{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.999534233814625, "eval_steps": 500, "global_step": 4292, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004657661853749418, "grad_norm": 10.327290872956251, "learning_rate": 5.813953488372093e-07, "loss": 0.8062, "step": 5 }, { "epoch": 0.009315323707498836, "grad_norm": 5.701153148526739, "learning_rate": 1.1627906976744186e-06, "loss": 0.7636, "step": 10 }, { "epoch": 0.013972985561248253, "grad_norm": 3.761857537173051, "learning_rate": 1.744186046511628e-06, "loss": 0.6956, "step": 15 }, { "epoch": 0.018630647414997672, "grad_norm": 3.428302823003635, "learning_rate": 2.325581395348837e-06, "loss": 0.6724, "step": 20 }, { "epoch": 0.02328830926874709, "grad_norm": 1.5916347397468573, "learning_rate": 2.9069767441860468e-06, "loss": 0.6344, "step": 25 }, { "epoch": 0.027945971122496506, "grad_norm": 1.3490903195620083, "learning_rate": 3.488372093023256e-06, "loss": 0.6074, "step": 30 }, { "epoch": 0.032603632976245925, "grad_norm": 1.2012497112727898, "learning_rate": 4.0697674418604655e-06, "loss": 0.5889, "step": 35 }, { "epoch": 0.037261294829995344, "grad_norm": 1.140742997018409, "learning_rate": 4.651162790697674e-06, "loss": 0.5669, "step": 40 }, { "epoch": 0.04191895668374476, "grad_norm": 1.2783660534778691, "learning_rate": 5.232558139534884e-06, "loss": 0.5273, "step": 45 }, { "epoch": 0.04657661853749418, "grad_norm": 1.3432556795075172, "learning_rate": 5.8139534883720935e-06, "loss": 0.5282, "step": 50 }, { "epoch": 0.05123428039124359, "grad_norm": 0.9801837861430305, "learning_rate": 6.395348837209303e-06, "loss": 0.5155, "step": 55 }, { "epoch": 0.05589194224499301, "grad_norm": 0.800992047208021, "learning_rate": 6.976744186046512e-06, "loss": 0.5111, "step": 60 }, { "epoch": 0.06054960409874243, "grad_norm": 0.6283114593824819, "learning_rate": 7.558139534883721e-06, "loss": 0.5037, "step": 65 }, { "epoch": 0.06520726595249185, "grad_norm": 0.6041097044034034, "learning_rate": 8.139534883720931e-06, "loss": 0.4834, "step": 70 }, { "epoch": 0.06986492780624126, "grad_norm": 0.6694096021901881, "learning_rate": 8.72093023255814e-06, "loss": 0.4857, "step": 75 }, { "epoch": 0.07452258965999069, "grad_norm": 0.9039256097642137, "learning_rate": 9.302325581395349e-06, "loss": 0.4971, "step": 80 }, { "epoch": 0.0791802515137401, "grad_norm": 0.9647061090242738, "learning_rate": 9.883720930232558e-06, "loss": 0.4763, "step": 85 }, { "epoch": 0.08383791336748952, "grad_norm": 0.6905778244797834, "learning_rate": 1.0465116279069768e-05, "loss": 0.483, "step": 90 }, { "epoch": 0.08849557522123894, "grad_norm": 1.022204529008532, "learning_rate": 1.1046511627906977e-05, "loss": 0.4882, "step": 95 }, { "epoch": 0.09315323707498836, "grad_norm": 0.8371582640286606, "learning_rate": 1.1627906976744187e-05, "loss": 0.4791, "step": 100 }, { "epoch": 0.09781089892873777, "grad_norm": 0.7844233713063761, "learning_rate": 1.2209302325581395e-05, "loss": 0.4821, "step": 105 }, { "epoch": 0.10246856078248719, "grad_norm": 0.870769588243361, "learning_rate": 1.2790697674418606e-05, "loss": 0.4711, "step": 110 }, { "epoch": 0.10712622263623661, "grad_norm": 0.7490116300873177, "learning_rate": 1.3372093023255814e-05, "loss": 0.4713, "step": 115 }, { "epoch": 0.11178388448998602, "grad_norm": 1.031113687769425, "learning_rate": 1.3953488372093024e-05, "loss": 0.4829, "step": 120 }, { "epoch": 0.11644154634373545, "grad_norm": 0.8598503735250171, "learning_rate": 1.4534883720930233e-05, "loss": 0.4637, "step": 125 }, { "epoch": 0.12109920819748486, "grad_norm": 0.812986665078488, "learning_rate": 1.5116279069767441e-05, "loss": 0.4666, "step": 130 }, { "epoch": 0.1257568700512343, "grad_norm": 0.8337177165317408, "learning_rate": 1.569767441860465e-05, "loss": 0.4739, "step": 135 }, { "epoch": 0.1304145319049837, "grad_norm": 0.7958829475666563, "learning_rate": 1.6279069767441862e-05, "loss": 0.4677, "step": 140 }, { "epoch": 0.1350721937587331, "grad_norm": 0.9510034390903989, "learning_rate": 1.686046511627907e-05, "loss": 0.4778, "step": 145 }, { "epoch": 0.13972985561248252, "grad_norm": 1.06399223210079, "learning_rate": 1.744186046511628e-05, "loss": 0.4727, "step": 150 }, { "epoch": 0.14438751746623196, "grad_norm": 0.9015828921654486, "learning_rate": 1.802325581395349e-05, "loss": 0.4555, "step": 155 }, { "epoch": 0.14904517931998137, "grad_norm": 1.3427173488128188, "learning_rate": 1.8604651162790697e-05, "loss": 0.4629, "step": 160 }, { "epoch": 0.1537028411737308, "grad_norm": 0.8939343604926175, "learning_rate": 1.918604651162791e-05, "loss": 0.4637, "step": 165 }, { "epoch": 0.1583605030274802, "grad_norm": 0.9254882241048366, "learning_rate": 1.9767441860465116e-05, "loss": 0.4618, "step": 170 }, { "epoch": 0.1630181648812296, "grad_norm": 0.722239429538961, "learning_rate": 2.0348837209302328e-05, "loss": 0.4732, "step": 175 }, { "epoch": 0.16767582673497905, "grad_norm": 0.835037179697375, "learning_rate": 2.0930232558139536e-05, "loss": 0.4688, "step": 180 }, { "epoch": 0.17233348858872846, "grad_norm": 1.7323538405206185, "learning_rate": 2.1511627906976744e-05, "loss": 0.4671, "step": 185 }, { "epoch": 0.17699115044247787, "grad_norm": 1.2690970114605151, "learning_rate": 2.2093023255813955e-05, "loss": 0.4621, "step": 190 }, { "epoch": 0.18164881229622729, "grad_norm": 1.2519286605369933, "learning_rate": 2.2674418604651163e-05, "loss": 0.4685, "step": 195 }, { "epoch": 0.18630647414997673, "grad_norm": 1.0712536925609135, "learning_rate": 2.3255813953488374e-05, "loss": 0.4419, "step": 200 }, { "epoch": 0.19096413600372614, "grad_norm": 1.534136413734939, "learning_rate": 2.3837209302325582e-05, "loss": 0.4629, "step": 205 }, { "epoch": 0.19562179785747555, "grad_norm": 1.0040246387501353, "learning_rate": 2.441860465116279e-05, "loss": 0.453, "step": 210 }, { "epoch": 0.20027945971122496, "grad_norm": 0.8680644234589916, "learning_rate": 2.5e-05, "loss": 0.4636, "step": 215 }, { "epoch": 0.20493712156497437, "grad_norm": 0.9104166413331498, "learning_rate": 2.5581395348837212e-05, "loss": 0.4603, "step": 220 }, { "epoch": 0.2095947834187238, "grad_norm": 1.2017304759131207, "learning_rate": 2.616279069767442e-05, "loss": 0.4639, "step": 225 }, { "epoch": 0.21425244527247322, "grad_norm": 0.8863045398361102, "learning_rate": 2.674418604651163e-05, "loss": 0.4625, "step": 230 }, { "epoch": 0.21891010712622264, "grad_norm": 1.1681668525310664, "learning_rate": 2.7325581395348836e-05, "loss": 0.4576, "step": 235 }, { "epoch": 0.22356776897997205, "grad_norm": 1.0351864784882119, "learning_rate": 2.7906976744186048e-05, "loss": 0.4563, "step": 240 }, { "epoch": 0.22822543083372146, "grad_norm": 0.9199270402279854, "learning_rate": 2.848837209302326e-05, "loss": 0.4478, "step": 245 }, { "epoch": 0.2328830926874709, "grad_norm": 0.95332450064731, "learning_rate": 2.9069767441860467e-05, "loss": 0.4456, "step": 250 }, { "epoch": 0.2375407545412203, "grad_norm": 0.7888040988857935, "learning_rate": 2.9651162790697678e-05, "loss": 0.4567, "step": 255 }, { "epoch": 0.24219841639496972, "grad_norm": 0.7290827873884927, "learning_rate": 3.0232558139534883e-05, "loss": 0.4612, "step": 260 }, { "epoch": 0.24685607824871914, "grad_norm": 0.9378372933381951, "learning_rate": 3.081395348837209e-05, "loss": 0.4563, "step": 265 }, { "epoch": 0.2515137401024686, "grad_norm": 0.993025628480833, "learning_rate": 3.13953488372093e-05, "loss": 0.4466, "step": 270 }, { "epoch": 0.25617140195621796, "grad_norm": 0.985970823850318, "learning_rate": 3.197674418604651e-05, "loss": 0.4626, "step": 275 }, { "epoch": 0.2608290638099674, "grad_norm": 1.089159665546101, "learning_rate": 3.2558139534883724e-05, "loss": 0.4516, "step": 280 }, { "epoch": 0.26548672566371684, "grad_norm": 1.034418514511183, "learning_rate": 3.313953488372093e-05, "loss": 0.4506, "step": 285 }, { "epoch": 0.2701443875174662, "grad_norm": 1.0091993134751827, "learning_rate": 3.372093023255814e-05, "loss": 0.4492, "step": 290 }, { "epoch": 0.27480204937121566, "grad_norm": 0.9153297600153939, "learning_rate": 3.430232558139535e-05, "loss": 0.4431, "step": 295 }, { "epoch": 0.27945971122496505, "grad_norm": 1.0449450938124245, "learning_rate": 3.488372093023256e-05, "loss": 0.4554, "step": 300 }, { "epoch": 0.2841173730787145, "grad_norm": 0.8329445094150849, "learning_rate": 3.5465116279069774e-05, "loss": 0.4604, "step": 305 }, { "epoch": 0.2887750349324639, "grad_norm": 0.9677155514590303, "learning_rate": 3.604651162790698e-05, "loss": 0.4563, "step": 310 }, { "epoch": 0.2934326967862133, "grad_norm": 0.8337599277146849, "learning_rate": 3.662790697674418e-05, "loss": 0.4473, "step": 315 }, { "epoch": 0.29809035863996275, "grad_norm": 0.9853467757131108, "learning_rate": 3.7209302325581394e-05, "loss": 0.4551, "step": 320 }, { "epoch": 0.30274802049371213, "grad_norm": 0.7658482898779524, "learning_rate": 3.7790697674418606e-05, "loss": 0.4576, "step": 325 }, { "epoch": 0.3074056823474616, "grad_norm": 1.146734606575659, "learning_rate": 3.837209302325582e-05, "loss": 0.4564, "step": 330 }, { "epoch": 0.312063344201211, "grad_norm": 0.9873194116119423, "learning_rate": 3.895348837209303e-05, "loss": 0.4426, "step": 335 }, { "epoch": 0.3167210060549604, "grad_norm": 0.9680919289631158, "learning_rate": 3.953488372093023e-05, "loss": 0.4552, "step": 340 }, { "epoch": 0.32137866790870984, "grad_norm": 0.9216116845910767, "learning_rate": 4.0116279069767444e-05, "loss": 0.4445, "step": 345 }, { "epoch": 0.3260363297624592, "grad_norm": 0.7482755882100446, "learning_rate": 4.0697674418604655e-05, "loss": 0.4473, "step": 350 }, { "epoch": 0.33069399161620866, "grad_norm": 1.283879547507912, "learning_rate": 4.127906976744187e-05, "loss": 0.4456, "step": 355 }, { "epoch": 0.3353516534699581, "grad_norm": 1.4165988738887307, "learning_rate": 4.186046511627907e-05, "loss": 0.4561, "step": 360 }, { "epoch": 0.3400093153237075, "grad_norm": 0.8012026601634945, "learning_rate": 4.2441860465116276e-05, "loss": 0.4565, "step": 365 }, { "epoch": 0.3446669771774569, "grad_norm": 1.16618560350076, "learning_rate": 4.302325581395349e-05, "loss": 0.4651, "step": 370 }, { "epoch": 0.3493246390312063, "grad_norm": 0.7449714816128542, "learning_rate": 4.36046511627907e-05, "loss": 0.4591, "step": 375 }, { "epoch": 0.35398230088495575, "grad_norm": 0.6673551751674572, "learning_rate": 4.418604651162791e-05, "loss": 0.4455, "step": 380 }, { "epoch": 0.3586399627387052, "grad_norm": 0.8319588849464178, "learning_rate": 4.476744186046512e-05, "loss": 0.4413, "step": 385 }, { "epoch": 0.36329762459245457, "grad_norm": 0.9693848571946022, "learning_rate": 4.5348837209302326e-05, "loss": 0.4475, "step": 390 }, { "epoch": 0.367955286446204, "grad_norm": 0.8052002720710977, "learning_rate": 4.593023255813954e-05, "loss": 0.4424, "step": 395 }, { "epoch": 0.37261294829995345, "grad_norm": 1.0882483524790372, "learning_rate": 4.651162790697675e-05, "loss": 0.4409, "step": 400 }, { "epoch": 0.37727061015370283, "grad_norm": 1.1080776994990877, "learning_rate": 4.709302325581396e-05, "loss": 0.4446, "step": 405 }, { "epoch": 0.3819282720074523, "grad_norm": 1.5501215325983868, "learning_rate": 4.7674418604651164e-05, "loss": 0.4525, "step": 410 }, { "epoch": 0.38658593386120166, "grad_norm": 1.2252690139413926, "learning_rate": 4.8255813953488375e-05, "loss": 0.4519, "step": 415 }, { "epoch": 0.3912435957149511, "grad_norm": 1.0658501211320766, "learning_rate": 4.883720930232558e-05, "loss": 0.4402, "step": 420 }, { "epoch": 0.39590125756870054, "grad_norm": 0.9730243650812543, "learning_rate": 4.941860465116279e-05, "loss": 0.456, "step": 425 }, { "epoch": 0.4005589194224499, "grad_norm": 0.8757859268702196, "learning_rate": 5e-05, "loss": 0.4491, "step": 430 }, { "epoch": 0.40521658127619936, "grad_norm": 0.9228690998410783, "learning_rate": 4.9935266701191095e-05, "loss": 0.4537, "step": 435 }, { "epoch": 0.40987424312994875, "grad_norm": 0.6961742016188762, "learning_rate": 4.987053340238219e-05, "loss": 0.4611, "step": 440 }, { "epoch": 0.4145319049836982, "grad_norm": 0.9306104185773012, "learning_rate": 4.980580010357328e-05, "loss": 0.4414, "step": 445 }, { "epoch": 0.4191895668374476, "grad_norm": 0.9293970368719495, "learning_rate": 4.9741066804764374e-05, "loss": 0.447, "step": 450 }, { "epoch": 0.423847228691197, "grad_norm": 1.0086747920339858, "learning_rate": 4.967633350595546e-05, "loss": 0.4646, "step": 455 }, { "epoch": 0.42850489054494645, "grad_norm": 0.7926305857725872, "learning_rate": 4.961160020714656e-05, "loss": 0.4459, "step": 460 }, { "epoch": 0.43316255239869583, "grad_norm": 0.7964692593049033, "learning_rate": 4.954686690833765e-05, "loss": 0.4552, "step": 465 }, { "epoch": 0.43782021425244527, "grad_norm": 0.9444642925272473, "learning_rate": 4.948213360952874e-05, "loss": 0.4465, "step": 470 }, { "epoch": 0.4424778761061947, "grad_norm": 0.9991039441546867, "learning_rate": 4.941740031071983e-05, "loss": 0.4556, "step": 475 }, { "epoch": 0.4471355379599441, "grad_norm": 0.786239616091064, "learning_rate": 4.935266701191093e-05, "loss": 0.4417, "step": 480 }, { "epoch": 0.45179319981369354, "grad_norm": 0.7628467103498474, "learning_rate": 4.9287933713102025e-05, "loss": 0.4436, "step": 485 }, { "epoch": 0.4564508616674429, "grad_norm": 0.7608488791728294, "learning_rate": 4.922320041429311e-05, "loss": 0.4467, "step": 490 }, { "epoch": 0.46110852352119236, "grad_norm": 0.5520622303627057, "learning_rate": 4.915846711548421e-05, "loss": 0.4392, "step": 495 }, { "epoch": 0.4657661853749418, "grad_norm": 0.5857858507729303, "learning_rate": 4.9093733816675304e-05, "loss": 0.446, "step": 500 }, { "epoch": 0.4704238472286912, "grad_norm": 0.5363206354862753, "learning_rate": 4.902900051786639e-05, "loss": 0.4401, "step": 505 }, { "epoch": 0.4750815090824406, "grad_norm": 0.7339718748781224, "learning_rate": 4.8964267219057483e-05, "loss": 0.4364, "step": 510 }, { "epoch": 0.47973917093619, "grad_norm": 0.6361306289982317, "learning_rate": 4.889953392024858e-05, "loss": 0.4473, "step": 515 }, { "epoch": 0.48439683278993945, "grad_norm": 0.727285907771692, "learning_rate": 4.883480062143967e-05, "loss": 0.4442, "step": 520 }, { "epoch": 0.4890544946436889, "grad_norm": 0.8972612409343087, "learning_rate": 4.877006732263076e-05, "loss": 0.4526, "step": 525 }, { "epoch": 0.49371215649743827, "grad_norm": 0.777061222572352, "learning_rate": 4.8705334023821855e-05, "loss": 0.4392, "step": 530 }, { "epoch": 0.4983698183511877, "grad_norm": 0.9079159510832142, "learning_rate": 4.864060072501295e-05, "loss": 0.4462, "step": 535 }, { "epoch": 0.5030274802049371, "grad_norm": 0.5802056984908713, "learning_rate": 4.857586742620404e-05, "loss": 0.4487, "step": 540 }, { "epoch": 0.5076851420586865, "grad_norm": 0.6777897794086118, "learning_rate": 4.8511134127395134e-05, "loss": 0.4393, "step": 545 }, { "epoch": 0.5123428039124359, "grad_norm": 0.6240678305978992, "learning_rate": 4.844640082858623e-05, "loss": 0.4522, "step": 550 }, { "epoch": 0.5170004657661854, "grad_norm": 0.7376668448663769, "learning_rate": 4.838166752977732e-05, "loss": 0.4408, "step": 555 }, { "epoch": 0.5216581276199348, "grad_norm": 0.6801561433030565, "learning_rate": 4.831693423096841e-05, "loss": 0.4456, "step": 560 }, { "epoch": 0.5263157894736842, "grad_norm": 0.6551090286321001, "learning_rate": 4.82522009321595e-05, "loss": 0.4437, "step": 565 }, { "epoch": 0.5309734513274337, "grad_norm": 0.6760400356966735, "learning_rate": 4.81874676333506e-05, "loss": 0.4431, "step": 570 }, { "epoch": 0.5356311131811831, "grad_norm": 0.6755777973169471, "learning_rate": 4.812273433454169e-05, "loss": 0.4398, "step": 575 }, { "epoch": 0.5402887750349324, "grad_norm": 0.6344800221690381, "learning_rate": 4.8058001035732785e-05, "loss": 0.44, "step": 580 }, { "epoch": 0.5449464368886818, "grad_norm": 0.6360289263835667, "learning_rate": 4.799326773692387e-05, "loss": 0.4364, "step": 585 }, { "epoch": 0.5496040987424313, "grad_norm": 0.5658395615942804, "learning_rate": 4.792853443811497e-05, "loss": 0.4513, "step": 590 }, { "epoch": 0.5542617605961807, "grad_norm": 0.671577686568308, "learning_rate": 4.7863801139306064e-05, "loss": 0.4423, "step": 595 }, { "epoch": 0.5589194224499301, "grad_norm": 0.7544590264298021, "learning_rate": 4.779906784049715e-05, "loss": 0.4477, "step": 600 }, { "epoch": 0.5635770843036796, "grad_norm": 0.8368749875677601, "learning_rate": 4.773433454168825e-05, "loss": 0.4232, "step": 605 }, { "epoch": 0.568234746157429, "grad_norm": 0.8479065186501227, "learning_rate": 4.766960124287934e-05, "loss": 0.441, "step": 610 }, { "epoch": 0.5728924080111784, "grad_norm": 0.6661880076529291, "learning_rate": 4.760486794407043e-05, "loss": 0.4339, "step": 615 }, { "epoch": 0.5775500698649279, "grad_norm": 0.6087100158095081, "learning_rate": 4.754013464526152e-05, "loss": 0.4367, "step": 620 }, { "epoch": 0.5822077317186772, "grad_norm": 0.9386228526906225, "learning_rate": 4.747540134645262e-05, "loss": 0.4465, "step": 625 }, { "epoch": 0.5868653935724266, "grad_norm": 0.730308381114445, "learning_rate": 4.741066804764371e-05, "loss": 0.4337, "step": 630 }, { "epoch": 0.5915230554261761, "grad_norm": 0.5807938733311218, "learning_rate": 4.73459347488348e-05, "loss": 0.4329, "step": 635 }, { "epoch": 0.5961807172799255, "grad_norm": 0.6750480320574985, "learning_rate": 4.7281201450025894e-05, "loss": 0.4375, "step": 640 }, { "epoch": 0.6008383791336749, "grad_norm": 0.7481101689745328, "learning_rate": 4.721646815121699e-05, "loss": 0.437, "step": 645 }, { "epoch": 0.6054960409874243, "grad_norm": 0.6277417236782211, "learning_rate": 4.715173485240808e-05, "loss": 0.4349, "step": 650 }, { "epoch": 0.6101537028411738, "grad_norm": 0.6798144229395184, "learning_rate": 4.708700155359917e-05, "loss": 0.4407, "step": 655 }, { "epoch": 0.6148113646949231, "grad_norm": 0.708619393935491, "learning_rate": 4.7022268254790266e-05, "loss": 0.4413, "step": 660 }, { "epoch": 0.6194690265486725, "grad_norm": 0.838660539058036, "learning_rate": 4.695753495598136e-05, "loss": 0.4357, "step": 665 }, { "epoch": 0.624126688402422, "grad_norm": 0.7143914409285944, "learning_rate": 4.689280165717245e-05, "loss": 0.4388, "step": 670 }, { "epoch": 0.6287843502561714, "grad_norm": 0.696811423117882, "learning_rate": 4.6828068358363545e-05, "loss": 0.4309, "step": 675 }, { "epoch": 0.6334420121099208, "grad_norm": 0.5920811536552839, "learning_rate": 4.676333505955464e-05, "loss": 0.4345, "step": 680 }, { "epoch": 0.6380996739636703, "grad_norm": 0.6475843830101498, "learning_rate": 4.669860176074573e-05, "loss": 0.4453, "step": 685 }, { "epoch": 0.6427573358174197, "grad_norm": 1.8963784661040046, "learning_rate": 4.6633868461936824e-05, "loss": 0.4374, "step": 690 }, { "epoch": 0.6474149976711691, "grad_norm": 0.5590882188481051, "learning_rate": 4.656913516312791e-05, "loss": 0.4355, "step": 695 }, { "epoch": 0.6520726595249184, "grad_norm": 0.8205506938841793, "learning_rate": 4.650440186431901e-05, "loss": 0.4324, "step": 700 }, { "epoch": 0.6567303213786679, "grad_norm": 0.5825429452444019, "learning_rate": 4.64396685655101e-05, "loss": 0.4299, "step": 705 }, { "epoch": 0.6613879832324173, "grad_norm": 0.9277372944479966, "learning_rate": 4.637493526670119e-05, "loss": 0.4419, "step": 710 }, { "epoch": 0.6660456450861667, "grad_norm": 0.8073040957496479, "learning_rate": 4.631020196789229e-05, "loss": 0.4374, "step": 715 }, { "epoch": 0.6707033069399162, "grad_norm": 1.1947145784552105, "learning_rate": 4.624546866908338e-05, "loss": 0.4276, "step": 720 }, { "epoch": 0.6753609687936656, "grad_norm": 2.4077286453325635, "learning_rate": 4.618073537027447e-05, "loss": 0.4654, "step": 725 }, { "epoch": 0.680018630647415, "grad_norm": 0.7396430648689338, "learning_rate": 4.611600207146556e-05, "loss": 0.4472, "step": 730 }, { "epoch": 0.6846762925011645, "grad_norm": 1.0594565596526018, "learning_rate": 4.605126877265666e-05, "loss": 0.4338, "step": 735 }, { "epoch": 0.6893339543549138, "grad_norm": 0.7278679767288331, "learning_rate": 4.598653547384775e-05, "loss": 0.4353, "step": 740 }, { "epoch": 0.6939916162086632, "grad_norm": 0.7807124424908749, "learning_rate": 4.592180217503884e-05, "loss": 0.431, "step": 745 }, { "epoch": 0.6986492780624126, "grad_norm": 0.9206283289232494, "learning_rate": 4.585706887622993e-05, "loss": 0.4359, "step": 750 }, { "epoch": 0.7033069399161621, "grad_norm": 0.6386150894379372, "learning_rate": 4.5792335577421026e-05, "loss": 0.4256, "step": 755 }, { "epoch": 0.7079646017699115, "grad_norm": 0.8579103809801604, "learning_rate": 4.572760227861212e-05, "loss": 0.428, "step": 760 }, { "epoch": 0.7126222636236609, "grad_norm": 0.5792409001547826, "learning_rate": 4.566286897980321e-05, "loss": 0.4357, "step": 765 }, { "epoch": 0.7172799254774104, "grad_norm": 0.651263234768284, "learning_rate": 4.5598135680994305e-05, "loss": 0.435, "step": 770 }, { "epoch": 0.7219375873311598, "grad_norm": 0.6140100886682245, "learning_rate": 4.55334023821854e-05, "loss": 0.4237, "step": 775 }, { "epoch": 0.7265952491849091, "grad_norm": 0.7520220030711136, "learning_rate": 4.546866908337649e-05, "loss": 0.4393, "step": 780 }, { "epoch": 0.7312529110386586, "grad_norm": 0.5804940863281571, "learning_rate": 4.5403935784567584e-05, "loss": 0.4336, "step": 785 }, { "epoch": 0.735910572892408, "grad_norm": 0.77658252502943, "learning_rate": 4.533920248575868e-05, "loss": 0.4261, "step": 790 }, { "epoch": 0.7405682347461574, "grad_norm": 0.573532643365261, "learning_rate": 4.527446918694977e-05, "loss": 0.4334, "step": 795 }, { "epoch": 0.7452258965999069, "grad_norm": 0.5186603984085262, "learning_rate": 4.520973588814086e-05, "loss": 0.4291, "step": 800 }, { "epoch": 0.7498835584536563, "grad_norm": 0.6313190830939789, "learning_rate": 4.5145002589331956e-05, "loss": 0.4441, "step": 805 }, { "epoch": 0.7545412203074057, "grad_norm": 1.3662133948918167, "learning_rate": 4.508026929052305e-05, "loss": 0.4362, "step": 810 }, { "epoch": 0.759198882161155, "grad_norm": 0.5761503911738722, "learning_rate": 4.501553599171414e-05, "loss": 0.4343, "step": 815 }, { "epoch": 0.7638565440149045, "grad_norm": 0.8834303464393425, "learning_rate": 4.495080269290523e-05, "loss": 0.4332, "step": 820 }, { "epoch": 0.7685142058686539, "grad_norm": 0.6617478499848966, "learning_rate": 4.488606939409633e-05, "loss": 0.4211, "step": 825 }, { "epoch": 0.7731718677224033, "grad_norm": 1.0093602458374686, "learning_rate": 4.482133609528742e-05, "loss": 0.4319, "step": 830 }, { "epoch": 0.7778295295761528, "grad_norm": 0.7765462382220336, "learning_rate": 4.475660279647851e-05, "loss": 0.4401, "step": 835 }, { "epoch": 0.7824871914299022, "grad_norm": 0.7688651630312342, "learning_rate": 4.46918694976696e-05, "loss": 0.4242, "step": 840 }, { "epoch": 0.7871448532836516, "grad_norm": 0.7647520870769418, "learning_rate": 4.46271361988607e-05, "loss": 0.4287, "step": 845 }, { "epoch": 0.7918025151374011, "grad_norm": 0.7294311023377945, "learning_rate": 4.4562402900051786e-05, "loss": 0.4304, "step": 850 }, { "epoch": 0.7964601769911505, "grad_norm": 0.7534770330283811, "learning_rate": 4.449766960124288e-05, "loss": 0.4237, "step": 855 }, { "epoch": 0.8011178388448998, "grad_norm": 0.8046872255517671, "learning_rate": 4.443293630243397e-05, "loss": 0.4259, "step": 860 }, { "epoch": 0.8057755006986492, "grad_norm": 0.7261829591460937, "learning_rate": 4.436820300362507e-05, "loss": 0.4286, "step": 865 }, { "epoch": 0.8104331625523987, "grad_norm": 0.6890876215992131, "learning_rate": 4.430346970481616e-05, "loss": 0.4222, "step": 870 }, { "epoch": 0.8150908244061481, "grad_norm": 0.6461688544064992, "learning_rate": 4.423873640600725e-05, "loss": 0.4309, "step": 875 }, { "epoch": 0.8197484862598975, "grad_norm": 0.5530794029903263, "learning_rate": 4.4174003107198344e-05, "loss": 0.4154, "step": 880 }, { "epoch": 0.824406148113647, "grad_norm": 0.5848628445010046, "learning_rate": 4.410926980838944e-05, "loss": 0.4302, "step": 885 }, { "epoch": 0.8290638099673964, "grad_norm": 0.6272517008711553, "learning_rate": 4.404453650958053e-05, "loss": 0.4294, "step": 890 }, { "epoch": 0.8337214718211458, "grad_norm": 0.646355712465477, "learning_rate": 4.397980321077162e-05, "loss": 0.4299, "step": 895 }, { "epoch": 0.8383791336748952, "grad_norm": 0.7442803870999123, "learning_rate": 4.3915069911962716e-05, "loss": 0.4241, "step": 900 }, { "epoch": 0.8430367955286446, "grad_norm": 1.0291879704785272, "learning_rate": 4.385033661315381e-05, "loss": 0.4275, "step": 905 }, { "epoch": 0.847694457382394, "grad_norm": 0.6032984961646253, "learning_rate": 4.37856033143449e-05, "loss": 0.4351, "step": 910 }, { "epoch": 0.8523521192361434, "grad_norm": 20.9040371533675, "learning_rate": 4.3720870015535995e-05, "loss": 0.426, "step": 915 }, { "epoch": 0.8570097810898929, "grad_norm": 1.27313054394576, "learning_rate": 4.365613671672709e-05, "loss": 0.4405, "step": 920 }, { "epoch": 0.8616674429436423, "grad_norm": 0.8621150167599367, "learning_rate": 4.359140341791818e-05, "loss": 0.4304, "step": 925 }, { "epoch": 0.8663251047973917, "grad_norm": 1.3255615759568606, "learning_rate": 4.352667011910927e-05, "loss": 0.4296, "step": 930 }, { "epoch": 0.8709827666511412, "grad_norm": 0.5076209088367677, "learning_rate": 4.346193682030037e-05, "loss": 0.4181, "step": 935 }, { "epoch": 0.8756404285048905, "grad_norm": 0.6544452242512707, "learning_rate": 4.339720352149146e-05, "loss": 0.4174, "step": 940 }, { "epoch": 0.8802980903586399, "grad_norm": 0.5643383377968159, "learning_rate": 4.3332470222682546e-05, "loss": 0.4211, "step": 945 }, { "epoch": 0.8849557522123894, "grad_norm": 0.6618196540819336, "learning_rate": 4.326773692387364e-05, "loss": 0.4108, "step": 950 }, { "epoch": 0.8896134140661388, "grad_norm": 0.5303046522400311, "learning_rate": 4.320300362506474e-05, "loss": 0.4239, "step": 955 }, { "epoch": 0.8942710759198882, "grad_norm": 1.0282918162637014, "learning_rate": 4.313827032625583e-05, "loss": 0.4299, "step": 960 }, { "epoch": 0.8989287377736377, "grad_norm": 0.5893071440076123, "learning_rate": 4.307353702744692e-05, "loss": 0.4243, "step": 965 }, { "epoch": 0.9035863996273871, "grad_norm": 0.6332664888738168, "learning_rate": 4.300880372863801e-05, "loss": 0.4278, "step": 970 }, { "epoch": 0.9082440614811365, "grad_norm": 1.6500486612700351, "learning_rate": 4.294407042982911e-05, "loss": 0.4217, "step": 975 }, { "epoch": 0.9129017233348858, "grad_norm": 0.6748607429689958, "learning_rate": 4.28793371310202e-05, "loss": 0.4252, "step": 980 }, { "epoch": 0.9175593851886353, "grad_norm": 0.5573086406452893, "learning_rate": 4.281460383221129e-05, "loss": 0.4297, "step": 985 }, { "epoch": 0.9222170470423847, "grad_norm": 0.7313059106558355, "learning_rate": 4.274987053340238e-05, "loss": 0.4036, "step": 990 }, { "epoch": 0.9268747088961341, "grad_norm": 0.6803564071886932, "learning_rate": 4.2685137234593476e-05, "loss": 0.4274, "step": 995 }, { "epoch": 0.9315323707498836, "grad_norm": 0.7123002330012534, "learning_rate": 4.262040393578457e-05, "loss": 0.4218, "step": 1000 }, { "epoch": 0.936190032603633, "grad_norm": 0.6885042502830875, "learning_rate": 4.255567063697566e-05, "loss": 0.4298, "step": 1005 }, { "epoch": 0.9408476944573824, "grad_norm": 0.7228807829515138, "learning_rate": 4.2490937338166755e-05, "loss": 0.4205, "step": 1010 }, { "epoch": 0.9455053563111319, "grad_norm": 0.5883247358358131, "learning_rate": 4.242620403935785e-05, "loss": 0.4217, "step": 1015 }, { "epoch": 0.9501630181648812, "grad_norm": 0.6371413432665373, "learning_rate": 4.236147074054894e-05, "loss": 0.4299, "step": 1020 }, { "epoch": 0.9548206800186306, "grad_norm": 0.5872384369507182, "learning_rate": 4.2296737441740034e-05, "loss": 0.4225, "step": 1025 }, { "epoch": 0.95947834187238, "grad_norm": 0.6292827061628509, "learning_rate": 4.223200414293113e-05, "loss": 0.4147, "step": 1030 }, { "epoch": 0.9641360037261295, "grad_norm": 0.696649530790446, "learning_rate": 4.216727084412222e-05, "loss": 0.4202, "step": 1035 }, { "epoch": 0.9687936655798789, "grad_norm": 1.492146565764485, "learning_rate": 4.2102537545313306e-05, "loss": 0.418, "step": 1040 }, { "epoch": 0.9734513274336283, "grad_norm": 0.6853557404131279, "learning_rate": 4.2037804246504406e-05, "loss": 0.4182, "step": 1045 }, { "epoch": 0.9781089892873778, "grad_norm": 0.6620928582693439, "learning_rate": 4.19730709476955e-05, "loss": 0.4173, "step": 1050 }, { "epoch": 0.9827666511411272, "grad_norm": 0.720308005829342, "learning_rate": 4.190833764888659e-05, "loss": 0.4192, "step": 1055 }, { "epoch": 0.9874243129948765, "grad_norm": 0.6812278466757765, "learning_rate": 4.184360435007768e-05, "loss": 0.4213, "step": 1060 }, { "epoch": 0.992081974848626, "grad_norm": 0.5877751047454203, "learning_rate": 4.177887105126878e-05, "loss": 0.4189, "step": 1065 }, { "epoch": 0.9967396367023754, "grad_norm": 0.6256591377339001, "learning_rate": 4.171413775245987e-05, "loss": 0.4115, "step": 1070 }, { "epoch": 1.00093153237075, "grad_norm": 2.1761453338367565, "learning_rate": 4.164940445365096e-05, "loss": 0.4222, "step": 1075 }, { "epoch": 1.0055891942244992, "grad_norm": 1.7584276336677116, "learning_rate": 4.158467115484205e-05, "loss": 0.3637, "step": 1080 }, { "epoch": 1.0102468560782487, "grad_norm": 0.6071819644284323, "learning_rate": 4.151993785603315e-05, "loss": 0.3523, "step": 1085 }, { "epoch": 1.0149045179319982, "grad_norm": 0.632258197097728, "learning_rate": 4.1455204557224236e-05, "loss": 0.3645, "step": 1090 }, { "epoch": 1.0195621797857475, "grad_norm": 0.6023673486302475, "learning_rate": 4.139047125841533e-05, "loss": 0.3574, "step": 1095 }, { "epoch": 1.024219841639497, "grad_norm": 0.5793870950058814, "learning_rate": 4.132573795960642e-05, "loss": 0.3598, "step": 1100 }, { "epoch": 1.0288775034932465, "grad_norm": 0.8292193105554476, "learning_rate": 4.1261004660797515e-05, "loss": 0.361, "step": 1105 }, { "epoch": 1.0335351653469957, "grad_norm": 0.6828218603012787, "learning_rate": 4.119627136198861e-05, "loss": 0.3624, "step": 1110 }, { "epoch": 1.0381928272007452, "grad_norm": 0.5404764094477691, "learning_rate": 4.11315380631797e-05, "loss": 0.3511, "step": 1115 }, { "epoch": 1.0428504890544947, "grad_norm": 0.6506340212392893, "learning_rate": 4.1066804764370794e-05, "loss": 0.3577, "step": 1120 }, { "epoch": 1.047508150908244, "grad_norm": 0.834817570850703, "learning_rate": 4.100207146556189e-05, "loss": 0.3661, "step": 1125 }, { "epoch": 1.0521658127619935, "grad_norm": 0.5892840629533278, "learning_rate": 4.093733816675298e-05, "loss": 0.3507, "step": 1130 }, { "epoch": 1.056823474615743, "grad_norm": 0.5109210515982364, "learning_rate": 4.087260486794407e-05, "loss": 0.3619, "step": 1135 }, { "epoch": 1.0614811364694923, "grad_norm": 0.5500208730931968, "learning_rate": 4.0807871569135166e-05, "loss": 0.3578, "step": 1140 }, { "epoch": 1.0661387983232418, "grad_norm": 0.5196813249471254, "learning_rate": 4.074313827032626e-05, "loss": 0.3589, "step": 1145 }, { "epoch": 1.0707964601769913, "grad_norm": 0.4595874312012886, "learning_rate": 4.067840497151735e-05, "loss": 0.3543, "step": 1150 }, { "epoch": 1.0754541220307405, "grad_norm": 0.5314722731330289, "learning_rate": 4.0613671672708445e-05, "loss": 0.3565, "step": 1155 }, { "epoch": 1.08011178388449, "grad_norm": 0.5325260926139438, "learning_rate": 4.054893837389954e-05, "loss": 0.3646, "step": 1160 }, { "epoch": 1.0847694457382393, "grad_norm": 0.4841981385256102, "learning_rate": 4.048420507509063e-05, "loss": 0.3654, "step": 1165 }, { "epoch": 1.0894271075919888, "grad_norm": 0.5982016586934674, "learning_rate": 4.041947177628172e-05, "loss": 0.3628, "step": 1170 }, { "epoch": 1.0940847694457383, "grad_norm": 0.5739500659566079, "learning_rate": 4.035473847747282e-05, "loss": 0.363, "step": 1175 }, { "epoch": 1.0987424312994876, "grad_norm": 0.5335997515110337, "learning_rate": 4.029000517866391e-05, "loss": 0.3547, "step": 1180 }, { "epoch": 1.103400093153237, "grad_norm": 0.5447062457449594, "learning_rate": 4.0225271879854996e-05, "loss": 0.3571, "step": 1185 }, { "epoch": 1.1080577550069866, "grad_norm": 0.4355168837833732, "learning_rate": 4.016053858104609e-05, "loss": 0.3393, "step": 1190 }, { "epoch": 1.1127154168607358, "grad_norm": 0.4669462404143387, "learning_rate": 4.009580528223719e-05, "loss": 0.3481, "step": 1195 }, { "epoch": 1.1173730787144853, "grad_norm": 0.4954837939990686, "learning_rate": 4.0031071983428275e-05, "loss": 0.3578, "step": 1200 }, { "epoch": 1.1220307405682348, "grad_norm": 0.6795977130375482, "learning_rate": 3.996633868461937e-05, "loss": 0.3647, "step": 1205 }, { "epoch": 1.126688402421984, "grad_norm": 0.5001000087445739, "learning_rate": 3.990160538581046e-05, "loss": 0.3597, "step": 1210 }, { "epoch": 1.1313460642757336, "grad_norm": 0.8531172516597587, "learning_rate": 3.9836872087001554e-05, "loss": 0.3555, "step": 1215 }, { "epoch": 1.136003726129483, "grad_norm": 0.5855961653768579, "learning_rate": 3.977213878819265e-05, "loss": 0.3659, "step": 1220 }, { "epoch": 1.1406613879832324, "grad_norm": 0.5337372399381383, "learning_rate": 3.970740548938374e-05, "loss": 0.356, "step": 1225 }, { "epoch": 1.1453190498369819, "grad_norm": 0.5597611070102028, "learning_rate": 3.964267219057483e-05, "loss": 0.3561, "step": 1230 }, { "epoch": 1.1499767116907313, "grad_norm": 0.49464484989505825, "learning_rate": 3.9577938891765926e-05, "loss": 0.3566, "step": 1235 }, { "epoch": 1.1546343735444806, "grad_norm": 0.4761928904066112, "learning_rate": 3.951320559295702e-05, "loss": 0.3623, "step": 1240 }, { "epoch": 1.1592920353982301, "grad_norm": 0.5388013267994733, "learning_rate": 3.944847229414811e-05, "loss": 0.3633, "step": 1245 }, { "epoch": 1.1639496972519794, "grad_norm": 0.6608817986152771, "learning_rate": 3.9383738995339205e-05, "loss": 0.366, "step": 1250 }, { "epoch": 1.1686073591057289, "grad_norm": 0.5289998653529552, "learning_rate": 3.93190056965303e-05, "loss": 0.3558, "step": 1255 }, { "epoch": 1.1732650209594784, "grad_norm": 0.4464694143567028, "learning_rate": 3.925427239772139e-05, "loss": 0.3678, "step": 1260 }, { "epoch": 1.1779226828132279, "grad_norm": 0.47832489809535667, "learning_rate": 3.9189539098912484e-05, "loss": 0.3531, "step": 1265 }, { "epoch": 1.1825803446669771, "grad_norm": 0.43463179381935385, "learning_rate": 3.912480580010358e-05, "loss": 0.3473, "step": 1270 }, { "epoch": 1.1872380065207266, "grad_norm": 0.4183238609779037, "learning_rate": 3.906007250129467e-05, "loss": 0.3592, "step": 1275 }, { "epoch": 1.191895668374476, "grad_norm": 0.7184358527674694, "learning_rate": 3.8995339202485756e-05, "loss": 0.3632, "step": 1280 }, { "epoch": 1.1965533302282254, "grad_norm": 0.48916847029175153, "learning_rate": 3.8930605903676856e-05, "loss": 0.3674, "step": 1285 }, { "epoch": 1.201210992081975, "grad_norm": 0.623382678624382, "learning_rate": 3.886587260486795e-05, "loss": 0.3556, "step": 1290 }, { "epoch": 1.2058686539357242, "grad_norm": 0.4800383787348193, "learning_rate": 3.8801139306059035e-05, "loss": 0.3594, "step": 1295 }, { "epoch": 1.2105263157894737, "grad_norm": 0.6375885751092937, "learning_rate": 3.873640600725013e-05, "loss": 0.355, "step": 1300 }, { "epoch": 1.2151839776432232, "grad_norm": 0.49911390469996464, "learning_rate": 3.867167270844123e-05, "loss": 0.3658, "step": 1305 }, { "epoch": 1.2198416394969724, "grad_norm": 0.4554497786686015, "learning_rate": 3.8606939409632314e-05, "loss": 0.368, "step": 1310 }, { "epoch": 1.224499301350722, "grad_norm": 0.4131665664704364, "learning_rate": 3.854220611082341e-05, "loss": 0.3577, "step": 1315 }, { "epoch": 1.2291569632044714, "grad_norm": 0.5693677148428811, "learning_rate": 3.84774728120145e-05, "loss": 0.3661, "step": 1320 }, { "epoch": 1.2338146250582207, "grad_norm": 0.4578723685810259, "learning_rate": 3.841273951320559e-05, "loss": 0.358, "step": 1325 }, { "epoch": 1.2384722869119702, "grad_norm": 0.4729308919136961, "learning_rate": 3.8348006214396686e-05, "loss": 0.3632, "step": 1330 }, { "epoch": 1.2431299487657197, "grad_norm": 0.5066895267318144, "learning_rate": 3.828327291558778e-05, "loss": 0.3566, "step": 1335 }, { "epoch": 1.247787610619469, "grad_norm": 0.4962138829349391, "learning_rate": 3.821853961677888e-05, "loss": 0.3587, "step": 1340 }, { "epoch": 1.2524452724732185, "grad_norm": 0.5734753363554875, "learning_rate": 3.8153806317969965e-05, "loss": 0.3488, "step": 1345 }, { "epoch": 1.257102934326968, "grad_norm": 0.6120310214739175, "learning_rate": 3.808907301916106e-05, "loss": 0.3576, "step": 1350 }, { "epoch": 1.2617605961807172, "grad_norm": 0.5658218576288578, "learning_rate": 3.802433972035215e-05, "loss": 0.3546, "step": 1355 }, { "epoch": 1.2664182580344667, "grad_norm": 0.6557222284100431, "learning_rate": 3.7959606421543244e-05, "loss": 0.3483, "step": 1360 }, { "epoch": 1.271075919888216, "grad_norm": 1.0588864854850915, "learning_rate": 3.789487312273434e-05, "loss": 0.361, "step": 1365 }, { "epoch": 1.2757335817419655, "grad_norm": 0.5731233070876053, "learning_rate": 3.783013982392543e-05, "loss": 0.3583, "step": 1370 }, { "epoch": 1.280391243595715, "grad_norm": 0.5782085162825689, "learning_rate": 3.776540652511652e-05, "loss": 0.3591, "step": 1375 }, { "epoch": 1.2850489054494645, "grad_norm": 0.5269999842650822, "learning_rate": 3.7700673226307616e-05, "loss": 0.3573, "step": 1380 }, { "epoch": 1.2897065673032138, "grad_norm": 0.5437266796088942, "learning_rate": 3.763593992749871e-05, "loss": 0.3572, "step": 1385 }, { "epoch": 1.2943642291569633, "grad_norm": 0.5978781187388409, "learning_rate": 3.7571206628689795e-05, "loss": 0.3658, "step": 1390 }, { "epoch": 1.2990218910107125, "grad_norm": 0.41807198858427225, "learning_rate": 3.7506473329880895e-05, "loss": 0.3656, "step": 1395 }, { "epoch": 1.303679552864462, "grad_norm": 0.5038295989601189, "learning_rate": 3.744174003107199e-05, "loss": 0.364, "step": 1400 }, { "epoch": 1.3083372147182115, "grad_norm": 0.6637278469000673, "learning_rate": 3.7377006732263074e-05, "loss": 0.3565, "step": 1405 }, { "epoch": 1.312994876571961, "grad_norm": 0.6240797367878401, "learning_rate": 3.731227343345417e-05, "loss": 0.3555, "step": 1410 }, { "epoch": 1.3176525384257103, "grad_norm": 0.5835116541397476, "learning_rate": 3.724754013464527e-05, "loss": 0.3752, "step": 1415 }, { "epoch": 1.3223102002794598, "grad_norm": 0.5077655915847764, "learning_rate": 3.718280683583635e-05, "loss": 0.3615, "step": 1420 }, { "epoch": 1.326967862133209, "grad_norm": 0.4283170431470846, "learning_rate": 3.7118073537027446e-05, "loss": 0.3565, "step": 1425 }, { "epoch": 1.3316255239869585, "grad_norm": 0.5126037257925429, "learning_rate": 3.705334023821854e-05, "loss": 0.3581, "step": 1430 }, { "epoch": 1.336283185840708, "grad_norm": 0.4521835218535128, "learning_rate": 3.698860693940964e-05, "loss": 0.3614, "step": 1435 }, { "epoch": 1.3409408476944573, "grad_norm": 0.712119612101472, "learning_rate": 3.6923873640600725e-05, "loss": 0.3609, "step": 1440 }, { "epoch": 1.3455985095482068, "grad_norm": 0.5625174596891963, "learning_rate": 3.685914034179182e-05, "loss": 0.3679, "step": 1445 }, { "epoch": 1.350256171401956, "grad_norm": 0.45938752028800234, "learning_rate": 3.679440704298292e-05, "loss": 0.3567, "step": 1450 }, { "epoch": 1.3549138332557056, "grad_norm": 0.44407635063101913, "learning_rate": 3.6729673744174004e-05, "loss": 0.3648, "step": 1455 }, { "epoch": 1.359571495109455, "grad_norm": 0.49932559193381354, "learning_rate": 3.66649404453651e-05, "loss": 0.3503, "step": 1460 }, { "epoch": 1.3642291569632046, "grad_norm": 0.5204089490452626, "learning_rate": 3.660020714655619e-05, "loss": 0.3553, "step": 1465 }, { "epoch": 1.3688868188169538, "grad_norm": 0.4898139175111853, "learning_rate": 3.653547384774728e-05, "loss": 0.3598, "step": 1470 }, { "epoch": 1.3735444806707033, "grad_norm": 0.47942248513574054, "learning_rate": 3.6470740548938376e-05, "loss": 0.3525, "step": 1475 }, { "epoch": 1.3782021425244526, "grad_norm": 0.5117008140291056, "learning_rate": 3.640600725012947e-05, "loss": 0.3558, "step": 1480 }, { "epoch": 1.382859804378202, "grad_norm": 0.5146827923709326, "learning_rate": 3.634127395132056e-05, "loss": 0.3626, "step": 1485 }, { "epoch": 1.3875174662319516, "grad_norm": 0.4987783340634908, "learning_rate": 3.6276540652511655e-05, "loss": 0.3636, "step": 1490 }, { "epoch": 1.392175128085701, "grad_norm": 0.43715066276200976, "learning_rate": 3.621180735370275e-05, "loss": 0.3625, "step": 1495 }, { "epoch": 1.3968327899394504, "grad_norm": 0.48921673899018714, "learning_rate": 3.6147074054893834e-05, "loss": 0.3519, "step": 1500 }, { "epoch": 1.4014904517931999, "grad_norm": 0.3988007094492051, "learning_rate": 3.6082340756084934e-05, "loss": 0.3563, "step": 1505 }, { "epoch": 1.4061481136469491, "grad_norm": 0.43467966511598455, "learning_rate": 3.601760745727603e-05, "loss": 0.3551, "step": 1510 }, { "epoch": 1.4108057755006986, "grad_norm": 0.48943076424102294, "learning_rate": 3.595287415846711e-05, "loss": 0.3657, "step": 1515 }, { "epoch": 1.4154634373544481, "grad_norm": 0.48209126073712294, "learning_rate": 3.5888140859658206e-05, "loss": 0.358, "step": 1520 }, { "epoch": 1.4201210992081974, "grad_norm": 0.5567439927871924, "learning_rate": 3.5823407560849306e-05, "loss": 0.3576, "step": 1525 }, { "epoch": 1.424778761061947, "grad_norm": 0.4200962456460126, "learning_rate": 3.57586742620404e-05, "loss": 0.3481, "step": 1530 }, { "epoch": 1.4294364229156964, "grad_norm": 0.49407522949582217, "learning_rate": 3.5693940963231485e-05, "loss": 0.3642, "step": 1535 }, { "epoch": 1.4340940847694457, "grad_norm": 0.45860567192865026, "learning_rate": 3.5629207664422585e-05, "loss": 0.3542, "step": 1540 }, { "epoch": 1.4387517466231952, "grad_norm": 0.47706198688283163, "learning_rate": 3.556447436561368e-05, "loss": 0.357, "step": 1545 }, { "epoch": 1.4434094084769447, "grad_norm": 0.4631267135241482, "learning_rate": 3.5499741066804764e-05, "loss": 0.3545, "step": 1550 }, { "epoch": 1.448067070330694, "grad_norm": 0.4282967972035589, "learning_rate": 3.543500776799586e-05, "loss": 0.348, "step": 1555 }, { "epoch": 1.4527247321844434, "grad_norm": 0.46718459221601966, "learning_rate": 3.537027446918696e-05, "loss": 0.3545, "step": 1560 }, { "epoch": 1.4573823940381927, "grad_norm": 0.4434558105201629, "learning_rate": 3.530554117037804e-05, "loss": 0.3619, "step": 1565 }, { "epoch": 1.4620400558919422, "grad_norm": 0.461355652696727, "learning_rate": 3.5240807871569136e-05, "loss": 0.3744, "step": 1570 }, { "epoch": 1.4666977177456917, "grad_norm": 0.3983045010357026, "learning_rate": 3.517607457276023e-05, "loss": 0.357, "step": 1575 }, { "epoch": 1.4713553795994412, "grad_norm": 0.5788834887570724, "learning_rate": 3.511134127395132e-05, "loss": 0.3494, "step": 1580 }, { "epoch": 1.4760130414531905, "grad_norm": 0.4394874908573785, "learning_rate": 3.5046607975142415e-05, "loss": 0.3567, "step": 1585 }, { "epoch": 1.48067070330694, "grad_norm": 0.5454916469643164, "learning_rate": 3.498187467633351e-05, "loss": 0.3563, "step": 1590 }, { "epoch": 1.4853283651606892, "grad_norm": 0.4506995718632648, "learning_rate": 3.49171413775246e-05, "loss": 0.3555, "step": 1595 }, { "epoch": 1.4899860270144387, "grad_norm": 0.42671675433365513, "learning_rate": 3.4852408078715694e-05, "loss": 0.3611, "step": 1600 }, { "epoch": 1.4946436888681882, "grad_norm": 0.5131117279777672, "learning_rate": 3.478767477990679e-05, "loss": 0.3497, "step": 1605 }, { "epoch": 1.4993013507219377, "grad_norm": 0.42551446565204576, "learning_rate": 3.472294148109787e-05, "loss": 0.3592, "step": 1610 }, { "epoch": 1.503959012575687, "grad_norm": 0.5177670761589634, "learning_rate": 3.465820818228897e-05, "loss": 0.3547, "step": 1615 }, { "epoch": 1.5086166744294365, "grad_norm": 0.5692243392697299, "learning_rate": 3.4593474883480066e-05, "loss": 0.3589, "step": 1620 }, { "epoch": 1.5132743362831858, "grad_norm": 0.5274651679821818, "learning_rate": 3.452874158467116e-05, "loss": 0.3615, "step": 1625 }, { "epoch": 1.5179319981369352, "grad_norm": 0.7666109031823494, "learning_rate": 3.4464008285862245e-05, "loss": 0.3585, "step": 1630 }, { "epoch": 1.5225896599906847, "grad_norm": 0.44060710518052243, "learning_rate": 3.4399274987053345e-05, "loss": 0.3691, "step": 1635 }, { "epoch": 1.5272473218444342, "grad_norm": 0.4523441559245014, "learning_rate": 3.433454168824444e-05, "loss": 0.3642, "step": 1640 }, { "epoch": 1.5319049836981835, "grad_norm": 0.708835777435254, "learning_rate": 3.4269808389435524e-05, "loss": 0.365, "step": 1645 }, { "epoch": 1.5365626455519328, "grad_norm": 0.4443964283871691, "learning_rate": 3.4205075090626624e-05, "loss": 0.3499, "step": 1650 }, { "epoch": 1.5412203074056823, "grad_norm": 0.46505203165986797, "learning_rate": 3.414034179181772e-05, "loss": 0.3493, "step": 1655 }, { "epoch": 1.5458779692594318, "grad_norm": 0.5009877511493096, "learning_rate": 3.40756084930088e-05, "loss": 0.3499, "step": 1660 }, { "epoch": 1.5505356311131813, "grad_norm": 0.5118843097894884, "learning_rate": 3.4010875194199896e-05, "loss": 0.3615, "step": 1665 }, { "epoch": 1.5551932929669308, "grad_norm": 0.46648335161418786, "learning_rate": 3.3946141895390996e-05, "loss": 0.3583, "step": 1670 }, { "epoch": 1.55985095482068, "grad_norm": 0.43858861188449033, "learning_rate": 3.388140859658208e-05, "loss": 0.3588, "step": 1675 }, { "epoch": 1.5645086166744293, "grad_norm": 0.4843145975850921, "learning_rate": 3.3816675297773175e-05, "loss": 0.3624, "step": 1680 }, { "epoch": 1.5691662785281788, "grad_norm": 0.5026684738264243, "learning_rate": 3.375194199896427e-05, "loss": 0.3504, "step": 1685 }, { "epoch": 1.5738239403819283, "grad_norm": 0.4637568053250778, "learning_rate": 3.368720870015536e-05, "loss": 0.3602, "step": 1690 }, { "epoch": 1.5784816022356778, "grad_norm": 0.423145691720623, "learning_rate": 3.3622475401346454e-05, "loss": 0.355, "step": 1695 }, { "epoch": 1.583139264089427, "grad_norm": 0.4574670721811121, "learning_rate": 3.355774210253755e-05, "loss": 0.3593, "step": 1700 }, { "epoch": 1.5877969259431766, "grad_norm": 0.41701873135432355, "learning_rate": 3.349300880372864e-05, "loss": 0.3549, "step": 1705 }, { "epoch": 1.5924545877969258, "grad_norm": 0.4757621290288763, "learning_rate": 3.342827550491973e-05, "loss": 0.361, "step": 1710 }, { "epoch": 1.5971122496506753, "grad_norm": 0.7719532221975699, "learning_rate": 3.3363542206110826e-05, "loss": 0.3628, "step": 1715 }, { "epoch": 1.6017699115044248, "grad_norm": 0.48203043759926095, "learning_rate": 3.329880890730191e-05, "loss": 0.3501, "step": 1720 }, { "epoch": 1.6064275733581743, "grad_norm": 0.607484305563493, "learning_rate": 3.323407560849301e-05, "loss": 0.3556, "step": 1725 }, { "epoch": 1.6110852352119236, "grad_norm": 0.6135311286646739, "learning_rate": 3.3169342309684105e-05, "loss": 0.3671, "step": 1730 }, { "epoch": 1.6157428970656729, "grad_norm": 0.4763852776720388, "learning_rate": 3.31046090108752e-05, "loss": 0.3661, "step": 1735 }, { "epoch": 1.6204005589194224, "grad_norm": 0.48283218615106893, "learning_rate": 3.3039875712066284e-05, "loss": 0.3473, "step": 1740 }, { "epoch": 1.6250582207731719, "grad_norm": 0.46194912198075855, "learning_rate": 3.2975142413257384e-05, "loss": 0.3768, "step": 1745 }, { "epoch": 1.6297158826269214, "grad_norm": 1.4221445715200824, "learning_rate": 3.291040911444848e-05, "loss": 0.3559, "step": 1750 }, { "epoch": 1.6343735444806708, "grad_norm": 0.47454861294050155, "learning_rate": 3.284567581563956e-05, "loss": 0.3654, "step": 1755 }, { "epoch": 1.6390312063344201, "grad_norm": 0.43692651548618333, "learning_rate": 3.278094251683066e-05, "loss": 0.3497, "step": 1760 }, { "epoch": 1.6436888681881694, "grad_norm": 0.5186454634415874, "learning_rate": 3.2716209218021756e-05, "loss": 0.3536, "step": 1765 }, { "epoch": 1.648346530041919, "grad_norm": 0.45932579778649213, "learning_rate": 3.265147591921284e-05, "loss": 0.3487, "step": 1770 }, { "epoch": 1.6530041918956684, "grad_norm": 0.46417720721957867, "learning_rate": 3.2586742620403935e-05, "loss": 0.3635, "step": 1775 }, { "epoch": 1.6576618537494179, "grad_norm": 0.5023929466845737, "learning_rate": 3.2522009321595035e-05, "loss": 0.3512, "step": 1780 }, { "epoch": 1.6623195156031674, "grad_norm": 0.4894634348948924, "learning_rate": 3.245727602278612e-05, "loss": 0.3598, "step": 1785 }, { "epoch": 1.6669771774569166, "grad_norm": 0.5048826565939405, "learning_rate": 3.2392542723977214e-05, "loss": 0.3504, "step": 1790 }, { "epoch": 1.671634839310666, "grad_norm": 0.5145217211825706, "learning_rate": 3.232780942516831e-05, "loss": 0.3511, "step": 1795 }, { "epoch": 1.6762925011644154, "grad_norm": 0.4024176318642373, "learning_rate": 3.22630761263594e-05, "loss": 0.3508, "step": 1800 }, { "epoch": 1.680950163018165, "grad_norm": 0.49327849470237983, "learning_rate": 3.219834282755049e-05, "loss": 0.3565, "step": 1805 }, { "epoch": 1.6856078248719144, "grad_norm": 0.45839399720377905, "learning_rate": 3.2133609528741586e-05, "loss": 0.3559, "step": 1810 }, { "epoch": 1.6902654867256637, "grad_norm": 0.4594056637683195, "learning_rate": 3.206887622993268e-05, "loss": 0.3565, "step": 1815 }, { "epoch": 1.6949231485794132, "grad_norm": 0.3330975796505, "learning_rate": 3.200414293112377e-05, "loss": 0.344, "step": 1820 }, { "epoch": 1.6995808104331624, "grad_norm": 0.4320511523445828, "learning_rate": 3.1939409632314865e-05, "loss": 0.3465, "step": 1825 }, { "epoch": 1.704238472286912, "grad_norm": 0.4508746942172372, "learning_rate": 3.187467633350596e-05, "loss": 0.3509, "step": 1830 }, { "epoch": 1.7088961341406614, "grad_norm": 0.3904518189045298, "learning_rate": 3.180994303469705e-05, "loss": 0.3597, "step": 1835 }, { "epoch": 1.713553795994411, "grad_norm": 0.43579954758781125, "learning_rate": 3.1745209735888144e-05, "loss": 0.3525, "step": 1840 }, { "epoch": 1.7182114578481602, "grad_norm": 0.43565868704380867, "learning_rate": 3.168047643707924e-05, "loss": 0.3572, "step": 1845 }, { "epoch": 1.7228691197019095, "grad_norm": 0.3977951937681229, "learning_rate": 3.161574313827032e-05, "loss": 0.3649, "step": 1850 }, { "epoch": 1.727526781555659, "grad_norm": 0.4330099692635278, "learning_rate": 3.155100983946142e-05, "loss": 0.3461, "step": 1855 }, { "epoch": 1.7321844434094085, "grad_norm": 0.460500356519855, "learning_rate": 3.1486276540652516e-05, "loss": 0.3715, "step": 1860 }, { "epoch": 1.736842105263158, "grad_norm": 0.5504758175221829, "learning_rate": 3.14215432418436e-05, "loss": 0.3512, "step": 1865 }, { "epoch": 1.7414997671169075, "grad_norm": 0.43719273038065815, "learning_rate": 3.13568099430347e-05, "loss": 0.3533, "step": 1870 }, { "epoch": 1.7461574289706567, "grad_norm": 0.4400861509481671, "learning_rate": 3.1292076644225795e-05, "loss": 0.3688, "step": 1875 }, { "epoch": 1.750815090824406, "grad_norm": 0.46567184462942324, "learning_rate": 3.122734334541688e-05, "loss": 0.3618, "step": 1880 }, { "epoch": 1.7554727526781555, "grad_norm": 1.1917558909216905, "learning_rate": 3.1162610046607974e-05, "loss": 0.3618, "step": 1885 }, { "epoch": 1.760130414531905, "grad_norm": 0.5227512432456358, "learning_rate": 3.1097876747799074e-05, "loss": 0.3601, "step": 1890 }, { "epoch": 1.7647880763856545, "grad_norm": 0.47292385773044443, "learning_rate": 3.103314344899016e-05, "loss": 0.3666, "step": 1895 }, { "epoch": 1.7694457382394038, "grad_norm": 0.40537252452985134, "learning_rate": 3.096841015018125e-05, "loss": 0.3577, "step": 1900 }, { "epoch": 1.7741034000931533, "grad_norm": 0.48054602546701, "learning_rate": 3.0903676851372346e-05, "loss": 0.3569, "step": 1905 }, { "epoch": 1.7787610619469025, "grad_norm": 0.5506290646284986, "learning_rate": 3.083894355256344e-05, "loss": 0.3489, "step": 1910 }, { "epoch": 1.783418723800652, "grad_norm": 0.5374831746437716, "learning_rate": 3.077421025375453e-05, "loss": 0.3456, "step": 1915 }, { "epoch": 1.7880763856544015, "grad_norm": 0.49023775966558913, "learning_rate": 3.0709476954945625e-05, "loss": 0.3496, "step": 1920 }, { "epoch": 1.792734047508151, "grad_norm": 0.45919121386728695, "learning_rate": 3.064474365613672e-05, "loss": 0.3594, "step": 1925 }, { "epoch": 1.7973917093619003, "grad_norm": 0.6713980718794391, "learning_rate": 3.058001035732781e-05, "loss": 0.349, "step": 1930 }, { "epoch": 1.8020493712156498, "grad_norm": 0.5944315080519817, "learning_rate": 3.0515277058518904e-05, "loss": 0.3449, "step": 1935 }, { "epoch": 1.806707033069399, "grad_norm": 0.4509399625969159, "learning_rate": 3.045054375971e-05, "loss": 0.3485, "step": 1940 }, { "epoch": 1.8113646949231486, "grad_norm": 5.075923931441117, "learning_rate": 3.0385810460901086e-05, "loss": 0.358, "step": 1945 }, { "epoch": 1.816022356776898, "grad_norm": 0.48777551087525495, "learning_rate": 3.0321077162092183e-05, "loss": 0.3499, "step": 1950 }, { "epoch": 1.8206800186306475, "grad_norm": 0.42648815650884947, "learning_rate": 3.0256343863283276e-05, "loss": 0.354, "step": 1955 }, { "epoch": 1.8253376804843968, "grad_norm": 0.4393440776891489, "learning_rate": 3.0191610564474365e-05, "loss": 0.355, "step": 1960 }, { "epoch": 1.829995342338146, "grad_norm": 0.3936466364379742, "learning_rate": 3.0126877265665458e-05, "loss": 0.3562, "step": 1965 }, { "epoch": 1.8346530041918956, "grad_norm": 0.4434411338811971, "learning_rate": 3.0062143966856555e-05, "loss": 0.35, "step": 1970 }, { "epoch": 1.839310666045645, "grad_norm": 0.5143599548717581, "learning_rate": 2.9997410668047644e-05, "loss": 0.3557, "step": 1975 }, { "epoch": 1.8439683278993946, "grad_norm": 0.6303950354070114, "learning_rate": 2.9932677369238737e-05, "loss": 0.3506, "step": 1980 }, { "epoch": 1.848625989753144, "grad_norm": 0.45776321898729805, "learning_rate": 2.9867944070429834e-05, "loss": 0.3642, "step": 1985 }, { "epoch": 1.8532836516068933, "grad_norm": 0.4983828610490197, "learning_rate": 2.980321077162092e-05, "loss": 0.3577, "step": 1990 }, { "epoch": 1.8579413134606426, "grad_norm": 0.3863672728357155, "learning_rate": 2.9738477472812016e-05, "loss": 0.3449, "step": 1995 }, { "epoch": 1.8625989753143921, "grad_norm": 0.37351126016989494, "learning_rate": 2.967374417400311e-05, "loss": 0.3535, "step": 2000 }, { "epoch": 1.8672566371681416, "grad_norm": 0.4327220658780403, "learning_rate": 2.96090108751942e-05, "loss": 0.3605, "step": 2005 }, { "epoch": 1.871914299021891, "grad_norm": 0.39839413885179564, "learning_rate": 2.9544277576385292e-05, "loss": 0.3495, "step": 2010 }, { "epoch": 1.8765719608756404, "grad_norm": 0.374126275160625, "learning_rate": 2.9479544277576388e-05, "loss": 0.3612, "step": 2015 }, { "epoch": 1.8812296227293899, "grad_norm": 0.42821521317553357, "learning_rate": 2.941481097876748e-05, "loss": 0.3477, "step": 2020 }, { "epoch": 1.8858872845831391, "grad_norm": 0.3874936015210937, "learning_rate": 2.935007767995857e-05, "loss": 0.3528, "step": 2025 }, { "epoch": 1.8905449464368886, "grad_norm": 0.4708072432032237, "learning_rate": 2.9285344381149664e-05, "loss": 0.3498, "step": 2030 }, { "epoch": 1.8952026082906381, "grad_norm": 0.498888491133848, "learning_rate": 2.922061108234076e-05, "loss": 0.3485, "step": 2035 }, { "epoch": 1.8998602701443876, "grad_norm": 0.8127154305153814, "learning_rate": 2.915587778353185e-05, "loss": 0.3574, "step": 2040 }, { "epoch": 1.904517931998137, "grad_norm": 0.4745980355418612, "learning_rate": 2.9091144484722943e-05, "loss": 0.3599, "step": 2045 }, { "epoch": 1.9091755938518864, "grad_norm": 0.47399947476713655, "learning_rate": 2.902641118591404e-05, "loss": 0.3545, "step": 2050 }, { "epoch": 1.9138332557056357, "grad_norm": 0.38031350696691324, "learning_rate": 2.8961677887105125e-05, "loss": 0.3542, "step": 2055 }, { "epoch": 1.9184909175593852, "grad_norm": 0.4533814887670319, "learning_rate": 2.889694458829622e-05, "loss": 0.349, "step": 2060 }, { "epoch": 1.9231485794131347, "grad_norm": 0.44224884178126095, "learning_rate": 2.8832211289487315e-05, "loss": 0.3505, "step": 2065 }, { "epoch": 1.9278062412668842, "grad_norm": 0.46610685858862294, "learning_rate": 2.8767477990678404e-05, "loss": 0.3542, "step": 2070 }, { "epoch": 1.9324639031206334, "grad_norm": 0.4899140729321592, "learning_rate": 2.8702744691869497e-05, "loss": 0.3533, "step": 2075 }, { "epoch": 1.9371215649743827, "grad_norm": 0.43432934286798436, "learning_rate": 2.8638011393060594e-05, "loss": 0.3469, "step": 2080 }, { "epoch": 1.9417792268281322, "grad_norm": 0.5739620989128141, "learning_rate": 2.8573278094251683e-05, "loss": 0.3571, "step": 2085 }, { "epoch": 1.9464368886818817, "grad_norm": 0.4937365242137196, "learning_rate": 2.8508544795442776e-05, "loss": 0.3433, "step": 2090 }, { "epoch": 1.9510945505356312, "grad_norm": 0.5543854067006561, "learning_rate": 2.8443811496633873e-05, "loss": 0.3503, "step": 2095 }, { "epoch": 1.9557522123893807, "grad_norm": 0.4163424169047461, "learning_rate": 2.837907819782496e-05, "loss": 0.3506, "step": 2100 }, { "epoch": 1.96040987424313, "grad_norm": 0.4955261585873019, "learning_rate": 2.8314344899016055e-05, "loss": 0.3588, "step": 2105 }, { "epoch": 1.9650675360968792, "grad_norm": 0.43693267953533543, "learning_rate": 2.8249611600207148e-05, "loss": 0.3435, "step": 2110 }, { "epoch": 1.9697251979506287, "grad_norm": 0.4794397843544659, "learning_rate": 2.8184878301398244e-05, "loss": 0.3522, "step": 2115 }, { "epoch": 1.9743828598043782, "grad_norm": 0.381177878344807, "learning_rate": 2.812014500258933e-05, "loss": 0.3549, "step": 2120 }, { "epoch": 1.9790405216581277, "grad_norm": 0.3964312922985258, "learning_rate": 2.8055411703780427e-05, "loss": 0.3496, "step": 2125 }, { "epoch": 1.983698183511877, "grad_norm": 0.4029797725417912, "learning_rate": 2.799067840497152e-05, "loss": 0.3526, "step": 2130 }, { "epoch": 1.9883558453656265, "grad_norm": 0.4113836784940735, "learning_rate": 2.792594510616261e-05, "loss": 0.3572, "step": 2135 }, { "epoch": 1.9930135072193758, "grad_norm": 0.5493285311857958, "learning_rate": 2.7861211807353703e-05, "loss": 0.3551, "step": 2140 }, { "epoch": 1.9976711690731253, "grad_norm": 0.5328890032230302, "learning_rate": 2.77964785085448e-05, "loss": 0.3561, "step": 2145 }, { "epoch": 2.0037261294829993, "grad_norm": 0.5984165582873675, "learning_rate": 2.773174520973589e-05, "loss": 0.2804, "step": 2150 }, { "epoch": 2.008383791336749, "grad_norm": 0.4714992480355112, "learning_rate": 2.766701191092698e-05, "loss": 0.2744, "step": 2155 }, { "epoch": 2.0130414531904983, "grad_norm": 0.4678816139163974, "learning_rate": 2.7602278612118078e-05, "loss": 0.2655, "step": 2160 }, { "epoch": 2.017699115044248, "grad_norm": 0.42447827115766357, "learning_rate": 2.7537545313309164e-05, "loss": 0.2636, "step": 2165 }, { "epoch": 2.0223567768979973, "grad_norm": 0.47173192457898244, "learning_rate": 2.747281201450026e-05, "loss": 0.2648, "step": 2170 }, { "epoch": 2.027014438751747, "grad_norm": 0.4561305755828067, "learning_rate": 2.7408078715691354e-05, "loss": 0.263, "step": 2175 }, { "epoch": 2.031672100605496, "grad_norm": 0.4522353799817268, "learning_rate": 2.7343345416882443e-05, "loss": 0.2629, "step": 2180 }, { "epoch": 2.0363297624592454, "grad_norm": 0.38229189586009915, "learning_rate": 2.7278612118073536e-05, "loss": 0.2685, "step": 2185 }, { "epoch": 2.040987424312995, "grad_norm": 0.4159439610819745, "learning_rate": 2.7213878819264633e-05, "loss": 0.2683, "step": 2190 }, { "epoch": 2.0456450861667443, "grad_norm": 0.3774427269329061, "learning_rate": 2.7149145520455722e-05, "loss": 0.2602, "step": 2195 }, { "epoch": 2.050302748020494, "grad_norm": 0.565695621556773, "learning_rate": 2.7084412221646815e-05, "loss": 0.2623, "step": 2200 }, { "epoch": 2.0549604098742433, "grad_norm": 0.49293318481894627, "learning_rate": 2.701967892283791e-05, "loss": 0.2715, "step": 2205 }, { "epoch": 2.0596180717279924, "grad_norm": 0.6585092985935234, "learning_rate": 2.6954945624029004e-05, "loss": 0.2537, "step": 2210 }, { "epoch": 2.064275733581742, "grad_norm": 0.38182097899515915, "learning_rate": 2.6890212325220094e-05, "loss": 0.2649, "step": 2215 }, { "epoch": 2.0689333954354914, "grad_norm": 0.3683418488670165, "learning_rate": 2.6825479026411187e-05, "loss": 0.2678, "step": 2220 }, { "epoch": 2.073591057289241, "grad_norm": 0.420590228635256, "learning_rate": 2.6760745727602283e-05, "loss": 0.2624, "step": 2225 }, { "epoch": 2.0782487191429904, "grad_norm": 0.4613111322394453, "learning_rate": 2.669601242879337e-05, "loss": 0.262, "step": 2230 }, { "epoch": 2.0829063809967394, "grad_norm": 0.3718600727520438, "learning_rate": 2.6631279129984466e-05, "loss": 0.2672, "step": 2235 }, { "epoch": 2.087564042850489, "grad_norm": 0.40582714619106275, "learning_rate": 2.656654583117556e-05, "loss": 0.2662, "step": 2240 }, { "epoch": 2.0922217047042384, "grad_norm": 0.37443549778787827, "learning_rate": 2.650181253236665e-05, "loss": 0.2694, "step": 2245 }, { "epoch": 2.096879366557988, "grad_norm": 0.45875250557655717, "learning_rate": 2.643707923355774e-05, "loss": 0.265, "step": 2250 }, { "epoch": 2.1015370284117374, "grad_norm": 0.45610937078260994, "learning_rate": 2.6372345934748838e-05, "loss": 0.2705, "step": 2255 }, { "epoch": 2.106194690265487, "grad_norm": 0.39262409693878664, "learning_rate": 2.6307612635939928e-05, "loss": 0.266, "step": 2260 }, { "epoch": 2.110852352119236, "grad_norm": 0.38655021127646183, "learning_rate": 2.624287933713102e-05, "loss": 0.2675, "step": 2265 }, { "epoch": 2.1155100139729854, "grad_norm": 0.3998257976477759, "learning_rate": 2.6178146038322117e-05, "loss": 0.2643, "step": 2270 }, { "epoch": 2.120167675826735, "grad_norm": 0.3728050051150394, "learning_rate": 2.6113412739513203e-05, "loss": 0.2734, "step": 2275 }, { "epoch": 2.1248253376804844, "grad_norm": 0.3859776406603847, "learning_rate": 2.60486794407043e-05, "loss": 0.2714, "step": 2280 }, { "epoch": 2.129482999534234, "grad_norm": 0.3514088615004306, "learning_rate": 2.5983946141895393e-05, "loss": 0.2658, "step": 2285 }, { "epoch": 2.1341406613879834, "grad_norm": 0.3993459698005776, "learning_rate": 2.5919212843086482e-05, "loss": 0.2743, "step": 2290 }, { "epoch": 2.1387983232417325, "grad_norm": 0.37448253228082584, "learning_rate": 2.5854479544277575e-05, "loss": 0.2756, "step": 2295 }, { "epoch": 2.143455985095482, "grad_norm": 0.4089824986116572, "learning_rate": 2.578974624546867e-05, "loss": 0.2699, "step": 2300 }, { "epoch": 2.1481136469492315, "grad_norm": 0.4102498090519893, "learning_rate": 2.5725012946659764e-05, "loss": 0.2656, "step": 2305 }, { "epoch": 2.152771308802981, "grad_norm": 0.37740072290090676, "learning_rate": 2.5660279647850854e-05, "loss": 0.2599, "step": 2310 }, { "epoch": 2.1574289706567304, "grad_norm": 0.4187670875249096, "learning_rate": 2.559554634904195e-05, "loss": 0.2649, "step": 2315 }, { "epoch": 2.16208663251048, "grad_norm": 0.3704887550582043, "learning_rate": 2.5530813050233043e-05, "loss": 0.266, "step": 2320 }, { "epoch": 2.166744294364229, "grad_norm": 0.41749860106499453, "learning_rate": 2.5466079751424133e-05, "loss": 0.2718, "step": 2325 }, { "epoch": 2.1714019562179785, "grad_norm": 0.4091742643963768, "learning_rate": 2.5401346452615226e-05, "loss": 0.2661, "step": 2330 }, { "epoch": 2.176059618071728, "grad_norm": 0.39802057961683956, "learning_rate": 2.5336613153806322e-05, "loss": 0.2661, "step": 2335 }, { "epoch": 2.1807172799254775, "grad_norm": 0.3755362152016269, "learning_rate": 2.527187985499741e-05, "loss": 0.274, "step": 2340 }, { "epoch": 2.185374941779227, "grad_norm": 0.3946817057524793, "learning_rate": 2.5207146556188505e-05, "loss": 0.2708, "step": 2345 }, { "epoch": 2.190032603632976, "grad_norm": 0.3587052604975335, "learning_rate": 2.5142413257379598e-05, "loss": 0.2602, "step": 2350 }, { "epoch": 2.1946902654867255, "grad_norm": 0.3592964805141227, "learning_rate": 2.5077679958570688e-05, "loss": 0.2686, "step": 2355 }, { "epoch": 2.199347927340475, "grad_norm": 0.38516040456877776, "learning_rate": 2.5012946659761784e-05, "loss": 0.2705, "step": 2360 }, { "epoch": 2.2040055891942245, "grad_norm": 0.35653956745080667, "learning_rate": 2.4948213360952874e-05, "loss": 0.2748, "step": 2365 }, { "epoch": 2.208663251047974, "grad_norm": 0.4112079806386243, "learning_rate": 2.488348006214397e-05, "loss": 0.2674, "step": 2370 }, { "epoch": 2.2133209129017235, "grad_norm": 0.4474539241301923, "learning_rate": 2.481874676333506e-05, "loss": 0.2741, "step": 2375 }, { "epoch": 2.2179785747554726, "grad_norm": 0.35197872763228255, "learning_rate": 2.4754013464526156e-05, "loss": 0.272, "step": 2380 }, { "epoch": 2.222636236609222, "grad_norm": 0.45668423796359864, "learning_rate": 2.4689280165717246e-05, "loss": 0.2795, "step": 2385 }, { "epoch": 2.2272938984629715, "grad_norm": 0.3704886190545978, "learning_rate": 2.462454686690834e-05, "loss": 0.2707, "step": 2390 }, { "epoch": 2.231951560316721, "grad_norm": 0.4167644651454507, "learning_rate": 2.455981356809943e-05, "loss": 0.2649, "step": 2395 }, { "epoch": 2.2366092221704705, "grad_norm": 0.43736906255101615, "learning_rate": 2.4495080269290524e-05, "loss": 0.2658, "step": 2400 }, { "epoch": 2.24126688402422, "grad_norm": 0.3457361702195315, "learning_rate": 2.4430346970481614e-05, "loss": 0.264, "step": 2405 }, { "epoch": 2.245924545877969, "grad_norm": 0.40879986903970805, "learning_rate": 2.436561367167271e-05, "loss": 0.27, "step": 2410 }, { "epoch": 2.2505822077317186, "grad_norm": 0.3554250829584864, "learning_rate": 2.4300880372863803e-05, "loss": 0.2635, "step": 2415 }, { "epoch": 2.255239869585468, "grad_norm": 0.5634529170427344, "learning_rate": 2.4236147074054896e-05, "loss": 0.2695, "step": 2420 }, { "epoch": 2.2598975314392176, "grad_norm": 0.3282809670722255, "learning_rate": 2.417141377524599e-05, "loss": 0.2662, "step": 2425 }, { "epoch": 2.264555193292967, "grad_norm": 0.36267855475875027, "learning_rate": 2.410668047643708e-05, "loss": 0.2676, "step": 2430 }, { "epoch": 2.2692128551467166, "grad_norm": 0.3519572830021516, "learning_rate": 2.4041947177628175e-05, "loss": 0.2655, "step": 2435 }, { "epoch": 2.2738705170004656, "grad_norm": 0.3699048260962973, "learning_rate": 2.3977213878819265e-05, "loss": 0.2709, "step": 2440 }, { "epoch": 2.278528178854215, "grad_norm": 0.3644291853440569, "learning_rate": 2.3912480580010358e-05, "loss": 0.2679, "step": 2445 }, { "epoch": 2.2831858407079646, "grad_norm": 0.35058538411241036, "learning_rate": 2.384774728120145e-05, "loss": 0.2692, "step": 2450 }, { "epoch": 2.287843502561714, "grad_norm": 0.34113601338207766, "learning_rate": 2.3783013982392544e-05, "loss": 0.2625, "step": 2455 }, { "epoch": 2.2925011644154636, "grad_norm": 0.41360101431801755, "learning_rate": 2.3718280683583634e-05, "loss": 0.2717, "step": 2460 }, { "epoch": 2.2971588262692126, "grad_norm": 0.39817768558901523, "learning_rate": 2.365354738477473e-05, "loss": 0.2751, "step": 2465 }, { "epoch": 2.301816488122962, "grad_norm": 0.3581599495294941, "learning_rate": 2.3588814085965823e-05, "loss": 0.2685, "step": 2470 }, { "epoch": 2.3064741499767116, "grad_norm": 0.35278644903557793, "learning_rate": 2.3524080787156916e-05, "loss": 0.2726, "step": 2475 }, { "epoch": 2.311131811830461, "grad_norm": 0.39196253502284617, "learning_rate": 2.345934748834801e-05, "loss": 0.2735, "step": 2480 }, { "epoch": 2.3157894736842106, "grad_norm": 0.36148941355080827, "learning_rate": 2.33946141895391e-05, "loss": 0.2664, "step": 2485 }, { "epoch": 2.32044713553796, "grad_norm": 0.3461838887999913, "learning_rate": 2.3329880890730195e-05, "loss": 0.2711, "step": 2490 }, { "epoch": 2.3251047973917096, "grad_norm": 0.3402855214001067, "learning_rate": 2.3265147591921284e-05, "loss": 0.2722, "step": 2495 }, { "epoch": 2.3297624592454587, "grad_norm": 0.35354780484835885, "learning_rate": 2.3200414293112377e-05, "loss": 0.2612, "step": 2500 }, { "epoch": 2.334420121099208, "grad_norm": 0.3348530506815726, "learning_rate": 2.313568099430347e-05, "loss": 0.2699, "step": 2505 }, { "epoch": 2.3390777829529577, "grad_norm": 0.40765057892007006, "learning_rate": 2.3070947695494563e-05, "loss": 0.2686, "step": 2510 }, { "epoch": 2.343735444806707, "grad_norm": 0.4102911806616052, "learning_rate": 2.3006214396685656e-05, "loss": 0.2713, "step": 2515 }, { "epoch": 2.3483931066604566, "grad_norm": 0.3562620388381706, "learning_rate": 2.294148109787675e-05, "loss": 0.2697, "step": 2520 }, { "epoch": 2.3530507685142057, "grad_norm": 0.4064627382613687, "learning_rate": 2.2876747799067842e-05, "loss": 0.2768, "step": 2525 }, { "epoch": 2.357708430367955, "grad_norm": 0.3563887789663656, "learning_rate": 2.2812014500258935e-05, "loss": 0.2643, "step": 2530 }, { "epoch": 2.3623660922217047, "grad_norm": 0.39545043684780473, "learning_rate": 2.274728120145003e-05, "loss": 0.2616, "step": 2535 }, { "epoch": 2.367023754075454, "grad_norm": 0.3361423848103306, "learning_rate": 2.2682547902641118e-05, "loss": 0.2734, "step": 2540 }, { "epoch": 2.3716814159292037, "grad_norm": 0.32815886965478525, "learning_rate": 2.2617814603832214e-05, "loss": 0.2702, "step": 2545 }, { "epoch": 2.376339077782953, "grad_norm": 0.34894240413223626, "learning_rate": 2.2553081305023304e-05, "loss": 0.271, "step": 2550 }, { "epoch": 2.380996739636702, "grad_norm": 0.42037764961424934, "learning_rate": 2.2488348006214397e-05, "loss": 0.2675, "step": 2555 }, { "epoch": 2.3856544014904517, "grad_norm": 0.37230182971619175, "learning_rate": 2.242361470740549e-05, "loss": 0.2687, "step": 2560 }, { "epoch": 2.390312063344201, "grad_norm": 0.36982479685423386, "learning_rate": 2.2358881408596583e-05, "loss": 0.2728, "step": 2565 }, { "epoch": 2.3949697251979507, "grad_norm": 0.35054834167471494, "learning_rate": 2.2294148109787676e-05, "loss": 0.2691, "step": 2570 }, { "epoch": 2.3996273870517, "grad_norm": 0.32092462414484474, "learning_rate": 2.222941481097877e-05, "loss": 0.2709, "step": 2575 }, { "epoch": 2.4042850489054493, "grad_norm": 1.2050143590001547, "learning_rate": 2.2164681512169862e-05, "loss": 0.2629, "step": 2580 }, { "epoch": 2.4089427107591987, "grad_norm": 0.33689475853765, "learning_rate": 2.2099948213360955e-05, "loss": 0.2671, "step": 2585 }, { "epoch": 2.4136003726129482, "grad_norm": 0.3671755543903409, "learning_rate": 2.2035214914552048e-05, "loss": 0.2683, "step": 2590 }, { "epoch": 2.4182580344666977, "grad_norm": 0.40263403450086455, "learning_rate": 2.1970481615743137e-05, "loss": 0.2751, "step": 2595 }, { "epoch": 2.4229156963204472, "grad_norm": 0.41221443001942837, "learning_rate": 2.1905748316934234e-05, "loss": 0.2712, "step": 2600 }, { "epoch": 2.4275733581741967, "grad_norm": 0.3652269897862454, "learning_rate": 2.1841015018125323e-05, "loss": 0.2634, "step": 2605 }, { "epoch": 2.432231020027946, "grad_norm": 0.3421908380271559, "learning_rate": 2.177628171931642e-05, "loss": 0.266, "step": 2610 }, { "epoch": 2.4368886818816953, "grad_norm": 0.402660546788801, "learning_rate": 2.171154842050751e-05, "loss": 0.2678, "step": 2615 }, { "epoch": 2.4415463437354448, "grad_norm": 0.32661166464182784, "learning_rate": 2.1646815121698602e-05, "loss": 0.2636, "step": 2620 }, { "epoch": 2.4462040055891943, "grad_norm": 0.3574564601430305, "learning_rate": 2.1582081822889695e-05, "loss": 0.2668, "step": 2625 }, { "epoch": 2.4508616674429438, "grad_norm": 0.3821106408395511, "learning_rate": 2.151734852408079e-05, "loss": 0.2656, "step": 2630 }, { "epoch": 2.4555193292966933, "grad_norm": 0.3477029236786589, "learning_rate": 2.145261522527188e-05, "loss": 0.2742, "step": 2635 }, { "epoch": 2.4601769911504423, "grad_norm": 0.3440252979580942, "learning_rate": 2.1387881926462974e-05, "loss": 0.2708, "step": 2640 }, { "epoch": 2.464834653004192, "grad_norm": 0.36361827965164945, "learning_rate": 2.1323148627654067e-05, "loss": 0.273, "step": 2645 }, { "epoch": 2.4694923148579413, "grad_norm": 0.38388101046779394, "learning_rate": 2.1258415328845157e-05, "loss": 0.2663, "step": 2650 }, { "epoch": 2.474149976711691, "grad_norm": 0.3448917702655118, "learning_rate": 2.1193682030036253e-05, "loss": 0.2634, "step": 2655 }, { "epoch": 2.4788076385654403, "grad_norm": 0.35537977017667854, "learning_rate": 2.1128948731227343e-05, "loss": 0.268, "step": 2660 }, { "epoch": 2.48346530041919, "grad_norm": 0.3611395803055931, "learning_rate": 2.106421543241844e-05, "loss": 0.265, "step": 2665 }, { "epoch": 2.488122962272939, "grad_norm": 0.37999205623173077, "learning_rate": 2.099948213360953e-05, "loss": 0.2666, "step": 2670 }, { "epoch": 2.4927806241266883, "grad_norm": 0.3144357001947592, "learning_rate": 2.0934748834800622e-05, "loss": 0.2661, "step": 2675 }, { "epoch": 2.497438285980438, "grad_norm": 0.36802186540936016, "learning_rate": 2.0870015535991715e-05, "loss": 0.27, "step": 2680 }, { "epoch": 2.5020959478341873, "grad_norm": 0.3635927275702697, "learning_rate": 2.0805282237182808e-05, "loss": 0.2625, "step": 2685 }, { "epoch": 2.506753609687937, "grad_norm": 0.36098253150816245, "learning_rate": 2.07405489383739e-05, "loss": 0.2612, "step": 2690 }, { "epoch": 2.511411271541686, "grad_norm": 0.32879608954796885, "learning_rate": 2.0675815639564994e-05, "loss": 0.2697, "step": 2695 }, { "epoch": 2.5160689333954354, "grad_norm": 0.34818375160509507, "learning_rate": 2.0611082340756087e-05, "loss": 0.257, "step": 2700 }, { "epoch": 2.520726595249185, "grad_norm": 0.3673945504496394, "learning_rate": 2.054634904194718e-05, "loss": 0.2694, "step": 2705 }, { "epoch": 2.5253842571029343, "grad_norm": 0.3776914324520908, "learning_rate": 2.0481615743138273e-05, "loss": 0.2677, "step": 2710 }, { "epoch": 2.530041918956684, "grad_norm": 0.34023868416264125, "learning_rate": 2.0416882444329362e-05, "loss": 0.2738, "step": 2715 }, { "epoch": 2.5346995808104333, "grad_norm": 0.3305889551239856, "learning_rate": 2.035214914552046e-05, "loss": 0.2715, "step": 2720 }, { "epoch": 2.539357242664183, "grad_norm": 0.3938738025769714, "learning_rate": 2.028741584671155e-05, "loss": 0.2701, "step": 2725 }, { "epoch": 2.544014904517932, "grad_norm": 0.37961051567522874, "learning_rate": 2.022268254790264e-05, "loss": 0.2722, "step": 2730 }, { "epoch": 2.5486725663716814, "grad_norm": 0.338048022840888, "learning_rate": 2.0157949249093734e-05, "loss": 0.2626, "step": 2735 }, { "epoch": 2.553330228225431, "grad_norm": 0.3379750374432762, "learning_rate": 2.0093215950284827e-05, "loss": 0.2679, "step": 2740 }, { "epoch": 2.5579878900791804, "grad_norm": 0.33543695956925573, "learning_rate": 2.002848265147592e-05, "loss": 0.2665, "step": 2745 }, { "epoch": 2.5626455519329294, "grad_norm": 0.41570547699962784, "learning_rate": 1.9963749352667013e-05, "loss": 0.2609, "step": 2750 }, { "epoch": 2.567303213786679, "grad_norm": 0.35784777320124683, "learning_rate": 1.9899016053858106e-05, "loss": 0.2693, "step": 2755 }, { "epoch": 2.5719608756404284, "grad_norm": 0.3238722081590453, "learning_rate": 1.98342827550492e-05, "loss": 0.2672, "step": 2760 }, { "epoch": 2.576618537494178, "grad_norm": 0.33209275620777656, "learning_rate": 1.9769549456240292e-05, "loss": 0.2642, "step": 2765 }, { "epoch": 2.5812761993479274, "grad_norm": 0.34595699646045136, "learning_rate": 1.9704816157431382e-05, "loss": 0.2611, "step": 2770 }, { "epoch": 2.585933861201677, "grad_norm": 0.35000726629254053, "learning_rate": 1.9640082858622478e-05, "loss": 0.2663, "step": 2775 }, { "epoch": 2.5905915230554264, "grad_norm": 0.3810367662533655, "learning_rate": 1.9575349559813568e-05, "loss": 0.2742, "step": 2780 }, { "epoch": 2.5952491849091754, "grad_norm": 0.35081805562218144, "learning_rate": 1.951061626100466e-05, "loss": 0.2713, "step": 2785 }, { "epoch": 2.599906846762925, "grad_norm": 0.3224982413684642, "learning_rate": 1.9445882962195754e-05, "loss": 0.2693, "step": 2790 }, { "epoch": 2.6045645086166744, "grad_norm": 0.3274694504519037, "learning_rate": 1.9381149663386847e-05, "loss": 0.2753, "step": 2795 }, { "epoch": 2.609222170470424, "grad_norm": 0.3865515291265883, "learning_rate": 1.931641636457794e-05, "loss": 0.2622, "step": 2800 }, { "epoch": 2.6138798323241734, "grad_norm": 0.3429375756253068, "learning_rate": 1.9251683065769033e-05, "loss": 0.2712, "step": 2805 }, { "epoch": 2.6185374941779225, "grad_norm": 0.3306661997550271, "learning_rate": 1.9186949766960126e-05, "loss": 0.2662, "step": 2810 }, { "epoch": 2.623195156031672, "grad_norm": 0.35165756461551106, "learning_rate": 1.912221646815122e-05, "loss": 0.2607, "step": 2815 }, { "epoch": 2.6278528178854215, "grad_norm": 0.32196621465801767, "learning_rate": 1.9057483169342312e-05, "loss": 0.2724, "step": 2820 }, { "epoch": 2.632510479739171, "grad_norm": 0.3725873737799732, "learning_rate": 1.89927498705334e-05, "loss": 0.2706, "step": 2825 }, { "epoch": 2.6371681415929205, "grad_norm": 0.3427825066259748, "learning_rate": 1.8928016571724498e-05, "loss": 0.2716, "step": 2830 }, { "epoch": 2.64182580344667, "grad_norm": 0.4171231601441779, "learning_rate": 1.8863283272915587e-05, "loss": 0.2713, "step": 2835 }, { "epoch": 2.6464834653004194, "grad_norm": 0.3487729857212252, "learning_rate": 1.879854997410668e-05, "loss": 0.2695, "step": 2840 }, { "epoch": 2.6511411271541685, "grad_norm": 0.3859190065888482, "learning_rate": 1.8733816675297773e-05, "loss": 0.2746, "step": 2845 }, { "epoch": 2.655798789007918, "grad_norm": 0.3283524006620455, "learning_rate": 1.8669083376488866e-05, "loss": 0.2707, "step": 2850 }, { "epoch": 2.6604564508616675, "grad_norm": 0.33170418069108204, "learning_rate": 1.860435007767996e-05, "loss": 0.2635, "step": 2855 }, { "epoch": 2.665114112715417, "grad_norm": 0.3492758067432271, "learning_rate": 1.8539616778871052e-05, "loss": 0.2717, "step": 2860 }, { "epoch": 2.669771774569166, "grad_norm": 0.3178192667374189, "learning_rate": 1.8474883480062145e-05, "loss": 0.2669, "step": 2865 }, { "epoch": 2.6744294364229155, "grad_norm": 0.38868738172991585, "learning_rate": 1.8410150181253238e-05, "loss": 0.2682, "step": 2870 }, { "epoch": 2.679087098276665, "grad_norm": 0.3057581075840038, "learning_rate": 1.834541688244433e-05, "loss": 0.2633, "step": 2875 }, { "epoch": 2.6837447601304145, "grad_norm": 0.34220436772127666, "learning_rate": 1.828068358363542e-05, "loss": 0.2743, "step": 2880 }, { "epoch": 2.688402421984164, "grad_norm": 0.3469436711736002, "learning_rate": 1.8215950284826517e-05, "loss": 0.2727, "step": 2885 }, { "epoch": 2.6930600838379135, "grad_norm": 0.3207374562364515, "learning_rate": 1.8151216986017607e-05, "loss": 0.2657, "step": 2890 }, { "epoch": 2.697717745691663, "grad_norm": 0.3604681362240733, "learning_rate": 1.8086483687208703e-05, "loss": 0.2696, "step": 2895 }, { "epoch": 2.702375407545412, "grad_norm": 0.3380424714572946, "learning_rate": 1.8021750388399793e-05, "loss": 0.2584, "step": 2900 }, { "epoch": 2.7070330693991616, "grad_norm": 0.3270002298696279, "learning_rate": 1.7957017089590886e-05, "loss": 0.27, "step": 2905 }, { "epoch": 2.711690731252911, "grad_norm": 0.36891357837732275, "learning_rate": 1.789228379078198e-05, "loss": 0.2589, "step": 2910 }, { "epoch": 2.7163483931066605, "grad_norm": 0.32050195017536137, "learning_rate": 1.7827550491973072e-05, "loss": 0.271, "step": 2915 }, { "epoch": 2.72100605496041, "grad_norm": 0.33638286636504805, "learning_rate": 1.7762817193164165e-05, "loss": 0.2732, "step": 2920 }, { "epoch": 2.725663716814159, "grad_norm": 0.3690466212905594, "learning_rate": 1.7698083894355258e-05, "loss": 0.2727, "step": 2925 }, { "epoch": 2.7303213786679086, "grad_norm": 0.3452740904525744, "learning_rate": 1.763335059554635e-05, "loss": 0.2692, "step": 2930 }, { "epoch": 2.734979040521658, "grad_norm": 0.31852830078117506, "learning_rate": 1.756861729673744e-05, "loss": 0.2634, "step": 2935 }, { "epoch": 2.7396367023754076, "grad_norm": 0.3264355108200968, "learning_rate": 1.7503883997928537e-05, "loss": 0.2713, "step": 2940 }, { "epoch": 2.744294364229157, "grad_norm": 0.32765176221760894, "learning_rate": 1.7439150699119626e-05, "loss": 0.2685, "step": 2945 }, { "epoch": 2.7489520260829066, "grad_norm": 0.3501093017055509, "learning_rate": 1.7374417400310723e-05, "loss": 0.2639, "step": 2950 }, { "epoch": 2.753609687936656, "grad_norm": 0.34367252159834, "learning_rate": 1.7309684101501812e-05, "loss": 0.266, "step": 2955 }, { "epoch": 2.758267349790405, "grad_norm": 0.3415440481251798, "learning_rate": 1.7244950802692905e-05, "loss": 0.271, "step": 2960 }, { "epoch": 2.7629250116441546, "grad_norm": 0.342207928727645, "learning_rate": 1.7180217503883998e-05, "loss": 0.2658, "step": 2965 }, { "epoch": 2.767582673497904, "grad_norm": 0.33216708822314667, "learning_rate": 1.711548420507509e-05, "loss": 0.2694, "step": 2970 }, { "epoch": 2.7722403353516536, "grad_norm": 0.4116945011466418, "learning_rate": 1.7050750906266184e-05, "loss": 0.2721, "step": 2975 }, { "epoch": 2.7768979972054026, "grad_norm": 0.3948657663423283, "learning_rate": 1.6986017607457277e-05, "loss": 0.2665, "step": 2980 }, { "epoch": 2.781555659059152, "grad_norm": 0.31755044796948273, "learning_rate": 1.692128430864837e-05, "loss": 0.2732, "step": 2985 }, { "epoch": 2.7862133209129016, "grad_norm": 0.3285941995472897, "learning_rate": 1.6856551009839463e-05, "loss": 0.2667, "step": 2990 }, { "epoch": 2.790870982766651, "grad_norm": 0.3290561422271861, "learning_rate": 1.6791817711030556e-05, "loss": 0.2684, "step": 2995 }, { "epoch": 2.7955286446204006, "grad_norm": 0.4374751514092447, "learning_rate": 1.6727084412221646e-05, "loss": 0.2677, "step": 3000 }, { "epoch": 2.80018630647415, "grad_norm": 0.31620699209288716, "learning_rate": 1.6662351113412742e-05, "loss": 0.272, "step": 3005 }, { "epoch": 2.8048439683278996, "grad_norm": 0.30997456646659277, "learning_rate": 1.6597617814603832e-05, "loss": 0.264, "step": 3010 }, { "epoch": 2.8095016301816487, "grad_norm": 0.3347599919260059, "learning_rate": 1.6532884515794925e-05, "loss": 0.2609, "step": 3015 }, { "epoch": 2.814159292035398, "grad_norm": 0.36292075688066167, "learning_rate": 1.6468151216986018e-05, "loss": 0.2703, "step": 3020 }, { "epoch": 2.8188169538891477, "grad_norm": 0.3660837127423678, "learning_rate": 1.640341791817711e-05, "loss": 0.2709, "step": 3025 }, { "epoch": 2.823474615742897, "grad_norm": 0.3373354471318142, "learning_rate": 1.6338684619368204e-05, "loss": 0.2679, "step": 3030 }, { "epoch": 2.8281322775966466, "grad_norm": 0.3310868415858172, "learning_rate": 1.6273951320559297e-05, "loss": 0.2623, "step": 3035 }, { "epoch": 2.8327899394503957, "grad_norm": 0.3236026938182987, "learning_rate": 1.620921802175039e-05, "loss": 0.2741, "step": 3040 }, { "epoch": 2.837447601304145, "grad_norm": 0.3302490680899949, "learning_rate": 1.6144484722941483e-05, "loss": 0.2586, "step": 3045 }, { "epoch": 2.8421052631578947, "grad_norm": 0.34619024527156284, "learning_rate": 1.6079751424132576e-05, "loss": 0.2703, "step": 3050 }, { "epoch": 2.846762925011644, "grad_norm": 0.33052299233233606, "learning_rate": 1.6015018125323665e-05, "loss": 0.2726, "step": 3055 }, { "epoch": 2.8514205868653937, "grad_norm": 0.3443009362960016, "learning_rate": 1.595028482651476e-05, "loss": 0.2743, "step": 3060 }, { "epoch": 2.856078248719143, "grad_norm": 0.3584379680425449, "learning_rate": 1.588555152770585e-05, "loss": 0.2656, "step": 3065 }, { "epoch": 2.8607359105728927, "grad_norm": 0.3164302799926693, "learning_rate": 1.5820818228896944e-05, "loss": 0.261, "step": 3070 }, { "epoch": 2.8653935724266417, "grad_norm": 0.3345379562517162, "learning_rate": 1.5756084930088037e-05, "loss": 0.2675, "step": 3075 }, { "epoch": 2.870051234280391, "grad_norm": 0.37039543970040956, "learning_rate": 1.569135163127913e-05, "loss": 0.2588, "step": 3080 }, { "epoch": 2.8747088961341407, "grad_norm": 0.3434282028900521, "learning_rate": 1.5626618332470223e-05, "loss": 0.2708, "step": 3085 }, { "epoch": 2.87936655798789, "grad_norm": 0.32473298635801773, "learning_rate": 1.5561885033661316e-05, "loss": 0.269, "step": 3090 }, { "epoch": 2.8840242198416393, "grad_norm": 0.3465577429537333, "learning_rate": 1.549715173485241e-05, "loss": 0.2647, "step": 3095 }, { "epoch": 2.8886818816953888, "grad_norm": 0.3318217325086482, "learning_rate": 1.5432418436043502e-05, "loss": 0.2671, "step": 3100 }, { "epoch": 2.8933395435491382, "grad_norm": 0.34325262500113335, "learning_rate": 1.5367685137234595e-05, "loss": 0.267, "step": 3105 }, { "epoch": 2.8979972054028877, "grad_norm": 0.30818856490624186, "learning_rate": 1.5302951838425685e-05, "loss": 0.255, "step": 3110 }, { "epoch": 2.9026548672566372, "grad_norm": 0.3237348294971786, "learning_rate": 1.5238218539616781e-05, "loss": 0.2652, "step": 3115 }, { "epoch": 2.9073125291103867, "grad_norm": 0.36023176039724325, "learning_rate": 1.5173485240807872e-05, "loss": 0.2724, "step": 3120 }, { "epoch": 2.9119701909641362, "grad_norm": 0.3082915968841976, "learning_rate": 1.5108751941998964e-05, "loss": 0.266, "step": 3125 }, { "epoch": 2.9166278528178853, "grad_norm": 0.30865139372526773, "learning_rate": 1.5044018643190058e-05, "loss": 0.2615, "step": 3130 }, { "epoch": 2.9212855146716348, "grad_norm": 0.38198116800774295, "learning_rate": 1.497928534438115e-05, "loss": 0.2703, "step": 3135 }, { "epoch": 2.9259431765253843, "grad_norm": 0.38602662557799444, "learning_rate": 1.4914552045572244e-05, "loss": 0.2694, "step": 3140 }, { "epoch": 2.9306008383791338, "grad_norm": 0.3274967177094095, "learning_rate": 1.4849818746763336e-05, "loss": 0.2799, "step": 3145 }, { "epoch": 2.935258500232883, "grad_norm": 0.32047074803859527, "learning_rate": 1.4785085447954427e-05, "loss": 0.2617, "step": 3150 }, { "epoch": 2.9399161620866323, "grad_norm": 0.32048986173039784, "learning_rate": 1.4720352149145522e-05, "loss": 0.2674, "step": 3155 }, { "epoch": 2.944573823940382, "grad_norm": 0.37994252109032023, "learning_rate": 1.4655618850336613e-05, "loss": 0.264, "step": 3160 }, { "epoch": 2.9492314857941313, "grad_norm": 0.38105255889314954, "learning_rate": 1.4590885551527706e-05, "loss": 0.2725, "step": 3165 }, { "epoch": 2.953889147647881, "grad_norm": 0.34264963114596897, "learning_rate": 1.45261522527188e-05, "loss": 0.2667, "step": 3170 }, { "epoch": 2.9585468095016303, "grad_norm": 0.36988970284017114, "learning_rate": 1.4461418953909892e-05, "loss": 0.2671, "step": 3175 }, { "epoch": 2.96320447135538, "grad_norm": 0.2883222472185222, "learning_rate": 1.4396685655100987e-05, "loss": 0.2633, "step": 3180 }, { "epoch": 2.9678621332091293, "grad_norm": 0.32864829660790307, "learning_rate": 1.4331952356292078e-05, "loss": 0.261, "step": 3185 }, { "epoch": 2.9725197950628783, "grad_norm": 0.400388359068227, "learning_rate": 1.4267219057483169e-05, "loss": 0.2642, "step": 3190 }, { "epoch": 2.977177456916628, "grad_norm": 0.32200667756120394, "learning_rate": 1.4202485758674264e-05, "loss": 0.278, "step": 3195 }, { "epoch": 2.9818351187703773, "grad_norm": 0.3255855279207029, "learning_rate": 1.4137752459865355e-05, "loss": 0.2644, "step": 3200 }, { "epoch": 2.986492780624127, "grad_norm": 0.3645186903384584, "learning_rate": 1.4073019161056446e-05, "loss": 0.2648, "step": 3205 }, { "epoch": 2.991150442477876, "grad_norm": 0.3151052168713354, "learning_rate": 1.4008285862247541e-05, "loss": 0.255, "step": 3210 }, { "epoch": 2.9958081043316254, "grad_norm": 0.3279494282099784, "learning_rate": 1.3943552563438634e-05, "loss": 0.2581, "step": 3215 }, { "epoch": 3.0009315323707497, "grad_norm": 0.579768750984454, "learning_rate": 1.3878819264629725e-05, "loss": 0.3069, "step": 3220 }, { "epoch": 3.005589194224499, "grad_norm": 0.4796763868184913, "learning_rate": 1.381408596582082e-05, "loss": 0.1835, "step": 3225 }, { "epoch": 3.0102468560782487, "grad_norm": 0.35857924679397607, "learning_rate": 1.3749352667011911e-05, "loss": 0.1727, "step": 3230 }, { "epoch": 3.014904517931998, "grad_norm": 0.3799864476295532, "learning_rate": 1.3684619368203006e-05, "loss": 0.1748, "step": 3235 }, { "epoch": 3.0195621797857477, "grad_norm": 0.3429720038277402, "learning_rate": 1.3619886069394097e-05, "loss": 0.1726, "step": 3240 }, { "epoch": 3.0242198416394968, "grad_norm": 0.4113348108721569, "learning_rate": 1.3555152770585189e-05, "loss": 0.1757, "step": 3245 }, { "epoch": 3.0288775034932462, "grad_norm": 0.3285166534541784, "learning_rate": 1.3490419471776283e-05, "loss": 0.1735, "step": 3250 }, { "epoch": 3.0335351653469957, "grad_norm": 0.3045279760365921, "learning_rate": 1.3425686172967375e-05, "loss": 0.1708, "step": 3255 }, { "epoch": 3.0381928272007452, "grad_norm": 0.3203846366595548, "learning_rate": 1.3360952874158466e-05, "loss": 0.1813, "step": 3260 }, { "epoch": 3.0428504890544947, "grad_norm": 0.2979979294305198, "learning_rate": 1.329621957534956e-05, "loss": 0.1727, "step": 3265 }, { "epoch": 3.0475081509082442, "grad_norm": 0.33264241721051796, "learning_rate": 1.3231486276540654e-05, "loss": 0.1768, "step": 3270 }, { "epoch": 3.0521658127619933, "grad_norm": 0.3025629831106057, "learning_rate": 1.3166752977731747e-05, "loss": 0.1746, "step": 3275 }, { "epoch": 3.0568234746157428, "grad_norm": 0.32753713527558037, "learning_rate": 1.310201967892284e-05, "loss": 0.1737, "step": 3280 }, { "epoch": 3.0614811364694923, "grad_norm": 0.32455937475309715, "learning_rate": 1.303728638011393e-05, "loss": 0.1763, "step": 3285 }, { "epoch": 3.0661387983232418, "grad_norm": 0.3153987190016253, "learning_rate": 1.2972553081305026e-05, "loss": 0.1718, "step": 3290 }, { "epoch": 3.0707964601769913, "grad_norm": 0.3111275558308378, "learning_rate": 1.2907819782496117e-05, "loss": 0.1728, "step": 3295 }, { "epoch": 3.0754541220307408, "grad_norm": 0.28415569239467636, "learning_rate": 1.2843086483687208e-05, "loss": 0.1701, "step": 3300 }, { "epoch": 3.08011178388449, "grad_norm": 0.28942699925412285, "learning_rate": 1.2778353184878303e-05, "loss": 0.1712, "step": 3305 }, { "epoch": 3.0847694457382393, "grad_norm": 0.29950472642172987, "learning_rate": 1.2713619886069394e-05, "loss": 0.1706, "step": 3310 }, { "epoch": 3.089427107591989, "grad_norm": 0.3075983192535228, "learning_rate": 1.2648886587260485e-05, "loss": 0.1715, "step": 3315 }, { "epoch": 3.0940847694457383, "grad_norm": 0.3558460973388745, "learning_rate": 1.258415328845158e-05, "loss": 0.1713, "step": 3320 }, { "epoch": 3.098742431299488, "grad_norm": 0.30585284593259077, "learning_rate": 1.2519419989642673e-05, "loss": 0.1767, "step": 3325 }, { "epoch": 3.1034000931532373, "grad_norm": 0.3018802388087219, "learning_rate": 1.2454686690833766e-05, "loss": 0.1729, "step": 3330 }, { "epoch": 3.1080577550069863, "grad_norm": 0.30915157795328013, "learning_rate": 1.2389953392024859e-05, "loss": 0.1786, "step": 3335 }, { "epoch": 3.112715416860736, "grad_norm": 0.32428183056646653, "learning_rate": 1.2325220093215952e-05, "loss": 0.1737, "step": 3340 }, { "epoch": 3.1173730787144853, "grad_norm": 0.2951722659886565, "learning_rate": 1.2260486794407043e-05, "loss": 0.1767, "step": 3345 }, { "epoch": 3.122030740568235, "grad_norm": 0.34799084272744174, "learning_rate": 1.2195753495598136e-05, "loss": 0.1762, "step": 3350 }, { "epoch": 3.1266884024219843, "grad_norm": 0.30781538893195465, "learning_rate": 1.213102019678923e-05, "loss": 0.1741, "step": 3355 }, { "epoch": 3.131346064275734, "grad_norm": 0.31490858643297387, "learning_rate": 1.2066286897980322e-05, "loss": 0.1765, "step": 3360 }, { "epoch": 3.136003726129483, "grad_norm": 0.31188002164658873, "learning_rate": 1.2001553599171414e-05, "loss": 0.1806, "step": 3365 }, { "epoch": 3.1406613879832324, "grad_norm": 0.28756263456020675, "learning_rate": 1.1936820300362507e-05, "loss": 0.1742, "step": 3370 }, { "epoch": 3.145319049836982, "grad_norm": 0.3029889115590081, "learning_rate": 1.18720870015536e-05, "loss": 0.1688, "step": 3375 }, { "epoch": 3.1499767116907313, "grad_norm": 0.3136803226550989, "learning_rate": 1.1807353702744693e-05, "loss": 0.1733, "step": 3380 }, { "epoch": 3.154634373544481, "grad_norm": 0.30910921837238453, "learning_rate": 1.1742620403935786e-05, "loss": 0.1734, "step": 3385 }, { "epoch": 3.15929203539823, "grad_norm": 0.31212950065999173, "learning_rate": 1.1677887105126878e-05, "loss": 0.1746, "step": 3390 }, { "epoch": 3.1639496972519794, "grad_norm": 0.3137210903752138, "learning_rate": 1.1613153806317971e-05, "loss": 0.1669, "step": 3395 }, { "epoch": 3.168607359105729, "grad_norm": 0.31624637296297164, "learning_rate": 1.1548420507509063e-05, "loss": 0.1733, "step": 3400 }, { "epoch": 3.1732650209594784, "grad_norm": 0.3153585906290225, "learning_rate": 1.1483687208700156e-05, "loss": 0.1744, "step": 3405 }, { "epoch": 3.177922682813228, "grad_norm": 0.31043422855490393, "learning_rate": 1.1418953909891249e-05, "loss": 0.1722, "step": 3410 }, { "epoch": 3.1825803446669774, "grad_norm": 0.30354789161365536, "learning_rate": 1.1354220611082342e-05, "loss": 0.1778, "step": 3415 }, { "epoch": 3.1872380065207264, "grad_norm": 0.29774987966215494, "learning_rate": 1.1289487312273433e-05, "loss": 0.1756, "step": 3420 }, { "epoch": 3.191895668374476, "grad_norm": 0.31949445160115675, "learning_rate": 1.1224754013464526e-05, "loss": 0.1776, "step": 3425 }, { "epoch": 3.1965533302282254, "grad_norm": 0.3078085794690288, "learning_rate": 1.1160020714655619e-05, "loss": 0.1785, "step": 3430 }, { "epoch": 3.201210992081975, "grad_norm": 2.4368232467206474, "learning_rate": 1.1095287415846712e-05, "loss": 0.1772, "step": 3435 }, { "epoch": 3.2058686539357244, "grad_norm": 0.29567043816323485, "learning_rate": 1.1030554117037805e-05, "loss": 0.1761, "step": 3440 }, { "epoch": 3.2105263157894735, "grad_norm": 0.32416250096990257, "learning_rate": 1.0965820818228898e-05, "loss": 0.1728, "step": 3445 }, { "epoch": 3.215183977643223, "grad_norm": 0.30650681599059415, "learning_rate": 1.0901087519419991e-05, "loss": 0.1744, "step": 3450 }, { "epoch": 3.2198416394969724, "grad_norm": 0.34460910983706455, "learning_rate": 1.0836354220611084e-05, "loss": 0.177, "step": 3455 }, { "epoch": 3.224499301350722, "grad_norm": 0.30653054556565085, "learning_rate": 1.0771620921802175e-05, "loss": 0.1709, "step": 3460 }, { "epoch": 3.2291569632044714, "grad_norm": 0.32388645354684625, "learning_rate": 1.0706887622993268e-05, "loss": 0.1767, "step": 3465 }, { "epoch": 3.233814625058221, "grad_norm": 0.31287414377148204, "learning_rate": 1.0642154324184361e-05, "loss": 0.1734, "step": 3470 }, { "epoch": 3.2384722869119704, "grad_norm": 0.32654995179702995, "learning_rate": 1.0577421025375453e-05, "loss": 0.1741, "step": 3475 }, { "epoch": 3.2431299487657195, "grad_norm": 0.3028326261873557, "learning_rate": 1.0512687726566546e-05, "loss": 0.1767, "step": 3480 }, { "epoch": 3.247787610619469, "grad_norm": 0.3270460954968079, "learning_rate": 1.0447954427757638e-05, "loss": 0.1796, "step": 3485 }, { "epoch": 3.2524452724732185, "grad_norm": 0.28957915094574055, "learning_rate": 1.0383221128948731e-05, "loss": 0.1818, "step": 3490 }, { "epoch": 3.257102934326968, "grad_norm": 0.3200611856127191, "learning_rate": 1.0318487830139824e-05, "loss": 0.1797, "step": 3495 }, { "epoch": 3.2617605961807175, "grad_norm": 0.30675000763296856, "learning_rate": 1.0253754531330917e-05, "loss": 0.1807, "step": 3500 }, { "epoch": 3.2664182580344665, "grad_norm": 0.30607287859754584, "learning_rate": 1.018902123252201e-05, "loss": 0.1758, "step": 3505 }, { "epoch": 3.271075919888216, "grad_norm": 0.3181179706468029, "learning_rate": 1.0124287933713103e-05, "loss": 0.1811, "step": 3510 }, { "epoch": 3.2757335817419655, "grad_norm": 0.3044390850282215, "learning_rate": 1.0059554634904195e-05, "loss": 0.1751, "step": 3515 }, { "epoch": 3.280391243595715, "grad_norm": 0.3317366302362263, "learning_rate": 9.994821336095288e-06, "loss": 0.1754, "step": 3520 }, { "epoch": 3.2850489054494645, "grad_norm": 0.3357279786412925, "learning_rate": 9.93008803728638e-06, "loss": 0.1748, "step": 3525 }, { "epoch": 3.289706567303214, "grad_norm": 0.30685946197341135, "learning_rate": 9.865354738477474e-06, "loss": 0.1711, "step": 3530 }, { "epoch": 3.294364229156963, "grad_norm": 0.35258812405999906, "learning_rate": 9.800621439668565e-06, "loss": 0.1778, "step": 3535 }, { "epoch": 3.2990218910107125, "grad_norm": 0.3296296234991465, "learning_rate": 9.735888140859658e-06, "loss": 0.1779, "step": 3540 }, { "epoch": 3.303679552864462, "grad_norm": 0.30300324101520915, "learning_rate": 9.671154842050751e-06, "loss": 0.1678, "step": 3545 }, { "epoch": 3.3083372147182115, "grad_norm": 0.3015920704044858, "learning_rate": 9.606421543241844e-06, "loss": 0.1717, "step": 3550 }, { "epoch": 3.312994876571961, "grad_norm": 0.29556667829609184, "learning_rate": 9.541688244432937e-06, "loss": 0.1739, "step": 3555 }, { "epoch": 3.31765253842571, "grad_norm": 0.2854007077953996, "learning_rate": 9.47695494562403e-06, "loss": 0.176, "step": 3560 }, { "epoch": 3.3223102002794596, "grad_norm": 0.31564587605399097, "learning_rate": 9.412221646815123e-06, "loss": 0.1771, "step": 3565 }, { "epoch": 3.326967862133209, "grad_norm": 0.31355027597609025, "learning_rate": 9.347488348006214e-06, "loss": 0.1723, "step": 3570 }, { "epoch": 3.3316255239869585, "grad_norm": 0.3222652762051767, "learning_rate": 9.282755049197307e-06, "loss": 0.177, "step": 3575 }, { "epoch": 3.336283185840708, "grad_norm": 0.30180835321660604, "learning_rate": 9.2180217503884e-06, "loss": 0.1717, "step": 3580 }, { "epoch": 3.3409408476944575, "grad_norm": 0.33213232605773185, "learning_rate": 9.153288451579493e-06, "loss": 0.178, "step": 3585 }, { "epoch": 3.345598509548207, "grad_norm": 0.28663027212237047, "learning_rate": 9.088555152770584e-06, "loss": 0.1716, "step": 3590 }, { "epoch": 3.350256171401956, "grad_norm": 0.2965020862542506, "learning_rate": 9.023821853961677e-06, "loss": 0.1709, "step": 3595 }, { "epoch": 3.3549138332557056, "grad_norm": 0.29277792960100496, "learning_rate": 8.95908855515277e-06, "loss": 0.1716, "step": 3600 }, { "epoch": 3.359571495109455, "grad_norm": 0.30084350774681656, "learning_rate": 8.894355256343863e-06, "loss": 0.1789, "step": 3605 }, { "epoch": 3.3642291569632046, "grad_norm": 0.2816028504726463, "learning_rate": 8.829621957534956e-06, "loss": 0.1706, "step": 3610 }, { "epoch": 3.368886818816954, "grad_norm": 0.387944582672212, "learning_rate": 8.76488865872605e-06, "loss": 0.1733, "step": 3615 }, { "epoch": 3.373544480670703, "grad_norm": 0.2994759040645287, "learning_rate": 8.700155359917142e-06, "loss": 0.1773, "step": 3620 }, { "epoch": 3.3782021425244526, "grad_norm": 0.292929541890169, "learning_rate": 8.635422061108235e-06, "loss": 0.1772, "step": 3625 }, { "epoch": 3.382859804378202, "grad_norm": 0.3226070207681405, "learning_rate": 8.570688762299327e-06, "loss": 0.1788, "step": 3630 }, { "epoch": 3.3875174662319516, "grad_norm": 0.30497470415473654, "learning_rate": 8.50595546349042e-06, "loss": 0.1733, "step": 3635 }, { "epoch": 3.392175128085701, "grad_norm": 0.3076683408175822, "learning_rate": 8.441222164681513e-06, "loss": 0.172, "step": 3640 }, { "epoch": 3.3968327899394506, "grad_norm": 0.2996326646039861, "learning_rate": 8.376488865872606e-06, "loss": 0.1735, "step": 3645 }, { "epoch": 3.4014904517931996, "grad_norm": 0.3128206381647326, "learning_rate": 8.311755567063697e-06, "loss": 0.1763, "step": 3650 }, { "epoch": 3.406148113646949, "grad_norm": 0.29114397160329614, "learning_rate": 8.24702226825479e-06, "loss": 0.1711, "step": 3655 }, { "epoch": 3.4108057755006986, "grad_norm": 0.3211500322465875, "learning_rate": 8.182288969445883e-06, "loss": 0.1706, "step": 3660 }, { "epoch": 3.415463437354448, "grad_norm": 0.3125511441562104, "learning_rate": 8.117555670636976e-06, "loss": 0.1743, "step": 3665 }, { "epoch": 3.4201210992081976, "grad_norm": 0.301780010938843, "learning_rate": 8.052822371828069e-06, "loss": 0.1714, "step": 3670 }, { "epoch": 3.4247787610619467, "grad_norm": 0.31603131789809963, "learning_rate": 7.988089073019162e-06, "loss": 0.1722, "step": 3675 }, { "epoch": 3.429436422915696, "grad_norm": 0.32876490078238074, "learning_rate": 7.923355774210255e-06, "loss": 0.1739, "step": 3680 }, { "epoch": 3.4340940847694457, "grad_norm": 0.29136084262502027, "learning_rate": 7.858622475401346e-06, "loss": 0.174, "step": 3685 }, { "epoch": 3.438751746623195, "grad_norm": 0.28115336273608404, "learning_rate": 7.793889176592439e-06, "loss": 0.1772, "step": 3690 }, { "epoch": 3.4434094084769447, "grad_norm": 0.3016008777136775, "learning_rate": 7.729155877783532e-06, "loss": 0.1735, "step": 3695 }, { "epoch": 3.448067070330694, "grad_norm": 0.30576220048352454, "learning_rate": 7.664422578974625e-06, "loss": 0.1772, "step": 3700 }, { "epoch": 3.4527247321844436, "grad_norm": 0.2861779945613481, "learning_rate": 7.599689280165717e-06, "loss": 0.1767, "step": 3705 }, { "epoch": 3.4573823940381927, "grad_norm": 0.28689934768522896, "learning_rate": 7.53495598135681e-06, "loss": 0.1735, "step": 3710 }, { "epoch": 3.462040055891942, "grad_norm": 0.29411493912614256, "learning_rate": 7.470222682547903e-06, "loss": 0.1756, "step": 3715 }, { "epoch": 3.4666977177456917, "grad_norm": 0.27708646086614636, "learning_rate": 7.405489383738996e-06, "loss": 0.1743, "step": 3720 }, { "epoch": 3.471355379599441, "grad_norm": 0.28320927258827877, "learning_rate": 7.340756084930088e-06, "loss": 0.1784, "step": 3725 }, { "epoch": 3.4760130414531907, "grad_norm": 0.31060819324684963, "learning_rate": 7.276022786121181e-06, "loss": 0.1684, "step": 3730 }, { "epoch": 3.4806707033069397, "grad_norm": 0.30830969919333406, "learning_rate": 7.211289487312274e-06, "loss": 0.1761, "step": 3735 }, { "epoch": 3.4853283651606892, "grad_norm": 0.2798785290276168, "learning_rate": 7.146556188503367e-06, "loss": 0.1711, "step": 3740 }, { "epoch": 3.4899860270144387, "grad_norm": 0.3170799788613841, "learning_rate": 7.081822889694459e-06, "loss": 0.1766, "step": 3745 }, { "epoch": 3.494643688868188, "grad_norm": 0.31221626603777886, "learning_rate": 7.017089590885552e-06, "loss": 0.1722, "step": 3750 }, { "epoch": 3.4993013507219377, "grad_norm": 0.2798075278234149, "learning_rate": 6.952356292076645e-06, "loss": 0.1752, "step": 3755 }, { "epoch": 3.503959012575687, "grad_norm": 0.28554402132422674, "learning_rate": 6.887622993267737e-06, "loss": 0.1708, "step": 3760 }, { "epoch": 3.5086166744294367, "grad_norm": 0.2832883275992911, "learning_rate": 6.82288969445883e-06, "loss": 0.1718, "step": 3765 }, { "epoch": 3.5132743362831858, "grad_norm": 0.28502816368405115, "learning_rate": 6.758156395649923e-06, "loss": 0.1717, "step": 3770 }, { "epoch": 3.5179319981369352, "grad_norm": 0.28393413290837494, "learning_rate": 6.693423096841016e-06, "loss": 0.1669, "step": 3775 }, { "epoch": 3.5225896599906847, "grad_norm": 0.29336395686580125, "learning_rate": 6.628689798032108e-06, "loss": 0.1706, "step": 3780 }, { "epoch": 3.5272473218444342, "grad_norm": 0.30165412846618006, "learning_rate": 6.563956499223201e-06, "loss": 0.1746, "step": 3785 }, { "epoch": 3.5319049836981833, "grad_norm": 0.30465706318639985, "learning_rate": 6.499223200414294e-06, "loss": 0.1732, "step": 3790 }, { "epoch": 3.536562645551933, "grad_norm": 0.3026352865090654, "learning_rate": 6.434489901605387e-06, "loss": 0.1726, "step": 3795 }, { "epoch": 3.5412203074056823, "grad_norm": 0.2948459285457107, "learning_rate": 6.369756602796478e-06, "loss": 0.176, "step": 3800 }, { "epoch": 3.5458779692594318, "grad_norm": 0.27992123765068, "learning_rate": 6.305023303987571e-06, "loss": 0.1755, "step": 3805 }, { "epoch": 3.5505356311131813, "grad_norm": 0.3035848864322718, "learning_rate": 6.240290005178664e-06, "loss": 0.1723, "step": 3810 }, { "epoch": 3.5551932929669308, "grad_norm": 0.2837563693171141, "learning_rate": 6.175556706369757e-06, "loss": 0.1774, "step": 3815 }, { "epoch": 3.5598509548206803, "grad_norm": 0.3039237837342328, "learning_rate": 6.11082340756085e-06, "loss": 0.1701, "step": 3820 }, { "epoch": 3.5645086166744293, "grad_norm": 0.28929404989213126, "learning_rate": 6.046090108751942e-06, "loss": 0.1728, "step": 3825 }, { "epoch": 3.569166278528179, "grad_norm": 0.2984711574600852, "learning_rate": 5.981356809943035e-06, "loss": 0.1759, "step": 3830 }, { "epoch": 3.5738239403819283, "grad_norm": 0.3040262231367376, "learning_rate": 5.916623511134127e-06, "loss": 0.1734, "step": 3835 }, { "epoch": 3.578481602235678, "grad_norm": 0.2973375523986782, "learning_rate": 5.85189021232522e-06, "loss": 0.1704, "step": 3840 }, { "epoch": 3.583139264089427, "grad_norm": 0.31157603427857145, "learning_rate": 5.787156913516313e-06, "loss": 0.1706, "step": 3845 }, { "epoch": 3.5877969259431763, "grad_norm": 0.3415882655555158, "learning_rate": 5.7224236147074054e-06, "loss": 0.1767, "step": 3850 }, { "epoch": 3.592454587796926, "grad_norm": 0.3183978437062741, "learning_rate": 5.6576903158984984e-06, "loss": 0.1725, "step": 3855 }, { "epoch": 3.5971122496506753, "grad_norm": 0.289337183993094, "learning_rate": 5.5929570170895906e-06, "loss": 0.1736, "step": 3860 }, { "epoch": 3.601769911504425, "grad_norm": 0.29641484144502483, "learning_rate": 5.5282237182806836e-06, "loss": 0.1757, "step": 3865 }, { "epoch": 3.6064275733581743, "grad_norm": 0.28754251461344277, "learning_rate": 5.4634904194717765e-06, "loss": 0.1753, "step": 3870 }, { "epoch": 3.611085235211924, "grad_norm": 0.29826146361905365, "learning_rate": 5.3987571206628695e-06, "loss": 0.1708, "step": 3875 }, { "epoch": 3.615742897065673, "grad_norm": 0.28775692745350007, "learning_rate": 5.334023821853962e-06, "loss": 0.1712, "step": 3880 }, { "epoch": 3.6204005589194224, "grad_norm": 0.28068703783262394, "learning_rate": 5.269290523045055e-06, "loss": 0.1699, "step": 3885 }, { "epoch": 3.625058220773172, "grad_norm": 0.2765990400297382, "learning_rate": 5.204557224236147e-06, "loss": 0.1709, "step": 3890 }, { "epoch": 3.6297158826269214, "grad_norm": 0.2760094583762265, "learning_rate": 5.139823925427241e-06, "loss": 0.1682, "step": 3895 }, { "epoch": 3.634373544480671, "grad_norm": 0.3032429789967516, "learning_rate": 5.075090626618333e-06, "loss": 0.1691, "step": 3900 }, { "epoch": 3.63903120633442, "grad_norm": 0.28907933803658026, "learning_rate": 5.010357327809426e-06, "loss": 0.1707, "step": 3905 }, { "epoch": 3.6436888681881694, "grad_norm": 0.2990052618425826, "learning_rate": 4.945624029000518e-06, "loss": 0.1724, "step": 3910 }, { "epoch": 3.648346530041919, "grad_norm": 0.31769597099353963, "learning_rate": 4.880890730191611e-06, "loss": 0.1654, "step": 3915 }, { "epoch": 3.6530041918956684, "grad_norm": 0.32591828276849877, "learning_rate": 4.816157431382704e-06, "loss": 0.1663, "step": 3920 }, { "epoch": 3.657661853749418, "grad_norm": 0.2892595641864456, "learning_rate": 4.751424132573796e-06, "loss": 0.167, "step": 3925 }, { "epoch": 3.6623195156031674, "grad_norm": 0.28217409965695506, "learning_rate": 4.686690833764889e-06, "loss": 0.1732, "step": 3930 }, { "epoch": 3.666977177456917, "grad_norm": 0.2719891548452871, "learning_rate": 4.621957534955981e-06, "loss": 0.1707, "step": 3935 }, { "epoch": 3.671634839310666, "grad_norm": 0.29073933828517257, "learning_rate": 4.557224236147074e-06, "loss": 0.1731, "step": 3940 }, { "epoch": 3.6762925011644154, "grad_norm": 0.28374171071689347, "learning_rate": 4.492490937338166e-06, "loss": 0.1682, "step": 3945 }, { "epoch": 3.680950163018165, "grad_norm": 0.2734188405912673, "learning_rate": 4.42775763852926e-06, "loss": 0.1736, "step": 3950 }, { "epoch": 3.6856078248719144, "grad_norm": 0.30990662115273976, "learning_rate": 4.363024339720352e-06, "loss": 0.1709, "step": 3955 }, { "epoch": 3.6902654867256635, "grad_norm": 0.2989037091544917, "learning_rate": 4.298291040911445e-06, "loss": 0.1714, "step": 3960 }, { "epoch": 3.694923148579413, "grad_norm": 0.2834331170086405, "learning_rate": 4.233557742102537e-06, "loss": 0.1685, "step": 3965 }, { "epoch": 3.6995808104331624, "grad_norm": 0.2841272619989864, "learning_rate": 4.16882444329363e-06, "loss": 0.1729, "step": 3970 }, { "epoch": 3.704238472286912, "grad_norm": 0.2870522579541302, "learning_rate": 4.104091144484723e-06, "loss": 0.1643, "step": 3975 }, { "epoch": 3.7088961341406614, "grad_norm": 0.28915510071008577, "learning_rate": 4.039357845675816e-06, "loss": 0.1784, "step": 3980 }, { "epoch": 3.713553795994411, "grad_norm": 0.2668867542791596, "learning_rate": 3.9746245468669085e-06, "loss": 0.1684, "step": 3985 }, { "epoch": 3.7182114578481604, "grad_norm": 0.2867219121506309, "learning_rate": 3.9098912480580015e-06, "loss": 0.1728, "step": 3990 }, { "epoch": 3.7228691197019095, "grad_norm": 0.2888053843886937, "learning_rate": 3.845157949249094e-06, "loss": 0.1731, "step": 3995 }, { "epoch": 3.727526781555659, "grad_norm": 0.28935130945950716, "learning_rate": 3.780424650440187e-06, "loss": 0.1703, "step": 4000 }, { "epoch": 3.7321844434094085, "grad_norm": 0.28865426988532034, "learning_rate": 3.715691351631279e-06, "loss": 0.1728, "step": 4005 }, { "epoch": 3.736842105263158, "grad_norm": 0.2887069134197156, "learning_rate": 3.650958052822372e-06, "loss": 0.1701, "step": 4010 }, { "epoch": 3.7414997671169075, "grad_norm": 0.29397281719246715, "learning_rate": 3.5862247540134647e-06, "loss": 0.1717, "step": 4015 }, { "epoch": 3.7461574289706565, "grad_norm": 0.28569249426014337, "learning_rate": 3.521491455204557e-06, "loss": 0.1725, "step": 4020 }, { "epoch": 3.750815090824406, "grad_norm": 0.29334341391919566, "learning_rate": 3.4567581563956503e-06, "loss": 0.1711, "step": 4025 }, { "epoch": 3.7554727526781555, "grad_norm": 1.4163547339786675, "learning_rate": 3.3920248575867424e-06, "loss": 0.1872, "step": 4030 }, { "epoch": 3.760130414531905, "grad_norm": 0.3005457540568029, "learning_rate": 3.3272915587778354e-06, "loss": 0.1698, "step": 4035 }, { "epoch": 3.7647880763856545, "grad_norm": 0.2824657486918758, "learning_rate": 3.262558259968928e-06, "loss": 0.1725, "step": 4040 }, { "epoch": 3.769445738239404, "grad_norm": 0.27660773319517856, "learning_rate": 3.197824961160021e-06, "loss": 0.1688, "step": 4045 }, { "epoch": 3.7741034000931535, "grad_norm": 0.2902053769744512, "learning_rate": 3.1330916623511135e-06, "loss": 0.175, "step": 4050 }, { "epoch": 3.7787610619469025, "grad_norm": 0.2875832918676906, "learning_rate": 3.0683583635422065e-06, "loss": 0.1752, "step": 4055 }, { "epoch": 3.783418723800652, "grad_norm": 0.2673410357764, "learning_rate": 3.003625064733299e-06, "loss": 0.1626, "step": 4060 }, { "epoch": 3.7880763856544015, "grad_norm": 0.2691781402984375, "learning_rate": 2.9388917659243916e-06, "loss": 0.1688, "step": 4065 }, { "epoch": 3.792734047508151, "grad_norm": 0.29243005854125637, "learning_rate": 2.874158467115484e-06, "loss": 0.1718, "step": 4070 }, { "epoch": 3.7973917093619, "grad_norm": 0.2667388668711131, "learning_rate": 2.8094251683065768e-06, "loss": 0.1648, "step": 4075 }, { "epoch": 3.8020493712156496, "grad_norm": 1.2942680861453115, "learning_rate": 2.7446918694976698e-06, "loss": 0.1733, "step": 4080 }, { "epoch": 3.806707033069399, "grad_norm": 0.29328650433167064, "learning_rate": 2.6799585706887623e-06, "loss": 0.1683, "step": 4085 }, { "epoch": 3.8113646949231486, "grad_norm": 0.2888867070726165, "learning_rate": 2.615225271879855e-06, "loss": 0.17, "step": 4090 }, { "epoch": 3.816022356776898, "grad_norm": 0.294101693099246, "learning_rate": 2.550491973070948e-06, "loss": 0.1679, "step": 4095 }, { "epoch": 3.8206800186306475, "grad_norm": 0.2750531699760472, "learning_rate": 2.4857586742620404e-06, "loss": 0.1709, "step": 4100 }, { "epoch": 3.825337680484397, "grad_norm": 0.296992571095876, "learning_rate": 2.421025375453133e-06, "loss": 0.1698, "step": 4105 }, { "epoch": 3.829995342338146, "grad_norm": 0.2896431213130989, "learning_rate": 2.356292076644226e-06, "loss": 0.1729, "step": 4110 }, { "epoch": 3.8346530041918956, "grad_norm": 0.277880433978223, "learning_rate": 2.2915587778353186e-06, "loss": 0.1721, "step": 4115 }, { "epoch": 3.839310666045645, "grad_norm": 0.27037721639455975, "learning_rate": 2.2268254790264115e-06, "loss": 0.1683, "step": 4120 }, { "epoch": 3.8439683278993946, "grad_norm": 0.2743440933282645, "learning_rate": 2.162092180217504e-06, "loss": 0.1688, "step": 4125 }, { "epoch": 3.848625989753144, "grad_norm": 0.2872863661695779, "learning_rate": 2.0973588814085967e-06, "loss": 0.1764, "step": 4130 }, { "epoch": 3.853283651606893, "grad_norm": 0.3140239446150683, "learning_rate": 2.0326255825996897e-06, "loss": 0.1735, "step": 4135 }, { "epoch": 3.8579413134606426, "grad_norm": 0.284225342505323, "learning_rate": 1.9678922837907822e-06, "loss": 0.1705, "step": 4140 }, { "epoch": 3.862598975314392, "grad_norm": 0.27234653440642975, "learning_rate": 1.903158984981875e-06, "loss": 0.1663, "step": 4145 }, { "epoch": 3.8672566371681416, "grad_norm": 0.2967177556172732, "learning_rate": 1.8384256861729676e-06, "loss": 0.1694, "step": 4150 }, { "epoch": 3.871914299021891, "grad_norm": 0.28364377343036595, "learning_rate": 1.77369238736406e-06, "loss": 0.1761, "step": 4155 }, { "epoch": 3.8765719608756406, "grad_norm": 0.2735623931750372, "learning_rate": 1.7089590885551527e-06, "loss": 0.1731, "step": 4160 }, { "epoch": 3.88122962272939, "grad_norm": 0.27664942457264796, "learning_rate": 1.6442257897462455e-06, "loss": 0.1696, "step": 4165 }, { "epoch": 3.885887284583139, "grad_norm": 0.2765648318293413, "learning_rate": 1.579492490937338e-06, "loss": 0.1725, "step": 4170 }, { "epoch": 3.8905449464368886, "grad_norm": 0.2776110808649495, "learning_rate": 1.514759192128431e-06, "loss": 0.1732, "step": 4175 }, { "epoch": 3.895202608290638, "grad_norm": 0.2820374186278737, "learning_rate": 1.4500258933195236e-06, "loss": 0.1702, "step": 4180 }, { "epoch": 3.8998602701443876, "grad_norm": 0.28982287110326627, "learning_rate": 1.3852925945106164e-06, "loss": 0.1665, "step": 4185 }, { "epoch": 3.9045179319981367, "grad_norm": 0.2820981913699354, "learning_rate": 1.320559295701709e-06, "loss": 0.1722, "step": 4190 }, { "epoch": 3.909175593851886, "grad_norm": 0.2840990416734394, "learning_rate": 1.2558259968928017e-06, "loss": 0.1683, "step": 4195 }, { "epoch": 3.9138332557056357, "grad_norm": 0.2792498470002113, "learning_rate": 1.1910926980838945e-06, "loss": 0.1697, "step": 4200 }, { "epoch": 3.918490917559385, "grad_norm": 0.31147521884433776, "learning_rate": 1.126359399274987e-06, "loss": 0.1669, "step": 4205 }, { "epoch": 3.9231485794131347, "grad_norm": 0.2719076704963801, "learning_rate": 1.0616261004660798e-06, "loss": 0.1665, "step": 4210 }, { "epoch": 3.927806241266884, "grad_norm": 0.2732241041868572, "learning_rate": 9.968928016571726e-07, "loss": 0.1661, "step": 4215 }, { "epoch": 3.9324639031206337, "grad_norm": 0.2710476294954427, "learning_rate": 9.321595028482653e-07, "loss": 0.1675, "step": 4220 }, { "epoch": 3.9371215649743827, "grad_norm": 0.279695652051787, "learning_rate": 8.674262040393578e-07, "loss": 0.171, "step": 4225 }, { "epoch": 3.941779226828132, "grad_norm": 0.2733394881422974, "learning_rate": 8.026929052304505e-07, "loss": 0.1691, "step": 4230 }, { "epoch": 3.9464368886818817, "grad_norm": 0.3390742328886147, "learning_rate": 7.379596064215433e-07, "loss": 0.1682, "step": 4235 }, { "epoch": 3.951094550535631, "grad_norm": 0.2719967087219711, "learning_rate": 6.73226307612636e-07, "loss": 0.1685, "step": 4240 }, { "epoch": 3.9557522123893807, "grad_norm": 0.27395520460203887, "learning_rate": 6.084930088037286e-07, "loss": 0.1651, "step": 4245 }, { "epoch": 3.9604098742431297, "grad_norm": 0.2633649573682904, "learning_rate": 5.437597099948214e-07, "loss": 0.1712, "step": 4250 }, { "epoch": 3.9650675360968792, "grad_norm": 0.2890329758428071, "learning_rate": 4.790264111859141e-07, "loss": 0.1719, "step": 4255 }, { "epoch": 3.9697251979506287, "grad_norm": 0.2828979970332904, "learning_rate": 4.1429311237700674e-07, "loss": 0.1704, "step": 4260 }, { "epoch": 3.974382859804378, "grad_norm": 0.2958354433244782, "learning_rate": 3.495598135680994e-07, "loss": 0.1734, "step": 4265 }, { "epoch": 3.9790405216581277, "grad_norm": 0.2770822846104833, "learning_rate": 2.8482651475919213e-07, "loss": 0.1678, "step": 4270 }, { "epoch": 3.983698183511877, "grad_norm": 0.29794882547389606, "learning_rate": 2.200932159502848e-07, "loss": 0.1709, "step": 4275 }, { "epoch": 3.9883558453656267, "grad_norm": 0.28071045232219255, "learning_rate": 1.5535991714137753e-07, "loss": 0.1674, "step": 4280 }, { "epoch": 3.9930135072193758, "grad_norm": 0.6686126513435188, "learning_rate": 9.062661833247022e-08, "loss": 0.1698, "step": 4285 }, { "epoch": 3.9976711690731253, "grad_norm": 0.2838758812817945, "learning_rate": 2.589331952356292e-08, "loss": 0.1668, "step": 4290 }, { "epoch": 3.999534233814625, "step": 4292, "total_flos": 3.674855338697294e+18, "train_loss": 0.11008119197060655, "train_runtime": 63774.8301, "train_samples_per_second": 1.077, "train_steps_per_second": 0.067 } ], "logging_steps": 5, "max_steps": 4292, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.674855338697294e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }