Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
2
Mirza Milan Farabi
mmfarabi
Follow
0 followers
ยท
12 following
m_milan_farabi
mmfarabi
mirza-milan-farabi-b31209258
AI & ML interests
AI & ML
Recent Activity
updated
a Space
about 2 months ago
mmfarabi/LeadGenAI
published
a Space
about 2 months ago
mmfarabi/LeadGenAI
reacted
to
davanstrien
's
post
with ๐
about 2 months ago
Hacked together a way to log trl GRPO training completions to a ๐ค 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: https://huggingface.co/datasets/davanstrien/test-logs Colab: https://colab.research.google.com/drive/1wzBFPVthRYYTp-mEYlznLg_e_0Za1M3g
View all activity
Organizations
None yet
spaces
1
Running
1
LeadGenAI
๐
LinkedIn Lead Generation and Business Optimization App
models
None public yet
datasets
None public yet