10-05-2026, 02:07 AM
Quote:I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. A lot of these thread
That matches what I was seeing. The pattern around batch size has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
learning in public
