File size: 1,051 Bytes
96fe658 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 |
# pip install math_verify # reward function
# pip install -U trl
# GPU memory: 80GiB
# You can set `--reward_model` to use a reward model to provide rewards.
# PTEngine(pytorch) to rollout
CUDA_VISIBLE_DEVICES=0 \
swift rlhf \
--rlhf_type grpo \
--model Qwen/Qwen2.5-7B \
--reward_funcs accuracy format \
--train_type lora \
--lora_rank 8 \
--lora_alpha 32 \
--target_modules all-linear \
--torch_dtype bfloat16 \
--dataset 'AI-MO/NuminaMath-TIR#1000' \
--max_completion_length 1024 \
--num_train_epochs 1 \
--per_device_train_batch_size 4 \
--per_device_eval_batch_size 4 \
--learning_rate 1e-5 \
--gradient_accumulation_steps 1 \
--eval_steps 100 \
--save_steps 100 \
--save_total_limit 2 \
--logging_steps 5 \
--max_length 2048 \
--output_dir output \
--warmup_ratio 0.05 \
--dataloader_num_workers 4 \
--dataset_num_proc 4 \
--num_generations 4 \
--temperature 0.9 \
--system 'examples/train/grpo/prompt.txt' \
--log_completions true
|