smids_10x_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: 0.9942
• Accuracy: 0.5776

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
1.1101	1.0	751	1.0912	0.3940
1.1137	2.0	1502	1.0874	0.3990
1.0977	3.0	2253	1.0838	0.4057
1.0963	4.0	3004	1.0803	0.4157
1.0734	5.0	3755	1.0769	0.4307
1.0814	6.0	4506	1.0737	0.4424
1.0905	7.0	5257	1.0705	0.4558
1.0682	8.0	6008	1.0673	0.4508
1.0698	9.0	6759	1.0643	0.4524
1.066	10.0	7510	1.0613	0.4608
1.0809	11.0	8261	1.0584	0.4691
1.0569	12.0	9012	1.0556	0.4708
1.0524	13.0	9763	1.0527	0.4908
1.051	14.0	10514	1.0500	0.5042
1.0693	15.0	11265	1.0473	0.5092
1.0517	16.0	12016	1.0446	0.5175
1.0588	17.0	12767	1.0419	0.5159
1.0399	18.0	13518	1.0394	0.5192
1.0367	19.0	14269	1.0368	0.5225
1.0366	20.0	15020	1.0343	0.5259
1.0281	21.0	15771	1.0318	0.5326
1.036	22.0	16522	1.0294	0.5342
1.0334	23.0	17273	1.0270	0.5359
1.0262	24.0	18024	1.0247	0.5376
1.0153	25.0	18775	1.0224	0.5392
1.0269	26.0	19526	1.0202	0.5409
1.0163	27.0	20277	1.0180	0.5459
1.0112	28.0	21028	1.0159	0.5459
1.0292	29.0	21779	1.0139	0.5509
1.0159	30.0	22530	1.0120	0.5526
1.0063	31.0	23281	1.0102	0.5526
1.0238	32.0	24032	1.0085	0.5543
0.9962	33.0	24783	1.0069	0.5543
1.0016	34.0	25534	1.0053	0.5593
1.0116	35.0	26285	1.0039	0.5593
1.0035	36.0	27036	1.0026	0.5626
1.0094	37.0	27787	1.0013	0.5659
0.9975	38.0	28538	1.0002	0.5676
1.0065	39.0	29289	0.9992	0.5743
0.9968	40.0	30040	0.9982	0.5760
0.9969	41.0	30791	0.9974	0.5760
0.9821	42.0	31542	0.9967	0.5776
0.9849	43.0	32293	0.9961	0.5776
1.002	44.0	33044	0.9955	0.5776
1.0006	45.0	33795	0.9951	0.5776
1.0018	46.0	34546	0.9948	0.5776
0.9926	47.0	35297	0.9945	0.5776
1.0075	48.0	36048	0.9943	0.5776
0.9883	49.0	36799	0.9942	0.5776
0.9793	50.0	37550	0.9942	0.5776

Framework versions

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