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: 9030

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.8734	0.1	903	0.4407	0.9340
0.1847	1.1001	1807	0.0499	0.9851
0.0493	2.1	2710	0.0379	0.9900
0.0795	3.1001	3614	0.0706	0.9763
0.0397	4.1	4517	0.0437	0.9925
0.0008	5.1001	5421	0.0485	0.9913
0.0191	6.1	6324	0.0326	0.9913
0.0513	7.1001	7228	0.0362	0.9925
0.0009	8.1	8131	0.0435	0.9938
0.0022	9.0995	9030	0.0261	0.9950

Shawon16/ViViT_default_fold__3__10_epoch_Aug_batch_2_4_BdSLW60

ViViT_default_fold__3__10_epoch_Aug_batch_2_4_BdSLW60