smids_3x_beit_base_adamax_0001_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: 0.8017
• Accuracy: 0.91

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
0.3218	1.0	225	0.3049	0.8783
0.1886	2.0	450	0.2841	0.8967
0.0936	3.0	675	0.2901	0.905
0.0347	4.0	900	0.3730	0.9067
0.0374	5.0	1125	0.5485	0.885
0.0265	6.0	1350	0.5296	0.8933
0.0077	7.0	1575	0.5235	0.9083
0.0372	8.0	1800	0.5900	0.915
0.0065	9.0	2025	0.6549	0.905
0.0316	10.0	2250	0.8684	0.88
0.0273	11.0	2475	0.6609	0.9133
0.0029	12.0	2700	0.7388	0.8983
0.001	13.0	2925	0.7878	0.8933
0.0056	14.0	3150	0.7685	0.9
0.0005	15.0	3375	0.7882	0.8933
0.0052	16.0	3600	0.7154	0.9017
0.0026	17.0	3825	0.6645	0.8967
0.0001	18.0	4050	0.7811	0.8917
0.0005	19.0	4275	0.8281	0.8883
0.001	20.0	4500	0.6603	0.9083
0.0022	21.0	4725	0.7385	0.905
0.0001	22.0	4950	0.7367	0.9033
0.0002	23.0	5175	0.8135	0.885
0.0001	24.0	5400	0.8005	0.8983
0.0193	25.0	5625	0.8350	0.8883
0.0	26.0	5850	0.7434	0.905
0.0	27.0	6075	0.7179	0.905
0.0001	28.0	6300	0.8254	0.9
0.0047	29.0	6525	0.8746	0.8933
0.006	30.0	6750	0.8594	0.8983
0.0021	31.0	6975	0.8754	0.8917
0.0	32.0	7200	0.8773	0.8983
0.0	33.0	7425	0.8925	0.8867
0.0	34.0	7650	0.9018	0.89
0.0	35.0	7875	0.8530	0.8983
0.0	36.0	8100	0.7923	0.905
0.0	37.0	8325	0.7837	0.905
0.0	38.0	8550	0.8324	0.9017
0.0	39.0	8775	0.8536	0.895
0.0	40.0	9000	0.8379	0.8917
0.0009	41.0	9225	0.8179	0.8983
0.0	42.0	9450	0.8003	0.9067
0.0	43.0	9675	0.8131	0.9033
0.0	44.0	9900	0.7802	0.9117
0.0	45.0	10125	0.8111	0.9
0.0	46.0	10350	0.8012	0.9033
0.0026	47.0	10575	0.7937	0.9117
0.0	48.0	10800	0.8052	0.9117
0.0	49.0	11025	0.8066	0.9083
0.0	50.0	11250	0.8017	0.91

Framework versions

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