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: 1.1444
Accuracy: 0.8217

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
0.9503	1.0	225	0.9116	0.5117
0.9706	2.0	450	0.9826	0.46
0.8	3.0	675	0.8216	0.55
0.7869	4.0	900	0.7274	0.6417
0.7386	5.0	1125	0.7210	0.65
0.6956	6.0	1350	0.8161	0.6183
0.8586	7.0	1575	0.7427	0.6283
0.6974	8.0	1800	0.7391	0.6467
0.6497	9.0	2025	0.6781	0.665
0.665	10.0	2250	0.6784	0.69
0.6749	11.0	2475	0.6355	0.7083
0.6727	12.0	2700	0.6116	0.7083
0.6759	13.0	2925	0.6229	0.715
0.6034	14.0	3150	0.6562	0.685
0.5372	15.0	3375	0.5788	0.755
0.539	16.0	3600	0.5524	0.7583
0.5144	17.0	3825	0.5824	0.7483
0.4796	18.0	4050	0.5455	0.7617
0.5096	19.0	4275	0.5692	0.765
0.4664	20.0	4500	0.5893	0.7533
0.3623	21.0	4725	0.5578	0.745
0.3075	22.0	4950	0.5688	0.7867
0.3806	23.0	5175	0.5983	0.7633
0.4403	24.0	5400	0.4856	0.8017
0.3263	25.0	5625	0.4951	0.8083
0.4298	26.0	5850	0.5186	0.8067
0.3696	27.0	6075	0.5017	0.8017
0.3505	28.0	6300	0.5055	0.805
0.2809	29.0	6525	0.5401	0.81
0.2639	30.0	6750	0.5378	0.8083
0.1827	31.0	6975	0.5714	0.815
0.2309	32.0	7200	0.5483	0.8167
0.2167	33.0	7425	0.5706	0.7967
0.1201	34.0	7650	0.6703	0.8117
0.1274	35.0	7875	0.7662	0.7917
0.1115	36.0	8100	0.6767	0.8183
0.1604	37.0	8325	0.8509	0.8083
0.0668	38.0	8550	0.7497	0.8233
0.1178	39.0	8775	0.8497	0.8067
0.0788	40.0	9000	0.9494	0.8033
0.0775	41.0	9225	0.9252	0.81
0.1033	42.0	9450	0.9696	0.8217
0.0903	43.0	9675	0.9856	0.8133
0.037	44.0	9900	1.0200	0.81
0.019	45.0	10125	1.1824	0.8067
0.0484	46.0	10350	1.0838	0.8183
0.0259	47.0	10575	1.1218	0.8083
0.0077	48.0	10800	1.1617	0.8133
0.0106	49.0	11025	1.1590	0.8117
0.0158	50.0	11250	1.1444	0.8217

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_3x_beit_base_rms_001_fold5

smids_3x_beit_base_rms_001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_beit_base_rms_001_fold5