[ { "step": 1, "phase": "head", "loss": 1.0358270406723022, "elapsed_seconds": 21.39684887509793 }, { "step": 2, "phase": "head", "loss": 1.5881792306900024, "elapsed_seconds": 42.79299670807086 }, { "step": 3, "phase": "head", "loss": 1.2357892990112305, "elapsed_seconds": 64.26003225008026 }, { "step": 4, "phase": "head", "loss": 1.3240026235580444, "elapsed_seconds": 85.91081562510226 }, { "step": 5, "phase": "head", "loss": 1.1746584177017212, "elapsed_seconds": 108.3202895000577 }, { "step": 6, "phase": "head", "loss": 1.2302554845809937, "elapsed_seconds": 130.1503050409956 }, { "step": 7, "phase": "head", "loss": 1.3740583658218384, "elapsed_seconds": 148.65321262506768 }, { "step": 8, "phase": "head", "loss": 1.430932641029358, "elapsed_seconds": 168.632031083107 }, { "step": 9, "phase": "head", "loss": 1.2234455347061157, "elapsed_seconds": 191.21938154101372 }, { "step": 10, "phase": "head", "loss": 1.424409031867981, "elapsed_seconds": 214.03913691604976 }, { "step": 11, "phase": "head", "loss": 1.5681360960006714, "elapsed_seconds": 236.70183370809536 }, { "step": 12, "phase": "head", "loss": 1.2993026971817017, "elapsed_seconds": 258.2772045410238 }, { "step": 13, "phase": "full", "loss": 1.0054945945739746, "elapsed_seconds": 290.8451167080784 }, { "step": 14, "phase": "full", "loss": 1.4848054647445679, "elapsed_seconds": 327.1629519580165 }, { "step": 15, "phase": "full", "loss": 1.0138325691223145, "elapsed_seconds": 364.1255071250489 }, { "step": 16, "phase": "full", "loss": 0.8827781081199646, "elapsed_seconds": 399.2407686660299 }, { "step": 17, "phase": "full", "loss": 1.8469165563583374, "elapsed_seconds": 434.1073451250559 }, { "step": 18, "phase": "full", "loss": 1.067769169807434, "elapsed_seconds": 469.13596341607627 }, { "step": 19, "phase": "full", "loss": 1.8086286783218384, "elapsed_seconds": 505.47001925006043 }, { "step": 20, "phase": "full", "loss": 1.5421682596206665, "elapsed_seconds": 537.0750485000899 }, { "step": 21, "phase": "full", "loss": 1.3690648078918457, "elapsed_seconds": 571.100124000106 }, { "step": 22, "phase": "full", "loss": 1.7340964078903198, "elapsed_seconds": 611.8985310411081 }, { "step": 23, "phase": "full", "loss": 1.1810988187789917, "elapsed_seconds": 647.113706916105 }, { "step": 24, "phase": "full", "loss": 1.127885341644287, "elapsed_seconds": 680.9674029580783 }, { "step": 25, "phase": "full", "loss": 1.5478988885879517, "elapsed_seconds": 711.7928336660843 }, { "step": 26, "phase": "full", "loss": 0.9801037311553955, "elapsed_seconds": 744.2371533750556 }, { "step": 27, "phase": "full", "loss": 1.036135196685791, "elapsed_seconds": 777.3775073330617 }, { "step": 28, "phase": "full", "loss": 0.7884108424186707, "elapsed_seconds": 811.0509314580122 }, { "step": 29, "phase": "full", "loss": 2.0523478984832764, "elapsed_seconds": 838.6753911660053 }, { "step": 30, "phase": "full", "loss": 0.9070138931274414, "elapsed_seconds": 873.1051842080196 }, { "step": 31, "phase": "full", "loss": 1.4279083013534546, "elapsed_seconds": 904.4878919580951 }, { "step": 32, "phase": "full", "loss": 1.2189459800720215, "elapsed_seconds": 936.015366958105 }, { "step": 33, "phase": "full", "loss": 1.2382389307022095, "elapsed_seconds": 967.0766764160944 }, { "step": 34, "phase": "full", "loss": 1.2455984354019165, "elapsed_seconds": 998.411497916095 }, { "step": 35, "phase": "full", "loss": 1.2292577028274536, "elapsed_seconds": 1030.2807210830506 }, { "step": 36, "phase": "full", "loss": 0.9969069957733154, "elapsed_seconds": 1059.8844907500315, "dev": { "accuracy": 0.34, "gold_nll": 1.1066088529192162, "teacher_ce": null, "questions": 50, "teacher_eligible": 0 } }, { "step": 37, "phase": "full", "loss": 0.999446451663971, "elapsed_seconds": 1146.1770910000196 }, { "step": 38, "phase": "full", "loss": 1.6754002571105957, "elapsed_seconds": 1175.7561304160627 }, { "step": 39, "phase": "full", "loss": 1.3945304155349731, "elapsed_seconds": 1207.6141162500717 }, { "step": 40, "phase": "full", "loss": 0.9822961688041687, "elapsed_seconds": 1240.1644967080792 }, { "step": 41, "phase": "full", "loss": 0.9746001362800598, "elapsed_seconds": 1273.516977958032 }, { "step": 42, "phase": "full", "loss": 0.9670464396476746, "elapsed_seconds": 1305.711035666056 }, { "step": 43, "phase": "full", "loss": 0.9533819556236267, "elapsed_seconds": 1337.8541815410135 }, { "step": 44, "phase": "full", "loss": 0.8764507174491882, "elapsed_seconds": 1369.7520588330226 }, { "step": 45, "phase": "full", "loss": 1.214897632598877, "elapsed_seconds": 1403.6393785000546 }, { "step": 46, "phase": "full", "loss": 1.022074580192566, "elapsed_seconds": 1436.2791370830964 }, { "step": 47, "phase": "full", "loss": 1.3641691207885742, "elapsed_seconds": 1468.7527020830894 }, { "step": 48, "phase": "full", "loss": 1.119236946105957, "elapsed_seconds": 1501.0106077500386 }, { "step": 49, "phase": "full", "loss": 1.347652554512024, "elapsed_seconds": 1532.056193083059 }, { "step": 50, "phase": "full", "loss": 1.057682991027832, "elapsed_seconds": 1564.7776902910555 }, { "step": 51, "phase": "full", "loss": 0.8642177581787109, "elapsed_seconds": 1594.557077625068 }, { "step": 52, "phase": "full", "loss": 1.1096471548080444, "elapsed_seconds": 1627.1093172500841 }, { "step": 53, "phase": "full", "loss": 1.109117865562439, "elapsed_seconds": 1660.6249515000964 }, { "step": 54, "phase": "full", "loss": 0.9797789454460144, "elapsed_seconds": 1693.2616550000384 }, { "step": 55, "phase": "full", "loss": 1.1058478355407715, "elapsed_seconds": 1720.968180625001 }, { "step": 56, "phase": "full", "loss": 1.6776695251464844, "elapsed_seconds": 1753.983091125032 }, { "step": 57, "phase": "full", "loss": 0.808769941329956, "elapsed_seconds": 1791.4561259580078 }, { "step": 58, "phase": "full", "loss": 0.8197898268699646, "elapsed_seconds": 1828.779023375013 }, { "step": 59, "phase": "full", "loss": 1.2141683101654053, "elapsed_seconds": 1865.4919785830425 }, { "step": 60, "phase": "full", "loss": 0.9604911804199219, "elapsed_seconds": 1902.7801405410282, "dev": { "accuracy": 0.48, "gold_nll": 1.0355953628363117, "teacher_ce": null, "questions": 50, "teacher_eligible": 0 } }, { "step": 61, "phase": "full", "loss": 1.2589226961135864, "elapsed_seconds": 1997.138345125015 }, { "step": 62, "phase": "full", "loss": 1.0764788389205933, "elapsed_seconds": 2033.710818874999 }, { "step": 63, "phase": "full", "loss": 1.1432734727859497, "elapsed_seconds": 2069.9912491251016 }, { "step": 64, "phase": "full", "loss": 1.152356743812561, "elapsed_seconds": 2106.7415259160334 }, { "step": 65, "phase": "full", "loss": 1.1369611024856567, "elapsed_seconds": 2143.2124613750493 }, { "step": 66, "phase": "full", "loss": 0.9269376397132874, "elapsed_seconds": 2177.4336624999996 }, { "step": 67, "phase": "full", "loss": 0.995410680770874, "elapsed_seconds": 2210.468237083056 }, { "step": 68, "phase": "full", "loss": 0.9980621933937073, "elapsed_seconds": 2244.7994083750527 }, { "step": 69, "phase": "full", "loss": 1.3542309999465942, "elapsed_seconds": 2278.506003541057 }, { "step": 70, "phase": "full", "loss": 1.1022883653640747, "elapsed_seconds": 2315.237080082996 }, { "step": 71, "phase": "full", "loss": 1.1127184629440308, "elapsed_seconds": 2346.8299000000115 }, { "step": 72, "phase": "full", "loss": 1.3658493757247925, "elapsed_seconds": 2377.773851541104 }, { "step": 73, "phase": "full", "loss": 0.9688565135002136, "elapsed_seconds": 2412.419474708033 }, { "step": 74, "phase": "full", "loss": 1.1298896074295044, "elapsed_seconds": 2443.605044750031 }, { "step": 75, "phase": "full", "loss": 0.9623610973358154, "elapsed_seconds": 2482.2857223750325 }, { "step": 76, "phase": "full", "loss": 0.9433451294898987, "elapsed_seconds": 2516.0513795410516 }, { "step": 77, "phase": "full", "loss": 1.1114636659622192, "elapsed_seconds": 2552.553472083062 }, { "step": 78, "phase": "full", "loss": 1.1702417135238647, "elapsed_seconds": 2585.3947185410652 }, { "step": 79, "phase": "full", "loss": 1.0909785032272339, "elapsed_seconds": 2622.1417561250273 }, { "step": 80, "phase": "full", "loss": 0.8747878074645996, "elapsed_seconds": 2657.6104994160123 }, { "step": 81, "phase": "full", "loss": 1.0923250913619995, "elapsed_seconds": 2693.5562725410564 }, { "step": 82, "phase": "full", "loss": 0.929922878742218, "elapsed_seconds": 2730.1534381250385 }, { "step": 83, "phase": "full", "loss": 0.7892135977745056, "elapsed_seconds": 2765.7202479580883 }, { "step": 84, "phase": "full", "loss": 0.8119182586669922, "elapsed_seconds": 2799.8012705410365, "dev": { "accuracy": 0.62, "gold_nll": 0.9414974572163429, "teacher_ce": null, "questions": 50, "teacher_eligible": 0 } }, { "step": 85, "phase": "full", "loss": 1.0668119192123413, "elapsed_seconds": 2894.236054625013 }, { "step": 86, "phase": "full", "loss": 0.8388192057609558, "elapsed_seconds": 2925.2011398330797 }, { "step": 87, "phase": "full", "loss": 1.0404200553894043, "elapsed_seconds": 2960.118140541017 }, { "step": 88, "phase": "full", "loss": 1.1635769605636597, "elapsed_seconds": 2995.7363711250946 }, { "step": 89, "phase": "full", "loss": 0.9327297210693359, "elapsed_seconds": 3031.9887070000404 }, { "step": 90, "phase": "full", "loss": 1.2483664751052856, "elapsed_seconds": 3061.8583062910475 }, { "step": 91, "phase": "full", "loss": 1.120055079460144, "elapsed_seconds": 3098.2382230410585 }, { "step": 92, "phase": "full", "loss": 1.1743687391281128, "elapsed_seconds": 3133.5135199161014 }, { "step": 93, "phase": "full", "loss": 1.1146589517593384, "elapsed_seconds": 3166.7914327910403 }, { "step": 94, "phase": "full", "loss": 0.7118216156959534, "elapsed_seconds": 3202.858146833023 }, { "step": 95, "phase": "full", "loss": 1.198585867881775, "elapsed_seconds": 3248.5645672910614 }, { "step": 96, "phase": "full", "loss": 0.9387406706809998, "elapsed_seconds": 3291.0167002500966 }, { "step": 97, "phase": "full", "loss": 1.123163104057312, "elapsed_seconds": 3336.526148333098 }, { "step": 98, "phase": "full", "loss": 0.7781522870063782, "elapsed_seconds": 3381.942671541008 }, { "step": 99, "phase": "full", "loss": 0.8041679859161377, "elapsed_seconds": 3427.6462735830573 }, { "step": 100, "phase": "full", "loss": 1.1331572532653809, "elapsed_seconds": 3474.8257086660014 }, { "step": 101, "phase": "full", "loss": 0.7643924355506897, "elapsed_seconds": 3520.876902583055 }, { "step": 102, "phase": "full", "loss": 0.5184159278869629, "elapsed_seconds": 3566.434486416052 }, { "step": 103, "phase": "full", "loss": 0.9888486266136169, "elapsed_seconds": 3612.2333593750373 }, { "step": 104, "phase": "full", "loss": 1.2430120706558228, "elapsed_seconds": 3658.180246666074 }, { "step": 105, "phase": "full", "loss": 0.5914709568023682, "elapsed_seconds": 3703.805315750069 }, { "step": 106, "phase": "full", "loss": 0.9983817934989929, "elapsed_seconds": 3808.800364500028 }, { "step": 107, "phase": "full", "loss": 0.8642576336860657, "elapsed_seconds": 3859.2171355410246 }, { "step": 108, "phase": "full", "loss": 1.1259199380874634, "elapsed_seconds": 3911.1026910830988, "dev": { "accuracy": 0.6, "gold_nll": 0.868566937740362, "teacher_ce": null, "questions": 50, "teacher_eligible": 0 } }, { "step": 109, "phase": "full", "loss": 0.8820890784263611, "elapsed_seconds": 4022.135893583065 }, { "step": 110, "phase": "full", "loss": 0.716766893863678, "elapsed_seconds": 4064.106598541024 }, { "step": 111, "phase": "full", "loss": 0.4306957423686981, "elapsed_seconds": 4105.331478875014 }, { "step": 112, "phase": "full", "loss": 2.0974812507629395, "elapsed_seconds": 4144.091363250045 }, { "step": 113, "phase": "full", "loss": 0.8339252471923828, "elapsed_seconds": 4189.388471125043 }, { "step": 114, "phase": "full", "loss": 1.2878187894821167, "elapsed_seconds": 4232.910714208032 }, { "step": 115, "phase": "full", "loss": 1.016721487045288, "elapsed_seconds": 4277.685553250019 }, { "step": 116, "phase": "full", "loss": 0.3491600453853607, "elapsed_seconds": 4323.378575333045 }, { "step": 117, "phase": "full", "loss": 1.4855451583862305, "elapsed_seconds": 4369.0337449579965 }, { "step": 118, "phase": "full", "loss": 0.7524747848510742, "elapsed_seconds": 4396.502832333092 }, { "step": 119, "phase": "full", "loss": 0.9670575261116028, "elapsed_seconds": 4426.10171395808 }, { "step": 120, "phase": "full", "loss": 0.8021886944770813, "elapsed_seconds": 4456.3194979580585 }, { "step": 121, "phase": "full", "loss": 1.1986188888549805, "elapsed_seconds": 4485.911970500019 }, { "step": 122, "phase": "full", "loss": 0.7328621745109558, "elapsed_seconds": 4518.876338083064 }, { "step": 123, "phase": "full", "loss": 1.3201788663864136, "elapsed_seconds": 4550.01389583305 }, { "step": 124, "phase": "full", "loss": 1.326168417930603, "elapsed_seconds": 4577.6777439580765 }, { "step": 125, "phase": "full", "loss": 0.7888900637626648, "elapsed_seconds": 4611.207910416066 }, { "step": 126, "phase": "full", "loss": 0.8839451670646667, "elapsed_seconds": 4642.470088458038 }, { "step": 127, "phase": "full", "loss": 1.181211233139038, "elapsed_seconds": 4679.391682540998 }, { "step": 128, "phase": "full", "loss": 0.894436776638031, "elapsed_seconds": 4714.468261875096 }, { "step": 129, "phase": "full", "loss": 1.0543349981307983, "elapsed_seconds": 4747.0247316660825 }, { "step": 130, "phase": "full", "loss": 1.343135952949524, "elapsed_seconds": 4780.644504375057 }, { "step": 131, "phase": "full", "loss": 1.2927340269088745, "elapsed_seconds": 4812.570610583061 }, { "step": 132, "phase": "full", "loss": 1.1182122230529785, "elapsed_seconds": 4845.136953916051, "dev": { "accuracy": 0.62, "gold_nll": 0.8775507748777074, "teacher_ce": null, "questions": 50, "teacher_eligible": 0 } } ]