| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9988505747126437, |
| "eval_steps": 500, |
| "global_step": 869, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005747126436781609, |
| "grad_norm": 11.50942325592041, |
| "learning_rate": 3.2463636363636365e-06, |
| "loss": 1.9136, |
| "mean_token_accuracy": 0.6757451295852661, |
| "num_tokens": 403129.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.011494252873563218, |
| "grad_norm": 3.601832866668701, |
| "learning_rate": 7.3043181818181825e-06, |
| "loss": 1.6064, |
| "mean_token_accuracy": 0.6915940046310425, |
| "num_tokens": 808163.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.017241379310344827, |
| "grad_norm": 2.5387675762176514, |
| "learning_rate": 1.1362272727272727e-05, |
| "loss": 1.178, |
| "mean_token_accuracy": 0.7406479597091675, |
| "num_tokens": 1212678.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.022988505747126436, |
| "grad_norm": 2.6335058212280273, |
| "learning_rate": 1.5420227272727274e-05, |
| "loss": 0.752, |
| "mean_token_accuracy": 0.8273701429367065, |
| "num_tokens": 1615888.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.028735632183908046, |
| "grad_norm": 1.3575574159622192, |
| "learning_rate": 1.9478181818181816e-05, |
| "loss": 0.3227, |
| "mean_token_accuracy": 0.9204407930374146, |
| "num_tokens": 2020108.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.034482758620689655, |
| "grad_norm": 4.603687763214111, |
| "learning_rate": 2.3536136363636365e-05, |
| "loss": 0.0922, |
| "mean_token_accuracy": 0.9775937318801879, |
| "num_tokens": 2425497.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.040229885057471264, |
| "grad_norm": 0.3694731295108795, |
| "learning_rate": 2.759409090909091e-05, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.983700180053711, |
| "num_tokens": 2828765.0, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.04597701149425287, |
| "grad_norm": 0.312744677066803, |
| "learning_rate": 3.1652045454545456e-05, |
| "loss": 0.0291, |
| "mean_token_accuracy": 0.991856825351715, |
| "num_tokens": 3233303.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.05172413793103448, |
| "grad_norm": 0.1357622891664505, |
| "learning_rate": 3.571e-05, |
| "loss": 0.0213, |
| "mean_token_accuracy": 0.9935701847076416, |
| "num_tokens": 3637991.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.05747126436781609, |
| "grad_norm": 0.11526472866535187, |
| "learning_rate": 3.570757864931307e-05, |
| "loss": 0.0188, |
| "mean_token_accuracy": 0.9941024422645569, |
| "num_tokens": 4042692.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.06321839080459771, |
| "grad_norm": 0.06420823186635971, |
| "learning_rate": 3.570031547288962e-05, |
| "loss": 0.0187, |
| "mean_token_accuracy": 0.9939285755157471, |
| "num_tokens": 4446677.0, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.06896551724137931, |
| "grad_norm": 0.07142060250043869, |
| "learning_rate": 3.568821309732495e-05, |
| "loss": 0.0179, |
| "mean_token_accuracy": 0.9940606236457825, |
| "num_tokens": 4851040.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.07471264367816093, |
| "grad_norm": 0.14311493933200836, |
| "learning_rate": 3.567127589922249e-05, |
| "loss": 0.0181, |
| "mean_token_accuracy": 0.9940086245536804, |
| "num_tokens": 5254512.0, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.08045977011494253, |
| "grad_norm": 0.1732994168996811, |
| "learning_rate": 3.5649510003611104e-05, |
| "loss": 0.0163, |
| "mean_token_accuracy": 0.9943243384361267, |
| "num_tokens": 5659208.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.08620689655172414, |
| "grad_norm": 0.03773409128189087, |
| "learning_rate": 3.562292328173002e-05, |
| "loss": 0.0154, |
| "mean_token_accuracy": 0.9946787118911743, |
| "num_tokens": 6064767.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.09195402298850575, |
| "grad_norm": 0.04296102374792099, |
| "learning_rate": 3.5591525348182415e-05, |
| "loss": 0.0174, |
| "mean_token_accuracy": 0.9942841291427612, |
| "num_tokens": 6467687.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.09770114942528736, |
| "grad_norm": 0.052675988525152206, |
| "learning_rate": 3.5555327557458406e-05, |
| "loss": 0.0168, |
| "mean_token_accuracy": 0.9943979263305665, |
| "num_tokens": 6870874.0, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.10344827586206896, |
| "grad_norm": 0.04074929654598236, |
| "learning_rate": 3.551434299982895e-05, |
| "loss": 0.0162, |
| "mean_token_accuracy": 0.9944364666938782, |
| "num_tokens": 7274927.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.10919540229885058, |
| "grad_norm": 0.053142838180065155, |
| "learning_rate": 3.546858649661196e-05, |
| "loss": 0.0166, |
| "mean_token_accuracy": 0.994316291809082, |
| "num_tokens": 7678668.0, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.11494252873563218, |
| "grad_norm": 0.05124868080019951, |
| "learning_rate": 3.5418074594812456e-05, |
| "loss": 0.0156, |
| "mean_token_accuracy": 0.9945274949073791, |
| "num_tokens": 8082319.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1206896551724138, |
| "grad_norm": 0.05799630656838417, |
| "learning_rate": 3.536282556113864e-05, |
| "loss": 0.0153, |
| "mean_token_accuracy": 0.9946353793144226, |
| "num_tokens": 8485887.0, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.12643678160919541, |
| "grad_norm": 0.048035357147455215, |
| "learning_rate": 3.530285937539609e-05, |
| "loss": 0.0153, |
| "mean_token_accuracy": 0.9946409940719605, |
| "num_tokens": 8888964.0, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.13218390804597702, |
| "grad_norm": 0.040226273238658905, |
| "learning_rate": 3.5238197723262395e-05, |
| "loss": 0.0151, |
| "mean_token_accuracy": 0.9946888566017151, |
| "num_tokens": 9291928.0, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.13793103448275862, |
| "grad_norm": 0.05495241656899452, |
| "learning_rate": 3.5168863988444935e-05, |
| "loss": 0.0149, |
| "mean_token_accuracy": 0.9946548223495484, |
| "num_tokens": 9695699.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.14367816091954022, |
| "grad_norm": 0.06851889193058014, |
| "learning_rate": 3.509488324422462e-05, |
| "loss": 0.0152, |
| "mean_token_accuracy": 0.9944992899894715, |
| "num_tokens": 10099209.0, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.14942528735632185, |
| "grad_norm": 0.04976602643728256, |
| "learning_rate": 3.5016282244388565e-05, |
| "loss": 0.0143, |
| "mean_token_accuracy": 0.9948261499404907, |
| "num_tokens": 10503188.0, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.15517241379310345, |
| "grad_norm": 0.05081531032919884, |
| "learning_rate": 3.493308941355507e-05, |
| "loss": 0.0155, |
| "mean_token_accuracy": 0.994414746761322, |
| "num_tokens": 10906288.0, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.16091954022988506, |
| "grad_norm": 0.050771500915288925, |
| "learning_rate": 3.48453348368944e-05, |
| "loss": 0.0143, |
| "mean_token_accuracy": 0.9947004079818725, |
| "num_tokens": 11311117.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.16666666666666666, |
| "grad_norm": 0.06757643818855286, |
| "learning_rate": 3.475305024924899e-05, |
| "loss": 0.0142, |
| "mean_token_accuracy": 0.994769024848938, |
| "num_tokens": 11715201.0, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.1724137931034483, |
| "grad_norm": 0.050865691155195236, |
| "learning_rate": 3.465626902365717e-05, |
| "loss": 0.0148, |
| "mean_token_accuracy": 0.9945730566978455, |
| "num_tokens": 12117386.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.1781609195402299, |
| "grad_norm": 0.038052380084991455, |
| "learning_rate": 3.455502615928437e-05, |
| "loss": 0.0143, |
| "mean_token_accuracy": 0.9947114586830139, |
| "num_tokens": 12519849.0, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.1839080459770115, |
| "grad_norm": 0.045970458537340164, |
| "learning_rate": 3.4449358268766333e-05, |
| "loss": 0.0149, |
| "mean_token_accuracy": 0.9944195628166199, |
| "num_tokens": 12922528.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.1896551724137931, |
| "grad_norm": 0.03716587647795677, |
| "learning_rate": 3.433930356496882e-05, |
| "loss": 0.0141, |
| "mean_token_accuracy": 0.994634211063385, |
| "num_tokens": 13325018.0, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.19540229885057472, |
| "grad_norm": 0.039773862808942795, |
| "learning_rate": 3.422490184716862e-05, |
| "loss": 0.0135, |
| "mean_token_accuracy": 0.9949192404747009, |
| "num_tokens": 13729095.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.20114942528735633, |
| "grad_norm": 0.058626800775527954, |
| "learning_rate": 3.4106194486660854e-05, |
| "loss": 0.014, |
| "mean_token_accuracy": 0.9947888255119324, |
| "num_tokens": 14132517.0, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.20689655172413793, |
| "grad_norm": 0.04217752069234848, |
| "learning_rate": 3.398322441179785e-05, |
| "loss": 0.014, |
| "mean_token_accuracy": 0.9947295308113098, |
| "num_tokens": 14537265.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.21264367816091953, |
| "grad_norm": 0.029374336823821068, |
| "learning_rate": 3.385603609246481e-05, |
| "loss": 0.014, |
| "mean_token_accuracy": 0.9946742534637452, |
| "num_tokens": 14941978.0, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.21839080459770116, |
| "grad_norm": 0.043314963579177856, |
| "learning_rate": 3.372467552399816e-05, |
| "loss": 0.0141, |
| "mean_token_accuracy": 0.9947606563568115, |
| "num_tokens": 15345327.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.22413793103448276, |
| "grad_norm": 0.03939647227525711, |
| "learning_rate": 3.358919021055213e-05, |
| "loss": 0.0139, |
| "mean_token_accuracy": 0.9946980714797974, |
| "num_tokens": 15749804.0, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.22988505747126436, |
| "grad_norm": 0.02790178172290325, |
| "learning_rate": 3.3449629147919754e-05, |
| "loss": 0.0143, |
| "mean_token_accuracy": 0.9946450471878052, |
| "num_tokens": 16154369.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.23563218390804597, |
| "grad_norm": 0.051178909838199615, |
| "learning_rate": 3.330604280581446e-05, |
| "loss": 0.0138, |
| "mean_token_accuracy": 0.9946406483650208, |
| "num_tokens": 16558165.0, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.2413793103448276, |
| "grad_norm": 0.08488579094409943, |
| "learning_rate": 3.315848310961857e-05, |
| "loss": 0.014, |
| "mean_token_accuracy": 0.994620680809021, |
| "num_tokens": 16962046.0, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.2471264367816092, |
| "grad_norm": 0.06223829835653305, |
| "learning_rate": 3.3007003421605485e-05, |
| "loss": 0.0139, |
| "mean_token_accuracy": 0.9947610378265381, |
| "num_tokens": 17365830.0, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.25287356321839083, |
| "grad_norm": 0.04801960662007332, |
| "learning_rate": 3.285165852164214e-05, |
| "loss": 0.014, |
| "mean_token_accuracy": 0.9947750210762024, |
| "num_tokens": 17769736.0, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.25862068965517243, |
| "grad_norm": 0.06384305655956268, |
| "learning_rate": 3.2692504587378904e-05, |
| "loss": 0.0142, |
| "mean_token_accuracy": 0.9945329785346985, |
| "num_tokens": 18173470.0, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.26436781609195403, |
| "grad_norm": 0.041138093918561935, |
| "learning_rate": 3.252959917393394e-05, |
| "loss": 0.0138, |
| "mean_token_accuracy": 0.9946693658828736, |
| "num_tokens": 18577196.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.27011494252873564, |
| "grad_norm": 0.03739451244473457, |
| "learning_rate": 3.236300119307945e-05, |
| "loss": 0.0136, |
| "mean_token_accuracy": 0.9948052048683167, |
| "num_tokens": 18981159.0, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.27586206896551724, |
| "grad_norm": 0.03280220553278923, |
| "learning_rate": 3.219277089193731e-05, |
| "loss": 0.014, |
| "mean_token_accuracy": 0.9946678638458252, |
| "num_tokens": 19384054.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.28160919540229884, |
| "grad_norm": 0.032432641834020615, |
| "learning_rate": 3.201896983119178e-05, |
| "loss": 0.0141, |
| "mean_token_accuracy": 0.9946418523788452, |
| "num_tokens": 19786850.0, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.28735632183908044, |
| "grad_norm": 0.03479701280593872, |
| "learning_rate": 3.184166086282724e-05, |
| "loss": 0.0139, |
| "mean_token_accuracy": 0.9946959257125855, |
| "num_tokens": 20190209.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.29310344827586204, |
| "grad_norm": 0.04647434875369072, |
| "learning_rate": 3.166090810739887e-05, |
| "loss": 0.0135, |
| "mean_token_accuracy": 0.9949136853218079, |
| "num_tokens": 20593987.0, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.2988505747126437, |
| "grad_norm": 0.05208832398056984, |
| "learning_rate": 3.147677693084465e-05, |
| "loss": 0.0144, |
| "mean_token_accuracy": 0.9945999264717102, |
| "num_tokens": 20996490.0, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.3045977011494253, |
| "grad_norm": 0.027506856247782707, |
| "learning_rate": 3.128933392084697e-05, |
| "loss": 0.0138, |
| "mean_token_accuracy": 0.9948423385620118, |
| "num_tokens": 21400522.0, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.3103448275862069, |
| "grad_norm": 0.04659893363714218, |
| "learning_rate": 3.109864686275239e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9948711514472961, |
| "num_tokens": 21805437.0, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.3160919540229885, |
| "grad_norm": 0.03459516912698746, |
| "learning_rate": 3.0904784715058294e-05, |
| "loss": 0.0136, |
| "mean_token_accuracy": 0.9946945190429688, |
| "num_tokens": 22210298.0, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.3218390804597701, |
| "grad_norm": 0.04663790389895439, |
| "learning_rate": 3.0707817584475316e-05, |
| "loss": 0.0141, |
| "mean_token_accuracy": 0.9947023153305053, |
| "num_tokens": 22614052.0, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.3275862068965517, |
| "grad_norm": 0.0350983701646328, |
| "learning_rate": 3.0507816700574574e-05, |
| "loss": 0.0135, |
| "mean_token_accuracy": 0.9948037743568421, |
| "num_tokens": 23017388.0, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.041611939668655396, |
| "learning_rate": 3.030485439002871e-05, |
| "loss": 0.0138, |
| "mean_token_accuracy": 0.9947538614273072, |
| "num_tokens": 23421547.0, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.3390804597701149, |
| "grad_norm": 0.044495340436697006, |
| "learning_rate": 3.009900405045633e-05, |
| "loss": 0.0139, |
| "mean_token_accuracy": 0.9946321249008179, |
| "num_tokens": 23824441.0, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.3448275862068966, |
| "grad_norm": 0.0457838736474514, |
| "learning_rate": 2.989034012387908e-05, |
| "loss": 0.0136, |
| "mean_token_accuracy": 0.9946706891059875, |
| "num_tokens": 24228304.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.3505747126436782, |
| "grad_norm": 0.05629606544971466, |
| "learning_rate": 2.9678938069801016e-05, |
| "loss": 0.0129, |
| "mean_token_accuracy": 0.9949870824813842, |
| "num_tokens": 24633847.0, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.3563218390804598, |
| "grad_norm": 0.03772628307342529, |
| "learning_rate": 2.9464874337920103e-05, |
| "loss": 0.0137, |
| "mean_token_accuracy": 0.9947891712188721, |
| "num_tokens": 25037659.0, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.3620689655172414, |
| "grad_norm": 0.04441123828291893, |
| "learning_rate": 2.924822634048154e-05, |
| "loss": 0.0136, |
| "mean_token_accuracy": 0.9948173046112061, |
| "num_tokens": 25441857.0, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.367816091954023, |
| "grad_norm": 0.032479654997587204, |
| "learning_rate": 2.9029072424283028e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9949279308319092, |
| "num_tokens": 25847022.0, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.3735632183908046, |
| "grad_norm": 0.03903662785887718, |
| "learning_rate": 2.8807491842342106e-05, |
| "loss": 0.014, |
| "mean_token_accuracy": 0.9946053504943848, |
| "num_tokens": 26250421.0, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.3793103448275862, |
| "grad_norm": 0.03149571642279625, |
| "learning_rate": 2.858356472523572e-05, |
| "loss": 0.0137, |
| "mean_token_accuracy": 0.9947115182876587, |
| "num_tokens": 26653852.0, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.3850574712643678, |
| "grad_norm": 0.05093760043382645, |
| "learning_rate": 2.8357372052122475e-05, |
| "loss": 0.0137, |
| "mean_token_accuracy": 0.99478600025177, |
| "num_tokens": 27056647.0, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.39080459770114945, |
| "grad_norm": 0.04730261117219925, |
| "learning_rate": 2.8128995621458e-05, |
| "loss": 0.0135, |
| "mean_token_accuracy": 0.9948318123817443, |
| "num_tokens": 27460001.0, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.39655172413793105, |
| "grad_norm": 0.035402730107307434, |
| "learning_rate": 2.7898518021414006e-05, |
| "loss": 0.0135, |
| "mean_token_accuracy": 0.9948247194290161, |
| "num_tokens": 27864720.0, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.40229885057471265, |
| "grad_norm": 0.038121409714221954, |
| "learning_rate": 2.766602260001181e-05, |
| "loss": 0.014, |
| "mean_token_accuracy": 0.994686484336853, |
| "num_tokens": 28268488.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.40804597701149425, |
| "grad_norm": 0.04125091806054115, |
| "learning_rate": 2.7431593434981018e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9948553442955017, |
| "num_tokens": 28672697.0, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.41379310344827586, |
| "grad_norm": 0.03373762220144272, |
| "learning_rate": 2.719531530335436e-05, |
| "loss": 0.014, |
| "mean_token_accuracy": 0.994598388671875, |
| "num_tokens": 29076416.0, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.41954022988505746, |
| "grad_norm": 0.05404042452573776, |
| "learning_rate": 2.695727365080962e-05, |
| "loss": 0.0139, |
| "mean_token_accuracy": 0.9946176290512085, |
| "num_tokens": 29479332.0, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.42528735632183906, |
| "grad_norm": 0.040191181004047394, |
| "learning_rate": 2.671755456076977e-05, |
| "loss": 0.0137, |
| "mean_token_accuracy": 0.9947783350944519, |
| "num_tokens": 29883389.0, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.43103448275862066, |
| "grad_norm": 0.05008212476968765, |
| "learning_rate": 2.6476244723272458e-05, |
| "loss": 0.0141, |
| "mean_token_accuracy": 0.9946029782295227, |
| "num_tokens": 30287635.0, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.4367816091954023, |
| "grad_norm": 0.03571382537484169, |
| "learning_rate": 2.6233431403620137e-05, |
| "loss": 0.014, |
| "mean_token_accuracy": 0.99459388256073, |
| "num_tokens": 30691089.0, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.4425287356321839, |
| "grad_norm": 0.03077247366309166, |
| "learning_rate": 2.598920241082219e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9948281884193421, |
| "num_tokens": 31095704.0, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.4482758620689655, |
| "grad_norm": 0.02985704317688942, |
| "learning_rate": 2.5743646065840346e-05, |
| "loss": 0.0136, |
| "mean_token_accuracy": 0.9947766423225403, |
| "num_tokens": 31499708.0, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.4540229885057471, |
| "grad_norm": 0.03301994130015373, |
| "learning_rate": 2.549685116964907e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9949437975883484, |
| "num_tokens": 31904187.0, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.45977011494252873, |
| "grad_norm": 0.04135014861822128, |
| "learning_rate": 2.5248906971122276e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9948192358016967, |
| "num_tokens": 32307081.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.46551724137931033, |
| "grad_norm": 0.05234241113066673, |
| "learning_rate": 2.4999903134758113e-05, |
| "loss": 0.0135, |
| "mean_token_accuracy": 0.9947088360786438, |
| "num_tokens": 32712091.0, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.47126436781609193, |
| "grad_norm": 0.03200434520840645, |
| "learning_rate": 2.4749929708253427e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9949337005615234, |
| "num_tokens": 33115832.0, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.47701149425287354, |
| "grad_norm": 0.025907520204782486, |
| "learning_rate": 2.4499077089939677e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9948367953300477, |
| "num_tokens": 33520665.0, |
| "step": 415 |
| }, |
| { |
| "epoch": 0.4827586206896552, |
| "grad_norm": 0.026905179023742676, |
| "learning_rate": 2.4247435996091983e-05, |
| "loss": 0.0135, |
| "mean_token_accuracy": 0.9948036670684814, |
| "num_tokens": 33924164.0, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.4885057471264368, |
| "grad_norm": 0.0450819693505764, |
| "learning_rate": 2.3995097428123274e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9949346303939819, |
| "num_tokens": 34329060.0, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.4942528735632184, |
| "grad_norm": 0.0394849069416523, |
| "learning_rate": 2.3742152639675284e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9948944926261902, |
| "num_tokens": 34733190.0, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.02788865938782692, |
| "learning_rate": 2.3488693103618318e-05, |
| "loss": 0.013, |
| "mean_token_accuracy": 0.9949518084526062, |
| "num_tokens": 35137740.0, |
| "step": 435 |
| }, |
| { |
| "epoch": 0.5057471264367817, |
| "grad_norm": 0.03805901110172272, |
| "learning_rate": 2.3234810478971772e-05, |
| "loss": 0.0136, |
| "mean_token_accuracy": 0.994696569442749, |
| "num_tokens": 35542288.0, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.5114942528735632, |
| "grad_norm": 0.032415661960840225, |
| "learning_rate": 2.2980596577757305e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9947757482528686, |
| "num_tokens": 35946058.0, |
| "step": 445 |
| }, |
| { |
| "epoch": 0.5172413793103449, |
| "grad_norm": 0.053135160356760025, |
| "learning_rate": 2.2726143331796738e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9948907971382142, |
| "num_tokens": 36349724.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.5229885057471264, |
| "grad_norm": 0.03707072511315346, |
| "learning_rate": 2.247154275946651e-05, |
| "loss": 0.0137, |
| "mean_token_accuracy": 0.9947781324386596, |
| "num_tokens": 36752494.0, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.5287356321839081, |
| "grad_norm": 0.032205525785684586, |
| "learning_rate": 2.2216886932420993e-05, |
| "loss": 0.0139, |
| "mean_token_accuracy": 0.9945814847946167, |
| "num_tokens": 37156356.0, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.5344827586206896, |
| "grad_norm": 0.0344030000269413, |
| "learning_rate": 2.19622679422964e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9949215650558472, |
| "num_tokens": 37560139.0, |
| "step": 465 |
| }, |
| { |
| "epoch": 0.5402298850574713, |
| "grad_norm": 0.024279696866869926, |
| "learning_rate": 2.170777786740754e-05, |
| "loss": 0.0138, |
| "mean_token_accuracy": 0.9947062373161316, |
| "num_tokens": 37965641.0, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.5459770114942529, |
| "grad_norm": 0.030384989455342293, |
| "learning_rate": 2.14535087394494e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9948716759681702, |
| "num_tokens": 38369757.0, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.5517241379310345, |
| "grad_norm": 0.04183518514037132, |
| "learning_rate": 2.1199552510215515e-05, |
| "loss": 0.0136, |
| "mean_token_accuracy": 0.9947738170623779, |
| "num_tokens": 38772941.0, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.5574712643678161, |
| "grad_norm": 0.03046581894159317, |
| "learning_rate": 2.0946001018345306e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9949072957038879, |
| "num_tokens": 39178203.0, |
| "step": 485 |
| }, |
| { |
| "epoch": 0.5632183908045977, |
| "grad_norm": 0.09169202297925949, |
| "learning_rate": 2.0692945956112318e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9949472784996033, |
| "num_tokens": 39581967.0, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.5689655172413793, |
| "grad_norm": 0.029076358303427696, |
| "learning_rate": 2.0440478836265358e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9948386192321778, |
| "num_tokens": 39984021.0, |
| "step": 495 |
| }, |
| { |
| "epoch": 0.5747126436781609, |
| "grad_norm": 0.05347994714975357, |
| "learning_rate": 2.0188690958934603e-05, |
| "loss": 0.0136, |
| "mean_token_accuracy": 0.9947713971138, |
| "num_tokens": 40387785.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5804597701149425, |
| "grad_norm": 0.023038016632199287, |
| "learning_rate": 1.993767337861455e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9948361039161682, |
| "num_tokens": 40791443.0, |
| "step": 505 |
| }, |
| { |
| "epoch": 0.5862068965517241, |
| "grad_norm": 0.03382337838411331, |
| "learning_rate": 1.9687516871235824e-05, |
| "loss": 0.0136, |
| "mean_token_accuracy": 0.9947430968284607, |
| "num_tokens": 41194964.0, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.5919540229885057, |
| "grad_norm": 0.03841397538781166, |
| "learning_rate": 1.9438311901337744e-05, |
| "loss": 0.0139, |
| "mean_token_accuracy": 0.9947336792945862, |
| "num_tokens": 41599118.0, |
| "step": 515 |
| }, |
| { |
| "epoch": 0.5977011494252874, |
| "grad_norm": 0.03508458286523819, |
| "learning_rate": 1.9190148589353425e-05, |
| "loss": 0.0138, |
| "mean_token_accuracy": 0.9947627902030944, |
| "num_tokens": 42001873.0, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.603448275862069, |
| "grad_norm": 0.0344594344496727, |
| "learning_rate": 1.8943116679019407e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9947917938232422, |
| "num_tokens": 42405413.0, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.6091954022988506, |
| "grad_norm": 0.024883072823286057, |
| "learning_rate": 1.869730550492144e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9948460817337036, |
| "num_tokens": 42809113.0, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.6149425287356322, |
| "grad_norm": 0.03987499698996544, |
| "learning_rate": 1.8452803960188304e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9949107050895691, |
| "num_tokens": 43213404.0, |
| "step": 535 |
| }, |
| { |
| "epoch": 0.6206896551724138, |
| "grad_norm": 0.04916604235768318, |
| "learning_rate": 1.8209700464345162e-05, |
| "loss": 0.013, |
| "mean_token_accuracy": 0.9949909687042237, |
| "num_tokens": 43616989.0, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.6264367816091954, |
| "grad_norm": 0.025707852095365524, |
| "learning_rate": 1.796808293133832e-05, |
| "loss": 0.0131, |
| "mean_token_accuracy": 0.9949591755867004, |
| "num_tokens": 44020557.0, |
| "step": 545 |
| }, |
| { |
| "epoch": 0.632183908045977, |
| "grad_norm": 0.03211604803800583, |
| "learning_rate": 1.7728038737742696e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9948301553726197, |
| "num_tokens": 44424704.0, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.6379310344827587, |
| "grad_norm": 0.03153684735298157, |
| "learning_rate": 1.748965469116373e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9949110507965088, |
| "num_tokens": 44828304.0, |
| "step": 555 |
| }, |
| { |
| "epoch": 0.6436781609195402, |
| "grad_norm": 0.044283442199230194, |
| "learning_rate": 1.7253016998844934e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.994849705696106, |
| "num_tokens": 45231864.0, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.6494252873563219, |
| "grad_norm": 0.03939127177000046, |
| "learning_rate": 1.7018211236492662e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9948228478431702, |
| "num_tokens": 45636143.0, |
| "step": 565 |
| }, |
| { |
| "epoch": 0.6551724137931034, |
| "grad_norm": 0.02582518756389618, |
| "learning_rate": 1.678532231732921e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9948286533355712, |
| "num_tokens": 46041434.0, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.6609195402298851, |
| "grad_norm": 0.03828392177820206, |
| "learning_rate": 1.655443446138546e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9949392199516296, |
| "num_tokens": 46445765.0, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.026919830590486526, |
| "learning_rate": 1.632563116504431e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9947931051254273, |
| "num_tokens": 46850075.0, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.6724137931034483, |
| "grad_norm": 0.031082892790436745, |
| "learning_rate": 1.6098995170845647e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.99483882188797, |
| "num_tokens": 47254907.0, |
| "step": 585 |
| }, |
| { |
| "epoch": 0.6781609195402298, |
| "grad_norm": 0.0375247485935688, |
| "learning_rate": 1.5874608437564096e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9948214530944824, |
| "num_tokens": 47659312.0, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.6839080459770115, |
| "grad_norm": 0.0356401652097702, |
| "learning_rate": 1.565255211057006e-05, |
| "loss": 0.013, |
| "mean_token_accuracy": 0.9949233651161193, |
| "num_tokens": 48062760.0, |
| "step": 595 |
| }, |
| { |
| "epoch": 0.6896551724137931, |
| "grad_norm": 0.046727504581213, |
| "learning_rate": 1.5432906492485005e-05, |
| "loss": 0.0131, |
| "mean_token_accuracy": 0.9949892401695252, |
| "num_tokens": 48466976.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.6954022988505747, |
| "grad_norm": 0.056539956480264664, |
| "learning_rate": 1.52157510141415e-05, |
| "loss": 0.0131, |
| "mean_token_accuracy": 0.9949196696281433, |
| "num_tokens": 48870906.0, |
| "step": 605 |
| }, |
| { |
| "epoch": 0.7011494252873564, |
| "grad_norm": 0.049220457673072815, |
| "learning_rate": 1.5001164205858465e-05, |
| "loss": 0.0131, |
| "mean_token_accuracy": 0.994917893409729, |
| "num_tokens": 49275039.0, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.7068965517241379, |
| "grad_norm": 0.04120581969618797, |
| "learning_rate": 1.4789223669042143e-05, |
| "loss": 0.0128, |
| "mean_token_accuracy": 0.994994330406189, |
| "num_tokens": 49678668.0, |
| "step": 615 |
| }, |
| { |
| "epoch": 0.7126436781609196, |
| "grad_norm": 0.02625158056616783, |
| "learning_rate": 1.4580006048122943e-05, |
| "loss": 0.0128, |
| "mean_token_accuracy": 0.9949682116508484, |
| "num_tokens": 50083729.0, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.7183908045977011, |
| "grad_norm": 0.05274219810962677, |
| "learning_rate": 1.43735870028384e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9948260664939881, |
| "num_tokens": 50488215.0, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.7241379310344828, |
| "grad_norm": 0.03466196358203888, |
| "learning_rate": 1.4170041180872212e-05, |
| "loss": 0.013, |
| "mean_token_accuracy": 0.9949446439743042, |
| "num_tokens": 50892168.0, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.7298850574712644, |
| "grad_norm": 0.03565268591046333, |
| "learning_rate": 1.3969442190859236e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9947892189025879, |
| "num_tokens": 51296446.0, |
| "step": 635 |
| }, |
| { |
| "epoch": 0.735632183908046, |
| "grad_norm": 0.03092004917562008, |
| "learning_rate": 1.3771862575766306e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9949315309524536, |
| "num_tokens": 51699117.0, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.7413793103448276, |
| "grad_norm": 0.05381985753774643, |
| "learning_rate": 1.3577373786658359e-05, |
| "loss": 0.013, |
| "mean_token_accuracy": 0.995068883895874, |
| "num_tokens": 52103973.0, |
| "step": 645 |
| }, |
| { |
| "epoch": 0.7471264367816092, |
| "grad_norm": 0.03023788332939148, |
| "learning_rate": 1.33860461568595e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9947940468788147, |
| "num_tokens": 52507158.0, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.7528735632183908, |
| "grad_norm": 0.04271196573972702, |
| "learning_rate": 1.3197948876518184e-05, |
| "loss": 0.0128, |
| "mean_token_accuracy": 0.9950397610664368, |
| "num_tokens": 52910307.0, |
| "step": 655 |
| }, |
| { |
| "epoch": 0.7586206896551724, |
| "grad_norm": 0.03678242862224579, |
| "learning_rate": 1.301314996758591e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9949288129806518, |
| "num_tokens": 53313505.0, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.764367816091954, |
| "grad_norm": 0.024950511753559113, |
| "learning_rate": 1.283171625921829e-05, |
| "loss": 0.0131, |
| "mean_token_accuracy": 0.994904899597168, |
| "num_tokens": 53718020.0, |
| "step": 665 |
| }, |
| { |
| "epoch": 0.7701149425287356, |
| "grad_norm": 0.0270620696246624, |
| "learning_rate": 1.2653713363607528e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9948266863822937, |
| "num_tokens": 54119480.0, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.7758620689655172, |
| "grad_norm": 0.027166401967406273, |
| "learning_rate": 1.2479205652254954e-05, |
| "loss": 0.0129, |
| "mean_token_accuracy": 0.9950602531433106, |
| "num_tokens": 54523011.0, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.7816091954022989, |
| "grad_norm": 0.037310510873794556, |
| "learning_rate": 1.2308256232692228e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9948535680770874, |
| "num_tokens": 54926247.0, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.7873563218390804, |
| "grad_norm": 0.030097058042883873, |
| "learning_rate": 1.2140926925659696e-05, |
| "loss": 0.013, |
| "mean_token_accuracy": 0.9949084520339966, |
| "num_tokens": 55329313.0, |
| "step": 685 |
| }, |
| { |
| "epoch": 0.7931034482758621, |
| "grad_norm": 0.031420208513736725, |
| "learning_rate": 1.1977278242749991e-05, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9948212742805481, |
| "num_tokens": 55732944.0, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.7988505747126436, |
| "grad_norm": 0.04165807366371155, |
| "learning_rate": 1.1817369364525179e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9948533535003662, |
| "num_tokens": 56137191.0, |
| "step": 695 |
| }, |
| { |
| "epoch": 0.8045977011494253, |
| "grad_norm": 0.04301629588007927, |
| "learning_rate": 1.1661258119115136e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9947885513305664, |
| "num_tokens": 56540742.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.8103448275862069, |
| "grad_norm": 0.030160659924149513, |
| "learning_rate": 1.1509000961305077e-05, |
| "loss": 0.0128, |
| "mean_token_accuracy": 0.9950136542320251, |
| "num_tokens": 56944001.0, |
| "step": 705 |
| }, |
| { |
| "epoch": 0.8160919540229885, |
| "grad_norm": 0.03499389439821243, |
| "learning_rate": 1.1360652952119732e-05, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9947500705718995, |
| "num_tokens": 57348147.0, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.8218390804597702, |
| "grad_norm": 0.024081142619252205, |
| "learning_rate": 1.1216267738911505e-05, |
| "loss": 0.0135, |
| "mean_token_accuracy": 0.9946637511253357, |
| "num_tokens": 57751838.0, |
| "step": 715 |
| }, |
| { |
| "epoch": 0.8275862068965517, |
| "grad_norm": 0.027669720351696014, |
| "learning_rate": 1.1075897535959896e-05, |
| "loss": 0.0129, |
| "mean_token_accuracy": 0.9950794219970703, |
| "num_tokens": 58155972.0, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 0.030040688812732697, |
| "learning_rate": 1.0939593105589159e-05, |
| "loss": 0.0125, |
| "mean_token_accuracy": 0.9951125979423523, |
| "num_tokens": 58561406.0, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.8390804597701149, |
| "grad_norm": 0.0329650342464447, |
| "learning_rate": 1.0807403739811037e-05, |
| "loss": 0.013, |
| "mean_token_accuracy": 0.994926369190216, |
| "num_tokens": 58964866.0, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.8448275862068966, |
| "grad_norm": 0.024679485708475113, |
| "learning_rate": 1.0679377242499197e-05, |
| "loss": 0.0125, |
| "mean_token_accuracy": 0.9951718211174011, |
| "num_tokens": 59368847.0, |
| "step": 735 |
| }, |
| { |
| "epoch": 0.8505747126436781, |
| "grad_norm": 0.06430592387914658, |
| "learning_rate": 1.0555559912101832e-05, |
| "loss": 0.013, |
| "mean_token_accuracy": 0.9949762463569641, |
| "num_tokens": 59772552.0, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.8563218390804598, |
| "grad_norm": 0.028835134580731392, |
| "learning_rate": 1.043599652489869e-05, |
| "loss": 0.0131, |
| "mean_token_accuracy": 0.9949678659439087, |
| "num_tokens": 60176799.0, |
| "step": 745 |
| }, |
| { |
| "epoch": 0.8620689655172413, |
| "grad_norm": 0.026038020849227905, |
| "learning_rate": 1.0320730318808507e-05, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9948094844818115, |
| "num_tokens": 60581056.0, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.867816091954023, |
| "grad_norm": 0.02826244942843914, |
| "learning_rate": 1.0209802977752852e-05, |
| "loss": 0.0131, |
| "mean_token_accuracy": 0.9948521971702575, |
| "num_tokens": 60985012.0, |
| "step": 755 |
| }, |
| { |
| "epoch": 0.8735632183908046, |
| "grad_norm": 0.037073444575071335, |
| "learning_rate": 1.0103254616581863e-05, |
| "loss": 0.0129, |
| "mean_token_accuracy": 0.9949637532234192, |
| "num_tokens": 61388779.0, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.8793103448275862, |
| "grad_norm": 0.032884031534194946, |
| "learning_rate": 1.0001123766567458e-05, |
| "loss": 0.0131, |
| "mean_token_accuracy": 0.9949699401855469, |
| "num_tokens": 61793039.0, |
| "step": 765 |
| }, |
| { |
| "epoch": 0.8850574712643678, |
| "grad_norm": 0.03468252718448639, |
| "learning_rate": 9.90344736146919e-06, |
| "loss": 0.0131, |
| "mean_token_accuracy": 0.9949258089065551, |
| "num_tokens": 62196261.0, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.8908045977011494, |
| "grad_norm": 0.024934224784374237, |
| "learning_rate": 9.810260724177834e-06, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9948127031326294, |
| "num_tokens": 62599709.0, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.896551724137931, |
| "grad_norm": 0.03356098756194115, |
| "learning_rate": 9.721597553941526e-06, |
| "loss": 0.0128, |
| "mean_token_accuracy": 0.9949464678764344, |
| "num_tokens": 63004030.0, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.9022988505747126, |
| "grad_norm": 0.038369644433259964, |
| "learning_rate": 9.637489914179006e-06, |
| "loss": 0.0129, |
| "mean_token_accuracy": 0.9949608087539673, |
| "num_tokens": 63408554.0, |
| "step": 785 |
| }, |
| { |
| "epoch": 0.9080459770114943, |
| "grad_norm": 0.03118038922548294, |
| "learning_rate": 9.557968220884502e-06, |
| "loss": 0.0134, |
| "mean_token_accuracy": 0.9947882890701294, |
| "num_tokens": 63811332.0, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.9137931034482759, |
| "grad_norm": 0.036854732781648636, |
| "learning_rate": 9.483061231628312e-06, |
| "loss": 0.013, |
| "mean_token_accuracy": 0.9949264883995056, |
| "num_tokens": 64214657.0, |
| "step": 795 |
| }, |
| { |
| "epoch": 0.9195402298850575, |
| "grad_norm": 0.04122990742325783, |
| "learning_rate": 9.412796035157183e-06, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9948729038238525, |
| "num_tokens": 64617148.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.9252873563218391, |
| "grad_norm": 0.05959238111972809, |
| "learning_rate": 9.347198041598134e-06, |
| "loss": 0.0129, |
| "mean_token_accuracy": 0.9949862718582153, |
| "num_tokens": 65022073.0, |
| "step": 805 |
| }, |
| { |
| "epoch": 0.9310344827586207, |
| "grad_norm": 0.03828701004385948, |
| "learning_rate": 9.286290973269366e-06, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9947553157806397, |
| "num_tokens": 65425185.0, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.9367816091954023, |
| "grad_norm": 0.03720645606517792, |
| "learning_rate": 9.230096856101493e-06, |
| "loss": 0.0126, |
| "mean_token_accuracy": 0.9950950860977172, |
| "num_tokens": 65827745.0, |
| "step": 815 |
| }, |
| { |
| "epoch": 0.9425287356321839, |
| "grad_norm": 0.028984155505895615, |
| "learning_rate": 9.178636011672301e-06, |
| "loss": 0.013, |
| "mean_token_accuracy": 0.9948612570762634, |
| "num_tokens": 66231352.0, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.9482758620689655, |
| "grad_norm": 0.029562933370471, |
| "learning_rate": 9.131927049857791e-06, |
| "loss": 0.0129, |
| "mean_token_accuracy": 0.9949148774147034, |
| "num_tokens": 66634894.0, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.9540229885057471, |
| "grad_norm": 0.03893503174185753, |
| "learning_rate": 9.089986862102262e-06, |
| "loss": 0.0129, |
| "mean_token_accuracy": 0.994910728931427, |
| "num_tokens": 67038555.0, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.9597701149425287, |
| "grad_norm": 0.025236055254936218, |
| "learning_rate": 9.052830615309845e-06, |
| "loss": 0.0127, |
| "mean_token_accuracy": 0.994949197769165, |
| "num_tokens": 67441898.0, |
| "step": 835 |
| }, |
| { |
| "epoch": 0.9655172413793104, |
| "grad_norm": 0.040895842015743256, |
| "learning_rate": 9.020471746359651e-06, |
| "loss": 0.0133, |
| "mean_token_accuracy": 0.9949271559715271, |
| "num_tokens": 67845282.0, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.9712643678160919, |
| "grad_norm": 0.030874410644173622, |
| "learning_rate": 8.992921957246571e-06, |
| "loss": 0.0135, |
| "mean_token_accuracy": 0.9948145151138306, |
| "num_tokens": 68248415.0, |
| "step": 845 |
| }, |
| { |
| "epoch": 0.9770114942528736, |
| "grad_norm": 0.02959192916750908, |
| "learning_rate": 8.970191210849467e-06, |
| "loss": 0.0132, |
| "mean_token_accuracy": 0.9948099732398987, |
| "num_tokens": 68652350.0, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.9827586206896551, |
| "grad_norm": 0.022801557555794716, |
| "learning_rate": 8.952287727328286e-06, |
| "loss": 0.0127, |
| "mean_token_accuracy": 0.995022428035736, |
| "num_tokens": 69057474.0, |
| "step": 855 |
| }, |
| { |
| "epoch": 0.9885057471264368, |
| "grad_norm": 0.02625376358628273, |
| "learning_rate": 8.939217981151367e-06, |
| "loss": 0.0131, |
| "mean_token_accuracy": 0.9948750615119935, |
| "num_tokens": 69460959.0, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.9942528735632183, |
| "grad_norm": 0.027628207579255104, |
| "learning_rate": 8.930986698754095e-06, |
| "loss": 0.0126, |
| "mean_token_accuracy": 0.9950263857841491, |
| "num_tokens": 69864907.0, |
| "step": 865 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 870, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.641453571692036e+18, |
| "train_batch_size": 20, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
