Tag: learning rate
-
Supervised Fine-Tuning End to End: The First Real Run
A full supervised fine-tune twice over: a bare PyTorch loop and the same job through a trainer. Hyperparameters that work, plus how…
-
AdamW Explained, Line by Line
AdamW dissected: where it runs, the lineage behind the name, the four update lines, why decoupled weight decay was a real fix,…