Update README.md

README.md

@@ -47,11 +47,14 @@ Character: {utterance}
 - `User` and `Character` should be replaced with appropriate names.
 
 
-## Training Hyperparameters
+## 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.
 
+### Training hyperparameters
+For both passes these settings were used:
+
 - learning_rate: 0.0002
 - lr_scheduler_type: constant
 - lora_r: 256
@@ -67,5 +70,5 @@ of 256 was used. It's suggested to merge it to the base Llama2-7B model.
 - gradient_accumulation_steps: 1
 - optimizer: adamw_torch
 
-For the multi-stage training, the `lora_model_dir` option was used to load and train the
-previously created adapter.
+In the second pass, the `lora_model_dir` option was used to load and train the adapter
+previously trained on a stories dataset.