{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0574669187145558,
  "eval_steps": 50,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.442822265625,
      "epoch": 0.015122873345935728,
      "grad_norm": 2.669071628071661,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.5928983211517334,
      "mean_token_accuracy": 0.8548422813415527,
      "num_tokens": 325432.0,
      "step": 5
    },
    {
      "entropy": 0.3935546875,
      "epoch": 0.030245746691871456,
      "grad_norm": 1.634140660130009,
      "learning_rate": 6e-06,
      "loss": 0.3988723993301392,
      "mean_token_accuracy": 0.8959574371576309,
      "num_tokens": 653193.0,
      "step": 10
    },
    {
      "entropy": 0.2187255859375,
      "epoch": 0.045368620037807186,
      "grad_norm": 0.9021532274129692,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.19831626415252684,
      "mean_token_accuracy": 0.9389900401234627,
      "num_tokens": 964453.0,
      "step": 15
    },
    {
      "entropy": 0.10172119140625,
      "epoch": 0.06049149338374291,
      "grad_norm": 0.4697352375821627,
      "learning_rate": 1.2666666666666667e-05,
      "loss": 0.10886554718017578,
      "mean_token_accuracy": 0.9637670248746872,
      "num_tokens": 1307238.0,
      "step": 20
    },
    {
      "entropy": 0.078204345703125,
      "epoch": 0.07561436672967864,
      "grad_norm": 0.39345906256866536,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0776131808757782,
      "mean_token_accuracy": 0.9740302637219429,
      "num_tokens": 1615672.0,
      "step": 25
    },
    {
      "entropy": 0.05927734375,
      "epoch": 0.09073724007561437,
      "grad_norm": 0.35679792282054484,
      "learning_rate": 1.9333333333333333e-05,
      "loss": 0.06322811841964722,
      "mean_token_accuracy": 0.9787174344062806,
      "num_tokens": 1935122.0,
      "step": 30
    },
    {
      "entropy": 0.055340576171875,
      "epoch": 0.10586011342155009,
      "grad_norm": 0.28127188289574473,
      "learning_rate": 1.99991486051959e-05,
      "loss": 0.055406326055526735,
      "mean_token_accuracy": 0.9811019197106361,
      "num_tokens": 2246001.0,
      "step": 35
    },
    {
      "entropy": 0.050018310546875,
      "epoch": 0.12098298676748583,
      "grad_norm": 0.23485165839069644,
      "learning_rate": 1.9995690062269985e-05,
      "loss": 0.05159962177276611,
      "mean_token_accuracy": 0.9823019146919251,
      "num_tokens": 2572728.0,
      "step": 40
    },
    {
      "entropy": 0.05009765625,
      "epoch": 0.13610586011342155,
      "grad_norm": 0.3286661753766386,
      "learning_rate": 1.9989572078514722e-05,
      "loss": 0.04924889206886292,
      "mean_token_accuracy": 0.983111384510994,
      "num_tokens": 2899222.0,
      "step": 45
    },
    {
      "entropy": 0.03935394287109375,
      "epoch": 0.15122873345935728,
      "grad_norm": 0.250685968179852,
      "learning_rate": 1.998079628167323e-05,
      "loss": 0.041659212112426756,
      "mean_token_accuracy": 0.9857470989227295,
      "num_tokens": 3199913.0,
      "step": 50
    },
    {
      "epoch": 0.15122873345935728,
      "eval_entropy": 0.040476572764170424,
      "eval_loss": 0.0391058586537838,
      "eval_mean_token_accuracy": 0.986595441092242,
      "eval_num_tokens": 3199913.0,
      "eval_runtime": 94.4655,
      "eval_samples_per_second": 14.069,
      "eval_steps_per_second": 3.525,
      "step": 50
    },
    {
      "entropy": 0.038671875,
      "epoch": 0.166351606805293,
      "grad_norm": 0.3054203398912923,
      "learning_rate": 1.9969365006623072e-05,
      "loss": 0.03826351165771484,
      "mean_token_accuracy": 0.9868962660431861,
      "num_tokens": 3519539.0,
      "step": 55
    },
    {
      "entropy": 0.035321044921875,
      "epoch": 0.18147448015122875,
      "grad_norm": 0.3848999837215887,
      "learning_rate": 1.9955281294755034e-05,
      "loss": 0.03624363541603089,
      "mean_token_accuracy": 0.9876649409532547,
      "num_tokens": 3846310.0,
      "step": 60
    },
    {
      "entropy": 0.035552978515625,
      "epoch": 0.19659735349716445,
      "grad_norm": 0.2606280391924725,
      "learning_rate": 1.9938548893163924e-05,
      "loss": 0.03628517687320709,
      "mean_token_accuracy": 0.9875744208693504,
      "num_tokens": 4173916.0,
      "step": 65
    },
    {
      "entropy": 0.0336944580078125,
      "epoch": 0.21172022684310018,
      "grad_norm": 0.24422090914230693,
      "learning_rate": 1.9919172253651637e-05,
      "loss": 0.033189314603805545,
      "mean_token_accuracy": 0.9885250389575958,
      "num_tokens": 4494452.0,
      "step": 70
    },
    {
      "entropy": 0.02899322509765625,
      "epoch": 0.22684310018903592,
      "grad_norm": 0.19378251727544818,
      "learning_rate": 1.9897156531542708e-05,
      "loss": 0.029927724599838258,
      "mean_token_accuracy": 0.9899556040763855,
      "num_tokens": 4813996.0,
      "step": 75
    },
    {
      "entropy": 0.0284515380859375,
      "epoch": 0.24196597353497165,
      "grad_norm": 0.2664077757245733,
      "learning_rate": 1.98725075843127e-05,
      "loss": 0.029463762044906618,
      "mean_token_accuracy": 0.9898741751909256,
      "num_tokens": 5154020.0,
      "step": 80
    },
    {
      "entropy": 0.0311767578125,
      "epoch": 0.2570888468809074,
      "grad_norm": 0.22537314543102535,
      "learning_rate": 1.9845231970029774e-05,
      "loss": 0.03209342658519745,
      "mean_token_accuracy": 0.9891638234257698,
      "num_tokens": 5484973.0,
      "step": 85
    },
    {
      "entropy": 0.0276885986328125,
      "epoch": 0.2722117202268431,
      "grad_norm": 0.2077524527319594,
      "learning_rate": 1.9815336945609834e-05,
      "loss": 0.029284730553627014,
      "mean_token_accuracy": 0.9901994511485099,
      "num_tokens": 5811817.0,
      "step": 90
    },
    {
      "entropy": 0.0260345458984375,
      "epoch": 0.28733459357277885,
      "grad_norm": 0.31080264218901027,
      "learning_rate": 1.9782830464885788e-05,
      "loss": 0.02565096616744995,
      "mean_token_accuracy": 0.991170009970665,
      "num_tokens": 6118979.0,
      "step": 95
    },
    {
      "entropy": 0.024970245361328126,
      "epoch": 0.30245746691871456,
      "grad_norm": 0.21180271207392207,
      "learning_rate": 1.974772117649135e-05,
      "loss": 0.024624763429164885,
      "mean_token_accuracy": 0.9913630470633507,
      "num_tokens": 6457003.0,
      "step": 100
    },
    {
      "epoch": 0.30245746691871456,
      "eval_entropy": 0.02398535009618994,
      "eval_loss": 0.025832440704107285,
      "eval_mean_token_accuracy": 0.9910635029947436,
      "eval_num_tokens": 6457003.0,
      "eval_runtime": 92.826,
      "eval_samples_per_second": 14.317,
      "eval_steps_per_second": 3.587,
      "step": 100
    },
    {
      "entropy": 0.0255767822265625,
      "epoch": 0.31758034026465026,
      "grad_norm": 0.19039718090172789,
      "learning_rate": 1.9710018421559995e-05,
      "loss": 0.026742279529571533,
      "mean_token_accuracy": 0.9909975379705429,
      "num_tokens": 6768352.0,
      "step": 105
    },
    {
      "entropy": 0.02334747314453125,
      "epoch": 0.332703213610586,
      "grad_norm": 0.15632220147486883,
      "learning_rate": 1.966973223123967e-05,
      "loss": 0.021733593940734864,
      "mean_token_accuracy": 0.9925331950187684,
      "num_tokens": 7086098.0,
      "step": 110
    },
    {
      "entropy": 0.02210235595703125,
      "epoch": 0.34782608695652173,
      "grad_norm": 0.2458450644732953,
      "learning_rate": 1.9626873324023915e-05,
      "loss": 0.02539382576942444,
      "mean_token_accuracy": 0.9917543068528175,
      "num_tokens": 7397835.0,
      "step": 115
    },
    {
      "entropy": 0.022796630859375,
      "epoch": 0.3629489603024575,
      "grad_norm": 0.511944627378666,
      "learning_rate": 1.9581453102900127e-05,
      "loss": 0.022371816635131835,
      "mean_token_accuracy": 0.9924163356423378,
      "num_tokens": 7720248.0,
      "step": 120
    },
    {
      "entropy": 0.02347259521484375,
      "epoch": 0.3780718336483932,
      "grad_norm": 0.22819135667809418,
      "learning_rate": 1.953348365231568e-05,
      "loss": 0.02383442670106888,
      "mean_token_accuracy": 0.9916202604770661,
      "num_tokens": 8046850.0,
      "step": 125
    },
    {
      "entropy": 0.02361907958984375,
      "epoch": 0.3931947069943289,
      "grad_norm": 0.23351254559117343,
      "learning_rate": 1.9482977734962753e-05,
      "loss": 0.0238445445895195,
      "mean_token_accuracy": 0.9918097272515297,
      "num_tokens": 8390721.0,
      "step": 130
    },
    {
      "entropy": 0.0227020263671875,
      "epoch": 0.40831758034026466,
      "grad_norm": 0.18760418206446414,
      "learning_rate": 1.9429948788382726e-05,
      "loss": 0.022852468490600585,
      "mean_token_accuracy": 0.9926092982292175,
      "num_tokens": 8741140.0,
      "step": 135
    },
    {
      "entropy": 0.02464141845703125,
      "epoch": 0.42344045368620037,
      "grad_norm": 0.17532160128342728,
      "learning_rate": 1.937441092139097e-05,
      "loss": 0.025189298391342162,
      "mean_token_accuracy": 0.9915472865104675,
      "num_tokens": 9066217.0,
      "step": 140
    },
    {
      "entropy": 0.022135162353515626,
      "epoch": 0.43856332703213613,
      "grad_norm": 0.2898150379760738,
      "learning_rate": 1.93163789103231e-05,
      "loss": 0.02323928475379944,
      "mean_token_accuracy": 0.9923686638474465,
      "num_tokens": 9398518.0,
      "step": 145
    },
    {
      "entropy": 0.022913360595703126,
      "epoch": 0.45368620037807184,
      "grad_norm": 0.20882908714005557,
      "learning_rate": 1.9255868195103596e-05,
      "loss": 0.023580947518348695,
      "mean_token_accuracy": 0.9922584399580956,
      "num_tokens": 9722146.0,
      "step": 150
    },
    {
      "epoch": 0.45368620037807184,
      "eval_entropy": 0.019961612002627627,
      "eval_loss": 0.021232564002275467,
      "eval_mean_token_accuracy": 0.9926312886200868,
      "eval_num_tokens": 9722146.0,
      "eval_runtime": 92.911,
      "eval_samples_per_second": 14.304,
      "eval_steps_per_second": 3.584,
      "step": 150
    },
    {
      "entropy": 0.02125396728515625,
      "epoch": 0.46880907372400754,
      "grad_norm": 0.16611123987930837,
      "learning_rate": 1.9192894875137864e-05,
      "loss": 0.022398817539215087,
      "mean_token_accuracy": 0.9927845776081086,
      "num_tokens": 10051130.0,
      "step": 155
    },
    {
      "entropy": 0.01784820556640625,
      "epoch": 0.4839319470699433,
      "grad_norm": 0.1705996270647505,
      "learning_rate": 1.9127475705028864e-05,
      "loss": 0.020223259925842285,
      "mean_token_accuracy": 0.9935442849993705,
      "num_tokens": 10364936.0,
      "step": 160
    },
    {
      "entropy": 0.02181854248046875,
      "epoch": 0.499054820415879,
      "grad_norm": 0.18993585672995894,
      "learning_rate": 1.9059628090119392e-05,
      "loss": 0.02131263315677643,
      "mean_token_accuracy": 0.9929479479789733,
      "num_tokens": 10684934.0,
      "step": 165
    },
    {
      "entropy": 0.01970977783203125,
      "epoch": 0.5141776937618148,
      "grad_norm": 0.23862681974692412,
      "learning_rate": 1.898937008186123e-05,
      "loss": 0.021003079414367676,
      "mean_token_accuracy": 0.992812205851078,
      "num_tokens": 11016640.0,
      "step": 170
    },
    {
      "entropy": 0.02065277099609375,
      "epoch": 0.5293005671077504,
      "grad_norm": 0.22580792158388535,
      "learning_rate": 1.8916720373012425e-05,
      "loss": 0.020279140770435335,
      "mean_token_accuracy": 0.9934262841939926,
      "num_tokens": 11335375.0,
      "step": 175
    },
    {
      "entropy": 0.02077484130859375,
      "epoch": 0.5444234404536862,
      "grad_norm": 0.18177690286836462,
      "learning_rate": 1.8841698292663887e-05,
      "loss": 0.021297402679920197,
      "mean_token_accuracy": 0.9927030056715012,
      "num_tokens": 11669483.0,
      "step": 180
    },
    {
      "entropy": 0.020357513427734376,
      "epoch": 0.5595463137996219,
      "grad_norm": 0.18951806144385833,
      "learning_rate": 1.876432380109673e-05,
      "loss": 0.02147246301174164,
      "mean_token_accuracy": 0.9929309383034706,
      "num_tokens": 11987399.0,
      "step": 185
    },
    {
      "entropy": 0.021063995361328126,
      "epoch": 0.5746691871455577,
      "grad_norm": 0.28328991051134833,
      "learning_rate": 1.8684617484471662e-05,
      "loss": 0.021729469299316406,
      "mean_token_accuracy": 0.9926604524254798,
      "num_tokens": 12321769.0,
      "step": 190
    },
    {
      "entropy": 0.016484832763671874,
      "epoch": 0.5897920604914934,
      "grad_norm": 0.2604043117050105,
      "learning_rate": 1.860260054935186e-05,
      "loss": 0.016648142039775847,
      "mean_token_accuracy": 0.9943771168589592,
      "num_tokens": 12637459.0,
      "step": 195
    },
    {
      "entropy": 0.016230010986328126,
      "epoch": 0.6049149338374291,
      "grad_norm": 0.1518215594544113,
      "learning_rate": 1.8518294817060777e-05,
      "loss": 0.016636769473552703,
      "mean_token_accuracy": 0.9944247990846634,
      "num_tokens": 12976497.0,
      "step": 200
    },
    {
      "epoch": 0.6049149338374291,
      "eval_entropy": 0.01848311324019332,
      "eval_loss": 0.018460111692547798,
      "eval_mean_token_accuracy": 0.9936752308596362,
      "eval_num_tokens": 12976497.0,
      "eval_runtime": 93.7884,
      "eval_samples_per_second": 14.17,
      "eval_steps_per_second": 3.551,
      "step": 200
    },
    {
      "entropy": 0.01815185546875,
      "epoch": 0.6200378071833649,
      "grad_norm": 0.2097083339362261,
      "learning_rate": 1.8431722717876383e-05,
      "loss": 0.01749354600906372,
      "mean_token_accuracy": 0.993867652118206,
      "num_tokens": 13302976.0,
      "step": 205
    },
    {
      "entropy": 0.01755523681640625,
      "epoch": 0.6351606805293005,
      "grad_norm": 0.17477493752672238,
      "learning_rate": 1.834290728506339e-05,
      "loss": 0.018500179052352905,
      "mean_token_accuracy": 0.9936169162392616,
      "num_tokens": 13627997.0,
      "step": 210
    },
    {
      "entropy": 0.018619537353515625,
      "epoch": 0.6502835538752363,
      "grad_norm": 0.1969863482217428,
      "learning_rate": 1.8251872148745075e-05,
      "loss": 0.017858733236789704,
      "mean_token_accuracy": 0.9939072072505951,
      "num_tokens": 13945104.0,
      "step": 215
    },
    {
      "entropy": 0.019687652587890625,
      "epoch": 0.665406427221172,
      "grad_norm": 0.2554011428793856,
      "learning_rate": 1.815864152961624e-05,
      "loss": 0.02146708369255066,
      "mean_token_accuracy": 0.9928086891770362,
      "num_tokens": 14279010.0,
      "step": 220
    },
    {
      "entropy": 0.0164215087890625,
      "epoch": 0.6805293005671077,
      "grad_norm": 0.22053987762264646,
      "learning_rate": 1.806324023249912e-05,
      "loss": 0.017443592846393585,
      "mean_token_accuracy": 0.9943347543478012,
      "num_tokens": 14608053.0,
      "step": 225
    },
    {
      "entropy": 0.01520233154296875,
      "epoch": 0.6956521739130435,
      "grad_norm": 0.15495690088956657,
      "learning_rate": 1.7965693639743816e-05,
      "loss": 0.015465393662452698,
      "mean_token_accuracy": 0.9950109854340553,
      "num_tokens": 14925691.0,
      "step": 230
    },
    {
      "entropy": 0.0169342041015625,
      "epoch": 0.7107750472589792,
      "grad_norm": 0.23516476733142996,
      "learning_rate": 1.786602770447513e-05,
      "loss": 0.017490310966968535,
      "mean_token_accuracy": 0.9939287096261978,
      "num_tokens": 15247510.0,
      "step": 235
    },
    {
      "entropy": 0.015985107421875,
      "epoch": 0.725897920604915,
      "grad_norm": 0.13394070957421397,
      "learning_rate": 1.776426894368746e-05,
      "loss": 0.015802830457687378,
      "mean_token_accuracy": 0.9947777166962624,
      "num_tokens": 15560305.0,
      "step": 240
    },
    {
      "entropy": 0.014200592041015625,
      "epoch": 0.7410207939508506,
      "grad_norm": 0.19432987534155574,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.014611494541168214,
      "mean_token_accuracy": 0.9948656380176544,
      "num_tokens": 15898787.0,
      "step": 245
    },
    {
      "entropy": 0.0140716552734375,
      "epoch": 0.7561436672967864,
      "grad_norm": 0.16144920711925453,
      "learning_rate": 1.7554581790402372e-05,
      "loss": 0.015314009785652161,
      "mean_token_accuracy": 0.9950292810797692,
      "num_tokens": 16236000.0,
      "step": 250
    },
    {
      "epoch": 0.7561436672967864,
      "eval_entropy": 0.01619310350389452,
      "eval_loss": 0.016467994078993797,
      "eval_mean_token_accuracy": 0.9943410491084194,
      "eval_num_tokens": 16236000.0,
      "eval_runtime": 92.8452,
      "eval_samples_per_second": 14.314,
      "eval_steps_per_second": 3.587,
      "step": 250
    },
    {
      "entropy": 0.017685699462890624,
      "epoch": 0.7712665406427222,
      "grad_norm": 0.17754228327893673,
      "learning_rate": 1.7446709187007383e-05,
      "loss": 0.018420988321304323,
      "mean_token_accuracy": 0.9938467770814896,
      "num_tokens": 16568742.0,
      "step": 255
    },
    {
      "entropy": 0.01598701477050781,
      "epoch": 0.7863894139886578,
      "grad_norm": 0.1753647354705704,
      "learning_rate": 1.7336855321455126e-05,
      "loss": 0.016123867034912108,
      "mean_token_accuracy": 0.9946757212281228,
      "num_tokens": 16886171.0,
      "step": 260
    },
    {
      "entropy": 0.01281585693359375,
      "epoch": 0.8015122873345936,
      "grad_norm": 0.1694346707825758,
      "learning_rate": 1.7225049421328024e-05,
      "loss": 0.01325436681509018,
      "mean_token_accuracy": 0.9954081103205681,
      "num_tokens": 17213518.0,
      "step": 265
    },
    {
      "entropy": 0.015825653076171876,
      "epoch": 0.8166351606805293,
      "grad_norm": 0.12320756121826888,
      "learning_rate": 1.7111321233564406e-05,
      "loss": 0.016265182197093962,
      "mean_token_accuracy": 0.9945767849683762,
      "num_tokens": 17526983.0,
      "step": 270
    },
    {
      "entropy": 0.01460418701171875,
      "epoch": 0.831758034026465,
      "grad_norm": 0.15708115348818796,
      "learning_rate": 1.699570101654404e-05,
      "loss": 0.013886567950248719,
      "mean_token_accuracy": 0.9951759412884712,
      "num_tokens": 17844226.0,
      "step": 275
    },
    {
      "entropy": 0.012836456298828125,
      "epoch": 0.8468809073724007,
      "grad_norm": 0.143701427710118,
      "learning_rate": 1.687821953203765e-05,
      "loss": 0.01477896273136139,
      "mean_token_accuracy": 0.9952674239873887,
      "num_tokens": 18154251.0,
      "step": 280
    },
    {
      "entropy": 0.013329315185546874,
      "epoch": 0.8620037807183365,
      "grad_norm": 0.14730660194978837,
      "learning_rate": 1.6758908037022446e-05,
      "loss": 0.01359080672264099,
      "mean_token_accuracy": 0.9955309063196183,
      "num_tokens": 18468667.0,
      "step": 285
    },
    {
      "entropy": 0.01543426513671875,
      "epoch": 0.8771266540642723,
      "grad_norm": 0.13900308540287734,
      "learning_rate": 1.6637798275365976e-05,
      "loss": 0.016150069236755372,
      "mean_token_accuracy": 0.9946491599082947,
      "num_tokens": 18806646.0,
      "step": 290
    },
    {
      "entropy": 0.012978363037109374,
      "epoch": 0.8922495274102079,
      "grad_norm": 0.13732124684095226,
      "learning_rate": 1.651492246938034e-05,
      "loss": 0.012651418149471284,
      "mean_token_accuracy": 0.995641553401947,
      "num_tokens": 19132756.0,
      "step": 295
    },
    {
      "entropy": 0.015012359619140625,
      "epoch": 0.9073724007561437,
      "grad_norm": 0.13977045253544546,
      "learning_rate": 1.6390313311249212e-05,
      "loss": 0.01540960967540741,
      "mean_token_accuracy": 0.9949710816144943,
      "num_tokens": 19465713.0,
      "step": 300
    },
    {
      "epoch": 0.9073724007561437,
      "eval_entropy": 0.014344957139756944,
      "eval_loss": 0.015235255472362041,
      "eval_mean_token_accuracy": 0.9947822013416806,
      "eval_num_tokens": 19465713.0,
      "eval_runtime": 92.3526,
      "eval_samples_per_second": 14.391,
      "eval_steps_per_second": 3.606,
      "step": 300
    },
    {
      "entropy": 0.013709640502929688,
      "epoch": 0.9224952741020794,
      "grad_norm": 0.19119314364034928,
      "learning_rate": 1.6264003954329762e-05,
      "loss": 0.01464797556400299,
      "mean_token_accuracy": 0.9951745182275772,
      "num_tokens": 19791857.0,
      "step": 305
    },
    {
      "entropy": 0.0113555908203125,
      "epoch": 0.9376181474480151,
      "grad_norm": 0.13382137381631254,
      "learning_rate": 1.613602800433194e-05,
      "loss": 0.012380270659923554,
      "mean_token_accuracy": 0.9959253877401352,
      "num_tokens": 20121726.0,
      "step": 310
    },
    {
      "entropy": 0.013879013061523438,
      "epoch": 0.9527410207939508,
      "grad_norm": 0.1786900745985722,
      "learning_rate": 1.600641951037736e-05,
      "loss": 0.013191039860248565,
      "mean_token_accuracy": 0.9955014079809189,
      "num_tokens": 20434281.0,
      "step": 315
    },
    {
      "entropy": 0.014342498779296876,
      "epoch": 0.9678638941398866,
      "grad_norm": 0.20383676268015227,
      "learning_rate": 1.5875212955940255e-05,
      "loss": 0.01611756980419159,
      "mean_token_accuracy": 0.9947072401642799,
      "num_tokens": 20753074.0,
      "step": 320
    },
    {
      "entropy": 0.013257980346679688,
      "epoch": 0.9829867674858223,
      "grad_norm": 0.1364426748258384,
      "learning_rate": 1.574244324967283e-05,
      "loss": 0.013307541608810425,
      "mean_token_accuracy": 0.9954897597432136,
      "num_tokens": 21086031.0,
      "step": 325
    },
    {
      "entropy": 0.0136016845703125,
      "epoch": 0.998109640831758,
      "grad_norm": 0.11139044118229276,
      "learning_rate": 1.5608145716117507e-05,
      "loss": 0.013101503252983093,
      "mean_token_accuracy": 0.9954297497868538,
      "num_tokens": 21385002.0,
      "step": 330
    },
    {
      "entropy": 0.010610631994298986,
      "epoch": 1.0120982986767486,
      "grad_norm": 0.11937254210200125,
      "learning_rate": 1.547235608630856e-05,
      "loss": 0.009768091142177582,
      "mean_token_accuracy": 0.9965261527009912,
      "num_tokens": 21651447.0,
      "step": 335
    },
    {
      "entropy": 0.008671951293945313,
      "epoch": 1.0272211720226843,
      "grad_norm": 0.12948932598689103,
      "learning_rate": 1.5335110488265497e-05,
      "loss": 0.00888235867023468,
      "mean_token_accuracy": 0.996855866909027,
      "num_tokens": 21981761.0,
      "step": 340
    },
    {
      "entropy": 0.009595108032226563,
      "epoch": 1.0423440453686201,
      "grad_norm": 0.21649437613862998,
      "learning_rate": 1.5196445437380941e-05,
      "loss": 0.010289055854082107,
      "mean_token_accuracy": 0.9964772433042526,
      "num_tokens": 22320903.0,
      "step": 345
    },
    {
      "entropy": 0.00907135009765625,
      "epoch": 1.0574669187145558,
      "grad_norm": 0.12728450692524118,
      "learning_rate": 1.5056397826705356e-05,
      "loss": 0.008513091504573822,
      "mean_token_accuracy": 0.9971326634287834,
      "num_tokens": 22652825.0,
      "step": 350
    },
    {
      "epoch": 1.0574669187145558,
      "eval_entropy": 0.011664244505736205,
      "eval_loss": 0.013880621641874313,
      "eval_mean_token_accuracy": 0.9952635595032403,
      "eval_num_tokens": 22652825.0,
      "eval_runtime": 91.6429,
      "eval_samples_per_second": 14.502,
      "eval_steps_per_second": 3.634,
      "step": 350
    }
  ],
  "logging_steps": 5,
  "max_steps": 993,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 45311893700608.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}