{
  "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": 4.746951723098755,
      "epoch": 0.004297378599054577,
      "grad_norm": 13.0,
      "learning_rate": 2e-06,
      "loss": 14.3802,
      "mean_token_accuracy": 0.0,
      "num_tokens": 10107.0,
      "step": 5
    },
    {
      "entropy": 4.743826389312744,
      "epoch": 0.008594757198109154,
      "grad_norm": 14.125,
      "learning_rate": 4.5e-06,
      "loss": 14.1741,
      "mean_token_accuracy": 0.00023007302079349756,
      "num_tokens": 18391.0,
      "step": 10
    },
    {
      "entropy": 4.808784341812133,
      "epoch": 0.01289213579716373,
      "grad_norm": 17.5,
      "learning_rate": 7e-06,
      "loss": 13.9391,
      "mean_token_accuracy": 0.0,
      "num_tokens": 27061.0,
      "step": 15
    },
    {
      "entropy": 5.067050266265869,
      "epoch": 0.017189514396218308,
      "grad_norm": 28.5,
      "learning_rate": 9.5e-06,
      "loss": 13.3774,
      "mean_token_accuracy": 0.0,
      "num_tokens": 36339.0,
      "step": 20
    },
    {
      "entropy": 7.5024512767791744,
      "epoch": 0.021486892995272882,
      "grad_norm": 19.5,
      "learning_rate": 1.2e-05,
      "loss": 11.6591,
      "mean_token_accuracy": 0.00038444948149845003,
      "num_tokens": 45770.0,
      "step": 25
    },
    {
      "entropy": 10.366794681549072,
      "epoch": 0.02578427159432746,
      "grad_norm": 4.0625,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.7655,
      "mean_token_accuracy": 0.00122114981058985,
      "num_tokens": 54575.0,
      "step": 30
    },
    {
      "entropy": 10.686303997039795,
      "epoch": 0.030081650193382038,
      "grad_norm": 3.09375,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.5273,
      "mean_token_accuracy": 0.03648172654211521,
      "num_tokens": 66403.0,
      "step": 35
    },
    {
      "entropy": 10.672397136688232,
      "epoch": 0.034379028792436615,
      "grad_norm": 2.640625,
      "learning_rate": 1.95e-05,
      "loss": 10.1061,
      "mean_token_accuracy": 0.058901159465312956,
      "num_tokens": 76510.0,
      "step": 40
    },
    {
      "entropy": 10.515008449554443,
      "epoch": 0.03867640739149119,
      "grad_norm": 2.296875,
      "learning_rate": 2.2e-05,
      "loss": 9.8287,
      "mean_token_accuracy": 0.05614017099142075,
      "num_tokens": 84836.0,
      "step": 45
    },
    {
      "entropy": 10.411137008666993,
      "epoch": 0.042973785990545764,
      "grad_norm": 1.84375,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.6563,
      "mean_token_accuracy": 0.05396632887423038,
      "num_tokens": 93197.0,
      "step": 50
    },
    {
      "entropy": 10.430077075958252,
      "epoch": 0.047271164589600345,
      "grad_norm": 2.40625,
      "learning_rate": 2.7e-05,
      "loss": 9.5344,
      "mean_token_accuracy": 0.055140935629606244,
      "num_tokens": 101546.0,
      "step": 55
    },
    {
      "entropy": 10.39182996749878,
      "epoch": 0.05156854318865492,
      "grad_norm": 1.8203125,
      "learning_rate": 2.95e-05,
      "loss": 9.5444,
      "mean_token_accuracy": 0.05580790489912033,
      "num_tokens": 111703.0,
      "step": 60
    },
    {
      "entropy": 10.338463401794433,
      "epoch": 0.055865921787709494,
      "grad_norm": 1.7734375,
      "learning_rate": 3.2e-05,
      "loss": 9.4004,
      "mean_token_accuracy": 0.0589165486395359,
      "num_tokens": 119894.0,
      "step": 65
    },
    {
      "entropy": 10.395281219482422,
      "epoch": 0.060163300386764075,
      "grad_norm": 1.921875,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.321,
      "mean_token_accuracy": 0.0635790053755045,
      "num_tokens": 128885.0,
      "step": 70
    },
    {
      "entropy": 10.310928249359131,
      "epoch": 0.06446067898581866,
      "grad_norm": 1.7109375,
      "learning_rate": 3.7e-05,
      "loss": 9.2708,
      "mean_token_accuracy": 0.05928411558270454,
      "num_tokens": 138106.0,
      "step": 75
    },
    {
      "entropy": 10.260056686401366,
      "epoch": 0.06875805758487323,
      "grad_norm": 1.65625,
      "learning_rate": 3.95e-05,
      "loss": 9.2086,
      "mean_token_accuracy": 0.0639796681702137,
      "num_tokens": 146691.0,
      "step": 80
    },
    {
      "entropy": 10.25273675918579,
      "epoch": 0.0730554361839278,
      "grad_norm": 1.671875,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.1145,
      "mean_token_accuracy": 0.07113314382731914,
      "num_tokens": 155792.0,
      "step": 85
    },
    {
      "entropy": 10.214042377471923,
      "epoch": 0.07735281478298238,
      "grad_norm": 1.5234375,
      "learning_rate": 4.45e-05,
      "loss": 9.1291,
      "mean_token_accuracy": 0.0655292171984911,
      "num_tokens": 166944.0,
      "step": 90
    },
    {
      "entropy": 10.106289291381836,
      "epoch": 0.08165019338203695,
      "grad_norm": 1.9296875,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 8.9072,
      "mean_token_accuracy": 0.0739534068852663,
      "num_tokens": 175303.0,
      "step": 95
    },
    {
      "entropy": 10.038150310516357,
      "epoch": 0.08594757198109153,
      "grad_norm": 1.4375,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 8.8898,
      "mean_token_accuracy": 0.0677933320403099,
      "num_tokens": 184708.0,
      "step": 100
    },
    {
      "entropy": 10.01686487197876,
      "epoch": 0.09024495058014612,
      "grad_norm": 1.46875,
      "learning_rate": 5.2e-05,
      "loss": 8.7892,
      "mean_token_accuracy": 0.06626052372157573,
      "num_tokens": 193835.0,
      "step": 105
    },
    {
      "entropy": 10.002698516845703,
      "epoch": 0.09454232917920069,
      "grad_norm": 1.546875,
      "learning_rate": 5.45e-05,
      "loss": 8.6916,
      "mean_token_accuracy": 0.07468680031597615,
      "num_tokens": 203344.0,
      "step": 110
    },
    {
      "entropy": 9.896427822113036,
      "epoch": 0.09883970777825526,
      "grad_norm": 1.2578125,
      "learning_rate": 5.7e-05,
      "loss": 8.6808,
      "mean_token_accuracy": 0.06314092017710209,
      "num_tokens": 213048.0,
      "step": 115
    },
    {
      "entropy": 9.836742782592774,
      "epoch": 0.10313708637730984,
      "grad_norm": 1.265625,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.5044,
      "mean_token_accuracy": 0.0604202140122652,
      "num_tokens": 221784.0,
      "step": 120
    },
    {
      "entropy": 9.552239894866943,
      "epoch": 0.10743446497636441,
      "grad_norm": 1.1484375,
      "learning_rate": 6.2e-05,
      "loss": 8.3827,
      "mean_token_accuracy": 0.07485125958919525,
      "num_tokens": 230971.0,
      "step": 125
    },
    {
      "entropy": 9.533222961425782,
      "epoch": 0.11173184357541899,
      "grad_norm": 1.1484375,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.2984,
      "mean_token_accuracy": 0.06787660419940948,
      "num_tokens": 240524.0,
      "step": 130
    },
    {
      "entropy": 9.320106983184814,
      "epoch": 0.11602922217447358,
      "grad_norm": 1.21875,
      "learning_rate": 6.7e-05,
      "loss": 8.2114,
      "mean_token_accuracy": 0.07236036621034145,
      "num_tokens": 249220.0,
      "step": 135
    },
    {
      "entropy": 9.246935367584229,
      "epoch": 0.12032660077352815,
      "grad_norm": 1.1640625,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.205,
      "mean_token_accuracy": 0.06581656485795975,
      "num_tokens": 258934.0,
      "step": 140
    },
    {
      "entropy": 9.093988609313964,
      "epoch": 0.12462397937258272,
      "grad_norm": 1.375,
      "learning_rate": 7.2e-05,
      "loss": 8.1081,
      "mean_token_accuracy": 0.07143516950309277,
      "num_tokens": 267680.0,
      "step": 145
    },
    {
      "entropy": 8.769672107696532,
      "epoch": 0.1289213579716373,
      "grad_norm": 1.1171875,
      "learning_rate": 7.45e-05,
      "loss": 8.0668,
      "mean_token_accuracy": 0.07136639766395092,
      "num_tokens": 276227.0,
      "step": 150
    },
    {
      "entropy": 8.74085454940796,
      "epoch": 0.1332187365706919,
      "grad_norm": 1.0390625,
      "learning_rate": 7.7e-05,
      "loss": 7.9531,
      "mean_token_accuracy": 0.07765112966299056,
      "num_tokens": 286342.0,
      "step": 155
    },
    {
      "entropy": 8.63883180618286,
      "epoch": 0.13751611516974646,
      "grad_norm": 0.91015625,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.9755,
      "mean_token_accuracy": 0.06722700893878937,
      "num_tokens": 294994.0,
      "step": 160
    },
    {
      "entropy": 8.51505479812622,
      "epoch": 0.14181349376880104,
      "grad_norm": 0.92578125,
      "learning_rate": 8.2e-05,
      "loss": 7.9472,
      "mean_token_accuracy": 0.07361817210912705,
      "num_tokens": 303882.0,
      "step": 165
    },
    {
      "entropy": 8.39471378326416,
      "epoch": 0.1461108723678556,
      "grad_norm": 0.78515625,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.9246,
      "mean_token_accuracy": 0.07520690858364106,
      "num_tokens": 312515.0,
      "step": 170
    },
    {
      "entropy": 8.389386463165284,
      "epoch": 0.15040825096691018,
      "grad_norm": 1.0703125,
      "learning_rate": 8.7e-05,
      "loss": 7.9233,
      "mean_token_accuracy": 0.07540233507752418,
      "num_tokens": 320801.0,
      "step": 175
    },
    {
      "entropy": 8.254477882385254,
      "epoch": 0.15470562956596476,
      "grad_norm": 1.140625,
      "learning_rate": 8.95e-05,
      "loss": 7.9058,
      "mean_token_accuracy": 0.08120642676949501,
      "num_tokens": 329382.0,
      "step": 180
    },
    {
      "entropy": 8.332880115509033,
      "epoch": 0.15900300816501933,
      "grad_norm": 0.9296875,
      "learning_rate": 9.2e-05,
      "loss": 7.8804,
      "mean_token_accuracy": 0.07222829759120941,
      "num_tokens": 337894.0,
      "step": 185
    },
    {
      "entropy": 8.286204624176026,
      "epoch": 0.1633003867640739,
      "grad_norm": 1.21875,
      "learning_rate": 9.45e-05,
      "loss": 7.8675,
      "mean_token_accuracy": 0.0751982007175684,
      "num_tokens": 346380.0,
      "step": 190
    },
    {
      "entropy": 8.191093826293946,
      "epoch": 0.16759776536312848,
      "grad_norm": 0.9609375,
      "learning_rate": 9.7e-05,
      "loss": 7.9246,
      "mean_token_accuracy": 0.0726242907345295,
      "num_tokens": 356305.0,
      "step": 195
    },
    {
      "entropy": 8.269799137115479,
      "epoch": 0.17189514396218306,
      "grad_norm": 1.0859375,
      "learning_rate": 9.95e-05,
      "loss": 7.8754,
      "mean_token_accuracy": 0.07030960507690906,
      "num_tokens": 364899.0,
      "step": 200
    },
    {
      "entropy": 8.152498531341553,
      "epoch": 0.17619252256123766,
      "grad_norm": 0.98046875,
      "learning_rate": 0.000102,
      "loss": 7.8478,
      "mean_token_accuracy": 0.07710132971405984,
      "num_tokens": 373663.0,
      "step": 205
    },
    {
      "entropy": 8.213716077804566,
      "epoch": 0.18048990116029223,
      "grad_norm": 1.3125,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.8339,
      "mean_token_accuracy": 0.07559528909623622,
      "num_tokens": 382730.0,
      "step": 210
    },
    {
      "entropy": 8.200652503967286,
      "epoch": 0.1847872797593468,
      "grad_norm": 2.3125,
      "learning_rate": 0.000107,
      "loss": 7.8751,
      "mean_token_accuracy": 0.06925368532538415,
      "num_tokens": 392676.0,
      "step": 215
    },
    {
      "entropy": 7.960573291778564,
      "epoch": 0.18908465835840138,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001095,
      "loss": 7.8586,
      "mean_token_accuracy": 0.08359932452440262,
      "num_tokens": 401050.0,
      "step": 220
    },
    {
      "entropy": 8.224654483795167,
      "epoch": 0.19338203695745596,
      "grad_norm": 0.86328125,
      "learning_rate": 0.000112,
      "loss": 7.7944,
      "mean_token_accuracy": 0.0739112664014101,
      "num_tokens": 410009.0,
      "step": 225
    },
    {
      "entropy": 8.076114654541016,
      "epoch": 0.19767941555651053,
      "grad_norm": 0.96484375,
      "learning_rate": 0.0001145,
      "loss": 7.784,
      "mean_token_accuracy": 0.07774697132408619,
      "num_tokens": 419302.0,
      "step": 230
    },
    {
      "entropy": 8.134877395629882,
      "epoch": 0.2019767941555651,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.7035,
      "mean_token_accuracy": 0.0846225418150425,
      "num_tokens": 427296.0,
      "step": 235
    },
    {
      "entropy": 8.007131862640382,
      "epoch": 0.20627417275461968,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.8318,
      "mean_token_accuracy": 0.07436586394906045,
      "num_tokens": 436368.0,
      "step": 240
    },
    {
      "entropy": 8.062287092208862,
      "epoch": 0.21057155135367425,
      "grad_norm": 1.5703125,
      "learning_rate": 0.000122,
      "loss": 7.7528,
      "mean_token_accuracy": 0.0802234098315239,
      "num_tokens": 445535.0,
      "step": 245
    },
    {
      "entropy": 8.11290283203125,
      "epoch": 0.21486892995272883,
      "grad_norm": 0.921875,
      "learning_rate": 0.0001245,
      "loss": 7.7292,
      "mean_token_accuracy": 0.07871693558990955,
      "num_tokens": 454769.0,
      "step": 250
    },
    {
      "entropy": 8.053960275650024,
      "epoch": 0.2191663085517834,
      "grad_norm": 1.15625,
      "learning_rate": 0.000127,
      "loss": 7.7547,
      "mean_token_accuracy": 0.08017503693699837,
      "num_tokens": 463975.0,
      "step": 255
    },
    {
      "entropy": 7.906766176223755,
      "epoch": 0.22346368715083798,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0001295,
      "loss": 7.7438,
      "mean_token_accuracy": 0.08368083834648132,
      "num_tokens": 472899.0,
      "step": 260
    },
    {
      "entropy": 8.039681100845337,
      "epoch": 0.22776106574989258,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000132,
      "loss": 7.7418,
      "mean_token_accuracy": 0.07471806854009629,
      "num_tokens": 481556.0,
      "step": 265
    },
    {
      "entropy": 8.029216766357422,
      "epoch": 0.23205844434894715,
      "grad_norm": 1.375,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.7123,
      "mean_token_accuracy": 0.08060996606945992,
      "num_tokens": 490253.0,
      "step": 270
    },
    {
      "entropy": 8.084418487548827,
      "epoch": 0.23635582294800173,
      "grad_norm": 1.296875,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.7157,
      "mean_token_accuracy": 0.07992063909769058,
      "num_tokens": 498444.0,
      "step": 275
    },
    {
      "entropy": 7.9231773853302006,
      "epoch": 0.2406532015470563,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0001395,
      "loss": 7.664,
      "mean_token_accuracy": 0.08332347348332406,
      "num_tokens": 508330.0,
      "step": 280
    },
    {
      "entropy": 7.949900054931641,
      "epoch": 0.24495058014611087,
      "grad_norm": 1.203125,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.7586,
      "mean_token_accuracy": 0.0789482720196247,
      "num_tokens": 517900.0,
      "step": 285
    },
    {
      "entropy": 7.986289691925049,
      "epoch": 0.24924795874516545,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0001445,
      "loss": 7.7176,
      "mean_token_accuracy": 0.07970602363348007,
      "num_tokens": 527808.0,
      "step": 290
    },
    {
      "entropy": 7.944300651550293,
      "epoch": 0.25354533734422,
      "grad_norm": 1.3046875,
      "learning_rate": 0.000147,
      "loss": 7.7025,
      "mean_token_accuracy": 0.074923125654459,
      "num_tokens": 536931.0,
      "step": 295
    },
    {
      "entropy": 8.035796642303467,
      "epoch": 0.2578427159432746,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0001495,
      "loss": 7.7166,
      "mean_token_accuracy": 0.08002732172608376,
      "num_tokens": 545758.0,
      "step": 300
    },
    {
      "entropy": 7.967339134216308,
      "epoch": 0.26214009454232917,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000152,
      "loss": 7.735,
      "mean_token_accuracy": 0.08182198479771614,
      "num_tokens": 555165.0,
      "step": 305
    },
    {
      "entropy": 7.954096126556396,
      "epoch": 0.2664374731413838,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.6505,
      "mean_token_accuracy": 0.08079984113574028,
      "num_tokens": 564719.0,
      "step": 310
    },
    {
      "entropy": 8.011483335494995,
      "epoch": 0.2707348517404383,
      "grad_norm": 1.59375,
      "learning_rate": 0.000157,
      "loss": 7.6203,
      "mean_token_accuracy": 0.0855506956577301,
      "num_tokens": 573572.0,
      "step": 315
    },
    {
      "entropy": 7.915408372879028,
      "epoch": 0.2750322303394929,
      "grad_norm": 1.203125,
      "learning_rate": 0.0001595,
      "loss": 7.7815,
      "mean_token_accuracy": 0.07522618100047111,
      "num_tokens": 581497.0,
      "step": 320
    },
    {
      "entropy": 7.911842298507691,
      "epoch": 0.27932960893854747,
      "grad_norm": 1.28125,
      "learning_rate": 0.000162,
      "loss": 7.6282,
      "mean_token_accuracy": 0.08246761485934258,
      "num_tokens": 591107.0,
      "step": 325
    },
    {
      "entropy": 7.908317279815674,
      "epoch": 0.28362698753760207,
      "grad_norm": 0.98046875,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.6727,
      "mean_token_accuracy": 0.07925951480865479,
      "num_tokens": 600241.0,
      "step": 330
    },
    {
      "entropy": 7.992547035217285,
      "epoch": 0.2879243661366566,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.5985,
      "mean_token_accuracy": 0.08225269913673401,
      "num_tokens": 608697.0,
      "step": 335
    },
    {
      "entropy": 7.899400424957276,
      "epoch": 0.2922217447357112,
      "grad_norm": 1.078125,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.5755,
      "mean_token_accuracy": 0.08702421039342881,
      "num_tokens": 617275.0,
      "step": 340
    },
    {
      "entropy": 7.919580078125,
      "epoch": 0.29651912333476577,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.6679,
      "mean_token_accuracy": 0.08152761459350585,
      "num_tokens": 626644.0,
      "step": 345
    },
    {
      "entropy": 7.855055665969848,
      "epoch": 0.30081650193382037,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.5941,
      "mean_token_accuracy": 0.08607768341898918,
      "num_tokens": 635110.0,
      "step": 350
    },
    {
      "entropy": 7.904864168167114,
      "epoch": 0.30511388053287497,
      "grad_norm": 1.140625,
      "learning_rate": 0.000177,
      "loss": 7.731,
      "mean_token_accuracy": 0.08116863258183002,
      "num_tokens": 644746.0,
      "step": 355
    },
    {
      "entropy": 8.003858804702759,
      "epoch": 0.3094112591319295,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0001795,
      "loss": 7.615,
      "mean_token_accuracy": 0.08461246490478516,
      "num_tokens": 654281.0,
      "step": 360
    },
    {
      "entropy": 7.807305002212525,
      "epoch": 0.3137086377309841,
      "grad_norm": 1.109375,
      "learning_rate": 0.000182,
      "loss": 7.6127,
      "mean_token_accuracy": 0.08584560602903366,
      "num_tokens": 663174.0,
      "step": 365
    },
    {
      "entropy": 7.868645715713501,
      "epoch": 0.31800601633003867,
      "grad_norm": 1.3125,
      "learning_rate": 0.0001845,
      "loss": 7.5401,
      "mean_token_accuracy": 0.08367656841874123,
      "num_tokens": 672178.0,
      "step": 370
    },
    {
      "entropy": 7.838464975357056,
      "epoch": 0.32230339492909327,
      "grad_norm": 1.09375,
      "learning_rate": 0.000187,
      "loss": 7.5441,
      "mean_token_accuracy": 0.08873862400650978,
      "num_tokens": 681323.0,
      "step": 375
    },
    {
      "entropy": 7.861468744277954,
      "epoch": 0.3266007735281478,
      "grad_norm": 1.015625,
      "learning_rate": 0.0001895,
      "loss": 7.4599,
      "mean_token_accuracy": 0.08782187923789024,
      "num_tokens": 690461.0,
      "step": 380
    },
    {
      "entropy": 7.801782035827637,
      "epoch": 0.3308981521272024,
      "grad_norm": 1.9375,
      "learning_rate": 0.000192,
      "loss": 7.5001,
      "mean_token_accuracy": 0.08662289157509803,
      "num_tokens": 699199.0,
      "step": 385
    },
    {
      "entropy": 7.801443576812744,
      "epoch": 0.33519553072625696,
      "grad_norm": 1.453125,
      "learning_rate": 0.0001945,
      "loss": 7.4921,
      "mean_token_accuracy": 0.09190349280834198,
      "num_tokens": 707949.0,
      "step": 390
    },
    {
      "entropy": 7.831652879714966,
      "epoch": 0.33949290932531156,
      "grad_norm": 1.203125,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.5308,
      "mean_token_accuracy": 0.08901702687144279,
      "num_tokens": 715752.0,
      "step": 395
    },
    {
      "entropy": 7.8149333000183105,
      "epoch": 0.3437902879243661,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.4733,
      "mean_token_accuracy": 0.08961250334978103,
      "num_tokens": 724416.0,
      "step": 400
    },
    {
      "entropy": 7.810607194900513,
      "epoch": 0.3480876665234207,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000202,
      "loss": 7.5157,
      "mean_token_accuracy": 0.08556607961654664,
      "num_tokens": 733116.0,
      "step": 405
    },
    {
      "entropy": 7.813943815231323,
      "epoch": 0.3523850451224753,
      "grad_norm": 1.203125,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.4905,
      "mean_token_accuracy": 0.08932617083191871,
      "num_tokens": 742093.0,
      "step": 410
    },
    {
      "entropy": 7.833597850799561,
      "epoch": 0.35668242372152986,
      "grad_norm": 1.078125,
      "learning_rate": 0.000207,
      "loss": 7.4856,
      "mean_token_accuracy": 0.08866851031780243,
      "num_tokens": 750402.0,
      "step": 415
    },
    {
      "entropy": 7.651254415512085,
      "epoch": 0.36097980232058446,
      "grad_norm": 1.234375,
      "learning_rate": 0.0002095,
      "loss": 7.4363,
      "mean_token_accuracy": 0.09088600948452949,
      "num_tokens": 760961.0,
      "step": 420
    },
    {
      "entropy": 7.848704862594604,
      "epoch": 0.365277180919639,
      "grad_norm": 0.9765625,
      "learning_rate": 0.000212,
      "loss": 7.5138,
      "mean_token_accuracy": 0.08746314346790314,
      "num_tokens": 770554.0,
      "step": 425
    },
    {
      "entropy": 7.62291374206543,
      "epoch": 0.3695745595186936,
      "grad_norm": 1.390625,
      "learning_rate": 0.0002145,
      "loss": 7.4938,
      "mean_token_accuracy": 0.09328901097178459,
      "num_tokens": 779172.0,
      "step": 430
    },
    {
      "entropy": 7.798684120178223,
      "epoch": 0.37387193811774816,
      "grad_norm": 1.265625,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.5411,
      "mean_token_accuracy": 0.0797388345003128,
      "num_tokens": 788040.0,
      "step": 435
    },
    {
      "entropy": 7.799862670898437,
      "epoch": 0.37816931671680276,
      "grad_norm": 1.7109375,
      "learning_rate": 0.0002195,
      "loss": 7.4367,
      "mean_token_accuracy": 0.09049512967467307,
      "num_tokens": 796786.0,
      "step": 440
    },
    {
      "entropy": 7.653696584701538,
      "epoch": 0.3824666953158573,
      "grad_norm": 1.21875,
      "learning_rate": 0.000222,
      "loss": 7.4549,
      "mean_token_accuracy": 0.08962092027068139,
      "num_tokens": 805520.0,
      "step": 445
    },
    {
      "entropy": 7.74529128074646,
      "epoch": 0.3867640739149119,
      "grad_norm": 1.296875,
      "learning_rate": 0.0002245,
      "loss": 7.3698,
      "mean_token_accuracy": 0.09231138080358506,
      "num_tokens": 814939.0,
      "step": 450
    },
    {
      "entropy": 7.6202319145202635,
      "epoch": 0.39106145251396646,
      "grad_norm": 1.171875,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.3903,
      "mean_token_accuracy": 0.08881158530712127,
      "num_tokens": 823862.0,
      "step": 455
    },
    {
      "entropy": 7.745624685287476,
      "epoch": 0.39535883111302106,
      "grad_norm": 1.140625,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.3957,
      "mean_token_accuracy": 0.09272652640938758,
      "num_tokens": 832820.0,
      "step": 460
    },
    {
      "entropy": 7.745703077316284,
      "epoch": 0.39965620971207566,
      "grad_norm": 1.125,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.3724,
      "mean_token_accuracy": 0.09544146358966828,
      "num_tokens": 841538.0,
      "step": 465
    },
    {
      "entropy": 7.645022964477539,
      "epoch": 0.4039535883111302,
      "grad_norm": 1.046875,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.4799,
      "mean_token_accuracy": 0.08852436989545823,
      "num_tokens": 851123.0,
      "step": 470
    },
    {
      "entropy": 7.723429012298584,
      "epoch": 0.4082509669101848,
      "grad_norm": 1.2421875,
      "learning_rate": 0.000237,
      "loss": 7.4569,
      "mean_token_accuracy": 0.09157502874732018,
      "num_tokens": 860357.0,
      "step": 475
    },
    {
      "entropy": 7.702331590652466,
      "epoch": 0.41254834550923936,
      "grad_norm": 1.265625,
      "learning_rate": 0.0002395,
      "loss": 7.3553,
      "mean_token_accuracy": 0.09141395911574364,
      "num_tokens": 869980.0,
      "step": 480
    },
    {
      "entropy": 7.594449472427368,
      "epoch": 0.41684572410829396,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000242,
      "loss": 7.3152,
      "mean_token_accuracy": 0.09529538601636886,
      "num_tokens": 878250.0,
      "step": 485
    },
    {
      "entropy": 7.647209882736206,
      "epoch": 0.4211431027073485,
      "grad_norm": 1.6484375,
      "learning_rate": 0.0002445,
      "loss": 7.432,
      "mean_token_accuracy": 0.08998423144221306,
      "num_tokens": 887624.0,
      "step": 490
    },
    {
      "entropy": 7.620798921585083,
      "epoch": 0.4254404813064031,
      "grad_norm": 1.15625,
      "learning_rate": 0.000247,
      "loss": 7.3811,
      "mean_token_accuracy": 0.09268759191036224,
      "num_tokens": 897120.0,
      "step": 495
    },
    {
      "entropy": 7.560871362686157,
      "epoch": 0.42973785990545765,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0002495,
      "loss": 7.3499,
      "mean_token_accuracy": 0.09775018766522407,
      "num_tokens": 906215.0,
      "step": 500
    },
    {
      "epoch": 0.42973785990545765,
      "eval_entropy": 7.452849494444357,
      "eval_loss": 7.401772499084473,
      "eval_mean_token_accuracy": 0.09653489479610512,
      "eval_num_tokens": 906215.0,
      "eval_runtime": 2.6878,
      "eval_samples_per_second": 1320.408,
      "eval_steps_per_second": 165.191,
      "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
}