#!/bin/bash

CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
    --stage ppo \
    --do_train \
    --model_name_or_path meta-llama/Llama-2-7b-hf \
    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
    --create_new_adapter \
    --dataset alpaca_gpt4_en \
    --dataset_dir ../../data \
    --template default \
    --finetuning_type lora \
    --lora_target q_proj,v_proj \
    --reward_model ../../saves/LLaMA2-7B/lora/reward \
    --output_dir ../../saves/LLaMA2-7B/lora/ppo \
    --overwrite_cache \
    --overwrite_output_dir \
    --cutoff_len 512 \
    --preprocessing_num_workers 16 \
    --per_device_train_batch_size 1 \
    --gradient_accumulation_steps 8 \
    --lr_scheduler_type cosine \
    --logging_steps 10 \
    --save_steps 100 \
    --learning_rate 1e-5 \
    --num_train_epochs 1.0 \
    --max_samples 1000 \
    --top_k 0 \
    --top_p 0.9 \
    --max_new_tokens 256 \
    --plot_loss \
    --fp16