{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.41334768568353,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0861141011840689,
      "grad_norm": 21.438983917236328,
      "learning_rate": 6.749999999999999e-06,
      "loss": 5.3584,
      "num_input_tokens_seen": 106432,
      "step": 10,
      "train_runtime": 108.6693,
      "train_tokens_per_second": 979.412
    },
    {
      "epoch": 0.1722282023681378,
      "grad_norm": 8.519647598266602,
      "learning_rate": 1.4249999999999999e-05,
      "loss": 4.8538,
      "num_input_tokens_seen": 213216,
      "step": 20,
      "train_runtime": 186.9434,
      "train_tokens_per_second": 1140.538
    },
    {
      "epoch": 0.25834230355220666,
      "grad_norm": 18.737985610961914,
      "learning_rate": 2.1749999999999997e-05,
      "loss": 3.6236,
      "num_input_tokens_seen": 319264,
      "step": 30,
      "train_runtime": 265.2215,
      "train_tokens_per_second": 1203.763
    },
    {
      "epoch": 0.3444564047362756,
      "grad_norm": 4.311729431152344,
      "learning_rate": 2.925e-05,
      "loss": 2.4654,
      "num_input_tokens_seen": 426464,
      "step": 40,
      "train_runtime": 343.9109,
      "train_tokens_per_second": 1240.042
    },
    {
      "epoch": 0.43057050592034446,
      "grad_norm": 2.5902934074401855,
      "learning_rate": 3.675e-05,
      "loss": 2.0086,
      "num_input_tokens_seen": 532576,
      "step": 50,
      "train_runtime": 421.9835,
      "train_tokens_per_second": 1262.078
    },
    {
      "epoch": 0.5166846071044133,
      "grad_norm": 3.0768535137176514,
      "learning_rate": 4.424999999999999e-05,
      "loss": 1.878,
      "num_input_tokens_seen": 639584,
      "step": 60,
      "train_runtime": 500.5067,
      "train_tokens_per_second": 1277.873
    },
    {
      "epoch": 0.6027987082884823,
      "grad_norm": 2.4493396282196045,
      "learning_rate": 5.174999999999999e-05,
      "loss": 1.8546,
      "num_input_tokens_seen": 747360,
      "step": 70,
      "train_runtime": 579.1392,
      "train_tokens_per_second": 1290.467
    },
    {
      "epoch": 0.6889128094725512,
      "grad_norm": 2.146406650543213,
      "learning_rate": 5.925e-05,
      "loss": 1.8364,
      "num_input_tokens_seen": 854304,
      "step": 80,
      "train_runtime": 657.8931,
      "train_tokens_per_second": 1298.545
    },
    {
      "epoch": 0.77502691065662,
      "grad_norm": 2.2075250148773193,
      "learning_rate": 6.675e-05,
      "loss": 1.8027,
      "num_input_tokens_seen": 962816,
      "step": 90,
      "train_runtime": 737.8649,
      "train_tokens_per_second": 1304.868
    },
    {
      "epoch": 0.8611410118406889,
      "grad_norm": 0.9837085008621216,
      "learning_rate": 7.424999999999999e-05,
      "loss": 1.7782,
      "num_input_tokens_seen": 1070240,
      "step": 100,
      "train_runtime": 817.3738,
      "train_tokens_per_second": 1309.364
    },
    {
      "epoch": 0.9472551130247578,
      "grad_norm": 3.0224859714508057,
      "learning_rate": 8.175e-05,
      "loss": 1.7681,
      "num_input_tokens_seen": 1175840,
      "step": 110,
      "train_runtime": 895.639,
      "train_tokens_per_second": 1312.85
    },
    {
      "epoch": 1.0258342303552206,
      "grad_norm": 1.015479326248169,
      "learning_rate": 8.924999999999999e-05,
      "loss": 1.5944,
      "num_input_tokens_seen": 1273184,
      "step": 120,
      "train_runtime": 967.2081,
      "train_tokens_per_second": 1316.35
    },
    {
      "epoch": 1.1119483315392895,
      "grad_norm": 1.2177729606628418,
      "learning_rate": 9.675e-05,
      "loss": 1.7489,
      "num_input_tokens_seen": 1380480,
      "step": 130,
      "train_runtime": 1045.876,
      "train_tokens_per_second": 1319.927
    },
    {
      "epoch": 1.1980624327233584,
      "grad_norm": 1.6441470384597778,
      "learning_rate": 0.00010424999999999999,
      "loss": 1.7265,
      "num_input_tokens_seen": 1487520,
      "step": 140,
      "train_runtime": 1124.3621,
      "train_tokens_per_second": 1322.99
    },
    {
      "epoch": 1.2841765339074274,
      "grad_norm": 1.1657848358154297,
      "learning_rate": 0.00011174999999999999,
      "loss": 1.7386,
      "num_input_tokens_seen": 1593472,
      "step": 150,
      "train_runtime": 1202.4025,
      "train_tokens_per_second": 1325.24
    },
    {
      "epoch": 1.3702906350914963,
      "grad_norm": 1.1126108169555664,
      "learning_rate": 0.00011925,
      "loss": 1.7229,
      "num_input_tokens_seen": 1700288,
      "step": 160,
      "train_runtime": 1280.6844,
      "train_tokens_per_second": 1327.64
    },
    {
      "epoch": 1.456404736275565,
      "grad_norm": 1.3799711465835571,
      "learning_rate": 0.00012675,
      "loss": 1.7513,
      "num_input_tokens_seen": 1807488,
      "step": 170,
      "train_runtime": 1359.2569,
      "train_tokens_per_second": 1329.762
    },
    {
      "epoch": 1.542518837459634,
      "grad_norm": 1.2127066850662231,
      "learning_rate": 0.00013424999999999998,
      "loss": 1.7105,
      "num_input_tokens_seen": 1914272,
      "step": 180,
      "train_runtime": 1437.7985,
      "train_tokens_per_second": 1331.391
    },
    {
      "epoch": 1.6286329386437028,
      "grad_norm": 1.4629660844802856,
      "learning_rate": 0.00014174999999999998,
      "loss": 1.7081,
      "num_input_tokens_seen": 2019584,
      "step": 190,
      "train_runtime": 1515.7685,
      "train_tokens_per_second": 1332.383
    },
    {
      "epoch": 1.7147470398277718,
      "grad_norm": 0.9486769437789917,
      "learning_rate": 0.00014925,
      "loss": 1.7133,
      "num_input_tokens_seen": 2126016,
      "step": 200,
      "train_runtime": 1593.9754,
      "train_tokens_per_second": 1333.782
    },
    {
      "epoch": 1.8008611410118407,
      "grad_norm": 1.6725178956985474,
      "learning_rate": 0.00014992177254124345,
      "loss": 1.7217,
      "num_input_tokens_seen": 2233824,
      "step": 210,
      "train_runtime": 1672.6238,
      "train_tokens_per_second": 1335.521
    },
    {
      "epoch": 1.8869752421959096,
      "grad_norm": 1.5028326511383057,
      "learning_rate": 0.00014965156613602355,
      "loss": 1.7094,
      "num_input_tokens_seen": 2341536,
      "step": 220,
      "train_runtime": 1751.4804,
      "train_tokens_per_second": 1336.89
    },
    {
      "epoch": 1.9730893433799785,
      "grad_norm": 1.0816280841827393,
      "learning_rate": 0.0001491891107057639,
      "loss": 1.7178,
      "num_input_tokens_seen": 2447072,
      "step": 230,
      "train_runtime": 1829.8444,
      "train_tokens_per_second": 1337.312
    },
    {
      "epoch": 2.051668460710441,
      "grad_norm": 0.8403604030609131,
      "learning_rate": 0.00014853559720478995,
      "loss": 1.5203,
      "num_input_tokens_seen": 2544928,
      "step": 240,
      "train_runtime": 1901.5872,
      "train_tokens_per_second": 1338.318
    },
    {
      "epoch": 2.13778256189451,
      "grad_norm": 0.805606484413147,
      "learning_rate": 0.00014769270861632517,
      "loss": 1.684,
      "num_input_tokens_seen": 2652064,
      "step": 250,
      "train_runtime": 1980.3904,
      "train_tokens_per_second": 1339.162
    },
    {
      "epoch": 2.223896663078579,
      "grad_norm": 0.7405467629432678,
      "learning_rate": 0.00014666261561833036,
      "loss": 1.6749,
      "num_input_tokens_seen": 2759904,
      "step": 260,
      "train_runtime": 2065.3272,
      "train_tokens_per_second": 1336.304
    },
    {
      "epoch": 2.310010764262648,
      "grad_norm": 0.8861342668533325,
      "learning_rate": 0.00014544797099339018,
      "loss": 1.6585,
      "num_input_tokens_seen": 2865952,
      "step": 270,
      "train_runtime": 2143.4821,
      "train_tokens_per_second": 1337.054
    },
    {
      "epoch": 2.396124865446717,
      "grad_norm": 1.0403251647949219,
      "learning_rate": 0.0001440519027970432,
      "loss": 1.6736,
      "num_input_tokens_seen": 2972928,
      "step": 280,
      "train_runtime": 2222.3903,
      "train_tokens_per_second": 1337.716
    },
    {
      "epoch": 2.482238966630786,
      "grad_norm": 2.1221981048583984,
      "learning_rate": 0.0001424780063021488,
      "loss": 1.6969,
      "num_input_tokens_seen": 3080512,
      "step": 290,
      "train_runtime": 2301.0804,
      "train_tokens_per_second": 1338.724
    },
    {
      "epoch": 2.5683530678148547,
      "grad_norm": 0.7471824884414673,
      "learning_rate": 0.00014073033474003643,
      "loss": 1.6699,
      "num_input_tokens_seen": 3187712,
      "step": 300,
      "train_runtime": 2379.4634,
      "train_tokens_per_second": 1339.677
    },
    {
      "epoch": 2.6544671689989237,
      "grad_norm": 0.7120847702026367,
      "learning_rate": 0.00013881338886228165,
      "loss": 1.6843,
      "num_input_tokens_seen": 3293920,
      "step": 310,
      "train_runtime": 2457.8176,
      "train_tokens_per_second": 1340.181
    },
    {
      "epoch": 2.7405812701829926,
      "grad_norm": 0.7970668077468872,
      "learning_rate": 0.00013673210534999016,
      "loss": 1.6693,
      "num_input_tokens_seen": 3400960,
      "step": 320,
      "train_runtime": 2536.9062,
      "train_tokens_per_second": 1340.594
    },
    {
      "epoch": 2.8266953713670615,
      "grad_norm": 0.6767310500144958,
      "learning_rate": 0.0001344918441004391,
      "loss": 1.6793,
      "num_input_tokens_seen": 3508032,
      "step": 330,
      "train_runtime": 2615.7057,
      "train_tokens_per_second": 1341.142
    },
    {
      "epoch": 2.91280947255113,
      "grad_norm": 0.9333407282829285,
      "learning_rate": 0.00013209837442381653,
      "loss": 1.6769,
      "num_input_tokens_seen": 3614176,
      "step": 340,
      "train_runtime": 2694.0699,
      "train_tokens_per_second": 1341.53
    },
    {
      "epoch": 2.9989235737351994,
      "grad_norm": 0.6378505229949951,
      "learning_rate": 0.0001295578601856059,
      "loss": 1.6701,
      "num_input_tokens_seen": 3721088,
      "step": 350,
      "train_runtime": 2772.4192,
      "train_tokens_per_second": 1342.181
    },
    {
      "epoch": 3.077502691065662,
      "grad_norm": 0.7191705107688904,
      "learning_rate": 0.0001268768439328786,
      "loss": 1.4983,
      "num_input_tokens_seen": 3819168,
      "step": 360,
      "train_runtime": 2844.1855,
      "train_tokens_per_second": 1342.798
    },
    {
      "epoch": 3.163616792249731,
      "grad_norm": 0.8273401856422424,
      "learning_rate": 0.0001240622300453734,
      "loss": 1.6384,
      "num_input_tokens_seen": 3925184,
      "step": 370,
      "train_runtime": 2922.2231,
      "train_tokens_per_second": 1343.218
    },
    {
      "epoch": 3.2497308934338,
      "grad_norm": 1.5716602802276611,
      "learning_rate": 0.00012112126695475425,
      "loss": 1.6345,
      "num_input_tokens_seen": 4032864,
      "step": 380,
      "train_runtime": 3000.8862,
      "train_tokens_per_second": 1343.891
    },
    {
      "epoch": 3.3358449946178688,
      "grad_norm": 0.6344667077064514,
      "learning_rate": 0.00011806152847783581,
      "loss": 1.6347,
      "num_input_tokens_seen": 4140288,
      "step": 390,
      "train_runtime": 3079.5638,
      "train_tokens_per_second": 1344.44
    },
    {
      "epoch": 3.4219590958019377,
      "grad_norm": 0.45537635684013367,
      "learning_rate": 0.0001148908943118504,
      "loss": 1.621,
      "num_input_tokens_seen": 4247264,
      "step": 400,
      "train_runtime": 3158.1824,
      "train_tokens_per_second": 1344.844
    },
    {
      "epoch": 3.5080731969860066,
      "grad_norm": 0.9383829832077026,
      "learning_rate": 0.00011161752974198511,
      "loss": 1.64,
      "num_input_tokens_seen": 4354272,
      "step": 410,
      "train_runtime": 3236.6237,
      "train_tokens_per_second": 1345.313
    },
    {
      "epoch": 3.594187298170075,
      "grad_norm": 0.704737663269043,
      "learning_rate": 0.00010824986461344928,
      "loss": 1.6314,
      "num_input_tokens_seen": 4462208,
      "step": 420,
      "train_runtime": 3315.3543,
      "train_tokens_per_second": 1345.922
    },
    {
      "epoch": 3.6803013993541445,
      "grad_norm": 0.6594169735908508,
      "learning_rate": 0.00010479657162222409,
      "loss": 1.6498,
      "num_input_tokens_seen": 4569632,
      "step": 430,
      "train_runtime": 3393.6946,
      "train_tokens_per_second": 1346.507
    },
    {
      "epoch": 3.766415500538213,
      "grad_norm": 0.6667532324790955,
      "learning_rate": 0.00010126654398040281,
      "loss": 1.633,
      "num_input_tokens_seen": 4676736,
      "step": 440,
      "train_runtime": 3472.7969,
      "train_tokens_per_second": 1346.677
    },
    {
      "epoch": 3.852529601722282,
      "grad_norm": 0.6092108488082886,
      "learning_rate": 9.766887251363892e-05,
      "loss": 1.6256,
      "num_input_tokens_seen": 4783264,
      "step": 450,
      "train_runtime": 3551.4865,
      "train_tokens_per_second": 1346.834
    },
    {
      "epoch": 3.938643702906351,
      "grad_norm": 0.9420148730278015,
      "learning_rate": 9.401282224968333e-05,
      "loss": 1.6179,
      "num_input_tokens_seen": 4890112,
      "step": 460,
      "train_runtime": 3630.0806,
      "train_tokens_per_second": 1347.108
    },
    {
      "epoch": 4.017222820236814,
      "grad_norm": 0.6568248867988586,
      "learning_rate": 9.030780855830153e-05,
      "loss": 1.4804,
      "num_input_tokens_seen": 4987136,
      "step": 470,
      "train_runtime": 3701.7389,
      "train_tokens_per_second": 1347.241
    },
    {
      "epoch": 4.103336921420882,
      "grad_norm": 0.46975892782211304,
      "learning_rate": 8.65633729040172e-05,
      "loss": 1.5986,
      "num_input_tokens_seen": 5092896,
      "step": 480,
      "train_runtime": 3780.0642,
      "train_tokens_per_second": 1347.304
    },
    {
      "epoch": 4.189451022604952,
      "grad_norm": 0.17200271785259247,
      "learning_rate": 8.278915827412616e-05,
      "loss": 1.603,
      "num_input_tokens_seen": 5200416,
      "step": 490,
      "train_runtime": 3859.043,
      "train_tokens_per_second": 1347.592
    },
    {
      "epoch": 4.27556512378902,
      "grad_norm": 1.3012012243270874,
      "learning_rate": 7.899488434526004e-05,
      "loss": 1.5983,
      "num_input_tokens_seen": 5306976,
      "step": 500,
      "train_runtime": 3937.2348,
      "train_tokens_per_second": 1347.894
    },
    {
      "epoch": 4.36167922497309,
      "grad_norm": 0.780907392501831,
      "learning_rate": 7.51903224524532e-05,
      "loss": 1.5965,
      "num_input_tokens_seen": 5414464,
      "step": 510,
      "train_runtime": 4022.017,
      "train_tokens_per_second": 1346.206
    },
    {
      "epoch": 4.447793326157158,
      "grad_norm": 0.6589680910110474,
      "learning_rate": 7.138527042517471e-05,
      "loss": 1.603,
      "num_input_tokens_seen": 5520224,
      "step": 520,
      "train_runtime": 4100.3341,
      "train_tokens_per_second": 1346.286
    },
    {
      "epoch": 4.533907427341227,
      "grad_norm": 0.5304105877876282,
      "learning_rate": 6.758952735512931e-05,
      "loss": 1.6065,
      "num_input_tokens_seen": 5628224,
      "step": 530,
      "train_runtime": 4179.0731,
      "train_tokens_per_second": 1346.764
    },
    {
      "epoch": 4.620021528525296,
      "grad_norm": 0.2885695695877075,
      "learning_rate": 6.381286836080796e-05,
      "loss": 1.6024,
      "num_input_tokens_seen": 5734816,
      "step": 540,
      "train_runtime": 4257.2922,
      "train_tokens_per_second": 1347.057
    },
    {
      "epoch": 4.706135629709365,
      "grad_norm": 0.3303077816963196,
      "learning_rate": 6.006501941377631e-05,
      "loss": 1.597,
      "num_input_tokens_seen": 5842240,
      "step": 550,
      "train_runtime": 4336.3619,
      "train_tokens_per_second": 1347.268
    },
    {
      "epoch": 4.792249730893434,
      "grad_norm": 0.4729728102684021,
      "learning_rate": 5.635563229153013e-05,
      "loss": 1.6005,
      "num_input_tokens_seen": 5950688,
      "step": 560,
      "train_runtime": 4415.38,
      "train_tokens_per_second": 1347.718
    },
    {
      "epoch": 4.878363832077502,
      "grad_norm": 0.6590526103973389,
      "learning_rate": 5.2694259721422185e-05,
      "loss": 1.6081,
      "num_input_tokens_seen": 6056416,
      "step": 570,
      "train_runtime": 4493.6142,
      "train_tokens_per_second": 1347.783
    },
    {
      "epoch": 4.964477933261572,
      "grad_norm": 0.5510996580123901,
      "learning_rate": 4.90903307796707e-05,
      "loss": 1.6024,
      "num_input_tokens_seen": 6163968,
      "step": 580,
      "train_runtime": 4572.3588,
      "train_tokens_per_second": 1348.094
    },
    {
      "epoch": 5.043057050592035,
      "grad_norm": 0.4095686376094818,
      "learning_rate": 4.555312660880527e-05,
      "loss": 1.4538,
      "num_input_tokens_seen": 6262560,
      "step": 590,
      "train_runtime": 4644.1546,
      "train_tokens_per_second": 1348.482
    },
    {
      "epoch": 5.129171151776103,
      "grad_norm": 0.17324793338775635,
      "learning_rate": 4.209175651608374e-05,
      "loss": 1.586,
      "num_input_tokens_seen": 6369280,
      "step": 600,
      "train_runtime": 4722.7601,
      "train_tokens_per_second": 1348.635
    },
    {
      "epoch": 5.2152852529601725,
      "grad_norm": 0.6640817523002625,
      "learning_rate": 3.871513451443412e-05,
      "loss": 1.5876,
      "num_input_tokens_seen": 6475072,
      "step": 610,
      "train_runtime": 4800.8785,
      "train_tokens_per_second": 1348.726
    },
    {
      "epoch": 5.301399354144241,
      "grad_norm": 0.17123615741729736,
      "learning_rate": 3.5431956366334576e-05,
      "loss": 1.587,
      "num_input_tokens_seen": 6582240,
      "step": 620,
      "train_runtime": 4879.5207,
      "train_tokens_per_second": 1348.952
    },
    {
      "epoch": 5.38751345532831,
      "grad_norm": 0.051739007234573364,
      "learning_rate": 3.225067718975078e-05,
      "loss": 1.5812,
      "num_input_tokens_seen": 6690496,
      "step": 630,
      "train_runtime": 4959.3413,
      "train_tokens_per_second": 1349.069
    },
    {
      "epoch": 5.473627556512379,
      "grad_norm": 0.889016330242157,
      "learning_rate": 2.917948968380125e-05,
      "loss": 1.5828,
      "num_input_tokens_seen": 6797088,
      "step": 640,
      "train_runtime": 5037.9025,
      "train_tokens_per_second": 1349.19
    },
    {
      "epoch": 5.559741657696447,
      "grad_norm": 0.20981049537658691,
      "learning_rate": 2.622630303022586e-05,
      "loss": 1.5837,
      "num_input_tokens_seen": 6904160,
      "step": 650,
      "train_runtime": 5116.2831,
      "train_tokens_per_second": 1349.448
    },
    {
      "epoch": 5.645855758880517,
      "grad_norm": 0.4966135621070862,
      "learning_rate": 2.3398722524992193e-05,
      "loss": 1.5806,
      "num_input_tokens_seen": 7011264,
      "step": 660,
      "train_runtime": 5194.5897,
      "train_tokens_per_second": 1349.724
    },
    {
      "epoch": 5.731969860064585,
      "grad_norm": 0.0645381435751915,
      "learning_rate": 2.0704029992494413e-05,
      "loss": 1.5831,
      "num_input_tokens_seen": 7117600,
      "step": 670,
      "train_runtime": 5272.7715,
      "train_tokens_per_second": 1349.878
    },
    {
      "epoch": 5.818083961248655,
      "grad_norm": 0.03474411740899086,
      "learning_rate": 1.8149165032783373e-05,
      "loss": 1.5842,
      "num_input_tokens_seen": 7223968,
      "step": 680,
      "train_runtime": 5351.0243,
      "train_tokens_per_second": 1350.016
    },
    {
      "epoch": 5.904198062432723,
      "grad_norm": 0.1602916270494461,
      "learning_rate": 1.574070715012184e-05,
      "loss": 1.5803,
      "num_input_tokens_seen": 7330624,
      "step": 690,
      "train_runtime": 5429.4442,
      "train_tokens_per_second": 1350.161
    },
    {
      "epoch": 5.990312163616792,
      "grad_norm": 0.6672658920288086,
      "learning_rate": 1.3484858808888777e-05,
      "loss": 1.5828,
      "num_input_tokens_seen": 7437664,
      "step": 700,
      "train_runtime": 5507.9983,
      "train_tokens_per_second": 1350.339
    },
    {
      "epoch": 6.0688912809472555,
      "grad_norm": 0.053765423595905304,
      "learning_rate": 1.1387429460468603e-05,
      "loss": 1.4417,
      "num_input_tokens_seen": 7535744,
      "step": 710,
      "train_runtime": 5579.9255,
      "train_tokens_per_second": 1350.51
    },
    {
      "epoch": 6.155005382131324,
      "grad_norm": 0.029805637896060944,
      "learning_rate": 9.453820582260826e-06,
      "loss": 1.5799,
      "num_input_tokens_seen": 7642368,
      "step": 720,
      "train_runtime": 5657.9716,
      "train_tokens_per_second": 1350.726
    },
    {
      "epoch": 6.2411194833153925,
      "grad_norm": 0.04558693990111351,
      "learning_rate": 7.689011767338823e-06,
      "loss": 1.5799,
      "num_input_tokens_seen": 7748992,
      "step": 730,
      "train_runtime": 5736.181,
      "train_tokens_per_second": 1350.897
    },
    {
      "epoch": 6.327233584499462,
      "grad_norm": 0.03208324313163757,
      "learning_rate": 6.097547900580538e-06,
      "loss": 1.5796,
      "num_input_tokens_seen": 7856928,
      "step": 740,
      "train_runtime": 5814.8518,
      "train_tokens_per_second": 1351.183
    },
    {
      "epoch": 6.41334768568353,
      "grad_norm": 0.03971538320183754,
      "learning_rate": 4.68352745429686e-06,
      "loss": 1.5801,
      "num_input_tokens_seen": 7964064,
      "step": 750,
      "train_runtime": 5893.167,
      "train_tokens_per_second": 1351.406
    }
  ],
  "logging_steps": 10,
  "max_steps": 819,
  "num_input_tokens_seen": 7964064,
  "num_train_epochs": 7,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.3558949813041664e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}