File size: 786 Bytes
cb2428f |
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 |
nproc_per_node=2
CUDA_VISIBLE_DEVICES=0,1 \
NPROC_PER_NODE=$nproc_per_node \
swift rlhf \
--rlhf_type orpo \
--model Qwen/Qwen2.5-7B-Instruct \
--train_type lora \
--dataset hjh0119/shareAI-Llama3-DPO-zh-en-emoji \
--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 all-linear \
--gradient_accumulation_steps $(expr 16 / $nproc_per_node) \
--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 \
--deepspeed zero2 \
--dataset_num_proc 4
|