learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
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: 100

Training Loss	Epoch	Step	Validation Loss	Chrf++	Gen Len
6.8153	1.9938	444	0.4818	33.9646	122.1124
5.2444	3.9848	888	0.1417	74.6167	126.582
0.6217	5.9758	1332	0.0677	85.3335	132.6539
0.4057	7.9668	1776	0.0613	86.9431	134.4382
0.2987	9.9578	2220	0.0625	88.0924	132.1663
0.2541	11.9488	2664	0.0666	86.4618	133.3775
0.2310	13.9399	3108	0.0727	85.7648	139.1393
0.2057	15.9309	3552	0.0738	87.4594	134.7708

Tsedeniya/finetuned_byT5large_ddo_joint

finetuned_byT5large_ddo_joint