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: 0.7867

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
1.2271	1.0	225	1.2660	0.34
1.1764	2.0	450	1.2039	0.36
1.0866	3.0	675	1.1482	0.3833
1.02	4.0	900	1.0954	0.41
0.9521	5.0	1125	1.0436	0.4433
0.9373	6.0	1350	0.9954	0.485
0.8962	7.0	1575	0.9512	0.5317
0.8694	8.0	1800	0.9106	0.5767
0.8253	9.0	2025	0.8739	0.5967
0.8297	10.0	2250	0.8416	0.635
0.8158	11.0	2475	0.8130	0.6633
0.75	12.0	2700	0.7869	0.685
0.7851	13.0	2925	0.7633	0.69
0.761	14.0	3150	0.7425	0.7017
0.6927	15.0	3375	0.7233	0.7117
0.7078	16.0	3600	0.7069	0.7217
0.698	17.0	3825	0.6913	0.7283
0.6847	18.0	4050	0.6778	0.7367
0.6863	19.0	4275	0.6656	0.7383
0.6396	20.0	4500	0.6548	0.7417
0.6511	21.0	4725	0.6448	0.745
0.6297	22.0	4950	0.6350	0.7517
0.6013	23.0	5175	0.6267	0.755
0.635	24.0	5400	0.6187	0.76
0.6174	25.0	5625	0.6116	0.7583
0.6201	26.0	5850	0.6053	0.7617
0.5888	27.0	6075	0.5991	0.7617
0.5833	28.0	6300	0.5934	0.7633
0.6387	29.0	6525	0.5887	0.7683
0.5339	30.0	6750	0.5839	0.7717
0.5756	31.0	6975	0.5797	0.7767
0.6386	32.0	7200	0.5758	0.775
0.6245	33.0	7425	0.5722	0.775
0.5779	34.0	7650	0.5690	0.7767
0.57	35.0	7875	0.5661	0.7767
0.5776	36.0	8100	0.5632	0.7767
0.5861	37.0	8325	0.5611	0.7767
0.5518	38.0	8550	0.5586	0.7767
0.604	39.0	8775	0.5567	0.7817
0.539	40.0	9000	0.5549	0.7833
0.5457	41.0	9225	0.5534	0.7833
0.6155	42.0	9450	0.5518	0.785
0.5379	43.0	9675	0.5506	0.785
0.5848	44.0	9900	0.5496	0.7867
0.5814	45.0	10125	0.5488	0.7867
0.5255	46.0	10350	0.5481	0.7867
0.5726	47.0	10575	0.5476	0.7867
0.5762	48.0	10800	0.5473	0.7867
0.6192	49.0	11025	0.5471	0.7867
0.5747	50.0	11250	0.5470	0.7867

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_fold3

smids_3x_beit_base_sgd_0001_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_beit_base_sgd_0001_fold3