a post-training issue
cmnfriend opened this issue · comments
Thanks for your nice work!
When I post-train the pruned model by running python post_training.py --prune_model prune_log/pytorch_model.bin --data_path yahma/alpaca-cleaned --output_dir tune_log --wandb_project llama_tune --lora_r 8 --num_epochs 2 --learning_rate 1e-4 --batch_size 64
, I meet with the following problem:
wandb.errors.UsageError: api_key not configured (no-tty). call wandb.login(key=[your_api_key])
Could you please tell me how I should deal with that? Thank you!
Hi. You need to first configure the wandb. You can follow the instructions of wandb😄
Thanks for your nice work!
When I post-train the pruned model by running
python post_training.py --prune_model prune_log/pytorch_model.bin --data_path yahma/alpaca-cleaned --output_dir tune_log --wandb_project llama_tune --lora_r 8 --num_epochs 2 --learning_rate 1e-4 --batch_size 64
, I meet with the following problem:
wandb.errors.UsageError: api_key not configured (no-tty). call wandb.login(key=[your_api_key])
Could you please tell me how I should deal with that? Thank you!
you could use python post_training.py --prune_model prune_log/pytorch_model.bin --data_path yahma/alpaca-cleaned --output_dir tune_log --wandb_project "none" --lora_r 8 --num_epochs 2 --learning_rate 1e-4 --batch_size 64
to run it