learning_rate: 1e-05
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
No log	1.0	7	43.9465
36.2225	2.0	14	30.9408
37.6802	3.0	21	44.0861
37.6802	4.0	28	27.0898
44.887	5.0	35	29.3322
43.7037	6.0	42	28.2237
43.7037	7.0	49	61.1012
38.833	8.0	56	61.5901
31.3654	9.0	63	42.7828
36.6742	10.0	70	41.9439
36.6742	11.0	77	42.8654
38.0664	12.0	84	41.6465
37.8928	13.0	91	35.5349
37.8928	14.0	98	42.7659
39.185	15.0	105	43.9577

Manjula116/flan-t5-base

flan-t5-base