search

IBM / molformer

Repository for MolFormer
Apache License 2.0
266 stars 43 forks source link

Inaccurate reproduction results on QM9 #15

Closed Park-ing-lot closed 1 year ago

Park-ing-lot commented 1 year ago

When I finetune the model from checkpoint "N-Step-Checkpoint_3_30000.ckpt", the reproduction results are much higher than them report in the paper.

For example, I got 1.4575 on u0 task, while the reported result on the same task is 0.3211. I have checked the finetune code several times, I cannot find issues.

Is there anyone who get similar results to the reported ones on any regression task?

hoffmansc commented 1 year ago

Please see the README. The provided checkpoints are for 10% ZINC + 10% PubChem, not the full MoLFormer-XL weights.