{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03269469692015955,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.742113399505616,
      "epoch": 0.0003269469692015955,
      "grad_norm": 4.78125,
      "learning_rate": 2e-06,
      "loss": 10.776,
      "mean_token_accuracy": 0.0,
      "num_tokens": 10275.0,
      "step": 5
    },
    {
      "entropy": 10.742127990722656,
      "epoch": 0.000653893938403191,
      "grad_norm": 4.65625,
      "learning_rate": 4.5e-06,
      "loss": 10.7595,
      "mean_token_accuracy": 0.0,
      "num_tokens": 20293.0,
      "step": 10
    },
    {
      "entropy": 10.742136764526368,
      "epoch": 0.0009808409076047864,
      "grad_norm": 4.625,
      "learning_rate": 7e-06,
      "loss": 10.7523,
      "mean_token_accuracy": 0.0,
      "num_tokens": 30769.0,
      "step": 15
    },
    {
      "entropy": 10.742146301269532,
      "epoch": 0.001307787876806382,
      "grad_norm": 4.125,
      "learning_rate": 9.5e-06,
      "loss": 10.7225,
      "mean_token_accuracy": 0.00012004801537841558,
      "num_tokens": 41351.0,
      "step": 20
    },
    {
      "entropy": 10.742047691345215,
      "epoch": 0.0016347348460079775,
      "grad_norm": 4.46875,
      "learning_rate": 1.2e-05,
      "loss": 10.636,
      "mean_token_accuracy": 0.0034249894786626102,
      "num_tokens": 51137.0,
      "step": 25
    },
    {
      "entropy": 10.741790771484375,
      "epoch": 0.001961681815209573,
      "grad_norm": 3.453125,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.5702,
      "mean_token_accuracy": 0.02547865901142359,
      "num_tokens": 61184.0,
      "step": 30
    },
    {
      "entropy": 10.740883350372314,
      "epoch": 0.0022886287844111684,
      "grad_norm": 3.25,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.4596,
      "mean_token_accuracy": 0.04042313378304243,
      "num_tokens": 71499.0,
      "step": 35
    },
    {
      "entropy": 10.737741374969483,
      "epoch": 0.002615575753612764,
      "grad_norm": 2.578125,
      "learning_rate": 1.95e-05,
      "loss": 10.3621,
      "mean_token_accuracy": 0.040610473789274695,
      "num_tokens": 81761.0,
      "step": 40
    },
    {
      "entropy": 10.730296325683593,
      "epoch": 0.0029425227228143595,
      "grad_norm": 2.03125,
      "learning_rate": 2.2e-05,
      "loss": 10.3001,
      "mean_token_accuracy": 0.04410006906837225,
      "num_tokens": 93149.0,
      "step": 45
    },
    {
      "entropy": 10.71926326751709,
      "epoch": 0.003269469692015955,
      "grad_norm": 1.953125,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 10.2165,
      "mean_token_accuracy": 0.04155384935438633,
      "num_tokens": 103201.0,
      "step": 50
    },
    {
      "entropy": 10.708568000793457,
      "epoch": 0.0035964166612175506,
      "grad_norm": 1.859375,
      "learning_rate": 2.7e-05,
      "loss": 10.1726,
      "mean_token_accuracy": 0.04020474925637245,
      "num_tokens": 114340.0,
      "step": 55
    },
    {
      "entropy": 10.701301193237304,
      "epoch": 0.003923363630419146,
      "grad_norm": 1.796875,
      "learning_rate": 2.95e-05,
      "loss": 10.1116,
      "mean_token_accuracy": 0.04064096435904503,
      "num_tokens": 125783.0,
      "step": 60
    },
    {
      "entropy": 10.697566413879395,
      "epoch": 0.004250310599620741,
      "grad_norm": 1.6796875,
      "learning_rate": 3.2e-05,
      "loss": 10.009,
      "mean_token_accuracy": 0.045371340587735176,
      "num_tokens": 135351.0,
      "step": 65
    },
    {
      "entropy": 10.687885189056397,
      "epoch": 0.004577257568822337,
      "grad_norm": 1.5234375,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 10.0007,
      "mean_token_accuracy": 0.04735755994915962,
      "num_tokens": 146942.0,
      "step": 70
    },
    {
      "entropy": 10.67340784072876,
      "epoch": 0.004904204538023932,
      "grad_norm": 1.53125,
      "learning_rate": 3.7e-05,
      "loss": 9.9564,
      "mean_token_accuracy": 0.04602020643651485,
      "num_tokens": 157676.0,
      "step": 75
    },
    {
      "entropy": 10.66284465789795,
      "epoch": 0.005231151507225528,
      "grad_norm": 1.625,
      "learning_rate": 3.95e-05,
      "loss": 9.8556,
      "mean_token_accuracy": 0.04378781914710998,
      "num_tokens": 168608.0,
      "step": 80
    },
    {
      "entropy": 10.652789783477782,
      "epoch": 0.0055580984764271235,
      "grad_norm": 1.59375,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.7935,
      "mean_token_accuracy": 0.04510065279901028,
      "num_tokens": 179268.0,
      "step": 85
    },
    {
      "entropy": 10.641815185546875,
      "epoch": 0.005885045445628719,
      "grad_norm": 1.3671875,
      "learning_rate": 4.45e-05,
      "loss": 9.7758,
      "mean_token_accuracy": 0.04471180438995361,
      "num_tokens": 189279.0,
      "step": 90
    },
    {
      "entropy": 10.630170726776123,
      "epoch": 0.006211992414830315,
      "grad_norm": 1.4375,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.6597,
      "mean_token_accuracy": 0.051299701631069186,
      "num_tokens": 198791.0,
      "step": 95
    },
    {
      "entropy": 10.610001182556152,
      "epoch": 0.00653893938403191,
      "grad_norm": 1.59375,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.6081,
      "mean_token_accuracy": 0.05303466804325581,
      "num_tokens": 208262.0,
      "step": 100
    },
    {
      "entropy": 10.579906845092774,
      "epoch": 0.006865886353233506,
      "grad_norm": 1.3828125,
      "learning_rate": 5.2e-05,
      "loss": 9.5352,
      "mean_token_accuracy": 0.056127872318029404,
      "num_tokens": 219359.0,
      "step": 105
    },
    {
      "entropy": 10.532975387573241,
      "epoch": 0.007192833322435101,
      "grad_norm": 1.3515625,
      "learning_rate": 5.45e-05,
      "loss": 9.3977,
      "mean_token_accuracy": 0.058200102671980856,
      "num_tokens": 229582.0,
      "step": 110
    },
    {
      "entropy": 10.477785778045654,
      "epoch": 0.007519780291636697,
      "grad_norm": 1.421875,
      "learning_rate": 5.7e-05,
      "loss": 9.3974,
      "mean_token_accuracy": 0.05185054987668991,
      "num_tokens": 239856.0,
      "step": 115
    },
    {
      "entropy": 10.430697154998779,
      "epoch": 0.007846727260838291,
      "grad_norm": 1.25,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 9.2645,
      "mean_token_accuracy": 0.05604934468865395,
      "num_tokens": 249620.0,
      "step": 120
    },
    {
      "entropy": 10.360366725921631,
      "epoch": 0.008173674230039887,
      "grad_norm": 1.296875,
      "learning_rate": 6.2e-05,
      "loss": 9.2143,
      "mean_token_accuracy": 0.056453173980116844,
      "num_tokens": 260081.0,
      "step": 125
    },
    {
      "entropy": 10.311341571807862,
      "epoch": 0.008500621199241483,
      "grad_norm": 1.25,
      "learning_rate": 6.450000000000001e-05,
      "loss": 9.0411,
      "mean_token_accuracy": 0.0628997091203928,
      "num_tokens": 269889.0,
      "step": 130
    },
    {
      "entropy": 10.249684810638428,
      "epoch": 0.008827568168443078,
      "grad_norm": 1.1640625,
      "learning_rate": 6.7e-05,
      "loss": 9.0288,
      "mean_token_accuracy": 0.05760575719177723,
      "num_tokens": 279884.0,
      "step": 135
    },
    {
      "entropy": 10.16486234664917,
      "epoch": 0.009154515137644674,
      "grad_norm": 1.0859375,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.9747,
      "mean_token_accuracy": 0.05335375927388668,
      "num_tokens": 290532.0,
      "step": 140
    },
    {
      "entropy": 10.097373962402344,
      "epoch": 0.00948146210684627,
      "grad_norm": 1.09375,
      "learning_rate": 7.2e-05,
      "loss": 8.822,
      "mean_token_accuracy": 0.0569435752928257,
      "num_tokens": 300384.0,
      "step": 145
    },
    {
      "entropy": 9.977852058410644,
      "epoch": 0.009808409076047865,
      "grad_norm": 1.0390625,
      "learning_rate": 7.45e-05,
      "loss": 8.682,
      "mean_token_accuracy": 0.059730267897248265,
      "num_tokens": 310486.0,
      "step": 150
    },
    {
      "entropy": 9.833982563018798,
      "epoch": 0.01013535604524946,
      "grad_norm": 0.9296875,
      "learning_rate": 7.7e-05,
      "loss": 8.6837,
      "mean_token_accuracy": 0.05625330694019794,
      "num_tokens": 320405.0,
      "step": 155
    },
    {
      "entropy": 9.774449253082276,
      "epoch": 0.010462303014451056,
      "grad_norm": 0.8671875,
      "learning_rate": 7.950000000000001e-05,
      "loss": 8.6079,
      "mean_token_accuracy": 0.05718303620815277,
      "num_tokens": 331041.0,
      "step": 160
    },
    {
      "entropy": 9.63415584564209,
      "epoch": 0.010789249983652651,
      "grad_norm": 0.90234375,
      "learning_rate": 8.2e-05,
      "loss": 8.5797,
      "mean_token_accuracy": 0.05304349213838577,
      "num_tokens": 341014.0,
      "step": 165
    },
    {
      "entropy": 9.469839668273925,
      "epoch": 0.011116196952854247,
      "grad_norm": 0.90234375,
      "learning_rate": 8.450000000000001e-05,
      "loss": 8.5053,
      "mean_token_accuracy": 0.056027017533779144,
      "num_tokens": 352840.0,
      "step": 170
    },
    {
      "entropy": 9.372684097290039,
      "epoch": 0.011443143922055843,
      "grad_norm": 0.796875,
      "learning_rate": 8.7e-05,
      "loss": 8.4457,
      "mean_token_accuracy": 0.05765199661254883,
      "num_tokens": 362829.0,
      "step": 175
    },
    {
      "entropy": 9.20329122543335,
      "epoch": 0.011770090891257438,
      "grad_norm": 0.91796875,
      "learning_rate": 8.95e-05,
      "loss": 8.3589,
      "mean_token_accuracy": 0.05721031129360199,
      "num_tokens": 373330.0,
      "step": 180
    },
    {
      "entropy": 9.161731624603272,
      "epoch": 0.012097037860459034,
      "grad_norm": 0.87890625,
      "learning_rate": 9.2e-05,
      "loss": 8.3475,
      "mean_token_accuracy": 0.0628576211631298,
      "num_tokens": 383488.0,
      "step": 185
    },
    {
      "entropy": 9.003976440429687,
      "epoch": 0.01242398482966063,
      "grad_norm": 0.67578125,
      "learning_rate": 9.45e-05,
      "loss": 8.3301,
      "mean_token_accuracy": 0.06189408227801323,
      "num_tokens": 393936.0,
      "step": 190
    },
    {
      "entropy": 8.969250679016113,
      "epoch": 0.012750931798862225,
      "grad_norm": 0.91796875,
      "learning_rate": 9.7e-05,
      "loss": 8.4052,
      "mean_token_accuracy": 0.05606413669884205,
      "num_tokens": 404013.0,
      "step": 195
    },
    {
      "entropy": 8.889835643768311,
      "epoch": 0.01307787876806382,
      "grad_norm": 0.69921875,
      "learning_rate": 9.95e-05,
      "loss": 8.306,
      "mean_token_accuracy": 0.06066743396222592,
      "num_tokens": 414009.0,
      "step": 200
    },
    {
      "entropy": 8.863146209716797,
      "epoch": 0.013404825737265416,
      "grad_norm": 0.734375,
      "learning_rate": 0.000102,
      "loss": 8.3384,
      "mean_token_accuracy": 0.061011272668838504,
      "num_tokens": 424011.0,
      "step": 205
    },
    {
      "entropy": 8.82211093902588,
      "epoch": 0.013731772706467011,
      "grad_norm": 0.859375,
      "learning_rate": 0.00010449999999999999,
      "loss": 8.2994,
      "mean_token_accuracy": 0.05930745899677277,
      "num_tokens": 434985.0,
      "step": 210
    },
    {
      "entropy": 8.761214542388917,
      "epoch": 0.014058719675668607,
      "grad_norm": 0.87109375,
      "learning_rate": 0.000107,
      "loss": 8.3062,
      "mean_token_accuracy": 0.05960893705487251,
      "num_tokens": 446276.0,
      "step": 215
    },
    {
      "entropy": 8.744998741149903,
      "epoch": 0.014385666644870202,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0001095,
      "loss": 8.2043,
      "mean_token_accuracy": 0.0643354371190071,
      "num_tokens": 455307.0,
      "step": 220
    },
    {
      "entropy": 8.685678005218506,
      "epoch": 0.014712613614071798,
      "grad_norm": 0.953125,
      "learning_rate": 0.000112,
      "loss": 8.292,
      "mean_token_accuracy": 0.06164254136383533,
      "num_tokens": 465253.0,
      "step": 225
    },
    {
      "entropy": 8.697282218933106,
      "epoch": 0.015039560583273394,
      "grad_norm": 0.83203125,
      "learning_rate": 0.0001145,
      "loss": 8.2881,
      "mean_token_accuracy": 0.058608485758304595,
      "num_tokens": 475588.0,
      "step": 230
    },
    {
      "entropy": 8.673004341125488,
      "epoch": 0.015366507552474989,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00011700000000000001,
      "loss": 8.1716,
      "mean_token_accuracy": 0.06607786752283573,
      "num_tokens": 485356.0,
      "step": 235
    },
    {
      "entropy": 8.679743576049805,
      "epoch": 0.015693454521676583,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00011949999999999999,
      "loss": 8.2042,
      "mean_token_accuracy": 0.06503303684294223,
      "num_tokens": 494798.0,
      "step": 240
    },
    {
      "entropy": 8.688579082489014,
      "epoch": 0.01602040149087818,
      "grad_norm": 0.78125,
      "learning_rate": 0.000122,
      "loss": 8.2481,
      "mean_token_accuracy": 0.066758993268013,
      "num_tokens": 504907.0,
      "step": 245
    },
    {
      "entropy": 8.61370620727539,
      "epoch": 0.016347348460079774,
      "grad_norm": 0.875,
      "learning_rate": 0.0001245,
      "loss": 8.27,
      "mean_token_accuracy": 0.06372609883546829,
      "num_tokens": 515219.0,
      "step": 250
    },
    {
      "entropy": 8.680877590179444,
      "epoch": 0.01667429542928137,
      "grad_norm": 0.953125,
      "learning_rate": 0.000127,
      "loss": 8.2037,
      "mean_token_accuracy": 0.06568075716495514,
      "num_tokens": 524467.0,
      "step": 255
    },
    {
      "entropy": 8.654908657073975,
      "epoch": 0.017001242398482965,
      "grad_norm": 0.9140625,
      "learning_rate": 0.0001295,
      "loss": 8.222,
      "mean_token_accuracy": 0.06575659550726413,
      "num_tokens": 533573.0,
      "step": 260
    },
    {
      "entropy": 8.531476593017578,
      "epoch": 0.01732818936768456,
      "grad_norm": 1.6171875,
      "learning_rate": 0.000132,
      "loss": 8.2469,
      "mean_token_accuracy": 0.06724704653024674,
      "num_tokens": 543373.0,
      "step": 265
    },
    {
      "entropy": 8.580636024475098,
      "epoch": 0.017655136336886156,
      "grad_norm": 0.88671875,
      "learning_rate": 0.00013450000000000002,
      "loss": 8.1985,
      "mean_token_accuracy": 0.06407700963318348,
      "num_tokens": 554398.0,
      "step": 270
    },
    {
      "entropy": 8.66346378326416,
      "epoch": 0.017982083306087752,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00013700000000000002,
      "loss": 8.1736,
      "mean_token_accuracy": 0.06911301650106907,
      "num_tokens": 564362.0,
      "step": 275
    },
    {
      "entropy": 8.573775577545167,
      "epoch": 0.018309030275289347,
      "grad_norm": 0.796875,
      "learning_rate": 0.0001395,
      "loss": 8.2462,
      "mean_token_accuracy": 0.06476497501134873,
      "num_tokens": 575658.0,
      "step": 280
    },
    {
      "entropy": 8.612453079223632,
      "epoch": 0.018635977244490943,
      "grad_norm": 0.984375,
      "learning_rate": 0.00014199999999999998,
      "loss": 8.2019,
      "mean_token_accuracy": 0.0694070715457201,
      "num_tokens": 585744.0,
      "step": 285
    },
    {
      "entropy": 8.532073974609375,
      "epoch": 0.01896292421369254,
      "grad_norm": 0.8125,
      "learning_rate": 0.0001445,
      "loss": 8.1013,
      "mean_token_accuracy": 0.06488311924040317,
      "num_tokens": 595435.0,
      "step": 290
    },
    {
      "entropy": 8.593374729156494,
      "epoch": 0.019289871182894134,
      "grad_norm": 0.94140625,
      "learning_rate": 0.000147,
      "loss": 8.1323,
      "mean_token_accuracy": 0.06929427571594715,
      "num_tokens": 605374.0,
      "step": 295
    },
    {
      "entropy": 8.474758338928222,
      "epoch": 0.01961681815209573,
      "grad_norm": 0.95703125,
      "learning_rate": 0.0001495,
      "loss": 8.2146,
      "mean_token_accuracy": 0.06380412466824055,
      "num_tokens": 616418.0,
      "step": 300
    },
    {
      "entropy": 8.502184677124024,
      "epoch": 0.019943765121297325,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000152,
      "loss": 8.1067,
      "mean_token_accuracy": 0.07269482649862766,
      "num_tokens": 625857.0,
      "step": 305
    },
    {
      "entropy": 8.525908470153809,
      "epoch": 0.02027071209049892,
      "grad_norm": 0.81640625,
      "learning_rate": 0.00015450000000000001,
      "loss": 8.1735,
      "mean_token_accuracy": 0.07054477296769619,
      "num_tokens": 636469.0,
      "step": 310
    },
    {
      "entropy": 8.518884563446045,
      "epoch": 0.020597659059700516,
      "grad_norm": 0.890625,
      "learning_rate": 0.000157,
      "loss": 8.1442,
      "mean_token_accuracy": 0.06903811804950237,
      "num_tokens": 648105.0,
      "step": 315
    },
    {
      "entropy": 8.525949001312256,
      "epoch": 0.02092460602890211,
      "grad_norm": 0.8984375,
      "learning_rate": 0.0001595,
      "loss": 8.0683,
      "mean_token_accuracy": 0.07465084679424763,
      "num_tokens": 657214.0,
      "step": 320
    },
    {
      "entropy": 8.480726528167725,
      "epoch": 0.021251552998103707,
      "grad_norm": 0.88671875,
      "learning_rate": 0.000162,
      "loss": 8.1398,
      "mean_token_accuracy": 0.06769934073090553,
      "num_tokens": 667228.0,
      "step": 325
    },
    {
      "entropy": 8.504579067230225,
      "epoch": 0.021578499967305303,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00016450000000000001,
      "loss": 8.0862,
      "mean_token_accuracy": 0.07170318402349948,
      "num_tokens": 677412.0,
      "step": 330
    },
    {
      "entropy": 8.48094425201416,
      "epoch": 0.0219054469365069,
      "grad_norm": 0.91796875,
      "learning_rate": 0.00016700000000000002,
      "loss": 8.0583,
      "mean_token_accuracy": 0.07172369435429574,
      "num_tokens": 687893.0,
      "step": 335
    },
    {
      "entropy": 8.471054744720458,
      "epoch": 0.022232393905708494,
      "grad_norm": 0.91015625,
      "learning_rate": 0.00016950000000000003,
      "loss": 8.1798,
      "mean_token_accuracy": 0.06923119835555554,
      "num_tokens": 698497.0,
      "step": 340
    },
    {
      "entropy": 8.496150588989257,
      "epoch": 0.02255934087491009,
      "grad_norm": 1.03125,
      "learning_rate": 0.00017199999999999998,
      "loss": 8.063,
      "mean_token_accuracy": 0.07196387574076653,
      "num_tokens": 708593.0,
      "step": 345
    },
    {
      "entropy": 8.432998275756836,
      "epoch": 0.022886287844111685,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00017449999999999999,
      "loss": 8.0788,
      "mean_token_accuracy": 0.07477995418012143,
      "num_tokens": 719781.0,
      "step": 350
    },
    {
      "entropy": 8.490119457244873,
      "epoch": 0.02321323481331328,
      "grad_norm": 0.875,
      "learning_rate": 0.000177,
      "loss": 8.088,
      "mean_token_accuracy": 0.0711702361702919,
      "num_tokens": 729946.0,
      "step": 355
    },
    {
      "entropy": 8.486604785919189,
      "epoch": 0.023540181782514876,
      "grad_norm": 0.87890625,
      "learning_rate": 0.0001795,
      "loss": 8.0756,
      "mean_token_accuracy": 0.07159654907882214,
      "num_tokens": 740542.0,
      "step": 360
    },
    {
      "entropy": 8.415905952453613,
      "epoch": 0.02386712875171647,
      "grad_norm": 1.3203125,
      "learning_rate": 0.000182,
      "loss": 7.9728,
      "mean_token_accuracy": 0.08065467663109302,
      "num_tokens": 750387.0,
      "step": 365
    },
    {
      "entropy": 8.41865062713623,
      "epoch": 0.024194075720918067,
      "grad_norm": 0.9375,
      "learning_rate": 0.0001845,
      "loss": 8.0256,
      "mean_token_accuracy": 0.07667291313409805,
      "num_tokens": 759708.0,
      "step": 370
    },
    {
      "entropy": 8.375955581665039,
      "epoch": 0.024521022690119663,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000187,
      "loss": 7.9862,
      "mean_token_accuracy": 0.07728637531399726,
      "num_tokens": 770655.0,
      "step": 375
    },
    {
      "entropy": 8.447672843933105,
      "epoch": 0.02484796965932126,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0001895,
      "loss": 8.0944,
      "mean_token_accuracy": 0.07428529076278209,
      "num_tokens": 780263.0,
      "step": 380
    },
    {
      "entropy": 8.440955066680909,
      "epoch": 0.025174916628522854,
      "grad_norm": 0.859375,
      "learning_rate": 0.000192,
      "loss": 7.9377,
      "mean_token_accuracy": 0.08051865920424461,
      "num_tokens": 789667.0,
      "step": 385
    },
    {
      "entropy": 8.339350986480714,
      "epoch": 0.02550186359772445,
      "grad_norm": 0.96484375,
      "learning_rate": 0.0001945,
      "loss": 7.9736,
      "mean_token_accuracy": 0.07487879581749439,
      "num_tokens": 800099.0,
      "step": 390
    },
    {
      "entropy": 8.333793830871581,
      "epoch": 0.025828810566926045,
      "grad_norm": 1.1875,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.9658,
      "mean_token_accuracy": 0.08434236496686935,
      "num_tokens": 809347.0,
      "step": 395
    },
    {
      "entropy": 8.389479732513427,
      "epoch": 0.02615575753612764,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.9885,
      "mean_token_accuracy": 0.07460427135229111,
      "num_tokens": 819721.0,
      "step": 400
    },
    {
      "entropy": 8.356211471557618,
      "epoch": 0.026482704505329236,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000202,
      "loss": 7.92,
      "mean_token_accuracy": 0.07878225892782212,
      "num_tokens": 830278.0,
      "step": 405
    },
    {
      "entropy": 8.31589298248291,
      "epoch": 0.02680965147453083,
      "grad_norm": 1.09375,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.9775,
      "mean_token_accuracy": 0.07939173206686974,
      "num_tokens": 839760.0,
      "step": 410
    },
    {
      "entropy": 8.388703918457031,
      "epoch": 0.027136598443732427,
      "grad_norm": 0.859375,
      "learning_rate": 0.000207,
      "loss": 7.9903,
      "mean_token_accuracy": 0.07688882425427437,
      "num_tokens": 850778.0,
      "step": 415
    },
    {
      "entropy": 8.303010845184327,
      "epoch": 0.027463545412934023,
      "grad_norm": 1.125,
      "learning_rate": 0.0002095,
      "loss": 7.9098,
      "mean_token_accuracy": 0.080412358045578,
      "num_tokens": 860419.0,
      "step": 420
    },
    {
      "entropy": 8.438417148590087,
      "epoch": 0.027790492382135618,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000212,
      "loss": 8.0202,
      "mean_token_accuracy": 0.08035937286913394,
      "num_tokens": 869939.0,
      "step": 425
    },
    {
      "entropy": 8.34555139541626,
      "epoch": 0.028117439351337214,
      "grad_norm": 0.9375,
      "learning_rate": 0.0002145,
      "loss": 7.9552,
      "mean_token_accuracy": 0.07891882248222828,
      "num_tokens": 880331.0,
      "step": 430
    },
    {
      "entropy": 8.413178730010987,
      "epoch": 0.02844438632053881,
      "grad_norm": 1.15625,
      "learning_rate": 0.00021700000000000002,
      "loss": 8.032,
      "mean_token_accuracy": 0.07255076095461846,
      "num_tokens": 891342.0,
      "step": 435
    },
    {
      "entropy": 8.292833995819091,
      "epoch": 0.028771333289740405,
      "grad_norm": 0.984375,
      "learning_rate": 0.0002195,
      "loss": 7.9823,
      "mean_token_accuracy": 0.07935103215277195,
      "num_tokens": 902253.0,
      "step": 440
    },
    {
      "entropy": 8.271970176696778,
      "epoch": 0.029098280258942,
      "grad_norm": 1.015625,
      "learning_rate": 0.000222,
      "loss": 7.9096,
      "mean_token_accuracy": 0.07985292673110962,
      "num_tokens": 913086.0,
      "step": 445
    },
    {
      "entropy": 8.302376174926758,
      "epoch": 0.029425227228143596,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0002245,
      "loss": 7.9366,
      "mean_token_accuracy": 0.08083747625350952,
      "num_tokens": 925082.0,
      "step": 450
    },
    {
      "entropy": 8.271292591094971,
      "epoch": 0.02975217419734519,
      "grad_norm": 1.015625,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.9089,
      "mean_token_accuracy": 0.07454345673322678,
      "num_tokens": 933955.0,
      "step": 455
    },
    {
      "entropy": 8.287126731872558,
      "epoch": 0.030079121166546787,
      "grad_norm": 0.94921875,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.8699,
      "mean_token_accuracy": 0.07939782850444317,
      "num_tokens": 943951.0,
      "step": 460
    },
    {
      "entropy": 8.33047170639038,
      "epoch": 0.030406068135748383,
      "grad_norm": 0.9296875,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.8629,
      "mean_token_accuracy": 0.081587253510952,
      "num_tokens": 955297.0,
      "step": 465
    },
    {
      "entropy": 8.157269191741943,
      "epoch": 0.030733015104949978,
      "grad_norm": 0.88671875,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.9056,
      "mean_token_accuracy": 0.08038199990987778,
      "num_tokens": 967012.0,
      "step": 470
    },
    {
      "entropy": 8.305221843719483,
      "epoch": 0.031059962074151574,
      "grad_norm": 0.90234375,
      "learning_rate": 0.000237,
      "loss": 7.8177,
      "mean_token_accuracy": 0.08144455999135972,
      "num_tokens": 977956.0,
      "step": 475
    },
    {
      "entropy": 8.184438991546632,
      "epoch": 0.031386909043353166,
      "grad_norm": 1.046875,
      "learning_rate": 0.0002395,
      "loss": 7.8361,
      "mean_token_accuracy": 0.08141265660524369,
      "num_tokens": 987270.0,
      "step": 480
    },
    {
      "entropy": 8.198512172698974,
      "epoch": 0.03171385601255476,
      "grad_norm": 0.9453125,
      "learning_rate": 0.000242,
      "loss": 7.824,
      "mean_token_accuracy": 0.08384960517287254,
      "num_tokens": 998010.0,
      "step": 485
    },
    {
      "entropy": 8.246695518493652,
      "epoch": 0.03204080298175636,
      "grad_norm": 1.09375,
      "learning_rate": 0.0002445,
      "loss": 7.86,
      "mean_token_accuracy": 0.09095575362443924,
      "num_tokens": 1008173.0,
      "step": 490
    },
    {
      "entropy": 8.233383846282958,
      "epoch": 0.03236774995095795,
      "grad_norm": 1.0703125,
      "learning_rate": 0.000247,
      "loss": 7.8713,
      "mean_token_accuracy": 0.08157122023403644,
      "num_tokens": 1019037.0,
      "step": 495
    },
    {
      "entropy": 8.247837829589844,
      "epoch": 0.03269469692015955,
      "grad_norm": 1.140625,
      "learning_rate": 0.0002495,
      "loss": 7.8742,
      "mean_token_accuracy": 0.08232737332582474,
      "num_tokens": 1028822.0,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 4000,
  "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": 243642072268800.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}