ben81828 commited on
Commit
5c84b34
·
verified ·
1 Parent(s): 04a2795

Model save

Browse files
README.md ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: ben81828/CADICA_qwenvl_direction
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: qwenvl-2B-cadica-direction-then-detect-and-classify-scale6
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # qwenvl-2B-cadica-direction-then-detect-and-classify-scale6
17
+
18
+ This model is a fine-tuned version of [ben81828/CADICA_qwenvl_direction](https://huggingface.co/ben81828/CADICA_qwenvl_direction) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4078
21
+ - Num Input Tokens Seen: 35305984
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 6
47
+ - total_train_batch_size: 24
48
+ - total_eval_batch_size: 4
49
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.05
52
+ - training_steps: 3400
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
57
+ |:-------------:|:------:|:----:|:---------------:|:-----------------:|
58
+ | 1.3918 | 0.0148 | 50 | 1.0422 | 516240 |
59
+ | 0.8208 | 0.0295 | 100 | 0.8917 | 1030696 |
60
+ | 0.8125 | 0.0443 | 150 | 0.9009 | 1550792 |
61
+ | 0.7675 | 0.0591 | 200 | 0.9007 | 2071176 |
62
+ | 0.7558 | 0.0739 | 250 | 0.8108 | 2587272 |
63
+ | 0.78 | 0.0886 | 300 | 0.8194 | 3107200 |
64
+ | 0.6602 | 0.1034 | 350 | 0.7663 | 3625752 |
65
+ | 0.6739 | 0.1182 | 400 | 0.7039 | 4142592 |
66
+ | 0.5661 | 0.1329 | 450 | 0.7133 | 4663320 |
67
+ | 0.6283 | 0.1477 | 500 | 0.6505 | 5183664 |
68
+ | 0.5957 | 0.1625 | 550 | 0.6883 | 5703016 |
69
+ | 0.6331 | 0.1773 | 600 | 0.5883 | 6222736 |
70
+ | 0.5483 | 0.1920 | 650 | 0.6101 | 6743120 |
71
+ | 0.477 | 0.2068 | 700 | 0.5884 | 7262832 |
72
+ | 0.514 | 0.2216 | 750 | 0.4666 | 7779872 |
73
+ | 0.4239 | 0.2363 | 800 | 0.4822 | 8301976 |
74
+ | 0.4949 | 0.2511 | 850 | 0.6122 | 8822832 |
75
+ | 0.4852 | 0.2659 | 900 | 0.5606 | 9345160 |
76
+ | 0.4737 | 0.2806 | 950 | 0.4791 | 9863168 |
77
+ | 0.4005 | 0.2954 | 1000 | 0.5501 | 10379136 |
78
+ | 0.3991 | 0.3102 | 1050 | 0.4378 | 10897528 |
79
+ | 0.4624 | 0.3250 | 1100 | 0.5301 | 11413120 |
80
+ | 0.4432 | 0.3397 | 1150 | 0.4249 | 11933632 |
81
+ | 0.3296 | 0.3545 | 1200 | 0.2966 | 12456040 |
82
+ | 0.335 | 0.3693 | 1250 | 0.3185 | 12972696 |
83
+ | 0.3594 | 0.3840 | 1300 | 0.4716 | 13493264 |
84
+ | 0.3731 | 0.3988 | 1350 | 0.5566 | 14014736 |
85
+ | 0.388 | 0.4136 | 1400 | 0.3866 | 14532288 |
86
+ | 0.3131 | 0.4284 | 1450 | 0.4740 | 15050992 |
87
+ | 0.2928 | 0.4431 | 1500 | 0.4049 | 15572048 |
88
+ | 0.3588 | 0.4579 | 1550 | 0.2871 | 16091960 |
89
+ | 0.3879 | 0.4727 | 1600 | 0.3136 | 16609960 |
90
+ | 0.2698 | 0.4874 | 1650 | 0.4020 | 17130896 |
91
+ | 0.3904 | 0.5022 | 1700 | 0.3297 | 17650984 |
92
+ | 0.3173 | 0.5170 | 1750 | 0.4491 | 18169344 |
93
+ | 0.3127 | 0.5318 | 1800 | 0.3499 | 18691928 |
94
+ | 0.2828 | 0.5465 | 1850 | 0.3781 | 19212992 |
95
+ | 0.306 | 0.5613 | 1900 | 0.3766 | 19735976 |
96
+ | 0.2992 | 0.5761 | 1950 | 0.3468 | 20253288 |
97
+ | 0.2341 | 0.5908 | 2000 | 0.3366 | 20770728 |
98
+ | 0.2931 | 0.6056 | 2050 | 0.3386 | 21291664 |
99
+ | 0.1826 | 0.6204 | 2100 | 0.5386 | 21813984 |
100
+ | 0.2387 | 0.6352 | 2150 | 0.2581 | 22332144 |
101
+ | 0.2662 | 0.6499 | 2200 | 0.4840 | 22849552 |
102
+ | 0.2332 | 0.6647 | 2250 | 0.4966 | 23366784 |
103
+ | 0.2481 | 0.6795 | 2300 | 0.2418 | 23883032 |
104
+ | 0.2313 | 0.6942 | 2350 | 0.1870 | 24401256 |
105
+ | 0.262 | 0.7090 | 2400 | 0.3471 | 24921872 |
106
+ | 0.2412 | 0.7238 | 2450 | 0.3456 | 25439896 |
107
+ | 0.2382 | 0.7386 | 2500 | 0.2543 | 25961056 |
108
+ | 0.2364 | 0.7533 | 2550 | 0.3871 | 26477208 |
109
+ | 0.2082 | 0.7681 | 2600 | 0.3406 | 26997904 |
110
+ | 0.1736 | 0.7829 | 2650 | 0.2697 | 27521088 |
111
+ | 0.2225 | 0.7976 | 2700 | 0.4155 | 28042992 |
112
+ | 0.2501 | 0.8124 | 2750 | 0.4115 | 28561248 |
113
+ | 0.2507 | 0.8272 | 2800 | 0.3223 | 29079576 |
114
+ | 0.1928 | 0.8419 | 2850 | 0.2828 | 29600536 |
115
+ | 0.2029 | 0.8567 | 2900 | 0.3943 | 30118072 |
116
+ | 0.1692 | 0.8715 | 2950 | 0.2034 | 30637448 |
117
+ | 0.234 | 0.8863 | 3000 | 0.2556 | 31159736 |
118
+ | 0.2303 | 0.9010 | 3050 | 0.2253 | 31679080 |
119
+ | 0.1999 | 0.9158 | 3100 | 0.2710 | 32196176 |
120
+ | 0.2069 | 0.9306 | 3150 | 0.2029 | 32713824 |
121
+ | 0.2135 | 0.9453 | 3200 | 0.3564 | 33235872 |
122
+ | 0.1964 | 0.9601 | 3250 | 0.3081 | 33752488 |
123
+ | 0.2131 | 0.9749 | 3300 | 0.3541 | 34269496 |
124
+ | 0.1779 | 0.9897 | 3350 | 0.2255 | 34784784 |
125
+ | 0.2173 | 1.0044 | 3400 | 0.4078 | 35305984 |
126
+
127
+
128
+ ### Framework versions
129
+
130
+ - PEFT 0.12.0
131
+ - Transformers 4.47.0.dev0
132
+ - Pytorch 2.5.1+cu121
133
+ - Datasets 3.1.0
134
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:302b9ce048dad99dc59725f9bc543136929b03fd0548bef61608ff98a26b885e
3
  size 29034840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e895c1cddd40eb0dbe387456240309b06d66fe014fd793905368c3b37bbbff4a
3
  size 29034840
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
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": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 12845056,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }