Update README.md

README.md

@@ -67,4 +67,5 @@ The original dataset contains over 50 million rows of completions (chatbot respo
 </figure>
 
 ### Training procedure
-The `gpt2_base_retry_and_continue_5m_reward_model` was trained using a [gpt2](https://huggingface.co/gpt2) base model and a classification head with single output. Binary Cross Entropy loss was used. The model was trained on 4xA40 GPUs, 16 per device batch size and gradient accumulation of 1 (therefore the effective batch size is 64), with 1e-5 learning rate for 2 epochs for a total of 156,240 steps. Tensor parallelism and pipeline parallelism were used to distribute the model across GPUs.
+The `gpt2_base_retry_and_continue_5m_reward_model` was trained using a [gpt2](https://huggingface.co/gpt2) base model and a classification head with single output. Binary Cross Entropy loss was used. The model was trained on 4xA40 GPUs, 16 per device batch size and gradient accumulation of 1 (therefore the effective batch size is 64), with 1e-5 learning rate for 2 epochs for a total of 156,240 steps. Tensor parallelism and pipeline parallelism were used to distribute the model across GPUs.
+[Weights and Biases Log](https://wandb.ai/jellywibble/reward)