Hugging Face's logo

ben81828
/
qwenvl-2B-cadica-stenosis-classify-scale4-frozenVision

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
ben81828 commited on
Commit
e224c94
•
1 Parent(s): 453f891

Model save

Browse files
Files changed (4) hide show
  1. README.md +134 -0
  2. adapter_model.safetensors +1 -1
  3. chat_template.json +3 -0
  4. preprocessor_config.json +29 -0
README.md ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: AdaptLLM/biomed-Qwen2-VL-2B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: qwenvl-2B-cadica-stenosis-classify-scale4-frozenVision
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-stenosis-classify-scale4-frozenVision
17
+
18
+ This model is a fine-tuned version of [AdaptLLM/biomed-Qwen2-VL-2B-Instruct](https://huggingface.co/AdaptLLM/biomed-Qwen2-VL-2B-Instruct) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.8603
21
+ - Num Input Tokens Seen: 39760664
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
+ | 0.9157 | 0.0258 | 50 | 0.9192 | 584856 |
59
+ | 0.901 | 0.0515 | 100 | 0.9078 | 1169664 |
60
+ | 0.9032 | 0.0773 | 150 | 0.8962 | 1754512 |
61
+ | 0.9053 | 0.1030 | 200 | 0.8982 | 2339304 |
62
+ | 0.9098 | 0.1288 | 250 | 0.8956 | 2924016 |
63
+ | 0.8893 | 0.1545 | 300 | 0.8909 | 3508888 |
64
+ | 0.9075 | 0.1803 | 350 | 0.8920 | 4093688 |
65
+ | 0.9004 | 0.2060 | 400 | 0.9086 | 4678384 |
66
+ | 0.9076 | 0.2318 | 450 | 0.8962 | 5263304 |
67
+ | 0.8962 | 0.2575 | 500 | 0.8988 | 5848048 |
68
+ | 0.9013 | 0.2833 | 550 | 0.9001 | 6432936 |
69
+ | 0.9046 | 0.3090 | 600 | 0.9053 | 7017576 |
70
+ | 0.904 | 0.3348 | 650 | 0.9033 | 7602512 |
71
+ | 0.8972 | 0.3605 | 700 | 0.9029 | 8187320 |
72
+ | 0.9005 | 0.3863 | 750 | 0.8982 | 8772104 |
73
+ | 0.8881 | 0.4121 | 800 | 0.8973 | 9357016 |
74
+ | 0.9035 | 0.4378 | 850 | 0.8779 | 9941896 |
75
+ | 0.8961 | 0.4636 | 900 | 0.8914 | 10526712 |
76
+ | 0.8852 | 0.4893 | 950 | 0.8916 | 11111520 |
77
+ | 0.8635 | 0.5151 | 1000 | 0.8602 | 11696200 |
78
+ | 0.8844 | 0.5408 | 1050 | 0.8446 | 12281072 |
79
+ | 0.8427 | 0.5666 | 1100 | 0.7743 | 12865992 |
80
+ | 0.8185 | 0.5923 | 1150 | 0.7827 | 13450720 |
81
+ | 0.8061 | 0.6181 | 1200 | 0.7594 | 14035544 |
82
+ | 0.7917 | 0.6438 | 1250 | 0.7407 | 14620336 |
83
+ | 0.7724 | 0.6696 | 1300 | 0.7190 | 15205064 |
84
+ | 0.7278 | 0.6953 | 1350 | 0.7129 | 15789848 |
85
+ | 0.7359 | 0.7211 | 1400 | 0.6644 | 16374784 |
86
+ | 0.6291 | 0.7468 | 1450 | 0.7531 | 16959632 |
87
+ | 0.6021 | 0.7726 | 1500 | 0.6329 | 17544440 |
88
+ | 0.667 | 0.7984 | 1550 | 0.6618 | 18129304 |
89
+ | 0.6564 | 0.8241 | 1600 | 0.6319 | 18714072 |
90
+ | 0.5668 | 0.8499 | 1650 | 0.6635 | 19298848 |
91
+ | 0.5701 | 0.8756 | 1700 | 0.7144 | 19883504 |
92
+ | 0.546 | 0.9014 | 1750 | 0.6723 | 20468200 |
93
+ | 0.412 | 0.9271 | 1800 | 0.6769 | 21053080 |
94
+ | 0.4347 | 0.9529 | 1850 | 0.6808 | 21637848 |
95
+ | 0.3737 | 0.9786 | 1900 | 0.7730 | 22222632 |
96
+ | 0.3783 | 1.0041 | 1950 | 0.6983 | 22801512 |
97
+ | 0.3328 | 1.0299 | 2000 | 0.7485 | 23386232 |
98
+ | 0.3602 | 1.0556 | 2050 | 0.7191 | 23971048 |
99
+ | 0.3351 | 1.0814 | 2100 | 0.8075 | 24555904 |
100
+ | 0.3699 | 1.1071 | 2150 | 0.8524 | 25140752 |
101
+ | 0.4016 | 1.1329 | 2200 | 0.7535 | 25725560 |
102
+ | 0.3442 | 1.1586 | 2250 | 0.7066 | 26310336 |
103
+ | 0.3877 | 1.1844 | 2300 | 0.7277 | 26895096 |
104
+ | 0.3871 | 1.2101 | 2350 | 0.7660 | 27479840 |
105
+ | 0.3486 | 1.2359 | 2400 | 0.7411 | 28064552 |
106
+ | 0.2966 | 1.2617 | 2450 | 0.7486 | 28649256 |
107
+ | 0.3221 | 1.2874 | 2500 | 0.7222 | 29233968 |
108
+ | 0.3231 | 1.3132 | 2550 | 0.7146 | 29818856 |
109
+ | 0.2779 | 1.3389 | 2600 | 0.6957 | 30403640 |
110
+ | 0.2962 | 1.3647 | 2650 | 0.7657 | 30988344 |
111
+ | 0.3163 | 1.3904 | 2700 | 0.7473 | 31573240 |
112
+ | 0.164 | 1.4162 | 2750 | 0.7807 | 32158144 |
113
+ | 0.2939 | 1.4419 | 2800 | 0.7913 | 32743032 |
114
+ | 0.2848 | 1.4677 | 2850 | 0.8045 | 33327720 |
115
+ | 0.29 | 1.4934 | 2900 | 0.8113 | 33912440 |
116
+ | 0.2494 | 1.5192 | 2950 | 0.8177 | 34497216 |
117
+ | 0.2259 | 1.5449 | 3000 | 0.8406 | 35082056 |
118
+ | 0.2851 | 1.5707 | 3050 | 0.8474 | 35666976 |
119
+ | 0.2351 | 1.5964 | 3100 | 0.8651 | 36251744 |
120
+ | 0.2638 | 1.6222 | 3150 | 0.8634 | 36836560 |
121
+ | 0.312 | 1.6480 | 3200 | 0.8680 | 37421416 |
122
+ | 0.2785 | 1.6737 | 3250 | 0.8640 | 38006200 |
123
+ | 0.2752 | 1.6995 | 3300 | 0.8644 | 38591128 |
124
+ | 0.2674 | 1.7252 | 3350 | 0.8666 | 39175888 |
125
+ | 0.1797 | 1.7510 | 3400 | 0.8603 | 39760664 |
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 sha256:2e3dd7488301b3ff8268dcffb6f575eefe718b69eb21c58090d96141890a4fd7
3
  size 18516456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f11513d52bcbabbebdae5c22382754c386d07651a25539e1cdcc0f4b4982a0f7
3
  size 18516456
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
+ }