learning_rate: 0.0005
train_batch_size: 16
eval_batch_size: 16
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
lr_scheduler_warmup_steps: 500
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss
No log	1.0	68	3.6423
4.394	2.0	136	2.7034
2.7578	3.0	204	2.2173
2.7578	4.0	272	2.0253
2.112	5.0	340	1.9120
1.8785	6.0	408	1.8537
1.8785	7.0	476	1.8738
1.7411	8.0	544	1.8045
1.6493	9.0	612	1.7871
1.6493	10.0	680	1.6829
1.4582	11.0	748	1.6645
1.3147	12.0	816	1.5850
1.3147	13.0	884	1.5597
1.1129	14.0	952	1.5595
0.9816	15.0	1020	1.5482

bashyaldhiraj2067/delete_nepali-char-t5-gec

delete_nepali-char-t5-gec