smids_3x_deit_small_sgd_001_fold2

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: 0.3562
• Accuracy: 0.8569

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: 0.001
• 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
0.8599	1.0	225	0.8308	0.6789
0.6572	2.0	450	0.6508	0.7488
0.5628	3.0	675	0.5574	0.7920
0.4888	4.0	900	0.5053	0.8053
0.4209	5.0	1125	0.4713	0.8136
0.3729	6.0	1350	0.4472	0.8253
0.4088	7.0	1575	0.4292	0.8270
0.3871	8.0	1800	0.4168	0.8353
0.3605	9.0	2025	0.4049	0.8369
0.2963	10.0	2250	0.3978	0.8403
0.3519	11.0	2475	0.3893	0.8469
0.3126	12.0	2700	0.3814	0.8536
0.2889	13.0	2925	0.3781	0.8519
0.3096	14.0	3150	0.3739	0.8552
0.3153	15.0	3375	0.3694	0.8586
0.3271	16.0	3600	0.3680	0.8619
0.2697	17.0	3825	0.3655	0.8602
0.2138	18.0	4050	0.3624	0.8602
0.2422	19.0	4275	0.3602	0.8636
0.288	20.0	4500	0.3609	0.8652
0.3039	21.0	4725	0.3587	0.8619
0.2907	22.0	4950	0.3580	0.8619
0.3138	23.0	5175	0.3576	0.8652
0.2718	24.0	5400	0.3569	0.8669
0.263	25.0	5625	0.3551	0.8669
0.245	26.0	5850	0.3538	0.8686
0.2019	27.0	6075	0.3530	0.8636
0.2353	28.0	6300	0.3539	0.8636
0.2451	29.0	6525	0.3558	0.8602
0.2565	30.0	6750	0.3536	0.8652
0.2202	31.0	6975	0.3542	0.8636
0.2433	32.0	7200	0.3552	0.8636
0.2621	33.0	7425	0.3534	0.8652
0.2353	34.0	7650	0.3541	0.8652
0.1836	35.0	7875	0.3533	0.8602
0.2199	36.0	8100	0.3554	0.8619
0.2271	37.0	8325	0.3536	0.8602
0.1937	38.0	8550	0.3541	0.8619
0.1782	39.0	8775	0.3547	0.8586
0.1988	40.0	9000	0.3551	0.8586
0.1613	41.0	9225	0.3546	0.8602
0.1997	42.0	9450	0.3550	0.8586
0.1938	43.0	9675	0.3554	0.8569
0.1972	44.0	9900	0.3557	0.8586
0.2519	45.0	10125	0.3555	0.8569
0.2003	46.0	10350	0.3557	0.8569
0.1846	47.0	10575	0.3560	0.8586
0.1808	48.0	10800	0.3561	0.8569
0.2273	49.0	11025	0.3561	0.8569
0.1583	50.0	11250	0.3562	0.8569

Framework versions

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