smids_10x_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: 0.9202
• Accuracy: 0.9098

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
0.3418	1.0	751	0.3645	0.8681
0.228	2.0	1502	0.3383	0.8815
0.2191	3.0	2253	0.3232	0.8915
0.2142	4.0	3004	0.3382	0.9015
0.1533	5.0	3755	0.4440	0.8681
0.1001	6.0	4506	0.4207	0.8698
0.085	7.0	5257	0.5360	0.8748
0.0859	8.0	6008	0.4176	0.9032
0.0802	9.0	6759	0.5292	0.8781
0.0332	10.0	7510	0.5218	0.9015
0.0553	11.0	8261	0.4537	0.9015
0.039	12.0	9012	0.7412	0.8848
0.0239	13.0	9763	0.6194	0.8915
0.0108	14.0	10514	0.7066	0.8848
0.0526	15.0	11265	0.6131	0.9032
0.0063	16.0	12016	0.8576	0.8681
0.0154	17.0	12767	0.6269	0.8948
0.0175	18.0	13518	0.6667	0.9048
0.0017	19.0	14269	0.6041	0.9048
0.0002	20.0	15020	0.7017	0.8798
0.0104	21.0	15771	0.6523	0.8965
0.0004	22.0	16522	0.5978	0.9065
0.0007	23.0	17273	0.7511	0.8982
0.0003	24.0	18024	0.8000	0.8948
0.0003	25.0	18775	0.7612	0.8932
0.0002	26.0	19526	0.7543	0.9032
0.0	27.0	20277	0.7144	0.9032
0.0	28.0	21028	0.8366	0.8831
0.0053	29.0	21779	0.9486	0.8815
0.0	30.0	22530	0.9579	0.8932
0.0	31.0	23281	0.8276	0.9015
0.0	32.0	24032	0.8430	0.9065
0.0	33.0	24783	0.7752	0.9098
0.0	34.0	25534	0.7966	0.9098
0.0	35.0	26285	0.8408	0.9048
0.0	36.0	27036	0.8314	0.9065
0.0	37.0	27787	0.8780	0.9015
0.0	38.0	28538	0.8886	0.8998
0.0	39.0	29289	0.8653	0.9048
0.0	40.0	30040	0.8404	0.9082
0.0	41.0	30791	0.8630	0.8998
0.0	42.0	31542	0.8333	0.9098
0.0	43.0	32293	0.9256	0.9048
0.0	44.0	33044	0.8529	0.9082
0.0	45.0	33795	0.8963	0.9082
0.0	46.0	34546	0.8944	0.9098
0.0	47.0	35297	0.9059	0.9098
0.0	48.0	36048	0.9120	0.9098
0.0	49.0	36799	0.9160	0.9098
0.0	50.0	37550	0.9202	0.9098

Framework versions

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