{ "status": "PASS", "dtype": "torch.bfloat16", "n_steps": 30, "sdpo_fired_nonzero": true, "max_sdpo_kl": 0.185546875, "loss_trend_down": true, "all_finite": true, "loss_first": 4.726175785064697, "loss_last": 0.0050478726625442505, "loss_curve": [ 4.7262, 2.9752, 1.8887, 1.1304, 0.6017, 0.3641, 0.1361, 0.037, 0.0142, 0.0077, 0.0061, 0.0055, 0.0053, 0.0053, 0.0052, 0.0052, 0.0052, 0.0051, 0.0051, 0.0051, 0.0051, 0.0051, 0.0051, 0.0051, 0.0051, 0.0051, 0.0051, 0.005, 0.005, 0.005 ], "sdpo_curve": [ 0.0801, 0.0757, 0.0771, 0.0903, 0.1387, 0.1855, 0.1445, 0.1113, 0.0679, 0.0574, 0.0381, 0.0151, 0.009, 0.0066, 0.0065, 0.0052, 0.0048, 0.0038, 0.0031, 0.0021, 0.0026, 0.0029, 0.0016, 0.0013, 0.0021, 0.0018, 0.0014, 0.0011, 0.0007, 0.0015 ], "run_date": "2026-05-29", "gpu": "A10G", "model": "Qwen/Qwen2.5-0.5B-Instruct" }