{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02567525932011913,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.742582702636719,
      "epoch": 0.00025675259320119136,
      "grad_norm": 5.15625,
      "learning_rate": 2e-06,
      "loss": 10.7385,
      "mean_token_accuracy": 0.0,
      "num_tokens": 8466.0,
      "step": 5
    },
    {
      "entropy": 10.742582893371582,
      "epoch": 0.0005135051864023827,
      "grad_norm": 5.375,
      "learning_rate": 4.5e-06,
      "loss": 10.7383,
      "mean_token_accuracy": 0.0,
      "num_tokens": 17819.0,
      "step": 10
    },
    {
      "entropy": 10.742578315734864,
      "epoch": 0.000770257779603574,
      "grad_norm": 5.15625,
      "learning_rate": 7e-06,
      "loss": 10.7074,
      "mean_token_accuracy": 8.474576170556248e-05,
      "num_tokens": 26701.0,
      "step": 15
    },
    {
      "entropy": 10.7426007270813,
      "epoch": 0.0010270103728047654,
      "grad_norm": 4.96875,
      "learning_rate": 9.5e-06,
      "loss": 10.6576,
      "mean_token_accuracy": 0.0011235648184083403,
      "num_tokens": 35386.0,
      "step": 20
    },
    {
      "entropy": 10.742522716522217,
      "epoch": 0.0012837629660059566,
      "grad_norm": 4.8125,
      "learning_rate": 1.2e-05,
      "loss": 10.5556,
      "mean_token_accuracy": 0.009902489895466715,
      "num_tokens": 44013.0,
      "step": 25
    },
    {
      "entropy": 10.742104721069335,
      "epoch": 0.001540515559207148,
      "grad_norm": 4.03125,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.4463,
      "mean_token_accuracy": 0.03455784637480974,
      "num_tokens": 52692.0,
      "step": 30
    },
    {
      "entropy": 10.740787982940674,
      "epoch": 0.0017972681524083393,
      "grad_norm": 3.6875,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.2846,
      "mean_token_accuracy": 0.04273700974881649,
      "num_tokens": 60741.0,
      "step": 35
    },
    {
      "entropy": 10.736649703979491,
      "epoch": 0.002054020745609531,
      "grad_norm": 2.5,
      "learning_rate": 1.95e-05,
      "loss": 10.1801,
      "mean_token_accuracy": 0.04606366418302059,
      "num_tokens": 69580.0,
      "step": 40
    },
    {
      "entropy": 10.729912948608398,
      "epoch": 0.002310773338810722,
      "grad_norm": 2.421875,
      "learning_rate": 2.2e-05,
      "loss": 10.036,
      "mean_token_accuracy": 0.04552499800920486,
      "num_tokens": 77450.0,
      "step": 45
    },
    {
      "entropy": 10.72356538772583,
      "epoch": 0.002567525932011913,
      "grad_norm": 2.25,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.9714,
      "mean_token_accuracy": 0.04347024708986282,
      "num_tokens": 85519.0,
      "step": 50
    },
    {
      "entropy": 10.719997215270997,
      "epoch": 0.0028242785252131047,
      "grad_norm": 2.125,
      "learning_rate": 2.7e-05,
      "loss": 9.8927,
      "mean_token_accuracy": 0.04672105684876442,
      "num_tokens": 93628.0,
      "step": 55
    },
    {
      "entropy": 10.717273998260499,
      "epoch": 0.003081031118414296,
      "grad_norm": 1.984375,
      "learning_rate": 2.95e-05,
      "loss": 9.8626,
      "mean_token_accuracy": 0.04250718653202057,
      "num_tokens": 102441.0,
      "step": 60
    },
    {
      "entropy": 10.714400959014892,
      "epoch": 0.0033377837116154874,
      "grad_norm": 2.015625,
      "learning_rate": 3.2e-05,
      "loss": 9.7868,
      "mean_token_accuracy": 0.04955284185707569,
      "num_tokens": 111166.0,
      "step": 65
    },
    {
      "entropy": 10.709486484527588,
      "epoch": 0.0035945363048166786,
      "grad_norm": 1.8984375,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.7258,
      "mean_token_accuracy": 0.04404304698109627,
      "num_tokens": 119300.0,
      "step": 70
    },
    {
      "entropy": 10.703517818450928,
      "epoch": 0.00385128889801787,
      "grad_norm": 1.8046875,
      "learning_rate": 3.7e-05,
      "loss": 9.6956,
      "mean_token_accuracy": 0.04594614543020725,
      "num_tokens": 127959.0,
      "step": 75
    },
    {
      "entropy": 10.697421169281006,
      "epoch": 0.004108041491219062,
      "grad_norm": 1.84375,
      "learning_rate": 3.95e-05,
      "loss": 9.6217,
      "mean_token_accuracy": 0.047571105882525444,
      "num_tokens": 136631.0,
      "step": 80
    },
    {
      "entropy": 10.68674201965332,
      "epoch": 0.004364794084420253,
      "grad_norm": 1.90625,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.5111,
      "mean_token_accuracy": 0.057168309763073924,
      "num_tokens": 145023.0,
      "step": 85
    },
    {
      "entropy": 10.670315933227538,
      "epoch": 0.004621546677621444,
      "grad_norm": 1.9140625,
      "learning_rate": 4.45e-05,
      "loss": 9.4523,
      "mean_token_accuracy": 0.05657172314822674,
      "num_tokens": 154075.0,
      "step": 90
    },
    {
      "entropy": 10.65313549041748,
      "epoch": 0.004878299270822635,
      "grad_norm": 1.921875,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.3482,
      "mean_token_accuracy": 0.06485468745231629,
      "num_tokens": 162006.0,
      "step": 95
    },
    {
      "entropy": 10.625462627410888,
      "epoch": 0.005135051864023826,
      "grad_norm": 1.8125,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.2717,
      "mean_token_accuracy": 0.06588986031711101,
      "num_tokens": 170230.0,
      "step": 100
    },
    {
      "entropy": 10.582051181793213,
      "epoch": 0.005391804457225018,
      "grad_norm": 1.6796875,
      "learning_rate": 5.2e-05,
      "loss": 9.2423,
      "mean_token_accuracy": 0.05897444784641266,
      "num_tokens": 179215.0,
      "step": 105
    },
    {
      "entropy": 10.52384090423584,
      "epoch": 0.0056485570504262094,
      "grad_norm": 1.7109375,
      "learning_rate": 5.45e-05,
      "loss": 9.1095,
      "mean_token_accuracy": 0.06802426725625992,
      "num_tokens": 187858.0,
      "step": 110
    },
    {
      "entropy": 10.461370754241944,
      "epoch": 0.005905309643627401,
      "grad_norm": 1.6171875,
      "learning_rate": 5.7e-05,
      "loss": 9.0136,
      "mean_token_accuracy": 0.06227913834154606,
      "num_tokens": 196198.0,
      "step": 115
    },
    {
      "entropy": 10.423934841156006,
      "epoch": 0.006162062236828592,
      "grad_norm": 1.7890625,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.8603,
      "mean_token_accuracy": 0.06186963692307472,
      "num_tokens": 204940.0,
      "step": 120
    },
    {
      "entropy": 10.381671047210693,
      "epoch": 0.006418814830029783,
      "grad_norm": 1.4921875,
      "learning_rate": 6.2e-05,
      "loss": 8.7743,
      "mean_token_accuracy": 0.0610227856785059,
      "num_tokens": 213092.0,
      "step": 125
    },
    {
      "entropy": 10.294575500488282,
      "epoch": 0.006675567423230975,
      "grad_norm": 1.484375,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.5688,
      "mean_token_accuracy": 0.06969367675483226,
      "num_tokens": 220978.0,
      "step": 130
    },
    {
      "entropy": 10.18680181503296,
      "epoch": 0.006932320016432166,
      "grad_norm": 1.4140625,
      "learning_rate": 6.7e-05,
      "loss": 8.5845,
      "mean_token_accuracy": 0.06069661751389503,
      "num_tokens": 229852.0,
      "step": 135
    },
    {
      "entropy": 10.096609592437744,
      "epoch": 0.007189072609633357,
      "grad_norm": 1.4609375,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.4392,
      "mean_token_accuracy": 0.06324404701590539,
      "num_tokens": 238908.0,
      "step": 140
    },
    {
      "entropy": 9.960357856750488,
      "epoch": 0.007445825202834548,
      "grad_norm": 1.4609375,
      "learning_rate": 7.2e-05,
      "loss": 8.3607,
      "mean_token_accuracy": 0.06009394600987435,
      "num_tokens": 248473.0,
      "step": 145
    },
    {
      "entropy": 9.86625270843506,
      "epoch": 0.00770257779603574,
      "grad_norm": 1.2109375,
      "learning_rate": 7.45e-05,
      "loss": 8.2554,
      "mean_token_accuracy": 0.06259206980466843,
      "num_tokens": 257210.0,
      "step": 150
    },
    {
      "entropy": 9.693745231628418,
      "epoch": 0.007959330389236931,
      "grad_norm": 1.0390625,
      "learning_rate": 7.7e-05,
      "loss": 8.1019,
      "mean_token_accuracy": 0.06411121524870396,
      "num_tokens": 266677.0,
      "step": 155
    },
    {
      "entropy": 9.491777038574218,
      "epoch": 0.008216082982438123,
      "grad_norm": 1.0546875,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.9959,
      "mean_token_accuracy": 0.06184820123016834,
      "num_tokens": 275216.0,
      "step": 160
    },
    {
      "entropy": 9.286455821990966,
      "epoch": 0.008472835575639314,
      "grad_norm": 0.984375,
      "learning_rate": 8.2e-05,
      "loss": 7.9137,
      "mean_token_accuracy": 0.06522414833307266,
      "num_tokens": 283770.0,
      "step": 165
    },
    {
      "entropy": 9.112856197357178,
      "epoch": 0.008729588168840506,
      "grad_norm": 0.89453125,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.8781,
      "mean_token_accuracy": 0.06161203049123287,
      "num_tokens": 292414.0,
      "step": 170
    },
    {
      "entropy": 8.901847839355469,
      "epoch": 0.008986340762041696,
      "grad_norm": 0.97265625,
      "learning_rate": 8.7e-05,
      "loss": 7.7992,
      "mean_token_accuracy": 0.06540008261799812,
      "num_tokens": 300569.0,
      "step": 175
    },
    {
      "entropy": 8.703197193145751,
      "epoch": 0.009243093355242888,
      "grad_norm": 1.0546875,
      "learning_rate": 8.95e-05,
      "loss": 7.6644,
      "mean_token_accuracy": 0.06989255100488663,
      "num_tokens": 308285.0,
      "step": 180
    },
    {
      "entropy": 8.601799583435058,
      "epoch": 0.00949984594844408,
      "grad_norm": 0.859375,
      "learning_rate": 9.2e-05,
      "loss": 7.7802,
      "mean_token_accuracy": 0.06652609743177891,
      "num_tokens": 317558.0,
      "step": 185
    },
    {
      "entropy": 8.49561529159546,
      "epoch": 0.00975659854164527,
      "grad_norm": 0.74609375,
      "learning_rate": 9.45e-05,
      "loss": 7.6158,
      "mean_token_accuracy": 0.06920971758663655,
      "num_tokens": 326377.0,
      "step": 190
    },
    {
      "entropy": 8.364750003814697,
      "epoch": 0.010013351134846462,
      "grad_norm": 0.734375,
      "learning_rate": 9.7e-05,
      "loss": 7.7265,
      "mean_token_accuracy": 0.06648653373122215,
      "num_tokens": 334669.0,
      "step": 195
    },
    {
      "entropy": 8.294552993774413,
      "epoch": 0.010270103728047653,
      "grad_norm": 0.921875,
      "learning_rate": 9.95e-05,
      "loss": 7.5956,
      "mean_token_accuracy": 0.07071267962455749,
      "num_tokens": 343100.0,
      "step": 200
    },
    {
      "entropy": 8.269872093200684,
      "epoch": 0.010526856321248845,
      "grad_norm": 0.8671875,
      "learning_rate": 0.000102,
      "loss": 7.6108,
      "mean_token_accuracy": 0.07263344749808312,
      "num_tokens": 351447.0,
      "step": 205
    },
    {
      "entropy": 8.213550281524657,
      "epoch": 0.010783608914450037,
      "grad_norm": 0.8828125,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.5708,
      "mean_token_accuracy": 0.06988951861858368,
      "num_tokens": 360908.0,
      "step": 210
    },
    {
      "entropy": 8.182147026062012,
      "epoch": 0.011040361507651227,
      "grad_norm": 0.91796875,
      "learning_rate": 0.000107,
      "loss": 7.5837,
      "mean_token_accuracy": 0.06750233620405197,
      "num_tokens": 370075.0,
      "step": 215
    },
    {
      "entropy": 8.132856750488282,
      "epoch": 0.011297114100852419,
      "grad_norm": 0.90625,
      "learning_rate": 0.0001095,
      "loss": 7.4565,
      "mean_token_accuracy": 0.07424333952367305,
      "num_tokens": 378598.0,
      "step": 220
    },
    {
      "entropy": 8.098768615722657,
      "epoch": 0.01155386669405361,
      "grad_norm": 0.96484375,
      "learning_rate": 0.000112,
      "loss": 7.5533,
      "mean_token_accuracy": 0.07423756159842014,
      "num_tokens": 387177.0,
      "step": 225
    },
    {
      "entropy": 8.190262031555175,
      "epoch": 0.011810619287254801,
      "grad_norm": 0.9765625,
      "learning_rate": 0.0001145,
      "loss": 7.6521,
      "mean_token_accuracy": 0.06974112130701542,
      "num_tokens": 396017.0,
      "step": 230
    },
    {
      "entropy": 8.12903299331665,
      "epoch": 0.012067371880455993,
      "grad_norm": 0.8828125,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.5765,
      "mean_token_accuracy": 0.07110274769365788,
      "num_tokens": 405324.0,
      "step": 235
    },
    {
      "entropy": 8.074048614501953,
      "epoch": 0.012324124473657183,
      "grad_norm": 0.8671875,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.5065,
      "mean_token_accuracy": 0.07165832705795765,
      "num_tokens": 414633.0,
      "step": 240
    },
    {
      "entropy": 8.055518102645873,
      "epoch": 0.012580877066858375,
      "grad_norm": 0.92578125,
      "learning_rate": 0.000122,
      "loss": 7.558,
      "mean_token_accuracy": 0.06795871779322624,
      "num_tokens": 424088.0,
      "step": 245
    },
    {
      "entropy": 8.072611761093139,
      "epoch": 0.012837629660059566,
      "grad_norm": 1.03125,
      "learning_rate": 0.0001245,
      "loss": 7.5031,
      "mean_token_accuracy": 0.0740334302186966,
      "num_tokens": 432868.0,
      "step": 250
    },
    {
      "entropy": 8.065638113021851,
      "epoch": 0.013094382253260758,
      "grad_norm": 0.8828125,
      "learning_rate": 0.000127,
      "loss": 7.4989,
      "mean_token_accuracy": 0.07697901576757431,
      "num_tokens": 442282.0,
      "step": 255
    },
    {
      "entropy": 8.062051105499268,
      "epoch": 0.01335113484646195,
      "grad_norm": 1.015625,
      "learning_rate": 0.0001295,
      "loss": 7.4639,
      "mean_token_accuracy": 0.07005516327917576,
      "num_tokens": 451600.0,
      "step": 260
    },
    {
      "entropy": 7.881219291687012,
      "epoch": 0.01360788743966314,
      "grad_norm": 0.8125,
      "learning_rate": 0.000132,
      "loss": 7.4421,
      "mean_token_accuracy": 0.07474162802100182,
      "num_tokens": 461072.0,
      "step": 265
    },
    {
      "entropy": 8.112028455734253,
      "epoch": 0.013864640032864332,
      "grad_norm": 0.91015625,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.5392,
      "mean_token_accuracy": 0.07459446638822556,
      "num_tokens": 469793.0,
      "step": 270
    },
    {
      "entropy": 7.97756552696228,
      "epoch": 0.014121392626065524,
      "grad_norm": 0.890625,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.4663,
      "mean_token_accuracy": 0.07501543574035167,
      "num_tokens": 479147.0,
      "step": 275
    },
    {
      "entropy": 8.046127462387085,
      "epoch": 0.014378145219266714,
      "grad_norm": 0.98046875,
      "learning_rate": 0.0001395,
      "loss": 7.491,
      "mean_token_accuracy": 0.07903510183095933,
      "num_tokens": 487684.0,
      "step": 280
    },
    {
      "entropy": 7.984290552139282,
      "epoch": 0.014634897812467906,
      "grad_norm": 0.87890625,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.4167,
      "mean_token_accuracy": 0.07433984354138375,
      "num_tokens": 496806.0,
      "step": 285
    },
    {
      "entropy": 7.933219766616821,
      "epoch": 0.014891650405669097,
      "grad_norm": 0.953125,
      "learning_rate": 0.0001445,
      "loss": 7.4893,
      "mean_token_accuracy": 0.07593215778470039,
      "num_tokens": 505937.0,
      "step": 290
    },
    {
      "entropy": 7.9124115943908695,
      "epoch": 0.015148402998870289,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000147,
      "loss": 7.3239,
      "mean_token_accuracy": 0.07792473435401917,
      "num_tokens": 515503.0,
      "step": 295
    },
    {
      "entropy": 8.034483766555786,
      "epoch": 0.01540515559207148,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0001495,
      "loss": 7.3811,
      "mean_token_accuracy": 0.07625493034720421,
      "num_tokens": 524506.0,
      "step": 300
    },
    {
      "entropy": 7.836033296585083,
      "epoch": 0.01566190818527267,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000152,
      "loss": 7.3815,
      "mean_token_accuracy": 0.0733937170356512,
      "num_tokens": 534009.0,
      "step": 305
    },
    {
      "entropy": 7.863447093963623,
      "epoch": 0.015918660778473863,
      "grad_norm": 0.9453125,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.266,
      "mean_token_accuracy": 0.07975648492574691,
      "num_tokens": 543104.0,
      "step": 310
    },
    {
      "entropy": 7.837308692932129,
      "epoch": 0.016175413371675055,
      "grad_norm": 1.171875,
      "learning_rate": 0.000157,
      "loss": 7.2217,
      "mean_token_accuracy": 0.0892428256571293,
      "num_tokens": 551303.0,
      "step": 315
    },
    {
      "entropy": 7.922349071502685,
      "epoch": 0.016432165964876247,
      "grad_norm": 1.078125,
      "learning_rate": 0.0001595,
      "loss": 7.4125,
      "mean_token_accuracy": 0.08186463341116905,
      "num_tokens": 559361.0,
      "step": 320
    },
    {
      "entropy": 7.849794530868531,
      "epoch": 0.016688918558077435,
      "grad_norm": 1.0625,
      "learning_rate": 0.000162,
      "loss": 7.333,
      "mean_token_accuracy": 0.08158622235059738,
      "num_tokens": 568629.0,
      "step": 325
    },
    {
      "entropy": 7.817071199417114,
      "epoch": 0.016945671151278627,
      "grad_norm": 1.2265625,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.2763,
      "mean_token_accuracy": 0.08513593450188636,
      "num_tokens": 576776.0,
      "step": 330
    },
    {
      "entropy": 7.845745038986206,
      "epoch": 0.01720242374447982,
      "grad_norm": 1.265625,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.3776,
      "mean_token_accuracy": 0.07514606490731239,
      "num_tokens": 585970.0,
      "step": 335
    },
    {
      "entropy": 7.911917018890381,
      "epoch": 0.01745917633768101,
      "grad_norm": 0.9375,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.4101,
      "mean_token_accuracy": 0.07996492646634579,
      "num_tokens": 594837.0,
      "step": 340
    },
    {
      "entropy": 7.7797877311706545,
      "epoch": 0.017715928930882203,
      "grad_norm": 1.125,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.3007,
      "mean_token_accuracy": 0.08453992381691933,
      "num_tokens": 602584.0,
      "step": 345
    },
    {
      "entropy": 7.790009212493897,
      "epoch": 0.017972681524083392,
      "grad_norm": 1.0625,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.3112,
      "mean_token_accuracy": 0.08209161311388016,
      "num_tokens": 611461.0,
      "step": 350
    },
    {
      "entropy": 7.816317987442017,
      "epoch": 0.018229434117284584,
      "grad_norm": 1.0,
      "learning_rate": 0.000177,
      "loss": 7.2513,
      "mean_token_accuracy": 0.0919821560382843,
      "num_tokens": 619873.0,
      "step": 355
    },
    {
      "entropy": 7.7200432300567625,
      "epoch": 0.018486186710485776,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0001795,
      "loss": 7.2821,
      "mean_token_accuracy": 0.08631467223167419,
      "num_tokens": 628487.0,
      "step": 360
    },
    {
      "entropy": 7.797741556167603,
      "epoch": 0.018742939303686968,
      "grad_norm": 1.03125,
      "learning_rate": 0.000182,
      "loss": 7.2589,
      "mean_token_accuracy": 0.08670427426695823,
      "num_tokens": 638162.0,
      "step": 365
    },
    {
      "entropy": 7.808457946777343,
      "epoch": 0.01899969189688816,
      "grad_norm": 1.046875,
      "learning_rate": 0.0001845,
      "loss": 7.153,
      "mean_token_accuracy": 0.08735950589179993,
      "num_tokens": 646802.0,
      "step": 370
    },
    {
      "entropy": 7.710161352157593,
      "epoch": 0.01925644449008935,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000187,
      "loss": 7.2292,
      "mean_token_accuracy": 0.0810220967978239,
      "num_tokens": 655527.0,
      "step": 375
    },
    {
      "entropy": 7.7011494636535645,
      "epoch": 0.01951319708329054,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001895,
      "loss": 7.2127,
      "mean_token_accuracy": 0.08935043439269066,
      "num_tokens": 664001.0,
      "step": 380
    },
    {
      "entropy": 7.72194185256958,
      "epoch": 0.019769949676491733,
      "grad_norm": 1.0390625,
      "learning_rate": 0.000192,
      "loss": 7.1847,
      "mean_token_accuracy": 0.09060925990343094,
      "num_tokens": 672972.0,
      "step": 385
    },
    {
      "entropy": 7.752814483642578,
      "epoch": 0.020026702269692925,
      "grad_norm": 1.0625,
      "learning_rate": 0.0001945,
      "loss": 7.1859,
      "mean_token_accuracy": 0.08640384674072266,
      "num_tokens": 681841.0,
      "step": 390
    },
    {
      "entropy": 7.733091974258423,
      "epoch": 0.020283454862894117,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.2036,
      "mean_token_accuracy": 0.08569250404834747,
      "num_tokens": 690903.0,
      "step": 395
    },
    {
      "entropy": 7.624167728424072,
      "epoch": 0.020540207456095305,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.208,
      "mean_token_accuracy": 0.08355596587061882,
      "num_tokens": 700411.0,
      "step": 400
    },
    {
      "entropy": 7.67492446899414,
      "epoch": 0.020796960049296497,
      "grad_norm": 1.03125,
      "learning_rate": 0.000202,
      "loss": 7.107,
      "mean_token_accuracy": 0.08860503733158112,
      "num_tokens": 709062.0,
      "step": 405
    },
    {
      "entropy": 7.748419570922851,
      "epoch": 0.02105371264249769,
      "grad_norm": 1.015625,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.2563,
      "mean_token_accuracy": 0.0841764748096466,
      "num_tokens": 718726.0,
      "step": 410
    },
    {
      "entropy": 7.661073493957519,
      "epoch": 0.02131046523569888,
      "grad_norm": 1.203125,
      "learning_rate": 0.000207,
      "loss": 7.1345,
      "mean_token_accuracy": 0.0915317751467228,
      "num_tokens": 726710.0,
      "step": 415
    },
    {
      "entropy": 7.460268259048462,
      "epoch": 0.021567217828900073,
      "grad_norm": 1.03125,
      "learning_rate": 0.0002095,
      "loss": 7.1529,
      "mean_token_accuracy": 0.09219859838485718,
      "num_tokens": 735145.0,
      "step": 420
    },
    {
      "entropy": 7.778389644622803,
      "epoch": 0.021823970422101262,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000212,
      "loss": 7.2522,
      "mean_token_accuracy": 0.0854285180568695,
      "num_tokens": 744267.0,
      "step": 425
    },
    {
      "entropy": 7.646036958694458,
      "epoch": 0.022080723015302454,
      "grad_norm": 1.171875,
      "learning_rate": 0.0002145,
      "loss": 7.1583,
      "mean_token_accuracy": 0.08593368083238602,
      "num_tokens": 753253.0,
      "step": 430
    },
    {
      "entropy": 7.666396236419677,
      "epoch": 0.022337475608503646,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.1065,
      "mean_token_accuracy": 0.09268246218562126,
      "num_tokens": 761697.0,
      "step": 435
    },
    {
      "entropy": 7.581840705871582,
      "epoch": 0.022594228201704838,
      "grad_norm": 1.15625,
      "learning_rate": 0.0002195,
      "loss": 7.0921,
      "mean_token_accuracy": 0.09590916931629181,
      "num_tokens": 769745.0,
      "step": 440
    },
    {
      "entropy": 7.527474021911621,
      "epoch": 0.02285098079490603,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000222,
      "loss": 7.0425,
      "mean_token_accuracy": 0.0901702880859375,
      "num_tokens": 778474.0,
      "step": 445
    },
    {
      "entropy": 7.621454095840454,
      "epoch": 0.02310773338810722,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0002245,
      "loss": 7.0576,
      "mean_token_accuracy": 0.09153895452618599,
      "num_tokens": 786581.0,
      "step": 450
    },
    {
      "entropy": 7.626477289199829,
      "epoch": 0.02336448598130841,
      "grad_norm": 1.140625,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.1844,
      "mean_token_accuracy": 0.08645047172904015,
      "num_tokens": 795359.0,
      "step": 455
    },
    {
      "entropy": 7.494252109527588,
      "epoch": 0.023621238574509602,
      "grad_norm": 1.0625,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.031,
      "mean_token_accuracy": 0.09843903109431267,
      "num_tokens": 802836.0,
      "step": 460
    },
    {
      "entropy": 7.607794904708863,
      "epoch": 0.023877991167710794,
      "grad_norm": 1.0625,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.0743,
      "mean_token_accuracy": 0.09356487020850182,
      "num_tokens": 811749.0,
      "step": 465
    },
    {
      "entropy": 7.594829416275024,
      "epoch": 0.024134743760911986,
      "grad_norm": 1.109375,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.0839,
      "mean_token_accuracy": 0.09629017040133477,
      "num_tokens": 820315.0,
      "step": 470
    },
    {
      "entropy": 7.577248907089233,
      "epoch": 0.024391496354113175,
      "grad_norm": 1.109375,
      "learning_rate": 0.000237,
      "loss": 7.0196,
      "mean_token_accuracy": 0.09056874141097068,
      "num_tokens": 828983.0,
      "step": 475
    },
    {
      "entropy": 7.597412490844727,
      "epoch": 0.024648248947314367,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0002395,
      "loss": 7.1117,
      "mean_token_accuracy": 0.09410159885883332,
      "num_tokens": 838622.0,
      "step": 480
    },
    {
      "entropy": 7.545994901657105,
      "epoch": 0.02490500154051556,
      "grad_norm": 0.98828125,
      "learning_rate": 0.000242,
      "loss": 7.0061,
      "mean_token_accuracy": 0.09935126826167107,
      "num_tokens": 848037.0,
      "step": 485
    },
    {
      "entropy": 7.420415019989013,
      "epoch": 0.02516175413371675,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0002445,
      "loss": 6.9918,
      "mean_token_accuracy": 0.09526313245296478,
      "num_tokens": 857048.0,
      "step": 490
    },
    {
      "entropy": 7.4686620235443115,
      "epoch": 0.025418506726917943,
      "grad_norm": 1.0625,
      "learning_rate": 0.000247,
      "loss": 6.907,
      "mean_token_accuracy": 0.09526302069425582,
      "num_tokens": 865120.0,
      "step": 495
    },
    {
      "entropy": 7.445110416412353,
      "epoch": 0.02567525932011913,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0002495,
      "loss": 7.0197,
      "mean_token_accuracy": 0.0922734022140503,
      "num_tokens": 874061.0,
      "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": 176823456399360.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}