ "loss": 0.0286,
2733
+ "step": 389
2734
+ },
2735
+ {
2736
+ "epoch": 0.1015889554571503,
2737
+ "grad_norm": 0.08884134888648987,
2738
+ "learning_rate": 0.00033944444444444446,
2739
+ "loss": 0.0148,
2740
+ "step": 390
2741
+ },
2742
+ {
2743
+ "epoch": 0.10184943995832248,
2744
+ "grad_norm": 0.17433515191078186,
2745
+ "learning_rate": 0.0003388888888888889,
2746
+ "loss": 0.0149,
2747
+ "step": 391
2748
+ },
2749
+ {
2750
+ "epoch": 0.10210992445949466,
2751
+ "grad_norm": 0.11985349655151367,
2752
+ "learning_rate": 0.00033833333333333334,
2753
+ "loss": 0.036,
2754
+ "step": 392
2755
+ },
2756
+ {
2757
+ "epoch": 0.10237040896066683,
2758
+ "grad_norm": 0.17169484496116638,
2759
+ "learning_rate": 0.00033777777777777777,
2760
+ "loss": 0.0214,
2761
+ "step": 393
2762
+ },
2763
+ {
2764
+ "epoch": 0.10263089346183903,
2765
+ "grad_norm": 0.1162295863032341,
2766
+ "learning_rate": 0.0003372222222222222,
2767
+ "loss": 0.0432,
2768
+ "step": 394
2769
+ },
2770
+ {
2771
+ "epoch": 0.1028913779630112,
2772
+ "grad_norm": 0.1161981150507927,
2773
+ "learning_rate": 0.0003366666666666667,
2774
+ "loss": 0.0345,
2775
+ "step": 395
2776
+ },
2777
+ {
2778
+ "epoch": 0.10315186246418338,
2779
+ "grad_norm": 0.08045128732919693,
2780
+ "learning_rate": 0.00033611111111111114,
2781
+ "loss": 0.0147,
2782
+ "step": 396
2783
+ },
2784
+ {
2785
+ "epoch": 0.10341234696535556,
2786
+ "grad_norm": 0.0739087387919426,
2787
+ "learning_rate": 0.0003355555555555556,
2788
+ "loss": 0.0237,
2789
+ "step": 397
2790
+ },
2791
+ {
2792
+ "epoch": 0.10367283146652774,
2793
+ "grad_norm": 0.10391904413700104,
2794
+ "learning_rate": 0.000335,
2795
+ "loss": 0.0302,
2796
+ "step": 398
2797
+ },
2798
+ {
2799
+ "epoch": 0.10393331596769992,
2800
+ "grad_norm": 0.10834187269210815,
2801
+ "learning_rate": 0.00033444444444444445,
2802
+ "loss": 0.0354,
2803
+ "step": 399
2804
+ },
2805
+ {
2806
+ "epoch": 0.1041938004688721,
2807
+ "grad_norm": 0.12172620743513107,
2808
+ "learning_rate": 0.0003338888888888889,
2809
+ "loss": 0.0142,
2810
+ "step": 400
2811
+ },
2812
+ {
2813
+ "epoch": 0.10445428497004428,
2814
+ "grad_norm": 0.07939380407333374,
2815
+ "learning_rate": 0.0003333333333333333,
2816
+ "loss": 0.0207,
2817
+ "step": 401
2818
+ },
2819
+ {
2820
+ "epoch": 0.10471476947121647,
2821
+ "grad_norm": 0.07943827658891678,
2822
+ "learning_rate": 0.0003327777777777778,
2823
+ "loss": 0.0263,
2824
+ "step": 402
2825
+ },
2826
+ {
2827
+ "epoch": 0.10497525397238865,
2828
+ "grad_norm": 0.08589910715818405,
2829
+ "learning_rate": 0.0003322222222222222,
2830
+ "loss": 0.0305,
2831
+ "step": 403
2832
+ },
2833
+ {
2834
+ "epoch": 0.10523573847356082,
2835
+ "grad_norm": 0.07241426408290863,
2836
+ "learning_rate": 0.0003316666666666667,
2837
+ "loss": 0.0282,
2838
+ "step": 404
2839
+ },
2840
+ {
2841
+ "epoch": 0.105496222974733,
2842
+ "grad_norm": 0.11648601293563843,
2843
+ "learning_rate": 0.0003311111111111111,
2844
+ "loss": 0.0157,
2845
+ "step": 405
2846
+ },
2847
+ {
2848
+ "epoch": 0.10575670747590518,
2849
+ "grad_norm": 0.06991654634475708,
2850
+ "learning_rate": 0.00033055555555555556,
2851
+ "loss": 0.0289,
2852
+ "step": 406
2853
+ },
2854
+ {
2855
+ "epoch": 0.10601719197707736,
2856
+ "grad_norm": 0.14965589344501495,
2857
+ "learning_rate": 0.00033,
2858
+ "loss": 0.0356,
2859
+ "step": 407
2860
+ },
2861
+ {
2862
+ "epoch": 0.10627767647824954,
2863
+ "grad_norm": 0.11378724128007889,
2864
+ "learning_rate": 0.00032944444444444444,
2865
+ "loss": 0.0351,
2866
+ "step": 408
2867
+ },
2868
+ {
2869
+ "epoch": 0.10653816097942173,
2870
+ "grad_norm": 0.13678783178329468,
2871
+ "learning_rate": 0.0003288888888888889,
2872
+ "loss": 0.0315,
2873
+ "step": 409
2874
+ },
2875
+ {
2876
+ "epoch": 0.10679864548059391,
2877
+ "grad_norm": 0.09216827154159546,
2878
+ "learning_rate": 0.0003283333333333333,
2879
+ "loss": 0.0294,
2880
+ "step": 410
2881
+ },
2882
+ {
2883
+ "epoch": 0.10705912998176609,
2884
+ "grad_norm": 0.08084861934185028,
2885
+ "learning_rate": 0.0003277777777777778,
2886
+ "loss": 0.0239,
2887
+ "step": 411
2888
+ },
2889
+ {
2890
+ "epoch": 0.10731961448293827,
2891
+ "grad_norm": 0.0898488387465477,
2892
+ "learning_rate": 0.00032722222222222224,
2893
+ "loss": 0.0187,
2894
+ "step": 412
2895
+ },
2896
+ {
2897
+ "epoch": 0.10758009898411044,
2898
+ "grad_norm": 0.14007185399532318,
2899
+ "learning_rate": 0.0003266666666666667,
2900
+ "loss": 0.0327,
2901
+ "step": 413
2902
+ },
2903
+ {
2904
+ "epoch": 0.10784058348528262,
2905
+ "grad_norm": 0.0782909020781517,
2906
+ "learning_rate": 0.0003261111111111111,
2907
+ "loss": 0.0301,
2908
+ "step": 414
2909
+ },
2910
+ {
2911
+ "epoch": 0.1081010679864548,
2912
+ "grad_norm": 0.12210501730442047,
2913
+ "learning_rate": 0.00032555555555555555,
2914
+ "loss": 0.0356,
2915
+ "step": 415
2916
+ },
2917
+ {
2918
+ "epoch": 0.10836155248762698,
2919
+ "grad_norm": 0.10311099886894226,
2920
+ "learning_rate": 0.00032500000000000004,
2921
+ "loss": 0.0161,
2922
+ "step": 416
2923
+ },
2924
+ {
2925
+ "epoch": 0.10862203698879917,
2926
+ "grad_norm": 0.10908329486846924,
2927
+ "learning_rate": 0.0003244444444444444,
2928
+ "loss": 0.0168,
2929
+ "step": 417
2930
+ },
2931
+ {
2932
+ "epoch": 0.10888252148997135,
2933
+ "grad_norm": 0.09817449748516083,
2934
+ "learning_rate": 0.0003238888888888889,
2935
+ "loss": 0.0118,
2936
+ "step": 418
2937
+ },
2938
+ {
2939
+ "epoch": 0.10914300599114353,
2940
+ "grad_norm": 0.061673179268836975,
2941
+ "learning_rate": 0.0003233333333333333,
2942
+ "loss": 0.0199,
2943
+ "step": 419
2944
+ },
2945
+ {
2946
+ "epoch": 0.10940349049231571,
2947
+ "grad_norm": 0.12285150587558746,
2948
+ "learning_rate": 0.0003227777777777778,
2949
+ "loss": 0.0347,
2950
+ "step": 420
2951
+ },
2952
+ {
2953
+ "epoch": 0.10966397499348789,
2954
+ "grad_norm": 0.1721012145280838,
2955
+ "learning_rate": 0.0003222222222222222,
2956
+ "loss": 0.0337,
2957
+ "step": 421
2958
+ },
2959
+ {
2960
+ "epoch": 0.10992445949466007,
2961
+ "grad_norm": 0.10047407448291779,
2962
+ "learning_rate": 0.00032166666666666666,
2963
+ "loss": 0.0138,
2964
+ "step": 422
2965
+ },
2966
+ {
2967
+ "epoch": 0.11018494399583224,
2968
+ "grad_norm": 0.09609969705343246,
2969
+ "learning_rate": 0.00032111111111111115,
2970
+ "loss": 0.0115,
2971
+ "step": 423
2972
+ },
2973
+ {
2974
+ "epoch": 0.11044542849700442,
2975
+ "grad_norm": 0.17365185916423798,
2976
+ "learning_rate": 0.00032055555555555554,
2977
+ "loss": 0.0384,
2978
+ "step": 424
2979
+ },
2980
+ {
2981
+ "epoch": 0.11070591299817661,
2982
+ "grad_norm": 0.2545756697654724,
2983
+ "learning_rate": 0.00032,
2984
+ "loss": 0.0486,
2985
+ "step": 425
2986
+ },
2987
+ {
2988
+ "epoch": 0.11096639749934879,
2989
+ "grad_norm": 0.07526978850364685,
2990
+ "learning_rate": 0.0003194444444444444,
2991
+ "loss": 0.0224,
2992
+ "step": 426
2993
+ },
2994
+ {
2995
+ "epoch": 0.11122688200052097,
2996
+ "grad_norm": 0.08974594622850418,
2997
+ "learning_rate": 0.0003188888888888889,
2998
+ "loss": 0.0134,
2999
+ "step": 427
3000
+ },
3001
+ {
3002
+ "epoch": 0.11148736650169315,
3003
+ "grad_norm": 0.13914678990840912,
3004
+ "learning_rate": 0.00031833333333333334,
3005
+ "loss": 0.0163,
3006
+ "step": 428
3007
+ },
3008
+ {
3009
+ "epoch": 0.11174785100286533,
3010
+ "grad_norm": 0.08919675648212433,
3011
+ "learning_rate": 0.0003177777777777778,
3012
+ "loss": 0.0126,
3013
+ "step": 429
3014
+ },
3015
+ {
3016
+ "epoch": 0.1120083355040375,
3017
+ "grad_norm": 0.13034509122371674,
3018
+ "learning_rate": 0.00031722222222222227,
3019
+ "loss": 0.0289,
3020
+ "step": 430
3021
+ },
3022
+ {
3023
+ "epoch": 0.11226882000520969,
3024
+ "grad_norm": 0.09612299501895905,
3025
+ "learning_rate": 0.00031666666666666665,
3026
+ "loss": 0.0183,
3027
+ "step": 431
3028
+ },
3029
+ {
3030
+ "epoch": 0.11252930450638186,
3031
+ "grad_norm": 0.09348250180482864,
3032
+ "learning_rate": 0.00031611111111111114,
3033
+ "loss": 0.0322,
3034
+ "step": 432
3035
+ },
3036
+ {
3037
+ "epoch": 0.11278978900755406,
3038
+ "grad_norm": 0.14950884878635406,
3039
+ "learning_rate": 0.0003155555555555555,
3040
+ "loss": 0.0411,
3041
+ "step": 433
3042
+ },
3043
+ {
3044
+ "epoch": 0.11305027350872623,
3045
+ "grad_norm": 0.13522475957870483,
3046
+ "learning_rate": 0.000315,
3047
+ "loss": 0.039,
3048
+ "step": 434
3049
+ },
3050
+ {
3051
+ "epoch": 0.11331075800989841,
3052
+ "grad_norm": 0.0809144377708435,
3053
+ "learning_rate": 0.0003144444444444445,
3054
+ "loss": 0.0305,
3055
+ "step": 435
3056
+ },
3057
+ {
3058
+ "epoch": 0.11357124251107059,
3059
+ "grad_norm": 0.09236025810241699,
3060
+ "learning_rate": 0.0003138888888888889,
3061
+ "loss": 0.0131,
3062
+ "step": 436
3063
+ },
3064
+ {
3065
+ "epoch": 0.11383172701224277,
3066
+ "grad_norm": 0.15586403012275696,
3067
+ "learning_rate": 0.0003133333333333334,
3068
+ "loss": 0.037,
3069
+ "step": 437
3070
+ },
3071
+ {
3072
+ "epoch": 0.11409221151341495,
3073
+ "grad_norm": 0.12417721003293991,
3074
+ "learning_rate": 0.00031277777777777776,
3075
+ "loss": 0.0375,
3076
+ "step": 438
3077
+ },
3078
+ {
3079
+ "epoch": 0.11435269601458713,
3080
+ "grad_norm": 0.09874928742647171,
3081
+ "learning_rate": 0.00031222222222222225,
3082
+ "loss": 0.0311,
3083
+ "step": 439
3084
+ },
3085
+ {
3086
+ "epoch": 0.11461318051575932,
3087
+ "grad_norm": 0.18468396365642548,
3088
+ "learning_rate": 0.00031166666666666663,
3089
+ "loss": 0.0391,
3090
+ "step": 440
3091
+ },
3092
+ {
3093
+ "epoch": 0.1148736650169315,
3094
+ "grad_norm": 0.12530437111854553,
3095
+ "learning_rate": 0.0003111111111111111,
3096
+ "loss": 0.0329,
3097
+ "step": 441
3098
+ },
3099
+ {
3100
+ "epoch": 0.11513414951810368,
3101
+ "grad_norm": 0.14760665595531464,
3102
+ "learning_rate": 0.0003105555555555555,
3103
+ "loss": 0.0329,
3104
+ "step": 442
3105
+ },
3106
+ {
3107
+ "epoch": 0.11539463401927585,
3108
+ "grad_norm": 0.05746585503220558,
3109
+ "learning_rate": 0.00031,
3110
+ "loss": 0.0236,
3111
+ "step": 443
3112
+ },
3113
+ {
3114
+ "epoch": 0.11565511852044803,
3115
+ "grad_norm": 0.09533420950174332,
3116
+ "learning_rate": 0.0003094444444444445,
3117
+ "loss": 0.0158,
3118
+ "step": 444
3119
+ },
3120
+ {
3121
+ "epoch": 0.11591560302162021,
3122
+ "grad_norm": 0.1520976573228836,
3123
+ "learning_rate": 0.0003088888888888889,
3124
+ "loss": 0.0129,
3125
+ "step": 445
3126
+ },
3127
+ {
3128
+ "epoch": 0.11617608752279239,
3129
+ "grad_norm": 0.07816439867019653,
3130
+ "learning_rate": 0.00030833333333333337,
3131
+ "loss": 0.0301,
3132
+ "step": 446
3133
+ },
3134
+ {
3135
+ "epoch": 0.11643657202396457,
3136
+ "grad_norm": 0.08245697617530823,
3137
+ "learning_rate": 0.00030777777777777775,
3138
+ "loss": 0.0322,
3139
+ "step": 447
3140
+ },
3141
+ {
3142
+ "epoch": 0.11669705652513676,
3143
+ "grad_norm": 0.0839148461818695,
3144
+ "learning_rate": 0.00030722222222222224,
3145
+ "loss": 0.0295,
3146
+ "step": 448
3147
+ },
3148
+ {
3149
+ "epoch": 0.11695754102630894,
3150
+ "grad_norm": 0.14252392947673798,
3151
+ "learning_rate": 0.0003066666666666667,
3152
+ "loss": 0.0397,
3153
+ "step": 449
3154
+ },
3155
+ {
3156
+ "epoch": 0.11721802552748112,
3157
+ "grad_norm": 0.15466183423995972,
3158
+ "learning_rate": 0.0003061111111111111,
3159
+ "loss": 0.0147,
3160
+ "step": 450
3161
+ },
3162
+ {
3163
+ "epoch": 0.1174785100286533,
3164
+ "grad_norm": 0.06841623783111572,
3165
+ "learning_rate": 0.0003055555555555556,
3166
+ "loss": 0.0261,
3167
+ "step": 451
3168
+ },
3169
+ {
3170
+ "epoch": 0.11773899452982547,
3171
+ "grad_norm": 0.11777552217245102,
3172
+ "learning_rate": 0.000305,
3173
+ "loss": 0.0149,
3174
+ "step": 452
3175
+ },
3176
+ {
3177
+ "epoch": 0.11799947903099765,
3178
+ "grad_norm": 0.09684286266565323,
3179
+ "learning_rate": 0.0003044444444444445,
3180
+ "loss": 0.0346,
3181
+ "step": 453
3182
+ },
3183
+ {
3184
+ "epoch": 0.11825996353216983,
3185
+ "grad_norm": 0.06864480674266815,
3186
+ "learning_rate": 0.00030388888888888886,
3187
+ "loss": 0.0295,
3188
+ "step": 454
3189
+ },
3190
+ {
3191
+ "epoch": 0.11852044803334201,
3192
+ "grad_norm": 0.08115808665752411,
3193
+ "learning_rate": 0.00030333333333333335,
3194
+ "loss": 0.0265,
3195
+ "step": 455
3196
+ },
3197
+ {
3198
+ "epoch": 0.1187809325345142,
3199
+ "grad_norm": 0.11336829513311386,
3200
+ "learning_rate": 0.0003027777777777778,
3201
+ "loss": 0.0281,
3202
+ "step": 456
3203
+ },
3204
+ {
3205
+ "epoch": 0.11904141703568638,
3206
+ "grad_norm": 0.0856219008564949,
3207
+ "learning_rate": 0.0003022222222222222,
3208
+ "loss": 0.0307,
3209
+ "step": 457
3210
+ },
3211
+ {
3212
+ "epoch": 0.11930190153685856,
3213
+ "grad_norm": 0.07512032985687256,
3214
+ "learning_rate": 0.0003016666666666667,
3215
+ "loss": 0.0294,
3216
+ "step": 458
3217
+ },
3218
+ {
3219
+ "epoch": 0.11956238603803074,
3220
+ "grad_norm": 0.10245606303215027,
3221
+ "learning_rate": 0.0003011111111111111,
3222
+ "loss": 0.0307,
3223
+ "step": 459
3224
+ },
3225
+ {
3226
+ "epoch": 0.11982287053920292,
3227
+ "grad_norm": 0.08995255082845688,
3228
+ "learning_rate": 0.0003005555555555556,
3229
+ "loss": 0.0276,
3230
+ "step": 460
3231
+ },
3232
+ {
3233
+ "epoch": 0.1200833550403751,
3234
+ "grad_norm": 0.08044669777154922,
3235
+ "learning_rate": 0.0003,
3236
+ "loss": 0.0269,
3237
+ "step": 461
3238
+ },
3239
+ {
3240
+ "epoch": 0.12034383954154727,
3241
+ "grad_norm": 0.07865863293409348,
3242
+ "learning_rate": 0.00029944444444444446,
3243
+ "loss": 0.0315,
3244
+ "step": 462
3245
+ },
3246
+ {
3247
+ "epoch": 0.12060432404271945,
3248
+ "grad_norm": 0.09515385329723358,
3249
+ "learning_rate": 0.0002988888888888889,
3250
+ "loss": 0.0312,
3251
+ "step": 463
3252
+ },
3253
+ {
3254
+ "epoch": 0.12086480854389164,
3255
+ "grad_norm": 0.06927935779094696,
3256
+ "learning_rate": 0.00029833333333333334,
3257
+ "loss": 0.0159,
3258
+ "step": 464
3259
+ },
3260
+ {
3261
+ "epoch": 0.12112529304506382,
3262
+ "grad_norm": 0.1430736929178238,
3263
+ "learning_rate": 0.0002977777777777778,
3264
+ "loss": 0.0163,
3265
+ "step": 465
3266
+ },
3267
+ {
3268
+ "epoch": 0.121385777546236,
3269
+ "grad_norm": 0.09657033532857895,
3270
+ "learning_rate": 0.0002972222222222222,
3271
+ "loss": 0.0268,
3272
+ "step": 466
3273
+ },
3274
+ {
3275
+ "epoch": 0.12164626204740818,
3276
+ "grad_norm": 0.06322190165519714,
3277
+ "learning_rate": 0.0002966666666666667,
3278
+ "loss": 0.0283,
3279
+ "step": 467
3280
+ },
3281
+ {
3282
+ "epoch": 0.12190674654858036,
3283
+ "grad_norm": 0.09344757348299026,
3284
+ "learning_rate": 0.0002961111111111111,
3285
+ "loss": 0.0121,
3286
+ "step": 468
3287
+ },
3288
+ {
3289
+ "epoch": 0.12216723104975254,
3290
+ "grad_norm": 0.08868320286273956,
3291
+ "learning_rate": 0.0002955555555555556,
3292
+ "loss": 0.0265,
3293
+ "step": 469
3294
+ },
3295
+ {
3296
+ "epoch": 0.12242771555092472,
3297
+ "grad_norm": 0.11758578568696976,
3298
+ "learning_rate": 0.000295,
3299
+ "loss": 0.0165,
3300
+ "step": 470
3301
+ },
3302
+ {
3303
+ "epoch": 0.1226882000520969,
3304
+ "grad_norm": 0.09136319160461426,
3305
+ "learning_rate": 0.00029444444444444445,
3306
+ "loss": 0.0184,
3307
+ "step": 471
3308
+ },
3309
+ {
3310
+ "epoch": 0.12294868455326909,
3311
+ "grad_norm": 0.12742240726947784,
3312
+ "learning_rate": 0.0002938888888888889,
3313
+ "loss": 0.0311,
3314
+ "step": 472
3315
+ },
3316
+ {
3317
+ "epoch": 0.12320916905444126,
3318
+ "grad_norm": 0.11562032252550125,
3319
+ "learning_rate": 0.0002933333333333333,
3320
+ "loss": 0.034,
3321
+ "step": 473
3322
+ },
3323
+ {
3324
+ "epoch": 0.12346965355561344,
3325
+ "grad_norm": 0.07075949758291245,
3326
+ "learning_rate": 0.0002927777777777778,
3327
+ "loss": 0.0261,
3328
+ "step": 474
3329
+ },
3330
+ {
3331
+ "epoch": 0.12373013805678562,
3332
+ "grad_norm": 0.20507678389549255,
3333
+ "learning_rate": 0.0002922222222222222,
3334
+ "loss": 0.0402,
3335
+ "step": 475
3336
+ },
3337
+ {
3338
+ "epoch": 0.1239906225579578,
3339
+ "grad_norm": 0.06373949348926544,
3340
+ "learning_rate": 0.0002916666666666667,
3341
+ "loss": 0.0274,
3342
+ "step": 476
3343
+ },
3344
+ {
3345
+ "epoch": 0.12425110705912998,
3346
+ "grad_norm": 0.06538847833871841,
3347
+ "learning_rate": 0.00029111111111111113,
3348
+ "loss": 0.025,
3349
+ "step": 477
3350
+ },
3351
+ {
3352
+ "epoch": 0.12451159156030216,
3353
+ "grad_norm": 0.16323456168174744,
3354
+ "learning_rate": 0.00029055555555555556,
3355
+ "loss": 0.0366,
3356
+ "step": 478
3357
+ },
3358
+ {
3359
+ "epoch": 0.12477207606147435,
3360
+ "grad_norm": 0.07732845097780228,
3361
+ "learning_rate": 0.00029,
3362
+ "loss": 0.0284,
3363
+ "step": 479
3364
+ },
3365
+ {
3366
+ "epoch": 0.12503256056264653,
3367
+ "grad_norm": 0.06152462214231491,
3368
+ "learning_rate": 0.00028944444444444444,
3369
+ "loss": 0.0244,
3370
+ "step": 480
3371
+ },
3372
+ {
3373
+ "epoch": 0.1252930450638187,
3374
+ "grad_norm": 0.10735264420509338,
3375
+ "learning_rate": 0.0002888888888888889,
3376
+ "loss": 0.0124,
3377
+ "step": 481
3378
+ },
3379
+ {
3380
+ "epoch": 0.12555352956499088,
3381
+ "grad_norm": 0.07874636352062225,
3382
+ "learning_rate": 0.0002883333333333333,
3383
+ "loss": 0.0286,
3384
+ "step": 482
3385
+ },
3386
+ {
3387
+ "epoch": 0.12581401406616308,
3388
+ "grad_norm": 0.07407646626234055,
3389
+ "learning_rate": 0.0002877777777777778,
3390
+ "loss": 0.0261,
3391
+ "step": 483
3392
+ },
3393
+ {
3394
+ "epoch": 0.12607449856733524,
3395
+ "grad_norm": 0.07773268967866898,
3396
+ "learning_rate": 0.00028722222222222224,
3397
+ "loss": 0.0148,
3398
+ "step": 484
3399
+ },
3400
+ {
3401
+ "epoch": 0.12633498306850743,
3402
+ "grad_norm": 0.0872015506029129,
3403
+ "learning_rate": 0.0002866666666666667,
3404
+ "loss": 0.0303,
3405
+ "step": 485
3406
+ },
3407
+ {
3408
+ "epoch": 0.1265954675696796,
3409
+ "grad_norm": 0.08122217655181885,
3410
+ "learning_rate": 0.0002861111111111111,
3411
+ "loss": 0.0262,
3412
+ "step": 486
3413
+ },
3414
+ {
3415
+ "epoch": 0.1268559520708518,
3416
+ "grad_norm": 0.1467408388853073,
3417
+ "learning_rate": 0.00028555555555555555,
3418
+ "loss": 0.0306,
3419
+ "step": 487
3420
+ },
3421
+ {
3422
+ "epoch": 0.12711643657202396,
3423
+ "grad_norm": 0.07901852577924728,
3424
+ "learning_rate": 0.000285,
3425
+ "loss": 0.0147,
3426
+ "step": 488
3427
+ },
3428
+ {
3429
+ "epoch": 0.12737692107319615,
3430
+ "grad_norm": 0.08532578498125076,
3431
+ "learning_rate": 0.0002844444444444444,
3432
+ "loss": 0.0258,
3433
+ "step": 489
3434
+ },
3435
+ {
3436
+ "epoch": 0.1276374055743683,
3437
+ "grad_norm": 0.08219342678785324,
3438
+ "learning_rate": 0.0002838888888888889,
3439
+ "loss": 0.0252,
3440
+ "step": 490
3441
+ },
3442
+ {
3443
+ "epoch": 0.1278978900755405,
3444
+ "grad_norm": 0.07493036240339279,
3445
+ "learning_rate": 0.00028333333333333335,
3446
+ "loss": 0.0259,
3447
+ "step": 491
3448
+ },
3449
+ {
3450
+ "epoch": 0.1281583745767127,
3451
+ "grad_norm": 0.10418077558279037,
3452
+ "learning_rate": 0.0002827777777777778,
3453
+ "loss": 0.0274,
3454
+ "step": 492
3455
+ },
3456
+ {
3457
+ "epoch": 0.12841885907788486,
3458
+ "grad_norm": 0.07653704285621643,
3459
+ "learning_rate": 0.00028222222222222223,
3460
+ "loss": 0.0281,
3461
+ "step": 493
3462
+ },
3463
+ {
3464
+ "epoch": 0.12867934357905705,
3465
+ "grad_norm": 0.06863569468259811,
3466
+ "learning_rate": 0.00028166666666666666,
3467
+ "loss": 0.0185,
3468
+ "step": 494
3469
+ },
3470
+ {
3471
+ "epoch": 0.12893982808022922,
3472
+ "grad_norm": 0.08756248652935028,
3473
+ "learning_rate": 0.0002811111111111111,
3474
+ "loss": 0.0298,
3475
+ "step": 495
3476
+ },
3477
+ {
3478
+ "epoch": 0.1292003125814014,
3479
+ "grad_norm": 0.12433123588562012,
3480
+ "learning_rate": 0.00028055555555555554,
3481
+ "loss": 0.0337,
3482
+ "step": 496
3483
+ },
3484
+ {
3485
+ "epoch": 0.12946079708257358,
3486
+ "grad_norm": 0.14893244206905365,
3487
+ "learning_rate": 0.00028000000000000003,
3488
+ "loss": 0.0381,
3489
+ "step": 497
3490
+ },
3491
+ {
3492
+ "epoch": 0.12972128158374577,
3493
+ "grad_norm": 0.13264304399490356,
3494
+ "learning_rate": 0.00027944444444444447,
3495
+ "loss": 0.0279,
3496
+ "step": 498
3497
+ },
3498
+ {
3499
+ "epoch": 0.12998176608491796,
3500
+ "grad_norm": 0.12043178826570511,
3501
+ "learning_rate": 0.0002788888888888889,
3502
+ "loss": 0.0143,
3503
+ "step": 499
3504
+ },
3505
+ {
3506
+ "epoch": 0.13024225058609012,
3507
+ "grad_norm": 0.09020431339740753,
3508
+ "learning_rate": 0.00027833333333333334,
3509
+ "loss": 0.0328,
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": 256,
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":"2025-12-31T20:57:11.806292921Z","level":"INFO","msg":"stream: starting","core version":"0.22.2"}
2
+ {"time":"2025-12-31T20:57:11.981069966Z","level":"INFO","msg":"stream: created new stream","id":"onkf9agw"}
3
+ {"time":"2025-12-31T20:57:11.981132978Z","level":"INFO","msg":"handler: started","stream_id":"onkf9agw"}
4
+ {"time":"2025-12-31T20:57:11.981191523Z","level":"INFO","msg":"stream: started","id":"onkf9agw"}
5
+ {"time":"2025-12-31T20:57:11.981222285Z","level":"INFO","msg":"writer: started","stream_id":"onkf9agw"}
6
+ {"time":"2025-12-31T20:57:11.981241501Z","level":"INFO","msg":"sender: started","stream_id":"onkf9agw"}
7
+ {"time":"2025-12-31T22:38:24.497789286Z","level":"INFO","msg":"stream: closing","id":"onkf9agw"}
8
+ {"time":"2025-12-31T22:38:24.906415762Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
9
+ {"time":"2025-12-31T22:38:25.067549955Z","level":"INFO","msg":"handler: closed","stream_id":"onkf9agw"}
10
+ {"time":"2025-12-31T22:38:25.067677063Z","level":"INFO","msg":"sender: closed","stream_id":"onkf9agw"}
11
+ {"time":"2025-12-31T22:38:25.067689626Z","level":"INFO","msg":"stream: closed","id":"onkf9agw"}
wandb/debug.log ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-12-31 20:57:11,594 INFO MainThread:3017764 [wandb_setup.py:_flush():81] Current SDK version is 0.22.2
2
+ 2025-12-31 20:57:11,594 INFO MainThread:3017764 [wandb_setup.py:_flush():81] Configure stats pid to 3017764
3
+ 2025-12-31 20:57:11,594 INFO MainThread:3017764 [wandb_setup.py:_flush():81] Loading settings from /home/v-menggao/.config/wandb/settings
4
+ 2025-12-31 20:57:11,594 INFO MainThread:3017764 [wandb_setup.py:_flush():81] Loading settings from /home/v-menggao/code/VLM2Vec/wandb/settings
5
+ 2025-12-31 20:57:11,594 INFO MainThread:3017764 [wandb_setup.py:_flush():81] Loading settings from environment variables
6
+ 2025-12-31 20:57:11,594 INFO MainThread:3017764 [wandb_init.py:setup_run_log_directory():705] Logging user logs to /home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_3B_multilayer_distill_AOP_10_pooling_12_26_a100_multinode_Classifier_Layer12_V5_i_ret_bsz128/wandb/run-20251231_205711-onkf9agw/logs/debug.log
7
+ 2025-12-31 20:57:11,594 INFO MainThread:3017764 [wandb_init.py:setup_run_log_directory():706] Logging internal logs to /home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_3B_multilayer_distill_AOP_10_pooling_12_26_a100_multinode_Classifier_Layer12_V5_i_ret_bsz128/wandb/run-20251231_205711-onkf9agw/logs/debug-internal.log
8
+ 2025-12-31 20:57:11,594 INFO MainThread:3017764 [wandb_init.py:init():832] calling init triggers
9
+ 2025-12-31 20:57:11,594 INFO MainThread:3017764 [wandb_init.py:init():837] wandb.init called with sweep_config: {}
10
+ config: {'_wandb': {}}
11
+ 2025-12-31 20:57:11,594 INFO MainThread:3017764 [wandb_init.py:init():880] starting backend
12
+ 2025-12-31 20:57:11,800 INFO MainThread:3017764 [wandb_init.py:init():883] sending inform_init request
13
+ 2025-12-31 20:57:11,805 INFO MainThread:3017764 [wandb_init.py:init():891] backend started and connected
14
+ 2025-12-31 20:57:11,806 INFO MainThread:3017764 [wandb_init.py:init():961] updated telemetry
15
+ 2025-12-31 20:57:11,812 INFO MainThread:3017764 [wandb_init.py:init():985] communicating run to backend with 90.0 second timeout
16
+ 2025-12-31 20:57:12,175 INFO MainThread:3017764 [wandb_init.py:init():1036] starting run threads in backend
17
+ 2025-12-31 20:57:12,286 INFO MainThread:3017764 [wandb_run.py:_console_start():2509] atexit reg
18
+ 2025-12-31 20:57:12,286 INFO MainThread:3017764 [wandb_run.py:_redirect():2357] redirect: wrap_raw
19
+ 2025-12-31 20:57:12,286 INFO MainThread:3017764 [wandb_run.py:_redirect():2426] Wrapping output streams.
20
+ 2025-12-31 20:57:12,286 INFO MainThread:3017764 [wandb_run.py:_redirect():2449] Redirects installed.
21
+ 2025-12-31 20:57:12,289 INFO MainThread:3017764 [wandb_init.py:init():1076] run started, returning control to user process
22
+ 2025-12-31 20:57:12,290 INFO MainThread:3017764 [wandb_run.py:_config_callback():1392] config_cb None None {'output_dir': '/home/v-menggao/code/VLM2Vec/experiments/Qwen2_5vl_3B_multilayer_distill_AOP_10_pooling_12_26_a100_multinode_Classifier_Layer12_V5_i_ret_bsz128', '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': 256, '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_3B_multilayer_distill_AOP_10_pooling_12_26_a100_multinode_Classifier_Layer12_V5_i_ret_bsz128/runs/Dec31_20-47-58_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_3B_multilayer_distill_AOP_10_pooling_12_26_a100_multinode_Classifier_Layer12_V5_i_ret_bsz128', '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
+ 2025-12-31 22:38:24,497 INFO wandb-AsyncioManager-main:3017764 [service_client.py:_forward_responses():80] Reached EOF.
24
+ 2025-12-31 22:38:24,498 INFO wandb-AsyncioManager-main:3017764 [mailbox.py:close():137] Closing mailbox, abandoning 1 handles.
wandb/run-20251231_205711-onkf9agw/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train_loss":0.08903209956176579,"_wandb":{"runtime":6072},"train/grad_norm":0.08689691126346588,"train/learning_rate":5.555555555555555e-07,"train/global_step":1000,"train/epoch":0.26048450117218025,"train_samples_per_second":42.182,"_timestamp":1.7672207002620344e+09,"train_runtime":6068.8965,"total_flos":0,"train/loss":0.0125,"_runtime":6072,"train_steps_per_second":0.165,"_step":1000}
wandb/run-20251231_205711-onkf9agw/logs/debug-internal.log ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2025-12-31T20:57:11.806292921Z","level":"INFO","msg":"stream: starting","core version":"0.22.2"}
2
+ {"time":"2025-12-31T20:57:11.981069966Z","level":"INFO","msg":"stream: created new stream","id":"onkf9agw"}
3
+ {"time":"2025-12-31T20:57:11.981132978Z","level":"INFO","msg":"handler: started","stream_id":"onkf9agw"}
4
+ {"time":"2025-12-31T20:57:11.981191523Z","level":"INFO","msg":"stream: started","id":"onkf9agw"}
5
+ {"time":"2025-12-31T20:57:11.981222285Z","level":"INFO","msg":"writer: started","stream_id":"onkf9agw"}
6
+ {"time":"2025-12-31T20:57:11.981241501Z","level":"INFO","msg":"sender: started","stream_id":"onkf9agw"}
7
+ {"time":"2025-12-31T22:38:24.497789286Z","level":"INFO","msg":"stream: closing","id":"onkf9agw"}
8
+ {"time":"2025-12-31T22:38:24.906415762Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
9
+ {"time":"2025-12-31T22:38:25.067549955Z","level":"INFO","msg":"handler: closed","stream_id":"onkf9agw"}
10
+ {"time":"2025-12-31T22:38:25.067677063Z","level":"INFO","msg":"sender: closed","stream_id":"onkf9agw"}
11
+ {"time":"2025-12-31T22:38:25.067689626Z","level":"INFO","msg":"stream: closed","id":"onkf9agw"}