japhba's picture
Upload eval_log.jsonl for failure_mode_enum
80e3d95 verified
Raw History Blame Contribute Delete
9.06 kB
{"timestamp": "2026-04-21T06:34:51Z", "step": 141, "fraction": 0.25, "metric_name": "procedure_margin", "metric_value": 0.6069618600606919, "metric_std": 0.438936724936368, "per_probe_values": [0.24603843688964844, 1.2443312406539917, 0.18752837181091309, 1.3827115297317505, -0.04594898223876953, 0.42896783351898193, 0.2443227767944336, 0.7940428256988525, 1.0264520645141602, 0.3158003091812134, -0.1126396656036377, 0.6722002029418945, -0.09944379329681396, 0.29664289951324463, 0.2117856740951538, 0.7533138990402222, 1.033814251422882, 0.513967752456665, 1.009741187095642, 1.0516213178634644, 1.0246267318725586, 0.7960375547409058, 1.0874724388122559, 0.3106708526611328, -0.4600266218185425, 0.7372547388076782, 0.7281931638717651, 0.5505306720733643, 0.4999821186065674, 0.4356423616409302, 0.4138098955154419, 0.06481802463531494, 1.0866954922676086, 1.024071455001831, 0.6597479581832886, 0.7169365882873535, -0.13865625858306885, 0.8402633666992188, 1.1236947178840637, 0.2503920793533325, 0.9442301988601685, 0.47235846519470215, 0.35516977310180664, 1.0276252031326294, 0.8059706687927246, 0.1309267282485962, 0.0835573673248291, 0.6686209440231323, 0.08914756774902344, 0.1542341709136963, 0.5726789236068726, 0.09785914421081543, 0.06711483001708984, 1.0444685220718384, 1.1055760383605957, 0.6528815031051636, 1.2797751426696777, 0.001740097999572754, 0.5037223100662231, 0.6847529411315918, 0.4884617328643799, 0.15491223335266113, -0.00806427001953125, 0.9484566450119019, 0.6322081089019775, 0.8775976896286011, 0.14397954940795898, 0.7885713577270508, 1.2415300607681274, 1.0972994565963745, 0.9138684272766113, 0.7840093374252319, 1.344711422920227, 0.3608362674713135, 1.3088446855545044, 0.5528961420059204, 1.1977778673171997, 0.328647255897522, 0.8733134269714355, 0.48255324363708496, 0.2371349334716797, 0.7666631937026978, 0.5997347831726074, 0.18824732303619385, 1.1820425987243652, 0.770761251449585, -0.07375228404998779, 0.9186443090438843, 0.42145025730133057, 0.4741854667663574, 0.36790645122528076, 0.2921113967895508, -0.28729748725891113, 0.9819209575653076, 0.42093729972839355, -0.012728095054626465, 1.5021754503250122, 1.2365527153015137, 1.5724104642868042, 0.9748563766479492], "wall_seconds": 11.550183773040771}
{"timestamp": "2026-04-21T06:41:02Z", "step": 282, "fraction": 0.5, "metric_name": "procedure_margin", "metric_value": 0.557972046136856, "metric_std": 0.4549335442460758, "per_probe_values": [0.21473026275634766, 1.351017951965332, 0.08710050582885742, 1.4616222381591797, -0.13403868675231934, 0.42823874950408936, 0.19223463535308838, 0.8089113235473633, 0.961948037147522, 0.21583235263824463, -0.12839794158935547, 0.6672964096069336, -0.14996790885925293, 0.25695502758026123, 0.1646566390991211, 0.756619930267334, 0.9700574278831482, 0.4433410167694092, 1.0191229581832886, 0.9965635538101196, 0.9845731258392334, 0.7076878547668457, 1.074620246887207, 0.2482912540435791, -0.4759916067123413, 0.6832040548324585, 0.6410200595855713, 0.49443793296813965, 0.5581237077713013, 0.3681032657623291, 0.37967419624328613, 0.008153915405273438, 1.0586223006248474, 1.061168909072876, 0.6588137149810791, 0.5751892328262329, -0.2201787233352661, 0.8922220468521118, 1.089190125465393, 0.2425004243850708, 0.85589599609375, 0.3304569721221924, 0.28734636306762695, 1.006538987159729, 0.7413375377655029, 0.07301533222198486, 0.0949561595916748, 0.6882567405700684, 0.018285512924194336, 0.18348932266235352, 0.3395419120788574, -0.03714156150817871, 0.02069878578186035, 1.0307683944702148, 1.1288628578186035, 0.5596528053283691, 1.3014847040176392, -0.003738880157470703, 0.3576676845550537, 0.576127290725708, 0.41304290294647217, 0.1779465675354004, -0.21592164039611816, 0.8657582998275757, 0.6270077228546143, 0.8061180114746094, -0.012998819351196289, 0.7470201253890991, 1.2254904508590698, 1.0423871278762817, 0.9207253456115723, 0.749697744846344, 1.3274224400520325, 0.36049580574035645, 1.330445647239685, 0.5100516080856323, 1.2047320008277893, 0.28524506092071533, 0.8306581974029541, 0.35120129585266113, 0.4394562244415283, 0.644775390625, 0.4943424463272095, 0.1525421142578125, 1.092415452003479, 0.6669893264770508, -0.09538745880126953, 0.8175995349884033, 0.36283087730407715, 0.38231992721557617, 0.2050853967666626, 0.20789813995361328, -0.43503761291503906, 0.9332960844039917, 0.375805139541626, -0.056819796562194824, 1.504446029663086, 1.0876898765563965, 1.5030593276023865, 0.8005988597869873], "wall_seconds": 11.079483985900879}
{"timestamp": "2026-04-21T06:47:02Z", "step": 423, "fraction": 0.75, "metric_name": "procedure_margin", "metric_value": 0.5140546494722367, "metric_std": 0.49620874475737153, "per_probe_values": [0.1586894989013672, 1.43850839138031, -0.01962578296661377, 1.590624213218689, -0.21886682510375977, 0.4250063896179199, 0.10315179824829102, 0.7876958847045898, 0.9232702255249023, 0.10080909729003906, -0.24703216552734375, 0.6491354703903198, -0.18393349647521973, 0.18056046962738037, 0.03409218788146973, 0.8959697484970093, 0.9348376989364624, 0.3534257411956787, 0.9698325395584106, 1.0525050163269043, 0.961207389831543, 0.6291173696517944, 1.1405998468399048, 0.1321350336074829, -0.6743590831756592, 0.6294784545898438, 0.5353752374649048, 0.41490113735198975, 0.570270299911499, 0.297879695892334, 0.26998281478881836, 0.11905860900878906, 1.0318506956100464, 1.1136308908462524, 0.6348844766616821, 0.46172869205474854, -0.32965993881225586, 0.8444802761077881, 1.063415765762329, 0.2535899877548218, 0.8287065029144287, 0.2690209150314331, 0.22417283058166504, 0.9820418357849121, 0.637629508972168, 0.04545998573303223, 0.02141892910003662, 0.6422797441482544, 0.10686326026916504, 0.2846534252166748, 0.23799729347229004, -0.1392533779144287, -0.07167339324951172, 1.066401481628418, 1.0543689727783203, 0.4072146415710449, 1.451325535774231, -0.08984696865081787, 0.14840734004974365, 0.4550663232803345, 0.3266274929046631, 0.30667543411254883, -0.34932374954223633, 0.7586398124694824, 0.6312787532806396, 0.793485164642334, -0.13067221641540527, 0.6777852773666382, 1.2134629487991333, 1.0435597896575928, 0.873896598815918, 0.7274841070175171, 1.370802640914917, 0.32068681716918945, 1.2991200685501099, 0.41966307163238525, 1.21573805809021, 0.17985296249389648, 0.849240779876709, 0.3864929676055908, 0.4225165843963623, 0.6761802434921265, 0.3512449264526367, 0.08803462982177734, 1.0196994543075562, 0.6244512796401978, -0.10663294792175293, 0.8897824287414551, 0.22793149948120117, 0.29607129096984863, 0.03989148139953613, 0.06592035293579102, -0.6025528907775879, 0.8733209371566772, 0.21642470359802246, -0.11373794078826904, 1.626348853111267, 1.0557093620300293, 1.4995947480201721, 0.7502906322479248], "wall_seconds": 11.258354663848877}
{"timestamp": "2026-04-21T06:53:01Z", "step": 564, "fraction": 1.0, "metric_name": "procedure_margin", "metric_value": 0.5201258718967438, "metric_std": 0.49452798587254587, "per_probe_values": [0.1508617401123047, 1.4381908178329468, -0.011031746864318848, 1.6057403087615967, -0.19915413856506348, 0.4158916473388672, 0.11424505710601807, 0.8092656135559082, 0.9434398412704468, 0.09571874141693115, -0.22511959075927734, 0.6648769378662109, -0.20190179347991943, 0.1836780309677124, 0.03449273109436035, 0.8884973526000977, 0.9519971609115601, 0.3479280471801758, 0.9764856100082397, 1.0579109191894531, 0.9665104150772095, 0.6324659585952759, 1.150787591934204, 0.1440267562866211, -0.6286289691925049, 0.6192866563796997, 0.5196913480758667, 0.4563363790512085, 0.5807545185089111, 0.33580780029296875, 0.27847766876220703, 0.12972617149353027, 1.0372658967971802, 1.1213510036468506, 0.6733260154724121, 0.48085856437683105, -0.3244781494140625, 0.8611682653427124, 1.063415765762329, 0.2295612096786499, 0.8152621984481812, 0.25627732276916504, 0.2373673915863037, 0.9980733394622803, 0.6406360864639282, 0.03610074520111084, 0.02832484245300293, 0.6338801383972168, 0.11232328414916992, 0.2975306510925293, 0.2258284091949463, -0.13958215713500977, -0.05594348907470703, 1.0871974229812622, 1.069336175918579, 0.4309265613555908, 1.4383233785629272, -0.056078195571899414, 0.17245924472808838, 0.47259533405303955, 0.346203088760376, 0.31288766860961914, -0.3240237236022949, 0.7845932245254517, 0.6729981899261475, 0.7850388288497925, -0.14721250534057617, 0.6794745922088623, 1.2228777408599854, 1.0209646224975586, 0.8638453483581543, 0.7409350872039795, 1.3703265190124512, 0.31197023391723633, 1.2844434976577759, 0.4364960193634033, 1.2361226081848145, 0.18182611465454102, 0.8313227891921997, 0.40080738067626953, 0.4029538631439209, 0.6581555604934692, 0.3831667900085449, 0.10687875747680664, 1.0374855995178223, 0.6264355182647705, -0.12204265594482422, 0.8842513561248779, 0.23662829399108887, 0.30416345596313477, 0.06154584884643555, 0.04856252670288086, -0.6247048377990723, 0.8789540529251099, 0.2318284511566162, -0.09554564952850342, 1.6203938722610474, 1.0596567392349243, 1.486108660697937, 0.7452508211135864], "wall_seconds": 11.043708086013794}