Skip to content

GitLab

Commit f1aa3954 authored by wanglch's avatar wanglch
Browse files

Update finetune_lora_single_gpu.sh

parent e43e75b3
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 2 deletions
finetune/finetune_lora_single_gpu.sh
View file @ f1aa3954
...@@ -13,7 +13,6 @@ export CUDA_VISIBLE_DEVICES=0 ...@@ -13,7 +13,6 @@ export CUDA_VISIBLE_DEVICES=0
python finetune.py \ python finetune.py \
--model_name_or_path $MODEL \ --model_name_or_path $MODEL \
--data_path $DATA \ --data_path $DATA \
--bf16 True \
--fix_vit True \ --fix_vit True \
--output_dir output_qwen \ --output_dir output_qwen \
--num_train_epochs 5 \ --num_train_epochs 5 \
...@@ -34,4 +33,4 @@ python finetune.py \ ...@@ -34,4 +33,4 @@ python finetune.py \
--model_max_length 2048 \ --model_max_length 2048 \
--lazy_preprocess True \ --lazy_preprocess True \
--gradient_checkpointing \ --gradient_checkpointing \
--use_lora --use_lora
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment