learning_rate: 5e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.1
num_epochs: 19
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.9482	1.0	125	1.5012	0.5685
0.9894	2.0	250	0.6444	0.7976
0.3321	3.0	375	0.3859	0.8958
0.1115	4.0	500	0.3081	0.9107
0.0387	5.0	625	0.2980	0.9137
0.0204	6.0	750	0.2936	0.9137
0.0169	7.0	875	0.2953	0.9196
0.0078	8.0	1000	0.3067	0.9226
0.0034	9.0	1125	0.3087	0.9286
0.0025	10.0	1250	0.3139	0.9196
0.0023	11.0	1375	0.3142	0.9196
0.0019	12.0	1500	0.3288	0.9196
0.0013	13.0	1625	0.3359	0.9196
0.001	14.0	1750	0.3413	0.9226
0.0009	15.0	1875	0.3425	0.9226

cvmil/vit-base-patch16-224_augmented-v2_fft

vit-base-patch16-224_rice-leaf-disease-augmented-v2_fft