smids_1x_deit_small_rms_00001_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: 0.8494
• Accuracy: 0.8702

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
0.391	1.0	75	0.3306	0.8569
0.2024	2.0	150	0.3078	0.8719
0.1659	3.0	225	0.3046	0.8636
0.1089	4.0	300	0.3233	0.8702
0.0832	5.0	375	0.4345	0.8552
0.0315	6.0	450	0.4227	0.8686
0.0247	7.0	525	0.5432	0.8652
0.0031	8.0	600	0.5857	0.8769
0.0058	9.0	675	0.5689	0.8619
0.0354	10.0	750	0.6368	0.8619
0.0193	11.0	825	0.5921	0.8752
0.0019	12.0	900	0.6514	0.8785
0.0447	13.0	975	0.6838	0.8686
0.0527	14.0	1050	0.6693	0.8735
0.0047	15.0	1125	0.6444	0.8735
0.0064	16.0	1200	0.7052	0.8719
0.0002	17.0	1275	0.7289	0.8636
0.0092	18.0	1350	0.7405	0.8669
0.0001	19.0	1425	0.7743	0.8619
0.0038	20.0	1500	0.7512	0.8686
0.0001	21.0	1575	0.8249	0.8602
0.0001	22.0	1650	0.7832	0.8686
0.0001	23.0	1725	0.8312	0.8636
0.0	24.0	1800	0.7877	0.8669
0.0	25.0	1875	0.7958	0.8719
0.0001	26.0	1950	0.7718	0.8752
0.0055	27.0	2025	0.7918	0.8686
0.0032	28.0	2100	0.8022	0.8735
0.0023	29.0	2175	0.8185	0.8735
0.0031	30.0	2250	0.8365	0.8735
0.0028	31.0	2325	0.7946	0.8686
0.0	32.0	2400	0.8222	0.8752
0.0	33.0	2475	0.7981	0.8719
0.0	34.0	2550	0.8313	0.8752
0.0084	35.0	2625	0.8895	0.8702
0.0	36.0	2700	0.8170	0.8686
0.0	37.0	2775	0.8344	0.8752
0.0	38.0	2850	0.8561	0.8735
0.0022	39.0	2925	0.8329	0.8702
0.0	40.0	3000	0.8473	0.8719
0.0026	41.0	3075	0.8354	0.8686
0.0	42.0	3150	0.8451	0.8735
0.0025	43.0	3225	0.8430	0.8735
0.0025	44.0	3300	0.8484	0.8719
0.0	45.0	3375	0.8461	0.8702
0.0	46.0	3450	0.8473	0.8735
0.0023	47.0	3525	0.8487	0.8719
0.0	48.0	3600	0.8492	0.8702
0.0022	49.0	3675	0.8491	0.8686
0.0022	50.0	3750	0.8494	0.8702

Framework versions

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