Update README.md

README.md

@@ -80,9 +80,10 @@ your desired response length:
 ![settings](https://files.catbox.moe/6lcz0u.png)
 
 ## Training procedure
-[Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training.
-The model has been trained as a 4-bit LoRA adapter. It's so large because a LoRA rank
-of 256 was used. It's suggested to merge it to the base Llama2-7B model.
+[Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
+on a single NVidia RTX3090 GPU. The model has been trained as a 4-bit LoRA adapter, which
+is so large because a LoRA rank of 256 was used. It's suggested to merge the adapter to
+the base Llama2-7B model (or other Llama2-based models).
 
 ### Training hyperparameters
 For the first pass these settings were used:
@@ -106,5 +107,6 @@ In the second pass, the `lora_model_dir` option was used to load and train the a
 previously trained on a stories dataset. These settings were also changed:
 
 - lora_dropout: 0.0
+- micro_batch_size: 1
 - gradient_accumulation_steps: 8
 - learning_rate: 0.0006