smids_3x_deit_base_rms_00001_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: 0.7561
• Accuracy: 0.9115

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
0.3187	1.0	226	0.2723	0.8898
0.146	2.0	452	0.2372	0.9115
0.0656	3.0	678	0.3870	0.8798
0.0534	4.0	904	0.4524	0.8881
0.0105	5.0	1130	0.4069	0.8982
0.0185	6.0	1356	0.4543	0.9032
0.0005	7.0	1582	0.5107	0.8982
0.004	8.0	1808	0.5982	0.8915
0.0085	9.0	2034	0.5226	0.9032
0.0004	10.0	2260	0.5577	0.8998
0.0002	11.0	2486	0.6123	0.8965
0.0001	12.0	2712	0.5861	0.9032
0.0037	13.0	2938	0.8045	0.8865
0.0067	14.0	3164	0.5419	0.9048
0.0003	15.0	3390	0.5952	0.9132
0.0	16.0	3616	0.5589	0.9048
0.003	17.0	3842	0.5765	0.9032
0.001	18.0	4068	0.6268	0.9032
0.0041	19.0	4294	0.6263	0.9098
0.0	20.0	4520	0.6013	0.9065
0.0134	21.0	4746	0.6132	0.9115
0.0041	22.0	4972	0.5973	0.9182
0.0031	23.0	5198	0.6373	0.9082
0.001	24.0	5424	0.6622	0.9149
0.0	25.0	5650	0.7262	0.8965
0.0	26.0	5876	0.7187	0.9082
0.0	27.0	6102	0.7175	0.9082
0.0	28.0	6328	0.6740	0.9082
0.0	29.0	6554	0.7038	0.9082
0.0	30.0	6780	0.7480	0.9015
0.0	31.0	7006	0.7529	0.8998
0.0	32.0	7232	0.7622	0.9048
0.0029	33.0	7458	0.7367	0.9048
0.0	34.0	7684	0.7218	0.9032
0.0	35.0	7910	0.7442	0.8982
0.0	36.0	8136	0.7444	0.9082
0.0	37.0	8362	0.7439	0.9082
0.0	38.0	8588	0.7353	0.9115
0.0	39.0	8814	0.7431	0.9048
0.0	40.0	9040	0.7357	0.9165
0.0027	41.0	9266	0.7445	0.9082
0.0025	42.0	9492	0.7447	0.9098
0.0	43.0	9718	0.7447	0.9065
0.0	44.0	9944	0.7513	0.9098
0.0	45.0	10170	0.7507	0.9132
0.0	46.0	10396	0.7520	0.9132
0.0	47.0	10622	0.7546	0.9115
0.0	48.0	10848	0.7555	0.9115
0.0	49.0	11074	0.7559	0.9115
0.0	50.0	11300	0.7561	0.9115

Framework versions

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