metadata
license: apache-2.0
Training hyperparameters LoRA: r=16 lora_alpha=16 lora_dropout=0.05 bias="none" task_type="CAUSAL_LM" target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
Training arguments: auto_find_batch_size=True gradient_checkpointing=True learning_rate=5e-7 lr_scheduler_type="cosine" max_steps=3922 optim="paged_adamw_32bit" warmup_steps=100
DPOTrainer: beta=0.1 max_prompt_length=1024 max_length=1536
Arxiv link: https://arxiv.org/abs/2403.02745