Kuiz berkaitan panduan · Sederhana Tahap
Kuiz Penjelasan Metrik Lulus@k
Menguji takrif pass@k, penganggar tidak berat sebelah daripada n sampel, kebolehpercayaan lulus^k dan cara biasa skor pass@k mendapat salah baca atau dinaikkan.
soalan 1 daripada 8
Apakah ukuran pass@k untuk satu masalah?
Pratonton setiap soalan8 soalan
Jawapan dan penjelasan muncul semasa anda mengambil kuiz.
- Apakah ukuran pass@k untuk satu masalah?
- The fraction of k samples that pass the tests
- The probability that at least one of k sampled attempts passes the tests
- The probability that the first attempt passes after k retries of fine-tuning
- The number of tests passed out of k tests
- HumanEval, penanda aras yang diperkenalkan dengan kertas Codex, mengandungi apa?
- 2,294 GitHub issues from Python projects
- 1,000 competitive programming problems in C++
- 164 hand-written Python programming problems with unit tests
- 500 human-verified bug reports
- Mengapakah kertas Codex menjana n sampel dengan n lebih besar daripada k?
- To compute an unbiased, lower-variance estimate of pass@k
- To let the model learn from its failures between samples
- Because the tests require at least 200 inputs
- To make the model's outputs deterministic
- Dengan n sampel dan c betul, ungkapan yang manakah merupakan penganggar pas@k tidak berat sebelah?
- c divided by n
- 1 minus (1 minus c/n) to the power k
- C(c, k) divided by C(n, k)
- 1 minus C(n minus c, k) divided by C(n, k)
- Apakah yang diukur oleh pas^k, yang ditakrifkan dalam kertas bangku tau?
- The chance that at least one of k trials succeeds
- The chance that all k independent trials succeed
- The average number of steps across k trials
- The score after k rounds of self-correction
- How does sampling temperature typically interact with k?
- Temperature has no effect on pass@k
- Low temperature is best for every k
- Higher temperature tends to help pass@k at large k because samples are more diverse
- Higher temperature always improves pass@1
- Why can a high pass@100 score overstate real-world usefulness?
- It assumes something already knows which of the samples is correct
- It only counts the first sample
- It ignores the unit tests
- It is always computed with greedy decoding
- If n = 20 samples include c = 18 correct ones, what is pass@5?
- 0.9
- About 0.5
- It cannot be computed because n is too small
- Tepat 1