| { | |
| "best_metric": 0.23624150454998016, | |
| "best_model_checkpoint": "data/hansken_human_hql/checkpoint-511", | |
| "epoch": 9.995110024449877, | |
| "eval_steps": 500, | |
| "global_step": 1022, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009779951100244499, | |
| "grad_norm": 1.0709587335586548, | |
| "learning_rate": 9.80392156862745e-07, | |
| "loss": 1.4707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0488997555012225, | |
| "grad_norm": 1.1860318183898926, | |
| "learning_rate": 4.901960784313726e-06, | |
| "loss": 1.4227, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.097799511002445, | |
| "grad_norm": 1.145372986793518, | |
| "learning_rate": 9.803921568627451e-06, | |
| "loss": 1.444, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1466992665036675, | |
| "grad_norm": 1.0051456689834595, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 1.3414, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19559902200489, | |
| "grad_norm": 0.5133008360862732, | |
| "learning_rate": 1.9607843137254903e-05, | |
| "loss": 1.2116, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24449877750611246, | |
| "grad_norm": 0.41832494735717773, | |
| "learning_rate": 2.4509803921568626e-05, | |
| "loss": 1.1424, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.293398533007335, | |
| "grad_norm": 0.41829216480255127, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 1.143, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3422982885085575, | |
| "grad_norm": 0.35495856404304504, | |
| "learning_rate": 3.431372549019608e-05, | |
| "loss": 1.0472, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.39119804400978, | |
| "grad_norm": 0.40399229526519775, | |
| "learning_rate": 3.9215686274509805e-05, | |
| "loss": 0.9879, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4400977995110024, | |
| "grad_norm": 0.31430941820144653, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 0.9467, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4889975550122249, | |
| "grad_norm": 0.29712405800819397, | |
| "learning_rate": 4.901960784313725e-05, | |
| "loss": 0.885, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5378973105134475, | |
| "grad_norm": 0.40078112483024597, | |
| "learning_rate": 5.392156862745098e-05, | |
| "loss": 0.7973, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.58679706601467, | |
| "grad_norm": 0.34199750423431396, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.776, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6356968215158925, | |
| "grad_norm": 0.4243955910205841, | |
| "learning_rate": 6.372549019607843e-05, | |
| "loss": 0.651, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.684596577017115, | |
| "grad_norm": 0.30432572960853577, | |
| "learning_rate": 6.862745098039216e-05, | |
| "loss": 0.5769, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7334963325183375, | |
| "grad_norm": 0.27279356122016907, | |
| "learning_rate": 7.352941176470589e-05, | |
| "loss": 0.5436, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.78239608801956, | |
| "grad_norm": 0.2576221823692322, | |
| "learning_rate": 7.843137254901961e-05, | |
| "loss": 0.501, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8312958435207825, | |
| "grad_norm": 0.22290439903736115, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.4915, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8801955990220048, | |
| "grad_norm": 0.21740856766700745, | |
| "learning_rate": 8.823529411764706e-05, | |
| "loss": 0.4487, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9290953545232273, | |
| "grad_norm": 0.21560043096542358, | |
| "learning_rate": 9.313725490196079e-05, | |
| "loss": 0.4351, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9779951100244498, | |
| "grad_norm": 0.2607389986515045, | |
| "learning_rate": 9.80392156862745e-05, | |
| "loss": 0.4508, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9975550122249389, | |
| "eval_loss": 0.44326770305633545, | |
| "eval_runtime": 398.4802, | |
| "eval_samples_per_second": 1.029, | |
| "eval_steps_per_second": 1.029, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.0268948655256724, | |
| "grad_norm": 0.21888603270053864, | |
| "learning_rate": 0.00010294117647058823, | |
| "loss": 0.3968, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.075794621026895, | |
| "grad_norm": 0.21742066740989685, | |
| "learning_rate": 0.00010784313725490196, | |
| "loss": 0.3785, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.1246943765281174, | |
| "grad_norm": 0.2523965537548065, | |
| "learning_rate": 0.0001127450980392157, | |
| "loss": 0.4034, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.17359413202934, | |
| "grad_norm": 0.2155005782842636, | |
| "learning_rate": 0.00011764705882352942, | |
| "loss": 0.3766, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2224938875305624, | |
| "grad_norm": 0.25576308369636536, | |
| "learning_rate": 0.00012254901960784316, | |
| "loss": 0.364, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.271393643031785, | |
| "grad_norm": 0.2288295179605484, | |
| "learning_rate": 0.00012745098039215687, | |
| "loss": 0.3451, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.3202933985330074, | |
| "grad_norm": 0.2045079469680786, | |
| "learning_rate": 0.0001323529411764706, | |
| "loss": 0.3425, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.36919315403423, | |
| "grad_norm": 0.2297014445066452, | |
| "learning_rate": 0.0001372549019607843, | |
| "loss": 0.3658, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4180929095354524, | |
| "grad_norm": 0.2170581817626953, | |
| "learning_rate": 0.00014215686274509804, | |
| "loss": 0.3482, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.466992665036675, | |
| "grad_norm": 0.2250969409942627, | |
| "learning_rate": 0.00014705882352941178, | |
| "loss": 0.3353, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5158924205378974, | |
| "grad_norm": 0.23191578686237335, | |
| "learning_rate": 0.00015196078431372549, | |
| "loss": 0.3271, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.56479217603912, | |
| "grad_norm": 0.2477528601884842, | |
| "learning_rate": 0.00015686274509803922, | |
| "loss": 0.3549, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6136919315403424, | |
| "grad_norm": 0.20846064388751984, | |
| "learning_rate": 0.00016176470588235295, | |
| "loss": 0.3171, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.662591687041565, | |
| "grad_norm": 0.21829602122306824, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.3642, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.7114914425427874, | |
| "grad_norm": 0.22842282056808472, | |
| "learning_rate": 0.0001715686274509804, | |
| "loss": 0.3116, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.76039119804401, | |
| "grad_norm": 0.24106037616729736, | |
| "learning_rate": 0.00017647058823529413, | |
| "loss": 0.3066, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8092909535452324, | |
| "grad_norm": 0.25696486234664917, | |
| "learning_rate": 0.00018137254901960786, | |
| "loss": 0.3053, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.858190709046455, | |
| "grad_norm": 0.22010771930217743, | |
| "learning_rate": 0.00018627450980392157, | |
| "loss": 0.3233, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.9070904645476774, | |
| "grad_norm": 0.2373352199792862, | |
| "learning_rate": 0.0001911764705882353, | |
| "loss": 0.3102, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.9559902200488999, | |
| "grad_norm": 0.21177123486995697, | |
| "learning_rate": 0.000196078431372549, | |
| "loss": 0.302, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.9951100244498776, | |
| "eval_loss": 0.3139691650867462, | |
| "eval_runtime": 387.4792, | |
| "eval_samples_per_second": 1.058, | |
| "eval_steps_per_second": 1.058, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.0048899755501224, | |
| "grad_norm": 0.2193712592124939, | |
| "learning_rate": 0.00019999985360565867, | |
| "loss": 0.2813, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.053789731051345, | |
| "grad_norm": 0.3371932804584503, | |
| "learning_rate": 0.00019999472984871732, | |
| "loss": 0.2844, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.1026894865525674, | |
| "grad_norm": 0.23578821122646332, | |
| "learning_rate": 0.00019998228680332932, | |
| "loss": 0.263, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.15158924205379, | |
| "grad_norm": 0.27435311675071716, | |
| "learning_rate": 0.00019996252538028507, | |
| "loss": 0.2752, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.2004889975550124, | |
| "grad_norm": 0.24362725019454956, | |
| "learning_rate": 0.00019993544702605638, | |
| "loss": 0.2572, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.249388753056235, | |
| "grad_norm": 0.24360118806362152, | |
| "learning_rate": 0.0001999010537226905, | |
| "loss": 0.3191, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.2982885085574574, | |
| "grad_norm": 0.2612737715244293, | |
| "learning_rate": 0.0001998593479876652, | |
| "loss": 0.2506, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.34718826405868, | |
| "grad_norm": 0.21556636691093445, | |
| "learning_rate": 0.00019981033287370443, | |
| "loss": 0.2416, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.3960880195599024, | |
| "grad_norm": 0.22406277060508728, | |
| "learning_rate": 0.00019975401196855482, | |
| "loss": 0.273, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.444987775061125, | |
| "grad_norm": 0.3020350933074951, | |
| "learning_rate": 0.00019969038939472315, | |
| "loss": 0.2457, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.4938875305623474, | |
| "grad_norm": 0.20698243379592896, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 0.2569, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.54278728606357, | |
| "grad_norm": 0.4294751286506653, | |
| "learning_rate": 0.00019954125840299165, | |
| "loss": 0.2246, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.591687041564792, | |
| "grad_norm": 0.37185847759246826, | |
| "learning_rate": 0.00019945576090099452, | |
| "loss": 0.229, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.640586797066015, | |
| "grad_norm": 0.2863105237483978, | |
| "learning_rate": 0.00019936298356132176, | |
| "loss": 0.2338, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.689486552567237, | |
| "grad_norm": 0.19301028549671173, | |
| "learning_rate": 0.00019926293317497245, | |
| "loss": 0.2167, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.73838630806846, | |
| "grad_norm": 0.22075964510440826, | |
| "learning_rate": 0.00019915561706530883, | |
| "loss": 0.2367, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.787286063569682, | |
| "grad_norm": 0.22829142212867737, | |
| "learning_rate": 0.0001990410430875205, | |
| "loss": 0.245, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.836185819070905, | |
| "grad_norm": 0.1982724666595459, | |
| "learning_rate": 0.00019891921962804943, | |
| "loss": 0.217, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.885085574572127, | |
| "grad_norm": 0.23672354221343994, | |
| "learning_rate": 0.00019879015560397587, | |
| "loss": 0.2298, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.93398533007335, | |
| "grad_norm": 0.21391943097114563, | |
| "learning_rate": 0.00019865386046236596, | |
| "loss": 0.2326, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.982885085574572, | |
| "grad_norm": 0.19821615517139435, | |
| "learning_rate": 0.00019851034417958, | |
| "loss": 0.2692, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.9926650366748166, | |
| "eval_loss": 0.2616053521633148, | |
| "eval_runtime": 387.9813, | |
| "eval_samples_per_second": 1.057, | |
| "eval_steps_per_second": 1.057, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 3.031784841075795, | |
| "grad_norm": 0.22108572721481323, | |
| "learning_rate": 0.0001983596172605423, | |
| "loss": 0.2104, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.0806845965770173, | |
| "grad_norm": 0.24487629532814026, | |
| "learning_rate": 0.00019820169073797228, | |
| "loss": 0.1942, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 3.12958435207824, | |
| "grad_norm": 0.2110164612531662, | |
| "learning_rate": 0.0001980365761715769, | |
| "loss": 0.1833, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.178484107579462, | |
| "grad_norm": 0.20861805975437164, | |
| "learning_rate": 0.0001978642856472045, | |
| "loss": 0.1981, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.227383863080685, | |
| "grad_norm": 0.1969948559999466, | |
| "learning_rate": 0.0001976848317759601, | |
| "loss": 0.1868, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.276283618581907, | |
| "grad_norm": 0.19443638622760773, | |
| "learning_rate": 0.0001974982276932824, | |
| "loss": 0.1902, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 3.32518337408313, | |
| "grad_norm": 0.30058181285858154, | |
| "learning_rate": 0.00019730448705798239, | |
| "loss": 0.2241, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.374083129584352, | |
| "grad_norm": 0.21647138893604279, | |
| "learning_rate": 0.00019710362405124334, | |
| "loss": 0.1838, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.422982885085575, | |
| "grad_norm": 0.19676022231578827, | |
| "learning_rate": 0.00019689565337558288, | |
| "loss": 0.1961, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.471882640586797, | |
| "grad_norm": 0.2371009737253189, | |
| "learning_rate": 0.00019668059025377703, | |
| "loss": 0.2052, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 3.52078239608802, | |
| "grad_norm": 0.21014133095741272, | |
| "learning_rate": 0.00019645845042774553, | |
| "loss": 0.1987, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.569682151589242, | |
| "grad_norm": 0.2178957760334015, | |
| "learning_rate": 0.00019622925015739997, | |
| "loss": 0.1903, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 3.618581907090465, | |
| "grad_norm": 0.21497862040996552, | |
| "learning_rate": 0.0001959930062194534, | |
| "loss": 0.2, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.667481662591687, | |
| "grad_norm": 0.22582682967185974, | |
| "learning_rate": 0.00019574973590619243, | |
| "loss": 0.1868, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 3.71638141809291, | |
| "grad_norm": 0.1827058047056198, | |
| "learning_rate": 0.00019549945702421144, | |
| "loss": 0.2172, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.765281173594132, | |
| "grad_norm": 0.19827835261821747, | |
| "learning_rate": 0.00019524218789310912, | |
| "loss": 0.1785, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 3.8141809290953548, | |
| "grad_norm": 0.2121572494506836, | |
| "learning_rate": 0.0001949779473441478, | |
| "loss": 0.1795, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.863080684596577, | |
| "grad_norm": 0.20197761058807373, | |
| "learning_rate": 0.0001947067547188747, | |
| "loss": 0.19, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 3.9119804400977998, | |
| "grad_norm": 0.21854069828987122, | |
| "learning_rate": 0.00019442862986770646, | |
| "loss": 0.1886, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.960880195599022, | |
| "grad_norm": 0.20974552631378174, | |
| "learning_rate": 0.0001941435931484761, | |
| "loss": 0.177, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.24309584498405457, | |
| "eval_runtime": 399.7773, | |
| "eval_samples_per_second": 1.026, | |
| "eval_steps_per_second": 1.026, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 4.009779951100245, | |
| "grad_norm": 0.19041913747787476, | |
| "learning_rate": 0.0001938516654249428, | |
| "loss": 0.1709, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.058679706601467, | |
| "grad_norm": 0.22610776126384735, | |
| "learning_rate": 0.00019355286806526493, | |
| "loss": 0.158, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 4.10757946210269, | |
| "grad_norm": 0.2044234424829483, | |
| "learning_rate": 0.00019324722294043558, | |
| "loss": 0.1522, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.156479217603912, | |
| "grad_norm": 0.2402704805135727, | |
| "learning_rate": 0.00019293475242268223, | |
| "loss": 0.1509, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 4.205378973105135, | |
| "grad_norm": 0.20224688947200775, | |
| "learning_rate": 0.0001926154793838288, | |
| "loss": 0.1565, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.254278728606357, | |
| "grad_norm": 0.21887710690498352, | |
| "learning_rate": 0.00019228942719362143, | |
| "loss": 0.1551, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 4.30317848410758, | |
| "grad_norm": 0.20886527001857758, | |
| "learning_rate": 0.00019195661971801827, | |
| "loss": 0.1568, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.352078239608802, | |
| "grad_norm": 0.21612216532230377, | |
| "learning_rate": 0.00019161708131744222, | |
| "loss": 0.1516, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 4.400977995110025, | |
| "grad_norm": 0.20036669075489044, | |
| "learning_rate": 0.00019127083684499806, | |
| "loss": 0.1529, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.449877750611247, | |
| "grad_norm": 0.3197900950908661, | |
| "learning_rate": 0.00019091791164465305, | |
| "loss": 0.1854, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 4.49877750611247, | |
| "grad_norm": 0.18851010501384735, | |
| "learning_rate": 0.00019055833154938207, | |
| "loss": 0.1574, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.547677261613692, | |
| "grad_norm": 0.214978888630867, | |
| "learning_rate": 0.00019019212287927663, | |
| "loss": 0.1555, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 4.596577017114915, | |
| "grad_norm": 0.21155217289924622, | |
| "learning_rate": 0.00018981931243961824, | |
| "loss": 0.176, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.645476772616137, | |
| "grad_norm": 0.18137674033641815, | |
| "learning_rate": 0.00018943992751891653, | |
| "loss": 0.1575, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 4.69437652811736, | |
| "grad_norm": 0.24663567543029785, | |
| "learning_rate": 0.00018905399588691163, | |
| "loss": 0.1568, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.743276283618582, | |
| "grad_norm": 0.19319510459899902, | |
| "learning_rate": 0.0001886615457925417, | |
| "loss": 0.1547, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 4.792176039119805, | |
| "grad_norm": 0.18611547350883484, | |
| "learning_rate": 0.00018826260596187505, | |
| "loss": 0.1755, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.841075794621027, | |
| "grad_norm": 0.47814473509788513, | |
| "learning_rate": 0.00018785720559600752, | |
| "loss": 0.1647, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 4.88997555012225, | |
| "grad_norm": 0.19350242614746094, | |
| "learning_rate": 0.00018744537436892516, | |
| "loss": 0.155, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.938875305623472, | |
| "grad_norm": 0.19956329464912415, | |
| "learning_rate": 0.00018702714242533204, | |
| "loss": 0.156, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 4.987775061124695, | |
| "grad_norm": 0.20709875226020813, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.1616, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.997555012224939, | |
| "eval_loss": 0.23624150454998016, | |
| "eval_runtime": 387.7068, | |
| "eval_samples_per_second": 1.058, | |
| "eval_steps_per_second": 1.058, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 5.036674816625917, | |
| "grad_norm": 0.22790652513504028, | |
| "learning_rate": 0.00018617159930774715, | |
| "loss": 0.1377, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 5.08557457212714, | |
| "grad_norm": 0.21796418726444244, | |
| "learning_rate": 0.00018573435075672424, | |
| "loss": 0.1326, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.134474327628362, | |
| "grad_norm": 0.19105204939842224, | |
| "learning_rate": 0.00018529082673054457, | |
| "loss": 0.1303, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 5.183374083129585, | |
| "grad_norm": 0.2682870328426361, | |
| "learning_rate": 0.00018484105969372182, | |
| "loss": 0.1316, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.232273838630807, | |
| "grad_norm": 0.18370023369789124, | |
| "learning_rate": 0.00018438508256773785, | |
| "loss": 0.1323, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 5.28117359413203, | |
| "grad_norm": 0.24072639644145966, | |
| "learning_rate": 0.00018392292872863267, | |
| "loss": 0.1332, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.330073349633252, | |
| "grad_norm": 0.19523735344409943, | |
| "learning_rate": 0.00018345463200456164, | |
| "loss": 0.1344, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 5.378973105134475, | |
| "grad_norm": 0.24865508079528809, | |
| "learning_rate": 0.0001829802266733193, | |
| "loss": 0.1359, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.427872860635697, | |
| "grad_norm": 0.2039840966463089, | |
| "learning_rate": 0.00018249974745983023, | |
| "loss": 0.1337, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 5.47677261613692, | |
| "grad_norm": 0.20024679601192474, | |
| "learning_rate": 0.00018201322953360758, | |
| "loss": 0.154, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.525672371638142, | |
| "grad_norm": 0.1976476013660431, | |
| "learning_rate": 0.0001815207085061784, | |
| "loss": 0.1353, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 5.574572127139365, | |
| "grad_norm": 0.1974327266216278, | |
| "learning_rate": 0.00018102222042847737, | |
| "loss": 0.1373, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.623471882640587, | |
| "grad_norm": 0.27005520462989807, | |
| "learning_rate": 0.00018051780178820765, | |
| "loss": 0.1437, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 5.67237163814181, | |
| "grad_norm": 0.20781448483467102, | |
| "learning_rate": 0.00018000748950717038, | |
| "loss": 0.1322, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.721271393643032, | |
| "grad_norm": 0.20179703831672668, | |
| "learning_rate": 0.000179491320938562, | |
| "loss": 0.1378, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 5.770171149144255, | |
| "grad_norm": 0.22105282545089722, | |
| "learning_rate": 0.00017896933386423998, | |
| "loss": 0.136, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.819070904645477, | |
| "grad_norm": 0.4113224446773529, | |
| "learning_rate": 0.00017844156649195759, | |
| "loss": 0.1495, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 5.8679706601467, | |
| "grad_norm": 0.20451286435127258, | |
| "learning_rate": 0.00017790805745256704, | |
| "loss": 0.1318, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.916870415647922, | |
| "grad_norm": 0.18566569685935974, | |
| "learning_rate": 0.0001773688457971919, | |
| "loss": 0.1359, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 5.965770171149144, | |
| "grad_norm": 0.1862591803073883, | |
| "learning_rate": 0.0001768239709943686, | |
| "loss": 0.1358, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.995110024449878, | |
| "eval_loss": 0.23938237130641937, | |
| "eval_runtime": 387.8478, | |
| "eval_samples_per_second": 1.057, | |
| "eval_steps_per_second": 1.057, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 6.014669926650367, | |
| "grad_norm": 0.16670842468738556, | |
| "learning_rate": 0.0001762734729271575, | |
| "loss": 0.1275, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 6.06356968215159, | |
| "grad_norm": 0.23901741206645966, | |
| "learning_rate": 0.00017571739189022365, | |
| "loss": 0.1113, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.112469437652812, | |
| "grad_norm": 0.19317218661308289, | |
| "learning_rate": 0.00017515576858688722, | |
| "loss": 0.1101, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 6.161369193154035, | |
| "grad_norm": 0.21369099617004395, | |
| "learning_rate": 0.00017458864412614434, | |
| "loss": 0.1122, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.210268948655257, | |
| "grad_norm": 0.21011659502983093, | |
| "learning_rate": 0.00017401606001965782, | |
| "loss": 0.1136, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 6.25916870415648, | |
| "grad_norm": 0.1860456019639969, | |
| "learning_rate": 0.00017343805817871886, | |
| "loss": 0.1305, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.308068459657702, | |
| "grad_norm": 0.23417602479457855, | |
| "learning_rate": 0.00017285468091117904, | |
| "loss": 0.1165, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 6.356968215158924, | |
| "grad_norm": 0.189472958445549, | |
| "learning_rate": 0.00017226597091835378, | |
| "loss": 0.119, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.405867970660147, | |
| "grad_norm": 0.2460348904132843, | |
| "learning_rate": 0.00017167197129189652, | |
| "loss": 0.1188, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 6.45476772616137, | |
| "grad_norm": 0.20059679448604584, | |
| "learning_rate": 0.00017107272551064473, | |
| "loss": 0.1194, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.503667481662592, | |
| "grad_norm": 0.19838838279247284, | |
| "learning_rate": 0.00017046827743743726, | |
| "loss": 0.1165, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 6.552567237163814, | |
| "grad_norm": 0.20280085504055023, | |
| "learning_rate": 0.00016985867131590383, | |
| "loss": 0.1168, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.601466992665037, | |
| "grad_norm": 0.27974265813827515, | |
| "learning_rate": 0.00016924395176722647, | |
| "loss": 0.122, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 6.65036674816626, | |
| "grad_norm": 0.1994495540857315, | |
| "learning_rate": 0.0001686241637868734, | |
| "loss": 0.1173, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.699266503667482, | |
| "grad_norm": 0.20043040812015533, | |
| "learning_rate": 0.00016799935274130546, | |
| "loss": 0.1183, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 6.748166259168704, | |
| "grad_norm": 0.19184747338294983, | |
| "learning_rate": 0.00016736956436465573, | |
| "loss": 0.1192, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.797066014669927, | |
| "grad_norm": 0.20747938752174377, | |
| "learning_rate": 0.00016673484475538146, | |
| "loss": 0.1188, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 6.84596577017115, | |
| "grad_norm": 0.19285354018211365, | |
| "learning_rate": 0.00016609524037289019, | |
| "loss": 0.117, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.894865525672372, | |
| "grad_norm": 0.18242338299751282, | |
| "learning_rate": 0.00016545079803413892, | |
| "loss": 0.1208, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 6.943765281173594, | |
| "grad_norm": 0.19887416064739227, | |
| "learning_rate": 0.00016480156491020727, | |
| "loss": 0.1227, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.992665036674817, | |
| "grad_norm": 0.19773922860622406, | |
| "learning_rate": 0.00016414758852284478, | |
| "loss": 0.1199, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 6.992665036674817, | |
| "eval_loss": 0.24741248786449432, | |
| "eval_runtime": 387.335, | |
| "eval_samples_per_second": 1.059, | |
| "eval_steps_per_second": 1.059, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 7.041564792176039, | |
| "grad_norm": 0.5106807351112366, | |
| "learning_rate": 0.0001634889167409923, | |
| "loss": 0.1051, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.090464547677262, | |
| "grad_norm": 0.18619847297668457, | |
| "learning_rate": 0.0001628255977772784, | |
| "loss": 0.0979, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 7.139364303178484, | |
| "grad_norm": 0.18676620721817017, | |
| "learning_rate": 0.00016215768018449012, | |
| "loss": 0.1009, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 7.188264058679707, | |
| "grad_norm": 0.2054695338010788, | |
| "learning_rate": 0.00016148521285201927, | |
| "loss": 0.1002, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 7.237163814180929, | |
| "grad_norm": 0.20496530830860138, | |
| "learning_rate": 0.00016080824500228367, | |
| "loss": 0.1011, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 7.286063569682152, | |
| "grad_norm": 0.18679122626781464, | |
| "learning_rate": 0.0001601268261871244, | |
| "loss": 0.1052, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 7.334963325183374, | |
| "grad_norm": 0.20614224672317505, | |
| "learning_rate": 0.00015944100628417868, | |
| "loss": 0.1021, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.383863080684597, | |
| "grad_norm": 0.20026642084121704, | |
| "learning_rate": 0.00015875083549322908, | |
| "loss": 0.1019, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 7.432762836185819, | |
| "grad_norm": 0.1852520853281021, | |
| "learning_rate": 0.00015805636433252891, | |
| "loss": 0.1028, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.481662591687042, | |
| "grad_norm": 0.19096429646015167, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 0.1031, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 7.530562347188264, | |
| "grad_norm": 0.18263529241085052, | |
| "learning_rate": 0.00015665472454503483, | |
| "loss": 0.1033, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.579462102689487, | |
| "grad_norm": 0.1884106546640396, | |
| "learning_rate": 0.00015594765851370684, | |
| "loss": 0.1063, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 7.628361858190709, | |
| "grad_norm": 0.2005338817834854, | |
| "learning_rate": 0.0001552364972960506, | |
| "loss": 0.1054, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.677261613691932, | |
| "grad_norm": 0.184016153216362, | |
| "learning_rate": 0.0001545212929467503, | |
| "loss": 0.1048, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 7.726161369193154, | |
| "grad_norm": 0.19765067100524902, | |
| "learning_rate": 0.0001538020978164341, | |
| "loss": 0.1044, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 7.775061124694377, | |
| "grad_norm": 0.18265607953071594, | |
| "learning_rate": 0.0001530789645478426, | |
| "loss": 0.1051, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 7.823960880195599, | |
| "grad_norm": 0.19815443456172943, | |
| "learning_rate": 0.00015235194607197508, | |
| "loss": 0.1081, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.872860635696822, | |
| "grad_norm": 0.22219662368297577, | |
| "learning_rate": 0.0001516210956042153, | |
| "loss": 0.1071, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 7.921760391198044, | |
| "grad_norm": 0.20078670978546143, | |
| "learning_rate": 0.0001508864666404365, | |
| "loss": 0.1075, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.970660146699267, | |
| "grad_norm": 0.17794115841388702, | |
| "learning_rate": 0.00015014811295308543, | |
| "loss": 0.1051, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.2625426948070526, | |
| "eval_runtime": 387.4946, | |
| "eval_samples_per_second": 1.058, | |
| "eval_steps_per_second": 1.058, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 8.01955990220049, | |
| "grad_norm": 0.1608039289712906, | |
| "learning_rate": 0.0001494060885872464, | |
| "loss": 0.0994, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 8.06845965770171, | |
| "grad_norm": 0.2323434203863144, | |
| "learning_rate": 0.00014866044785668563, | |
| "loss": 0.0895, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 8.117359413202934, | |
| "grad_norm": 0.17606528103351593, | |
| "learning_rate": 0.0001479112453398753, | |
| "loss": 0.0849, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 8.166259168704157, | |
| "grad_norm": 0.19025173783302307, | |
| "learning_rate": 0.0001471585358759987, | |
| "loss": 0.0886, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 8.21515892420538, | |
| "grad_norm": 0.1990627497434616, | |
| "learning_rate": 0.00014640237456093634, | |
| "loss": 0.0905, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 8.2640586797066, | |
| "grad_norm": 0.1725684553384781, | |
| "learning_rate": 0.00014564281674323297, | |
| "loss": 0.0899, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 8.312958435207824, | |
| "grad_norm": 0.18845060467720032, | |
| "learning_rate": 0.00014487991802004623, | |
| "loss": 0.0886, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 8.361858190709047, | |
| "grad_norm": 0.23856212198734283, | |
| "learning_rate": 0.00014411373423307714, | |
| "loss": 0.0924, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 8.41075794621027, | |
| "grad_norm": 0.18084120750427246, | |
| "learning_rate": 0.00014334432146448272, | |
| "loss": 0.0918, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 8.45965770171149, | |
| "grad_norm": 0.18600909411907196, | |
| "learning_rate": 0.00014257173603277095, | |
| "loss": 0.0913, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 8.508557457212714, | |
| "grad_norm": 0.1851680874824524, | |
| "learning_rate": 0.00014179603448867835, | |
| "loss": 0.0912, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 8.557457212713937, | |
| "grad_norm": 0.1818709820508957, | |
| "learning_rate": 0.00014101727361103076, | |
| "loss": 0.0903, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 8.60635696821516, | |
| "grad_norm": 0.19458520412445068, | |
| "learning_rate": 0.00014023551040258725, | |
| "loss": 0.0916, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.65525672371638, | |
| "grad_norm": 0.17777447402477264, | |
| "learning_rate": 0.00013945080208586775, | |
| "loss": 0.0928, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 8.704156479217604, | |
| "grad_norm": 0.20647075772285461, | |
| "learning_rate": 0.00013866320609896447, | |
| "loss": 0.0926, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 8.753056234718827, | |
| "grad_norm": 0.18589670956134796, | |
| "learning_rate": 0.00013787278009133776, | |
| "loss": 0.0934, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 8.80195599022005, | |
| "grad_norm": 0.19582615792751312, | |
| "learning_rate": 0.00013707958191959608, | |
| "loss": 0.0954, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.85085574572127, | |
| "grad_norm": 0.19688870012760162, | |
| "learning_rate": 0.00013628366964326153, | |
| "loss": 0.0925, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 8.899755501222494, | |
| "grad_norm": 0.1874823123216629, | |
| "learning_rate": 0.00013548510152051963, | |
| "loss": 0.0939, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 8.948655256723717, | |
| "grad_norm": 0.1876133382320404, | |
| "learning_rate": 0.00013468393600395525, | |
| "loss": 0.097, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 8.99755501222494, | |
| "grad_norm": 0.1735718548297882, | |
| "learning_rate": 0.00013388023173627414, | |
| "loss": 0.0945, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.99755501222494, | |
| "eval_loss": 0.27974453568458557, | |
| "eval_runtime": 387.9073, | |
| "eval_samples_per_second": 1.057, | |
| "eval_steps_per_second": 1.057, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 9.04645476772616, | |
| "grad_norm": 0.1655295491218567, | |
| "learning_rate": 0.00013307404754601013, | |
| "loss": 0.0806, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 9.095354523227384, | |
| "grad_norm": 0.19395217299461365, | |
| "learning_rate": 0.0001322654424432195, | |
| "loss": 0.0788, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 9.144254278728607, | |
| "grad_norm": 0.18941174447536469, | |
| "learning_rate": 0.00013145447561516138, | |
| "loss": 0.0793, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 9.19315403422983, | |
| "grad_norm": 0.20010443031787872, | |
| "learning_rate": 0.00013064120642196548, | |
| "loss": 0.0807, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 9.24205378973105, | |
| "grad_norm": 0.20777645707130432, | |
| "learning_rate": 0.00012982569439228713, | |
| "loss": 0.08, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 9.290953545232274, | |
| "grad_norm": 0.173665389418602, | |
| "learning_rate": 0.00012900799921895003, | |
| "loss": 0.0808, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 9.339853300733497, | |
| "grad_norm": 0.20865468680858612, | |
| "learning_rate": 0.0001281881807545769, | |
| "loss": 0.0808, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 9.38875305623472, | |
| "grad_norm": 0.18372130393981934, | |
| "learning_rate": 0.0001273662990072083, | |
| "loss": 0.0804, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 9.43765281173594, | |
| "grad_norm": 0.1785283237695694, | |
| "learning_rate": 0.00012654241413591054, | |
| "loss": 0.0812, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 9.486552567237164, | |
| "grad_norm": 0.17695043981075287, | |
| "learning_rate": 0.000125716586446372, | |
| "loss": 0.0827, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 9.535452322738386, | |
| "grad_norm": 0.18287776410579681, | |
| "learning_rate": 0.00012488887638648907, | |
| "loss": 0.083, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 9.58435207823961, | |
| "grad_norm": 0.20748884975910187, | |
| "learning_rate": 0.00012405934454194146, | |
| "loss": 0.0816, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.63325183374083, | |
| "grad_norm": 0.18160052597522736, | |
| "learning_rate": 0.00012322805163175762, | |
| "loss": 0.0823, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 9.682151589242054, | |
| "grad_norm": 0.17889925837516785, | |
| "learning_rate": 0.0001223950585038703, | |
| "loss": 0.0822, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 9.731051344743276, | |
| "grad_norm": 0.1896965056657791, | |
| "learning_rate": 0.00012156042613066258, | |
| "loss": 0.0839, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 9.7799511002445, | |
| "grad_norm": 0.19203361868858337, | |
| "learning_rate": 0.00012072421560450497, | |
| "loss": 0.0828, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.82885085574572, | |
| "grad_norm": 0.18262554705142975, | |
| "learning_rate": 0.00011988648813328367, | |
| "loss": 0.0838, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 9.877750611246944, | |
| "grad_norm": 0.18471267819404602, | |
| "learning_rate": 0.0001190473050359203, | |
| "loss": 0.084, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 9.926650366748166, | |
| "grad_norm": 0.18675756454467773, | |
| "learning_rate": 0.00011820672773788353, | |
| "loss": 0.0835, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 9.97555012224939, | |
| "grad_norm": 0.17983846366405487, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 0.0843, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 9.995110024449877, | |
| "eval_loss": 0.2892283499240875, | |
| "eval_runtime": 389.1699, | |
| "eval_samples_per_second": 1.054, | |
| "eval_steps_per_second": 1.054, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 9.995110024449877, | |
| "step": 1022, | |
| "total_flos": 7.585797735459062e+17, | |
| "train_loss": 0.2326957560244605, | |
| "train_runtime": 28787.7929, | |
| "train_samples_per_second": 0.568, | |
| "train_steps_per_second": 0.071 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2040, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.585797735459062e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |