learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 18560
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
3.1124	0.0501	929	1.5155	0.705	0.7529	0.705	0.6760
0.1216	1.0501	1858	0.6576	0.8167	0.8197	0.8167	0.7920
0.0048	2.0501	2787	0.4630	0.86	0.8868	0.86	0.8338
0.0086	3.0501	3716	0.4305	0.8733	0.8927	0.8733	0.8600
0.2527	4.0501	4645	1.0763	0.755	0.8136	0.755	0.7172
0.0681	5.0501	5574	0.7836	0.8283	0.8202	0.8283	0.8002
0.0256	6.0501	6503	0.7197	0.8333	0.8667	0.8333	0.8153
0.064	7.0501	7432	0.6918	0.8533	0.8730	0.8533	0.8374
0.0001	8.0501	8361	0.6841	0.86	0.8823	0.86	0.8452

Shawon16/ViViT_BdSLW60_FrameRate_Corrected_without_Augment_20_epch

ViViT_BdSLW60_FrameRate_Corrected_without_Augment_20_epch