wehub-resource-sync
30 lines
881 B
Bash
30 lines
881 B
Bash
# 42GB
|
|
# https://github.com/modelscope/ms-swift/pull/5277
|
|
CUDA_VISIBLE_DEVICES=0 \
|
|
swift sft \
|
|
--model openai-mirror/gpt-oss-20b \
|
|
--tuner_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 \
|
|
--router_aux_loss_coef 1e-3 \
|
|
--learning_rate 1e-4 \
|
|
--lora_rank 8 \
|
|
--lora_alpha 32 \
|
|
--target_modules all-linear \
|
|
--gradient_accumulation_steps 16 \
|
|
--eval_steps 50 \
|
|
--save_steps 50 \
|
|
--save_total_limit 2 \
|
|
--logging_steps 5 \
|
|
--max_length 2048 \
|
|
--output_dir output \
|
|
--warmup_ratio 0.05 \
|
|
--dataloader_num_workers 4 \
|
|
--model_author swift \
|
|
--model_name swift-robot
|