Hugging Face's logo
Daniel van Strien's picture
731 379 956

Daniel van Strien PRO

davanstrien
m-ric's profile picture introvoyz041's profile picture mariagrandury's profile picture
·
https://danielvanstrien.xyz/

AI & ML interests

Machine Learning Librarian

Recent Activity

updated a dataset about 3 hours ago
davanstrien/magpie-preference
updated a dataset about 3 hours ago
data-is-better-together/fineweb-c-progress
updated a dataset about 3 hours ago
librarian-bots/model_cards_with_metadata
View all activity

Organizations

Hugging Face's profile picture Notebooks-explorers's profile picture Living with Machines's profile picture BigScience Workshop's profile picture Spaces-explorers's profile picture BigScience Catalogue Data's profile picture Hacks/Hackers's profile picture flyswot's profile picture BigScience: LMs for Historical Texts's profile picture Cohere For AI's profile picture Webhooks Explorers (BETA)'s profile picture HuggingFaceM4's profile picture Open Access AI Collective's profile picture HF Canonical Model Maintainers's profile picture BigLAM: BigScience Libraries, Archives and Museums's profile picture Hugging Face OSS Metrics's profile picture ImageIN's profile picture Stable Diffusion Bias Eval's profile picture Librarian Bots's profile picture Blog-explorers's profile picture Hacktoberfest 2023's profile picture Hugging Face TB Research's profile picture geospatial's profile picture HF-IA-archiving's profile picture 2A2I Legacy Models & Datasets's profile picture testy's profile picture DIBT-for-Klingon's profile picture Wikimedia Movement's profile picture DIBT-for-Esperanto's profile picture Journalists on Hugging Face's profile picture PleIAs's profile picture Argilla Explorers's profile picture Persian AI Community's profile picture HuggingFaceFW's profile picture Data Is Better Together's profile picture Social Post Explorers's profile picture OMOTO AI's profile picture academic-datasets's profile picture HuggingFaceFW-Dev's profile picture Hugging Face Discord Community's profile picture UCSF-JHU Opioid Industry Documents Archive's profile picture Dataset Tools's profile picture PDFPages's profile picture dibt-private's profile picture Data Is Better Together Contributor's profile picture Bluesky Community's profile picture Open R1's profile picture

davanstrien's activity

updated 3 datasets about 3 hours ago
liked 2 datasets about 5 hours ago
updated a dataset about 6 hours ago
updated 2 datasets about 14 hours ago
liked a dataset about 20 hours ago
liked a model about 21 hours ago
liked a dataset about 21 hours ago
liked a model about 22 hours ago
commented 2 papers about 22 hours ago
posted an update about 22 hours ago
view post
Post
1384
Hacked together a way to log trl GRPO training completions to a 🤗 dataset repo. This allows you to:

- Track rewards from multiple reward functions
- Treat the completion and rewards from training as a "proper" dataset and do EDA
- Share results for open science

The implementation is super hacky, but I'm curious if people would find this useful.

To push completions to the Hub, you just need two extra parameters:

log_completions=True
log_completions_hub_repo='your-username/repo-name'

Example dataset: davanstrien/test-logs
Colab: https://colab.research.google.com/drive/1wzBFPVthRYYTp-mEYlznLg_e_0Za1M3g
liked 2 datasets about 23 hours ago
updated a dataset 1 day ago
published a dataset 1 day ago
updated a dataset 1 day ago