{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 151450, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01650709805216243, "grad_norm": 6.768320083618164, "learning_rate": 6.986e-05, "loss": 3.916618408203125, "step": 500 }, { "epoch": 0.03301419610432486, "grad_norm": 6.386398792266846, "learning_rate": 6.976859887379927e-05, "loss": 2.682754638671875, "step": 1000 }, { "epoch": 0.04952129415648729, "grad_norm": 5.085998058319092, "learning_rate": 6.953673401788671e-05, "loss": 2.58737890625, "step": 1500 }, { "epoch": 0.06602839220864971, "grad_norm": 6.801213264465332, "learning_rate": 6.930486916197416e-05, "loss": 2.503279541015625, "step": 2000 }, { "epoch": 0.08253549026081215, "grad_norm": 8.394940376281738, "learning_rate": 6.90730043060616e-05, "loss": 2.269076171875, "step": 2500 }, { "epoch": 0.09904258831297458, "grad_norm": 9.456356048583984, "learning_rate": 6.884113945014905e-05, "loss": 2.202457275390625, "step": 3000 }, { "epoch": 0.115549686365137, "grad_norm": 10.7513427734375, "learning_rate": 6.860927459423649e-05, "loss": 2.08675927734375, "step": 3500 }, { "epoch": 0.13205678441729943, "grad_norm": 10.78842830657959, "learning_rate": 6.837740973832394e-05, "loss": 2.0077203369140624, "step": 4000 }, { "epoch": 0.14856388246946187, "grad_norm": 6.0438008308410645, "learning_rate": 6.814554488241139e-05, "loss": 1.9853677978515625, "step": 4500 }, { "epoch": 0.1650709805216243, "grad_norm": 10.89460277557373, "learning_rate": 6.791368002649884e-05, "loss": 1.929447998046875, "step": 5000 }, { "epoch": 0.18157807857378672, "grad_norm": 9.953587532043457, "learning_rate": 6.768181517058628e-05, "loss": 1.8683162841796874, "step": 5500 }, { "epoch": 0.19808517662594916, "grad_norm": 9.359884262084961, "learning_rate": 6.744995031467373e-05, "loss": 1.8459879150390626, "step": 6000 }, { "epoch": 0.2145922746781116, "grad_norm": 9.435839653015137, "learning_rate": 6.721808545876117e-05, "loss": 1.8140406494140624, "step": 6500 }, { "epoch": 0.231099372730274, "grad_norm": 10.773674964904785, "learning_rate": 6.698622060284862e-05, "loss": 1.7336441650390626, "step": 7000 }, { "epoch": 0.24760647078243644, "grad_norm": 5.851812362670898, "learning_rate": 6.675435574693606e-05, "loss": 1.6996578369140625, "step": 7500 }, { "epoch": 0.26411356883459886, "grad_norm": 7.684477806091309, "learning_rate": 6.65224908910235e-05, "loss": 1.6819129638671875, "step": 8000 }, { "epoch": 0.2806206668867613, "grad_norm": 10.268860816955566, "learning_rate": 6.629062603511096e-05, "loss": 1.6636182861328126, "step": 8500 }, { "epoch": 0.29712776493892373, "grad_norm": 10.829591751098633, "learning_rate": 6.60587611791984e-05, "loss": 1.638398681640625, "step": 9000 }, { "epoch": 0.31363486299108617, "grad_norm": 12.45463752746582, "learning_rate": 6.582689632328585e-05, "loss": 1.59802294921875, "step": 9500 }, { "epoch": 0.3301419610432486, "grad_norm": 8.353343963623047, "learning_rate": 6.55950314673733e-05, "loss": 1.58032958984375, "step": 10000 }, { "epoch": 0.34664905909541105, "grad_norm": 10.791740417480469, "learning_rate": 6.536316661146074e-05, "loss": 1.54497607421875, "step": 10500 }, { "epoch": 0.36315615714757343, "grad_norm": 11.632283210754395, "learning_rate": 6.513130175554819e-05, "loss": 1.54123291015625, "step": 11000 }, { "epoch": 0.37966325519973587, "grad_norm": 11.200041770935059, "learning_rate": 6.489943689963564e-05, "loss": 1.4861546630859375, "step": 11500 }, { "epoch": 0.3961703532518983, "grad_norm": 7.682310581207275, "learning_rate": 6.466757204372308e-05, "loss": 1.468400390625, "step": 12000 }, { "epoch": 0.41267745130406075, "grad_norm": 9.859110832214355, "learning_rate": 6.443570718781052e-05, "loss": 1.466673583984375, "step": 12500 }, { "epoch": 0.4291845493562232, "grad_norm": 11.913779258728027, "learning_rate": 6.420384233189798e-05, "loss": 1.43177294921875, "step": 13000 }, { "epoch": 0.4456916474083856, "grad_norm": 11.289583206176758, "learning_rate": 6.397197747598542e-05, "loss": 1.4270911865234375, "step": 13500 }, { "epoch": 0.462198745460548, "grad_norm": 13.098183631896973, "learning_rate": 6.374011262007286e-05, "loss": 1.4143895263671875, "step": 14000 }, { "epoch": 0.47870584351271045, "grad_norm": 14.500001907348633, "learning_rate": 6.350824776416032e-05, "loss": 1.37860498046875, "step": 14500 }, { "epoch": 0.4952129415648729, "grad_norm": 12.09792709350586, "learning_rate": 6.327638290824776e-05, "loss": 1.3556072998046875, "step": 15000 }, { "epoch": 0.5117200396170353, "grad_norm": 11.116087913513184, "learning_rate": 6.30445180523352e-05, "loss": 1.3589134521484374, "step": 15500 }, { "epoch": 0.5282271376691977, "grad_norm": 9.960223197937012, "learning_rate": 6.281265319642264e-05, "loss": 1.35077294921875, "step": 16000 }, { "epoch": 0.5447342357213601, "grad_norm": 9.27863597869873, "learning_rate": 6.25807883405101e-05, "loss": 1.311365478515625, "step": 16500 }, { "epoch": 0.5612413337735226, "grad_norm": 13.592756271362305, "learning_rate": 6.234892348459754e-05, "loss": 1.2956400146484375, "step": 17000 }, { "epoch": 0.577748431825685, "grad_norm": 12.149269104003906, "learning_rate": 6.211705862868498e-05, "loss": 1.284468017578125, "step": 17500 }, { "epoch": 0.5942555298778475, "grad_norm": 9.661849975585938, "learning_rate": 6.188519377277244e-05, "loss": 1.22178564453125, "step": 18000 }, { "epoch": 0.6107626279300099, "grad_norm": 12.476922035217285, "learning_rate": 6.165332891685988e-05, "loss": 1.2305272216796874, "step": 18500 }, { "epoch": 0.6272697259821723, "grad_norm": 12.08813190460205, "learning_rate": 6.142146406094732e-05, "loss": 1.237330322265625, "step": 19000 }, { "epoch": 0.6437768240343348, "grad_norm": 11.65064811706543, "learning_rate": 6.118959920503478e-05, "loss": 1.2016610107421875, "step": 19500 }, { "epoch": 0.6602839220864972, "grad_norm": 6.9960408210754395, "learning_rate": 6.095773434912222e-05, "loss": 1.2316639404296874, "step": 20000 }, { "epoch": 0.6767910201386597, "grad_norm": 11.649785995483398, "learning_rate": 6.072586949320966e-05, "loss": 1.2090703125, "step": 20500 }, { "epoch": 0.6932981181908221, "grad_norm": 12.47722053527832, "learning_rate": 6.049400463729711e-05, "loss": 1.212951171875, "step": 21000 }, { "epoch": 0.7098052162429845, "grad_norm": 11.645233154296875, "learning_rate": 6.026213978138456e-05, "loss": 1.1909053955078126, "step": 21500 }, { "epoch": 0.7263123142951469, "grad_norm": 9.064743041992188, "learning_rate": 6.003027492547201e-05, "loss": 1.192686279296875, "step": 22000 }, { "epoch": 0.7428194123473093, "grad_norm": 14.388778686523438, "learning_rate": 5.979841006955945e-05, "loss": 1.151447509765625, "step": 22500 }, { "epoch": 0.7593265103994717, "grad_norm": 16.274160385131836, "learning_rate": 5.95665452136469e-05, "loss": 1.103416259765625, "step": 23000 }, { "epoch": 0.7758336084516342, "grad_norm": 7.260326862335205, "learning_rate": 5.933468035773434e-05, "loss": 1.12520703125, "step": 23500 }, { "epoch": 0.7923407065037966, "grad_norm": 14.798515319824219, "learning_rate": 5.910281550182179e-05, "loss": 1.119353271484375, "step": 24000 }, { "epoch": 0.8088478045559591, "grad_norm": 6.670722961425781, "learning_rate": 5.887095064590924e-05, "loss": 1.09283935546875, "step": 24500 }, { "epoch": 0.8253549026081215, "grad_norm": 8.306891441345215, "learning_rate": 5.863908578999668e-05, "loss": 1.08545166015625, "step": 25000 }, { "epoch": 0.8418620006602839, "grad_norm": 12.713698387145996, "learning_rate": 5.840722093408413e-05, "loss": 1.100177490234375, "step": 25500 }, { "epoch": 0.8583690987124464, "grad_norm": 10.735971450805664, "learning_rate": 5.817535607817157e-05, "loss": 1.075918212890625, "step": 26000 }, { "epoch": 0.8748761967646088, "grad_norm": 13.791357040405273, "learning_rate": 5.794349122225902e-05, "loss": 1.0408736572265624, "step": 26500 }, { "epoch": 0.8913832948167713, "grad_norm": 9.611358642578125, "learning_rate": 5.771162636634647e-05, "loss": 1.0739583740234375, "step": 27000 }, { "epoch": 0.9078903928689337, "grad_norm": 8.19464111328125, "learning_rate": 5.747976151043391e-05, "loss": 1.018624267578125, "step": 27500 }, { "epoch": 0.924397490921096, "grad_norm": 10.252764701843262, "learning_rate": 5.724789665452136e-05, "loss": 1.012904052734375, "step": 28000 }, { "epoch": 0.9409045889732585, "grad_norm": 12.519780158996582, "learning_rate": 5.701603179860881e-05, "loss": 1.01883544921875, "step": 28500 }, { "epoch": 0.9574116870254209, "grad_norm": 9.025200843811035, "learning_rate": 5.678416694269625e-05, "loss": 1.0169927978515625, "step": 29000 }, { "epoch": 0.9739187850775833, "grad_norm": 10.392664909362793, "learning_rate": 5.65523020867837e-05, "loss": 1.0009882202148437, "step": 29500 }, { "epoch": 0.9904258831297458, "grad_norm": 5.833681583404541, "learning_rate": 5.632043723087114e-05, "loss": 0.9873718872070313, "step": 30000 }, { "epoch": 1.0069329811819083, "grad_norm": 10.545165061950684, "learning_rate": 5.608857237495859e-05, "loss": 0.9407935791015625, "step": 30500 }, { "epoch": 1.0234400792340705, "grad_norm": 7.148210525512695, "learning_rate": 5.585670751904604e-05, "loss": 0.90660498046875, "step": 31000 }, { "epoch": 1.039947177286233, "grad_norm": 9.806315422058105, "learning_rate": 5.5624842663133487e-05, "loss": 0.9245291748046875, "step": 31500 }, { "epoch": 1.0564542753383954, "grad_norm": 9.850616455078125, "learning_rate": 5.539297780722093e-05, "loss": 0.8889409790039062, "step": 32000 }, { "epoch": 1.0729613733905579, "grad_norm": 10.582934379577637, "learning_rate": 5.516111295130838e-05, "loss": 0.91727734375, "step": 32500 }, { "epoch": 1.0894684714427203, "grad_norm": 7.4774603843688965, "learning_rate": 5.492924809539582e-05, "loss": 0.8960700073242187, "step": 33000 }, { "epoch": 1.1059755694948827, "grad_norm": 8.407513618469238, "learning_rate": 5.469738323948327e-05, "loss": 0.893159912109375, "step": 33500 }, { "epoch": 1.1224826675470452, "grad_norm": 7.253698348999023, "learning_rate": 5.4465518383570716e-05, "loss": 0.8912428588867187, "step": 34000 }, { "epoch": 1.1389897655992076, "grad_norm": 7.6082916259765625, "learning_rate": 5.4233653527658165e-05, "loss": 0.907773681640625, "step": 34500 }, { "epoch": 1.15549686365137, "grad_norm": 10.549741744995117, "learning_rate": 5.400178867174561e-05, "loss": 0.8663541259765625, "step": 35000 }, { "epoch": 1.1720039617035325, "grad_norm": 8.778446197509766, "learning_rate": 5.376992381583305e-05, "loss": 0.8958565063476562, "step": 35500 }, { "epoch": 1.188511059755695, "grad_norm": 14.129327774047852, "learning_rate": 5.35380589599205e-05, "loss": 0.8555714111328125, "step": 36000 }, { "epoch": 1.2050181578078574, "grad_norm": 12.760954856872559, "learning_rate": 5.3306194104007946e-05, "loss": 0.8641258544921875, "step": 36500 }, { "epoch": 1.2215252558600198, "grad_norm": 10.197360038757324, "learning_rate": 5.3074329248095395e-05, "loss": 0.8500394897460938, "step": 37000 }, { "epoch": 1.2380323539121822, "grad_norm": 7.2205681800842285, "learning_rate": 5.284246439218284e-05, "loss": 0.85755419921875, "step": 37500 }, { "epoch": 1.2545394519643447, "grad_norm": 14.817720413208008, "learning_rate": 5.261059953627028e-05, "loss": 0.8412261352539062, "step": 38000 }, { "epoch": 1.2710465500165071, "grad_norm": 11.277249336242676, "learning_rate": 5.237873468035773e-05, "loss": 0.8301785278320313, "step": 38500 }, { "epoch": 1.2875536480686696, "grad_norm": 9.662931442260742, "learning_rate": 5.2146869824445176e-05, "loss": 0.8327305908203125, "step": 39000 }, { "epoch": 1.304060746120832, "grad_norm": 13.154888153076172, "learning_rate": 5.1915004968532625e-05, "loss": 0.8583154907226562, "step": 39500 }, { "epoch": 1.3205678441729944, "grad_norm": 9.764476776123047, "learning_rate": 5.1683140112620074e-05, "loss": 0.8371921997070313, "step": 40000 }, { "epoch": 1.3370749422251569, "grad_norm": 11.355097770690918, "learning_rate": 5.145127525670751e-05, "loss": 0.8261190185546875, "step": 40500 }, { "epoch": 1.3535820402773193, "grad_norm": 11.159167289733887, "learning_rate": 5.121941040079496e-05, "loss": 0.80646337890625, "step": 41000 }, { "epoch": 1.3700891383294818, "grad_norm": 13.455395698547363, "learning_rate": 5.0987545544882406e-05, "loss": 0.807060302734375, "step": 41500 }, { "epoch": 1.386596236381644, "grad_norm": 4.177359580993652, "learning_rate": 5.0755680688969855e-05, "loss": 0.803145751953125, "step": 42000 }, { "epoch": 1.4031033344338066, "grad_norm": 6.803620338439941, "learning_rate": 5.0523815833057303e-05, "loss": 0.7886021728515625, "step": 42500 }, { "epoch": 1.4196104324859689, "grad_norm": 16.001049041748047, "learning_rate": 5.029195097714475e-05, "loss": 0.7924509887695312, "step": 43000 }, { "epoch": 1.4361175305381315, "grad_norm": 10.750406265258789, "learning_rate": 5.006008612123219e-05, "loss": 0.7977892456054687, "step": 43500 }, { "epoch": 1.4526246285902937, "grad_norm": 12.50289249420166, "learning_rate": 4.9828221265319636e-05, "loss": 0.7672181396484375, "step": 44000 }, { "epoch": 1.4691317266424564, "grad_norm": 7.765811920166016, "learning_rate": 4.9596356409407085e-05, "loss": 0.7968384399414062, "step": 44500 }, { "epoch": 1.4856388246946186, "grad_norm": 12.1741304397583, "learning_rate": 4.936449155349453e-05, "loss": 0.7688109130859375, "step": 45000 }, { "epoch": 1.5021459227467813, "grad_norm": 7.9205241203308105, "learning_rate": 4.913262669758198e-05, "loss": 0.7822945556640625, "step": 45500 }, { "epoch": 1.5186530207989435, "grad_norm": 17.7078857421875, "learning_rate": 4.890076184166942e-05, "loss": 0.7615552978515625, "step": 46000 }, { "epoch": 1.535160118851106, "grad_norm": 7.357752799987793, "learning_rate": 4.8668896985756866e-05, "loss": 0.7523964233398438, "step": 46500 }, { "epoch": 1.5516672169032684, "grad_norm": 16.061647415161133, "learning_rate": 4.8437032129844315e-05, "loss": 0.7507512817382812, "step": 47000 }, { "epoch": 1.5681743149554308, "grad_norm": 10.651959419250488, "learning_rate": 4.820516727393176e-05, "loss": 0.7326008911132813, "step": 47500 }, { "epoch": 1.5846814130075932, "grad_norm": 10.769551277160645, "learning_rate": 4.797330241801921e-05, "loss": 0.76511767578125, "step": 48000 }, { "epoch": 1.6011885110597557, "grad_norm": 10.808145523071289, "learning_rate": 4.7741437562106654e-05, "loss": 0.7534960327148438, "step": 48500 }, { "epoch": 1.6176956091119181, "grad_norm": 13.4517183303833, "learning_rate": 4.7509572706194096e-05, "loss": 0.7673146362304688, "step": 49000 }, { "epoch": 1.6342027071640806, "grad_norm": 9.001216888427734, "learning_rate": 4.7277707850281544e-05, "loss": 0.7670245361328125, "step": 49500 }, { "epoch": 1.650709805216243, "grad_norm": 11.86727523803711, "learning_rate": 4.704584299436899e-05, "loss": 0.76016455078125, "step": 50000 }, { "epoch": 1.6672169032684054, "grad_norm": 15.86520004272461, "learning_rate": 4.681397813845644e-05, "loss": 0.7096920776367187, "step": 50500 }, { "epoch": 1.6837240013205679, "grad_norm": 7.089796543121338, "learning_rate": 4.6582113282543884e-05, "loss": 0.7482293090820312, "step": 51000 }, { "epoch": 1.7002310993727303, "grad_norm": 10.229025840759277, "learning_rate": 4.635024842663133e-05, "loss": 0.7204423828125, "step": 51500 }, { "epoch": 1.7167381974248928, "grad_norm": 8.949728965759277, "learning_rate": 4.6118383570718774e-05, "loss": 0.7349423828125, "step": 52000 }, { "epoch": 1.733245295477055, "grad_norm": 11.888359069824219, "learning_rate": 4.588651871480622e-05, "loss": 0.7251813354492187, "step": 52500 }, { "epoch": 1.7497523935292176, "grad_norm": 9.384441375732422, "learning_rate": 4.565465385889367e-05, "loss": 0.7346632690429687, "step": 53000 }, { "epoch": 1.7662594915813798, "grad_norm": 5.9711198806762695, "learning_rate": 4.542278900298112e-05, "loss": 0.7205990600585938, "step": 53500 }, { "epoch": 1.7827665896335425, "grad_norm": 8.23914909362793, "learning_rate": 4.519092414706856e-05, "loss": 0.7091600952148438, "step": 54000 }, { "epoch": 1.7992736876857047, "grad_norm": 6.286433696746826, "learning_rate": 4.4959059291156004e-05, "loss": 0.6958182373046875, "step": 54500 }, { "epoch": 1.8157807857378674, "grad_norm": 10.756072998046875, "learning_rate": 4.472719443524345e-05, "loss": 0.6938084716796875, "step": 55000 }, { "epoch": 1.8322878837900296, "grad_norm": 6.075191020965576, "learning_rate": 4.44953295793309e-05, "loss": 0.7118016967773437, "step": 55500 }, { "epoch": 1.8487949818421923, "grad_norm": 11.144367218017578, "learning_rate": 4.426346472341835e-05, "loss": 0.6961680908203125, "step": 56000 }, { "epoch": 1.8653020798943545, "grad_norm": 8.398560523986816, "learning_rate": 4.403159986750579e-05, "loss": 0.6863855590820312, "step": 56500 }, { "epoch": 1.8818091779465171, "grad_norm": 7.511946678161621, "learning_rate": 4.379973501159324e-05, "loss": 0.6969609985351563, "step": 57000 }, { "epoch": 1.8983162759986794, "grad_norm": 9.697932243347168, "learning_rate": 4.356787015568068e-05, "loss": 0.7151924438476562, "step": 57500 }, { "epoch": 1.914823374050842, "grad_norm": 3.7480437755584717, "learning_rate": 4.333600529976813e-05, "loss": 0.6817891235351563, "step": 58000 }, { "epoch": 1.9313304721030042, "grad_norm": 13.129742622375488, "learning_rate": 4.310414044385558e-05, "loss": 0.69914208984375, "step": 58500 }, { "epoch": 1.9478375701551667, "grad_norm": 11.975391387939453, "learning_rate": 4.287227558794302e-05, "loss": 0.7080562744140625, "step": 59000 }, { "epoch": 1.9643446682073291, "grad_norm": 8.200759887695312, "learning_rate": 4.264041073203047e-05, "loss": 0.717212890625, "step": 59500 }, { "epoch": 1.9808517662594916, "grad_norm": 7.388723373413086, "learning_rate": 4.240854587611792e-05, "loss": 0.71891650390625, "step": 60000 }, { "epoch": 1.997358864311654, "grad_norm": 6.114139556884766, "learning_rate": 4.217668102020536e-05, "loss": 0.6720064697265625, "step": 60500 }, { "epoch": 2.0138659623638167, "grad_norm": 5.123030662536621, "learning_rate": 4.194481616429281e-05, "loss": 0.6121041259765625, "step": 61000 }, { "epoch": 2.030373060415979, "grad_norm": 13.57762622833252, "learning_rate": 4.171295130838025e-05, "loss": 0.6164039306640625, "step": 61500 }, { "epoch": 2.046880158468141, "grad_norm": 12.116388320922852, "learning_rate": 4.14810864524677e-05, "loss": 0.6297982788085937, "step": 62000 }, { "epoch": 2.0633872565203037, "grad_norm": 6.75944709777832, "learning_rate": 4.124922159655515e-05, "loss": 0.6248591918945312, "step": 62500 }, { "epoch": 2.079894354572466, "grad_norm": 16.17805290222168, "learning_rate": 4.101735674064259e-05, "loss": 0.6369038696289062, "step": 63000 }, { "epoch": 2.0964014526246286, "grad_norm": 21.333209991455078, "learning_rate": 4.078549188473004e-05, "loss": 0.6213809814453125, "step": 63500 }, { "epoch": 2.112908550676791, "grad_norm": 7.218705177307129, "learning_rate": 4.055362702881748e-05, "loss": 0.5863359985351563, "step": 64000 }, { "epoch": 2.1294156487289535, "grad_norm": 8.422419548034668, "learning_rate": 4.032176217290493e-05, "loss": 0.623065673828125, "step": 64500 }, { "epoch": 2.1459227467811157, "grad_norm": 9.404297828674316, "learning_rate": 4.008989731699238e-05, "loss": 0.6076830444335938, "step": 65000 }, { "epoch": 2.1624298448332784, "grad_norm": 4.4386467933654785, "learning_rate": 3.985803246107983e-05, "loss": 0.6162603759765625, "step": 65500 }, { "epoch": 2.1789369428854406, "grad_norm": 15.584720611572266, "learning_rate": 3.962616760516727e-05, "loss": 0.6011383666992187, "step": 66000 }, { "epoch": 2.1954440409376033, "grad_norm": 9.569726943969727, "learning_rate": 3.939430274925471e-05, "loss": 0.6116184692382812, "step": 66500 }, { "epoch": 2.2119511389897655, "grad_norm": 9.182621002197266, "learning_rate": 3.916243789334216e-05, "loss": 0.6062463989257812, "step": 67000 }, { "epoch": 2.228458237041928, "grad_norm": 10.512551307678223, "learning_rate": 3.893057303742961e-05, "loss": 0.598578857421875, "step": 67500 }, { "epoch": 2.2449653350940904, "grad_norm": 6.855907440185547, "learning_rate": 3.869870818151706e-05, "loss": 0.6043606567382812, "step": 68000 }, { "epoch": 2.261472433146253, "grad_norm": 8.246521949768066, "learning_rate": 3.8466843325604506e-05, "loss": 0.5944453735351563, "step": 68500 }, { "epoch": 2.2779795311984152, "grad_norm": 18.470109939575195, "learning_rate": 3.823497846969194e-05, "loss": 0.5788815307617188, "step": 69000 }, { "epoch": 2.294486629250578, "grad_norm": 16.012584686279297, "learning_rate": 3.800311361377939e-05, "loss": 0.598007568359375, "step": 69500 }, { "epoch": 2.31099372730274, "grad_norm": 9.843379974365234, "learning_rate": 3.777124875786684e-05, "loss": 0.5795284423828125, "step": 70000 }, { "epoch": 2.3275008253549028, "grad_norm": 7.261438369750977, "learning_rate": 3.753938390195429e-05, "loss": 0.5743106079101562, "step": 70500 }, { "epoch": 2.344007923407065, "grad_norm": 3.9521117210388184, "learning_rate": 3.7307519046041736e-05, "loss": 0.606105224609375, "step": 71000 }, { "epoch": 2.3605150214592276, "grad_norm": 6.825229167938232, "learning_rate": 3.707565419012917e-05, "loss": 0.5898988647460938, "step": 71500 }, { "epoch": 2.37702211951139, "grad_norm": 9.514444351196289, "learning_rate": 3.684378933421662e-05, "loss": 0.60453564453125, "step": 72000 }, { "epoch": 2.393529217563552, "grad_norm": 5.445614814758301, "learning_rate": 3.661192447830407e-05, "loss": 0.5751649780273438, "step": 72500 }, { "epoch": 2.4100363156157147, "grad_norm": 11.861237525939941, "learning_rate": 3.638005962239152e-05, "loss": 0.5959569702148437, "step": 73000 }, { "epoch": 2.4265434136678774, "grad_norm": 10.26689338684082, "learning_rate": 3.6148194766478966e-05, "loss": 0.5889039306640625, "step": 73500 }, { "epoch": 2.4430505117200396, "grad_norm": 14.596261024475098, "learning_rate": 3.5916329910566415e-05, "loss": 0.5678682861328125, "step": 74000 }, { "epoch": 2.459557609772202, "grad_norm": 7.374675750732422, "learning_rate": 3.568446505465385e-05, "loss": 0.6002325439453124, "step": 74500 }, { "epoch": 2.4760647078243645, "grad_norm": 10.496848106384277, "learning_rate": 3.54526001987413e-05, "loss": 0.5713438720703125, "step": 75000 }, { "epoch": 2.4925718058765267, "grad_norm": 13.315743446350098, "learning_rate": 3.522073534282875e-05, "loss": 0.5691968994140625, "step": 75500 }, { "epoch": 2.5090789039286894, "grad_norm": 10.1326265335083, "learning_rate": 3.4988870486916196e-05, "loss": 0.5541436767578125, "step": 76000 }, { "epoch": 2.5255860019808516, "grad_norm": 6.859860420227051, "learning_rate": 3.475700563100364e-05, "loss": 0.5757225341796876, "step": 76500 }, { "epoch": 2.5420931000330143, "grad_norm": 6.147298336029053, "learning_rate": 3.452514077509109e-05, "loss": 0.5582262573242187, "step": 77000 }, { "epoch": 2.5586001980851765, "grad_norm": 9.422947883605957, "learning_rate": 3.4293275919178535e-05, "loss": 0.5809881591796875, "step": 77500 }, { "epoch": 2.575107296137339, "grad_norm": 9.929452896118164, "learning_rate": 3.406141106326598e-05, "loss": 0.5612611694335937, "step": 78000 }, { "epoch": 2.5916143941895013, "grad_norm": 2.059706926345825, "learning_rate": 3.3829546207353426e-05, "loss": 0.5463908081054687, "step": 78500 }, { "epoch": 2.608121492241664, "grad_norm": 9.060196876525879, "learning_rate": 3.3597681351440875e-05, "loss": 0.5624230346679687, "step": 79000 }, { "epoch": 2.6246285902938262, "grad_norm": 5.973160266876221, "learning_rate": 3.336581649552832e-05, "loss": 0.5693687744140625, "step": 79500 }, { "epoch": 2.641135688345989, "grad_norm": 7.426895618438721, "learning_rate": 3.3133951639615765e-05, "loss": 0.5336575927734375, "step": 80000 }, { "epoch": 2.657642786398151, "grad_norm": 10.789342880249023, "learning_rate": 3.2902086783703214e-05, "loss": 0.573309814453125, "step": 80500 }, { "epoch": 2.6741498844503138, "grad_norm": 11.855134010314941, "learning_rate": 3.2670221927790656e-05, "loss": 0.5442750244140625, "step": 81000 }, { "epoch": 2.690656982502476, "grad_norm": 8.535783767700195, "learning_rate": 3.2438357071878105e-05, "loss": 0.5696862182617187, "step": 81500 }, { "epoch": 2.7071640805546386, "grad_norm": 12.383220672607422, "learning_rate": 3.220649221596555e-05, "loss": 0.5558529663085937, "step": 82000 }, { "epoch": 2.723671178606801, "grad_norm": 6.949540138244629, "learning_rate": 3.1974627360052995e-05, "loss": 0.5468307495117187, "step": 82500 }, { "epoch": 2.7401782766589635, "grad_norm": 10.960880279541016, "learning_rate": 3.1742762504140444e-05, "loss": 0.5583523559570313, "step": 83000 }, { "epoch": 2.7566853747111257, "grad_norm": 17.600597381591797, "learning_rate": 3.1510897648227886e-05, "loss": 0.5444569702148437, "step": 83500 }, { "epoch": 2.773192472763288, "grad_norm": 6.94141960144043, "learning_rate": 3.1279032792315335e-05, "loss": 0.5510944213867187, "step": 84000 }, { "epoch": 2.7896995708154506, "grad_norm": 11.447288513183594, "learning_rate": 3.104716793640278e-05, "loss": 0.522359375, "step": 84500 }, { "epoch": 2.8062066688676133, "grad_norm": 11.601890563964844, "learning_rate": 3.0815303080490225e-05, "loss": 0.5576813354492187, "step": 85000 }, { "epoch": 2.8227137669197755, "grad_norm": 8.161893844604492, "learning_rate": 3.0583438224577674e-05, "loss": 0.5306047973632813, "step": 85500 }, { "epoch": 2.8392208649719377, "grad_norm": 10.267998695373535, "learning_rate": 3.035157336866512e-05, "loss": 0.54469873046875, "step": 86000 }, { "epoch": 2.8557279630241004, "grad_norm": 13.7251558303833, "learning_rate": 3.0119708512752564e-05, "loss": 0.5550822143554688, "step": 86500 }, { "epoch": 2.872235061076263, "grad_norm": 19.00032615661621, "learning_rate": 2.988784365684001e-05, "loss": 0.5725646362304687, "step": 87000 }, { "epoch": 2.8887421591284252, "grad_norm": 10.842531204223633, "learning_rate": 2.965597880092746e-05, "loss": 0.5253878784179687, "step": 87500 }, { "epoch": 2.9052492571805875, "grad_norm": 6.362691879272461, "learning_rate": 2.94241139450149e-05, "loss": 0.5517511596679687, "step": 88000 }, { "epoch": 2.92175635523275, "grad_norm": 5.822941780090332, "learning_rate": 2.919224908910235e-05, "loss": 0.5589564208984374, "step": 88500 }, { "epoch": 2.938263453284913, "grad_norm": 6.517460823059082, "learning_rate": 2.8960384233189798e-05, "loss": 0.5495121459960938, "step": 89000 }, { "epoch": 2.954770551337075, "grad_norm": 7.94489049911499, "learning_rate": 2.872851937727724e-05, "loss": 0.540964599609375, "step": 89500 }, { "epoch": 2.971277649389237, "grad_norm": 4.831021308898926, "learning_rate": 2.8496654521364688e-05, "loss": 0.5309302368164063, "step": 90000 }, { "epoch": 2.9877847474414, "grad_norm": 13.597745895385742, "learning_rate": 2.8264789665452137e-05, "loss": 0.5202194213867187, "step": 90500 }, { "epoch": 3.004291845493562, "grad_norm": 11.4650297164917, "learning_rate": 2.803292480953958e-05, "loss": 0.527130615234375, "step": 91000 }, { "epoch": 3.0207989435457248, "grad_norm": 7.096149921417236, "learning_rate": 2.7801059953627028e-05, "loss": 0.443453125, "step": 91500 }, { "epoch": 3.037306041597887, "grad_norm": 25.524545669555664, "learning_rate": 2.7569195097714473e-05, "loss": 0.4611954650878906, "step": 92000 }, { "epoch": 3.0538131396500496, "grad_norm": 7.1986823081970215, "learning_rate": 2.7337330241801918e-05, "loss": 0.4974554748535156, "step": 92500 }, { "epoch": 3.070320237702212, "grad_norm": 17.93976593017578, "learning_rate": 2.7105465385889367e-05, "loss": 0.5080933532714844, "step": 93000 }, { "epoch": 3.0868273357543745, "grad_norm": 4.9785614013671875, "learning_rate": 2.687360052997681e-05, "loss": 0.48324435424804685, "step": 93500 }, { "epoch": 3.1033344338065367, "grad_norm": 4.591154098510742, "learning_rate": 2.6641735674064257e-05, "loss": 0.49523236083984373, "step": 94000 }, { "epoch": 3.1198415318586994, "grad_norm": 5.788321018218994, "learning_rate": 2.6409870818151703e-05, "loss": 0.46864627075195314, "step": 94500 }, { "epoch": 3.1363486299108616, "grad_norm": 7.044639587402344, "learning_rate": 2.6178005962239148e-05, "loss": 0.4788813171386719, "step": 95000 }, { "epoch": 3.1528557279630243, "grad_norm": 11.35835075378418, "learning_rate": 2.5946141106326597e-05, "loss": 0.5045942993164062, "step": 95500 }, { "epoch": 3.1693628260151865, "grad_norm": 9.185290336608887, "learning_rate": 2.5714276250414042e-05, "loss": 0.4803794860839844, "step": 96000 }, { "epoch": 3.185869924067349, "grad_norm": 8.142857551574707, "learning_rate": 2.5482411394501487e-05, "loss": 0.46914306640625, "step": 96500 }, { "epoch": 3.2023770221195114, "grad_norm": 10.733062744140625, "learning_rate": 2.5250546538588936e-05, "loss": 0.4719870300292969, "step": 97000 }, { "epoch": 3.218884120171674, "grad_norm": 11.454483032226562, "learning_rate": 2.501868168267638e-05, "loss": 0.45844384765625, "step": 97500 }, { "epoch": 3.2353912182238362, "grad_norm": 19.816076278686523, "learning_rate": 2.4786816826763827e-05, "loss": 0.4567518005371094, "step": 98000 }, { "epoch": 3.251898316275999, "grad_norm": 8.554481506347656, "learning_rate": 2.4554951970851272e-05, "loss": 0.47145968627929685, "step": 98500 }, { "epoch": 3.268405414328161, "grad_norm": 4.202885627746582, "learning_rate": 2.432308711493872e-05, "loss": 0.4863616638183594, "step": 99000 }, { "epoch": 3.2849125123803233, "grad_norm": 5.994730472564697, "learning_rate": 2.4091222259026166e-05, "loss": 0.4707845458984375, "step": 99500 }, { "epoch": 3.301419610432486, "grad_norm": 10.900041580200195, "learning_rate": 2.385935740311361e-05, "loss": 0.4817855224609375, "step": 100000 }, { "epoch": 3.317926708484648, "grad_norm": 18.980676651000977, "learning_rate": 2.362749254720106e-05, "loss": 0.4693571472167969, "step": 100500 }, { "epoch": 3.334433806536811, "grad_norm": 16.007965087890625, "learning_rate": 2.3395627691288502e-05, "loss": 0.48550283813476564, "step": 101000 }, { "epoch": 3.350940904588973, "grad_norm": 15.75615406036377, "learning_rate": 2.316376283537595e-05, "loss": 0.47613949584960935, "step": 101500 }, { "epoch": 3.3674480026411358, "grad_norm": 14.896931648254395, "learning_rate": 2.29318979794634e-05, "loss": 0.47577984619140623, "step": 102000 }, { "epoch": 3.383955100693298, "grad_norm": 17.77467918395996, "learning_rate": 2.270003312355084e-05, "loss": 0.45754031372070314, "step": 102500 }, { "epoch": 3.4004621987454606, "grad_norm": 10.033401489257812, "learning_rate": 2.246816826763829e-05, "loss": 0.4792729187011719, "step": 103000 }, { "epoch": 3.416969296797623, "grad_norm": 4.162666320800781, "learning_rate": 2.2236303411725732e-05, "loss": 0.4584093322753906, "step": 103500 }, { "epoch": 3.4334763948497855, "grad_norm": 16.417449951171875, "learning_rate": 2.200443855581318e-05, "loss": 0.46188922119140624, "step": 104000 }, { "epoch": 3.4499834929019477, "grad_norm": 10.017684936523438, "learning_rate": 2.177257369990063e-05, "loss": 0.4741541442871094, "step": 104500 }, { "epoch": 3.4664905909541104, "grad_norm": 14.131627082824707, "learning_rate": 2.154070884398807e-05, "loss": 0.45993768310546873, "step": 105000 }, { "epoch": 3.4829976890062726, "grad_norm": 11.576376914978027, "learning_rate": 2.130884398807552e-05, "loss": 0.44119857788085937, "step": 105500 }, { "epoch": 3.4995047870584353, "grad_norm": 7.9193644523620605, "learning_rate": 2.107697913216297e-05, "loss": 0.4613685607910156, "step": 106000 }, { "epoch": 3.5160118851105975, "grad_norm": 6.768561840057373, "learning_rate": 2.084511427625041e-05, "loss": 0.47672256469726565, "step": 106500 }, { "epoch": 3.53251898316276, "grad_norm": 21.917171478271484, "learning_rate": 2.061324942033786e-05, "loss": 0.4663753662109375, "step": 107000 }, { "epoch": 3.5490260812149224, "grad_norm": 12.410985946655273, "learning_rate": 2.0381384564425308e-05, "loss": 0.47280987548828124, "step": 107500 }, { "epoch": 3.565533179267085, "grad_norm": 8.704672813415527, "learning_rate": 2.014951970851275e-05, "loss": 0.47054962158203123, "step": 108000 }, { "epoch": 3.5820402773192472, "grad_norm": 11.220333099365234, "learning_rate": 1.9917654852600198e-05, "loss": 0.46597244262695314, "step": 108500 }, { "epoch": 3.5985473753714095, "grad_norm": 7.277413845062256, "learning_rate": 1.9685789996687644e-05, "loss": 0.47163360595703124, "step": 109000 }, { "epoch": 3.615054473423572, "grad_norm": 7.527535915374756, "learning_rate": 1.945392514077509e-05, "loss": 0.4580298156738281, "step": 109500 }, { "epoch": 3.6315615714757348, "grad_norm": 3.370473861694336, "learning_rate": 1.9222060284862538e-05, "loss": 0.4702852478027344, "step": 110000 }, { "epoch": 3.648068669527897, "grad_norm": 4.207464694976807, "learning_rate": 1.8990195428949983e-05, "loss": 0.47686077880859373, "step": 110500 }, { "epoch": 3.664575767580059, "grad_norm": 3.0146734714508057, "learning_rate": 1.8758330573037428e-05, "loss": 0.4447147216796875, "step": 111000 }, { "epoch": 3.681082865632222, "grad_norm": 8.923477172851562, "learning_rate": 1.8526465717124873e-05, "loss": 0.456516357421875, "step": 111500 }, { "epoch": 3.6975899636843845, "grad_norm": 6.79431676864624, "learning_rate": 1.829460086121232e-05, "loss": 0.4572928161621094, "step": 112000 }, { "epoch": 3.7140970617365467, "grad_norm": 12.184188842773438, "learning_rate": 1.8062736005299767e-05, "loss": 0.44392245483398435, "step": 112500 }, { "epoch": 3.730604159788709, "grad_norm": 6.109889030456543, "learning_rate": 1.7830871149387213e-05, "loss": 0.4647085876464844, "step": 113000 }, { "epoch": 3.7471112578408716, "grad_norm": 16.428634643554688, "learning_rate": 1.7599006293474658e-05, "loss": 0.4340731201171875, "step": 113500 }, { "epoch": 3.763618355893034, "grad_norm": 14.924697875976562, "learning_rate": 1.7367141437562103e-05, "loss": 0.470101806640625, "step": 114000 }, { "epoch": 3.7801254539451965, "grad_norm": 14.087942123413086, "learning_rate": 1.7135276581649552e-05, "loss": 0.47080560302734376, "step": 114500 }, { "epoch": 3.7966325519973587, "grad_norm": 16.107940673828125, "learning_rate": 1.6903411725736997e-05, "loss": 0.46590252685546873, "step": 115000 }, { "epoch": 3.8131396500495214, "grad_norm": 10.144551277160645, "learning_rate": 1.6671546869824443e-05, "loss": 0.4599480285644531, "step": 115500 }, { "epoch": 3.8296467481016836, "grad_norm": 10.14151382446289, "learning_rate": 1.6439682013911888e-05, "loss": 0.46120849609375, "step": 116000 }, { "epoch": 3.8461538461538463, "grad_norm": 11.59428596496582, "learning_rate": 1.6207817157999337e-05, "loss": 0.4505504760742188, "step": 116500 }, { "epoch": 3.8626609442060085, "grad_norm": 7.489445209503174, "learning_rate": 1.5975952302086782e-05, "loss": 0.45775439453125, "step": 117000 }, { "epoch": 3.879168042258171, "grad_norm": 6.898009300231934, "learning_rate": 1.5744087446174227e-05, "loss": 0.437826904296875, "step": 117500 }, { "epoch": 3.8956751403103334, "grad_norm": 8.67469310760498, "learning_rate": 1.5512222590261676e-05, "loss": 0.46209564208984377, "step": 118000 }, { "epoch": 3.912182238362496, "grad_norm": 9.536890029907227, "learning_rate": 1.528035773434912e-05, "loss": 0.4517965087890625, "step": 118500 }, { "epoch": 3.9286893364146582, "grad_norm": 12.719433784484863, "learning_rate": 1.5048492878436566e-05, "loss": 0.44278268432617185, "step": 119000 }, { "epoch": 3.945196434466821, "grad_norm": 6.761035919189453, "learning_rate": 1.4816628022524012e-05, "loss": 0.4437563781738281, "step": 119500 }, { "epoch": 3.961703532518983, "grad_norm": 9.321235656738281, "learning_rate": 1.458476316661146e-05, "loss": 0.4429962158203125, "step": 120000 }, { "epoch": 3.9782106305711453, "grad_norm": 13.229169845581055, "learning_rate": 1.4352898310698906e-05, "loss": 0.4453585510253906, "step": 120500 }, { "epoch": 3.994717728623308, "grad_norm": 12.225985527038574, "learning_rate": 1.4121033454786351e-05, "loss": 0.43215255737304686, "step": 121000 }, { "epoch": 4.011224826675471, "grad_norm": 6.612095355987549, "learning_rate": 1.3889168598873798e-05, "loss": 0.42794491577148436, "step": 121500 }, { "epoch": 4.027731924727633, "grad_norm": 19.95702362060547, "learning_rate": 1.3657303742961245e-05, "loss": 0.40834698486328125, "step": 122000 }, { "epoch": 4.044239022779795, "grad_norm": 11.839484214782715, "learning_rate": 1.342543888704869e-05, "loss": 0.41184072875976563, "step": 122500 }, { "epoch": 4.060746120831958, "grad_norm": 4.341104030609131, "learning_rate": 1.3193574031136136e-05, "loss": 0.4033194580078125, "step": 123000 }, { "epoch": 4.07725321888412, "grad_norm": 12.381763458251953, "learning_rate": 1.2961709175223583e-05, "loss": 0.3985845947265625, "step": 123500 }, { "epoch": 4.093760316936282, "grad_norm": 11.846001625061035, "learning_rate": 1.272984431931103e-05, "loss": 0.41433114624023437, "step": 124000 }, { "epoch": 4.110267414988445, "grad_norm": 11.04519271850586, "learning_rate": 1.2497979463398475e-05, "loss": 0.40165704345703124, "step": 124500 }, { "epoch": 4.1267745130406075, "grad_norm": 12.111519813537598, "learning_rate": 1.2266114607485922e-05, "loss": 0.40655184936523436, "step": 125000 }, { "epoch": 4.14328161109277, "grad_norm": 13.776103019714355, "learning_rate": 1.2034249751573367e-05, "loss": 0.4055103454589844, "step": 125500 }, { "epoch": 4.159788709144932, "grad_norm": 17.371768951416016, "learning_rate": 1.1802384895660813e-05, "loss": 0.3992621459960938, "step": 126000 }, { "epoch": 4.176295807197095, "grad_norm": 24.995500564575195, "learning_rate": 1.1570520039748261e-05, "loss": 0.36630471801757813, "step": 126500 }, { "epoch": 4.192802905249257, "grad_norm": 5.215199947357178, "learning_rate": 1.1338655183835707e-05, "loss": 0.4138486328125, "step": 127000 }, { "epoch": 4.20931000330142, "grad_norm": 1.1457958221435547, "learning_rate": 1.1106790327923152e-05, "loss": 0.41272543334960937, "step": 127500 }, { "epoch": 4.225817101353582, "grad_norm": 5.064228057861328, "learning_rate": 1.0874925472010597e-05, "loss": 0.4165557861328125, "step": 128000 }, { "epoch": 4.242324199405744, "grad_norm": 4.753109931945801, "learning_rate": 1.0643060616098046e-05, "loss": 0.406870849609375, "step": 128500 }, { "epoch": 4.258831297457907, "grad_norm": 14.215486526489258, "learning_rate": 1.0411195760185491e-05, "loss": 0.41836679077148436, "step": 129000 }, { "epoch": 4.27533839551007, "grad_norm": 14.64974308013916, "learning_rate": 1.0179330904272936e-05, "loss": 0.41488427734375, "step": 129500 }, { "epoch": 4.291845493562231, "grad_norm": 6.21533727645874, "learning_rate": 9.947466048360383e-06, "loss": 0.4024839477539062, "step": 130000 }, { "epoch": 4.308352591614394, "grad_norm": 14.10433292388916, "learning_rate": 9.71560119244783e-06, "loss": 0.396489013671875, "step": 130500 }, { "epoch": 4.324859689666557, "grad_norm": 13.063375473022461, "learning_rate": 9.483736336535276e-06, "loss": 0.3887447509765625, "step": 131000 }, { "epoch": 4.341366787718719, "grad_norm": 15.06894588470459, "learning_rate": 9.251871480622723e-06, "loss": 0.414082763671875, "step": 131500 }, { "epoch": 4.357873885770881, "grad_norm": 4.036756992340088, "learning_rate": 9.020006624710168e-06, "loss": 0.4040983581542969, "step": 132000 }, { "epoch": 4.374380983823044, "grad_norm": 3.5342495441436768, "learning_rate": 8.788141768797613e-06, "loss": 0.37372430419921876, "step": 132500 }, { "epoch": 4.3908880818752065, "grad_norm": 5.4125590324401855, "learning_rate": 8.55627691288506e-06, "loss": 0.3862229614257813, "step": 133000 }, { "epoch": 4.407395179927369, "grad_norm": 10.269238471984863, "learning_rate": 8.324412056972506e-06, "loss": 0.39998532104492185, "step": 133500 }, { "epoch": 4.423902277979531, "grad_norm": 17.385026931762695, "learning_rate": 8.092547201059953e-06, "loss": 0.4000919189453125, "step": 134000 }, { "epoch": 4.440409376031694, "grad_norm": 9.967487335205078, "learning_rate": 7.8606823451474e-06, "loss": 0.41085659790039064, "step": 134500 }, { "epoch": 4.456916474083856, "grad_norm": 7.279437065124512, "learning_rate": 7.628817489234845e-06, "loss": 0.41115106201171875, "step": 135000 }, { "epoch": 4.473423572136019, "grad_norm": 20.997140884399414, "learning_rate": 7.396952633322292e-06, "loss": 0.37628985595703124, "step": 135500 }, { "epoch": 4.489930670188181, "grad_norm": 20.638233184814453, "learning_rate": 7.165087777409737e-06, "loss": 0.3844537353515625, "step": 136000 }, { "epoch": 4.506437768240343, "grad_norm": 10.948421478271484, "learning_rate": 6.933222921497184e-06, "loss": 0.41525863647460937, "step": 136500 }, { "epoch": 4.522944866292506, "grad_norm": 5.250335216522217, "learning_rate": 6.70135806558463e-06, "loss": 0.39825369262695315, "step": 137000 }, { "epoch": 4.539451964344668, "grad_norm": 11.97547721862793, "learning_rate": 6.4694932096720765e-06, "loss": 0.38035321044921877, "step": 137500 }, { "epoch": 4.5559590623968305, "grad_norm": 22.62888526916504, "learning_rate": 6.237628353759523e-06, "loss": 0.38635723876953126, "step": 138000 }, { "epoch": 4.572466160448993, "grad_norm": 8.603704452514648, "learning_rate": 6.005763497846968e-06, "loss": 0.3930986328125, "step": 138500 }, { "epoch": 4.588973258501156, "grad_norm": 4.589338779449463, "learning_rate": 5.773898641934415e-06, "loss": 0.37287020874023435, "step": 139000 }, { "epoch": 4.6054803565533176, "grad_norm": 13.401651382446289, "learning_rate": 5.542033786021862e-06, "loss": 0.3726418762207031, "step": 139500 }, { "epoch": 4.62198745460548, "grad_norm": 11.4149808883667, "learning_rate": 5.310168930109307e-06, "loss": 0.39665234375, "step": 140000 }, { "epoch": 4.638494552657643, "grad_norm": 7.317187309265137, "learning_rate": 5.078304074196753e-06, "loss": 0.4172890319824219, "step": 140500 }, { "epoch": 4.6550016507098055, "grad_norm": 9.344099998474121, "learning_rate": 4.8464392182841995e-06, "loss": 0.40045440673828125, "step": 141000 }, { "epoch": 4.671508748761967, "grad_norm": 10.729949951171875, "learning_rate": 4.614574362371646e-06, "loss": 0.3803172607421875, "step": 141500 }, { "epoch": 4.68801584681413, "grad_norm": 7.420276165008545, "learning_rate": 4.382709506459092e-06, "loss": 0.38827316284179686, "step": 142000 }, { "epoch": 4.704522944866293, "grad_norm": 15.778042793273926, "learning_rate": 4.150844650546538e-06, "loss": 0.39117340087890623, "step": 142500 }, { "epoch": 4.721030042918455, "grad_norm": 4.193133354187012, "learning_rate": 3.918979794633984e-06, "loss": 0.41804022216796877, "step": 143000 }, { "epoch": 4.737537140970617, "grad_norm": 8.706432342529297, "learning_rate": 3.6871149387214307e-06, "loss": 0.39569940185546876, "step": 143500 }, { "epoch": 4.75404423902278, "grad_norm": 6.802443504333496, "learning_rate": 3.455250082808877e-06, "loss": 0.3666829528808594, "step": 144000 }, { "epoch": 4.770551337074942, "grad_norm": 6.266483783721924, "learning_rate": 3.223385226896323e-06, "loss": 0.3998408203125, "step": 144500 }, { "epoch": 4.787058435127104, "grad_norm": 10.942164421081543, "learning_rate": 2.991520370983769e-06, "loss": 0.3830989990234375, "step": 145000 }, { "epoch": 4.803565533179267, "grad_norm": 21.07566261291504, "learning_rate": 2.7596555150712153e-06, "loss": 0.3703013916015625, "step": 145500 }, { "epoch": 4.8200726312314295, "grad_norm": 5.540200710296631, "learning_rate": 2.5277906591586614e-06, "loss": 0.3869327392578125, "step": 146000 }, { "epoch": 4.836579729283592, "grad_norm": 11.823589324951172, "learning_rate": 2.295925803246108e-06, "loss": 0.3982554931640625, "step": 146500 }, { "epoch": 4.853086827335755, "grad_norm": 12.406991004943848, "learning_rate": 2.064060947333554e-06, "loss": 0.3886056823730469, "step": 147000 }, { "epoch": 4.869593925387917, "grad_norm": 6.8308000564575195, "learning_rate": 1.832196091421e-06, "loss": 0.4027244567871094, "step": 147500 }, { "epoch": 4.886101023440079, "grad_norm": 10.677574157714844, "learning_rate": 1.6003312355084462e-06, "loss": 0.3799744567871094, "step": 148000 }, { "epoch": 4.902608121492242, "grad_norm": 12.361015319824219, "learning_rate": 1.3684663795958926e-06, "loss": 0.37549533081054687, "step": 148500 }, { "epoch": 4.919115219544404, "grad_norm": 10.424262046813965, "learning_rate": 1.1366015236833387e-06, "loss": 0.38190765380859376, "step": 149000 }, { "epoch": 4.935622317596566, "grad_norm": 4.839986324310303, "learning_rate": 9.04736667770785e-07, "loss": 0.378268310546875, "step": 149500 }, { "epoch": 4.952129415648729, "grad_norm": 11.162050247192383, "learning_rate": 6.728718118582311e-07, "loss": 0.3968852233886719, "step": 150000 }, { "epoch": 4.968636513700892, "grad_norm": 8.690582275390625, "learning_rate": 4.410069559456773e-07, "loss": 0.38345846557617186, "step": 150500 }, { "epoch": 4.985143611753053, "grad_norm": 6.007940769195557, "learning_rate": 2.0914210003312351e-07, "loss": 0.39504232788085936, "step": 151000 }, { "epoch": 5.0, "step": 151450, "total_flos": 3.401845517119488e+16, "train_loss": 0.744352999637134, "train_runtime": 30010.6452, "train_samples_per_second": 80.743, "train_steps_per_second": 5.047 } ], "logging_steps": 500, "max_steps": 151450, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.401845517119488e+16, "train_batch_size": 16, "trial_name": null, "trial_params": null }