Hugging Face's logo

ben81828
/
qwenvl-2B-cadica-stenosis-detect-scale4

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
ben81828 commited on
Commit
d9b710e
·
verified ·
1 Parent(s): 847c72c

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-detect-scale4
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-detect-scale4
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 the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4702
21
+ - Num Input Tokens Seen: 35706848
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
+ | 1.3506 | 0.0129 | 50 | 1.1727 | 524648 |
59
+ | 0.7577 | 0.0258 | 100 | 0.7517 | 1049816 |
60
+ | 0.7018 | 0.0386 | 150 | 0.7310 | 1573376 |
61
+ | 0.7594 | 0.0515 | 200 | 0.7274 | 2099008 |
62
+ | 0.7346 | 0.0644 | 250 | 0.7182 | 2625352 |
63
+ | 0.6815 | 0.0773 | 300 | 0.7074 | 3149032 |
64
+ | 0.6932 | 0.0901 | 350 | 0.7045 | 3673152 |
65
+ | 0.7089 | 0.1030 | 400 | 0.6848 | 4197072 |
66
+ | 0.6732 | 0.1159 | 450 | 0.6526 | 4722528 |
67
+ | 0.6304 | 0.1288 | 500 | 0.6272 | 5246640 |
68
+ | 0.5596 | 0.1416 | 550 | 0.5833 | 5774880 |
69
+ | 0.5794 | 0.1545 | 600 | 0.6039 | 6299656 |
70
+ | 0.5959 | 0.1674 | 650 | 0.5542 | 6824008 |
71
+ | 0.5014 | 0.1803 | 700 | 0.5440 | 7347040 |
72
+ | 0.541 | 0.1931 | 750 | 0.5274 | 7870520 |
73
+ | 0.5291 | 0.2060 | 800 | 0.5219 | 8393696 |
74
+ | 0.5063 | 0.2189 | 850 | 0.5526 | 8919608 |
75
+ | 0.5251 | 0.2318 | 900 | 0.4960 | 9443616 |
76
+ | 0.5862 | 0.2447 | 950 | 0.5085 | 9970600 |
77
+ | 0.483 | 0.2575 | 1000 | 0.5305 | 10495592 |
78
+ | 0.4628 | 0.2704 | 1050 | 0.5040 | 11021656 |
79
+ | 0.4825 | 0.2833 | 1100 | 0.4799 | 11547008 |
80
+ | 0.4553 | 0.2962 | 1150 | 0.4538 | 12071088 |
81
+ | 0.454 | 0.3090 | 1200 | 0.4925 | 12596208 |
82
+ | 0.4725 | 0.3219 | 1250 | 0.4340 | 13125624 |
83
+ | 0.4794 | 0.3348 | 1300 | 0.4992 | 13650264 |
84
+ | 0.3994 | 0.3477 | 1350 | 0.4608 | 14173240 |
85
+ | 0.437 | 0.3605 | 1400 | 0.4662 | 14697136 |
86
+ | 0.4065 | 0.3734 | 1450 | 0.4395 | 15222568 |
87
+ | 0.4338 | 0.3863 | 1500 | 0.4548 | 15744848 |
88
+ | 0.3872 | 0.3992 | 1550 | 0.4417 | 16269896 |
89
+ | 0.3914 | 0.4121 | 1600 | 0.4658 | 16798768 |
90
+ | 0.3755 | 0.4249 | 1650 | 0.4727 | 17323232 |
91
+ | 0.3796 | 0.4378 | 1700 | 0.4555 | 17845600 |
92
+ | 0.3767 | 0.4507 | 1750 | 0.4234 | 18371928 |
93
+ | 0.4484 | 0.4636 | 1800 | 0.4194 | 18898888 |
94
+ | 0.3941 | 0.4764 | 1850 | 0.4510 | 19424688 |
95
+ | 0.2877 | 0.4893 | 1900 | 0.4512 | 19950480 |
96
+ | 0.365 | 0.5022 | 1950 | 0.4764 | 20476176 |
97
+ | 0.3814 | 0.5151 | 2000 | 0.5098 | 21002032 |
98
+ | 0.3389 | 0.5279 | 2050 | 0.4328 | 21527496 |
99
+ | 0.3983 | 0.5408 | 2100 | 0.4818 | 22050376 |
100
+ | 0.3687 | 0.5537 | 2150 | 0.4505 | 22574104 |
101
+ | 0.3232 | 0.5666 | 2200 | 0.4517 | 23101488 |
102
+ | 0.325 | 0.5794 | 2250 | 0.4991 | 23626952 |
103
+ | 0.3322 | 0.5923 | 2300 | 0.4960 | 24154624 |
104
+ | 0.3651 | 0.6052 | 2350 | 0.4146 | 24678768 |
105
+ | 0.3445 | 0.6181 | 2400 | 0.4281 | 25206168 |
106
+ | 0.3413 | 0.6310 | 2450 | 0.4691 | 25730432 |
107
+ | 0.363 | 0.6438 | 2500 | 0.4471 | 26252584 |
108
+ | 0.3195 | 0.6567 | 2550 | 0.4373 | 26776816 |
109
+ | 0.3075 | 0.6696 | 2600 | 0.4505 | 27301776 |
110
+ | 0.324 | 0.6825 | 2650 | 0.5080 | 27827480 |
111
+ | 0.3076 | 0.6953 | 2700 | 0.4338 | 28352368 |
112
+ | 0.2817 | 0.7082 | 2750 | 0.4440 | 28877960 |
113
+ | 0.3567 | 0.7211 | 2800 | 0.4282 | 29402040 |
114
+ | 0.3024 | 0.7340 | 2850 | 0.4704 | 29928032 |
115
+ | 0.3167 | 0.7468 | 2900 | 0.4632 | 30455480 |
116
+ | 0.2899 | 0.7597 | 2950 | 0.4720 | 30979312 |
117
+ | 0.3522 | 0.7726 | 3000 | 0.4726 | 31503344 |
118
+ | 0.3137 | 0.7855 | 3050 | 0.4747 | 32030016 |
119
+ | 0.2856 | 0.7984 | 3100 | 0.4740 | 32553288 |
120
+ | 0.2669 | 0.8112 | 3150 | 0.4687 | 33078960 |
121
+ | 0.3322 | 0.8241 | 3200 | 0.4703 | 33604328 |
122
+ | 0.2836 | 0.8370 | 3250 | 0.4657 | 34129832 |
123
+ | 0.3135 | 0.8499 | 3300 | 0.4714 | 34654480 |
124
+ | 0.3253 | 0.8627 | 3350 | 0.4715 | 35179104 |
125
+ | 0.3187 | 0.8756 | 3400 | 0.4702 | 35706848 |
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:d712f05560ef9d87500810ebe4e96f57f0c9005ed8838b0dd018fe564e447831
3
  size 29034840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8464937776286fdba4fee3aa59e0e0cefe29cc3b83812b6842ff0a56228048f2
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
+ }