smids_3x_beit_base_rms_00001_fold2

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: 0.9909
• Accuracy: 0.9002

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
0.2362	1.0	225	0.2699	0.9035
0.1679	2.0	450	0.2716	0.9101
0.0726	3.0	675	0.3178	0.8968
0.0695	4.0	900	0.3843	0.9035
0.0417	5.0	1125	0.4680	0.8835
0.0473	6.0	1350	0.5055	0.9002
0.0543	7.0	1575	0.5652	0.8935
0.0498	8.0	1800	0.5730	0.9018
0.0051	9.0	2025	0.7436	0.8985
0.0809	10.0	2250	0.7929	0.8968
0.0184	11.0	2475	0.8279	0.8702
0.0005	12.0	2700	0.7228	0.8985
0.0232	13.0	2925	0.7729	0.8869
0.0419	14.0	3150	0.7425	0.8985
0.0106	15.0	3375	0.7246	0.8952
0.0338	16.0	3600	0.7871	0.8885
0.0349	17.0	3825	0.8649	0.9002
0.0092	18.0	4050	0.7633	0.8902
0.0509	19.0	4275	0.8796	0.8885
0.0566	20.0	4500	0.8230	0.9068
0.0001	21.0	4725	0.8115	0.8968
0.0178	22.0	4950	0.8547	0.9118
0.0024	23.0	5175	0.8065	0.9135
0.0	24.0	5400	0.8301	0.9085
0.0494	25.0	5625	0.9352	0.9035
0.0	26.0	5850	0.9033	0.8902
0.0001	27.0	6075	0.8768	0.8918
0.0	28.0	6300	0.8873	0.9002
0.0	29.0	6525	0.8635	0.9018
0.007	30.0	6750	0.8770	0.8952
0.0055	31.0	6975	0.9657	0.8985
0.0	32.0	7200	0.9004	0.8935
0.0016	33.0	7425	0.9326	0.8918
0.003	34.0	7650	0.9751	0.9002
0.0	35.0	7875	0.9491	0.9052
0.0043	36.0	8100	0.9618	0.8952
0.0087	37.0	8325	0.9634	0.8902
0.0294	38.0	8550	1.0166	0.8952
0.0044	39.0	8775	0.9519	0.8968
0.0	40.0	9000	0.9467	0.8985
0.0001	41.0	9225	0.9520	0.9002
0.0002	42.0	9450	0.9492	0.9002
0.0	43.0	9675	0.9742	0.8985
0.0	44.0	9900	1.0125	0.9018
0.0	45.0	10125	0.9921	0.9002
0.0	46.0	10350	0.9848	0.9002
0.0	47.0	10575	0.9786	0.8985
0.0	48.0	10800	0.9903	0.9002
0.0039	49.0	11025	0.9883	0.9002
0.0003	50.0	11250	0.9909	0.9002

Framework versions

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