smids_1x_beit_base_adamax_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: 0.7289
• Accuracy: 0.8852

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
0.4217	1.0	75	0.3814	0.8419
0.2549	2.0	150	0.3222	0.8735
0.2258	3.0	225	0.2946	0.8802
0.1818	4.0	300	0.2874	0.8935
0.1414	5.0	375	0.3063	0.8869
0.1276	6.0	450	0.3088	0.8835
0.1278	7.0	525	0.3231	0.8885
0.0712	8.0	600	0.3560	0.8869
0.0461	9.0	675	0.3613	0.8918
0.0475	10.0	750	0.3784	0.8952
0.0242	11.0	825	0.4079	0.8885
0.0506	12.0	900	0.4429	0.8869
0.0272	13.0	975	0.4714	0.8869
0.0444	14.0	1050	0.5396	0.8802
0.0206	15.0	1125	0.5526	0.8735
0.0163	16.0	1200	0.5286	0.8852
0.0204	17.0	1275	0.5940	0.8819
0.0355	18.0	1350	0.5758	0.8769
0.0442	19.0	1425	0.5804	0.8785
0.0309	20.0	1500	0.5941	0.8819
0.0106	21.0	1575	0.6105	0.8802
0.0257	22.0	1650	0.6126	0.8835
0.0159	23.0	1725	0.6156	0.8852
0.0399	24.0	1800	0.6198	0.8785
0.0047	25.0	1875	0.6196	0.8819
0.0247	26.0	1950	0.6464	0.8835
0.024	27.0	2025	0.6527	0.8869
0.0438	28.0	2100	0.7050	0.8819
0.0088	29.0	2175	0.6605	0.8902
0.0182	30.0	2250	0.6570	0.8885
0.0251	31.0	2325	0.6796	0.8819
0.017	32.0	2400	0.6922	0.8852
0.033	33.0	2475	0.7245	0.8719
0.0216	34.0	2550	0.6972	0.8785
0.0144	35.0	2625	0.7562	0.8819
0.0161	36.0	2700	0.6986	0.8835
0.0005	37.0	2775	0.6981	0.8819
0.0053	38.0	2850	0.7088	0.8869
0.0506	39.0	2925	0.7290	0.8869
0.0237	40.0	3000	0.7146	0.8885
0.0005	41.0	3075	0.7241	0.8802
0.0171	42.0	3150	0.7294	0.8819
0.0152	43.0	3225	0.7178	0.8869
0.0007	44.0	3300	0.7168	0.8819
0.0066	45.0	3375	0.7243	0.8819
0.0023	46.0	3450	0.7324	0.8835
0.053	47.0	3525	0.7341	0.8852
0.0015	48.0	3600	0.7298	0.8852
0.0034	49.0	3675	0.7290	0.8852
0.0068	50.0	3750	0.7289	0.8852

Framework versions

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