OpenRLHF
/

Llama-3-8b-iter-dpo-179k

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

chuyi777 commited on Jul 13, 2024

Commit

7a433bb

·

verified ·

1 Parent(s): 0121069

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -11,4 +11,5 @@ Learning Rate: 5e-7
 Beta: 0.1
 Scheduler: Cosine with Warmup and MinLR
 Rollout Batch Size: 20000
 ```

 Beta: 0.1
 Scheduler: Cosine with Warmup and MinLR
 Rollout Batch Size: 20000
+Number of Iterations: 9
 ```