learning_rate: 1e-08
train_batch_size: 4
eval_batch_size: 4
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: linear
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss
0.7014	1.0	18	0.3952
0.6857	2.0	36	0.3952
0.6964	3.0	54	0.3952
0.6941	4.0	72	0.3952
0.6533	5.0	90	0.3952
0.6713	6.0	108	0.3952
0.7016	7.0	126	0.3952
0.6409	8.0	144	0.3952
0.6611	9.0	162	0.3952
0.683	10.0	180	0.3952
0.6567	11.0	198	0.3952
0.7313	12.0	216	0.3952
0.6923	13.0	234	0.3952
0.7162	14.0	252	0.3952
0.7108	15.0	270	0.3952

Chiranjeevisai18/flan-t5-base

flan-t5-base