learning_rate: 0.0003
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_steps: 256
num_epochs: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0668	0.5	64	2.0394	0.2315
1.9552	1.0	128	1.8918	0.4732
1.7698	1.5	192	1.7030	0.5503
1.5743	2.0	256	1.5134	0.5906
1.407	2.5	320	1.3642	0.6141
1.2913	3.0	384	1.2665	0.6141
1.2168	3.5	448	1.2017	0.6342
1.1533	4.0	512	1.1555	0.6376
1.1233	4.5	576	1.1270	0.6477
1.0956	5.0	640	1.1135	0.6745
1.0896	5.5	704	1.1057	0.6745
1.0753	6.0	768	1.1023	0.6779
1.0847	6.5	832	1.0877	0.6879
1.032	7.0	896	1.0350	0.7047
1.0147	7.5	960	0.9967	0.6980
0.9511	8.0	1024	0.9739	0.7013
0.9373	8.5	1088	0.9508	0.7013
0.9326	9.0	1152	0.9413	0.7114
0.9241	9.5	1216	0.9334	0.7181
0.903	10.0	1280	0.9299	0.7215
0.9152	10.5	1344	0.9290	0.7215
0.8964	11.0	1408	0.9093	0.7349
0.8792	11.5	1472	0.8971	0.7248
0.8604	12.0	1536	0.8656	0.7416
0.8454	12.5	1600	0.8580	0.7416
0.8219	13.0	1664	0.8458	0.7416
0.8147	13.5	1728	0.8380	0.7483
0.8137	14.0	1792	0.8352	0.7416
0.8032	14.5	1856	0.8339	0.7450
0.8118	15.0	1920	0.8337	0.7416

SodaXII/convnextv2-base-1k-224_rice-leaf-disease-augmented-v4_tl

convnextv2-base-1k-224_rice-leaf-disease-augmented-v4_tl