output_dir: hh-rlhf-gen_pythia2.8b-dpo
dataset_name: "sophiex/hh-rlhf"
model_name: null
lora_model: True
train_split: train[:20000]
batch_size: 4
max_prompt_length: 256
max_new_tokens: 256
temperature: 0.7
top_p: 1.0
dtype: bfloat16