Sam137
/

deepseek6.7-summarize-coder

Generated from Trainer

Model card Files Files and versions Community

Sam137 commited on Aug 18

Commit

6b295d6

•

1 Parent(s): 5f4a97c

Model save

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -32,12 +32,12 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
 - train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
-- lr_scheduler_type: cosine_with_restarts
 - lr_scheduler_warmup_steps: 400
 - num_epochs: 2

 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 0.0005
 - train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 400
 - num_epochs: 2