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: 0.5470
Accuracy: 0.7833

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
1.227	1.0	225	1.2590	0.3417
1.1831	2.0	450	1.2003	0.3717
1.084	3.0	675	1.1460	0.4017
1.0157	4.0	900	1.0941	0.42
0.9735	5.0	1125	1.0438	0.455
0.9436	6.0	1350	0.9975	0.4917
0.9179	7.0	1575	0.9541	0.5333
0.8784	8.0	1800	0.9154	0.5717
0.884	9.0	2025	0.8784	0.595
0.8367	10.0	2250	0.8446	0.6217
0.8299	11.0	2475	0.8151	0.6483
0.7845	12.0	2700	0.7879	0.6617
0.7765	13.0	2925	0.7642	0.6667
0.7469	14.0	3150	0.7428	0.6783
0.7257	15.0	3375	0.7247	0.69
0.6997	16.0	3600	0.7073	0.7
0.7213	17.0	3825	0.6920	0.7083
0.698	18.0	4050	0.6780	0.7183
0.7064	19.0	4275	0.6649	0.7217
0.6988	20.0	4500	0.6533	0.735
0.6396	21.0	4725	0.6426	0.7383
0.6558	22.0	4950	0.6328	0.7483
0.6628	23.0	5175	0.6239	0.75
0.6417	24.0	5400	0.6165	0.7533
0.6414	25.0	5625	0.6079	0.7517
0.6773	26.0	5850	0.6018	0.7567
0.662	27.0	6075	0.5968	0.7583
0.6119	28.0	6300	0.5913	0.765
0.6058	29.0	6525	0.5864	0.765
0.5469	30.0	6750	0.5816	0.7683
0.6085	31.0	6975	0.5777	0.7667
0.557	32.0	7200	0.5744	0.7667
0.5975	33.0	7425	0.5708	0.7683
0.5747	34.0	7650	0.5675	0.7717
0.6075	35.0	7875	0.5645	0.7717
0.5661	36.0	8100	0.5618	0.7733
0.5862	37.0	8325	0.5597	0.7733
0.5867	38.0	8550	0.5581	0.775
0.5414	39.0	8775	0.5562	0.7767
0.5431	40.0	9000	0.5546	0.775
0.5693	41.0	9225	0.5532	0.7767
0.5499	42.0	9450	0.5518	0.7783
0.5959	43.0	9675	0.5505	0.78
0.6402	44.0	9900	0.5495	0.78
0.5702	45.0	10125	0.5486	0.7817
0.5765	46.0	10350	0.5481	0.7833
0.6208	47.0	10575	0.5477	0.7833
0.5613	48.0	10800	0.5473	0.7833
0.6326	49.0	11025	0.5471	0.7833
0.5777	50.0	11250	0.5470	0.7833

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_0001_fold5

smids_3x_beit_base_sgd_0001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_beit_base_sgd_0001_fold5