learning_rate: 1e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_steps: 750
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss
1.7899	1.0	54	1.6850
1.7335	2.0	108	1.5802
1.593	3.0	162	1.3848
1.3898	4.0	216	1.2504
1.2958	5.0	270	1.2021
1.258	6.0	324	1.1684
1.2047	7.0	378	1.1390
1.1975	8.0	432	1.1171
1.1593	9.0	486	1.0993
1.1221	10.0	540	1.0846
1.1018	11.0	594	1.0704
1.0643	12.0	648	1.0574
1.0284	13.0	702	1.0463
1.0013	14.0	756	1.0364
0.9785	15.0	810	1.0276
0.9346	16.0	864	1.0203
0.9385	17.0	918	1.0184
0.92	18.0	972	1.0168
0.9074	19.0	1026	1.0151
0.8907	20.0	1080	1.0151

touno/english_to_taglish_8483_v2

english_to_taglish_8483_v2