learning_rate: 0.0002
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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: linear
num_epochs: 1
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
1.9423	0.0703	500	1.7860
1.8964	0.1405	1000	1.7491
1.8636	0.2108	1500	1.7210
1.8715	0.2811	2000	1.7103
1.8336	0.3513	2500	1.7005
1.8521	0.4216	3000	1.6903
1.7806	0.4919	3500	1.6823
1.8209	0.5622	4000	1.6788
1.8205	0.6324	4500	1.6714
1.8183	0.7027	5000	1.6670
1.8176	0.7730	5500	1.6664
1.8072	0.8432	6000	1.6653
1.785	0.9135	6500	1.6637
1.8074	0.9838	7000	1.6629

lamdoanh2468/new-vit5-fast

new-vit5-fast