smids_5x_deit_small_rms_0001_fold5

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

• Loss: 0.8725
• Accuracy: 0.915

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
0.2465	1.0	375	0.3246	0.8817
0.1757	2.0	750	0.3108	0.8983
0.1416	3.0	1125	0.4018	0.8917
0.0805	4.0	1500	0.5614	0.8733
0.0831	5.0	1875	0.4489	0.8783
0.0313	6.0	2250	0.6222	0.8833
0.0541	7.0	2625	0.5461	0.9017
0.0151	8.0	3000	0.5573	0.9017
0.0125	9.0	3375	0.6886	0.8817
0.0415	10.0	3750	0.5097	0.8967
0.0264	11.0	4125	0.6554	0.89
0.0122	12.0	4500	0.5509	0.8983
0.004	13.0	4875	0.6519	0.895
0.0092	14.0	5250	0.8038	0.88
0.0491	15.0	5625	0.5627	0.9117
0.0096	16.0	6000	0.7380	0.885
0.003	17.0	6375	0.6721	0.8967
0.0153	18.0	6750	0.6251	0.9017
0.0001	19.0	7125	0.7496	0.8933
0.0067	20.0	7500	0.7015	0.895
0.0015	21.0	7875	0.7054	0.9017
0.0117	22.0	8250	0.7731	0.8933
0.0015	23.0	8625	0.6632	0.9033
0.0003	24.0	9000	0.7347	0.9
0.0	25.0	9375	0.8344	0.8917
0.0002	26.0	9750	0.7080	0.905
0.0026	27.0	10125	0.8121	0.8933
0.0001	28.0	10500	0.7303	0.915
0.0285	29.0	10875	0.7237	0.905
0.0021	30.0	11250	0.7546	0.9
0.0096	31.0	11625	0.8217	0.8933
0.0	32.0	12000	0.8254	0.9017
0.0	33.0	12375	0.7430	0.905
0.0	34.0	12750	0.7668	0.9083
0.0002	35.0	13125	0.7980	0.9117
0.0018	36.0	13500	0.8507	0.9017
0.0	37.0	13875	0.7364	0.9133
0.0038	38.0	14250	0.7573	0.9133
0.0	39.0	14625	0.7786	0.9083
0.0	40.0	15000	0.7610	0.915
0.0	41.0	15375	0.7902	0.9117
0.0	42.0	15750	0.7539	0.9133
0.0	43.0	16125	0.8516	0.9133
0.0	44.0	16500	0.8335	0.9183
0.0	45.0	16875	0.8847	0.905
0.0	46.0	17250	0.9773	0.8967
0.0028	47.0	17625	0.8669	0.915
0.0	48.0	18000	0.8681	0.9133
0.0	49.0	18375	0.8719	0.9133
0.0019	50.0	18750	0.8725	0.915

Framework versions

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