learning_rate: 5e-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: 20

Training Loss	Epoch	Step	Validation Loss
3.0319	1.0	1215	2.5742
2.8082	2.0	2430	2.4943
2.4514	3.0	3645	2.4608
2.5153	4.0	4860	2.4289
2.6134	5.0	6075	2.4050
2.465	6.0	7290	2.3773
2.4011	7.0	8505	2.3693
2.4235	8.0	9720	2.3578
2.1888	9.0	10935	2.3513
2.2665	10.0	12150	2.3424
2.1565	11.0	13365	2.3363
2.131	12.0	14580	2.3309
2.3443	13.0	15795	2.3249
2.454	14.0	17010	2.3203
2.1481	15.0	18225	2.3209
2.4553	16.0	19440	2.3157
2.1019	17.0	20655	2.3159
2.4616	18.0	21870	2.3141
2.1074	19.0	23085	2.3137
2.2554	20.0	24300	2.3139

Ayushi26/t5-largedata1

t5-largedata1