smids_5x_beit_base_rms_00001_fold3

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: 0.9185
• Accuracy: 0.9133

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
0.2283	1.0	375	0.2339	0.9183
0.0993	2.0	750	0.2718	0.9117
0.0737	3.0	1125	0.3409	0.9133
0.0242	4.0	1500	0.3831	0.92
0.0583	5.0	1875	0.4502	0.915
0.0327	6.0	2250	0.4867	0.9183
0.0228	7.0	2625	0.5343	0.9333
0.0011	8.0	3000	0.6969	0.91
0.0064	9.0	3375	0.8807	0.89
0.0562	10.0	3750	0.8333	0.9117
0.0104	11.0	4125	0.6930	0.9083
0.0118	12.0	4500	0.8317	0.8933
0.0001	13.0	4875	0.8634	0.9
0.0154	14.0	5250	0.7424	0.9233
0.0231	15.0	5625	0.8048	0.9133
0.0	16.0	6000	0.8245	0.9083
0.0137	17.0	6375	0.7565	0.92
0.0069	18.0	6750	0.7751	0.9183
0.0115	19.0	7125	0.7824	0.9233
0.0051	20.0	7500	0.7691	0.9183
0.0	21.0	7875	0.8067	0.9117
0.0207	22.0	8250	0.7817	0.915
0.0053	23.0	8625	0.8276	0.9083
0.0001	24.0	9000	0.7978	0.9117
0.0169	25.0	9375	0.8806	0.9067
0.0007	26.0	9750	0.8278	0.9267
0.0038	27.0	10125	0.9428	0.9183
0.0	28.0	10500	0.8806	0.9167
0.0	29.0	10875	0.8180	0.91
0.0029	30.0	11250	0.9090	0.9117
0.0	31.0	11625	0.8537	0.9133
0.0002	32.0	12000	0.8596	0.915
0.0003	33.0	12375	0.8995	0.9183
0.0	34.0	12750	0.8853	0.925
0.0	35.0	13125	0.8638	0.9133
0.0	36.0	13500	0.8296	0.9167
0.0	37.0	13875	0.8113	0.9217
0.0	38.0	14250	0.8781	0.92
0.027	39.0	14625	0.8890	0.92
0.0038	40.0	15000	0.8330	0.925
0.0	41.0	15375	0.9306	0.9167
0.0	42.0	15750	0.8569	0.9183
0.0	43.0	16125	0.9060	0.9133
0.0	44.0	16500	0.8854	0.9167
0.0	45.0	16875	0.9021	0.91
0.0001	46.0	17250	0.9154	0.9133
0.0	47.0	17625	0.8802	0.915
0.0	48.0	18000	0.8999	0.915
0.0	49.0	18375	0.9100	0.9117
0.0	50.0	18750	0.9185	0.9133

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2