Update README.md

README.md

@@ -68,13 +68,15 @@ The model was trained on [@borisdayma's tweets](https://twitter.com/borisdayma).
 </tbody>
 </table>
 
-[Explore the data](https://app.wandb.ai/wandb/huggingtweets-dev/runs/1gw8etu0/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
+[Explore the data](https://app.wandb.ai/wandb/huggingtweets-dev/runs/3tgyy752/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 
 ## Training procedure
 
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @borisdayma's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets-dev/runs/2db9ywak) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets-dev/runs/2g6tg8tv) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets-dev/runs/2g6tg8tv/artifacts)) is logged and versioned.
 
 ## Intended uses & limitations