hushem_40x_deit_small_adamax_001_fold1

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: 2.1541
• Accuracy: 0.7556

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
0.1447	1.0	215	1.0279	0.7556
0.0939	2.0	430	1.6244	0.7333
0.025	3.0	645	1.1738	0.8
0.0505	4.0	860	1.8318	0.6667
0.02	5.0	1075	1.9882	0.7333
0.1072	6.0	1290	1.2076	0.7333
0.0633	7.0	1505	1.6747	0.7333
0.0604	8.0	1720	1.1018	0.8
0.0484	9.0	1935	2.2857	0.6444
0.0045	10.0	2150	2.0338	0.7556
0.0317	11.0	2365	2.1474	0.7556
0.0239	12.0	2580	1.5303	0.7778
0.0001	13.0	2795	2.3569	0.6444
0.0001	14.0	3010	2.2079	0.7556
0.0	15.0	3225	1.6648	0.7778
0.0065	16.0	3440	1.7779	0.7778
0.0	17.0	3655	1.9802	0.7556
0.0	18.0	3870	2.1669	0.7778
0.0001	19.0	4085	1.9508	0.8
0.0	20.0	4300	3.0396	0.6889
0.0	21.0	4515	1.8449	0.7333
0.0	22.0	4730	1.8614	0.7333
0.0	23.0	4945	1.8711	0.7333
0.0	24.0	5160	1.8758	0.7333
0.0	25.0	5375	1.8839	0.7333
0.0	26.0	5590	1.8890	0.7111
0.0	27.0	5805	1.8959	0.7111
0.0	28.0	6020	1.9021	0.7111
0.0	29.0	6235	1.9100	0.7111
0.0	30.0	6450	1.9180	0.7111
0.0	31.0	6665	1.9279	0.7111
0.0	32.0	6880	1.9382	0.7333
0.0	33.0	7095	1.9497	0.7333
0.0	34.0	7310	1.9619	0.7333
0.0	35.0	7525	1.9743	0.7333
0.0	36.0	7740	1.9878	0.7333
0.0	37.0	7955	2.0026	0.7333
0.0	38.0	8170	2.0159	0.7333
0.0	39.0	8385	2.0312	0.7333
0.0	40.0	8600	2.0457	0.7333
0.0	41.0	8815	2.0615	0.7333
0.0	42.0	9030	2.0758	0.7333
0.0	43.0	9245	2.0899	0.7333
0.0	44.0	9460	2.1029	0.7333
0.0	45.0	9675	2.1161	0.7333
0.0	46.0	9890	2.1279	0.7556
0.0	47.0	10105	2.1385	0.7556
0.0	48.0	10320	2.1469	0.7556
0.0	49.0	10535	2.1525	0.7556
0.0	50.0	10750	2.1541	0.7556

Framework versions

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