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: 0.9950
Accuracy: 0.9052

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
0.2499	1.0	375	0.2304	0.9185
0.1775	2.0	750	0.2550	0.9018
0.1217	3.0	1125	0.4013	0.8869
0.0433	4.0	1500	0.5189	0.8819
0.0358	5.0	1875	0.4893	0.8985
0.0375	6.0	2250	0.5725	0.9052
0.0405	7.0	2625	0.5904	0.9101
0.012	8.0	3000	0.7002	0.9018
0.0053	9.0	3375	0.7065	0.9052
0.0037	10.0	3750	0.7485	0.8985
0.0126	11.0	4125	0.7919	0.8985
0.0005	12.0	4500	0.7919	0.8968
0.0159	13.0	4875	0.8564	0.8902
0.0001	14.0	5250	0.8426	0.8852
0.0002	15.0	5625	0.8433	0.8918
0.0148	16.0	6000	0.7634	0.9018
0.0208	17.0	6375	0.8403	0.8952
0.0001	18.0	6750	0.8471	0.9018
0.0491	19.0	7125	0.8371	0.9035
0.0	20.0	7500	0.7423	0.9052
0.0126	21.0	7875	0.8759	0.8935
0.0008	22.0	8250	0.8648	0.9002
0.0	23.0	8625	0.9554	0.9002
0.0005	24.0	9000	0.9755	0.8918
0.0184	25.0	9375	0.9160	0.8918
0.0	26.0	9750	0.9691	0.8918
0.0	27.0	10125	0.8701	0.8968
0.0002	28.0	10500	0.7677	0.9035
0.0001	29.0	10875	0.9258	0.9035
0.0033	30.0	11250	0.9080	0.9002
0.0045	31.0	11625	1.0210	0.8935
0.0045	32.0	12000	0.9883	0.8985
0.0017	33.0	12375	0.8984	0.9035
0.0	34.0	12750	0.8844	0.9101
0.0007	35.0	13125	0.9085	0.8918
0.0002	36.0	13500	0.9790	0.9035
0.0	37.0	13875	1.0705	0.8985
0.0	38.0	14250	1.0172	0.9035
0.0	39.0	14625	1.0259	0.9052
0.0032	40.0	15000	1.0712	0.9018
0.0	41.0	15375	1.0107	0.9002
0.0025	42.0	15750	1.0002	0.9068
0.0023	43.0	16125	1.0032	0.9035
0.003	44.0	16500	0.9837	0.9052
0.0018	45.0	16875	1.0127	0.9035
0.0	46.0	17250	0.9843	0.9068
0.0056	47.0	17625	1.0283	0.9002
0.0033	48.0	18000	1.0135	0.9052
0.0031	49.0	18375	0.9997	0.9052
0.0025	50.0	18750	0.9950	0.9052

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_beit_base_rms_00001_fold2

smids_5x_beit_base_rms_00001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_beit_base_rms_00001_fold2