New issue
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
运用prefix_projection 方法训练test acc不变一直是62.1 #13
Comments
Hi, prefix projection needs a careful hyper-parameter tuning, and in practice we find it does not work for every tasks. |
BoolQ and RTE result on the table of github is not same with paper report |
As we stated in the README.md, the hyperparameters provided in the repo is reimplemented with 3090 GPUs, rather than A100s (on which our paper results come from). |
thanks,I think it will only affect the speed. Does it have anything to do with the result? |
As is in the README.md If you do not have the exact same environment, we highly recommend you to run hyper-parameter search in your environment |
12/07/2021 19:30:19 - INFO - training.trainer_base - ***** Epoch 12: Best results ***** 12/07/2021 19:30:19 - INFO - training.trainer_base - best_epoch = 0
12/07/2021 19:30:19 - INFO - training.trainer_base - best_eval_accuracy = 0.6217125382262997
12/07/2021 19:30:19 - INFO - training.trainer_base - epoch = 12.0
OrderedDict([('best_epoch', 0), ('best_eval_accuracy', 0.6217125382262997), ('epoch', 13.0)])
{'loss': 0.7488, 'learning_rate': 0.006054054054054054, 'epoch': 13.51}
The text was updated successfully, but these errors were encountered: