Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
frostedoyster created a review comment on a pull request on metatensor/metatrain
Ok! It's now there
SanggyuChong created a review on a pull request on metatensor/metatrain
To me it looks good, didn't understand the shift from computing something on the energies and forces to working directly on the loss functions, but now i understand and see it now. Thanks for t...
PicoCentauri pushed 1 commit to download-model metatensor/metatrain
- allow exporting models on remote locations e8e3248
PicoCentauri pushed 1 commit to download-model metatensor/metatrain
- allow exporting models on remote locations 60abba5
HannaTuerk created a branch on metatensor/metatrain
pet_history - Training and evaluating machine learning models for atomistic systems.
github-actions[bot] pushed 1 commit to gh-pages metatensor/metatrain
- deploy: 6af1bed826252f35e3be4c7242f6ffba9d2b89d4 b7c9c56
abmazitov closed an issue on metatensor/metatrain
Energies per atom are written to the `output.xyz` instead of full energies
While running the `mtt eval`, I noticed that instead of writing total energies to the `xyz` file with the predictions, we write the energies per atom. This happens because of the following lines: ...abmazitov pushed 1 commit to main metatensor/metatrain
- Adding total energies to the output during mtt eval (#367) * Adding total energies to the output during mtt eval ... 6af1bed
abmazitov pushed 1 commit to full_output_energies_on_eval metatensor/metatrain
- Updated PET dependency c46c66c
abmazitov pushed 1 commit to full_output_energies_on_eval metatensor/metatrain
- Updated PET dependency f53bdaa
PicoCentauri created a review comment on a pull request on metatensor/metatrain
We should inform the user that the training is continued if the `outputs` directory is found or maybe error or warn if continue="auto" and now directory is found.
PicoCentauri created a review on a pull request on metatensor/metatrain
Might be a good idea. If this moves further remember to explain this well in the docs. We aren't writing the checkpoints of the current training run in the directory where the training is starte...
PicoCentauri created a review on a pull request on metatensor/metatrain
Might be a good idea. If this moves further remember to explain this well in the docs. We aren't writing the checkpoints of the current training run in the directory where the training is starte...
frostedoyster pushed 2 commits to nanopet metatensor/metatrain
abmazitov opened a pull request on metatensor/metatrain
Adding total energies to the output during mtt eval
<!-- What does this implement/fix? Explain your changes here. --> # Contributor (creator of pull-request) checklist - [ ] Tests updated (for new features and bugfixes)? - [ ] Documenta...abmazitov created a branch on metatensor/metatrain
full_output_energies_on_eval - Training and evaluating machine learning models for atomistic systems.
abmazitov opened an issue on metatensor/metatrain
Energies per atom are written to the `output.xyz` instead of full energies
While running the `mtt eval`, I noticed that instead of writing total energies to the `xyz` file with the predictions, we write the energies per atom. This happens because of the following lines: ...github-actions[bot] pushed 1 commit to gh-pages metatensor/metatrain
- deploy: 6b5fb29f258c70f7dc322b6b667204e7461746fe 0306fe3
github-actions[bot] pushed 1 commit to gh-pages metatensor/metatrain
- deploy: fc17b495e9648b681f80aa2aeeac1c8738cfc567 fc68b13