Skip to content
conftrace_

compute optimization

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

scaling law (3) learning rate schedule (2) constrained setting (1) constrained training (1) adamw optimizer (1) cosine decay (1) neural network (1) large language model (1) parameter count (1) causal language model (1)

Papers

Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs ICLR 2025 Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations NeurIPS 2024 Training Compute-Optimal Protein Language Models NeurIPS 2024 Scaling Laws for a Multi-Agent Reinforcement Learning Model ICLR 2023 How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task ACL 2021