How Many Epochs Does Fine-Tuning Actually Need?
from My Weird Prompts
Almost nobody picks an epoch count in advance — they set a ceiling, evaluate often, keep the best checkpoint, and the epoch count is whatever that turns out to be. This episode works through two concrete cases: a Whisper speech fine-tune scored on word error rate, and an instruction-tuned language model using SFT or LoRA. Along the way: why steps and tokens beat epochs as a unit, why validation loss and word error rate can tell opposite stories, why the best LoRA learning rate runs about ten times the full fine-tuning rate, and what the position of your best checkpoint tells you about what to change next. Episode 6223 — myweirdprompts.com/n/6223 (permanent short link: myweirdprompts.com/407740) Listen on Android: MWP FM Player — myweirdprompts.com/apk
Embed this episode
Chapters
No transcript yet.