metadata

license: apache-2.0
tags:
  - generated_from_trainer
base_model: google/vit-base-patch16-224
metrics:
  - accuracy
model-index:
  - name: model
    results: []

model

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

Loss: 0.5652
Accuracy: 0.7486
Roc Auc: 0.7023

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: 5e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Roc Auc
0.5665	0.14	50	0.5829	0.71	0.6554
0.5428	0.29	100	0.6787	0.71	0.6873
0.5793	0.43	150	0.5501	0.7429	0.6910
0.567	0.57	200	0.5489	0.7443	0.6951
0.5427	0.71	250	0.5758	0.73	0.6809
0.5022	0.86	300	0.5784	0.7229	0.6489
0.5415	1.0	350	0.5530	0.7429	0.6791
0.5731	1.14	400	0.5440	0.7457	0.6955
0.4746	1.29	450	0.5632	0.7486	0.6916
0.6076	1.43	500	0.5356	0.7571	0.7089
0.4674	1.57	550	0.5477	0.7471	0.7247
0.546	1.71	600	0.5774	0.7457	0.7038
0.5776	1.86	650	0.5367	0.7443	0.7139
0.4802	2.0	700	0.5418	0.7429	0.7038
0.5612	2.14	750	0.6319	0.6714	0.6911
0.4281	2.29	800	0.5550	0.7443	0.6951
0.518	2.43	850	0.6038	0.7014	0.6743
0.505	2.57	900	0.5480	0.7486	0.7036
0.4689	2.71	950	0.5304	0.7571	0.7191
0.5685	2.86	1000	0.5453	0.7557	0.7009
0.4624	3.0	1050	0.6102	0.7386	0.7176
0.5246	3.14	1100	0.5674	0.7243	0.6932
0.4601	3.29	1150	0.5538	0.74	0.7035
0.4663	3.43	1200	0.5531	0.75	0.7036
0.4084	3.57	1250	0.5787	0.7429	0.6901
0.3992	3.71	1300	0.5691	0.7386	0.6965
0.4385	3.86	1350	0.5701	0.7457	0.7012
0.5024	4.0	1400	0.5652	0.7486	0.7023

Framework versions

Transformers 4.39.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2