Update Automated MNLP evaluation report (2026-06-11)
Browse files- EVAL_REPORT.md +10 -10
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-vibe-trainers/general_knowledge_model`](https://huggingface.co/cs-552-2026-vibe-trainers/general_knowledge_model)
|
| 4 |
- **Owner(s):** group **vibe-trainers**
|
| 5 |
-
- **Generated at:** 2026-06-
|
| 6 |
- **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
|
| 7 |
|
| 8 |
_This PR is opened automatically by the course CI. It is **non-blocking** — you do not need to merge it. The next nightly run will refresh this file._
|
|
@@ -18,7 +18,7 @@ _This PR is opened automatically by the course CI. It is **non-blocking** — yo
|
|
| 18 |
| Benchmark | Accuracy | Status |
|
| 19 |
|---|---:|---|
|
| 20 |
| Math | — | not run |
|
| 21 |
-
| Knowledge | 0.
|
| 22 |
| Multilingual | — | not run |
|
| 23 |
| Safety | — | not run |
|
| 24 |
|
|
@@ -30,26 +30,26 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
-
- **reference**: `
|
| 34 |
- **overall** (1/1 completions correct)
|
| 35 |
-
- **extracted** (✓): `
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
-
Reasoning:
|
| 40 |
|
| 41 |
-
Final answer: \boxed{
|
| 42 |
```
|
| 43 |
|
| 44 |
**Incorrect** (1 shown)
|
| 45 |
|
| 46 |
-
- **reference**: `
|
| 47 |
- **overall** (0/1 completions correct)
|
| 48 |
-
- **extracted** (✗): `
|
| 49 |
- **completion**:
|
| 50 |
|
| 51 |
```text
|
| 52 |
-
Reasoning: The
|
| 53 |
|
| 54 |
-
Final answer: \boxed{
|
| 55 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-vibe-trainers/general_knowledge_model`](https://huggingface.co/cs-552-2026-vibe-trainers/general_knowledge_model)
|
| 4 |
- **Owner(s):** group **vibe-trainers**
|
| 5 |
+
- **Generated at:** 2026-06-11T04:19:46+00:00 (UTC)
|
| 6 |
- **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
|
| 7 |
|
| 8 |
_This PR is opened automatically by the course CI. It is **non-blocking** — you do not need to merge it. The next nightly run will refresh this file._
|
|
|
|
| 18 |
| Benchmark | Accuracy | Status |
|
| 19 |
|---|---:|---|
|
| 20 |
| Math | — | not run |
|
| 21 |
+
| Knowledge | 0.3900 | ok |
|
| 22 |
| Multilingual | — | not run |
|
| 23 |
| Safety | — | not run |
|
| 24 |
|
|
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
+
- **reference**: `C`
|
| 34 |
- **overall** (1/1 completions correct)
|
| 35 |
+
- **extracted** (✓): `C`
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
+
Reasoning: Alzheimer's disease is characterized by progressive loss of acetylcholine in the brain, and research has established a strong link between acetylcholine deficiency and the disease's progression.
|
| 40 |
|
| 41 |
+
Final answer: \boxed{C}
|
| 42 |
```
|
| 43 |
|
| 44 |
**Incorrect** (1 shown)
|
| 45 |
|
| 46 |
+
- **reference**: `A`
|
| 47 |
- **overall** (0/1 completions correct)
|
| 48 |
+
- **extracted** (✗): `H`
|
| 49 |
- **completion**:
|
| 50 |
|
| 51 |
```text
|
| 52 |
+
Reasoning: The power spectral density of a convolution of two signals is the product of their power spectral densities. Here, $f(t)$ is the convolution of $h(t)$ and $\phi(t)$, so $G_f(\omega) = G_h(\omega) G_\phi(\omega)$. The Fourier transform of $h(t)$ is $H(\omega)$, so $G_h(\omega) = |H(\omega)|^2$. Thus, $G_f(\omega) = |H(\omega)|^2 G_\phi(\omega)$.
|
| 53 |
|
| 54 |
+
Final answer: \boxed{H}
|
| 55 |
```
|