初始化项目,由ModelHub XC社区提供模型

Model: tburns-actual/legion-ares
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-25 13:52:10 +08:00
commit 3836d7b76b
16 changed files with 849 additions and 0 deletions

View File

@@ -0,0 +1,89 @@
{
"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
}
}
]
}

View File

@@ -0,0 +1,175 @@
{
"run_id": "20260706T124233Z",
"status": "ok",
"config": {
"run_id": "20260706T124233Z",
"tier": "legion-ares:qwen3-1.7b",
"base_model": "Qwen/Qwen3-1.7B",
"teacher_model": "qwen3:14b",
"time_budget_min": 240.0,
"instructions_per": 3,
"n_per": 8,
"smoke": false,
"wall_clock_min": 256.7,
"cycles": 5
},
"dataset": {
"candidates": 329,
"accepted": 329,
"rejected": 0,
"deduped": 58,
"train": 217,
"val": 54,
"test": 48,
"by_backend": {
"model": 228,
"template": 43
},
"reject_reasons": []
},
"baseline_eval": {
"model": "Qwen/Qwen3-1.7B (base)",
"n": 48,
"passed": 8,
"pass_rate": 0.16666666666666666,
"invented_total": 4,
"grounding": 0.9583333333333334,
"format": 0.5208333333333334,
"citation_coverage": 0.84375,
"anti_parrot": 0.9236111111111112,
"mean_latency_s": 3.9846893250000903,
"gates_cleared": false
},
"best_eval": {
"model": "Qwen/Qwen3-1.7B+adapter",
"n": 48,
"passed": 39,
"pass_rate": 0.8125,
"invented_total": 1,
"grounding": 0.9791666666666666,
"format": 1.0,
"citation_coverage": 0.9479166666666666,
"anti_parrot": 0.9340277777777778,
"mean_latency_s": 10.969979652083111,
"gates_cleared": false
},
"best_adapter": "F:\\dev\\legion-agent\\ares-training\\.work\\iter-20260706T124233Z\\cycle4\\adapter",
"promote": {
"promote": false,
"reason": "candidate did not clear all eval gates",
"candidate_pass_rate": 0.8125,
"baseline_pass_rate": 0.16666666666666666
},
"cycles": [
{
"cfg": {
"rank": 16,
"steps": 150,
"lr": 0.0002,
"cap_min": 45
},
"train": "ok",
"eval": {
"model": "Qwen/Qwen3-1.7B+adapter",
"n": 48,
"passed": 29,
"pass_rate": 0.6041666666666666,
"invented_total": 1,
"grounding": 0.9791666666666666,
"format": 1.0,
"citation_coverage": 0.9270833333333334,
"anti_parrot": 0.8767361111111112,
"mean_latency_s": 10.295820183333452,
"gates_cleared": false
}
},
{
"cfg": {
"rank": 32,
"steps": 250,
"lr": 0.0002,
"cap_min": 60
},
"train": "ok",
"eval": {
"model": "Qwen/Qwen3-1.7B+adapter",
"n": 48,
"passed": 35,
"pass_rate": 0.7291666666666666,
"invented_total": 3,
"grounding": 0.9479166666666666,
"format": 1.0,
"citation_coverage": 0.8854166666666666,
"anti_parrot": 0.9826388888888888,
"mean_latency_s": 11.041281214583591,
"gates_cleared": false
}
},
{
"cfg": {
"rank": 32,
"steps": 400,
"lr": 0.0001,
"cap_min": 70
},
"train": "ok",
"eval": {
"model": "Qwen/Qwen3-1.7B+adapter",
"n": 48,
"passed": 34,
"pass_rate": 0.7083333333333334,
"invented_total": 3,
"grounding": 0.9479166666666666,
"format": 1.0,
"citation_coverage": 0.9270833333333334,
"anti_parrot": 0.9513888888888888,
"mean_latency_s": 10.63382095000001,
"gates_cleared": false
}
},
{
"cfg": {
"rank": 64,
"steps": 300,
"lr": 0.0002,
"cap_min": 70
},
"train": "ok",
"eval": {
"model": "Qwen/Qwen3-1.7B+adapter",
"n": 48,
"passed": 39,
"pass_rate": 0.8125,
"invented_total": 1,
"grounding": 0.9791666666666666,
"format": 1.0,
"citation_coverage": 0.9479166666666666,
"anti_parrot": 0.9340277777777778,
"mean_latency_s": 10.969979652083111,
"gates_cleared": false
}
},
{
"cfg": {
"rank": 64,
"steps": 500,
"lr": 0.0001,
"cap_min": 80
},
"train": "partial",
"eval": {
"model": "Qwen/Qwen3-1.7B+adapter",
"n": 48,
"passed": 31,
"pass_rate": 0.6458333333333334,
"invented_total": 3,
"grounding": 0.9722222222222222,
"format": 1.0,
"citation_coverage": 0.9479166666666666,
"anti_parrot": 0.9201388888888888,
"mean_latency_s": 19.72521776874987,
"gates_cleared": false
}
}
]
}