smids_5x_beit_base_rms_0001_fold1

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

• Loss: 0.9099
• Accuracy: 0.9032

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2877	1.0	376	0.3734	0.8397
0.263	2.0	752	0.2897	0.8898
0.214	3.0	1128	0.4392	0.8815
0.1401	4.0	1504	0.3640	0.8865
0.0913	5.0	1880	0.4071	0.8982
0.0792	6.0	2256	0.5796	0.8765
0.0326	7.0	2632	0.5828	0.8781
0.0613	8.0	3008	0.5485	0.8965
0.0614	9.0	3384	0.5394	0.8815
0.0378	10.0	3760	0.5802	0.8932
0.016	11.0	4136	0.5517	0.8998
0.1114	12.0	4512	0.5851	0.8798
0.0304	13.0	4888	0.5301	0.8731
0.0236	14.0	5264	0.6243	0.8965
0.0147	15.0	5640	0.5697	0.8998
0.0009	16.0	6016	0.5289	0.9098
0.003	17.0	6392	0.6450	0.8932
0.045	18.0	6768	0.7662	0.8915
0.0003	19.0	7144	0.6709	0.8898
0.0083	20.0	7520	0.7941	0.8865
0.0011	21.0	7896	0.8204	0.8831
0.0265	22.0	8272	0.7663	0.8798
0.0065	23.0	8648	0.7543	0.8865
0.0005	24.0	9024	0.8605	0.8881
0.0223	25.0	9400	0.7879	0.8815
0.0093	26.0	9776	0.8444	0.8748
0.0004	27.0	10152	0.7708	0.8781
0.0001	28.0	10528	0.7477	0.8948
0.0051	29.0	10904	0.7865	0.8831
0.0131	30.0	11280	0.8049	0.9098
0.0	31.0	11656	0.8832	0.8915
0.0001	32.0	12032	0.8723	0.8965
0.0007	33.0	12408	1.0043	0.8865
0.0001	34.0	12784	0.9137	0.8881
0.0019	35.0	13160	0.7356	0.9048
0.0	36.0	13536	0.7048	0.9032
0.0	37.0	13912	0.8706	0.9015
0.0	38.0	14288	0.7699	0.9032
0.0	39.0	14664	0.8383	0.8982
0.0	40.0	15040	0.8533	0.9048
0.0008	41.0	15416	0.8710	0.9015
0.0001	42.0	15792	0.9271	0.8898
0.0	43.0	16168	0.9308	0.8982
0.0	44.0	16544	0.9577	0.8982
0.0	45.0	16920	0.9412	0.8898
0.0033	46.0	17296	0.9423	0.8998
0.0	47.0	17672	0.9136	0.9048
0.0	48.0	18048	0.9005	0.9065
0.0001	49.0	18424	0.9138	0.9048
0.0023	50.0	18800	0.9099	0.9032

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2