Quiz dostrajający

Odpowiedzi i wyjaśnienia pojawiają się w miarę rozwiązywania quizu.

1. Jakie zmiany zachodzą podczas dostrajania, w odróżnieniu od dodawania przykładów do podpowiedzi?
   • Learned parameters of an existing model are updated through further training
   • Only the current request text changes, while model parameters stay fixed
   • A current document is fetched at answer time without changing the model
   • The model's output is edited after generation with no training
2. Asystent pomocy technicznej pisze wyraźnie, ale musi stosować zasady aktualizowane co tydzień. Który pierwszy test najlepiej pasuje do przewodnika?
   • Retrain the model after every policy edit before considering other options
   • Put an old policy into training examples and rely on model recall
   • Retrieve the current policy at answer time and evaluate its use
   • Tune only the model's output style and assume policy facts remain current
3. W modelu wielokrotnie brakuje stabilnego formatu odpowiedzi. Jakie porównanie powinno poprzedzać decyzję o dostrojeniu?
   • Only compare training loss across fine-tuned checkpoints
   • Compare prompt changes with a carefully evaluated fine-tuning dataset
   • Replace the held-out evaluation set with more training examples
   • Assume retrieval of unrelated documents will fix formatting
4. Dlaczego zbiór ocen powinien pozostać oddzielony zarówno od danych dostrajających, jak i decyzji dotyczących dostrajania?
   • To make the training set contain fewer labels by definition
   • To guarantee that every output will cite a source
   • To avoid recording the base model version
   • To measure behavior on examples that were not used to fit or select the model
5. Jakich kontroli zbioru danych wymaga przewodnik przed dostrojeniem?
   • Only whether the training job can parse every record
   • Labels, duplicate records, permissions and confidential information
   • Only whether examples have the desired output length
   • Only whether the dataset is larger than the model's context window
6. A method trains only a subset of model parameters. What requirement still applies?
   • Evaluate the target task and capabilities that should remain intact
   • Assume lower memory use proves equal quality on every task
   • Skip the held-out set because fewer weights changed
   • Treat training loss as a complete safety evaluation
7. The fine-tuned model improves the target classifier but performs worse on unrelated tasks. What does that show?
   • That the model must have received an invalid prompt
   • That held-out tests are unnecessary if training loss falls
   • That retrieval can never work with a fine-tuned model
   • A gain in one measured behavior can come with a regression elsewhere
8. What should a team record to make a fine-tuned release reviewable and reversible?
   • Only the final training loss and public model name
   • Only the prompt used during one successful demonstration
   • Base model, dataset version, training settings, checkpoint and rollback plan
   • Only the number of examples and the selected learning rate