smids_3x_deit_base_rms_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: 0.6681
• Accuracy: 0.7730

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
0.858	1.0	226	2.2476	0.3289
0.8652	2.0	452	0.8983	0.5242
0.8184	3.0	678	0.9071	0.5008
0.8998	4.0	904	0.8629	0.5142
0.8039	5.0	1130	0.9089	0.4958
0.8516	6.0	1356	0.8861	0.5025
0.7034	7.0	1582	0.8149	0.6010
0.7133	8.0	1808	0.9764	0.5559
0.6649	9.0	2034	0.8042	0.6160
0.7571	10.0	2260	0.7526	0.6644
0.7133	11.0	2486	0.7559	0.6678
0.7109	12.0	2712	0.7911	0.6411
0.6513	13.0	2938	0.7985	0.6461
0.642	14.0	3164	0.6827	0.7028
0.6582	15.0	3390	0.7203	0.6728
0.6538	16.0	3616	0.7567	0.6678
0.5556	17.0	3842	0.7078	0.6694
0.6192	18.0	4068	0.6570	0.7129
0.6471	19.0	4294	0.7189	0.6995
0.5592	20.0	4520	0.7057	0.6995
0.6811	21.0	4746	0.6584	0.7262
0.6379	22.0	4972	0.6924	0.6912
0.641	23.0	5198	0.6895	0.7212
0.5889	24.0	5424	0.6980	0.6995
0.639	25.0	5650	0.6309	0.7279
0.6445	26.0	5876	0.6685	0.7379
0.524	27.0	6102	0.6179	0.7362
0.5828	28.0	6328	0.6999	0.6761
0.5112	29.0	6554	0.7255	0.6945
0.5736	30.0	6780	0.6697	0.7012
0.5437	31.0	7006	0.6621	0.7262
0.4721	32.0	7232	0.6063	0.7412
0.4483	33.0	7458	0.6550	0.7062
0.4826	34.0	7684	0.7265	0.6845
0.4436	35.0	7910	0.5926	0.7713
0.479	36.0	8136	0.5652	0.7579
0.4615	37.0	8362	0.5901	0.7563
0.4618	38.0	8588	0.6669	0.7346
0.4189	39.0	8814	0.6189	0.7646
0.486	40.0	9040	0.6150	0.7613
0.4426	41.0	9266	0.6125	0.7663
0.4773	42.0	9492	0.6744	0.7396
0.4281	43.0	9718	0.6291	0.7730
0.3986	44.0	9944	0.6315	0.7880
0.4375	45.0	10170	0.6494	0.7679
0.3887	46.0	10396	0.6596	0.7746
0.4097	47.0	10622	0.6522	0.7679
0.4037	48.0	10848	0.6698	0.7763
0.3545	49.0	11074	0.6604	0.7730
0.3857	50.0	11300	0.6681	0.7730

Framework versions

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