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

Language Modeling on FineWeb-Edu 10K steps (train)

3.338Training Loss

Delta Block

3.3273.401253.47553.54975May 13, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
3.338
2026.05
3.339
2026.05
3.36
2026.05
3.401
2026.05
3.405
2026.05
3.422
2026.05
3.423
2026.05
3.428
2026.05
3.428
2026.05
3.474
2026.05
3.563
2026.05
3.577
2026.05
3.577
2026.05
3.586
2026.05
3.613