Quanwei Tang
Quanwei Tang
Traceback (most recent call last): File "/usr/local/python3.10.15/lib/python3.10/site-packages/swift/cli/sft.py", line 7, in sft_main() File "/usr/local/python3.10.15/lib/python3.10/site-packages/swift/llm/train/sft.py", line 267, in sft_main return SwiftSft(args).main() File "/usr/local/python3.10.15/lib/python3.10/site-packages/swift/llm/train/sft.py", line 27, in __init__ super().__init__(args) File "/usr/local/python3.10.15/lib/python3.10/site-packages/swift/llm/base.py", line 19,...
ASCEND_RT_VISIBLE_DEVICES=0,1 NPROC_PER_NODE=2 swift sft \ ... --train_type full \ --torch_dtype bfloat16 \ --num_train_epochs 2 \ --per_device_train_batch_size 1 \ --per_device_eval_batch_size 1 \ --device_map auto \ --learning_rate 1e-4 \ --target_modules all-linear \...