{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.42973785990545765,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.691965675354004,
      "epoch": 0.004297378599054577,
      "grad_norm": 14.1875,
      "learning_rate": 2e-06,
      "loss": 10.8333,
      "mean_token_accuracy": 0.0,
      "num_tokens": 10107.0,
      "step": 5
    },
    {
      "entropy": 10.691940116882325,
      "epoch": 0.008594757198109154,
      "grad_norm": 14.0,
      "learning_rate": 4.5e-06,
      "loss": 10.7061,
      "mean_token_accuracy": 0.0001254705130122602,
      "num_tokens": 18391.0,
      "step": 10
    },
    {
      "entropy": 10.690368461608887,
      "epoch": 0.01289213579716373,
      "grad_norm": 10.25,
      "learning_rate": 7e-06,
      "loss": 10.4329,
      "mean_token_accuracy": 0.039750428823754194,
      "num_tokens": 27061.0,
      "step": 15
    },
    {
      "entropy": 10.658441638946533,
      "epoch": 0.017189514396218308,
      "grad_norm": 6.71875,
      "learning_rate": 9.5e-06,
      "loss": 10.1104,
      "mean_token_accuracy": 0.05699652768671513,
      "num_tokens": 36339.0,
      "step": 20
    },
    {
      "entropy": 10.46299867630005,
      "epoch": 0.021486892995272882,
      "grad_norm": 3.6875,
      "learning_rate": 1.2e-05,
      "loss": 9.8252,
      "mean_token_accuracy": 0.05812832042574882,
      "num_tokens": 45770.0,
      "step": 25
    },
    {
      "entropy": 10.438103103637696,
      "epoch": 0.02578427159432746,
      "grad_norm": 3.109375,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 9.7045,
      "mean_token_accuracy": 0.05137639828026295,
      "num_tokens": 54575.0,
      "step": 30
    },
    {
      "entropy": 10.417833423614502,
      "epoch": 0.030081650193382038,
      "grad_norm": 2.640625,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.6957,
      "mean_token_accuracy": 0.05632184371352196,
      "num_tokens": 66403.0,
      "step": 35
    },
    {
      "entropy": 10.414659309387208,
      "epoch": 0.034379028792436615,
      "grad_norm": 2.34375,
      "learning_rate": 1.95e-05,
      "loss": 9.5706,
      "mean_token_accuracy": 0.05973100401461125,
      "num_tokens": 76510.0,
      "step": 40
    },
    {
      "entropy": 10.398680400848388,
      "epoch": 0.03867640739149119,
      "grad_norm": 2.453125,
      "learning_rate": 2.2e-05,
      "loss": 9.5207,
      "mean_token_accuracy": 0.05555921196937561,
      "num_tokens": 84836.0,
      "step": 45
    },
    {
      "entropy": 10.38410243988037,
      "epoch": 0.042973785990545764,
      "grad_norm": 2.328125,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.4948,
      "mean_token_accuracy": 0.05959299132227898,
      "num_tokens": 93197.0,
      "step": 50
    },
    {
      "entropy": 10.410307884216309,
      "epoch": 0.047271164589600345,
      "grad_norm": 2.921875,
      "learning_rate": 2.7e-05,
      "loss": 9.4126,
      "mean_token_accuracy": 0.07061550468206405,
      "num_tokens": 101546.0,
      "step": 55
    },
    {
      "entropy": 10.19266414642334,
      "epoch": 0.05156854318865492,
      "grad_norm": 2.078125,
      "learning_rate": 2.95e-05,
      "loss": 9.4273,
      "mean_token_accuracy": 0.06822829730808735,
      "num_tokens": 111703.0,
      "step": 60
    },
    {
      "entropy": 10.230934810638427,
      "epoch": 0.055865921787709494,
      "grad_norm": 2.03125,
      "learning_rate": 3.2e-05,
      "loss": 9.2909,
      "mean_token_accuracy": 0.071290984749794,
      "num_tokens": 119894.0,
      "step": 65
    },
    {
      "entropy": 10.18722620010376,
      "epoch": 0.060163300386764075,
      "grad_norm": 1.8828125,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.2147,
      "mean_token_accuracy": 0.07613217085599899,
      "num_tokens": 128885.0,
      "step": 70
    },
    {
      "entropy": 10.178893566131592,
      "epoch": 0.06446067898581866,
      "grad_norm": 2.03125,
      "learning_rate": 3.7e-05,
      "loss": 9.1672,
      "mean_token_accuracy": 0.07484854124486447,
      "num_tokens": 138106.0,
      "step": 75
    },
    {
      "entropy": 10.157839488983154,
      "epoch": 0.06875805758487323,
      "grad_norm": 2.0625,
      "learning_rate": 3.95e-05,
      "loss": 9.102,
      "mean_token_accuracy": 0.07415809743106365,
      "num_tokens": 146691.0,
      "step": 80
    },
    {
      "entropy": 10.076846313476562,
      "epoch": 0.0730554361839278,
      "grad_norm": 2.015625,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.0178,
      "mean_token_accuracy": 0.07684990540146827,
      "num_tokens": 155792.0,
      "step": 85
    },
    {
      "entropy": 10.131054401397705,
      "epoch": 0.07735281478298238,
      "grad_norm": 1.65625,
      "learning_rate": 4.45e-05,
      "loss": 9.041,
      "mean_token_accuracy": 0.0714216936379671,
      "num_tokens": 166944.0,
      "step": 90
    },
    {
      "entropy": 10.075201606750488,
      "epoch": 0.08165019338203695,
      "grad_norm": 2.234375,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 8.8173,
      "mean_token_accuracy": 0.08133668191730976,
      "num_tokens": 175303.0,
      "step": 95
    },
    {
      "entropy": 9.932421398162841,
      "epoch": 0.08594757198109153,
      "grad_norm": 1.765625,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 8.7966,
      "mean_token_accuracy": 0.0745367206633091,
      "num_tokens": 184708.0,
      "step": 100
    },
    {
      "entropy": 10.040246391296387,
      "epoch": 0.09024495058014612,
      "grad_norm": 1.859375,
      "learning_rate": 5.2e-05,
      "loss": 8.6871,
      "mean_token_accuracy": 0.07615455649793149,
      "num_tokens": 193835.0,
      "step": 105
    },
    {
      "entropy": 9.88200340270996,
      "epoch": 0.09454232917920069,
      "grad_norm": 1.8984375,
      "learning_rate": 5.45e-05,
      "loss": 8.6105,
      "mean_token_accuracy": 0.08173681348562241,
      "num_tokens": 203344.0,
      "step": 110
    },
    {
      "entropy": 9.8795636177063,
      "epoch": 0.09883970777825526,
      "grad_norm": 1.5234375,
      "learning_rate": 5.7e-05,
      "loss": 8.6013,
      "mean_token_accuracy": 0.06998304352164268,
      "num_tokens": 213048.0,
      "step": 115
    },
    {
      "entropy": 9.673752784729004,
      "epoch": 0.10313708637730984,
      "grad_norm": 2.40625,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.4264,
      "mean_token_accuracy": 0.08312096372246743,
      "num_tokens": 221784.0,
      "step": 120
    },
    {
      "entropy": 9.593516635894776,
      "epoch": 0.10743446497636441,
      "grad_norm": 1.453125,
      "learning_rate": 6.2e-05,
      "loss": 8.3091,
      "mean_token_accuracy": 0.0795404627919197,
      "num_tokens": 230971.0,
      "step": 125
    },
    {
      "entropy": 9.516329765319824,
      "epoch": 0.11173184357541899,
      "grad_norm": 1.421875,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.2258,
      "mean_token_accuracy": 0.08525455147027969,
      "num_tokens": 240524.0,
      "step": 130
    },
    {
      "entropy": 9.287061023712159,
      "epoch": 0.11602922217447358,
      "grad_norm": 1.34375,
      "learning_rate": 6.7e-05,
      "loss": 8.1406,
      "mean_token_accuracy": 0.07961341962218285,
      "num_tokens": 249220.0,
      "step": 135
    },
    {
      "entropy": 9.293281650543213,
      "epoch": 0.12032660077352815,
      "grad_norm": 1.359375,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.1524,
      "mean_token_accuracy": 0.07657627090811729,
      "num_tokens": 258934.0,
      "step": 140
    },
    {
      "entropy": 9.01927890777588,
      "epoch": 0.12462397937258272,
      "grad_norm": 1.4296875,
      "learning_rate": 7.2e-05,
      "loss": 8.0306,
      "mean_token_accuracy": 0.07841632440686226,
      "num_tokens": 267680.0,
      "step": 145
    },
    {
      "entropy": 8.906111335754394,
      "epoch": 0.1289213579716373,
      "grad_norm": 1.265625,
      "learning_rate": 7.45e-05,
      "loss": 7.9934,
      "mean_token_accuracy": 0.08083904013037682,
      "num_tokens": 276227.0,
      "step": 150
    },
    {
      "entropy": 8.772429847717286,
      "epoch": 0.1332187365706919,
      "grad_norm": 1.1484375,
      "learning_rate": 7.7e-05,
      "loss": 7.8676,
      "mean_token_accuracy": 0.08683294653892518,
      "num_tokens": 286342.0,
      "step": 155
    },
    {
      "entropy": 8.59535722732544,
      "epoch": 0.13751611516974646,
      "grad_norm": 1.3671875,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.875,
      "mean_token_accuracy": 0.0787959948182106,
      "num_tokens": 294994.0,
      "step": 160
    },
    {
      "entropy": 8.52799425125122,
      "epoch": 0.14181349376880104,
      "grad_norm": 1.203125,
      "learning_rate": 8.2e-05,
      "loss": 7.8586,
      "mean_token_accuracy": 0.083160999417305,
      "num_tokens": 303882.0,
      "step": 165
    },
    {
      "entropy": 8.462903499603271,
      "epoch": 0.1461108723678556,
      "grad_norm": 1.046875,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.8291,
      "mean_token_accuracy": 0.08582018166780472,
      "num_tokens": 312515.0,
      "step": 170
    },
    {
      "entropy": 8.407231998443603,
      "epoch": 0.15040825096691018,
      "grad_norm": 1.34375,
      "learning_rate": 8.7e-05,
      "loss": 7.8147,
      "mean_token_accuracy": 0.08485982567071915,
      "num_tokens": 320801.0,
      "step": 175
    },
    {
      "entropy": 8.276727199554443,
      "epoch": 0.15470562956596476,
      "grad_norm": 1.1640625,
      "learning_rate": 8.95e-05,
      "loss": 7.7982,
      "mean_token_accuracy": 0.08752225190401078,
      "num_tokens": 329382.0,
      "step": 180
    },
    {
      "entropy": 8.329781436920166,
      "epoch": 0.15900300816501933,
      "grad_norm": 1.109375,
      "learning_rate": 9.2e-05,
      "loss": 7.7867,
      "mean_token_accuracy": 0.08166329339146614,
      "num_tokens": 337894.0,
      "step": 185
    },
    {
      "entropy": 8.223849201202393,
      "epoch": 0.1633003867640739,
      "grad_norm": 1.1328125,
      "learning_rate": 9.45e-05,
      "loss": 7.763,
      "mean_token_accuracy": 0.0833988644182682,
      "num_tokens": 346380.0,
      "step": 190
    },
    {
      "entropy": 8.166347885131836,
      "epoch": 0.16759776536312848,
      "grad_norm": 1.203125,
      "learning_rate": 9.7e-05,
      "loss": 7.8225,
      "mean_token_accuracy": 0.07767418175935745,
      "num_tokens": 356305.0,
      "step": 195
    },
    {
      "entropy": 8.312477111816406,
      "epoch": 0.17189514396218306,
      "grad_norm": 1.1171875,
      "learning_rate": 9.95e-05,
      "loss": 7.7712,
      "mean_token_accuracy": 0.08167372904717922,
      "num_tokens": 364899.0,
      "step": 200
    },
    {
      "entropy": 8.078741836547852,
      "epoch": 0.17619252256123766,
      "grad_norm": 1.2734375,
      "learning_rate": 0.000102,
      "loss": 7.7396,
      "mean_token_accuracy": 0.0805903747677803,
      "num_tokens": 373663.0,
      "step": 205
    },
    {
      "entropy": 8.12859468460083,
      "epoch": 0.18048990116029223,
      "grad_norm": 1.359375,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.7106,
      "mean_token_accuracy": 0.0817422017455101,
      "num_tokens": 382730.0,
      "step": 210
    },
    {
      "entropy": 8.151737308502197,
      "epoch": 0.1847872797593468,
      "grad_norm": 1.453125,
      "learning_rate": 0.000107,
      "loss": 7.7463,
      "mean_token_accuracy": 0.08051776215434074,
      "num_tokens": 392676.0,
      "step": 215
    },
    {
      "entropy": 8.053222179412842,
      "epoch": 0.18908465835840138,
      "grad_norm": 1.4296875,
      "learning_rate": 0.0001095,
      "loss": 7.7332,
      "mean_token_accuracy": 0.08385580405592918,
      "num_tokens": 401050.0,
      "step": 220
    },
    {
      "entropy": 8.128051567077637,
      "epoch": 0.19338203695745596,
      "grad_norm": 1.125,
      "learning_rate": 0.000112,
      "loss": 7.6847,
      "mean_token_accuracy": 0.08319979459047318,
      "num_tokens": 410009.0,
      "step": 225
    },
    {
      "entropy": 8.011648893356323,
      "epoch": 0.19767941555651053,
      "grad_norm": 1.109375,
      "learning_rate": 0.0001145,
      "loss": 7.6685,
      "mean_token_accuracy": 0.08485263586044312,
      "num_tokens": 419302.0,
      "step": 230
    },
    {
      "entropy": 8.079462242126464,
      "epoch": 0.2019767941555651,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.5827,
      "mean_token_accuracy": 0.09158513993024826,
      "num_tokens": 427296.0,
      "step": 235
    },
    {
      "entropy": 8.013971376419068,
      "epoch": 0.20627417275461968,
      "grad_norm": 1.140625,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.7232,
      "mean_token_accuracy": 0.08320990726351737,
      "num_tokens": 436368.0,
      "step": 240
    },
    {
      "entropy": 8.017411470413208,
      "epoch": 0.21057155135367425,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000122,
      "loss": 7.6329,
      "mean_token_accuracy": 0.08677152320742607,
      "num_tokens": 445535.0,
      "step": 245
    },
    {
      "entropy": 7.988703823089599,
      "epoch": 0.21486892995272883,
      "grad_norm": 1.046875,
      "learning_rate": 0.0001245,
      "loss": 7.6242,
      "mean_token_accuracy": 0.08498941510915756,
      "num_tokens": 454769.0,
      "step": 250
    },
    {
      "entropy": 7.950494480133057,
      "epoch": 0.2191663085517834,
      "grad_norm": 1.15625,
      "learning_rate": 0.000127,
      "loss": 7.6389,
      "mean_token_accuracy": 0.08514668568968772,
      "num_tokens": 463975.0,
      "step": 255
    },
    {
      "entropy": 7.953547191619873,
      "epoch": 0.22346368715083798,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0001295,
      "loss": 7.6256,
      "mean_token_accuracy": 0.0869191125035286,
      "num_tokens": 472899.0,
      "step": 260
    },
    {
      "entropy": 8.079424142837524,
      "epoch": 0.22776106574989258,
      "grad_norm": 1.2734375,
      "learning_rate": 0.000132,
      "loss": 7.6169,
      "mean_token_accuracy": 0.08434697091579438,
      "num_tokens": 481556.0,
      "step": 265
    },
    {
      "entropy": 7.917314720153809,
      "epoch": 0.23205844434894715,
      "grad_norm": 1.4375,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.5906,
      "mean_token_accuracy": 0.08885264247655869,
      "num_tokens": 490253.0,
      "step": 270
    },
    {
      "entropy": 7.981470727920533,
      "epoch": 0.23635582294800173,
      "grad_norm": 1.296875,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.6123,
      "mean_token_accuracy": 0.08401632830500602,
      "num_tokens": 498444.0,
      "step": 275
    },
    {
      "entropy": 7.889223909378051,
      "epoch": 0.2406532015470563,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0001395,
      "loss": 7.5345,
      "mean_token_accuracy": 0.089448182284832,
      "num_tokens": 508330.0,
      "step": 280
    },
    {
      "entropy": 7.9246303081512455,
      "epoch": 0.24495058014611087,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.6371,
      "mean_token_accuracy": 0.08723574504256248,
      "num_tokens": 517900.0,
      "step": 285
    },
    {
      "entropy": 7.941996765136719,
      "epoch": 0.24924795874516545,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0001445,
      "loss": 7.6012,
      "mean_token_accuracy": 0.08463213071227074,
      "num_tokens": 527808.0,
      "step": 290
    },
    {
      "entropy": 7.864819860458374,
      "epoch": 0.25354533734422,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000147,
      "loss": 7.5607,
      "mean_token_accuracy": 0.08868518695235253,
      "num_tokens": 536931.0,
      "step": 295
    },
    {
      "entropy": 8.03366231918335,
      "epoch": 0.2578427159432746,
      "grad_norm": 1.296875,
      "learning_rate": 0.0001495,
      "loss": 7.5922,
      "mean_token_accuracy": 0.08514139242470264,
      "num_tokens": 545758.0,
      "step": 300
    },
    {
      "entropy": 7.859347915649414,
      "epoch": 0.26214009454232917,
      "grad_norm": 1.25,
      "learning_rate": 0.000152,
      "loss": 7.5998,
      "mean_token_accuracy": 0.08533880487084389,
      "num_tokens": 555165.0,
      "step": 305
    },
    {
      "entropy": 7.95199933052063,
      "epoch": 0.2664374731413838,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.5021,
      "mean_token_accuracy": 0.09082270339131356,
      "num_tokens": 564719.0,
      "step": 310
    },
    {
      "entropy": 7.8452857494354244,
      "epoch": 0.2707348517404383,
      "grad_norm": 1.265625,
      "learning_rate": 0.000157,
      "loss": 7.4768,
      "mean_token_accuracy": 0.0927261844277382,
      "num_tokens": 573572.0,
      "step": 315
    },
    {
      "entropy": 7.885577821731568,
      "epoch": 0.2750322303394929,
      "grad_norm": 1.65625,
      "learning_rate": 0.0001595,
      "loss": 7.6561,
      "mean_token_accuracy": 0.08534143045544625,
      "num_tokens": 581497.0,
      "step": 320
    },
    {
      "entropy": 7.828050327301026,
      "epoch": 0.27932960893854747,
      "grad_norm": 1.2734375,
      "learning_rate": 0.000162,
      "loss": 7.5095,
      "mean_token_accuracy": 0.08862045854330063,
      "num_tokens": 591107.0,
      "step": 325
    },
    {
      "entropy": 7.820580291748047,
      "epoch": 0.28362698753760207,
      "grad_norm": 1.09375,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.5394,
      "mean_token_accuracy": 0.08959158807992935,
      "num_tokens": 600241.0,
      "step": 330
    },
    {
      "entropy": 7.917682647705078,
      "epoch": 0.2879243661366566,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.4679,
      "mean_token_accuracy": 0.087359119951725,
      "num_tokens": 608697.0,
      "step": 335
    },
    {
      "entropy": 7.84361424446106,
      "epoch": 0.2922217447357112,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.4459,
      "mean_token_accuracy": 0.09482443928718567,
      "num_tokens": 617275.0,
      "step": 340
    },
    {
      "entropy": 7.767910099029541,
      "epoch": 0.29651912333476577,
      "grad_norm": 1.234375,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.5397,
      "mean_token_accuracy": 0.08964255526661873,
      "num_tokens": 626644.0,
      "step": 345
    },
    {
      "entropy": 7.85635404586792,
      "epoch": 0.30081650193382037,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.4583,
      "mean_token_accuracy": 0.09355088248848915,
      "num_tokens": 635110.0,
      "step": 350
    },
    {
      "entropy": 7.811613988876343,
      "epoch": 0.30511388053287497,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000177,
      "loss": 7.6085,
      "mean_token_accuracy": 0.0853718601167202,
      "num_tokens": 644746.0,
      "step": 355
    },
    {
      "entropy": 7.915624761581421,
      "epoch": 0.3094112591319295,
      "grad_norm": 1.203125,
      "learning_rate": 0.0001795,
      "loss": 7.5016,
      "mean_token_accuracy": 0.09187210947275162,
      "num_tokens": 654281.0,
      "step": 360
    },
    {
      "entropy": 7.767735958099365,
      "epoch": 0.3137086377309841,
      "grad_norm": 1.3046875,
      "learning_rate": 0.000182,
      "loss": 7.4717,
      "mean_token_accuracy": 0.09581760317087173,
      "num_tokens": 663174.0,
      "step": 365
    },
    {
      "entropy": 7.733127641677856,
      "epoch": 0.31800601633003867,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0001845,
      "loss": 7.4106,
      "mean_token_accuracy": 0.09181510880589486,
      "num_tokens": 672178.0,
      "step": 370
    },
    {
      "entropy": 7.764935684204102,
      "epoch": 0.32230339492909327,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000187,
      "loss": 7.4192,
      "mean_token_accuracy": 0.09482730180025101,
      "num_tokens": 681323.0,
      "step": 375
    },
    {
      "entropy": 7.748341512680054,
      "epoch": 0.3266007735281478,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001895,
      "loss": 7.3494,
      "mean_token_accuracy": 0.09762883707880973,
      "num_tokens": 690461.0,
      "step": 380
    },
    {
      "entropy": 7.726337242126465,
      "epoch": 0.3308981521272024,
      "grad_norm": 1.3671875,
      "learning_rate": 0.000192,
      "loss": 7.385,
      "mean_token_accuracy": 0.0929147757589817,
      "num_tokens": 699199.0,
      "step": 385
    },
    {
      "entropy": 7.714869022369385,
      "epoch": 0.33519553072625696,
      "grad_norm": 1.265625,
      "learning_rate": 0.0001945,
      "loss": 7.3466,
      "mean_token_accuracy": 0.09913949891924859,
      "num_tokens": 707949.0,
      "step": 390
    },
    {
      "entropy": 7.790979957580566,
      "epoch": 0.33949290932531156,
      "grad_norm": 1.359375,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.4025,
      "mean_token_accuracy": 0.09461145251989364,
      "num_tokens": 715752.0,
      "step": 395
    },
    {
      "entropy": 7.699273300170899,
      "epoch": 0.3437902879243661,
      "grad_norm": 1.40625,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.3498,
      "mean_token_accuracy": 0.0960754208266735,
      "num_tokens": 724416.0,
      "step": 400
    },
    {
      "entropy": 7.691787385940552,
      "epoch": 0.3480876665234207,
      "grad_norm": 1.3125,
      "learning_rate": 0.000202,
      "loss": 7.3931,
      "mean_token_accuracy": 0.09644346088171005,
      "num_tokens": 733116.0,
      "step": 405
    },
    {
      "entropy": 7.731271648406983,
      "epoch": 0.3523850451224753,
      "grad_norm": 1.5390625,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.3842,
      "mean_token_accuracy": 0.09576574862003326,
      "num_tokens": 742093.0,
      "step": 410
    },
    {
      "entropy": 7.707010555267334,
      "epoch": 0.35668242372152986,
      "grad_norm": 1.140625,
      "learning_rate": 0.000207,
      "loss": 7.3749,
      "mean_token_accuracy": 0.09439021646976471,
      "num_tokens": 750402.0,
      "step": 415
    },
    {
      "entropy": 7.543523073196411,
      "epoch": 0.36097980232058446,
      "grad_norm": 1.15625,
      "learning_rate": 0.0002095,
      "loss": 7.3356,
      "mean_token_accuracy": 0.09795518517494202,
      "num_tokens": 760961.0,
      "step": 420
    },
    {
      "entropy": 7.811382913589478,
      "epoch": 0.365277180919639,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000212,
      "loss": 7.4027,
      "mean_token_accuracy": 0.09610488563776017,
      "num_tokens": 770554.0,
      "step": 425
    },
    {
      "entropy": 7.553221845626831,
      "epoch": 0.3695745595186936,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0002145,
      "loss": 7.3782,
      "mean_token_accuracy": 0.09901996925473214,
      "num_tokens": 779172.0,
      "step": 430
    },
    {
      "entropy": 7.695575714111328,
      "epoch": 0.37387193811774816,
      "grad_norm": 1.125,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.4409,
      "mean_token_accuracy": 0.09009857177734375,
      "num_tokens": 788040.0,
      "step": 435
    },
    {
      "entropy": 7.697094821929932,
      "epoch": 0.37816931671680276,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0002195,
      "loss": 7.3336,
      "mean_token_accuracy": 0.0955778069794178,
      "num_tokens": 796786.0,
      "step": 440
    },
    {
      "entropy": 7.651894569396973,
      "epoch": 0.3824666953158573,
      "grad_norm": 1.328125,
      "learning_rate": 0.000222,
      "loss": 7.3424,
      "mean_token_accuracy": 0.0917925551533699,
      "num_tokens": 805520.0,
      "step": 445
    },
    {
      "entropy": 7.574945497512817,
      "epoch": 0.3867640739149119,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0002245,
      "loss": 7.2618,
      "mean_token_accuracy": 0.09809256345033646,
      "num_tokens": 814939.0,
      "step": 450
    },
    {
      "entropy": 7.574750566482544,
      "epoch": 0.39106145251396646,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.2789,
      "mean_token_accuracy": 0.09702842682600021,
      "num_tokens": 823862.0,
      "step": 455
    },
    {
      "entropy": 7.632641363143921,
      "epoch": 0.39535883111302106,
      "grad_norm": 1.234375,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.289,
      "mean_token_accuracy": 0.09691592380404472,
      "num_tokens": 832820.0,
      "step": 460
    },
    {
      "entropy": 7.676099395751953,
      "epoch": 0.39965620971207566,
      "grad_norm": 1.25,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.2716,
      "mean_token_accuracy": 0.0997233621776104,
      "num_tokens": 841538.0,
      "step": 465
    },
    {
      "entropy": 7.588865423202515,
      "epoch": 0.4039535883111302,
      "grad_norm": 1.171875,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.3935,
      "mean_token_accuracy": 0.09301438555121422,
      "num_tokens": 851123.0,
      "step": 470
    },
    {
      "entropy": 7.607400226593017,
      "epoch": 0.4082509669101848,
      "grad_norm": 1.28125,
      "learning_rate": 0.000237,
      "loss": 7.3539,
      "mean_token_accuracy": 0.10057086423039437,
      "num_tokens": 860357.0,
      "step": 475
    },
    {
      "entropy": 7.581248617172241,
      "epoch": 0.41254834550923936,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0002395,
      "loss": 7.2498,
      "mean_token_accuracy": 0.09947932437062264,
      "num_tokens": 869980.0,
      "step": 480
    },
    {
      "entropy": 7.5202593326568605,
      "epoch": 0.41684572410829396,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000242,
      "loss": 7.2247,
      "mean_token_accuracy": 0.10081686452031136,
      "num_tokens": 878250.0,
      "step": 485
    },
    {
      "entropy": 7.625096321105957,
      "epoch": 0.4211431027073485,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0002445,
      "loss": 7.3273,
      "mean_token_accuracy": 0.09839151874184608,
      "num_tokens": 887624.0,
      "step": 490
    },
    {
      "entropy": 7.487894821166992,
      "epoch": 0.4254404813064031,
      "grad_norm": 1.171875,
      "learning_rate": 0.000247,
      "loss": 7.2795,
      "mean_token_accuracy": 0.10116326585412025,
      "num_tokens": 897120.0,
      "step": 495
    },
    {
      "entropy": 7.501826333999634,
      "epoch": 0.42973785990545765,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0002495,
      "loss": 7.2414,
      "mean_token_accuracy": 0.1031015545129776,
      "num_tokens": 906215.0,
      "step": 500
    },
    {
      "epoch": 0.42973785990545765,
      "eval_entropy": 7.422262197142249,
      "eval_loss": 7.298919677734375,
      "eval_mean_token_accuracy": 0.10195983114006284,
      "eval_num_tokens": 906215.0,
      "eval_runtime": 2.6905,
      "eval_samples_per_second": 1319.07,
      "eval_steps_per_second": 165.023,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 11630,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 1378388957184000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}