metadata

library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - medmnist-v2
metrics:
  - accuracy
  - f1
model-index:
  - name: ViT_breastmnist_std_60
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: medmnist-v2
          type: medmnist-v2
          config: breastmnist
          split: validation
          args: breastmnist
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7756410256410257
          - name: F1
            type: f1
            value: 0.6137247966041741

ViT_breastmnist_std_60

This model is a fine-tuned version of google/vit-base-patch16-224 on the medmnist-v2 dataset. It achieves the following results on the evaluation set:

Loss: 0.5157
Accuracy: 0.7756
F1: 0.6137

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5179	0.2597	20	0.5240	0.7436	0.5385
0.4306	0.5195	40	0.4807	0.7949	0.6855
0.4258	0.7792	60	0.4812	0.7949	0.6518
0.4613	1.0390	80	0.4491	0.8333	0.7247
0.4194	1.2987	100	0.4573	0.8333	0.7247
0.3693	1.5584	120	0.4665	0.8205	0.6953
0.3825	1.8182	140	0.4695	0.7821	0.6733
0.387	2.0779	160	0.4410	0.8205	0.7248
0.3341	2.3377	180	0.4422	0.8205	0.7367
0.3192	2.5974	200	0.4457	0.8205	0.7111
0.3062	2.8571	220	0.4575	0.8205	0.7111
0.2485	3.1169	240	0.4526	0.8333	0.7383
0.2415	3.3766	260	0.4430	0.8462	0.7641
0.2377	3.6364	280	0.4529	0.8333	0.7247
0.2417	3.8961	300	0.4386	0.8205	0.7111
0.1783	4.1558	320	0.4467	0.8333	0.7383
0.193	4.4156	340	0.4724	0.8077	0.6823
0.1736	4.6753	360	0.4757	0.8333	0.7383
0.1656	4.9351	380	0.4677	0.8333	0.7383
0.1214	5.1948	400	0.4747	0.8077	0.6981
0.0851	5.4545	420	0.4782	0.7949	0.6698
0.0893	5.7143	440	0.4842	0.8077	0.6823
0.0978	5.9740	460	0.4883	0.8077	0.6823
0.0518	6.2338	480	0.4861	0.8077	0.6981
0.0662	6.4935	500	0.5017	0.8077	0.6981
0.058	6.7532	520	0.5092	0.7949	0.6518
0.0511	7.0130	540	0.5003	0.8205	0.7111
0.0235	7.2727	560	0.5041	0.8077	0.6823
0.0204	7.5325	580	0.5140	0.8205	0.7111
0.0196	7.7922	600	0.5122	0.8205	0.7111
0.0108	8.0519	620	0.5186	0.8205	0.7111
0.012	8.3117	640	0.5315	0.8333	0.7247
0.0077	8.5714	660	0.5319	0.8205	0.7111
0.0187	8.8312	680	0.5279	0.8205	0.7111
0.0063	9.0909	700	0.5304	0.8205	0.7111
0.004	9.3506	720	0.5312	0.8205	0.7111
0.0044	9.6104	740	0.5310	0.8205	0.7111
0.0076	9.8701	760	0.5323	0.8205	0.7111

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0