#!/bin/bash
# use `--tokenized_path` in training script to load data

CUDA_VISIBLE_DEVICES= llamafactory-cli train \
    --stage sft \
    --do_train \
    --model_name_or_path meta-llama/Llama-2-7b-hf \
    --dataset alpaca_gpt4_en,glaive_toolcall \
    --dataset_dir ../../data \
    --template default \
    --finetuning_type lora \
    --lora_target q_proj,v_proj \
    --output_dir ../../saves/LLaMA2-7B/lora/sft \
    --overwrite_cache \
    --overwrite_output_dir \
    --cutoff_len 1024 \
    --preprocessing_num_workers 16 \
    --max_samples 3000 \
    --tokenized_path ../../saves/datasets/sft