# Hyperparameter Search (AlexNet) on SVHN

Source: [Hyperparameter Search (AlexNet) on SVHN](<https://www.sota2.com/research/sota/hyperparameter-search-alexnet-on-svhn>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-08T06:58:50.974Z

Evaluation of hyperparameter search strategies specifically using the AlexNet architecture on the SVHN dataset, focusing on validity counts and performance advantages derived from source guidance.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Hyperparameter Search (AlexNet) |
| Dataset (including any stated split) | SVHN |
| Metric | Non-source Validity Count |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Non-source Validity Count](<https://www.sota2.com/research/sota/hyperparameter-search-alexnet-on-svhn.md?metric=Non-source%20Validity%20Count>): Higher is better; unit: SCALAR.

- [Non-source Best Valid Acc](<https://www.sota2.com/research/sota/hyperparameter-search-alexnet-on-svhn.md?metric=Non-source%20Best%20Valid%20Acc>): Higher is better; unit: PERCENT.

- [Source-guided Validity Count](<https://www.sota2.com/research/sota/hyperparameter-search-alexnet-on-svhn.md?metric=Source-guided%20Validity%20Count>): Higher is better; unit: SCALAR.

- [Source-guided Best Valid Acc](<https://www.sota2.com/research/sota/hyperparameter-search-alexnet-on-svhn.md?metric=Source-guided%20Best%20Valid%20Acc>): Higher is better; unit: PERCENT.

- [Best Advantage Score](<https://www.sota2.com/research/sota/hyperparameter-search-alexnet-on-svhn.md?metric=Best%20Advantage%20Score>): Higher is better; unit: SCALAR.

- [Mean Advantage Score](<https://www.sota2.com/research/sota/hyperparameter-search-alexnet-on-svhn.md?metric=Mean%20Advantage%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Non-source Validity Count | Result date | Report paper |
| --- | --- | --- | --- |
| DeepSeek-Coder-6.7B | 64 | Not recorded | 6a4dd9b24da6617fe9198c3f |
| OlympicCoder-7B | 45 | Not recorded | 6a4dd9b24da6617fe9198c3f |
| Qwen2.5-Coder-7B | 25 | Not recorded | 6a4dd9b24da6617fe9198c3f |

### DeepSeek-Coder-6.7B

Non-source Validity Count: 64. Result ID: 6a4df51f60b88bb339d6a72c.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b24da6617fe9198c3f.md>)

Recorded evaluation configuration: {"LLM":"DeepSeek6.7B","N (Candidates per arm)":"32"}. This record does not assert independent reproduction.

### OlympicCoder-7B

Non-source Validity Count: 45. Result ID: 6a4df51f60b88bb339d6a72e.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b24da6617fe9198c3f.md>)

Recorded evaluation configuration: {"LLM":"Olympic7B","N (Candidates per arm)":"32"}. This record does not assert independent reproduction.

### Qwen2.5-Coder-7B

Non-source Validity Count: 25. Result ID: 6a4df51f60b88bb339d6a72d.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b24da6617fe9198c3f.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-7B","N (Candidates per arm)":"32"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
