smids_1x_deit_small_rms_00001_fold4

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: 1.2283
• Accuracy: 0.86

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
0.3693	1.0	75	0.4169	0.8367
0.25	2.0	150	0.3480	0.86
0.1826	3.0	225	0.3907	0.8517
0.103	4.0	300	0.4268	0.8533
0.0588	5.0	375	0.4745	0.8517
0.0211	6.0	450	0.5873	0.86
0.0762	7.0	525	0.6785	0.8567
0.0033	8.0	600	0.6768	0.8533
0.0377	9.0	675	0.7784	0.855
0.0107	10.0	750	0.8289	0.8467
0.0009	11.0	825	0.8979	0.845
0.0002	12.0	900	0.8647	0.8617
0.0003	13.0	975	0.8591	0.8583
0.0077	14.0	1050	0.9903	0.8483
0.0002	15.0	1125	0.9262	0.86
0.0075	16.0	1200	1.1297	0.8283
0.0005	17.0	1275	0.9421	0.86
0.0146	18.0	1350	0.8922	0.86
0.0001	19.0	1425	0.9244	0.8683
0.0001	20.0	1500	0.9926	0.8683
0.003	21.0	1575	0.9538	0.8633
0.0001	22.0	1650	0.9796	0.8633
0.0	23.0	1725	0.9957	0.865
0.0079	24.0	1800	0.9969	0.8667
0.0074	25.0	1875	1.0816	0.86
0.0	26.0	1950	1.1025	0.8617
0.0	27.0	2025	1.1525	0.8467
0.0057	28.0	2100	1.1210	0.855
0.0181	29.0	2175	1.1276	0.86
0.0	30.0	2250	1.1208	0.8617
0.0	31.0	2325	1.1193	0.865
0.0	32.0	2400	1.1408	0.8617
0.0	33.0	2475	1.1431	0.8633
0.0	34.0	2550	1.1491	0.86
0.0	35.0	2625	1.1589	0.8617
0.0	36.0	2700	1.1620	0.8617
0.0031	37.0	2775	1.1838	0.8633
0.0	38.0	2850	1.1840	0.8633
0.0	39.0	2925	1.1861	0.8617
0.0	40.0	3000	1.2058	0.8633
0.0028	41.0	3075	1.1981	0.865
0.0	42.0	3150	1.2026	0.8617
0.0	43.0	3225	1.2159	0.86
0.0	44.0	3300	1.2159	0.86
0.0	45.0	3375	1.2189	0.86
0.0	46.0	3450	1.2225	0.86
0.0	47.0	3525	1.2244	0.86
0.0	48.0	3600	1.2263	0.86
0.0	49.0	3675	1.2278	0.86
0.0	50.0	3750	1.2283	0.86

Framework versions

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