smids_3x_beit_base_adamax_001_fold3

This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.9113
• Accuracy: 0.8833

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
0.7164	1.0	225	0.4684	0.81
0.3974	2.0	450	0.3760	0.845
0.3042	3.0	675	0.4562	0.82
0.264	4.0	900	0.3521	0.86
0.2635	5.0	1125	0.3585	0.8567
0.3122	6.0	1350	0.3482	0.87
0.1881	7.0	1575	0.4250	0.8583
0.2288	8.0	1800	0.4228	0.8583
0.1644	9.0	2025	0.5487	0.8367
0.1666	10.0	2250	0.4820	0.8467
0.1186	11.0	2475	0.6337	0.835
0.1307	12.0	2700	0.4076	0.87
0.0842	13.0	2925	0.5631	0.8733
0.0933	14.0	3150	0.5566	0.8767
0.0383	15.0	3375	0.6882	0.8433
0.0107	16.0	3600	0.5512	0.87
0.0331	17.0	3825	0.5868	0.8617
0.0654	18.0	4050	0.7675	0.8517
0.0588	19.0	4275	0.5953	0.8833
0.0197	20.0	4500	0.6863	0.875
0.0147	21.0	4725	0.7719	0.8717
0.0638	22.0	4950	0.7585	0.87
0.0213	23.0	5175	0.7631	0.8667
0.0027	24.0	5400	0.8123	0.8717
0.0619	25.0	5625	0.6777	0.87
0.0044	26.0	5850	0.7468	0.8833
0.0118	27.0	6075	0.7959	0.8683
0.0014	28.0	6300	0.6725	0.8733
0.0196	29.0	6525	0.8072	0.8733
0.0092	30.0	6750	0.7937	0.8833
0.0065	31.0	6975	0.9261	0.875
0.0008	32.0	7200	0.8949	0.875
0.0001	33.0	7425	0.8856	0.89
0.0027	34.0	7650	0.8960	0.8633
0.0	35.0	7875	0.9060	0.87
0.0	36.0	8100	0.8882	0.875
0.0044	37.0	8325	0.9127	0.8783
0.0	38.0	8550	0.9987	0.8767
0.0	39.0	8775	0.9306	0.8817
0.0	40.0	9000	0.8606	0.885
0.0	41.0	9225	0.8647	0.8817
0.0	42.0	9450	0.8530	0.88
0.0	43.0	9675	0.8745	0.885
0.0	44.0	9900	0.8799	0.8817
0.0	45.0	10125	0.9191	0.87
0.0	46.0	10350	0.9238	0.88
0.0033	47.0	10575	0.9260	0.8783
0.0	48.0	10800	0.9161	0.8767
0.0	49.0	11025	0.9134	0.88
0.0	50.0	11250	0.9113	0.8833

Framework versions

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