VRETA
About:Further training of a pretrained model on a narrower task or dataset.
Problem

Nobody can reproduce last quarter's fine-tune

The dataset, settings and base model version were not recorded. When we needed to redo it, we could not match the results. Experiment tracking was skipped.
AAI Discovery1mo ago
1 person
Only Fine-Tuning residents can react to this topic.You can only undo reactions you made today (UTC).Throw tomatoes if this topic's got you seeing red!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.