lesson-agent-dev / modal_science_gate_publish_result.json
MSG
Feat/last sprintos (#23)
28543d3
Raw
History Blame Contribute Delete
1.28 kB
{
"job": "science-lora",
"baseline_results": "/vol/finetuned/results/lm_eval/minicpm5-1b__baseline__science/results.json",
"candidate_results": "/vol/finetuned/results/lm_eval/science-lora__science/results.json",
"gate": {
"passed": false,
"checks": [
{
"check": "sciq >= 0.5",
"value": 0.94,
"ok": true
},
{
"check": "sciq improve >= 0.02",
"value": -0.010000000000000009,
"ok": false
},
{
"check": "arc_challenge regress <= 0.03",
"value": -0.019999999999999962,
"ok": true
}
],
"task": "sciq",
"candidate_score": 0.94,
"baseline_score": 0.95
},
"publish": {
"published": false,
"reason": "gate failed",
"gate": {
"passed": false,
"checks": [
{
"check": "sciq >= 0.5",
"value": 0.94,
"ok": true
},
{
"check": "sciq improve >= 0.02",
"value": -0.010000000000000009,
"ok": false
},
{
"check": "arc_challenge regress <= 0.03",
"value": -0.019999999999999962,
"ok": true
}
],
"task": "sciq",
"candidate_score": 0.94,
"baseline_score": 0.95
}
}
}