learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 1
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	9693	nan	0.006	0.0021	0.0027
2.0	19386	nan	0.006	0.0021	0.0027
3.0	29079	nan	0.006	0.0021	0.0027
4.0	38772	nan	0.006	0.0021	0.0027
5.0	48465	nan	0.006	0.0021	0.0027
6.0	58158	nan	0.006	0.0021	0.0027
7.0	67851	nan	0.006	0.0021	0.0027
8.0	77544	nan	0.006	0.0021	0.0027
9.0	87237	nan	0.006	0.0021	0.0027
10.0	96930	nan	0.006	0.0021	0.0027
11.0	106623	nan	0.006	0.0021	0.0027
12.0	116316	nan	0.006	0.0021	0.0027
13.0	126009	nan	0.006	0.0021	0.0027
14.0	135702	nan	0.006	0.0021	0.0027
15.0	145395	nan	0.006	0.0021	0.0027

e22vvb/mt5-base_TH_spider

mt5-base_TH_spider