image_classification

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

• Loss: 1.5809
• Accuracy: 0.45

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0715	1.0	10	2.0701	0.1313
2.0623	2.0	20	2.0531	0.2
2.0302	3.0	30	2.0127	0.25
1.9632	4.0	40	1.9530	0.2812
1.8736	5.0	50	1.8625	0.325
1.7788	6.0	60	1.7627	0.3625
1.677	7.0	70	1.7067	0.3625
1.5986	8.0	80	1.6461	0.4313
1.5581	9.0	90	1.6029	0.45
1.5082	10.0	100	1.6011	0.4188
1.4822	11.0	110	1.5765	0.4625
1.4599	12.0	120	1.5717	0.4562
1.451	13.0	130	1.5575	0.4313
1.446	14.0	140	1.5642	0.4125
1.4422	15.0	150	1.5705	0.4437

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Tokenizers 0.21.0