| # Manually select `target_modules` to avoid 'all-linear' selecting 'gate' | |
| CUDA_VISIBLE_DEVICES=0,1 \ | |
| swift sft \ | |
| --model Qwen/Qwen2-57B-A14B-Instruct \ | |
| --train_type lora \ | |
| --dataset 'AI-ModelScope/alpaca-gpt4-data-zh#500' \ | |
| 'AI-ModelScope/alpaca-gpt4-data-en#500' \ | |
| 'swift/self-cognition#500' \ | |
| --torch_dtype bfloat16 \ | |
| --num_train_epochs 1 \ | |
| --per_device_train_batch_size 1 \ | |
| --per_device_eval_batch_size 1 \ | |
| --learning_rate 1e-4 \ | |
| --lora_rank 8 \ | |
| --lora_alpha 32 \ | |
| --target_modules q_proj k_proj v_proj o_proj gate_proj up_proj down_proj \ | |
| --gradient_accumulation_steps 16 \ | |
| --eval_steps 50 \ | |
| --save_steps 50 \ | |
| --save_total_limit 2 \ | |
| --logging_steps 5 \ | |
| --max_length 2048 \ | |
| --output_dir output \ | |
| --system 'You are a helpful assistant.' \ | |
| --warmup_ratio 0.05 \ | |
| --dataloader_num_workers 4 \ | |
| --model_author swift \ | |
| --model_name swift-robot | |