update Read.me

README.md

@@ -11,4 +11,31 @@ tags:
 - HH-RLHF
 - PPO
 - lama-1.3B
----
+---
+
+# RLHF with ppo_Trainer and Lora
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c0be34e175dd56a57151ca/piXU-OqDgrBKs7qR7fICw.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c0be34e175dd56a57151ca/OXD2TqlQQY9NuC7JTiv_H.png)
+
+# Hyperparameter
+
+#ppo
+  learning_rate=5e-6,
+  batch_size=32,
+  mini_batch_size=1,
+  horizon=10000,
+  cliprange =0.2,
+  cliprange_value=0.2,
+  lam=0.95,
+  target_kl=2,
+  use_score_scaling = True,
+  log_with='wandb'
+
+#lora
+  r=16,
+  lora_alpha=32,
+  lora_dropout=0.05,
+  bias="none",
+  task_type="CAUSAL_LM",