Hugging Face's logo

KiViDrag
/
ViT_breastmnist_std_0

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
KiViDrag commited on
Commit
2e984b5
•
1 Parent(s): 810c6b9

End of training

Browse files
Files changed (7) hide show
  1. README.md +118 -0
  2. config.json +32 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +22 -0
  5. runs/Nov09_15-42-31_3e2ecbcb3930/events.out.tfevents.1731166953.3e2ecbcb3930.30.0 +3 -0
  6. runs/Nov09_15-42-31_3e2ecbcb3930/events.out.tfevents.1731168081.3e2ecbcb3930.30.1 +3 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/vit-base-patch16-224
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - medmnist-v2
9
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ model-index:
13
+ - name: ViT_breastmnist_std_0
14
+ results:
15
+ - task:
16
+ name: Image Classification
17
+ type: image-classification
18
+ dataset:
19
+ name: medmnist-v2
20
+ type: medmnist-v2
21
+ config: breastmnist
22
+ split: validation
23
+ args: breastmnist
24
+ metrics:
25
+ - name: Accuracy
26
+ type: accuracy
27
+ value: 0.8717948717948718
28
+ - name: F1
29
+ type: f1
30
+ value: 0.8370927318295739
31
+ ---
32
+
33
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
34
+ should probably proofread and complete it, then remove this comment. -->
35
+
36
+ # ViT_breastmnist_std_0
37
+
38
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the medmnist-v2 dataset.
39
+ It achieves the following results on the evaluation set:
40
+ - Loss: 0.3272
41
+ - Accuracy: 0.8718
42
+ - F1: 0.8371
43
+
44
+ ## Model description
45
+
46
+ More information needed
47
+
48
+ ## Intended uses & limitations
49
+
50
+ More information needed
51
+
52
+ ## Training and evaluation data
53
+
54
+ More information needed
55
+
56
+ ## Training procedure
57
+
58
+ ### Training hyperparameters
59
+
60
+ The following hyperparameters were used during training:
61
+ - learning_rate: 2e-05
62
+ - train_batch_size: 64
63
+ - eval_batch_size: 16
64
+ - seed: 42
65
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
+ - lr_scheduler_type: linear
67
+ - num_epochs: 10
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
72
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
73
+ | 0.3533 | 0.2597 | 20 | 0.3035 | 0.8846 | 0.8406 |
74
+ | 0.1354 | 0.5195 | 40 | 0.2280 | 0.8974 | 0.8655 |
75
+ | 0.0247 | 0.7792 | 60 | 0.2669 | 0.9231 | 0.8956 |
76
+ | 0.0089 | 1.0390 | 80 | 0.2742 | 0.9231 | 0.8956 |
77
+ | 0.003 | 1.2987 | 100 | 0.3404 | 0.9103 | 0.8803 |
78
+ | 0.0018 | 1.5584 | 120 | 0.3583 | 0.9231 | 0.8956 |
79
+ | 0.0013 | 1.8182 | 140 | 0.3720 | 0.9231 | 0.8956 |
80
+ | 0.0009 | 2.0779 | 160 | 0.3892 | 0.9231 | 0.8956 |
81
+ | 0.0007 | 2.3377 | 180 | 0.3933 | 0.9231 | 0.8956 |
82
+ | 0.0006 | 2.5974 | 200 | 0.3948 | 0.9231 | 0.8956 |
83
+ | 0.0005 | 2.8571 | 220 | 0.4038 | 0.9231 | 0.8956 |
84
+ | 0.0005 | 3.1169 | 240 | 0.4145 | 0.9231 | 0.8956 |
85
+ | 0.0004 | 3.3766 | 260 | 0.4176 | 0.9231 | 0.8956 |
86
+ | 0.0004 | 3.6364 | 280 | 0.4230 | 0.9231 | 0.8956 |
87
+ | 0.0003 | 3.8961 | 300 | 0.4274 | 0.9103 | 0.8803 |
88
+ | 0.0003 | 4.1558 | 320 | 0.4344 | 0.9231 | 0.8956 |
89
+ | 0.0003 | 4.4156 | 340 | 0.4380 | 0.9231 | 0.8956 |
90
+ | 0.0003 | 4.6753 | 360 | 0.4406 | 0.9103 | 0.8803 |
91
+ | 0.0003 | 4.9351 | 380 | 0.4459 | 0.9231 | 0.8956 |
92
+ | 0.0002 | 5.1948 | 400 | 0.4472 | 0.9103 | 0.8803 |
93
+ | 0.0002 | 5.4545 | 420 | 0.4514 | 0.9103 | 0.8803 |
94
+ | 0.0002 | 5.7143 | 440 | 0.4550 | 0.9231 | 0.8956 |
95
+ | 0.0002 | 5.9740 | 460 | 0.4579 | 0.9231 | 0.8956 |
96
+ | 0.0002 | 6.2338 | 480 | 0.4600 | 0.9231 | 0.8956 |
97
+ | 0.0002 | 6.4935 | 500 | 0.4614 | 0.9103 | 0.8803 |
98
+ | 0.0002 | 6.7532 | 520 | 0.4637 | 0.9231 | 0.8956 |
99
+ | 0.0002 | 7.0130 | 540 | 0.4660 | 0.9231 | 0.8956 |
100
+ | 0.0002 | 7.2727 | 560 | 0.4684 | 0.9231 | 0.8956 |
101
+ | 0.0002 | 7.5325 | 580 | 0.4695 | 0.9231 | 0.8956 |
102
+ | 0.0002 | 7.7922 | 600 | 0.4710 | 0.9103 | 0.8803 |
103
+ | 0.0001 | 8.0519 | 620 | 0.4719 | 0.9103 | 0.8803 |
104
+ | 0.0001 | 8.3117 | 640 | 0.4726 | 0.9103 | 0.8803 |
105
+ | 0.0001 | 8.5714 | 660 | 0.4742 | 0.9103 | 0.8803 |
106
+ | 0.0001 | 8.8312 | 680 | 0.4754 | 0.9231 | 0.8956 |
107
+ | 0.0002 | 9.0909 | 700 | 0.4757 | 0.9231 | 0.8956 |
108
+ | 0.0001 | 9.3506 | 720 | 0.4759 | 0.9231 | 0.8956 |
109
+ | 0.0001 | 9.6104 | 740 | 0.4763 | 0.9231 | 0.8956 |
110
+ | 0.0001 | 9.8701 | 760 | 0.4765 | 0.9231 | 0.8956 |
111
+
112
+
113
+ ### Framework versions
114
+
115
+ - Transformers 4.45.1
116
+ - Pytorch 2.4.0
117
+ - Datasets 3.0.1
118
+ - Tokenizers 0.20.0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "malignant",
13
+ "1": "normal, benign"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "malignant": "0",
20
+ "normal, benign": "1"
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
+ "qkv_bias": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.45.1"
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05922884a6a61222f533736b16ee3d30298e551e1a9e828f1c3fbef90d0cb5b
3
+ size 343223968
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
runs/Nov09_15-42-31_3e2ecbcb3930/events.out.tfevents.1731166953.3e2ecbcb3930.30.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd4dc9f4eea3a012abf60409b3fd61c706135aa481361903fb8695d43aa58ea
3
+ size 35510
runs/Nov09_15-42-31_3e2ecbcb3930/events.out.tfevents.1731168081.3e2ecbcb3930.30.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15b6f842db7e82c7af41114bc74ae183a5a4015e09a65d22ad78e18531bcbc8d
3
+ size 457
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aea87bfd036207745fb8f3982565828a180c608e197368da5b5c47a8ed161aa
3
+ size 5240