Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Language Modeling on FineWeb-EDU (train)

2.993Loss

sHC

2.822843.971425.126.26858Mar 5, 2026Mar 7, 2026Mar 10, 2026Mar 13, 2026Mar 15, 2026Mar 18, 2026Mar 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
2.993---
2026.03
3.013---
2026.03
3.017---
2026.03
3.058---
2026.03
3.112---
2026.03
3.23---
2026.03
3.241---
2026.03
3.241---
2026.03
3.276---
2026.03
3.313---
2026.03
6.68---
2026.03
6.718---
2026.03
6.731---
2026.03
6.735---
2026.03
6.798---
2026.03
7.247---
2026.03
-10.8325.1237.62
2026.03
-10.0125.3932.51
2026.03
-10.5930.0333.88