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
0.443	1.0	13	0.3769
0.4377	2.0	26	0.3768
0.4645	3.0	39	0.3765
0.4371	4.0	52	0.3762
0.4223	5.0	65	0.3760
0.4468	6.0	78	0.3757
0.4323	7.0	91	0.3755
0.426	8.0	104	0.3754
0.4324	9.0	117	0.3753
0.4144	10.0	130	0.3752
0.435	11.0	143	0.3752
0.4567	12.0	156	0.3751
0.4316	13.0	169	0.3751
0.4572	14.0	182	0.3750
0.4493	15.0	195	0.3750

Swap6/flan-t5-base

flan-t5-base