Hejianping868
/

llama3-8b-sft-qlora-re

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

Hejianping868 commited on Aug 20

Commit

621bf52

•

1 Parent(s): 22c55d2

Model save

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -36,8 +36,8 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant

 The following hyperparameters were used during training:
 - learning_rate: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant