Published March 17, 2026
| Version 03-17-2026
Software
Open
BERTology of Molecular Property Prediction (Data Size Effect: Base-BERT, Part 5)
Authors/Creators
-
1.
Molecular Sciences Software Institute
-
2.
Virginia Tech
Description
Data Size Effects on Pre-Training
Base-BERT (Part 5)
This record pertains to Data Size Effects on Pre-Training Experiments.It includes the following files:
- base-binidx-5-ms-1234-ds-1234.tar.gz
- base-binidx-5-ms-1234-ds-2345.tar.gz
- base-binidx-5-ms-2345-ds-1234.tar.gz
Each tar file contains all model artifacts (checkpoints, random-number generator states, optimizer states etc.), training logs (Tensorboard, MLFlow and Weights & Biases), and evaluation results, configuration files, run scripts, SLURM sbatch driver scripts, and any additional artifacts generated during the experiments.
Preprint: https://doi.org/10.48550/arXiv.2603.13627
Files
Files
(31.7 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:7e7a394404f592a6504e49eac4845355
|
14.9 GB | Download |
|
md5:7e8193c5a8ba06a7affc71914230c64b
|
2.0 GB | Download |
|
md5:f9293c872a4a81d9ef5023cbbab7076b
|
14.9 GB | Download |
Additional details
Software
- Repository URL
- https://github.com/molssi-ai/bertology
- Programming language
- Python
- Development Status
- Active