{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.025718180181570353,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.742102813720702,
      "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
    }
  ],
  "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": 178115181281280.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}