We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
CUDA_VISIBLE_DEVICES=0 python src/train.py --stage sft --model_name_or_path $base_model_dir --do_train --dataset juben_train --dataset_dir $dataset_dir --template baichuan2 --cutoff_len 512 --finetuning_type lora --lora_target W_pack --output_dir $output_dir --overwrite_output_dir --overwrite_cache --per_device_train_batch_size 16 --gradient_accumulation_steps 1 --lr_scheduler_type cosine --bf16 --double_quant --quantization_bit 4 --quantization_type nf4 --warmup_ratio 0.05 --logging_steps 10 --save_steps 50 --learning_rate 1e-4 --num_train_epochs 10.0 --plot_loss
CUDA_VISIBLE_DEVICES=0 python src/train.py --stage sft --do_predict --model_name_or_path $base_model_dir --adapter_name_or_path $output_dir --dataset_dir $dataset_dir --dataset juben_test --template baichuan2 --finetuning_type lora --output_dir $predict_dir --per_device_eval_batch_size 1 --max_samples 1000 --predict_with_generate --max_length 1024 --generation_max_length 1024 --fp16
模型微调后用于推理,发现生成的generated_predictions_0.jsonl文件中的label这个键的值不全问题
No response
The text was updated successfully, but these errors were encountered:
我也遇到了,我临时用datasets的output代替label了
Sorry, something went wrong.
No branches or pull requests
Reminder
Reproduction
CUDA_VISIBLE_DEVICES=0 python src/train.py
--stage sft
--model_name_or_path $base_model_dir
--do_train
--dataset juben_train
--dataset_dir $dataset_dir
--template baichuan2
--cutoff_len 512
--finetuning_type lora
--lora_target W_pack
--output_dir $output_dir
--overwrite_output_dir
--overwrite_cache
--per_device_train_batch_size 16
--gradient_accumulation_steps 1
--lr_scheduler_type cosine
--bf16
--double_quant
--quantization_bit 4
--quantization_type nf4
--warmup_ratio 0.05
--logging_steps 10
--save_steps 50
--learning_rate 1e-4
--num_train_epochs 10.0
--plot_loss
CUDA_VISIBLE_DEVICES=0 python src/train.py
--stage sft
--do_predict
--model_name_or_path $base_model_dir
--adapter_name_or_path $output_dir
--dataset_dir $dataset_dir
--dataset juben_test
--template baichuan2
--finetuning_type lora
--output_dir $predict_dir
--per_device_eval_batch_size 1
--max_samples 1000
--predict_with_generate
--max_length 1024
--generation_max_length 1024
--fp16
Expected behavior
模型微调后用于推理,发现生成的generated_predictions_0.jsonl文件中的label这个键的值不全问题
System Info
No response
Others
No response
The text was updated successfully, but these errors were encountered: