smids_3x_beit_base_adamax_0001_fold5

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: 0.9117
• Accuracy: 0.9083

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: 0.0001
• 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
0.2915	1.0	225	0.2769	0.8883
0.1074	2.0	450	0.2359	0.91
0.1094	3.0	675	0.3670	0.8817
0.1305	4.0	900	0.3641	0.905
0.0531	5.0	1125	0.4414	0.8967
0.0329	6.0	1350	0.4726	0.91
0.0583	7.0	1575	0.5580	0.8967
0.0317	8.0	1800	0.6015	0.905
0.0116	9.0	2025	0.6249	0.9
0.0004	10.0	2250	0.8362	0.8783
0.0225	11.0	2475	0.6370	0.905
0.0342	12.0	2700	0.8273	0.8967
0.0002	13.0	2925	0.8223	0.8983
0.0011	14.0	3150	0.7285	0.9017
0.0015	15.0	3375	0.8002	0.9017
0.0005	16.0	3600	0.7883	0.8983
0.0005	17.0	3825	1.0010	0.8867
0.0374	18.0	4050	0.8850	0.89
0.0379	19.0	4275	0.9596	0.885
0.0024	20.0	4500	0.8051	0.9
0.0007	21.0	4725	0.8980	0.8917
0.0	22.0	4950	0.8632	0.8967
0.0	23.0	5175	0.7801	0.905
0.0066	24.0	5400	0.9114	0.895
0.0001	25.0	5625	0.8232	0.905
0.0001	26.0	5850	0.9069	0.8983
0.0001	27.0	6075	0.9702	0.8933
0.0	28.0	6300	0.9355	0.9017
0.007	29.0	6525	0.9409	0.8933
0.0	30.0	6750	0.9196	0.905
0.0	31.0	6975	0.9430	0.89
0.0	32.0	7200	0.9769	0.8867
0.003	33.0	7425	0.9480	0.8917
0.0	34.0	7650	0.8822	0.9033
0.001	35.0	7875	0.9164	0.8983
0.0	36.0	8100	0.8790	0.9083
0.0069	37.0	8325	0.9068	0.9017
0.0	38.0	8550	0.8640	0.9017
0.0002	39.0	8775	0.9430	0.905
0.0017	40.0	9000	0.9609	0.8983
0.0	41.0	9225	0.9713	0.8933
0.0	42.0	9450	0.9484	0.905
0.003	43.0	9675	0.9360	0.9067
0.0	44.0	9900	0.8845	0.905
0.0	45.0	10125	0.8663	0.905
0.0	46.0	10350	0.8862	0.905
0.0	47.0	10575	0.9026	0.9067
0.0	48.0	10800	0.9052	0.905
0.0	49.0	11025	0.9131	0.9083
0.0	50.0	11250	0.9117	0.9083

Framework versions

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