learning_rate: 5e-05
train_batch_size: 50
eval_batch_size: 16
seed: 42
optimizer: Use 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: 15
mixed_precision_training: Native AMP

Epoch	Step	Validation Loss	Rouge2 Precision	Rouge2 Recall	Rouge2 Fmeasure
1.0	1296	nan	0.0021	0.0009	0.0013
2.0	2592	nan	0.0021	0.0009	0.0013
3.0	3888	nan	0.0021	0.0009	0.0013
4.0	5184	nan	0.0021	0.0009	0.0013
5.0	6480	nan	0.0021	0.0009	0.0013
6.0	7776	nan	0.0021	0.0009	0.0013
7.0	9072	nan	0.0021	0.0009	0.0013
8.0	10368	nan	0.0021	0.0009	0.0013
9.0	11664	nan	0.0021	0.0009	0.0013
10.0	12960	nan	0.0021	0.0009	0.0013
11.0	14256	nan	0.0021	0.0009	0.0013
12.0	15552	nan	0.0021	0.0009	0.0013
13.0	16848	nan	0.0021	0.0009	0.0013
14.0	18144	nan	0.0021	0.0009	0.0013
15.0	19440	nan	0.0021	0.0009	0.0013

e22vvb/mt5_base_TH_wiki

mt5_base_TH_wiki