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: 1.2065
Accuracy: 0.4444

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
1.469	1.0	27	1.4260	0.2444
1.3863	2.0	54	1.3825	0.2889
1.3604	3.0	81	1.3624	0.3333
1.3505	4.0	108	1.3566	0.4
1.2837	5.0	135	1.3537	0.4
1.2588	6.0	162	1.3503	0.4
1.243	7.0	189	1.3481	0.4
1.2286	8.0	216	1.3453	0.4222
1.1857	9.0	243	1.3417	0.4222
1.1652	10.0	270	1.3373	0.4222
1.135	11.0	297	1.3328	0.4222
1.1257	12.0	324	1.3276	0.4222
1.1465	13.0	351	1.3209	0.4444
1.0952	14.0	378	1.3151	0.4444
1.0919	15.0	405	1.3098	0.4444
1.0847	16.0	432	1.3049	0.4222
1.0446	17.0	459	1.2985	0.4667
1.0054	18.0	486	1.2928	0.4444
1.0169	19.0	513	1.2866	0.4222
1.0001	20.0	540	1.2827	0.4222
0.9603	21.0	567	1.2785	0.4222
0.9735	22.0	594	1.2740	0.4444
0.9444	23.0	621	1.2697	0.4667
0.9156	24.0	648	1.2621	0.4444
0.9658	25.0	675	1.2568	0.4444
0.9699	26.0	702	1.2527	0.4444
0.8985	27.0	729	1.2504	0.4444
0.8958	28.0	756	1.2453	0.4222
0.9214	29.0	783	1.2429	0.4444
0.9068	30.0	810	1.2374	0.4222
0.8659	31.0	837	1.2336	0.4222
0.8774	32.0	864	1.2303	0.4222
0.8587	33.0	891	1.2279	0.4222
0.8719	34.0	918	1.2241	0.4222
0.8448	35.0	945	1.2216	0.4222
0.8563	36.0	972	1.2203	0.4222
0.8555	37.0	999	1.2179	0.4222
0.8252	38.0	1026	1.2169	0.4222
0.83	39.0	1053	1.2146	0.4222
0.8062	40.0	1080	1.2129	0.4222
0.8472	41.0	1107	1.2110	0.4222
0.8075	42.0	1134	1.2099	0.4222
0.8415	43.0	1161	1.2087	0.4222
0.8064	44.0	1188	1.2081	0.4444
0.8219	45.0	1215	1.2076	0.4444
0.8297	46.0	1242	1.2069	0.4444
0.8108	47.0	1269	1.2066	0.4444
0.8128	48.0	1296	1.2065	0.4444
0.8385	49.0	1323	1.2065	0.4444
0.8247	50.0	1350	1.2065	0.4444

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_5x_deit_small_sgd_001_fold1

hushem_5x_deit_small_sgd_001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_5x_deit_small_sgd_001_fold1