smids_1x_deit_tiny_sgd_00001_fold2

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: 1.1866
• Accuracy: 0.3544

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
1.3496	1.0	75	1.3448	0.3444
1.342	2.0	150	1.3359	0.3444
1.3049	3.0	225	1.3273	0.3428
1.3212	4.0	300	1.3189	0.3428
1.2683	5.0	375	1.3112	0.3394
1.3476	6.0	450	1.3037	0.3394
1.3281	7.0	525	1.2966	0.3378
1.2813	8.0	600	1.2897	0.3394
1.3177	9.0	675	1.2831	0.3394
1.2768	10.0	750	1.2769	0.3394
1.2973	11.0	825	1.2710	0.3394
1.2616	12.0	900	1.2654	0.3428
1.2694	13.0	975	1.2600	0.3428
1.1891	14.0	1050	1.2550	0.3361
1.2441	15.0	1125	1.2502	0.3411
1.211	16.0	1200	1.2456	0.3428
1.247	17.0	1275	1.2413	0.3411
1.2791	18.0	1350	1.2372	0.3411
1.2453	19.0	1425	1.2333	0.3428
1.2386	20.0	1500	1.2296	0.3444
1.2461	21.0	1575	1.2262	0.3461
1.2333	22.0	1650	1.2229	0.3461
1.2716	23.0	1725	1.2198	0.3478
1.2019	24.0	1800	1.2169	0.3461
1.1715	25.0	1875	1.2141	0.3444
1.1932	26.0	1950	1.2116	0.3461
1.2512	27.0	2025	1.2092	0.3444
1.1951	28.0	2100	1.2069	0.3444
1.2421	29.0	2175	1.2047	0.3461
1.1922	30.0	2250	1.2027	0.3478
1.2041	31.0	2325	1.2008	0.3478
1.2208	32.0	2400	1.1991	0.3478
1.1905	33.0	2475	1.1975	0.3478
1.1949	34.0	2550	1.1960	0.3478
1.1944	35.0	2625	1.1946	0.3527
1.1832	36.0	2700	1.1934	0.3561
1.2088	37.0	2775	1.1923	0.3577
1.2643	38.0	2850	1.1913	0.3594
1.2153	39.0	2925	1.1904	0.3561
1.2054	40.0	3000	1.1896	0.3561
1.188	41.0	3075	1.1889	0.3561
1.2171	42.0	3150	1.1883	0.3577
1.1949	43.0	3225	1.1878	0.3577
1.159	44.0	3300	1.1874	0.3561
1.1443	45.0	3375	1.1871	0.3544
1.1683	46.0	3450	1.1869	0.3544
1.2029	47.0	3525	1.1867	0.3544
1.1913	48.0	3600	1.1867	0.3544
1.1814	49.0	3675	1.1866	0.3544
1.1739	50.0	3750	1.1866	0.3544

Framework versions

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