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
1.8025	1.0	54	1.6970
1.7482	2.0	108	1.5924
1.6068	3.0	162	1.3961
1.4075	4.0	216	1.2624
1.3085	5.0	270	1.2121
1.2652	6.0	324	1.1755
1.2165	7.0	378	1.1466
1.2033	8.0	432	1.1246
1.1661	9.0	486	1.1065
1.1321	10.0	540	1.0912
1.1071	11.0	594	1.0768
1.071	12.0	648	1.0630
1.0326	13.0	702	1.0514
1.0086	14.0	756	1.0405
0.9863	15.0	810	1.0318
0.9383	16.0	864	1.0258
0.9415	17.0	918	1.0232
0.9261	18.0	972	1.0211
0.9096	19.0	1026	1.0201
0.8966	20.0	1080	1.0203

touno/english_to_taglish_8483

english_to_taglish_8483