update safetensors

eval.py

@@ -19,10 +19,9 @@ if __name__ == "__main__":
     
     agent = PPO.load("model.zip")
 
-    # Save the state dict as a safetensors file
-    policy_state_dict = agent.policy.state_dict()
+    # Save the model as a safetensors file
     save_model(agent.policy, "model.safetensors")
-    
+
     mean_reward, std_reward = evaluate_policy(agent, env, n_eval_episodes=n_eval_episodes, deterministic=deterministic)
     
     print(f"reward : {mean_reward} +/- {std_reward}")

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32f14418431437b7d5f5a4e2ae80b4454939ccaab5cf811387a30409082e8baa
+oid sha256:79b3e4e51bfe3236e98c6ab08e1d19809b6879d64c561e426e0c7b2db7902db3
 size 8978048