You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository was archived by the owner on Oct 31, 2023. It is now read-only.
I have run successfully BERT with MAPO. Everything is running fine. This is the command I used : python experiments.py train --seed 0 --cuda --work-dir=runs/demo_run --config=data/config/config.vanilla_bert.json --extra-config='{"actor_use_table_bert_proxy": true}'. This is the MAPO code https://github.com/pcyin/pytorch_neural_symbolic_machines.
Now I am trying to reproduce TaBERT with MAPO. But when I do this the code is not running. The Learner exits and that is where it ends. Same command as BERT.
For running TaBERT with MAPO I have downloaded the model from 'https://drive.google.com/uc?id=17NTNIqxqYexAzaH_TgEfK42-KmjIRC-g'. Then I just have changed the config file 'table_bert_model_or_config' param with TaBERT model path.
I am trying to reproduce Table 1 in https://www.aclweb.org/anthology/2020.acl-main.745.pdf : w/ TABERTLarge (K = 3) 52.2 ±0.7 , 53.0 , 51.8 ±0.6 , 52.3 .
Can you please let me know where I am doing error?