japhba's picture
Upload eval_log.jsonl for bayesian_update
ff55ab4 verified
Raw History Blame Contribute Delete
9.22 kB
{"timestamp": "2026-04-21T04:51:53Z", "step": 141, "fraction": 0.25, "metric_name": "procedure_margin", "metric_value": 0.2970070624351501, "metric_std": 0.31542884031937496, "per_probe_values": [0.2524911165237427, 0.335440993309021, 0.14094245433807373, 0.4559493064880371, 0.3929719924926758, -0.021545767784118652, 0.3980858325958252, 0.5601708889007568, 0.3803377151489258, 0.40226030349731445, 0.4904041290283203, -0.3030802011489868, 0.41899120807647705, -0.06800127029418945, 0.6410071849822998, -0.013068675994873047, 0.1538996696472168, 0.572993278503418, 0.0320817232131958, 0.3963063955307007, -0.21842288970947266, 0.42288172245025635, 0.571351170539856, 0.21090340614318848, 0.6800471544265747, 0.47049033641815186, 0.06056487560272217, 0.15205609798431396, 0.8807955980300903, 0.13477420806884766, 0.625385046005249, 0.3245210647583008, 0.16714906692504883, 0.6686869859695435, -0.01075601577758789, 0.5123815536499023, -0.322590708732605, 0.06270396709442139, 0.30177223682403564, 0.4753953218460083, -0.11873781681060791, 0.3793189525604248, 0.165685772895813, 0.34327149391174316, 0.2039858102798462, 0.49862754344940186, -0.4424694776535034, 0.38748717308044434, 0.37576770782470703, 0.18256020545959473, 0.7535239458084106, 0.619220495223999, -0.06251955032348633, 0.6188862323760986, -0.251498818397522, 0.48338544368743896, 0.39609336853027344, 0.04237699508666992, 0.06346118450164795, -0.08079588413238525, -0.17525851726531982, 0.4297752380371094, 0.3456597328186035, 0.43026602268218994, -0.49457716941833496, 0.15993273258209229, 0.5075579881668091, 0.38762736320495605, -0.34829068183898926, 0.4975159168243408, -0.016994118690490723, 0.4435986280441284, 0.7050672769546509, 0.12905871868133545, 0.18172287940979004, 0.32986557483673096, -0.003811955451965332, 0.3801109790802002, 0.22328758239746094, 0.34155356884002686, 0.7336320877075195, 0.5177263021469116, 0.9785832166671753, 0.6815670728683472, 0.4274144172668457, 0.15133070945739746, 1.2324810028076172, 0.6957566738128662, 0.27149415016174316, 0.9819673299789429, 0.2228316068649292, 0.01449286937713623, 0.5269652605056763, -0.0040130615234375, 0.31158924102783203, 0.7019540071487427, -0.01941990852355957, 0.058551907539367676, -0.02306497097015381, 0.438839316368103], "wall_seconds": 11.341804265975952}
{"timestamp": "2026-04-21T04:58:07Z", "step": 282, "fraction": 0.5, "metric_name": "procedure_margin", "metric_value": 0.27911544680595396, "metric_std": 0.32909301703161653, "per_probe_values": [0.30652177333831787, 0.31655454635620117, 0.1569455862045288, 0.46252405643463135, 0.3919031620025635, 0.03329658508300781, 0.4496424198150635, 0.5133278369903564, 0.42438602447509766, 0.3412797451019287, 0.5234047174453735, -0.41835832595825195, 0.28882551193237305, -0.10042917728424072, 0.7051494121551514, 0.029995441436767578, 0.234177827835083, 0.5337036848068237, -0.0334547758102417, 0.35076451301574707, -0.23223388195037842, 0.4065697193145752, 0.5139752626419067, 0.1424245834350586, 0.6480735540390015, 0.47737741470336914, 0.08372128009796143, 0.10035395622253418, 0.8983122110366821, 0.1198354959487915, 0.5762732028961182, 0.33658576011657715, 0.18418550491333008, 0.6339237689971924, 0.05680859088897705, 0.5002108812332153, -0.3545182943344116, 0.025615930557250977, 0.26151251792907715, 0.46056830883026123, -0.19783461093902588, 0.3276693820953369, 0.1021585464477539, 0.381081223487854, 0.21078741550445557, 0.4425455331802368, -0.3643113374710083, 0.4095085859298706, 0.3324476480484009, 0.16873502731323242, 0.7700936794281006, 0.6688913106918335, -0.19023382663726807, 0.622880220413208, -0.2752324342727661, 0.47994720935821533, 0.41660892963409424, -0.02394735813140869, 0.04926872253417969, -0.1600489616394043, -0.22639822959899902, 0.3939722776412964, 0.3604252338409424, 0.4398341178894043, -0.5060874223709106, 0.10470211505889893, 0.334118127822876, 0.3224916458129883, -0.40525615215301514, 0.4963158369064331, -0.04267740249633789, 0.38462066650390625, 0.6885664463043213, 0.12298083305358887, 0.21565735340118408, 0.28258955478668213, -0.014044046401977539, 0.3481217622756958, 0.20187854766845703, 0.3461421728134155, 0.7052346467971802, 0.5252448320388794, 1.102968454360962, 0.670486330986023, 0.3771723508834839, 0.09619927406311035, 1.3323290348052979, 0.6101351976394653, 0.18822050094604492, 0.9625594615936279, 0.21937990188598633, -0.08508133888244629, 0.5198942422866821, -0.0803368091583252, 0.24369025230407715, 0.7167598009109497, -0.06060612201690674, 0.15710043907165527, -0.0720905065536499, 0.413580060005188], "wall_seconds": 11.256399393081665}
{"timestamp": "2026-04-21T05:04:18Z", "step": 423, "fraction": 0.75, "metric_name": "procedure_margin", "metric_value": 0.22783050775527955, "metric_std": 0.3703104293068648, "per_probe_values": [0.2683306932449341, 0.3080953359603882, 0.05526900291442871, 0.43213653564453125, 0.3272991180419922, -0.019545555114746094, 0.36217188835144043, 0.48522114753723145, 0.3858773708343506, 0.32440710067749023, 0.5445650815963745, -0.5224580764770508, 0.16615593433380127, -0.18337202072143555, 0.6820436716079712, -0.00386655330657959, 0.15688657760620117, 0.5437061786651611, -0.11242544651031494, 0.33348023891448975, -0.4297295808792114, 0.39374685287475586, 0.4776424169540405, 0.1149904727935791, 0.6083381175994873, 0.4791797399520874, -0.006411314010620117, 0.01763319969177246, 0.9673763513565063, 0.05794215202331543, 0.5203644037246704, 0.2980971336364746, 0.0723714828491211, 0.5426254272460938, 0.018733978271484375, 0.5155497789382935, -0.4881160259246826, -0.09693765640258789, 0.1625443696975708, 0.40575408935546875, -0.3240928649902344, 0.23196697235107422, 0.0574641227722168, 0.36378014087677, 0.11222720146179199, 0.4642965793609619, -0.4813481569290161, 0.3270282745361328, 0.27101683616638184, 0.1489330530166626, 0.7456396818161011, 0.5806996822357178, -0.25629448890686035, 0.5756727457046509, -0.35602879524230957, 0.40678632259368896, 0.4018784761428833, -0.10943150520324707, -0.02561020851135254, -0.23667562007904053, -0.33466362953186035, 0.36999082565307617, 0.2665596008300781, 0.4202432632446289, -0.5868726968765259, 0.015591144561767578, 0.2634749412536621, 0.2781710624694824, -0.5212733745574951, 0.3472146987915039, -0.06529688835144043, 0.4012417793273926, 0.7168704271316528, 0.09361779689788818, 0.11843860149383545, 0.2893027067184448, -0.08948731422424316, 0.30954229831695557, 0.23407721519470215, 0.3019266128540039, 0.7448701858520508, 0.46047329902648926, 1.2590324878692627, 0.6799230575561523, 0.30661511421203613, -0.006041526794433594, 1.5213875770568848, 0.6115870475769043, 0.14438438415527344, 1.0097459554672241, 0.19291996955871582, -0.18302536010742188, 0.5037500858306885, -0.2264021635055542, 0.13895392417907715, 0.6229135990142822, -0.1632380485534668, 0.09313929080963135, -0.1716916561126709, 0.3515024185180664], "wall_seconds": 11.565159320831299}
{"timestamp": "2026-04-21T05:10:30Z", "step": 564, "fraction": 1.0, "metric_name": "procedure_margin", "metric_value": 0.23320517301559449, "metric_std": 0.3700106636847924, "per_probe_values": [0.28703761100769043, 0.3401932716369629, 0.06243562698364258, 0.4166675806045532, 0.32406556606292725, -0.0074956417083740234, 0.37607264518737793, 0.4932985305786133, 0.4132869243621826, 0.312946081161499, 0.5538520812988281, -0.5082976818084717, 0.16691601276397705, -0.18013453483581543, 0.6964899301528931, 0.0036841630935668945, 0.15010380744934082, 0.5467402935028076, -0.09487271308898926, 0.3338667154312134, -0.4176006317138672, 0.39865732192993164, 0.49416375160217285, 0.11960864067077637, 0.6267551183700562, 0.48178231716156006, 0.004223227500915527, 0.007275819778442383, 0.9848726987838745, 0.07474660873413086, 0.5355156660079956, 0.2989230155944824, 0.08137059211730957, 0.5547206401824951, 0.015674591064453125, 0.5021933317184448, -0.4811168909072876, -0.09477806091308594, 0.17746484279632568, 0.4065539836883545, -0.3347318172454834, 0.231207013130188, 0.047141313552856445, 0.38365280628204346, 0.12286090850830078, 0.48130154609680176, -0.4664350748062134, 0.3368939161300659, 0.27147912979125977, 0.16270875930786133, 0.7314589023590088, 0.6058752536773682, -0.25297117233276367, 0.5805656909942627, -0.3425956964492798, 0.42926323413848877, 0.40686023235321045, -0.11493897438049316, -0.0062705278396606445, -0.24495768547058105, -0.3317601680755615, 0.36463236808776855, 0.25147247314453125, 0.4569559097290039, -0.5757393836975098, -0.007654905319213867, 0.2497107982635498, 0.2525925636291504, -0.5273846387863159, 0.364742636680603, -0.05180764198303223, 0.3869349956512451, 0.7308008670806885, 0.09380865097045898, 0.13312065601348877, 0.3018585443496704, -0.07151985168457031, 0.33615338802337646, 0.22244906425476074, 0.30123913288116455, 0.7636278867721558, 0.4690206050872803, 1.2384259700775146, 0.7116596698760986, 0.3279975652694702, -0.01973879337310791, 1.5116245746612549, 0.5915408134460449, 0.16308975219726562, 1.0035039186477661, 0.20137596130371094, -0.18200349807739258, 0.5149854421615601, -0.22574687004089355, 0.13248443603515625, 0.6125607490539551, -0.15961265563964844, 0.11340045928955078, -0.16141736507415771, 0.34690260887145996], "wall_seconds": 11.016287565231323}