psxjp5
/

mt5-small

Text2Text Generation

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

psxjp5 commited on Aug 11, 2023

Commit

6582fd0

•

1 Parent(s): 3c0c29c

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -97,7 +97,8 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 20
-- weight_decay = 0.007
 ### Training results

 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 20
+- weight_decay: 0.007
+- dropout: 0.4
 ### Training results