learning_rate: 0.001
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	9.1803
9.3683	2.0	14	9.1743
9.2102	3.0	21	9.0925
9.2102	4.0	28	8.9160
9.1206	5.0	35	8.8353
9.1677	6.0	42	8.8664
9.1677	7.0	49	8.8229
9.0556	8.0	56	8.9306
8.891	9.0	63	8.8649
9.0597	10.0	70	8.8148
9.0597	11.0	77	8.8811
9.0373	12.0	84	8.9017
8.8946	13.0	91	8.8119
8.8946	14.0	98	8.8853
9.0261	15.0	105	8.8301

Joshikaa/flan-t5-base

flan-t5-base