smids_3x_deit_base_sgd_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: 1.0659
• Accuracy: 0.4491

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
1.1289	1.0	226	1.0936	0.3873
1.088	2.0	452	1.0923	0.3907
1.1393	3.0	678	1.0911	0.3940
1.1082	4.0	904	1.0899	0.3957
1.1039	5.0	1130	1.0887	0.3973
1.1198	6.0	1356	1.0876	0.3957
1.1055	7.0	1582	1.0865	0.3957
1.1209	8.0	1808	1.0854	0.3973
1.0984	9.0	2034	1.0844	0.3990
1.0834	10.0	2260	1.0834	0.4040
1.1107	11.0	2486	1.0825	0.4057
1.1106	12.0	2712	1.0815	0.4107
1.0951	13.0	2938	1.0807	0.4107
1.084	14.0	3164	1.0798	0.4140
1.0913	15.0	3390	1.0790	0.4224
1.0879	16.0	3616	1.0781	0.4274
1.0942	17.0	3842	1.0774	0.4290
1.1034	18.0	4068	1.0766	0.4290
1.0749	19.0	4294	1.0759	0.4290
1.0856	20.0	4520	1.0752	0.4341
1.0907	21.0	4746	1.0745	0.4407
1.0776	22.0	4972	1.0739	0.4424
1.0863	23.0	5198	1.0733	0.4407
1.0887	24.0	5424	1.0727	0.4424
1.0775	25.0	5650	1.0722	0.4474
1.092	26.0	5876	1.0716	0.4457
1.09	27.0	6102	1.0711	0.4424
1.0932	28.0	6328	1.0707	0.4391
1.0761	29.0	6554	1.0702	0.4407
1.0937	30.0	6780	1.0698	0.4407
1.0661	31.0	7006	1.0694	0.4424
1.0826	32.0	7232	1.0690	0.4424
1.0898	33.0	7458	1.0686	0.4407
1.0784	34.0	7684	1.0683	0.4457
1.0944	35.0	7910	1.0680	0.4457
1.08	36.0	8136	1.0677	0.4474
1.0796	37.0	8362	1.0674	0.4474
1.08	38.0	8588	1.0672	0.4491
1.0835	39.0	8814	1.0670	0.4491
1.0952	40.0	9040	1.0668	0.4491
1.0844	41.0	9266	1.0666	0.4474
1.0907	42.0	9492	1.0664	0.4474
1.087	43.0	9718	1.0663	0.4474
1.0798	44.0	9944	1.0662	0.4474
1.0672	45.0	10170	1.0661	0.4457
1.0874	46.0	10396	1.0660	0.4457
1.0866	47.0	10622	1.0660	0.4457
1.0871	48.0	10848	1.0660	0.4474
1.0775	49.0	11074	1.0659	0.4491
1.0886	50.0	11300	1.0659	0.4491

Framework versions

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