oilyshelf
/

gemma-2-27b-epfl-pre-trained-4bit

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

oilyshelf commited on Oct 14

Commit

da21a0c

•

1 Parent(s): 22442a6

End of training

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- training_steps: 20
 - mixed_precision_training: Native AMP
 ### Training results

 - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 ### Training results