Skip to main content
llm_surgery
Projects
gemma-zephyr
Run groups
gemma-2b
Logs
Group
Workspace
Runs
Logs
Files
Artifacts

Autometa's group workspace

Timestamps visible
2024-02-29 21:48:33
|  - high_school_biology                |      0|none            |None  |acc        |0.4032|±  |0.0279|
2024-02-29 21:48:33
|  - high_school_chemistry              |      0|none            |None  |acc        |0.2956|±  |0.0321|
2024-02-29 21:48:33
|  - high_school_computer_science       |      0|none            |None  |acc        |0.2900|±  |0.0456|
2024-02-29 21:48:33
|  - high_school_mathematics            |      0|none            |None  |acc        |0.2630|±  |0.0268|
2024-02-29 21:48:33
|  - high_school_physics                |      0|none            |None  |acc        |0.2980|±  |0.0373|
2024-02-29 21:48:33
|  - high_school_statistics             |      0|none            |None  |acc        |0.3287|±  |0.0320|
2024-02-29 21:48:33
|  - machine_learning                   |      0|none            |None  |acc        |0.3036|±  |0.0436|
2024-02-29 21:48:33
|hellaswag                              |      1|none            |None  |acc        |0.5278|±  |0.0050|
2024-02-29 21:48:33
|                                       |       |none            |None  |acc_norm   |0.7144|±  |0.0045|
2024-02-29 21:48:33
|gsm8k                                  |      3|strict-match    |5     |exact_match|0.1812|±  |0.0106|
2024-02-29 21:48:33
|                                       |       |flexible-extract|5     |exact_match|0.1812|±  |0.0106|
2024-02-29 21:48:33
|arc_challenge                          |      1|none            |None  |acc        |0.4036|±  |0.0143|
2024-02-29 21:48:33
|                                       |       |none            |None  |acc_norm   |0.4215|±  |0.0144|
2024-02-29 21:48:33
|      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|
2024-02-29 21:48:33
|------------------|-------|------|------|------|-----:|---|-----:|
2024-02-29 21:48:33
|mmlu              |N/A    |none  |     0|acc   |0.3346|±  |0.0040|
2024-02-29 21:48:33
| - humanities     |N/A    |none  |None  |acc   |0.3296|±  |0.0068|
2024-02-29 21:48:33
| - other          |N/A    |none  |None  |acc   |0.3466|±  |0.0085|
2024-02-29 21:48:33
| - social_sciences|N/A    |none  |None  |acc   |0.3419|±  |0.0085|
2024-02-29 21:48:33
| - stem           |N/A    |none  |None  |acc   |0.3232|±  |0.0083|