Resolving Discrepancies in Compute-Optimal Scaling of Language Models

Oct-10-2025, 14:12:10 GMT–Neural Information Processing Systems

We explain the discrepancy by reproducing the Kaplan et al. scaling law on two datasets (OpenWebText2 and RefinedWeb)

batch size, experiment, hyperparameter, (16 more...)

Neural Information Processing Systems

Oct-10-2025, 14:12:10 GMT

Conferences PDF

Country:
- Europe
  - Germany (0.04)
  - Italy > Calabria
    - Catanzaro Province > Catanzaro (0.04)
- Asia > Middle East
  - Jordan (0.04)
  - Israel > Tel Aviv District
    - Tel Aviv (0.04)

Genre:
- Research Report
  - New Finding (1.00)
  - Experimental Study (1.00)

Technology:
- Information Technology > Artificial Intelligence
  - Natural Language
    - Large Language Model (1.00)
    - Chatbot (0.93)
  - Machine Learning > Neural Networks
    - Deep Learning (1.00)

Duplicate Docs Excel Report

Title
Resolving Discrepancies in Compute-Optimal Scaling of Language Models

Similar Docs Excel Report more

Title	Similarity	Source
None found