smids_1x_beit_base_rms_00001_fold4

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: 1.2766
• Accuracy: 0.8683

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
0.295	1.0	75	0.3791	0.8483
0.2062	2.0	150	0.3581	0.8683
0.101	3.0	225	0.4288	0.8783
0.0893	4.0	300	0.4864	0.8633
0.005	5.0	375	0.6074	0.8617
0.0333	6.0	450	0.7247	0.855
0.0079	7.0	525	0.7367	0.8667
0.0011	8.0	600	0.7491	0.8767
0.0337	9.0	675	0.8841	0.8667
0.023	10.0	750	0.9423	0.8617
0.0015	11.0	825	0.9063	0.87
0.0273	12.0	900	0.8724	0.8717
0.0004	13.0	975	0.8534	0.875
0.0254	14.0	1050	1.0178	0.8667
0.0142	15.0	1125	1.0491	0.86
0.0062	16.0	1200	1.0376	0.8733
0.0472	17.0	1275	1.0729	0.8683
0.0106	18.0	1350	1.0840	0.875
0.0563	19.0	1425	1.0588	0.8733
0.0079	20.0	1500	1.0867	0.87
0.0097	21.0	1575	1.1355	0.8567
0.0002	22.0	1650	1.1387	0.8633
0.0053	23.0	1725	1.0714	0.8633
0.0003	24.0	1800	1.0507	0.8717
0.006	25.0	1875	1.0737	0.87
0.0012	26.0	1950	1.0580	0.8817
0.0001	27.0	2025	1.0351	0.8733
0.0	28.0	2100	1.0876	0.8633
0.0003	29.0	2175	1.1172	0.865
0.0	30.0	2250	1.1601	0.8567
0.0175	31.0	2325	1.2685	0.8683
0.0003	32.0	2400	1.2370	0.8617
0.0	33.0	2475	1.2456	0.865
0.0	34.0	2550	1.2360	0.865
0.0047	35.0	2625	1.3021	0.8567
0.0001	36.0	2700	1.2287	0.8583
0.0	37.0	2775	1.2544	0.8667
0.0032	38.0	2850	1.2432	0.8683
0.0007	39.0	2925	1.3277	0.8633
0.0	40.0	3000	1.2887	0.86
0.0034	41.0	3075	1.2930	0.86
0.0066	42.0	3150	1.2756	0.855
0.0	43.0	3225	1.2450	0.8583
0.0	44.0	3300	1.2340	0.8633
0.0001	45.0	3375	1.2507	0.8667
0.0	46.0	3450	1.2915	0.8633
0.0	47.0	3525	1.2863	0.8683
0.0	48.0	3600	1.2824	0.8667
0.0022	49.0	3675	1.2757	0.8683
0.0021	50.0	3750	1.2766	0.8683

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0