smids_1x_deit_small_sgd_00001_fold3

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: 1.0491
• Accuracy: 0.47

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: 1e-05
• 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
1.0941	1.0	75	1.0867	0.3867
1.1031	2.0	150	1.0847	0.3883
1.0678	3.0	225	1.0827	0.39
1.0493	4.0	300	1.0809	0.395
1.0783	5.0	375	1.0791	0.4017
1.0689	6.0	450	1.0774	0.4083
1.0606	7.0	525	1.0758	0.4117
1.0286	8.0	600	1.0743	0.4117
1.0504	9.0	675	1.0729	0.415
1.0349	10.0	750	1.0714	0.415
1.0372	11.0	825	1.0701	0.4167
1.0665	12.0	900	1.0688	0.4233
1.0542	13.0	975	1.0676	0.4233
1.0662	14.0	1050	1.0664	0.4267
1.0308	15.0	1125	1.0653	0.4283
1.0599	16.0	1200	1.0642	0.4283
1.0281	17.0	1275	1.0632	0.43
1.0433	18.0	1350	1.0622	0.4383
1.0474	19.0	1425	1.0612	0.4433
1.0662	20.0	1500	1.0603	0.4467
1.0359	21.0	1575	1.0595	0.4417
1.0248	22.0	1650	1.0587	0.4417
1.0401	23.0	1725	1.0579	0.445
1.0329	24.0	1800	1.0572	0.4467
1.053	25.0	1875	1.0565	0.4533
1.0305	26.0	1950	1.0558	0.4533
1.0308	27.0	2025	1.0552	0.455
1.0523	28.0	2100	1.0546	0.4567
1.0577	29.0	2175	1.0541	0.4583
1.0456	30.0	2250	1.0535	0.4583
1.0268	31.0	2325	1.0531	0.4583
1.0567	32.0	2400	1.0526	0.4617
1.0191	33.0	2475	1.0522	0.465
1.0381	34.0	2550	1.0518	0.47
1.0572	35.0	2625	1.0514	0.47
1.0481	36.0	2700	1.0511	0.47
1.022	37.0	2775	1.0508	0.4683
1.0366	38.0	2850	1.0505	0.4683
1.029	39.0	2925	1.0502	0.4683
1.0115	40.0	3000	1.0500	0.47
1.0512	41.0	3075	1.0498	0.47
1.0219	42.0	3150	1.0496	0.47
1.046	43.0	3225	1.0495	0.47
1.0476	44.0	3300	1.0494	0.47
1.0512	45.0	3375	1.0493	0.47
1.0286	46.0	3450	1.0492	0.47
1.0307	47.0	3525	1.0491	0.47
1.0266	48.0	3600	1.0491	0.47
1.0403	49.0	3675	1.0491	0.47
1.011	50.0	3750	1.0491	0.47

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0