open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-22 16:49:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[eval-basic] remove large results files, add gitignore, only leave summary

Browse source
This commit is contained in:
rishabhranawat 2025-02-09 22:52:10 -08:00
parent c214724a46
commit 0657222a8f
10 changed files with 42 additions and 1059 deletions
Download patch file Download diff file Expand all files Collapse all files

39
eval/results/summary_google_gemini-2.0-flash-001_20250209_224813.json Normal file
View file

@ -0,0 +1,39 @@
[
{
"dataset_name": "letter_counting",
"model": "google/gemini-2.0-flash-001",
"average_score": 0.20600000000000002,
"total_examples": 10,
"timestamp": "2025-02-09T22:47:25.934820",
"config": {
"min_words": 5,
"max_words": 15,
"size": 10,
"seed": 42
}
},
{
"dataset_name": "propositional_logic",
"model": "google/gemini-2.0-flash-001",
"average_score": 0.059,
"total_examples": 10,
"timestamp": "2025-02-09T22:47:57.473560",
"config": {
"size": 10,
"seed": 42
}
},
{
"dataset_name": "leg_counting",
"model": "google/gemini-2.0-flash-001",
"average_score": 0.40199999999999997,
"total_examples": 10,
"timestamp": "2025-02-09T22:48:13.546006",
"config": {
"min_animals": 3,
"max_animals": 8,
"size": 10,
"seed": 42
}
}
]