Hugging Face's logo

X-GenGroup
/
PaCo-Reward-7B-Lora

Image-Text-to-Text
Transformers
Safetensors
conversational
Model card Files
xet
Community
1
Jayce-Ping commited on
Commit
73c53ea
·
verified ·
1 Parent(s): ea5e489

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. adapter_config.json +123 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +24 -0
  5. chat_template.jinja +7 -0
  6. merges.txt +0 -0
  7. preprocessor_config.json +39 -0
  8. special_tokens_map.json +31 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +209 -0
  11. trainer_state.json +1139 -0
  12. training_args.bin +3 -0
  13. video_preprocessor_config.json +43 -0
  14. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 32,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "layers.8.mlp.up_proj",
29
+ "layers.12.mlp.down_proj",
30
+ "layers.11.mlp.up_proj",
31
+ "layers.23.mlp.up_proj",
32
+ "layers.26.mlp.up_proj",
33
+ "layers.5.mlp.gate_proj",
34
+ "layers.10.mlp.up_proj",
35
+ "layers.19.mlp.up_proj",
36
+ "k_proj",
37
+ "q_proj",
38
+ "layers.4.mlp.up_proj",
39
+ "layers.9.mlp.down_proj",
40
+ "layers.20.mlp.down_proj",
41
+ "layers.5.mlp.up_proj",
42
+ "layers.1.mlp.up_proj",
43
+ "layers.4.mlp.down_proj",
44
+ "layers.27.mlp.down_proj",
45
+ "layers.6.mlp.down_proj",
46
+ "layers.13.mlp.down_proj",
47
+ "layers.1.mlp.down_proj",
48
+ "layers.26.mlp.gate_proj",
49
+ "layers.21.mlp.up_proj",
50
+ "layers.12.mlp.up_proj",
51
+ "layers.22.mlp.up_proj",
52
+ "layers.22.mlp.down_proj",
53
+ "layers.10.mlp.gate_proj",
54
+ "layers.18.mlp.down_proj",
55
+ "layers.2.mlp.gate_proj",
56
+ "layers.3.mlp.up_proj",
57
+ "layers.0.mlp.up_proj",
58
+ "layers.24.mlp.gate_proj",
59
+ "layers.23.mlp.down_proj",
60
+ "layers.21.mlp.gate_proj",
61
+ "layers.11.mlp.gate_proj",
62
+ "layers.3.mlp.down_proj",
63
+ "layers.14.mlp.gate_proj",
64
+ "layers.27.mlp.gate_proj",
65
+ "layers.6.mlp.up_proj",
66
+ "layers.19.mlp.down_proj",
67
+ "layers.9.mlp.gate_proj",
68
+ "layers.2.mlp.up_proj",
69
+ "layers.5.mlp.down_proj",
70
+ "layers.22.mlp.gate_proj",
71
+ "o_proj",
72
+ "layers.4.mlp.gate_proj",
73
+ "layers.7.mlp.up_proj",
74
+ "layers.16.mlp.down_proj",
75
+ "layers.23.mlp.gate_proj",
76
+ "layers.0.mlp.down_proj",
77
+ "layers.15.mlp.down_proj",
78
+ "v_proj",
79
+ "layers.7.mlp.gate_proj",
80
+ "layers.26.mlp.down_proj",
81
+ "layers.16.mlp.up_proj",
82
+ "layers.17.mlp.gate_proj",
83
+ "layers.12.mlp.gate_proj",
84
+ "layers.27.mlp.up_proj",
85
+ "layers.25.mlp.gate_proj",
86
+ "layers.21.mlp.down_proj",
87
+ "layers.15.mlp.gate_proj",
88
+ "layers.25.mlp.up_proj",
89
+ "layers.18.mlp.gate_proj",
90
+ "layers.20.mlp.up_proj",
91
+ "layers.15.mlp.up_proj",
92
+ "layers.9.mlp.up_proj",
93
+ "layers.16.mlp.gate_proj",
94
+ "layers.14.mlp.up_proj",
95
+ "layers.24.mlp.up_proj",
96
+ "layers.6.mlp.gate_proj",
97
+ "layers.19.mlp.gate_proj",
98
+ "layers.14.mlp.down_proj",
99
+ "layers.24.mlp.down_proj",
100
+ "layers.10.mlp.down_proj",
101
+ "layers.17.mlp.down_proj",
102
+ "layers.1.mlp.gate_proj",
103
+ "layers.8.mlp.down_proj",
104
+ "layers.11.mlp.down_proj",
105
+ "layers.13.mlp.gate_proj",
106
+ "layers.13.mlp.up_proj",
107
+ "layers.8.mlp.gate_proj",
108
+ "layers.25.mlp.down_proj",
109
+ "layers.18.mlp.up_proj",
110
+ "layers.2.mlp.down_proj",
111
+ "layers.17.mlp.up_proj",
112
+ "layers.20.mlp.gate_proj",
113
+ "layers.7.mlp.down_proj",
114
+ "layers.0.mlp.gate_proj",
115
+ "layers.3.mlp.gate_proj"
116
+ ],
117
+ "target_parameters": null,
118
+ "task_type": "CAUSAL_LM",
119
+ "trainable_token_indices": null,
120
+ "use_dora": false,
121
+ "use_qalora": false,
122
+ "use_rslora": false
123
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ddb62275077fca1abe7230446a6c73fa45f4a1077e5924a063e00c8b97c0d8
3
+ size 323020048
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 %}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 12845056,
26
+ "merge_size": 2,
27
+ "min_pixels": 3136,
28
+ "pad_size": null,
29
+ "patch_size": 14,
30
+ "processor_class": "Qwen2_5_VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 12845056,
36
+ "shortest_edge": 3136
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
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.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "padding_side": "right",
205
+ "processor_class": "Qwen2_5_VLProcessor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
trainer_state.json ADDED
@@ -0,0 +1,1139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1552,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.012890750886239123,
14
+ "grad_norm": 1.7974083423614502,
15
+ "learning_rate": 1.153846153846154e-05,
16
+ "loss": 2.5309,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.025781501772478246,
21
+ "grad_norm": 0.9546365737915039,
22
+ "learning_rate": 2.435897435897436e-05,
23
+ "loss": 2.2805,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.03867225265871737,
28
+ "grad_norm": 0.6726247072219849,
29
+ "learning_rate": 3.717948717948718e-05,
30
+ "loss": 1.9329,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.05156300354495649,
35
+ "grad_norm": 0.5635246634483337,
36
+ "learning_rate": 5e-05,
37
+ "loss": 1.7205,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.06445375443119562,
42
+ "grad_norm": 0.48018646240234375,
43
+ "learning_rate": 6.282051282051282e-05,
44
+ "loss": 1.6227,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.07734450531743474,
49
+ "grad_norm": 0.4588874578475952,
50
+ "learning_rate": 7.564102564102564e-05,
51
+ "loss": 1.565,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.09023525620367387,
56
+ "grad_norm": 0.5382615923881531,
57
+ "learning_rate": 8.846153846153847e-05,
58
+ "loss": 1.5151,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.10312600708991299,
63
+ "grad_norm": 0.5467047691345215,
64
+ "learning_rate": 0.00010128205128205129,
65
+ "loss": 1.4629,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.11601675797615212,
70
+ "grad_norm": 0.5823647379875183,
71
+ "learning_rate": 0.0001141025641025641,
72
+ "loss": 1.457,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.12890750886239125,
77
+ "grad_norm": 0.6547259092330933,
78
+ "learning_rate": 0.00012692307692307693,
79
+ "loss": 1.4192,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.14179825974863036,
84
+ "grad_norm": 0.5140829086303711,
85
+ "learning_rate": 0.00013974358974358974,
86
+ "loss": 1.3869,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.15468901063486948,
91
+ "grad_norm": 0.6194220185279846,
92
+ "learning_rate": 0.00015256410256410255,
93
+ "loss": 1.365,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.1675797615211086,
98
+ "grad_norm": 0.6340938806533813,
99
+ "learning_rate": 0.0001653846153846154,
100
+ "loss": 1.3559,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.18047051240734774,
105
+ "grad_norm": 0.5935661792755127,
106
+ "learning_rate": 0.00017820512820512823,
107
+ "loss": 1.3447,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.19336126329358685,
112
+ "grad_norm": 0.5271995663642883,
113
+ "learning_rate": 0.00019102564102564104,
114
+ "loss": 1.3229,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.20625201417982597,
119
+ "grad_norm": 0.5766036510467529,
120
+ "learning_rate": 0.00019999772102388783,
121
+ "loss": 1.3238,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.2191427650660651,
126
+ "grad_norm": 0.4888124167919159,
127
+ "learning_rate": 0.0001999572087826214,
128
+ "loss": 1.3371,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.23203351595230423,
133
+ "grad_norm": 0.5345163345336914,
134
+ "learning_rate": 0.00019986607624302306,
135
+ "loss": 1.3455,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.24492426683854335,
140
+ "grad_norm": 0.4851045310497284,
141
+ "learning_rate": 0.00019972436955640487,
142
+ "loss": 1.3176,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.2578150177247825,
147
+ "grad_norm": 0.47015997767448425,
148
+ "learning_rate": 0.0001995321604858227,
149
+ "loss": 1.3131,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.2707057686110216,
154
+ "grad_norm": 0.5002295970916748,
155
+ "learning_rate": 0.00019928954636973373,
156
+ "loss": 1.2997,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.2835965194972607,
161
+ "grad_norm": 0.46887412667274475,
162
+ "learning_rate": 0.00019899665007270265,
163
+ "loss": 1.279,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.2964872703834998,
168
+ "grad_norm": 0.4887183606624603,
169
+ "learning_rate": 0.00019865361992318033,
170
+ "loss": 1.2773,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.30937802126973896,
175
+ "grad_norm": 0.49127480387687683,
176
+ "learning_rate": 0.00019826062963838753,
177
+ "loss": 1.2674,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.3222687721559781,
182
+ "grad_norm": 0.49845078587532043,
183
+ "learning_rate": 0.0001978178782363411,
184
+ "loss": 1.2723,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.3351595230422172,
189
+ "grad_norm": 0.4858417809009552,
190
+ "learning_rate": 0.00019732558993506723,
191
+ "loss": 1.273,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.34805027392845633,
196
+ "grad_norm": 0.47399166226387024,
197
+ "learning_rate": 0.00019678401403905307,
198
+ "loss": 1.2629,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.3609410248146955,
203
+ "grad_norm": 0.47289639711380005,
204
+ "learning_rate": 0.0001961934248129941,
205
+ "loss": 1.2408,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.37383177570093457,
210
+ "grad_norm": 0.48805466294288635,
211
+ "learning_rate": 0.00019555412134290102,
212
+ "loss": 1.2421,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.3867225265871737,
217
+ "grad_norm": 0.47072649002075195,
218
+ "learning_rate": 0.00019486642738463674,
219
+ "loss": 1.2583,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.39961327747341285,
224
+ "grad_norm": 0.4364190101623535,
225
+ "learning_rate": 0.00019413069119995994,
226
+ "loss": 1.2377,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.41250402835965194,
231
+ "grad_norm": 0.4522920250892639,
232
+ "learning_rate": 0.0001933472853801586,
233
+ "loss": 1.2331,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.4253947792458911,
238
+ "grad_norm": 0.46202462911605835,
239
+ "learning_rate": 0.0001925166066573624,
240
+ "loss": 1.2277,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.4382855301321302,
245
+ "grad_norm": 0.43247494101524353,
246
+ "learning_rate": 0.00019163907570362963,
247
+ "loss": 1.2369,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.4511762810183693,
252
+ "grad_norm": 0.47149762511253357,
253
+ "learning_rate": 0.00019071513691791079,
254
+ "loss": 1.2394,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.46406703190460846,
259
+ "grad_norm": 0.44876205921173096,
260
+ "learning_rate": 0.00018974525820099607,
261
+ "loss": 1.2318,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.47695778279084755,
266
+ "grad_norm": 0.44522625207901,
267
+ "learning_rate": 0.00018872993071856114,
268
+ "loss": 1.2214,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.4898485336770867,
273
+ "grad_norm": 0.45371952652931213,
274
+ "learning_rate": 0.0001876696686524314,
275
+ "loss": 1.2152,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.5027392845633258,
280
+ "grad_norm": 0.45091456174850464,
281
+ "learning_rate": 0.00018656500894018987,
282
+ "loss": 1.2025,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.515630035449565,
287
+ "grad_norm": 0.47521355748176575,
288
+ "learning_rate": 0.00018541651100326175,
289
+ "loss": 1.2107,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.528520786335804,
294
+ "grad_norm": 0.4451088607311249,
295
+ "learning_rate": 0.0001842247564636121,
296
+ "loss": 1.1974,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.5414115372220432,
301
+ "grad_norm": 0.4933655858039856,
302
+ "learning_rate": 0.0001829903488492013,
303
+ "loss": 1.1847,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.5543022881082823,
308
+ "grad_norm": 0.4385446608066559,
309
+ "learning_rate": 0.00018171391328834638,
310
+ "loss": 1.1925,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.5671930389945214,
315
+ "grad_norm": 0.46878549456596375,
316
+ "learning_rate": 0.0001803960961931439,
317
+ "loss": 1.176,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.5800837898807606,
322
+ "grad_norm": 0.45197296142578125,
323
+ "learning_rate": 0.000179037564932114,
324
+ "loss": 1.1888,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.5929745407669996,
329
+ "grad_norm": 0.4496542811393738,
330
+ "learning_rate": 0.00017763900749223196,
331
+ "loss": 1.1823,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.6058652916532388,
336
+ "grad_norm": 0.4356934428215027,
337
+ "learning_rate": 0.00017620113213051797,
338
+ "loss": 1.1877,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.6187560425394779,
343
+ "grad_norm": 0.46125900745391846,
344
+ "learning_rate": 0.00017472466701536193,
345
+ "loss": 1.1797,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.6316467934257171,
350
+ "grad_norm": 0.45797720551490784,
351
+ "learning_rate": 0.0001732103598577645,
352
+ "loss": 1.1777,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.6445375443119562,
357
+ "grad_norm": 0.4385370910167694,
358
+ "learning_rate": 0.0001716589775326817,
359
+ "loss": 1.1562,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.6574282951981953,
364
+ "grad_norm": 0.46976742148399353,
365
+ "learning_rate": 0.00017007130569066413,
366
+ "loss": 1.1677,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.6703190460844344,
371
+ "grad_norm": 0.46103382110595703,
372
+ "learning_rate": 0.00016844814835998825,
373
+ "loss": 1.1776,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.6832097969706735,
378
+ "grad_norm": 0.5240194201469421,
379
+ "learning_rate": 0.00016679032753948056,
380
+ "loss": 1.1489,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.6961005478569127,
385
+ "grad_norm": 0.4437713027000427,
386
+ "learning_rate": 0.00016509868278224125,
387
+ "loss": 1.1721,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.7089912987431518,
392
+ "grad_norm": 0.4481850862503052,
393
+ "learning_rate": 0.00016337407077047784,
394
+ "loss": 1.1613,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.721882049629391,
399
+ "grad_norm": 0.46106868982315063,
400
+ "learning_rate": 0.00016161736488166462,
401
+ "loss": 1.155,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.73477280051563,
406
+ "grad_norm": 0.4505125880241394,
407
+ "learning_rate": 0.000159829454746247,
408
+ "loss": 1.159,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.7476635514018691,
413
+ "grad_norm": 0.4489360749721527,
414
+ "learning_rate": 0.00015801124579711525,
415
+ "loss": 1.1794,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.7605543022881083,
420
+ "grad_norm": 0.4428081214427948,
421
+ "learning_rate": 0.0001561636588110753,
422
+ "loss": 1.1524,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.7734450531743474,
427
+ "grad_norm": 0.4341617226600647,
428
+ "learning_rate": 0.00015428762944254932,
429
+ "loss": 1.1497,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.7863358040605866,
434
+ "grad_norm": 0.43959757685661316,
435
+ "learning_rate": 0.00015238410774974186,
436
+ "loss": 1.1364,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.7992265549468257,
441
+ "grad_norm": 0.456399530172348,
442
+ "learning_rate": 0.00015045405771351193,
443
+ "loss": 1.1266,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.8121173058330647,
448
+ "grad_norm": 0.4572042226791382,
449
+ "learning_rate": 0.00014849845674919364,
450
+ "loss": 1.1417,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.8250080567193039,
455
+ "grad_norm": 0.4575168788433075,
456
+ "learning_rate": 0.00014651829521161424,
457
+ "loss": 1.1532,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.837898807605543,
462
+ "grad_norm": 0.4344440996646881,
463
+ "learning_rate": 0.00014451457589355872,
464
+ "loss": 1.137,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.8507895584917822,
469
+ "grad_norm": 0.4362059235572815,
470
+ "learning_rate": 0.00014248831351793592,
471
+ "loss": 1.1408,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.8636803093780213,
476
+ "grad_norm": 0.46403059363365173,
477
+ "learning_rate": 0.0001404405342239028,
478
+ "loss": 1.1227,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.8765710602642603,
483
+ "grad_norm": 0.47248131036758423,
484
+ "learning_rate": 0.0001383722750472074,
485
+ "loss": 1.1363,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.8894618111504995,
490
+ "grad_norm": 0.4404482841491699,
491
+ "learning_rate": 0.00013628458339501348,
492
+ "loss": 1.1179,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.9023525620367386,
497
+ "grad_norm": 0.4384572207927704,
498
+ "learning_rate": 0.00013417851651547307,
499
+ "loss": 1.1066,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.9152433129229778,
504
+ "grad_norm": 0.4435371458530426,
505
+ "learning_rate": 0.0001320551409623149,
506
+ "loss": 1.12,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.9281340638092169,
511
+ "grad_norm": 0.5222971439361572,
512
+ "learning_rate": 0.00012991553205472092,
513
+ "loss": 1.1164,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.941024814695456,
518
+ "grad_norm": 0.45858514308929443,
519
+ "learning_rate": 0.00012776077333276326,
520
+ "loss": 1.1182,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.9539155655816951,
525
+ "grad_norm": 0.45299065113067627,
526
+ "learning_rate": 0.0001255919560086783,
527
+ "loss": 1.1174,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.9668063164679342,
532
+ "grad_norm": 0.4541768729686737,
533
+ "learning_rate": 0.0001234101784142553,
534
+ "loss": 1.1221,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.9796970673541734,
539
+ "grad_norm": 0.4411795139312744,
540
+ "learning_rate": 0.0001212165454446196,
541
+ "loss": 1.1113,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.9925878182404125,
546
+ "grad_norm": 0.4533502161502838,
547
+ "learning_rate": 0.00011901216799869188,
548
+ "loss": 1.1122,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.0,
553
+ "eval_accuracy": 0.6748553734614313,
554
+ "eval_first_token_accuracy": 0.8449519230769231,
555
+ "eval_loss": 1.118744134902954,
556
+ "eval_runtime": 727.7965,
557
+ "eval_samples_per_second": 6.851,
558
+ "eval_steps_per_second": 0.429,
559
+ "step": 776
560
+ },
561
+ {
562
+ "epoch": 1.0051563003544957,
563
+ "grad_norm": 0.4265609085559845,
564
+ "learning_rate": 0.0001167981624166072,
565
+ "loss": 1.0876,
566
+ "step": 780
567
+ },
568
+ {
569
+ "epoch": 1.0180470512407347,
570
+ "grad_norm": 0.48834115266799927,
571
+ "learning_rate": 0.00011457564991437823,
572
+ "loss": 1.0156,
573
+ "step": 790
574
+ },
575
+ {
576
+ "epoch": 1.030937802126974,
577
+ "grad_norm": 0.4989129602909088,
578
+ "learning_rate": 0.00011234575601608957,
579
+ "loss": 1.0072,
580
+ "step": 800
581
+ },
582
+ {
583
+ "epoch": 1.043828553013213,
584
+ "grad_norm": 0.4992086887359619,
585
+ "learning_rate": 0.00011010960998391002,
586
+ "loss": 1.0185,
587
+ "step": 810
588
+ },
589
+ {
590
+ "epoch": 1.0567193038994522,
591
+ "grad_norm": 0.5244722366333008,
592
+ "learning_rate": 0.00010786834424621211,
593
+ "loss": 1.013,
594
+ "step": 820
595
+ },
596
+ {
597
+ "epoch": 1.0696100547856913,
598
+ "grad_norm": 0.5480940937995911,
599
+ "learning_rate": 0.000105623093824088,
600
+ "loss": 1.0116,
601
+ "step": 830
602
+ },
603
+ {
604
+ "epoch": 1.0825008056719303,
605
+ "grad_norm": 0.49391430616378784,
606
+ "learning_rate": 0.00010337499575655249,
607
+ "loss": 0.9852,
608
+ "step": 840
609
+ },
610
+ {
611
+ "epoch": 1.0953915565581696,
612
+ "grad_norm": 0.48984748125076294,
613
+ "learning_rate": 0.00010112518852472414,
614
+ "loss": 1.0052,
615
+ "step": 850
616
+ },
617
+ {
618
+ "epoch": 1.1082823074444086,
619
+ "grad_norm": 0.5330230593681335,
620
+ "learning_rate": 9.887481147527588e-05,
621
+ "loss": 1.0058,
622
+ "step": 860
623
+ },
624
+ {
625
+ "epoch": 1.1211730583306478,
626
+ "grad_norm": 0.4981665313243866,
627
+ "learning_rate": 9.66250042434475e-05,
628
+ "loss": 1.0037,
629
+ "step": 870
630
+ },
631
+ {
632
+ "epoch": 1.1340638092168869,
633
+ "grad_norm": 0.5282273888587952,
634
+ "learning_rate": 9.437690617591202e-05,
635
+ "loss": 0.9962,
636
+ "step": 880
637
+ },
638
+ {
639
+ "epoch": 1.1469545601031261,
640
+ "grad_norm": 0.5284985303878784,
641
+ "learning_rate": 9.213165575378793e-05,
642
+ "loss": 1.0142,
643
+ "step": 890
644
+ },
645
+ {
646
+ "epoch": 1.1598453109893652,
647
+ "grad_norm": 0.5249062776565552,
648
+ "learning_rate": 8.989039001609e-05,
649
+ "loss": 1.0031,
650
+ "step": 900
651
+ },
652
+ {
653
+ "epoch": 1.1727360618756042,
654
+ "grad_norm": 0.5115840435028076,
655
+ "learning_rate": 8.765424398391047e-05,
656
+ "loss": 1.0149,
657
+ "step": 910
658
+ },
659
+ {
660
+ "epoch": 1.1856268127618435,
661
+ "grad_norm": 0.5123730897903442,
662
+ "learning_rate": 8.54243500856218e-05,
663
+ "loss": 0.9993,
664
+ "step": 920
665
+ },
666
+ {
667
+ "epoch": 1.1985175636480825,
668
+ "grad_norm": 0.5423418879508972,
669
+ "learning_rate": 8.320183758339284e-05,
670
+ "loss": 0.9911,
671
+ "step": 930
672
+ },
673
+ {
674
+ "epoch": 1.2114083145343217,
675
+ "grad_norm": 0.5046626925468445,
676
+ "learning_rate": 8.098783200130813e-05,
677
+ "loss": 0.9909,
678
+ "step": 940
679
+ },
680
+ {
681
+ "epoch": 1.2242990654205608,
682
+ "grad_norm": 0.5180662870407104,
683
+ "learning_rate": 7.878345455538043e-05,
684
+ "loss": 0.9852,
685
+ "step": 950
686
+ },
687
+ {
688
+ "epoch": 1.2371898163067998,
689
+ "grad_norm": 0.5029054880142212,
690
+ "learning_rate": 7.65898215857447e-05,
691
+ "loss": 0.984,
692
+ "step": 960
693
+ },
694
+ {
695
+ "epoch": 1.250080567193039,
696
+ "grad_norm": 0.5463522672653198,
697
+ "learning_rate": 7.440804399132173e-05,
698
+ "loss": 0.994,
699
+ "step": 970
700
+ },
701
+ {
702
+ "epoch": 1.262971318079278,
703
+ "grad_norm": 0.517109215259552,
704
+ "learning_rate": 7.223922666723678e-05,
705
+ "loss": 0.9825,
706
+ "step": 980
707
+ },
708
+ {
709
+ "epoch": 1.2758620689655173,
710
+ "grad_norm": 0.5118828415870667,
711
+ "learning_rate": 7.00844679452791e-05,
712
+ "loss": 0.9941,
713
+ "step": 990
714
+ },
715
+ {
716
+ "epoch": 1.2887528198517564,
717
+ "grad_norm": 0.5242361426353455,
718
+ "learning_rate": 6.794485903768513e-05,
719
+ "loss": 0.9787,
720
+ "step": 1000
721
+ },
722
+ {
723
+ "epoch": 1.3016435707379954,
724
+ "grad_norm": 0.5021597743034363,
725
+ "learning_rate": 6.5821483484527e-05,
726
+ "loss": 0.9871,
727
+ "step": 1010
728
+ },
729
+ {
730
+ "epoch": 1.3145343216242347,
731
+ "grad_norm": 0.5013926029205322,
732
+ "learning_rate": 6.371541660498652e-05,
733
+ "loss": 0.9859,
734
+ "step": 1020
735
+ },
736
+ {
737
+ "epoch": 1.3274250725104737,
738
+ "grad_norm": 0.5455625057220459,
739
+ "learning_rate": 6.162772495279265e-05,
740
+ "loss": 0.9731,
741
+ "step": 1030
742
+ },
743
+ {
744
+ "epoch": 1.340315823396713,
745
+ "grad_norm": 0.5966176986694336,
746
+ "learning_rate": 5.955946577609721e-05,
747
+ "loss": 1.0026,
748
+ "step": 1040
749
+ },
750
+ {
751
+ "epoch": 1.353206574282952,
752
+ "grad_norm": 0.5418857336044312,
753
+ "learning_rate": 5.75116864820641e-05,
754
+ "loss": 0.9798,
755
+ "step": 1050
756
+ },
757
+ {
758
+ "epoch": 1.366097325169191,
759
+ "grad_norm": 0.5456270575523376,
760
+ "learning_rate": 5.548542410644132e-05,
761
+ "loss": 0.9737,
762
+ "step": 1060
763
+ },
764
+ {
765
+ "epoch": 1.3789880760554303,
766
+ "grad_norm": 0.5252659916877747,
767
+ "learning_rate": 5.3481704788385786e-05,
768
+ "loss": 0.9775,
769
+ "step": 1070
770
+ },
771
+ {
772
+ "epoch": 1.3918788269416693,
773
+ "grad_norm": 0.5047706961631775,
774
+ "learning_rate": 5.150154325080636e-05,
775
+ "loss": 0.9755,
776
+ "step": 1080
777
+ },
778
+ {
779
+ "epoch": 1.4047695778279086,
780
+ "grad_norm": 0.5461093187332153,
781
+ "learning_rate": 4.954594228648807e-05,
782
+ "loss": 0.9716,
783
+ "step": 1090
784
+ },
785
+ {
786
+ "epoch": 1.4176603287141476,
787
+ "grad_norm": 0.5116148591041565,
788
+ "learning_rate": 4.761589225025811e-05,
789
+ "loss": 0.9821,
790
+ "step": 1100
791
+ },
792
+ {
793
+ "epoch": 1.4305510796003866,
794
+ "grad_norm": 0.5131816267967224,
795
+ "learning_rate": 4.571237055745074e-05,
796
+ "loss": 0.9857,
797
+ "step": 1110
798
+ },
799
+ {
800
+ "epoch": 1.4434418304866259,
801
+ "grad_norm": 0.5409175157546997,
802
+ "learning_rate": 4.383634118892472e-05,
803
+ "loss": 0.9768,
804
+ "step": 1120
805
+ },
806
+ {
807
+ "epoch": 1.456332581372865,
808
+ "grad_norm": 0.5277559757232666,
809
+ "learning_rate": 4.1988754202884775e-05,
810
+ "loss": 0.965,
811
+ "step": 1130
812
+ },
813
+ {
814
+ "epoch": 1.4692233322591042,
815
+ "grad_norm": 0.522885799407959,
816
+ "learning_rate": 4.0170545253752986e-05,
817
+ "loss": 0.9576,
818
+ "step": 1140
819
+ },
820
+ {
821
+ "epoch": 1.4821140831453432,
822
+ "grad_norm": 0.5148813128471375,
823
+ "learning_rate": 3.838263511833542e-05,
824
+ "loss": 0.9676,
825
+ "step": 1150
826
+ },
827
+ {
828
+ "epoch": 1.4950048340315822,
829
+ "grad_norm": 0.5167680978775024,
830
+ "learning_rate": 3.662592922952218e-05,
831
+ "loss": 0.9694,
832
+ "step": 1160
833
+ },
834
+ {
835
+ "epoch": 1.5078955849178215,
836
+ "grad_norm": 0.5245492458343506,
837
+ "learning_rate": 3.4901317217758764e-05,
838
+ "loss": 0.9603,
839
+ "step": 1170
840
+ },
841
+ {
842
+ "epoch": 1.5207863358040608,
843
+ "grad_norm": 0.51069176197052,
844
+ "learning_rate": 3.3209672460519425e-05,
845
+ "loss": 0.9687,
846
+ "step": 1180
847
+ },
848
+ {
849
+ "epoch": 1.5336770866902998,
850
+ "grad_norm": 0.5380834341049194,
851
+ "learning_rate": 3.155185164001176e-05,
852
+ "loss": 0.9653,
853
+ "step": 1190
854
+ },
855
+ {
856
+ "epoch": 1.5465678375765388,
857
+ "grad_norm": 0.5268071889877319,
858
+ "learning_rate": 2.9928694309335914e-05,
859
+ "loss": 0.9785,
860
+ "step": 1200
861
+ },
862
+ {
863
+ "epoch": 1.5594585884627779,
864
+ "grad_norm": 0.5809852480888367,
865
+ "learning_rate": 2.8341022467318335e-05,
866
+ "loss": 0.9628,
867
+ "step": 1210
868
+ },
869
+ {
870
+ "epoch": 1.572349339349017,
871
+ "grad_norm": 0.5032438635826111,
872
+ "learning_rate": 2.678964014223553e-05,
873
+ "loss": 0.9641,
874
+ "step": 1220
875
+ },
876
+ {
877
+ "epoch": 1.5852400902352564,
878
+ "grad_norm": 0.5497922897338867,
879
+ "learning_rate": 2.52753329846381e-05,
880
+ "loss": 0.969,
881
+ "step": 1230
882
+ },
883
+ {
884
+ "epoch": 1.5981308411214954,
885
+ "grad_norm": 0.5357956886291504,
886
+ "learning_rate": 2.3798867869482044e-05,
887
+ "loss": 0.9598,
888
+ "step": 1240
889
+ },
890
+ {
891
+ "epoch": 1.6110215920077344,
892
+ "grad_norm": 0.5199883580207825,
893
+ "learning_rate": 2.2360992507768052e-05,
894
+ "loss": 0.9733,
895
+ "step": 1250
896
+ },
897
+ {
898
+ "epoch": 1.6239123428939735,
899
+ "grad_norm": 0.5282153487205505,
900
+ "learning_rate": 2.096243506788602e-05,
901
+ "loss": 0.9565,
902
+ "step": 1260
903
+ },
904
+ {
905
+ "epoch": 1.6368030937802127,
906
+ "grad_norm": 0.5048473477363586,
907
+ "learning_rate": 1.9603903806856106e-05,
908
+ "loss": 0.9506,
909
+ "step": 1270
910
+ },
911
+ {
912
+ "epoch": 1.649693844666452,
913
+ "grad_norm": 0.5167466998100281,
914
+ "learning_rate": 1.8286086711653605e-05,
915
+ "loss": 0.9618,
916
+ "step": 1280
917
+ },
918
+ {
919
+ "epoch": 1.662584595552691,
920
+ "grad_norm": 0.5307776927947998,
921
+ "learning_rate": 1.7009651150798712e-05,
922
+ "loss": 0.9708,
923
+ "step": 1290
924
+ },
925
+ {
926
+ "epoch": 1.67547534643893,
927
+ "grad_norm": 0.5388936400413513,
928
+ "learning_rate": 1.577524353638791e-05,
929
+ "loss": 0.9672,
930
+ "step": 1300
931
+ },
932
+ {
933
+ "epoch": 1.688366097325169,
934
+ "grad_norm": 0.5254285931587219,
935
+ "learning_rate": 1.4583488996738293e-05,
936
+ "loss": 0.9615,
937
+ "step": 1310
938
+ },
939
+ {
940
+ "epoch": 1.7012568482114083,
941
+ "grad_norm": 0.5476789474487305,
942
+ "learning_rate": 1.3434991059810153e-05,
943
+ "loss": 0.9772,
944
+ "step": 1320
945
+ },
946
+ {
947
+ "epoch": 1.7141475990976476,
948
+ "grad_norm": 0.5789813995361328,
949
+ "learning_rate": 1.2330331347568636e-05,
950
+ "loss": 0.9613,
951
+ "step": 1330
952
+ },
953
+ {
954
+ "epoch": 1.7270383499838866,
955
+ "grad_norm": 0.5327284336090088,
956
+ "learning_rate": 1.1270069281438866e-05,
957
+ "loss": 0.96,
958
+ "step": 1340
959
+ },
960
+ {
961
+ "epoch": 1.7399291008701256,
962
+ "grad_norm": 0.5267541408538818,
963
+ "learning_rate": 1.0254741799003976e-05,
964
+ "loss": 0.9668,
965
+ "step": 1350
966
+ },
967
+ {
968
+ "epoch": 1.7528198517563647,
969
+ "grad_norm": 0.5468846559524536,
970
+ "learning_rate": 9.284863082089224e-06,
971
+ "loss": 0.9686,
972
+ "step": 1360
973
+ },
974
+ {
975
+ "epoch": 1.765710602642604,
976
+ "grad_norm": 0.6118249297142029,
977
+ "learning_rate": 8.360924296370376e-06,
978
+ "loss": 0.9679,
979
+ "step": 1370
980
+ },
981
+ {
982
+ "epoch": 1.7786013535288432,
983
+ "grad_norm": 0.535074770450592,
984
+ "learning_rate": 7.4833933426376345e-06,
985
+ "loss": 0.957,
986
+ "step": 1380
987
+ },
988
+ {
989
+ "epoch": 1.7914921044150822,
990
+ "grad_norm": 0.5529636144638062,
991
+ "learning_rate": 6.652714619841405e-06,
992
+ "loss": 0.9498,
993
+ "step": 1390
994
+ },
995
+ {
996
+ "epoch": 1.8043828553013213,
997
+ "grad_norm": 0.5263587236404419,
998
+ "learning_rate": 5.869308800040074e-06,
999
+ "loss": 0.9551,
1000
+ "step": 1400
1001
+ },
1002
+ {
1003
+ "epoch": 1.8172736061875603,
1004
+ "grad_norm": 0.5330998301506042,
1005
+ "learning_rate": 5.133572615363269e-06,
1006
+ "loss": 0.9545,
1007
+ "step": 1410
1008
+ },
1009
+ {
1010
+ "epoch": 1.8301643570737995,
1011
+ "grad_norm": 0.5292595624923706,
1012
+ "learning_rate": 4.445878657098978e-06,
1013
+ "loss": 0.958,
1014
+ "step": 1420
1015
+ },
1016
+ {
1017
+ "epoch": 1.8430551079600388,
1018
+ "grad_norm": 0.536263644695282,
1019
+ "learning_rate": 3.806575187005901e-06,
1020
+ "loss": 0.96,
1021
+ "step": 1430
1022
+ },
1023
+ {
1024
+ "epoch": 1.8559458588462778,
1025
+ "grad_norm": 0.5184710025787354,
1026
+ "learning_rate": 3.2159859609469436e-06,
1027
+ "loss": 0.9556,
1028
+ "step": 1440
1029
+ },
1030
+ {
1031
+ "epoch": 1.8688366097325169,
1032
+ "grad_norm": 0.5328414440155029,
1033
+ "learning_rate": 2.6744100649327974e-06,
1034
+ "loss": 0.9576,
1035
+ "step": 1450
1036
+ },
1037
+ {
1038
+ "epoch": 1.881727360618756,
1039
+ "grad_norm": 0.5515352487564087,
1040
+ "learning_rate": 2.1821217636589176e-06,
1041
+ "loss": 0.9769,
1042
+ "step": 1460
1043
+ },
1044
+ {
1045
+ "epoch": 1.8946181115049952,
1046
+ "grad_norm": 0.5316532850265503,
1047
+ "learning_rate": 1.7393703616124802e-06,
1048
+ "loss": 0.9587,
1049
+ "step": 1470
1050
+ },
1051
+ {
1052
+ "epoch": 1.9075088623912344,
1053
+ "grad_norm": 0.521430492401123,
1054
+ "learning_rate": 1.3463800768196866e-06,
1055
+ "loss": 0.9687,
1056
+ "step": 1480
1057
+ },
1058
+ {
1059
+ "epoch": 1.9203996132774734,
1060
+ "grad_norm": 0.5210091471672058,
1061
+ "learning_rate": 1.0033499272973701e-06,
1062
+ "loss": 0.9604,
1063
+ "step": 1490
1064
+ },
1065
+ {
1066
+ "epoch": 1.9332903641637125,
1067
+ "grad_norm": 0.530375063419342,
1068
+ "learning_rate": 7.104536302662834e-07,
1069
+ "loss": 0.9459,
1070
+ "step": 1500
1071
+ },
1072
+ {
1073
+ "epoch": 1.9461811150499515,
1074
+ "grad_norm": 0.5609223246574402,
1075
+ "learning_rate": 4.678395141773373e-07,
1076
+ "loss": 0.9529,
1077
+ "step": 1510
1078
+ },
1079
+ {
1080
+ "epoch": 1.9590718659361908,
1081
+ "grad_norm": 0.5311603546142578,
1082
+ "learning_rate": 2.756304435951429e-07,
1083
+ "loss": 0.9477,
1084
+ "step": 1520
1085
+ },
1086
+ {
1087
+ "epoch": 1.97196261682243,
1088
+ "grad_norm": 0.561936616897583,
1089
+ "learning_rate": 1.3392375697696136e-07,
1090
+ "loss": 0.9538,
1091
+ "step": 1530
1092
+ },
1093
+ {
1094
+ "epoch": 1.984853367708669,
1095
+ "grad_norm": 0.5377177000045776,
1096
+ "learning_rate": 4.279121737859049e-08,
1097
+ "loss": 0.9633,
1098
+ "step": 1540
1099
+ },
1100
+ {
1101
+ "epoch": 1.997744118594908,
1102
+ "grad_norm": 0.5239057540893555,
1103
+ "learning_rate": 2.2789761121688735e-09,
1104
+ "loss": 0.9598,
1105
+ "step": 1550
1106
+ },
1107
+ {
1108
+ "epoch": 2.0,
1109
+ "eval_accuracy": 0.6875442401796923,
1110
+ "eval_first_token_accuracy": 0.8729967948717948,
1111
+ "eval_loss": 1.0595165491104126,
1112
+ "eval_runtime": 684.7375,
1113
+ "eval_samples_per_second": 7.282,
1114
+ "eval_steps_per_second": 0.456,
1115
+ "step": 1552
1116
+ }
1117
+ ],
1118
+ "logging_steps": 10,
1119
+ "max_steps": 1552,
1120
+ "num_input_tokens_seen": 0,
1121
+ "num_train_epochs": 2,
1122
+ "save_steps": 200,
1123
+ "stateful_callbacks": {
1124
+ "TrainerControl": {
1125
+ "args": {
1126
+ "should_epoch_stop": false,
1127
+ "should_evaluate": false,
1128
+ "should_log": false,
1129
+ "should_save": true,
1130
+ "should_training_stop": true
1131
+ },
1132
+ "attributes": {}
1133
+ }
1134
+ },
1135
+ "total_flos": 1.0014393801042297e+19,
1136
+ "train_batch_size": 8,
1137
+ "trial_name": null,
1138
+ "trial_params": null
1139
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70993e231590dcbc252cb908216528196daf0c32dfd784af8384eac683c27e34
3
+ size 6417
video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": false,
12
+ "fps": null,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "max_pixels": 12845056,
26
+ "merge_size": 2,
27
+ "min_frames": 4,
28
+ "min_pixels": 3136,
29
+ "num_frames": null,
30
+ "pad_size": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2_5_VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "return_metadata": false,
36
+ "size": {
37
+ "longest_edge": 12845056,
38
+ "shortest_edge": 3136
39
+ },
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff