lucy666
/

llama3.1-8B-Fine-tuned

Generated from Trainer

Model card Files Files and versions Community

lucy666 commited on Aug 16

Commit

b37e95b

•

1 Parent(s): 172b8de

Model save

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- training_steps: 10
 - mixed_precision_training: Native AMP
 ### Training results

 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
+- training_steps: 300
 - mixed_precision_training: Native AMP
 ### Training results