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: 0.3078
Accuracy: 0.8686

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: 0.001
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
0.8275	1.0	225	0.8216	0.6506
0.6191	2.0	450	0.6029	0.7704
0.5649	3.0	675	0.5207	0.7953
0.5387	4.0	900	0.4780	0.8070
0.4277	5.0	1125	0.4562	0.8020
0.4656	6.0	1350	0.4304	0.8170
0.4051	7.0	1575	0.4146	0.8220
0.4601	8.0	1800	0.4030	0.8353
0.3696	9.0	2025	0.3828	0.8369
0.3307	10.0	2250	0.3745	0.8403
0.3955	11.0	2475	0.3651	0.8386
0.3579	12.0	2700	0.3632	0.8419
0.3293	13.0	2925	0.3578	0.8536
0.3333	14.0	3150	0.3518	0.8502
0.3685	15.0	3375	0.3389	0.8619
0.3757	16.0	3600	0.3549	0.8519
0.2934	17.0	3825	0.3349	0.8619
0.3154	18.0	4050	0.3310	0.8586
0.2645	19.0	4275	0.3332	0.8602
0.3308	20.0	4500	0.3318	0.8536
0.3463	21.0	4725	0.3245	0.8669
0.3576	22.0	4950	0.3244	0.8602
0.3535	23.0	5175	0.3229	0.8652
0.3392	24.0	5400	0.3212	0.8636
0.3203	25.0	5625	0.3258	0.8569
0.3082	26.0	5850	0.3176	0.8652
0.273	27.0	6075	0.3142	0.8652
0.2914	28.0	6300	0.3128	0.8652
0.2752	29.0	6525	0.3158	0.8602
0.2968	30.0	6750	0.3177	0.8602
0.286	31.0	6975	0.3206	0.8586
0.2639	32.0	7200	0.3171	0.8619
0.3029	33.0	7425	0.3130	0.8652
0.2671	34.0	7650	0.3120	0.8636
0.2568	35.0	7875	0.3117	0.8652
0.291	36.0	8100	0.3108	0.8669
0.2853	37.0	8325	0.3128	0.8669
0.2438	38.0	8550	0.3121	0.8652
0.2575	39.0	8775	0.3073	0.8702
0.2608	40.0	9000	0.3102	0.8652
0.2156	41.0	9225	0.3132	0.8686
0.2705	42.0	9450	0.3087	0.8669
0.2268	43.0	9675	0.3074	0.8702
0.2401	44.0	9900	0.3088	0.8686
0.2744	45.0	10125	0.3055	0.8702
0.2462	46.0	10350	0.3088	0.8719
0.2575	47.0	10575	0.3071	0.8702
0.254	48.0	10800	0.3073	0.8686
0.2358	49.0	11025	0.3080	0.8686
0.216	50.0	11250	0.3078	0.8686

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_3x_beit_base_sgd_001_fold2

smids_3x_beit_base_sgd_001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_beit_base_sgd_001_fold2