learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
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
lr_scheduler_warmup_steps: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
3.1043	0.9942	151	2.9472
2.8353	1.9942	302	2.7468
2.8157	2.9942	453	2.6553
2.6871	3.9942	604	2.5978
2.7011	4.9942	755	2.5583
2.6723	5.9942	906	2.5332
2.5578	6.9942	1057	2.5225
2.7176	7.9942	1208	2.5076
2.6958	8.9942	1359	2.5055
2.6155	9.9942	1510	2.5028

Ayushi26/t5-largedata

t5-largedata