image_classification

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.2364
• Accuracy: 0.5938

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: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0702	1.0	10	2.0666	0.1437
2.0583	2.0	20	2.0476	0.2125
2.0291	3.0	30	2.0018	0.3
1.9639	4.0	40	1.9175	0.3563
1.8582	5.0	50	1.7997	0.4375
1.7385	6.0	60	1.6756	0.4625
1.5984	7.0	70	1.5469	0.4625
1.4739	8.0	80	1.4684	0.5188
1.3737	9.0	90	1.4090	0.5125
1.2719	10.0	100	1.3740	0.525
1.2072	11.0	110	1.3527	0.55
1.1158	12.0	120	1.3118	0.5188
1.0487	13.0	130	1.2349	0.6
0.9873	14.0	140	1.2931	0.525
0.8928	15.0	150	1.2731	0.55

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1