smids_5x_deit_base_adamax_001_fold1

This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.7497
• Accuracy: 0.9132

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
0.329	1.0	376	0.4277	0.8464
0.2087	2.0	752	0.3407	0.8698
0.2485	3.0	1128	0.3788	0.8598
0.178	4.0	1504	0.4197	0.8531
0.1258	5.0	1880	0.4173	0.8648
0.1206	6.0	2256	0.3586	0.8848
0.1282	7.0	2632	0.3517	0.8865
0.0583	8.0	3008	0.5359	0.8765
0.0747	9.0	3384	0.5100	0.8731
0.0435	10.0	3760	0.5516	0.8781
0.06	11.0	4136	0.3933	0.8998
0.0257	12.0	4512	0.5267	0.8848
0.0686	13.0	4888	0.4896	0.9065
0.016	14.0	5264	0.5666	0.8881
0.011	15.0	5640	0.5612	0.8965
0.0019	16.0	6016	0.6453	0.8848
0.0015	17.0	6392	0.5726	0.8948
0.0354	18.0	6768	0.5332	0.9048
0.0037	19.0	7144	0.5726	0.8965
0.0094	20.0	7520	0.5926	0.9032
0.0008	21.0	7896	0.5520	0.8998
0.0004	22.0	8272	0.4436	0.9165
0.0006	23.0	8648	0.6077	0.8965
0.001	24.0	9024	0.6248	0.9132
0.0003	25.0	9400	0.6715	0.8982
0.0035	26.0	9776	0.6641	0.9082
0.0	27.0	10152	0.6982	0.9048
0.0	28.0	10528	0.7269	0.8982
0.0054	29.0	10904	0.6756	0.9098
0.0034	30.0	11280	0.6451	0.9065
0.0	31.0	11656	0.6535	0.9098
0.0	32.0	12032	0.6650	0.9065
0.0	33.0	12408	0.6759	0.9082
0.0	34.0	12784	0.6731	0.9048
0.0	35.0	13160	0.6782	0.9082
0.0001	36.0	13536	0.6755	0.9032
0.0	37.0	13912	0.7594	0.9098
0.0	38.0	14288	0.7065	0.9115
0.0	39.0	14664	0.7005	0.9082
0.0	40.0	15040	0.7058	0.9149
0.0	41.0	15416	0.6924	0.9115
0.0	42.0	15792	0.7078	0.9149
0.0	43.0	16168	0.7156	0.9149
0.0	44.0	16544	0.7204	0.9165
0.0	45.0	16920	0.7358	0.9149
0.003	46.0	17296	0.7278	0.9165
0.0	47.0	17672	0.7349	0.9149
0.0	48.0	18048	0.7414	0.9149
0.0	49.0	18424	0.7464	0.9149
0.0023	50.0	18800	0.7497	0.9132

Framework versions

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