{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.051436360363140705,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.742102813720702,
      "epoch": 0.0002571818018157035,
      "grad_norm": 5.21875,
      "learning_rate": 2e-06,
      "loss": 10.7614,
      "mean_token_accuracy": 8.620689623057842e-05,
      "num_tokens": 9573.0,
      "step": 5
    },
    {
      "entropy": 10.742151069641114,
      "epoch": 0.000514363603631407,
      "grad_norm": 4.84375,
      "learning_rate": 4.5e-06,
      "loss": 10.7583,
      "mean_token_accuracy": 0.0,
      "num_tokens": 18933.0,
      "step": 10
    },
    {
      "entropy": 10.742130088806153,
      "epoch": 0.0007715454054471106,
      "grad_norm": 5.21875,
      "learning_rate": 7e-06,
      "loss": 10.7448,
      "mean_token_accuracy": 0.0,
      "num_tokens": 29028.0,
      "step": 15
    },
    {
      "entropy": 10.742134284973144,
      "epoch": 0.001028727207262814,
      "grad_norm": 4.9375,
      "learning_rate": 9.5e-06,
      "loss": 10.6881,
      "mean_token_accuracy": 0.00012970168609172106,
      "num_tokens": 37987.0,
      "step": 20
    },
    {
      "entropy": 10.742049884796142,
      "epoch": 0.0012859090090785177,
      "grad_norm": 4.4375,
      "learning_rate": 1.2e-05,
      "loss": 10.5852,
      "mean_token_accuracy": 0.0029032987426035107,
      "num_tokens": 47163.0,
      "step": 25
    },
    {
      "entropy": 10.741710948944093,
      "epoch": 0.0015430908108942211,
      "grad_norm": 4.25,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.4809,
      "mean_token_accuracy": 0.02479298785328865,
      "num_tokens": 56096.0,
      "step": 30
    },
    {
      "entropy": 10.740671920776368,
      "epoch": 0.0018002726127099246,
      "grad_norm": 3.296875,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.3641,
      "mean_token_accuracy": 0.03960379287600517,
      "num_tokens": 65823.0,
      "step": 35
    },
    {
      "entropy": 10.737626838684083,
      "epoch": 0.002057454414525628,
      "grad_norm": 2.578125,
      "learning_rate": 1.95e-05,
      "loss": 10.2147,
      "mean_token_accuracy": 0.04078627172857523,
      "num_tokens": 75005.0,
      "step": 40
    },
    {
      "entropy": 10.73199462890625,
      "epoch": 0.0023146362163413317,
      "grad_norm": 2.53125,
      "learning_rate": 2.2e-05,
      "loss": 10.1015,
      "mean_token_accuracy": 0.04431910365819931,
      "num_tokens": 83340.0,
      "step": 45
    },
    {
      "entropy": 10.72521743774414,
      "epoch": 0.0025718180181570354,
      "grad_norm": 2.140625,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 10.0212,
      "mean_token_accuracy": 0.049253365769982335,
      "num_tokens": 92004.0,
      "step": 50
    },
    {
      "entropy": 10.719530010223389,
      "epoch": 0.0028289998199727386,
      "grad_norm": 2.078125,
      "learning_rate": 2.7e-05,
      "loss": 9.9673,
      "mean_token_accuracy": 0.04715999849140644,
      "num_tokens": 101196.0,
      "step": 55
    },
    {
      "entropy": 10.713758850097657,
      "epoch": 0.0030861816217884423,
      "grad_norm": 2.078125,
      "learning_rate": 2.95e-05,
      "loss": 9.8887,
      "mean_token_accuracy": 0.04930844120681286,
      "num_tokens": 109931.0,
      "step": 60
    },
    {
      "entropy": 10.709882545471192,
      "epoch": 0.003343363423604146,
      "grad_norm": 2.0625,
      "learning_rate": 3.2e-05,
      "loss": 9.8563,
      "mean_token_accuracy": 0.046213630586862564,
      "num_tokens": 118450.0,
      "step": 65
    },
    {
      "entropy": 10.70816535949707,
      "epoch": 0.003600545225419849,
      "grad_norm": 1.96875,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.7843,
      "mean_token_accuracy": 0.04638329595327377,
      "num_tokens": 127311.0,
      "step": 70
    },
    {
      "entropy": 10.705178928375243,
      "epoch": 0.003857727027235553,
      "grad_norm": 1.875,
      "learning_rate": 3.7e-05,
      "loss": 9.7153,
      "mean_token_accuracy": 0.05029761902987957,
      "num_tokens": 136529.0,
      "step": 75
    },
    {
      "entropy": 10.696865940093994,
      "epoch": 0.004114908829051256,
      "grad_norm": 1.828125,
      "learning_rate": 3.95e-05,
      "loss": 9.6593,
      "mean_token_accuracy": 0.050337107852101326,
      "num_tokens": 145754.0,
      "step": 80
    },
    {
      "entropy": 10.685219669342041,
      "epoch": 0.00437209063086696,
      "grad_norm": 1.8046875,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.6217,
      "mean_token_accuracy": 0.04981501027941704,
      "num_tokens": 155229.0,
      "step": 85
    },
    {
      "entropy": 10.669653797149659,
      "epoch": 0.004629272432682663,
      "grad_norm": 1.8984375,
      "learning_rate": 4.45e-05,
      "loss": 9.4894,
      "mean_token_accuracy": 0.06370054408907891,
      "num_tokens": 163766.0,
      "step": 90
    },
    {
      "entropy": 10.649745845794678,
      "epoch": 0.004886454234498367,
      "grad_norm": 1.7265625,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.4341,
      "mean_token_accuracy": 0.05732584930956364,
      "num_tokens": 172309.0,
      "step": 95
    },
    {
      "entropy": 10.618613624572754,
      "epoch": 0.005143636036314071,
      "grad_norm": 1.7421875,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.2855,
      "mean_token_accuracy": 0.06327233165502548,
      "num_tokens": 180242.0,
      "step": 100
    },
    {
      "entropy": 10.569914817810059,
      "epoch": 0.0054008178381297735,
      "grad_norm": 1.75,
      "learning_rate": 5.2e-05,
      "loss": 9.2324,
      "mean_token_accuracy": 0.060527439787983896,
      "num_tokens": 189044.0,
      "step": 105
    },
    {
      "entropy": 10.520080757141113,
      "epoch": 0.005657999639945477,
      "grad_norm": 1.5390625,
      "learning_rate": 5.45e-05,
      "loss": 9.1122,
      "mean_token_accuracy": 0.06187737137079239,
      "num_tokens": 197779.0,
      "step": 110
    },
    {
      "entropy": 10.468755054473878,
      "epoch": 0.005915181441761181,
      "grad_norm": 1.5859375,
      "learning_rate": 5.7e-05,
      "loss": 8.9561,
      "mean_token_accuracy": 0.06379008032381535,
      "num_tokens": 206025.0,
      "step": 115
    },
    {
      "entropy": 10.407035160064698,
      "epoch": 0.0061723632435768845,
      "grad_norm": 1.453125,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.9663,
      "mean_token_accuracy": 0.05617102049291134,
      "num_tokens": 216620.0,
      "step": 120
    },
    {
      "entropy": 10.3653733253479,
      "epoch": 0.006429545045392588,
      "grad_norm": 1.375,
      "learning_rate": 6.2e-05,
      "loss": 8.7968,
      "mean_token_accuracy": 0.059108608216047284,
      "num_tokens": 225654.0,
      "step": 125
    },
    {
      "entropy": 10.301421070098877,
      "epoch": 0.006686726847208292,
      "grad_norm": 1.4609375,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.6036,
      "mean_token_accuracy": 0.06164416745305061,
      "num_tokens": 233967.0,
      "step": 130
    },
    {
      "entropy": 10.185540676116943,
      "epoch": 0.006943908649023995,
      "grad_norm": 1.4140625,
      "learning_rate": 6.7e-05,
      "loss": 8.5469,
      "mean_token_accuracy": 0.06072752773761749,
      "num_tokens": 241911.0,
      "step": 135
    },
    {
      "entropy": 10.0550705909729,
      "epoch": 0.007201090450839698,
      "grad_norm": 1.25,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.4323,
      "mean_token_accuracy": 0.06439580023288727,
      "num_tokens": 250771.0,
      "step": 140
    },
    {
      "entropy": 9.967238235473634,
      "epoch": 0.007458272252655402,
      "grad_norm": 1.1171875,
      "learning_rate": 7.2e-05,
      "loss": 8.3391,
      "mean_token_accuracy": 0.06209088861942291,
      "num_tokens": 260036.0,
      "step": 145
    },
    {
      "entropy": 9.832792282104492,
      "epoch": 0.007715454054471106,
      "grad_norm": 1.1875,
      "learning_rate": 7.45e-05,
      "loss": 8.2272,
      "mean_token_accuracy": 0.06231529638171196,
      "num_tokens": 268614.0,
      "step": 150
    },
    {
      "entropy": 9.642397022247314,
      "epoch": 0.00797263585628681,
      "grad_norm": 1.0546875,
      "learning_rate": 7.7e-05,
      "loss": 8.085,
      "mean_token_accuracy": 0.06268828995525837,
      "num_tokens": 278205.0,
      "step": 155
    },
    {
      "entropy": 9.471720123291016,
      "epoch": 0.008229817658102512,
      "grad_norm": 1.109375,
      "learning_rate": 7.950000000000001e-05,
      "loss": 8.0285,
      "mean_token_accuracy": 0.054571619257330894,
      "num_tokens": 287369.0,
      "step": 160
    },
    {
      "entropy": 9.277729606628418,
      "epoch": 0.008486999459918217,
      "grad_norm": 0.9765625,
      "learning_rate": 8.2e-05,
      "loss": 7.8389,
      "mean_token_accuracy": 0.0658249743282795,
      "num_tokens": 295469.0,
      "step": 165
    },
    {
      "entropy": 9.065653324127197,
      "epoch": 0.00874418126173392,
      "grad_norm": 0.875,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.8802,
      "mean_token_accuracy": 0.05946259275078773,
      "num_tokens": 304108.0,
      "step": 170
    },
    {
      "entropy": 8.9242995262146,
      "epoch": 0.009001363063549624,
      "grad_norm": 0.83203125,
      "learning_rate": 8.7e-05,
      "loss": 7.7549,
      "mean_token_accuracy": 0.06102342195808887,
      "num_tokens": 312797.0,
      "step": 175
    },
    {
      "entropy": 8.724368000030518,
      "epoch": 0.009258544865365327,
      "grad_norm": 0.89453125,
      "learning_rate": 8.95e-05,
      "loss": 7.726,
      "mean_token_accuracy": 0.05993276461958885,
      "num_tokens": 321947.0,
      "step": 180
    },
    {
      "entropy": 8.550490474700927,
      "epoch": 0.00951572666718103,
      "grad_norm": 0.859375,
      "learning_rate": 9.2e-05,
      "loss": 7.7268,
      "mean_token_accuracy": 0.06107203662395477,
      "num_tokens": 330881.0,
      "step": 185
    },
    {
      "entropy": 8.48734483718872,
      "epoch": 0.009772908468996734,
      "grad_norm": 0.8125,
      "learning_rate": 9.45e-05,
      "loss": 7.6738,
      "mean_token_accuracy": 0.06392239518463612,
      "num_tokens": 339615.0,
      "step": 190
    },
    {
      "entropy": 8.382297706604003,
      "epoch": 0.010030090270812437,
      "grad_norm": 0.9765625,
      "learning_rate": 9.7e-05,
      "loss": 7.5319,
      "mean_token_accuracy": 0.0668424092233181,
      "num_tokens": 347445.0,
      "step": 195
    },
    {
      "entropy": 8.23064022064209,
      "epoch": 0.010287272072628141,
      "grad_norm": 0.81640625,
      "learning_rate": 9.95e-05,
      "loss": 7.6527,
      "mean_token_accuracy": 0.0642503272742033,
      "num_tokens": 356466.0,
      "step": 200
    },
    {
      "entropy": 8.293260860443116,
      "epoch": 0.010544453874443844,
      "grad_norm": 0.890625,
      "learning_rate": 0.000102,
      "loss": 7.6586,
      "mean_token_accuracy": 0.06924829706549644,
      "num_tokens": 364582.0,
      "step": 205
    },
    {
      "entropy": 8.233483600616456,
      "epoch": 0.010801635676259547,
      "grad_norm": 0.87890625,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.5999,
      "mean_token_accuracy": 0.06699038669466972,
      "num_tokens": 373816.0,
      "step": 210
    },
    {
      "entropy": 8.192768096923828,
      "epoch": 0.011058817478075252,
      "grad_norm": 0.96484375,
      "learning_rate": 0.000107,
      "loss": 7.6079,
      "mean_token_accuracy": 0.06721281111240388,
      "num_tokens": 382663.0,
      "step": 215
    },
    {
      "entropy": 8.15766954421997,
      "epoch": 0.011315999279890954,
      "grad_norm": 0.875,
      "learning_rate": 0.0001095,
      "loss": 7.5084,
      "mean_token_accuracy": 0.06859233565628528,
      "num_tokens": 391146.0,
      "step": 220
    },
    {
      "entropy": 8.103716373443604,
      "epoch": 0.011573181081706659,
      "grad_norm": 0.8125,
      "learning_rate": 0.000112,
      "loss": 7.5845,
      "mean_token_accuracy": 0.06810487173497677,
      "num_tokens": 400693.0,
      "step": 225
    },
    {
      "entropy": 8.105987453460694,
      "epoch": 0.011830362883522362,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0001145,
      "loss": 7.539,
      "mean_token_accuracy": 0.06601319462060928,
      "num_tokens": 409706.0,
      "step": 230
    },
    {
      "entropy": 8.056668090820313,
      "epoch": 0.012087544685338066,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.4696,
      "mean_token_accuracy": 0.06857900470495223,
      "num_tokens": 418717.0,
      "step": 235
    },
    {
      "entropy": 8.077108192443848,
      "epoch": 0.012344726487153769,
      "grad_norm": 1.046875,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.5335,
      "mean_token_accuracy": 0.06780378967523575,
      "num_tokens": 428630.0,
      "step": 240
    },
    {
      "entropy": 8.065593910217284,
      "epoch": 0.012601908288969472,
      "grad_norm": 0.9609375,
      "learning_rate": 0.000122,
      "loss": 7.559,
      "mean_token_accuracy": 0.06397245228290557,
      "num_tokens": 438762.0,
      "step": 245
    },
    {
      "entropy": 8.016668844223023,
      "epoch": 0.012859090090785176,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0001245,
      "loss": 7.4803,
      "mean_token_accuracy": 0.06500645838677883,
      "num_tokens": 447419.0,
      "step": 250
    },
    {
      "entropy": 8.066792869567871,
      "epoch": 0.01311627189260088,
      "grad_norm": 0.97265625,
      "learning_rate": 0.000127,
      "loss": 7.4872,
      "mean_token_accuracy": 0.07560092583298683,
      "num_tokens": 455818.0,
      "step": 255
    },
    {
      "entropy": 8.00608172416687,
      "epoch": 0.013373453694416584,
      "grad_norm": 1.0625,
      "learning_rate": 0.0001295,
      "loss": 7.4407,
      "mean_token_accuracy": 0.0703579068183899,
      "num_tokens": 464411.0,
      "step": 260
    },
    {
      "entropy": 8.006528282165528,
      "epoch": 0.013630635496232286,
      "grad_norm": 0.95703125,
      "learning_rate": 0.000132,
      "loss": 7.4791,
      "mean_token_accuracy": 0.07310711704194546,
      "num_tokens": 473181.0,
      "step": 265
    },
    {
      "entropy": 7.954403877258301,
      "epoch": 0.01388781729804799,
      "grad_norm": 0.890625,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.3802,
      "mean_token_accuracy": 0.07561531476676464,
      "num_tokens": 481776.0,
      "step": 270
    },
    {
      "entropy": 7.960335302352905,
      "epoch": 0.014144999099863694,
      "grad_norm": 0.91796875,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.3739,
      "mean_token_accuracy": 0.07225163355469703,
      "num_tokens": 490482.0,
      "step": 275
    },
    {
      "entropy": 7.908543682098388,
      "epoch": 0.014402180901679397,
      "grad_norm": 1.046875,
      "learning_rate": 0.0001395,
      "loss": 7.3373,
      "mean_token_accuracy": 0.08000247925519943,
      "num_tokens": 498394.0,
      "step": 280
    },
    {
      "entropy": 7.912304162979126,
      "epoch": 0.014659362703495101,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.3847,
      "mean_token_accuracy": 0.07234559133648873,
      "num_tokens": 507194.0,
      "step": 285
    },
    {
      "entropy": 7.905929660797119,
      "epoch": 0.014916544505310804,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001445,
      "loss": 7.3824,
      "mean_token_accuracy": 0.07954801470041276,
      "num_tokens": 515538.0,
      "step": 290
    },
    {
      "entropy": 7.906702852249145,
      "epoch": 0.015173726307126508,
      "grad_norm": 0.98828125,
      "learning_rate": 0.000147,
      "loss": 7.4258,
      "mean_token_accuracy": 0.0705490980297327,
      "num_tokens": 524544.0,
      "step": 295
    },
    {
      "entropy": 7.956319189071655,
      "epoch": 0.015430908108942211,
      "grad_norm": 0.95703125,
      "learning_rate": 0.0001495,
      "loss": 7.3581,
      "mean_token_accuracy": 0.0792141430079937,
      "num_tokens": 533096.0,
      "step": 300
    },
    {
      "entropy": 7.908858060836792,
      "epoch": 0.015688089910757916,
      "grad_norm": 0.95703125,
      "learning_rate": 0.000152,
      "loss": 7.2829,
      "mean_token_accuracy": 0.07599962502717972,
      "num_tokens": 542254.0,
      "step": 305
    },
    {
      "entropy": 7.929060173034668,
      "epoch": 0.01594527171257362,
      "grad_norm": 0.97265625,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.3804,
      "mean_token_accuracy": 0.07816362082958221,
      "num_tokens": 550985.0,
      "step": 310
    },
    {
      "entropy": 7.865027332305909,
      "epoch": 0.01620245351438932,
      "grad_norm": 1.09375,
      "learning_rate": 0.000157,
      "loss": 7.3625,
      "mean_token_accuracy": 0.07863678447902203,
      "num_tokens": 560224.0,
      "step": 315
    },
    {
      "entropy": 7.856458759307861,
      "epoch": 0.016459635316205024,
      "grad_norm": 0.98828125,
      "learning_rate": 0.0001595,
      "loss": 7.2099,
      "mean_token_accuracy": 0.0831373617053032,
      "num_tokens": 569268.0,
      "step": 320
    },
    {
      "entropy": 7.8261981964111325,
      "epoch": 0.01671681711802073,
      "grad_norm": 1.03125,
      "learning_rate": 0.000162,
      "loss": 7.305,
      "mean_token_accuracy": 0.07629284039139747,
      "num_tokens": 577876.0,
      "step": 325
    },
    {
      "entropy": 7.825508499145508,
      "epoch": 0.016973998919836433,
      "grad_norm": 0.94921875,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.1964,
      "mean_token_accuracy": 0.08476228266954422,
      "num_tokens": 586622.0,
      "step": 330
    },
    {
      "entropy": 7.87431845664978,
      "epoch": 0.017231180721652136,
      "grad_norm": 0.9609375,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.3968,
      "mean_token_accuracy": 0.07733883932232857,
      "num_tokens": 596544.0,
      "step": 335
    },
    {
      "entropy": 7.786734390258789,
      "epoch": 0.01748836252346784,
      "grad_norm": 1.140625,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.2342,
      "mean_token_accuracy": 0.07911348566412926,
      "num_tokens": 605349.0,
      "step": 340
    },
    {
      "entropy": 7.809148788452148,
      "epoch": 0.01774554432528354,
      "grad_norm": 0.98828125,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.2457,
      "mean_token_accuracy": 0.07915201708674431,
      "num_tokens": 614266.0,
      "step": 345
    },
    {
      "entropy": 7.771593856811523,
      "epoch": 0.018002726127099248,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.2829,
      "mean_token_accuracy": 0.07773459404706955,
      "num_tokens": 622534.0,
      "step": 350
    },
    {
      "entropy": 7.822271633148193,
      "epoch": 0.01825990792891495,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000177,
      "loss": 7.2365,
      "mean_token_accuracy": 0.08085938617587089,
      "num_tokens": 631838.0,
      "step": 355
    },
    {
      "entropy": 7.698997259140015,
      "epoch": 0.018517089730730654,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0001795,
      "loss": 7.2539,
      "mean_token_accuracy": 0.08351444229483604,
      "num_tokens": 641386.0,
      "step": 360
    },
    {
      "entropy": 7.703382873535157,
      "epoch": 0.018774271532546356,
      "grad_norm": 1.09375,
      "learning_rate": 0.000182,
      "loss": 7.2384,
      "mean_token_accuracy": 0.0824521966278553,
      "num_tokens": 650465.0,
      "step": 365
    },
    {
      "entropy": 7.835447978973389,
      "epoch": 0.01903145333436206,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0001845,
      "loss": 7.1401,
      "mean_token_accuracy": 0.08636756986379623,
      "num_tokens": 659509.0,
      "step": 370
    },
    {
      "entropy": 7.586853075027466,
      "epoch": 0.019288635136177765,
      "grad_norm": 1.109375,
      "learning_rate": 0.000187,
      "loss": 7.1678,
      "mean_token_accuracy": 0.08730523958802223,
      "num_tokens": 668137.0,
      "step": 375
    },
    {
      "entropy": 7.862004041671753,
      "epoch": 0.019545816937993468,
      "grad_norm": 1.078125,
      "learning_rate": 0.0001895,
      "loss": 7.2499,
      "mean_token_accuracy": 0.0831152357161045,
      "num_tokens": 677784.0,
      "step": 380
    },
    {
      "entropy": 7.637575674057007,
      "epoch": 0.01980299873980917,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000192,
      "loss": 7.1701,
      "mean_token_accuracy": 0.08491914793848991,
      "num_tokens": 686088.0,
      "step": 385
    },
    {
      "entropy": 7.752926158905029,
      "epoch": 0.020060180541624874,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001945,
      "loss": 7.3326,
      "mean_token_accuracy": 0.08027631081640721,
      "num_tokens": 695131.0,
      "step": 390
    },
    {
      "entropy": 7.793869876861573,
      "epoch": 0.020317362343440577,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.1152,
      "mean_token_accuracy": 0.08675874844193458,
      "num_tokens": 703976.0,
      "step": 395
    },
    {
      "entropy": 7.674239635467529,
      "epoch": 0.020574544145256283,
      "grad_norm": 1.15625,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.1607,
      "mean_token_accuracy": 0.08738962039351464,
      "num_tokens": 712080.0,
      "step": 400
    },
    {
      "entropy": 7.662798118591309,
      "epoch": 0.020831725947071986,
      "grad_norm": 1.109375,
      "learning_rate": 0.000202,
      "loss": 7.2073,
      "mean_token_accuracy": 0.08529370948672295,
      "num_tokens": 721151.0,
      "step": 405
    },
    {
      "entropy": 7.703192710876465,
      "epoch": 0.02108890774888769,
      "grad_norm": 1.03125,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.2059,
      "mean_token_accuracy": 0.08231882154941558,
      "num_tokens": 730957.0,
      "step": 410
    },
    {
      "entropy": 7.6682192325592045,
      "epoch": 0.02134608955070339,
      "grad_norm": 1.0625,
      "learning_rate": 0.000207,
      "loss": 7.115,
      "mean_token_accuracy": 0.09367254376411438,
      "num_tokens": 740054.0,
      "step": 415
    },
    {
      "entropy": 7.710998058319092,
      "epoch": 0.021603271352519094,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0002095,
      "loss": 7.1138,
      "mean_token_accuracy": 0.0901214174926281,
      "num_tokens": 748576.0,
      "step": 420
    },
    {
      "entropy": 7.615434312820435,
      "epoch": 0.0218604531543348,
      "grad_norm": 0.91015625,
      "learning_rate": 0.000212,
      "loss": 7.1257,
      "mean_token_accuracy": 0.08843043595552444,
      "num_tokens": 758078.0,
      "step": 425
    },
    {
      "entropy": 7.6622356414794925,
      "epoch": 0.022117634956150503,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0002145,
      "loss": 7.1976,
      "mean_token_accuracy": 0.08554179668426513,
      "num_tokens": 767041.0,
      "step": 430
    },
    {
      "entropy": 7.6705575466156,
      "epoch": 0.022374816757966206,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.192,
      "mean_token_accuracy": 0.08901726603507995,
      "num_tokens": 775675.0,
      "step": 435
    },
    {
      "entropy": 7.627669334411621,
      "epoch": 0.02263199855978191,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0002195,
      "loss": 7.0133,
      "mean_token_accuracy": 0.09209411665797233,
      "num_tokens": 784105.0,
      "step": 440
    },
    {
      "entropy": 7.484321117401123,
      "epoch": 0.022889180361597615,
      "grad_norm": 1.03125,
      "learning_rate": 0.000222,
      "loss": 6.9712,
      "mean_token_accuracy": 0.09117011949419976,
      "num_tokens": 792861.0,
      "step": 445
    },
    {
      "entropy": 7.594349336624146,
      "epoch": 0.023146362163413318,
      "grad_norm": 1.0625,
      "learning_rate": 0.0002245,
      "loss": 7.0314,
      "mean_token_accuracy": 0.08824475556612014,
      "num_tokens": 801642.0,
      "step": 450
    },
    {
      "entropy": 7.497442388534546,
      "epoch": 0.02340354396522902,
      "grad_norm": 1.09375,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.9939,
      "mean_token_accuracy": 0.08806813433766365,
      "num_tokens": 811105.0,
      "step": 455
    },
    {
      "entropy": 7.556538200378418,
      "epoch": 0.023660725767044723,
      "grad_norm": 1.15625,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.0195,
      "mean_token_accuracy": 0.09214109480381012,
      "num_tokens": 819989.0,
      "step": 460
    },
    {
      "entropy": 7.516587781906128,
      "epoch": 0.023917907568860426,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.0303,
      "mean_token_accuracy": 0.0912808708846569,
      "num_tokens": 829532.0,
      "step": 465
    },
    {
      "entropy": 7.524700498580932,
      "epoch": 0.024175089370676132,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.9313,
      "mean_token_accuracy": 0.09493043571710587,
      "num_tokens": 838071.0,
      "step": 470
    },
    {
      "entropy": 7.6139366149902346,
      "epoch": 0.024432271172491835,
      "grad_norm": 1.03125,
      "learning_rate": 0.000237,
      "loss": 7.1399,
      "mean_token_accuracy": 0.0876034751534462,
      "num_tokens": 848094.0,
      "step": 475
    },
    {
      "entropy": 7.520268821716309,
      "epoch": 0.024689452974307538,
      "grad_norm": 1.15625,
      "learning_rate": 0.0002395,
      "loss": 7.0461,
      "mean_token_accuracy": 0.09003157168626785,
      "num_tokens": 856585.0,
      "step": 480
    },
    {
      "entropy": 7.4084981918334964,
      "epoch": 0.02494663477612324,
      "grad_norm": 1.0,
      "learning_rate": 0.000242,
      "loss": 7.0064,
      "mean_token_accuracy": 0.09524489566683769,
      "num_tokens": 865866.0,
      "step": 485
    },
    {
      "entropy": 7.565576791763306,
      "epoch": 0.025203816577938944,
      "grad_norm": 1.390625,
      "learning_rate": 0.0002445,
      "loss": 7.0857,
      "mean_token_accuracy": 0.09243087470531464,
      "num_tokens": 874963.0,
      "step": 490
    },
    {
      "entropy": 7.522153425216675,
      "epoch": 0.02546099837975465,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000247,
      "loss": 7.0253,
      "mean_token_accuracy": 0.09747636616230011,
      "num_tokens": 883670.0,
      "step": 495
    },
    {
      "entropy": 7.411280775070191,
      "epoch": 0.025718180181570353,
      "grad_norm": 1.234375,
      "learning_rate": 0.0002495,
      "loss": 6.9456,
      "mean_token_accuracy": 0.09364836364984512,
      "num_tokens": 892322.0,
      "step": 500
    },
    {
      "entropy": 7.502190637588501,
      "epoch": 0.025975361983386056,
      "grad_norm": 0.98828125,
      "learning_rate": 0.000252,
      "loss": 7.0,
      "mean_token_accuracy": 0.09010454788804054,
      "num_tokens": 901450.0,
      "step": 505
    },
    {
      "entropy": 7.450657367706299,
      "epoch": 0.02623254378520176,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0002545,
      "loss": 6.9258,
      "mean_token_accuracy": 0.0917640596628189,
      "num_tokens": 910499.0,
      "step": 510
    },
    {
      "entropy": 7.4553405284881595,
      "epoch": 0.02648972558701746,
      "grad_norm": 0.9921875,
      "learning_rate": 0.000257,
      "loss": 7.042,
      "mean_token_accuracy": 0.08597794771194459,
      "num_tokens": 920223.0,
      "step": 515
    },
    {
      "entropy": 7.50772066116333,
      "epoch": 0.026746907388833167,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0002595,
      "loss": 7.014,
      "mean_token_accuracy": 0.08768303692340851,
      "num_tokens": 929414.0,
      "step": 520
    },
    {
      "entropy": 7.4105640888214115,
      "epoch": 0.02700408919064887,
      "grad_norm": 1.28125,
      "learning_rate": 0.000262,
      "loss": 6.98,
      "mean_token_accuracy": 0.08690723404288292,
      "num_tokens": 938059.0,
      "step": 525
    },
    {
      "entropy": 7.362936401367188,
      "epoch": 0.027261270992464573,
      "grad_norm": 1.1875,
      "learning_rate": 0.00026450000000000003,
      "loss": 7.0251,
      "mean_token_accuracy": 0.08964922651648521,
      "num_tokens": 946868.0,
      "step": 530
    },
    {
      "entropy": 7.468600177764893,
      "epoch": 0.027518452794280276,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00026700000000000004,
      "loss": 6.867,
      "mean_token_accuracy": 0.09712589457631111,
      "num_tokens": 954997.0,
      "step": 535
    },
    {
      "entropy": 7.428448724746704,
      "epoch": 0.02777563459609598,
      "grad_norm": 1.15625,
      "learning_rate": 0.00026950000000000005,
      "loss": 6.9816,
      "mean_token_accuracy": 0.09053401798009872,
      "num_tokens": 964488.0,
      "step": 540
    },
    {
      "entropy": 7.317347574234009,
      "epoch": 0.028032816397911685,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00027200000000000005,
      "loss": 6.8074,
      "mean_token_accuracy": 0.10062685832381249,
      "num_tokens": 972901.0,
      "step": 545
    },
    {
      "entropy": 7.45094141960144,
      "epoch": 0.028289998199727388,
      "grad_norm": 1.0,
      "learning_rate": 0.0002745,
      "loss": 7.0093,
      "mean_token_accuracy": 0.09124675542116165,
      "num_tokens": 981922.0,
      "step": 550
    },
    {
      "entropy": 7.441890525817871,
      "epoch": 0.02854718000154309,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000277,
      "loss": 6.9774,
      "mean_token_accuracy": 0.09369566291570663,
      "num_tokens": 990419.0,
      "step": 555
    },
    {
      "entropy": 7.304813051223755,
      "epoch": 0.028804361803358793,
      "grad_norm": 1.125,
      "learning_rate": 0.0002795,
      "loss": 6.8424,
      "mean_token_accuracy": 0.09960516914725304,
      "num_tokens": 998236.0,
      "step": 560
    },
    {
      "entropy": 7.3862227439880375,
      "epoch": 0.0290615436051745,
      "grad_norm": 1.015625,
      "learning_rate": 0.00028199999999999997,
      "loss": 6.8905,
      "mean_token_accuracy": 0.09915700182318687,
      "num_tokens": 1008258.0,
      "step": 565
    },
    {
      "entropy": 7.355383062362671,
      "epoch": 0.029318725406990202,
      "grad_norm": 1.09375,
      "learning_rate": 0.0002845,
      "loss": 6.8729,
      "mean_token_accuracy": 0.09238902553915977,
      "num_tokens": 1017029.0,
      "step": 570
    },
    {
      "entropy": 7.315412712097168,
      "epoch": 0.029575907208805905,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000287,
      "loss": 6.9067,
      "mean_token_accuracy": 0.09177370145916938,
      "num_tokens": 1026497.0,
      "step": 575
    },
    {
      "entropy": 7.337841367721557,
      "epoch": 0.029833089010621608,
      "grad_norm": 1.234375,
      "learning_rate": 0.0002895,
      "loss": 6.8092,
      "mean_token_accuracy": 0.10336045101284981,
      "num_tokens": 1034728.0,
      "step": 580
    },
    {
      "entropy": 7.256781911849975,
      "epoch": 0.03009027081243731,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000292,
      "loss": 6.8645,
      "mean_token_accuracy": 0.09807764887809753,
      "num_tokens": 1043556.0,
      "step": 585
    },
    {
      "entropy": 7.315465259552002,
      "epoch": 0.030347452614253017,
      "grad_norm": 1.25,
      "learning_rate": 0.0002945,
      "loss": 6.7914,
      "mean_token_accuracy": 0.10462642684578896,
      "num_tokens": 1053449.0,
      "step": 590
    },
    {
      "entropy": 7.294723844528198,
      "epoch": 0.03060463441606872,
      "grad_norm": 1.25,
      "learning_rate": 0.000297,
      "loss": 6.8701,
      "mean_token_accuracy": 0.09261535704135895,
      "num_tokens": 1062691.0,
      "step": 595
    },
    {
      "entropy": 7.328425025939941,
      "epoch": 0.030861816217884423,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0002995,
      "loss": 6.8732,
      "mean_token_accuracy": 0.09672143906354905,
      "num_tokens": 1072194.0,
      "step": 600
    },
    {
      "entropy": 7.280484533309936,
      "epoch": 0.031118998019700125,
      "grad_norm": 1.109375,
      "learning_rate": 0.000302,
      "loss": 6.7832,
      "mean_token_accuracy": 0.09872276112437248,
      "num_tokens": 1080781.0,
      "step": 605
    },
    {
      "entropy": 7.2788474559783936,
      "epoch": 0.03137617982151583,
      "grad_norm": 1.09375,
      "learning_rate": 0.0003045,
      "loss": 6.9191,
      "mean_token_accuracy": 0.09485599771142006,
      "num_tokens": 1090048.0,
      "step": 610
    },
    {
      "entropy": 7.34011402130127,
      "epoch": 0.03163336162333153,
      "grad_norm": 1.03125,
      "learning_rate": 0.000307,
      "loss": 6.9368,
      "mean_token_accuracy": 0.09523111060261727,
      "num_tokens": 1100121.0,
      "step": 615
    },
    {
      "entropy": 7.326197099685669,
      "epoch": 0.03189054342514724,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0003095,
      "loss": 6.8036,
      "mean_token_accuracy": 0.09568134695291519,
      "num_tokens": 1108569.0,
      "step": 620
    },
    {
      "entropy": 7.213407182693482,
      "epoch": 0.032147725226962943,
      "grad_norm": 1.171875,
      "learning_rate": 0.000312,
      "loss": 6.776,
      "mean_token_accuracy": 0.09914244189858437,
      "num_tokens": 1118247.0,
      "step": 625
    },
    {
      "entropy": 7.210325479507446,
      "epoch": 0.03240490702877864,
      "grad_norm": 1.1875,
      "learning_rate": 0.0003145,
      "loss": 6.7999,
      "mean_token_accuracy": 0.09887302219867707,
      "num_tokens": 1126951.0,
      "step": 630
    },
    {
      "entropy": 7.209123611450195,
      "epoch": 0.03266208883059435,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000317,
      "loss": 6.7651,
      "mean_token_accuracy": 0.10773184821009636,
      "num_tokens": 1135390.0,
      "step": 635
    },
    {
      "entropy": 7.2418413162231445,
      "epoch": 0.03291927063241005,
      "grad_norm": 1.171875,
      "learning_rate": 0.0003195,
      "loss": 6.8057,
      "mean_token_accuracy": 0.09772193506360054,
      "num_tokens": 1143911.0,
      "step": 640
    },
    {
      "entropy": 7.288219833374024,
      "epoch": 0.033176452434225755,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000322,
      "loss": 6.7833,
      "mean_token_accuracy": 0.10312128961086273,
      "num_tokens": 1152957.0,
      "step": 645
    },
    {
      "entropy": 7.144729995727539,
      "epoch": 0.03343363423604146,
      "grad_norm": 0.96484375,
      "learning_rate": 0.00032450000000000003,
      "loss": 6.7073,
      "mean_token_accuracy": 0.10490344762802124,
      "num_tokens": 1161911.0,
      "step": 650
    },
    {
      "entropy": 7.214617156982422,
      "epoch": 0.03369081603785716,
      "grad_norm": 1.203125,
      "learning_rate": 0.00032700000000000003,
      "loss": 6.7621,
      "mean_token_accuracy": 0.10395861864089966,
      "num_tokens": 1170932.0,
      "step": 655
    },
    {
      "entropy": 7.226040458679199,
      "epoch": 0.03394799783967287,
      "grad_norm": 1.015625,
      "learning_rate": 0.00032950000000000004,
      "loss": 6.8979,
      "mean_token_accuracy": 0.09301602616906166,
      "num_tokens": 1180417.0,
      "step": 660
    },
    {
      "entropy": 7.148654270172119,
      "epoch": 0.034205179641488566,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00033200000000000005,
      "loss": 6.7629,
      "mean_token_accuracy": 0.09860587194561958,
      "num_tokens": 1189153.0,
      "step": 665
    },
    {
      "entropy": 7.214554643630981,
      "epoch": 0.03446236144330427,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00033450000000000005,
      "loss": 6.7476,
      "mean_token_accuracy": 0.1043582171201706,
      "num_tokens": 1197903.0,
      "step": 670
    },
    {
      "entropy": 7.1135680198669435,
      "epoch": 0.03471954324511998,
      "grad_norm": 1.046875,
      "learning_rate": 0.000337,
      "loss": 6.7435,
      "mean_token_accuracy": 0.10275317579507828,
      "num_tokens": 1207310.0,
      "step": 675
    },
    {
      "entropy": 7.197217321395874,
      "epoch": 0.03497672504693568,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0003395,
      "loss": 6.7117,
      "mean_token_accuracy": 0.10364129021763802,
      "num_tokens": 1215577.0,
      "step": 680
    },
    {
      "entropy": 7.160997724533081,
      "epoch": 0.035233906848751384,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000342,
      "loss": 6.801,
      "mean_token_accuracy": 0.10323198661208152,
      "num_tokens": 1223906.0,
      "step": 685
    },
    {
      "entropy": 7.1171308040618895,
      "epoch": 0.03549108865056708,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00034449999999999997,
      "loss": 6.7434,
      "mean_token_accuracy": 0.10217863768339157,
      "num_tokens": 1232689.0,
      "step": 690
    },
    {
      "entropy": 7.243052577972412,
      "epoch": 0.03574827045238279,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000347,
      "loss": 6.777,
      "mean_token_accuracy": 0.10172305777668952,
      "num_tokens": 1241079.0,
      "step": 695
    },
    {
      "entropy": 7.0958874225616455,
      "epoch": 0.036005452254198496,
      "grad_norm": 1.125,
      "learning_rate": 0.0003495,
      "loss": 6.6994,
      "mean_token_accuracy": 0.10428043976426124,
      "num_tokens": 1249540.0,
      "step": 700
    },
    {
      "entropy": 7.236631059646607,
      "epoch": 0.036262634056014195,
      "grad_norm": 1.15625,
      "learning_rate": 0.000352,
      "loss": 6.767,
      "mean_token_accuracy": 0.10423633679747582,
      "num_tokens": 1257823.0,
      "step": 705
    },
    {
      "entropy": 7.162586879730225,
      "epoch": 0.0365198158578299,
      "grad_norm": 1.15625,
      "learning_rate": 0.0003545,
      "loss": 6.7752,
      "mean_token_accuracy": 0.10328136906027793,
      "num_tokens": 1267242.0,
      "step": 710
    },
    {
      "entropy": 7.095451688766479,
      "epoch": 0.0367769976596456,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000357,
      "loss": 6.6616,
      "mean_token_accuracy": 0.10539852529764175,
      "num_tokens": 1275942.0,
      "step": 715
    },
    {
      "entropy": 7.087832736968994,
      "epoch": 0.03703417946146131,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0003595,
      "loss": 6.716,
      "mean_token_accuracy": 0.10562722086906433,
      "num_tokens": 1284840.0,
      "step": 720
    },
    {
      "entropy": 7.123103380203247,
      "epoch": 0.03729136126327701,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000362,
      "loss": 6.6864,
      "mean_token_accuracy": 0.10260284543037415,
      "num_tokens": 1293592.0,
      "step": 725
    },
    {
      "entropy": 7.171104860305786,
      "epoch": 0.03754854306509271,
      "grad_norm": 1.15625,
      "learning_rate": 0.0003645,
      "loss": 6.8006,
      "mean_token_accuracy": 0.10065393671393394,
      "num_tokens": 1301903.0,
      "step": 730
    },
    {
      "entropy": 7.110880374908447,
      "epoch": 0.03780572486690842,
      "grad_norm": 1.265625,
      "learning_rate": 0.000367,
      "loss": 6.6262,
      "mean_token_accuracy": 0.105719206482172,
      "num_tokens": 1310230.0,
      "step": 735
    },
    {
      "entropy": 7.178726625442505,
      "epoch": 0.03806290666872412,
      "grad_norm": 1.140625,
      "learning_rate": 0.0003695,
      "loss": 6.7676,
      "mean_token_accuracy": 0.10490798503160477,
      "num_tokens": 1320029.0,
      "step": 740
    },
    {
      "entropy": 7.001174449920654,
      "epoch": 0.038320088470539825,
      "grad_norm": 1.0703125,
      "learning_rate": 0.000372,
      "loss": 6.6133,
      "mean_token_accuracy": 0.10703234896063804,
      "num_tokens": 1329155.0,
      "step": 745
    },
    {
      "entropy": 7.125448083877563,
      "epoch": 0.03857727027235553,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0003745,
      "loss": 6.8029,
      "mean_token_accuracy": 0.1019430361688137,
      "num_tokens": 1337958.0,
      "step": 750
    },
    {
      "entropy": 7.109465599060059,
      "epoch": 0.03883445207417123,
      "grad_norm": 1.3125,
      "learning_rate": 0.000377,
      "loss": 6.7375,
      "mean_token_accuracy": 0.09966553151607513,
      "num_tokens": 1347105.0,
      "step": 755
    },
    {
      "entropy": 7.161317777633667,
      "epoch": 0.039091633875986936,
      "grad_norm": 1.234375,
      "learning_rate": 0.0003795,
      "loss": 6.6791,
      "mean_token_accuracy": 0.10060147866606713,
      "num_tokens": 1356161.0,
      "step": 760
    },
    {
      "entropy": 6.9970433712005615,
      "epoch": 0.039348815677802636,
      "grad_norm": 1.140625,
      "learning_rate": 0.000382,
      "loss": 6.6891,
      "mean_token_accuracy": 0.10932381451129913,
      "num_tokens": 1365291.0,
      "step": 765
    },
    {
      "entropy": 7.0630707263946535,
      "epoch": 0.03960599747961834,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0003845,
      "loss": 6.6481,
      "mean_token_accuracy": 0.1059026412665844,
      "num_tokens": 1374057.0,
      "step": 770
    },
    {
      "entropy": 7.118219041824341,
      "epoch": 0.03986317928143405,
      "grad_norm": 1.296875,
      "learning_rate": 0.00038700000000000003,
      "loss": 6.6895,
      "mean_token_accuracy": 0.09991606175899506,
      "num_tokens": 1383204.0,
      "step": 775
    },
    {
      "entropy": 7.0793726444244385,
      "epoch": 0.04012036108324975,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00038950000000000003,
      "loss": 6.7114,
      "mean_token_accuracy": 0.1018392451107502,
      "num_tokens": 1392303.0,
      "step": 780
    },
    {
      "entropy": 7.041213703155518,
      "epoch": 0.040377542885065454,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00039200000000000004,
      "loss": 6.6789,
      "mean_token_accuracy": 0.10870900377631187,
      "num_tokens": 1401955.0,
      "step": 785
    },
    {
      "entropy": 7.127471685409546,
      "epoch": 0.04063472468688115,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00039450000000000005,
      "loss": 6.6934,
      "mean_token_accuracy": 0.10036104544997215,
      "num_tokens": 1410467.0,
      "step": 790
    },
    {
      "entropy": 6.975720405578613,
      "epoch": 0.04089190648869686,
      "grad_norm": 1.0625,
      "learning_rate": 0.00039700000000000005,
      "loss": 6.6748,
      "mean_token_accuracy": 0.09731148779392243,
      "num_tokens": 1420337.0,
      "step": 795
    },
    {
      "entropy": 7.059706926345825,
      "epoch": 0.041149088290512566,
      "grad_norm": 1.078125,
      "learning_rate": 0.0003995,
      "loss": 6.6711,
      "mean_token_accuracy": 0.10144198536872864,
      "num_tokens": 1429453.0,
      "step": 800
    },
    {
      "entropy": 7.094644546508789,
      "epoch": 0.041406270092328265,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000402,
      "loss": 6.6208,
      "mean_token_accuracy": 0.10604123547673225,
      "num_tokens": 1438417.0,
      "step": 805
    },
    {
      "entropy": 6.986465740203857,
      "epoch": 0.04166345189414397,
      "grad_norm": 1.40625,
      "learning_rate": 0.0004045,
      "loss": 6.6667,
      "mean_token_accuracy": 0.10473878160119057,
      "num_tokens": 1446480.0,
      "step": 810
    },
    {
      "entropy": 6.946633005142212,
      "epoch": 0.04192063369595967,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00040699999999999997,
      "loss": 6.6306,
      "mean_token_accuracy": 0.10496868267655372,
      "num_tokens": 1455102.0,
      "step": 815
    },
    {
      "entropy": 7.14404935836792,
      "epoch": 0.04217781549777538,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0004095,
      "loss": 6.6538,
      "mean_token_accuracy": 0.10508396551012993,
      "num_tokens": 1463839.0,
      "step": 820
    },
    {
      "entropy": 7.024435377120971,
      "epoch": 0.04243499729959108,
      "grad_norm": 1.15625,
      "learning_rate": 0.000412,
      "loss": 6.6836,
      "mean_token_accuracy": 0.10788170769810676,
      "num_tokens": 1472806.0,
      "step": 825
    },
    {
      "entropy": 6.979895305633545,
      "epoch": 0.04269217910140678,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0004145,
      "loss": 6.6016,
      "mean_token_accuracy": 0.10319365486502648,
      "num_tokens": 1481707.0,
      "step": 830
    },
    {
      "entropy": 6.948284530639649,
      "epoch": 0.04294936090322249,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000417,
      "loss": 6.6068,
      "mean_token_accuracy": 0.10952205657958984,
      "num_tokens": 1491057.0,
      "step": 835
    },
    {
      "entropy": 6.963069152832031,
      "epoch": 0.04320654270503819,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0004195,
      "loss": 6.5666,
      "mean_token_accuracy": 0.10177317038178443,
      "num_tokens": 1500331.0,
      "step": 840
    },
    {
      "entropy": 6.964898347854614,
      "epoch": 0.043463724506853894,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000422,
      "loss": 6.6376,
      "mean_token_accuracy": 0.10519776120781898,
      "num_tokens": 1509051.0,
      "step": 845
    },
    {
      "entropy": 7.032815408706665,
      "epoch": 0.0437209063086696,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0004245,
      "loss": 6.5931,
      "mean_token_accuracy": 0.10714114159345627,
      "num_tokens": 1517082.0,
      "step": 850
    },
    {
      "entropy": 6.869009304046631,
      "epoch": 0.0439780881104853,
      "grad_norm": 1.203125,
      "learning_rate": 0.000427,
      "loss": 6.5338,
      "mean_token_accuracy": 0.11201286613941193,
      "num_tokens": 1525498.0,
      "step": 855
    },
    {
      "entropy": 6.827907609939575,
      "epoch": 0.044235269912301006,
      "grad_norm": 1.140625,
      "learning_rate": 0.0004295,
      "loss": 6.4978,
      "mean_token_accuracy": 0.11273056790232658,
      "num_tokens": 1534476.0,
      "step": 860
    },
    {
      "entropy": 6.958985805511475,
      "epoch": 0.04449245171411671,
      "grad_norm": 1.15625,
      "learning_rate": 0.000432,
      "loss": 6.5896,
      "mean_token_accuracy": 0.10771357268095016,
      "num_tokens": 1542905.0,
      "step": 865
    },
    {
      "entropy": 6.942825794219971,
      "epoch": 0.04474963351593241,
      "grad_norm": 1.109375,
      "learning_rate": 0.0004345,
      "loss": 6.583,
      "mean_token_accuracy": 0.10546278730034828,
      "num_tokens": 1551763.0,
      "step": 870
    },
    {
      "entropy": 6.906496191024781,
      "epoch": 0.04500681531774812,
      "grad_norm": 1.109375,
      "learning_rate": 0.000437,
      "loss": 6.5085,
      "mean_token_accuracy": 0.11341241300106049,
      "num_tokens": 1560520.0,
      "step": 875
    },
    {
      "entropy": 6.904255485534668,
      "epoch": 0.04526399711956382,
      "grad_norm": 1.0625,
      "learning_rate": 0.0004395,
      "loss": 6.4871,
      "mean_token_accuracy": 0.11152468100190163,
      "num_tokens": 1569401.0,
      "step": 880
    },
    {
      "entropy": 6.922533941268921,
      "epoch": 0.045521178921379524,
      "grad_norm": 1.046875,
      "learning_rate": 0.000442,
      "loss": 6.5564,
      "mean_token_accuracy": 0.10919757708907127,
      "num_tokens": 1578440.0,
      "step": 885
    },
    {
      "entropy": 6.789845991134643,
      "epoch": 0.04577836072319523,
      "grad_norm": 1.234375,
      "learning_rate": 0.0004445,
      "loss": 6.4462,
      "mean_token_accuracy": 0.11144870221614837,
      "num_tokens": 1587551.0,
      "step": 890
    },
    {
      "entropy": 6.944276809692383,
      "epoch": 0.04603554252501093,
      "grad_norm": 1.1875,
      "learning_rate": 0.000447,
      "loss": 6.6154,
      "mean_token_accuracy": 0.10818377807736397,
      "num_tokens": 1596314.0,
      "step": 895
    },
    {
      "entropy": 6.900253582000732,
      "epoch": 0.046292724326826636,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00044950000000000003,
      "loss": 6.4889,
      "mean_token_accuracy": 0.1112966388463974,
      "num_tokens": 1605025.0,
      "step": 900
    },
    {
      "entropy": 6.905750894546509,
      "epoch": 0.046549906128642335,
      "grad_norm": 1.2265625,
      "learning_rate": 0.00045200000000000004,
      "loss": 6.5348,
      "mean_token_accuracy": 0.10826415568590164,
      "num_tokens": 1613295.0,
      "step": 905
    },
    {
      "entropy": 6.862349224090576,
      "epoch": 0.04680708793045804,
      "grad_norm": 1.328125,
      "learning_rate": 0.00045450000000000004,
      "loss": 6.5131,
      "mean_token_accuracy": 0.1080511450767517,
      "num_tokens": 1621865.0,
      "step": 910
    },
    {
      "entropy": 6.87268099784851,
      "epoch": 0.04706426973227375,
      "grad_norm": 1.09375,
      "learning_rate": 0.00045700000000000005,
      "loss": 6.517,
      "mean_token_accuracy": 0.11334388554096222,
      "num_tokens": 1631036.0,
      "step": 915
    },
    {
      "entropy": 6.960796642303467,
      "epoch": 0.04732145153408945,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00045950000000000006,
      "loss": 6.6083,
      "mean_token_accuracy": 0.10900305211544037,
      "num_tokens": 1640311.0,
      "step": 920
    },
    {
      "entropy": 6.877505731582642,
      "epoch": 0.04757863333590515,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000462,
      "loss": 6.5707,
      "mean_token_accuracy": 0.11122839301824569,
      "num_tokens": 1648651.0,
      "step": 925
    },
    {
      "entropy": 6.814219570159912,
      "epoch": 0.04783581513772085,
      "grad_norm": 1.2109375,
      "learning_rate": 0.0004645,
      "loss": 6.5091,
      "mean_token_accuracy": 0.11311314180493355,
      "num_tokens": 1657493.0,
      "step": 930
    },
    {
      "entropy": 6.919810724258423,
      "epoch": 0.04809299693953656,
      "grad_norm": 1.203125,
      "learning_rate": 0.000467,
      "loss": 6.5672,
      "mean_token_accuracy": 0.10320627093315124,
      "num_tokens": 1666909.0,
      "step": 935
    },
    {
      "entropy": 6.835229587554932,
      "epoch": 0.048350178741352265,
      "grad_norm": 1.109375,
      "learning_rate": 0.0004695,
      "loss": 6.5857,
      "mean_token_accuracy": 0.10411025136709214,
      "num_tokens": 1676071.0,
      "step": 940
    },
    {
      "entropy": 6.990052223205566,
      "epoch": 0.048607360543167964,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000472,
      "loss": 6.6305,
      "mean_token_accuracy": 0.10452140420675278,
      "num_tokens": 1685240.0,
      "step": 945
    },
    {
      "entropy": 6.916949987411499,
      "epoch": 0.04886454234498367,
      "grad_norm": 1.078125,
      "learning_rate": 0.0004745,
      "loss": 6.5346,
      "mean_token_accuracy": 0.117493636906147,
      "num_tokens": 1694441.0,
      "step": 950
    },
    {
      "entropy": 6.721475076675415,
      "epoch": 0.04912172414679937,
      "grad_norm": 1.171875,
      "learning_rate": 0.000477,
      "loss": 6.4578,
      "mean_token_accuracy": 0.1129125975072384,
      "num_tokens": 1702925.0,
      "step": 955
    },
    {
      "entropy": 6.895248603820801,
      "epoch": 0.049378905948615076,
      "grad_norm": 1.125,
      "learning_rate": 0.0004795,
      "loss": 6.4835,
      "mean_token_accuracy": 0.10699952915310859,
      "num_tokens": 1711708.0,
      "step": 960
    },
    {
      "entropy": 6.799575614929199,
      "epoch": 0.04963608775043078,
      "grad_norm": 1.21875,
      "learning_rate": 0.000482,
      "loss": 6.4901,
      "mean_token_accuracy": 0.10597067773342132,
      "num_tokens": 1720543.0,
      "step": 965
    },
    {
      "entropy": 6.862289619445801,
      "epoch": 0.04989326955224648,
      "grad_norm": 1.171875,
      "learning_rate": 0.0004845,
      "loss": 6.4988,
      "mean_token_accuracy": 0.11304299309849739,
      "num_tokens": 1729776.0,
      "step": 970
    },
    {
      "entropy": 6.8804943561553955,
      "epoch": 0.05015045135406219,
      "grad_norm": 1.171875,
      "learning_rate": 0.000487,
      "loss": 6.4822,
      "mean_token_accuracy": 0.11637242883443832,
      "num_tokens": 1738249.0,
      "step": 975
    },
    {
      "entropy": 6.828695917129517,
      "epoch": 0.05040763315587789,
      "grad_norm": 1.171875,
      "learning_rate": 0.0004895,
      "loss": 6.5063,
      "mean_token_accuracy": 0.11184739843010902,
      "num_tokens": 1747262.0,
      "step": 980
    },
    {
      "entropy": 6.891150426864624,
      "epoch": 0.050664814957693594,
      "grad_norm": 1.2890625,
      "learning_rate": 0.000492,
      "loss": 6.5072,
      "mean_token_accuracy": 0.11530979126691818,
      "num_tokens": 1755320.0,
      "step": 985
    },
    {
      "entropy": 6.7496922492980955,
      "epoch": 0.0509219967595093,
      "grad_norm": 1.078125,
      "learning_rate": 0.0004945,
      "loss": 6.5038,
      "mean_token_accuracy": 0.11211839094758033,
      "num_tokens": 1763798.0,
      "step": 990
    },
    {
      "entropy": 6.788990116119384,
      "epoch": 0.051179178561325,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000497,
      "loss": 6.4671,
      "mean_token_accuracy": 0.11327328234910965,
      "num_tokens": 1773862.0,
      "step": 995
    },
    {
      "entropy": 6.837374210357666,
      "epoch": 0.051436360363140705,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0004995,
      "loss": 6.5248,
      "mean_token_accuracy": 0.11146914437413216,
      "num_tokens": 1783552.0,
      "step": 1000
    }
  ],
  "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": 353654176481280.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}