smids_1x_deit_tiny_sgd_00001_fold1

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

• Loss: 1.1750
• Accuracy: 0.3890

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
1.3532	1.0	76	1.3243	0.3506
1.4232	2.0	152	1.3155	0.3489
1.3221	3.0	228	1.3073	0.3489
1.3312	4.0	304	1.2992	0.3489
1.2834	5.0	380	1.2918	0.3539
1.3512	6.0	456	1.2848	0.3573
1.3029	7.0	532	1.2778	0.3573
1.3216	8.0	608	1.2712	0.3606
1.2731	9.0	684	1.2652	0.3656
1.2932	10.0	760	1.2593	0.3639
1.3065	11.0	836	1.2537	0.3606
1.2874	12.0	912	1.2484	0.3606
1.2669	13.0	988	1.2434	0.3623
1.2861	14.0	1064	1.2386	0.3639
1.3203	15.0	1140	1.2340	0.3639
1.3343	16.0	1216	1.2296	0.3639
1.3239	17.0	1292	1.2256	0.3656
1.2639	18.0	1368	1.2217	0.3639
1.2169	19.0	1444	1.2180	0.3673
1.1959	20.0	1520	1.2146	0.3689
1.2012	21.0	1596	1.2114	0.3723
1.1569	22.0	1672	1.2083	0.3706
1.2377	23.0	1748	1.2054	0.3656
1.2417	24.0	1824	1.2027	0.3673
1.2459	25.0	1900	1.2001	0.3689
1.2355	26.0	1976	1.1977	0.3673
1.2821	27.0	2052	1.1955	0.3656
1.2546	28.0	2128	1.1935	0.3706
1.2602	29.0	2204	1.1915	0.3689
1.1654	30.0	2280	1.1896	0.3723
1.2138	31.0	2356	1.1879	0.3740
1.2289	32.0	2432	1.1863	0.3756
1.1744	33.0	2508	1.1849	0.3756
1.2018	34.0	2584	1.1835	0.3756
1.2411	35.0	2660	1.1823	0.3773
1.2021	36.0	2736	1.1812	0.3840
1.172	37.0	2812	1.1802	0.3840
1.2015	38.0	2888	1.1792	0.3840
1.2305	39.0	2964	1.1784	0.3840
1.1165	40.0	3040	1.1777	0.3840
1.2641	41.0	3116	1.1771	0.3856
1.2228	42.0	3192	1.1765	0.3856
1.1905	43.0	3268	1.1761	0.3856
1.1893	44.0	3344	1.1757	0.3873
1.2905	45.0	3420	1.1755	0.3873
1.194	46.0	3496	1.1753	0.3873
1.1805	47.0	3572	1.1751	0.3873
1.1703	48.0	3648	1.1750	0.3873
1.2028	49.0	3724	1.1750	0.3890
1.2474	50.0	3800	1.1750	0.3890

Framework versions

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