diff --git a/README.md b/README.md
index 4e7907417b54b5764b862482dbc10097e16b0e22..ddf5b8630cedfd7b340772ad6362c805a0e08d52 100644
--- a/README.md
+++ b/README.md
@@ -36,7 +36,7 @@ push_to_hub(
 After identifying with the command : `huggingface-cli login`
 
 ## Weights & Biases
-The run of the model is [here](https://wandb.ai/ghelfi/cartpole-training/runs/06exlpbm).
+The run of the model is [here](https://wandb.ai/ghelfi/cartpole-training/runs/t95xgk54).
 
 Realized with the code below: 
 ```
@@ -59,8 +59,7 @@ while True:
     if done:
         break
 
-print("Mean Reward: ", np.mean(rewards))
-wandb.log({'reward_mean': np.mean(rewards)})
+wandb.log({'rewards': np.sum(rewards)})
 ```