llama3-8B-Agent-Lora-adapter

Llama-3-8B-Agent

This Adapter is fine-tune from meta-llama/Meta-Llama-3-8B-Instruct using LLaMA-Factory

Environment

LLaMA-Factory Commit Version: db7f3b9784d21ef5c18a11679ad995bb97d61f7c

GPU RTX-4090 24G 单卡

Python 310

Training hyperparameters

Please ensure FA2 installed

CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
    --stage sft \
    --do_train \
    --model_name_or_path /data/models/Meta-Llama-3-8B-Instruct \
    --dataset alpaca_gpt4_zh,glaive_toolcall \
    --dataset_dir data \
    --template llama3 \
    --finetuning_type lora \
    --lora_target all \
    --output_dir saves/LLaMA3-8B/lora/sft \
    --overwrite_cache \
    --overwrite_output_dir \
    --cutoff_len 8192 \
    --preprocessing_num_workers 16 \
    --per_device_train_batch_size 1 \
    --per_device_eval_batch_size 2 \
    --gradient_accumulation_steps 8 \
    --lr_scheduler_type cosine \
    --logging_steps 10 \
    --warmup_steps 20 \
    --save_steps 1000 \
    --eval_steps 1000 \
    --max_samples 6000 \
    --evaluation_strategy steps \
    --load_best_model_at_end \
    --learning_rate 5e-6 \
    --num_train_epochs 3.0 \
    --val_size 0.1 \
    --plot_loss \
    --fp16 \
    --flash_attn

training loss

example