89 lines
2.0 KiB
JSON
89 lines
2.0 KiB
JSON
|
|
{
|
||
|
|
"run_id": "20260627T181044Z",
|
||
|
|
"status": "ok",
|
||
|
|
"config": {
|
||
|
|
"tier": "legion-ares:qwen3-1.7b",
|
||
|
|
"base_model": "Qwen/Qwen3-1.7B",
|
||
|
|
"teacher_model": "qwen3:14b",
|
||
|
|
"time_budget_min": 360,
|
||
|
|
"n_per": 8,
|
||
|
|
"cycles": 6,
|
||
|
|
"wall_clock_min": 360,
|
||
|
|
"note": "run crashed at cycle6 eval (window-close); best=cycle5, summary reconstructed from runs.log"
|
||
|
|
},
|
||
|
|
"dataset": {
|
||
|
|
"accepted": 601,
|
||
|
|
"rejected": 0,
|
||
|
|
"by_backend": {
|
||
|
|
"model": 430,
|
||
|
|
"template": 63
|
||
|
|
},
|
||
|
|
"train": 395,
|
||
|
|
"val": 98,
|
||
|
|
"test": 47
|
||
|
|
},
|
||
|
|
"baseline_eval": {
|
||
|
|
"model": "Qwen/Qwen3-1.7B (base)",
|
||
|
|
"passed": 10,
|
||
|
|
"n": 47,
|
||
|
|
"pass_rate": 0.213,
|
||
|
|
"invented_total": 4,
|
||
|
|
"grounding": 0.961,
|
||
|
|
"citation_coverage": null,
|
||
|
|
"anti_parrot": null,
|
||
|
|
"gates_cleared": false
|
||
|
|
},
|
||
|
|
"best_eval": {
|
||
|
|
"model": "Qwen/Qwen3-1.7B+adapter (cycle5 rank64/steps500)",
|
||
|
|
"passed": 41,
|
||
|
|
"n": 47,
|
||
|
|
"pass_rate": 0.872,
|
||
|
|
"invented_total": 0,
|
||
|
|
"grounding": 1.0,
|
||
|
|
"citation_coverage": 0.968,
|
||
|
|
"anti_parrot": 0.979,
|
||
|
|
"gates_cleared": true
|
||
|
|
},
|
||
|
|
"best_adapter": "F:\\dev\\legion-agent\\ares-training\\models\\best-181044Z-cycle5-41of47",
|
||
|
|
"promote": {
|
||
|
|
"promote": true,
|
||
|
|
"reason": "clears every eval gate (grounding 1.0, invented 0); pass 41/47 vs baseline 10/47"
|
||
|
|
},
|
||
|
|
"cycles": [
|
||
|
|
{
|
||
|
|
"cfg": "rank16/steps150",
|
||
|
|
"eval": {
|
||
|
|
"passed": 32,
|
||
|
|
"gates_cleared": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cfg": "rank32/steps250",
|
||
|
|
"eval": {
|
||
|
|
"passed": 37,
|
||
|
|
"gates_cleared": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cfg": "rank32/steps400",
|
||
|
|
"eval": {
|
||
|
|
"passed": 38,
|
||
|
|
"gates_cleared": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cfg": "rank64/steps300",
|
||
|
|
"eval": {
|
||
|
|
"passed": 39,
|
||
|
|
"gates_cleared": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cfg": "rank64/steps500",
|
||
|
|
"eval": {
|
||
|
|
"passed": 41,
|
||
|
|
"gates_cleared": true
|
||
|
|
}
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|