ViT_fine_tuning

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

• Loss: 0.7794

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: 10
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss
0.1869	1.0	47	0.6323
0.3301	2.0	94	0.7937
0.3993	3.0	141	0.5598
0.2497	4.0	188	0.9144
0.3625	5.0	235	0.5646
0.3431	6.0	282	0.4955
0.2343	7.0	329	0.6660
0.287	8.0	376	0.6463
0.2958	9.0	423	0.7023
0.2301	10.0	470	0.7207
0.2303	11.0	517	0.8630
0.2671	12.0	564	0.7658
0.2605	13.0	611	0.6844
0.2491	14.0	658	0.6254
0.1739	15.0	705	0.7874
0.2482	16.0	752	0.6596
0.2007	17.0	799	0.7415
0.222	18.0	846	0.7555
0.2514	19.0	893	0.6816
0.1492	20.0	940	0.8623
0.1895	21.0	987	0.8038
0.1804	22.0	1034	0.7286
0.1719	23.0	1081	0.8166
0.1904	24.0	1128	0.8291
0.1732	25.0	1175	0.8563
0.1931	26.0	1222	0.7805
0.1616	27.0	1269	0.8687
0.1654	28.0	1316	0.8710
0.1956	29.0	1363	0.7511
0.1803	30.0	1410	0.7749
0.1173	31.0	1457	0.8292
0.12	32.0	1504	0.7924
0.1114	33.0	1551	0.7781
0.1192	34.0	1598	0.8182
0.1568	35.0	1645	0.7458
0.1375	36.0	1692	0.7571
0.0909	37.0	1739	0.8052
0.0931	38.0	1786	0.7864
0.1537	39.0	1833	0.7738
0.1144	40.0	1880	0.7794

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1