{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10287272072628141,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.7425612449646,
      "epoch": 0.0002571818018157035,
      "grad_norm": 5.65625,
      "learning_rate": 2e-06,
      "loss": 10.7388,
      "mean_token_accuracy": 0.0,
      "num_tokens": 9030.0,
      "step": 5
    },
    {
      "entropy": 10.742591857910156,
      "epoch": 0.000514363603631407,
      "grad_norm": 5.25,
      "learning_rate": 4.5e-06,
      "loss": 10.7331,
      "mean_token_accuracy": 0.0,
      "num_tokens": 18084.0,
      "step": 10
    },
    {
      "entropy": 10.742617130279541,
      "epoch": 0.0007715454054471106,
      "grad_norm": 5.1875,
      "learning_rate": 7e-06,
      "loss": 10.6991,
      "mean_token_accuracy": 0.0,
      "num_tokens": 26309.0,
      "step": 15
    },
    {
      "entropy": 10.742614936828613,
      "epoch": 0.001028727207262814,
      "grad_norm": 5.1875,
      "learning_rate": 9.5e-06,
      "loss": 10.661,
      "mean_token_accuracy": 0.0013652202673256398,
      "num_tokens": 35204.0,
      "step": 20
    },
    {
      "entropy": 10.74255428314209,
      "epoch": 0.0012859090090785177,
      "grad_norm": 4.3125,
      "learning_rate": 1.2e-05,
      "loss": 10.5708,
      "mean_token_accuracy": 0.009783844836056233,
      "num_tokens": 44540.0,
      "step": 25
    },
    {
      "entropy": 10.74219331741333,
      "epoch": 0.0015430908108942211,
      "grad_norm": 4.03125,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.4335,
      "mean_token_accuracy": 0.035427753999829295,
      "num_tokens": 53118.0,
      "step": 30
    },
    {
      "entropy": 10.740796661376953,
      "epoch": 0.0018002726127099246,
      "grad_norm": 3.28125,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.3091,
      "mean_token_accuracy": 0.04362985044717789,
      "num_tokens": 61753.0,
      "step": 35
    },
    {
      "entropy": 10.736623382568359,
      "epoch": 0.002057454414525628,
      "grad_norm": 2.765625,
      "learning_rate": 1.95e-05,
      "loss": 10.1821,
      "mean_token_accuracy": 0.044929017499089244,
      "num_tokens": 71102.0,
      "step": 40
    },
    {
      "entropy": 10.729742622375488,
      "epoch": 0.0023146362163413317,
      "grad_norm": 2.3125,
      "learning_rate": 2.2e-05,
      "loss": 10.0932,
      "mean_token_accuracy": 0.04235424343496561,
      "num_tokens": 80094.0,
      "step": 45
    },
    {
      "entropy": 10.723683643341065,
      "epoch": 0.0025718180181570354,
      "grad_norm": 2.109375,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.9838,
      "mean_token_accuracy": 0.04485577754676342,
      "num_tokens": 88770.0,
      "step": 50
    },
    {
      "entropy": 10.720681381225585,
      "epoch": 0.0028289998199727386,
      "grad_norm": 2.046875,
      "learning_rate": 2.7e-05,
      "loss": 9.944,
      "mean_token_accuracy": 0.043965942412614825,
      "num_tokens": 97608.0,
      "step": 55
    },
    {
      "entropy": 10.717811107635498,
      "epoch": 0.0030861816217884423,
      "grad_norm": 1.875,
      "learning_rate": 2.95e-05,
      "loss": 9.8684,
      "mean_token_accuracy": 0.04390094466507435,
      "num_tokens": 106204.0,
      "step": 60
    },
    {
      "entropy": 10.713484477996825,
      "epoch": 0.003343363423604146,
      "grad_norm": 1.90625,
      "learning_rate": 3.2e-05,
      "loss": 9.841,
      "mean_token_accuracy": 0.04340735748410225,
      "num_tokens": 115241.0,
      "step": 65
    },
    {
      "entropy": 10.708874225616455,
      "epoch": 0.003600545225419849,
      "grad_norm": 1.984375,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.7416,
      "mean_token_accuracy": 0.04423734098672867,
      "num_tokens": 123734.0,
      "step": 70
    },
    {
      "entropy": 10.703791618347168,
      "epoch": 0.003857727027235553,
      "grad_norm": 1.8984375,
      "learning_rate": 3.7e-05,
      "loss": 9.7488,
      "mean_token_accuracy": 0.04389217719435692,
      "num_tokens": 132701.0,
      "step": 75
    },
    {
      "entropy": 10.697965526580811,
      "epoch": 0.004114908829051256,
      "grad_norm": 1.921875,
      "learning_rate": 3.95e-05,
      "loss": 9.6173,
      "mean_token_accuracy": 0.04561489634215832,
      "num_tokens": 141064.0,
      "step": 80
    },
    {
      "entropy": 10.6871018409729,
      "epoch": 0.00437209063086696,
      "grad_norm": 1.96875,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.5084,
      "mean_token_accuracy": 0.05098861046135426,
      "num_tokens": 149340.0,
      "step": 85
    },
    {
      "entropy": 10.67187786102295,
      "epoch": 0.004629272432682663,
      "grad_norm": 1.828125,
      "learning_rate": 4.45e-05,
      "loss": 9.4949,
      "mean_token_accuracy": 0.05393466129899025,
      "num_tokens": 158312.0,
      "step": 90
    },
    {
      "entropy": 10.659277820587159,
      "epoch": 0.004886454234498367,
      "grad_norm": 1.640625,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.445,
      "mean_token_accuracy": 0.0573005523532629,
      "num_tokens": 167203.0,
      "step": 95
    },
    {
      "entropy": 10.643789291381836,
      "epoch": 0.005143636036314071,
      "grad_norm": 1.8046875,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.2598,
      "mean_token_accuracy": 0.0629499789327383,
      "num_tokens": 175929.0,
      "step": 100
    },
    {
      "entropy": 10.604194068908692,
      "epoch": 0.0054008178381297735,
      "grad_norm": 1.7734375,
      "learning_rate": 5.2e-05,
      "loss": 9.2354,
      "mean_token_accuracy": 0.05866244621574879,
      "num_tokens": 185619.0,
      "step": 105
    },
    {
      "entropy": 10.549863052368163,
      "epoch": 0.005657999639945477,
      "grad_norm": 1.6875,
      "learning_rate": 5.45e-05,
      "loss": 9.1507,
      "mean_token_accuracy": 0.05989648550748825,
      "num_tokens": 195005.0,
      "step": 110
    },
    {
      "entropy": 10.489420223236085,
      "epoch": 0.005915181441761181,
      "grad_norm": 1.59375,
      "learning_rate": 5.7e-05,
      "loss": 8.9373,
      "mean_token_accuracy": 0.0647052500396967,
      "num_tokens": 203392.0,
      "step": 115
    },
    {
      "entropy": 10.426068687438965,
      "epoch": 0.0061723632435768845,
      "grad_norm": 1.578125,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.8217,
      "mean_token_accuracy": 0.060671578347682956,
      "num_tokens": 211689.0,
      "step": 120
    },
    {
      "entropy": 10.359361457824708,
      "epoch": 0.006429545045392588,
      "grad_norm": 1.4296875,
      "learning_rate": 6.2e-05,
      "loss": 8.756,
      "mean_token_accuracy": 0.06377223357558251,
      "num_tokens": 220798.0,
      "step": 125
    },
    {
      "entropy": 10.30004062652588,
      "epoch": 0.006686726847208292,
      "grad_norm": 1.4453125,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.6622,
      "mean_token_accuracy": 0.06106479801237583,
      "num_tokens": 229652.0,
      "step": 130
    },
    {
      "entropy": 10.221406269073487,
      "epoch": 0.006943908649023995,
      "grad_norm": 1.453125,
      "learning_rate": 6.7e-05,
      "loss": 8.4588,
      "mean_token_accuracy": 0.06428722217679024,
      "num_tokens": 238320.0,
      "step": 135
    },
    {
      "entropy": 10.105729293823241,
      "epoch": 0.007201090450839698,
      "grad_norm": 1.5,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.431,
      "mean_token_accuracy": 0.06200639493763447,
      "num_tokens": 247033.0,
      "step": 140
    },
    {
      "entropy": 9.967057228088379,
      "epoch": 0.007458272252655402,
      "grad_norm": 1.203125,
      "learning_rate": 7.2e-05,
      "loss": 8.3441,
      "mean_token_accuracy": 0.06121456101536751,
      "num_tokens": 256666.0,
      "step": 145
    },
    {
      "entropy": 9.81930513381958,
      "epoch": 0.007715454054471106,
      "grad_norm": 1.15625,
      "learning_rate": 7.45e-05,
      "loss": 8.1686,
      "mean_token_accuracy": 0.06682926267385483,
      "num_tokens": 265689.0,
      "step": 150
    },
    {
      "entropy": 9.67783327102661,
      "epoch": 0.00797263585628681,
      "grad_norm": 0.9921875,
      "learning_rate": 7.7e-05,
      "loss": 8.1019,
      "mean_token_accuracy": 0.06226279996335506,
      "num_tokens": 274276.0,
      "step": 155
    },
    {
      "entropy": 9.495966053009033,
      "epoch": 0.008229817658102512,
      "grad_norm": 1.0703125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.9704,
      "mean_token_accuracy": 0.06119140088558197,
      "num_tokens": 283825.0,
      "step": 160
    },
    {
      "entropy": 9.309716987609864,
      "epoch": 0.008486999459918217,
      "grad_norm": 0.96484375,
      "learning_rate": 8.2e-05,
      "loss": 7.8795,
      "mean_token_accuracy": 0.06309534795582294,
      "num_tokens": 292223.0,
      "step": 165
    },
    {
      "entropy": 9.042353534698487,
      "epoch": 0.00874418126173392,
      "grad_norm": 0.8046875,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.8385,
      "mean_token_accuracy": 0.06506023034453393,
      "num_tokens": 300889.0,
      "step": 170
    },
    {
      "entropy": 8.90816011428833,
      "epoch": 0.009001363063549624,
      "grad_norm": 1.0078125,
      "learning_rate": 8.7e-05,
      "loss": 7.7842,
      "mean_token_accuracy": 0.0640747856348753,
      "num_tokens": 309729.0,
      "step": 175
    },
    {
      "entropy": 8.687435150146484,
      "epoch": 0.009258544865365327,
      "grad_norm": 0.8125,
      "learning_rate": 8.95e-05,
      "loss": 7.7211,
      "mean_token_accuracy": 0.060701503232121465,
      "num_tokens": 318611.0,
      "step": 180
    },
    {
      "entropy": 8.534039783477784,
      "epoch": 0.00951572666718103,
      "grad_norm": 0.8828125,
      "learning_rate": 9.2e-05,
      "loss": 7.6722,
      "mean_token_accuracy": 0.06427375338971615,
      "num_tokens": 326948.0,
      "step": 185
    },
    {
      "entropy": 8.478750228881836,
      "epoch": 0.009772908468996734,
      "grad_norm": 0.81640625,
      "learning_rate": 9.45e-05,
      "loss": 7.6806,
      "mean_token_accuracy": 0.06457847729325294,
      "num_tokens": 336249.0,
      "step": 190
    },
    {
      "entropy": 8.388401317596436,
      "epoch": 0.010030090270812437,
      "grad_norm": 0.7265625,
      "learning_rate": 9.7e-05,
      "loss": 7.6163,
      "mean_token_accuracy": 0.06882799975574017,
      "num_tokens": 345182.0,
      "step": 195
    },
    {
      "entropy": 8.318638229370118,
      "epoch": 0.010287272072628141,
      "grad_norm": 0.79296875,
      "learning_rate": 9.95e-05,
      "loss": 7.632,
      "mean_token_accuracy": 0.06467234715819359,
      "num_tokens": 353642.0,
      "step": 200
    },
    {
      "entropy": 8.238949489593505,
      "epoch": 0.010544453874443844,
      "grad_norm": 1.015625,
      "learning_rate": 0.000102,
      "loss": 7.6098,
      "mean_token_accuracy": 0.06644487231969834,
      "num_tokens": 362269.0,
      "step": 205
    },
    {
      "entropy": 8.207266712188721,
      "epoch": 0.010801635676259547,
      "grad_norm": 0.92578125,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.5609,
      "mean_token_accuracy": 0.06878665201365948,
      "num_tokens": 371024.0,
      "step": 210
    },
    {
      "entropy": 8.225072002410888,
      "epoch": 0.011058817478075252,
      "grad_norm": 0.8671875,
      "learning_rate": 0.000107,
      "loss": 7.5979,
      "mean_token_accuracy": 0.06695215404033661,
      "num_tokens": 379876.0,
      "step": 215
    },
    {
      "entropy": 8.130556297302245,
      "epoch": 0.011315999279890954,
      "grad_norm": 0.8671875,
      "learning_rate": 0.0001095,
      "loss": 7.6058,
      "mean_token_accuracy": 0.06531222015619279,
      "num_tokens": 388907.0,
      "step": 220
    },
    {
      "entropy": 8.187319278717041,
      "epoch": 0.011573181081706659,
      "grad_norm": 1.0625,
      "learning_rate": 0.000112,
      "loss": 7.5483,
      "mean_token_accuracy": 0.0684064768254757,
      "num_tokens": 397629.0,
      "step": 225
    },
    {
      "entropy": 8.132099628448486,
      "epoch": 0.011830362883522362,
      "grad_norm": 0.87890625,
      "learning_rate": 0.0001145,
      "loss": 7.5356,
      "mean_token_accuracy": 0.06274137385189534,
      "num_tokens": 406919.0,
      "step": 230
    },
    {
      "entropy": 8.15430727005005,
      "epoch": 0.012087544685338066,
      "grad_norm": 0.95703125,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.5962,
      "mean_token_accuracy": 0.068911187723279,
      "num_tokens": 415471.0,
      "step": 235
    },
    {
      "entropy": 8.099409580230713,
      "epoch": 0.012344726487153769,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.5735,
      "mean_token_accuracy": 0.0665768850594759,
      "num_tokens": 424532.0,
      "step": 240
    },
    {
      "entropy": 8.095283269882202,
      "epoch": 0.012601908288969472,
      "grad_norm": 1.0234375,
      "learning_rate": 0.000122,
      "loss": 7.5317,
      "mean_token_accuracy": 0.06533802710473538,
      "num_tokens": 433457.0,
      "step": 245
    },
    {
      "entropy": 8.048843669891358,
      "epoch": 0.012859090090785176,
      "grad_norm": 0.90625,
      "learning_rate": 0.0001245,
      "loss": 7.5112,
      "mean_token_accuracy": 0.06810796111822129,
      "num_tokens": 442765.0,
      "step": 250
    },
    {
      "entropy": 8.033838605880737,
      "epoch": 0.01311627189260088,
      "grad_norm": 0.890625,
      "learning_rate": 0.000127,
      "loss": 7.5382,
      "mean_token_accuracy": 0.06802100911736489,
      "num_tokens": 451853.0,
      "step": 255
    },
    {
      "entropy": 8.045299959182739,
      "epoch": 0.013373453694416584,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001295,
      "loss": 7.4256,
      "mean_token_accuracy": 0.07066994272172451,
      "num_tokens": 460210.0,
      "step": 260
    },
    {
      "entropy": 7.9866725444793705,
      "epoch": 0.013630635496232286,
      "grad_norm": 0.90625,
      "learning_rate": 0.000132,
      "loss": 7.4002,
      "mean_token_accuracy": 0.08060714676976204,
      "num_tokens": 468673.0,
      "step": 265
    },
    {
      "entropy": 8.092905473709106,
      "epoch": 0.01388781729804799,
      "grad_norm": 0.94140625,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.4123,
      "mean_token_accuracy": 0.07691804766654968,
      "num_tokens": 477194.0,
      "step": 270
    },
    {
      "entropy": 7.961445760726929,
      "epoch": 0.014144999099863694,
      "grad_norm": 1.046875,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.381,
      "mean_token_accuracy": 0.07125308774411679,
      "num_tokens": 486869.0,
      "step": 275
    },
    {
      "entropy": 7.966795444488525,
      "epoch": 0.014402180901679397,
      "grad_norm": 1.09375,
      "learning_rate": 0.0001395,
      "loss": 7.3379,
      "mean_token_accuracy": 0.07665478959679603,
      "num_tokens": 495731.0,
      "step": 280
    },
    {
      "entropy": 7.958342027664185,
      "epoch": 0.014659362703495101,
      "grad_norm": 0.94140625,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.3933,
      "mean_token_accuracy": 0.07646878808736801,
      "num_tokens": 504071.0,
      "step": 285
    },
    {
      "entropy": 7.9638275623321535,
      "epoch": 0.014916544505310804,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0001445,
      "loss": 7.4247,
      "mean_token_accuracy": 0.07719123288989067,
      "num_tokens": 512927.0,
      "step": 290
    },
    {
      "entropy": 7.965741872787476,
      "epoch": 0.015173726307126508,
      "grad_norm": 1.015625,
      "learning_rate": 0.000147,
      "loss": 7.2639,
      "mean_token_accuracy": 0.07586801275610924,
      "num_tokens": 521405.0,
      "step": 295
    },
    {
      "entropy": 7.823179912567139,
      "epoch": 0.015430908108942211,
      "grad_norm": 0.8984375,
      "learning_rate": 0.0001495,
      "loss": 7.3976,
      "mean_token_accuracy": 0.07964370101690292,
      "num_tokens": 530473.0,
      "step": 300
    },
    {
      "entropy": 7.85285005569458,
      "epoch": 0.015688089910757916,
      "grad_norm": 0.90625,
      "learning_rate": 0.000152,
      "loss": 7.3457,
      "mean_token_accuracy": 0.07974019274115562,
      "num_tokens": 540058.0,
      "step": 305
    },
    {
      "entropy": 7.974370861053467,
      "epoch": 0.01594527171257362,
      "grad_norm": 0.953125,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.407,
      "mean_token_accuracy": 0.07686455249786377,
      "num_tokens": 548492.0,
      "step": 310
    },
    {
      "entropy": 7.900070238113403,
      "epoch": 0.01620245351438932,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000157,
      "loss": 7.313,
      "mean_token_accuracy": 0.07973849661648273,
      "num_tokens": 556788.0,
      "step": 315
    },
    {
      "entropy": 7.812545537948608,
      "epoch": 0.016459635316205024,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001595,
      "loss": 7.2565,
      "mean_token_accuracy": 0.07418388202786445,
      "num_tokens": 566122.0,
      "step": 320
    },
    {
      "entropy": 7.9200437545776365,
      "epoch": 0.01671681711802073,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000162,
      "loss": 7.2952,
      "mean_token_accuracy": 0.07806292176246643,
      "num_tokens": 575574.0,
      "step": 325
    },
    {
      "entropy": 7.8590294361114506,
      "epoch": 0.016973998919836433,
      "grad_norm": 0.98046875,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.3445,
      "mean_token_accuracy": 0.07793254256248475,
      "num_tokens": 584552.0,
      "step": 330
    },
    {
      "entropy": 7.8465721130371096,
      "epoch": 0.017231180721652136,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.3252,
      "mean_token_accuracy": 0.07768969610333443,
      "num_tokens": 593572.0,
      "step": 335
    },
    {
      "entropy": 7.80656795501709,
      "epoch": 0.01748836252346784,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.2293,
      "mean_token_accuracy": 0.07511881664395333,
      "num_tokens": 603205.0,
      "step": 340
    },
    {
      "entropy": 7.84014139175415,
      "epoch": 0.01774554432528354,
      "grad_norm": 1.125,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.2884,
      "mean_token_accuracy": 0.07499681413173676,
      "num_tokens": 612268.0,
      "step": 345
    },
    {
      "entropy": 7.784244871139526,
      "epoch": 0.018002726127099248,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.2643,
      "mean_token_accuracy": 0.07596472017467022,
      "num_tokens": 621213.0,
      "step": 350
    },
    {
      "entropy": 7.803834342956543,
      "epoch": 0.01825990792891495,
      "grad_norm": 0.9609375,
      "learning_rate": 0.000177,
      "loss": 7.3069,
      "mean_token_accuracy": 0.08319237679243088,
      "num_tokens": 630231.0,
      "step": 355
    },
    {
      "entropy": 7.815704870223999,
      "epoch": 0.018517089730730654,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0001795,
      "loss": 7.2149,
      "mean_token_accuracy": 0.0825786791741848,
      "num_tokens": 639217.0,
      "step": 360
    },
    {
      "entropy": 7.837387752532959,
      "epoch": 0.018774271532546356,
      "grad_norm": 1.03125,
      "learning_rate": 0.000182,
      "loss": 7.2476,
      "mean_token_accuracy": 0.07730407565832138,
      "num_tokens": 648233.0,
      "step": 365
    },
    {
      "entropy": 7.710758781433105,
      "epoch": 0.01903145333436206,
      "grad_norm": 1.21875,
      "learning_rate": 0.0001845,
      "loss": 7.2316,
      "mean_token_accuracy": 0.08014441356062889,
      "num_tokens": 657817.0,
      "step": 370
    },
    {
      "entropy": 7.747053003311157,
      "epoch": 0.019288635136177765,
      "grad_norm": 1.140625,
      "learning_rate": 0.000187,
      "loss": 7.1701,
      "mean_token_accuracy": 0.08062060177326202,
      "num_tokens": 666335.0,
      "step": 375
    },
    {
      "entropy": 7.7258199691772464,
      "epoch": 0.019545816937993468,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001895,
      "loss": 7.0682,
      "mean_token_accuracy": 0.08676183447241784,
      "num_tokens": 674766.0,
      "step": 380
    },
    {
      "entropy": 7.720611429214477,
      "epoch": 0.01980299873980917,
      "grad_norm": 1.171875,
      "learning_rate": 0.000192,
      "loss": 7.1426,
      "mean_token_accuracy": 0.0820883870124817,
      "num_tokens": 683125.0,
      "step": 385
    },
    {
      "entropy": 7.673658752441407,
      "epoch": 0.020060180541624874,
      "grad_norm": 0.9453125,
      "learning_rate": 0.0001945,
      "loss": 7.1867,
      "mean_token_accuracy": 0.08598564639687538,
      "num_tokens": 691561.0,
      "step": 390
    },
    {
      "entropy": 7.715641736984253,
      "epoch": 0.020317362343440577,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.1201,
      "mean_token_accuracy": 0.08909595757722855,
      "num_tokens": 701015.0,
      "step": 395
    },
    {
      "entropy": 7.7091387748718265,
      "epoch": 0.020574544145256283,
      "grad_norm": 0.98046875,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.1455,
      "mean_token_accuracy": 0.0916555643081665,
      "num_tokens": 709940.0,
      "step": 400
    },
    {
      "entropy": 7.6161031246185305,
      "epoch": 0.020831725947071986,
      "grad_norm": 1.0625,
      "learning_rate": 0.000202,
      "loss": 7.0992,
      "mean_token_accuracy": 0.08667092099785804,
      "num_tokens": 719304.0,
      "step": 405
    },
    {
      "entropy": 7.635785293579102,
      "epoch": 0.02108890774888769,
      "grad_norm": 1.109375,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.1057,
      "mean_token_accuracy": 0.08669973537325859,
      "num_tokens": 728489.0,
      "step": 410
    },
    {
      "entropy": 7.667731189727784,
      "epoch": 0.02134608955070339,
      "grad_norm": 1.109375,
      "learning_rate": 0.000207,
      "loss": 7.1789,
      "mean_token_accuracy": 0.08465257212519646,
      "num_tokens": 737769.0,
      "step": 415
    },
    {
      "entropy": 7.64384446144104,
      "epoch": 0.021603271352519094,
      "grad_norm": 1.03125,
      "learning_rate": 0.0002095,
      "loss": 7.0319,
      "mean_token_accuracy": 0.08635761365294456,
      "num_tokens": 746540.0,
      "step": 420
    },
    {
      "entropy": 7.658045482635498,
      "epoch": 0.0218604531543348,
      "grad_norm": 1.046875,
      "learning_rate": 0.000212,
      "loss": 7.216,
      "mean_token_accuracy": 0.08415560573339462,
      "num_tokens": 756118.0,
      "step": 425
    },
    {
      "entropy": 7.623081970214844,
      "epoch": 0.022117634956150503,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0002145,
      "loss": 7.0563,
      "mean_token_accuracy": 0.09152830839157104,
      "num_tokens": 764091.0,
      "step": 430
    },
    {
      "entropy": 7.5571778297424315,
      "epoch": 0.022374816757966206,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.0872,
      "mean_token_accuracy": 0.08672986775636674,
      "num_tokens": 773220.0,
      "step": 435
    },
    {
      "entropy": 7.645488929748535,
      "epoch": 0.02263199855978191,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0002195,
      "loss": 7.1345,
      "mean_token_accuracy": 0.08709268644452095,
      "num_tokens": 781937.0,
      "step": 440
    },
    {
      "entropy": 7.57753210067749,
      "epoch": 0.022889180361597615,
      "grad_norm": 1.03125,
      "learning_rate": 0.000222,
      "loss": 7.0728,
      "mean_token_accuracy": 0.08992104157805443,
      "num_tokens": 791685.0,
      "step": 445
    },
    {
      "entropy": 7.5337488651275635,
      "epoch": 0.023146362163413318,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0002245,
      "loss": 6.9439,
      "mean_token_accuracy": 0.08900289312005043,
      "num_tokens": 800759.0,
      "step": 450
    },
    {
      "entropy": 7.569718551635742,
      "epoch": 0.02340354396522902,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.0617,
      "mean_token_accuracy": 0.08903328478336334,
      "num_tokens": 809508.0,
      "step": 455
    },
    {
      "entropy": 7.4335291385650635,
      "epoch": 0.023660725767044723,
      "grad_norm": 1.15625,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.9777,
      "mean_token_accuracy": 0.08975348770618438,
      "num_tokens": 819262.0,
      "step": 460
    },
    {
      "entropy": 7.5286821842193605,
      "epoch": 0.023917907568860426,
      "grad_norm": 1.140625,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.0061,
      "mean_token_accuracy": 0.09333336725831032,
      "num_tokens": 827902.0,
      "step": 465
    },
    {
      "entropy": 7.5438226699829105,
      "epoch": 0.024175089370676132,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.071,
      "mean_token_accuracy": 0.08738465905189514,
      "num_tokens": 836678.0,
      "step": 470
    },
    {
      "entropy": 7.578305292129516,
      "epoch": 0.024432271172491835,
      "grad_norm": 1.109375,
      "learning_rate": 0.000237,
      "loss": 7.0481,
      "mean_token_accuracy": 0.08780269175767899,
      "num_tokens": 845604.0,
      "step": 475
    },
    {
      "entropy": 7.495909070968628,
      "epoch": 0.024689452974307538,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0002395,
      "loss": 6.9237,
      "mean_token_accuracy": 0.09766526669263839,
      "num_tokens": 854530.0,
      "step": 480
    },
    {
      "entropy": 7.472972011566162,
      "epoch": 0.02494663477612324,
      "grad_norm": 1.0234375,
      "learning_rate": 0.000242,
      "loss": 6.9801,
      "mean_token_accuracy": 0.08929606899619102,
      "num_tokens": 863038.0,
      "step": 485
    },
    {
      "entropy": 7.4176201820373535,
      "epoch": 0.025203816577938944,
      "grad_norm": 1.140625,
      "learning_rate": 0.0002445,
      "loss": 6.9488,
      "mean_token_accuracy": 0.09348267316818237,
      "num_tokens": 871691.0,
      "step": 490
    },
    {
      "entropy": 7.523787260055542,
      "epoch": 0.02546099837975465,
      "grad_norm": 1.109375,
      "learning_rate": 0.000247,
      "loss": 6.9412,
      "mean_token_accuracy": 0.09506363123655319,
      "num_tokens": 881026.0,
      "step": 495
    },
    {
      "entropy": 7.421153450012207,
      "epoch": 0.025718180181570353,
      "grad_norm": 1.28125,
      "learning_rate": 0.0002495,
      "loss": 6.9932,
      "mean_token_accuracy": 0.0955754928290844,
      "num_tokens": 889829.0,
      "step": 500
    },
    {
      "entropy": 7.390109062194824,
      "epoch": 0.025975361983386056,
      "grad_norm": 1.0390625,
      "learning_rate": 0.000252,
      "loss": 7.0112,
      "mean_token_accuracy": 0.0914897546172142,
      "num_tokens": 898992.0,
      "step": 505
    },
    {
      "entropy": 7.555384731292724,
      "epoch": 0.02623254378520176,
      "grad_norm": 1.15625,
      "learning_rate": 0.0002545,
      "loss": 7.0507,
      "mean_token_accuracy": 0.08820229396224022,
      "num_tokens": 908237.0,
      "step": 510
    },
    {
      "entropy": 7.433199691772461,
      "epoch": 0.02648972558701746,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000257,
      "loss": 6.8716,
      "mean_token_accuracy": 0.09959734976291656,
      "num_tokens": 916715.0,
      "step": 515
    },
    {
      "entropy": 7.360012674331665,
      "epoch": 0.026746907388833167,
      "grad_norm": 1.0,
      "learning_rate": 0.0002595,
      "loss": 6.9746,
      "mean_token_accuracy": 0.0938393734395504,
      "num_tokens": 925834.0,
      "step": 520
    },
    {
      "entropy": 7.439189624786377,
      "epoch": 0.02700408919064887,
      "grad_norm": 1.0234375,
      "learning_rate": 0.000262,
      "loss": 6.9216,
      "mean_token_accuracy": 0.09481378644704819,
      "num_tokens": 935725.0,
      "step": 525
    },
    {
      "entropy": 7.516362428665161,
      "epoch": 0.027261270992464573,
      "grad_norm": 0.98828125,
      "learning_rate": 0.00026450000000000003,
      "loss": 7.0258,
      "mean_token_accuracy": 0.09422887191176414,
      "num_tokens": 944788.0,
      "step": 530
    },
    {
      "entropy": 7.29243836402893,
      "epoch": 0.027518452794280276,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00026700000000000004,
      "loss": 6.8317,
      "mean_token_accuracy": 0.09764747545123101,
      "num_tokens": 953561.0,
      "step": 535
    },
    {
      "entropy": 7.504419994354248,
      "epoch": 0.02777563459609598,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00026950000000000005,
      "loss": 6.9259,
      "mean_token_accuracy": 0.09662783890962601,
      "num_tokens": 961942.0,
      "step": 540
    },
    {
      "entropy": 7.3940901279449465,
      "epoch": 0.028032816397911685,
      "grad_norm": 1.34375,
      "learning_rate": 0.00027200000000000005,
      "loss": 6.8816,
      "mean_token_accuracy": 0.09403559938073158,
      "num_tokens": 970699.0,
      "step": 545
    },
    {
      "entropy": 7.347795295715332,
      "epoch": 0.028289998199727388,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0002745,
      "loss": 6.9946,
      "mean_token_accuracy": 0.09083672165870667,
      "num_tokens": 980352.0,
      "step": 550
    },
    {
      "entropy": 7.459839010238648,
      "epoch": 0.02854718000154309,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000277,
      "loss": 6.8925,
      "mean_token_accuracy": 0.09576373025774956,
      "num_tokens": 988771.0,
      "step": 555
    },
    {
      "entropy": 7.296186876296997,
      "epoch": 0.028804361803358793,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0002795,
      "loss": 6.7979,
      "mean_token_accuracy": 0.09578228294849396,
      "num_tokens": 997564.0,
      "step": 560
    },
    {
      "entropy": 7.341630935668945,
      "epoch": 0.0290615436051745,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00028199999999999997,
      "loss": 6.8745,
      "mean_token_accuracy": 0.09284131526947022,
      "num_tokens": 1005945.0,
      "step": 565
    },
    {
      "entropy": 7.347255086898803,
      "epoch": 0.029318725406990202,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0002845,
      "loss": 6.9394,
      "mean_token_accuracy": 0.09283768609166146,
      "num_tokens": 1015012.0,
      "step": 570
    },
    {
      "entropy": 7.4236492156982425,
      "epoch": 0.029575907208805905,
      "grad_norm": 1.046875,
      "learning_rate": 0.000287,
      "loss": 6.9536,
      "mean_token_accuracy": 0.09391803517937661,
      "num_tokens": 1024240.0,
      "step": 575
    },
    {
      "entropy": 7.367508506774902,
      "epoch": 0.029833089010621608,
      "grad_norm": 1.21875,
      "learning_rate": 0.0002895,
      "loss": 6.8857,
      "mean_token_accuracy": 0.09755372777581214,
      "num_tokens": 1033277.0,
      "step": 580
    },
    {
      "entropy": 7.279513311386109,
      "epoch": 0.03009027081243731,
      "grad_norm": 1.34375,
      "learning_rate": 0.000292,
      "loss": 6.8268,
      "mean_token_accuracy": 0.09293166324496269,
      "num_tokens": 1042312.0,
      "step": 585
    },
    {
      "entropy": 7.353345108032227,
      "epoch": 0.030347452614253017,
      "grad_norm": 1.1875,
      "learning_rate": 0.0002945,
      "loss": 6.8653,
      "mean_token_accuracy": 0.0949218288064003,
      "num_tokens": 1052756.0,
      "step": 590
    },
    {
      "entropy": 7.368993330001831,
      "epoch": 0.03060463441606872,
      "grad_norm": 1.2421875,
      "learning_rate": 0.000297,
      "loss": 6.8974,
      "mean_token_accuracy": 0.10047846585512162,
      "num_tokens": 1061563.0,
      "step": 595
    },
    {
      "entropy": 7.286983442306519,
      "epoch": 0.030861816217884423,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0002995,
      "loss": 6.7907,
      "mean_token_accuracy": 0.10389479920268059,
      "num_tokens": 1070177.0,
      "step": 600
    },
    {
      "entropy": 7.252815437316895,
      "epoch": 0.031118998019700125,
      "grad_norm": 1.0625,
      "learning_rate": 0.000302,
      "loss": 6.8292,
      "mean_token_accuracy": 0.09795110002160072,
      "num_tokens": 1079662.0,
      "step": 605
    },
    {
      "entropy": 7.261862182617188,
      "epoch": 0.03137617982151583,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0003045,
      "loss": 6.7916,
      "mean_token_accuracy": 0.0980616994202137,
      "num_tokens": 1088719.0,
      "step": 610
    },
    {
      "entropy": 7.310345602035523,
      "epoch": 0.03163336162333153,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000307,
      "loss": 6.7727,
      "mean_token_accuracy": 0.10127385258674622,
      "num_tokens": 1096663.0,
      "step": 615
    },
    {
      "entropy": 7.34635648727417,
      "epoch": 0.03189054342514724,
      "grad_norm": 1.15625,
      "learning_rate": 0.0003095,
      "loss": 6.8751,
      "mean_token_accuracy": 0.0975107342004776,
      "num_tokens": 1105484.0,
      "step": 620
    },
    {
      "entropy": 7.2787559032440186,
      "epoch": 0.032147725226962943,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000312,
      "loss": 6.8409,
      "mean_token_accuracy": 0.096168252825737,
      "num_tokens": 1114781.0,
      "step": 625
    },
    {
      "entropy": 7.194593715667724,
      "epoch": 0.03240490702877864,
      "grad_norm": 1.0625,
      "learning_rate": 0.0003145,
      "loss": 6.8495,
      "mean_token_accuracy": 0.1023260697722435,
      "num_tokens": 1124075.0,
      "step": 630
    },
    {
      "entropy": 7.284073257446289,
      "epoch": 0.03266208883059435,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000317,
      "loss": 6.7928,
      "mean_token_accuracy": 0.09392334222793579,
      "num_tokens": 1132863.0,
      "step": 635
    },
    {
      "entropy": 7.23821120262146,
      "epoch": 0.03291927063241005,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0003195,
      "loss": 6.8477,
      "mean_token_accuracy": 0.10305669158697128,
      "num_tokens": 1141324.0,
      "step": 640
    },
    {
      "entropy": 7.2563272476196286,
      "epoch": 0.033176452434225755,
      "grad_norm": 1.1875,
      "learning_rate": 0.000322,
      "loss": 6.716,
      "mean_token_accuracy": 0.10566487908363342,
      "num_tokens": 1149406.0,
      "step": 645
    },
    {
      "entropy": 7.335630702972412,
      "epoch": 0.03343363423604146,
      "grad_norm": 1.3359375,
      "learning_rate": 0.00032450000000000003,
      "loss": 6.8656,
      "mean_token_accuracy": 0.09870733916759492,
      "num_tokens": 1158488.0,
      "step": 650
    },
    {
      "entropy": 7.255077314376831,
      "epoch": 0.03369081603785716,
      "grad_norm": 1.3203125,
      "learning_rate": 0.00032700000000000003,
      "loss": 6.8075,
      "mean_token_accuracy": 0.10482278540730476,
      "num_tokens": 1166756.0,
      "step": 655
    },
    {
      "entropy": 7.2207207679748535,
      "epoch": 0.03394799783967287,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00032950000000000004,
      "loss": 6.7814,
      "mean_token_accuracy": 0.10137899518013001,
      "num_tokens": 1175930.0,
      "step": 660
    },
    {
      "entropy": 7.146165227890014,
      "epoch": 0.034205179641488566,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00033200000000000005,
      "loss": 6.7864,
      "mean_token_accuracy": 0.1040356308221817,
      "num_tokens": 1184348.0,
      "step": 665
    },
    {
      "entropy": 7.224062728881836,
      "epoch": 0.03446236144330427,
      "grad_norm": 1.15625,
      "learning_rate": 0.00033450000000000005,
      "loss": 6.7721,
      "mean_token_accuracy": 0.10236084014177323,
      "num_tokens": 1192800.0,
      "step": 670
    },
    {
      "entropy": 7.279936122894287,
      "epoch": 0.03471954324511998,
      "grad_norm": 1.046875,
      "learning_rate": 0.000337,
      "loss": 6.8795,
      "mean_token_accuracy": 0.09708840399980545,
      "num_tokens": 1201446.0,
      "step": 675
    },
    {
      "entropy": 7.065876436233521,
      "epoch": 0.03497672504693568,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0003395,
      "loss": 6.6507,
      "mean_token_accuracy": 0.1062047965824604,
      "num_tokens": 1210088.0,
      "step": 680
    },
    {
      "entropy": 7.077348375320435,
      "epoch": 0.035233906848751384,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000342,
      "loss": 6.5917,
      "mean_token_accuracy": 0.11215948089957237,
      "num_tokens": 1219425.0,
      "step": 685
    },
    {
      "entropy": 7.214649200439453,
      "epoch": 0.03549108865056708,
      "grad_norm": 1.0625,
      "learning_rate": 0.00034449999999999997,
      "loss": 6.7802,
      "mean_token_accuracy": 0.09808368533849716,
      "num_tokens": 1228332.0,
      "step": 690
    },
    {
      "entropy": 7.219751453399658,
      "epoch": 0.03574827045238279,
      "grad_norm": 1.0234375,
      "learning_rate": 0.000347,
      "loss": 6.8329,
      "mean_token_accuracy": 0.09870714694261551,
      "num_tokens": 1237953.0,
      "step": 695
    },
    {
      "entropy": 7.24316897392273,
      "epoch": 0.036005452254198496,
      "grad_norm": 1.265625,
      "learning_rate": 0.0003495,
      "loss": 6.8479,
      "mean_token_accuracy": 0.09783646762371064,
      "num_tokens": 1247387.0,
      "step": 700
    },
    {
      "entropy": 7.2066491603851315,
      "epoch": 0.036262634056014195,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000352,
      "loss": 6.7471,
      "mean_token_accuracy": 0.10154265984892845,
      "num_tokens": 1256215.0,
      "step": 705
    },
    {
      "entropy": 7.0408368587493895,
      "epoch": 0.0365198158578299,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0003545,
      "loss": 6.6315,
      "mean_token_accuracy": 0.10381938368082047,
      "num_tokens": 1265963.0,
      "step": 710
    },
    {
      "entropy": 7.164453172683716,
      "epoch": 0.0367769976596456,
      "grad_norm": 1.28125,
      "learning_rate": 0.000357,
      "loss": 6.6903,
      "mean_token_accuracy": 0.1119053155183792,
      "num_tokens": 1275024.0,
      "step": 715
    },
    {
      "entropy": 7.111461877822876,
      "epoch": 0.03703417946146131,
      "grad_norm": 1.171875,
      "learning_rate": 0.0003595,
      "loss": 6.7586,
      "mean_token_accuracy": 0.10169535055756569,
      "num_tokens": 1283981.0,
      "step": 720
    },
    {
      "entropy": 7.1354100704193115,
      "epoch": 0.03729136126327701,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000362,
      "loss": 6.62,
      "mean_token_accuracy": 0.10666845366358757,
      "num_tokens": 1292834.0,
      "step": 725
    },
    {
      "entropy": 7.122345590591431,
      "epoch": 0.03754854306509271,
      "grad_norm": 1.1875,
      "learning_rate": 0.0003645,
      "loss": 6.7978,
      "mean_token_accuracy": 0.1032055139541626,
      "num_tokens": 1301429.0,
      "step": 730
    },
    {
      "entropy": 7.0510656356811525,
      "epoch": 0.03780572486690842,
      "grad_norm": 1.046875,
      "learning_rate": 0.000367,
      "loss": 6.7053,
      "mean_token_accuracy": 0.10353485718369485,
      "num_tokens": 1310088.0,
      "step": 735
    },
    {
      "entropy": 7.182754850387573,
      "epoch": 0.03806290666872412,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0003695,
      "loss": 6.7723,
      "mean_token_accuracy": 0.10199789181351662,
      "num_tokens": 1318249.0,
      "step": 740
    },
    {
      "entropy": 7.0828611850738525,
      "epoch": 0.038320088470539825,
      "grad_norm": 1.3046875,
      "learning_rate": 0.000372,
      "loss": 6.6795,
      "mean_token_accuracy": 0.10390995517373085,
      "num_tokens": 1327075.0,
      "step": 745
    },
    {
      "entropy": 7.114889192581177,
      "epoch": 0.03857727027235553,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0003745,
      "loss": 6.7128,
      "mean_token_accuracy": 0.1041706345975399,
      "num_tokens": 1335995.0,
      "step": 750
    },
    {
      "entropy": 7.040337038040161,
      "epoch": 0.03883445207417123,
      "grad_norm": 1.28125,
      "learning_rate": 0.000377,
      "loss": 6.6914,
      "mean_token_accuracy": 0.10317371264100075,
      "num_tokens": 1344789.0,
      "step": 755
    },
    {
      "entropy": 7.120604038238525,
      "epoch": 0.039091633875986936,
      "grad_norm": 1.234375,
      "learning_rate": 0.0003795,
      "loss": 6.6955,
      "mean_token_accuracy": 0.10629725456237793,
      "num_tokens": 1352940.0,
      "step": 760
    },
    {
      "entropy": 7.052408075332641,
      "epoch": 0.039348815677802636,
      "grad_norm": 1.015625,
      "learning_rate": 0.000382,
      "loss": 6.637,
      "mean_token_accuracy": 0.10945691764354706,
      "num_tokens": 1361803.0,
      "step": 765
    },
    {
      "entropy": 7.069132375717163,
      "epoch": 0.03960599747961834,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0003845,
      "loss": 6.7294,
      "mean_token_accuracy": 0.10019565001130104,
      "num_tokens": 1371647.0,
      "step": 770
    },
    {
      "entropy": 7.164604377746582,
      "epoch": 0.03986317928143405,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00038700000000000003,
      "loss": 6.7523,
      "mean_token_accuracy": 0.10618292987346649,
      "num_tokens": 1380447.0,
      "step": 775
    },
    {
      "entropy": 7.114570999145508,
      "epoch": 0.04012036108324975,
      "grad_norm": 1.453125,
      "learning_rate": 0.00038950000000000003,
      "loss": 6.7284,
      "mean_token_accuracy": 0.09737010598182679,
      "num_tokens": 1388902.0,
      "step": 780
    },
    {
      "entropy": 7.0223623752594,
      "epoch": 0.040377542885065454,
      "grad_norm": 1.09375,
      "learning_rate": 0.00039200000000000004,
      "loss": 6.5808,
      "mean_token_accuracy": 0.1079009048640728,
      "num_tokens": 1398178.0,
      "step": 785
    },
    {
      "entropy": 7.056776905059815,
      "epoch": 0.04063472468688115,
      "grad_norm": 1.2890625,
      "learning_rate": 0.00039450000000000005,
      "loss": 6.6511,
      "mean_token_accuracy": 0.11126778572797776,
      "num_tokens": 1406042.0,
      "step": 790
    },
    {
      "entropy": 7.084379482269287,
      "epoch": 0.04089190648869686,
      "grad_norm": 1.2890625,
      "learning_rate": 0.00039700000000000005,
      "loss": 6.6815,
      "mean_token_accuracy": 0.10524625033140182,
      "num_tokens": 1415562.0,
      "step": 795
    },
    {
      "entropy": 7.051506662368775,
      "epoch": 0.041149088290512566,
      "grad_norm": 1.171875,
      "learning_rate": 0.0003995,
      "loss": 6.6008,
      "mean_token_accuracy": 0.10510810911655426,
      "num_tokens": 1424782.0,
      "step": 800
    },
    {
      "entropy": 6.966880178451538,
      "epoch": 0.041406270092328265,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000402,
      "loss": 6.6177,
      "mean_token_accuracy": 0.10489397794008255,
      "num_tokens": 1433737.0,
      "step": 805
    },
    {
      "entropy": 7.0082066535949705,
      "epoch": 0.04166345189414397,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0004045,
      "loss": 6.6886,
      "mean_token_accuracy": 0.10373986288905143,
      "num_tokens": 1442948.0,
      "step": 810
    },
    {
      "entropy": 7.030193662643432,
      "epoch": 0.04192063369595967,
      "grad_norm": 1.0625,
      "learning_rate": 0.00040699999999999997,
      "loss": 6.617,
      "mean_token_accuracy": 0.1067310206592083,
      "num_tokens": 1452333.0,
      "step": 815
    },
    {
      "entropy": 6.962583208084107,
      "epoch": 0.04217781549777538,
      "grad_norm": 1.109375,
      "learning_rate": 0.0004095,
      "loss": 6.6201,
      "mean_token_accuracy": 0.10676174983382225,
      "num_tokens": 1461160.0,
      "step": 820
    },
    {
      "entropy": 6.962631416320801,
      "epoch": 0.04243499729959108,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000412,
      "loss": 6.6449,
      "mean_token_accuracy": 0.10844494923949241,
      "num_tokens": 1470248.0,
      "step": 825
    },
    {
      "entropy": 7.0632740497589115,
      "epoch": 0.04269217910140678,
      "grad_norm": 1.078125,
      "learning_rate": 0.0004145,
      "loss": 6.6382,
      "mean_token_accuracy": 0.11155002191662788,
      "num_tokens": 1478992.0,
      "step": 830
    },
    {
      "entropy": 7.077846574783325,
      "epoch": 0.04294936090322249,
      "grad_norm": 1.21875,
      "learning_rate": 0.000417,
      "loss": 6.6672,
      "mean_token_accuracy": 0.1010983519256115,
      "num_tokens": 1488341.0,
      "step": 835
    },
    {
      "entropy": 6.8585468292236325,
      "epoch": 0.04320654270503819,
      "grad_norm": 1.1875,
      "learning_rate": 0.0004195,
      "loss": 6.5807,
      "mean_token_accuracy": 0.10849210470914841,
      "num_tokens": 1496986.0,
      "step": 840
    },
    {
      "entropy": 7.0004956245422365,
      "epoch": 0.043463724506853894,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000422,
      "loss": 6.5236,
      "mean_token_accuracy": 0.11627273112535477,
      "num_tokens": 1505455.0,
      "step": 845
    },
    {
      "entropy": 7.062360429763794,
      "epoch": 0.0437209063086696,
      "grad_norm": 1.109375,
      "learning_rate": 0.0004245,
      "loss": 6.6677,
      "mean_token_accuracy": 0.11094246879220009,
      "num_tokens": 1515240.0,
      "step": 850
    },
    {
      "entropy": 6.843272590637207,
      "epoch": 0.0439780881104853,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000427,
      "loss": 6.4627,
      "mean_token_accuracy": 0.11083339005708695,
      "num_tokens": 1523234.0,
      "step": 855
    },
    {
      "entropy": 6.870317792892456,
      "epoch": 0.044235269912301006,
      "grad_norm": 1.25,
      "learning_rate": 0.0004295,
      "loss": 6.5185,
      "mean_token_accuracy": 0.10689858049154281,
      "num_tokens": 1531836.0,
      "step": 860
    },
    {
      "entropy": 6.954329633712769,
      "epoch": 0.04449245171411671,
      "grad_norm": 1.15625,
      "learning_rate": 0.000432,
      "loss": 6.5619,
      "mean_token_accuracy": 0.1082220919430256,
      "num_tokens": 1540611.0,
      "step": 865
    },
    {
      "entropy": 6.9597697257995605,
      "epoch": 0.04474963351593241,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0004345,
      "loss": 6.5767,
      "mean_token_accuracy": 0.10847441479563713,
      "num_tokens": 1549652.0,
      "step": 870
    },
    {
      "entropy": 6.933281469345093,
      "epoch": 0.04500681531774812,
      "grad_norm": 1.234375,
      "learning_rate": 0.000437,
      "loss": 6.654,
      "mean_token_accuracy": 0.10323531776666642,
      "num_tokens": 1559040.0,
      "step": 875
    },
    {
      "entropy": 6.976513767242432,
      "epoch": 0.04526399711956382,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0004395,
      "loss": 6.5506,
      "mean_token_accuracy": 0.10878390446305275,
      "num_tokens": 1567745.0,
      "step": 880
    },
    {
      "entropy": 6.939139747619629,
      "epoch": 0.045521178921379524,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000442,
      "loss": 6.5311,
      "mean_token_accuracy": 0.11226821094751357,
      "num_tokens": 1576077.0,
      "step": 885
    },
    {
      "entropy": 6.885157585144043,
      "epoch": 0.04577836072319523,
      "grad_norm": 1.203125,
      "learning_rate": 0.0004445,
      "loss": 6.597,
      "mean_token_accuracy": 0.10303749218583107,
      "num_tokens": 1584641.0,
      "step": 890
    },
    {
      "entropy": 6.9989728927612305,
      "epoch": 0.04603554252501093,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000447,
      "loss": 6.5356,
      "mean_token_accuracy": 0.10896688029170036,
      "num_tokens": 1594131.0,
      "step": 895
    },
    {
      "entropy": 6.9140125751495365,
      "epoch": 0.046292724326826636,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00044950000000000003,
      "loss": 6.5217,
      "mean_token_accuracy": 0.10893905013799668,
      "num_tokens": 1603099.0,
      "step": 900
    },
    {
      "entropy": 6.941550970077515,
      "epoch": 0.046549906128642335,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00045200000000000004,
      "loss": 6.5503,
      "mean_token_accuracy": 0.11116070300340652,
      "num_tokens": 1611453.0,
      "step": 905
    },
    {
      "entropy": 6.77474455833435,
      "epoch": 0.04680708793045804,
      "grad_norm": 1.25,
      "learning_rate": 0.00045450000000000004,
      "loss": 6.5397,
      "mean_token_accuracy": 0.10877310186624527,
      "num_tokens": 1619577.0,
      "step": 910
    },
    {
      "entropy": 7.0068763256072994,
      "epoch": 0.04706426973227375,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00045700000000000005,
      "loss": 6.6618,
      "mean_token_accuracy": 0.10706020519137383,
      "num_tokens": 1629026.0,
      "step": 915
    },
    {
      "entropy": 6.97544412612915,
      "epoch": 0.04732145153408945,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00045950000000000006,
      "loss": 6.5855,
      "mean_token_accuracy": 0.11112762615084648,
      "num_tokens": 1638556.0,
      "step": 920
    },
    {
      "entropy": 6.83156042098999,
      "epoch": 0.04757863333590515,
      "grad_norm": 1.2109375,
      "learning_rate": 0.000462,
      "loss": 6.4674,
      "mean_token_accuracy": 0.11065400391817093,
      "num_tokens": 1647756.0,
      "step": 925
    },
    {
      "entropy": 6.925829887390137,
      "epoch": 0.04783581513772085,
      "grad_norm": 1.078125,
      "learning_rate": 0.0004645,
      "loss": 6.5459,
      "mean_token_accuracy": 0.10694767236709594,
      "num_tokens": 1656614.0,
      "step": 930
    },
    {
      "entropy": 6.851103353500366,
      "epoch": 0.04809299693953656,
      "grad_norm": 1.078125,
      "learning_rate": 0.000467,
      "loss": 6.5566,
      "mean_token_accuracy": 0.11177869439125061,
      "num_tokens": 1666213.0,
      "step": 935
    },
    {
      "entropy": 6.823415803909302,
      "epoch": 0.048350178741352265,
      "grad_norm": 1.15625,
      "learning_rate": 0.0004695,
      "loss": 6.5108,
      "mean_token_accuracy": 0.11019086241722106,
      "num_tokens": 1675435.0,
      "step": 940
    },
    {
      "entropy": 6.8377485275268555,
      "epoch": 0.048607360543167964,
      "grad_norm": 1.15625,
      "learning_rate": 0.000472,
      "loss": 6.4806,
      "mean_token_accuracy": 0.11481974124908448,
      "num_tokens": 1684268.0,
      "step": 945
    },
    {
      "entropy": 6.837112474441528,
      "epoch": 0.04886454234498367,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0004745,
      "loss": 6.566,
      "mean_token_accuracy": 0.10879503637552261,
      "num_tokens": 1692665.0,
      "step": 950
    },
    {
      "entropy": 7.00029149055481,
      "epoch": 0.04912172414679937,
      "grad_norm": 1.109375,
      "learning_rate": 0.000477,
      "loss": 6.6023,
      "mean_token_accuracy": 0.11165886968374253,
      "num_tokens": 1701321.0,
      "step": 955
    },
    {
      "entropy": 6.796492385864258,
      "epoch": 0.049378905948615076,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0004795,
      "loss": 6.5413,
      "mean_token_accuracy": 0.10716139823198319,
      "num_tokens": 1710476.0,
      "step": 960
    },
    {
      "entropy": 6.805513620376587,
      "epoch": 0.04963608775043078,
      "grad_norm": 1.03125,
      "learning_rate": 0.000482,
      "loss": 6.4891,
      "mean_token_accuracy": 0.10693883448839188,
      "num_tokens": 1719949.0,
      "step": 965
    },
    {
      "entropy": 6.972143602371216,
      "epoch": 0.04989326955224648,
      "grad_norm": 1.046875,
      "learning_rate": 0.0004845,
      "loss": 6.6165,
      "mean_token_accuracy": 0.10792995691299438,
      "num_tokens": 1729362.0,
      "step": 970
    },
    {
      "entropy": 6.834133863449097,
      "epoch": 0.05015045135406219,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000487,
      "loss": 6.5197,
      "mean_token_accuracy": 0.10525891557335854,
      "num_tokens": 1739001.0,
      "step": 975
    },
    {
      "entropy": 6.7445004940032955,
      "epoch": 0.05040763315587789,
      "grad_norm": 1.109375,
      "learning_rate": 0.0004895,
      "loss": 6.4256,
      "mean_token_accuracy": 0.11702816039323807,
      "num_tokens": 1748249.0,
      "step": 980
    },
    {
      "entropy": 6.755212068557739,
      "epoch": 0.050664814957693594,
      "grad_norm": 1.09375,
      "learning_rate": 0.000492,
      "loss": 6.4386,
      "mean_token_accuracy": 0.1141409620642662,
      "num_tokens": 1757070.0,
      "step": 985
    },
    {
      "entropy": 6.799167490005493,
      "epoch": 0.0509219967595093,
      "grad_norm": 1.109375,
      "learning_rate": 0.0004945,
      "loss": 6.4032,
      "mean_token_accuracy": 0.11792294010519981,
      "num_tokens": 1765737.0,
      "step": 990
    },
    {
      "entropy": 6.891513156890869,
      "epoch": 0.051179178561325,
      "grad_norm": 1.109375,
      "learning_rate": 0.000497,
      "loss": 6.5878,
      "mean_token_accuracy": 0.11050201207399368,
      "num_tokens": 1774942.0,
      "step": 995
    },
    {
      "entropy": 6.857363891601563,
      "epoch": 0.051436360363140705,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0004995,
      "loss": 6.5936,
      "mean_token_accuracy": 0.10368210449814796,
      "num_tokens": 1784256.0,
      "step": 1000
    },
    {
      "entropy": 6.849530935287476,
      "epoch": 0.051693542164956405,
      "grad_norm": 1.078125,
      "learning_rate": 0.000499998026082006,
      "loss": 6.5383,
      "mean_token_accuracy": 0.10572032853960991,
      "num_tokens": 1792926.0,
      "step": 1005
    },
    {
      "entropy": 6.72293267250061,
      "epoch": 0.05195072396677211,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0004999900070995136,
      "loss": 6.4893,
      "mean_token_accuracy": 0.11575818508863449,
      "num_tokens": 1802070.0,
      "step": 1010
    },
    {
      "entropy": 6.841842365264893,
      "epoch": 0.05220790576858782,
      "grad_norm": 1.03125,
      "learning_rate": 0.0004999758199023239,
      "loss": 6.5344,
      "mean_token_accuracy": 0.10665113478899002,
      "num_tokens": 1811507.0,
      "step": 1015
    },
    {
      "entropy": 6.851677942276001,
      "epoch": 0.05246508757040352,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0004999554648793858,
      "loss": 6.4522,
      "mean_token_accuracy": 0.11116268336772919,
      "num_tokens": 1820311.0,
      "step": 1020
    },
    {
      "entropy": 6.710117959976197,
      "epoch": 0.05272226937221922,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0004999289425887425,
      "loss": 6.4099,
      "mean_token_accuracy": 0.1138461858034134,
      "num_tokens": 1828948.0,
      "step": 1025
    },
    {
      "entropy": 6.834085750579834,
      "epoch": 0.05297945117403492,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0004998962537575161,
      "loss": 6.5724,
      "mean_token_accuracy": 0.1098745584487915,
      "num_tokens": 1838350.0,
      "step": 1030
    },
    {
      "entropy": 6.842246675491333,
      "epoch": 0.05323663297585063,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0004998573992818874,
      "loss": 6.4004,
      "mean_token_accuracy": 0.12005882859230041,
      "num_tokens": 1847162.0,
      "step": 1035
    },
    {
      "entropy": 6.665293884277344,
      "epoch": 0.053493814777666335,
      "grad_norm": 1.09375,
      "learning_rate": 0.0004998123802270715,
      "loss": 6.4849,
      "mean_token_accuracy": 0.11263752803206444,
      "num_tokens": 1856275.0,
      "step": 1040
    },
    {
      "entropy": 6.729813432693481,
      "epoch": 0.053750996579482034,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0004997611978272886,
      "loss": 6.3855,
      "mean_token_accuracy": 0.11651406660676003,
      "num_tokens": 1864663.0,
      "step": 1045
    },
    {
      "entropy": 6.733455944061279,
      "epoch": 0.05400817838129774,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0004997038534857298,
      "loss": 6.424,
      "mean_token_accuracy": 0.1177938535809517,
      "num_tokens": 1874622.0,
      "step": 1050
    },
    {
      "entropy": 6.7023192882537845,
      "epoch": 0.05426536018311344,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0004996403487745194,
      "loss": 6.3922,
      "mean_token_accuracy": 0.11079680770635605,
      "num_tokens": 1884257.0,
      "step": 1055
    },
    {
      "entropy": 6.801939916610718,
      "epoch": 0.054522541984929146,
      "grad_norm": 0.96875,
      "learning_rate": 0.000499570685434671,
      "loss": 6.4462,
      "mean_token_accuracy": 0.11080927178263664,
      "num_tokens": 1894336.0,
      "step": 1060
    },
    {
      "entropy": 6.734097909927368,
      "epoch": 0.05477972378674485,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0004994948653760405,
      "loss": 6.4129,
      "mean_token_accuracy": 0.11459591910243035,
      "num_tokens": 1903305.0,
      "step": 1065
    },
    {
      "entropy": 6.686365461349487,
      "epoch": 0.05503690558856055,
      "grad_norm": 1.171875,
      "learning_rate": 0.0004994128906772729,
      "loss": 6.4414,
      "mean_token_accuracy": 0.11344051584601403,
      "num_tokens": 1911992.0,
      "step": 1070
    },
    {
      "entropy": 6.707837152481079,
      "epoch": 0.05529408739037626,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000499324763585746,
      "loss": 6.3462,
      "mean_token_accuracy": 0.12238444536924362,
      "num_tokens": 1920826.0,
      "step": 1075
    },
    {
      "entropy": 6.851500606536865,
      "epoch": 0.05555126919219196,
      "grad_norm": 1.15625,
      "learning_rate": 0.0004992304865175085,
      "loss": 6.5005,
      "mean_token_accuracy": 0.11342206448316575,
      "num_tokens": 1930181.0,
      "step": 1080
    },
    {
      "entropy": 6.683105993270874,
      "epoch": 0.05580845099400766,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0004991300620572138,
      "loss": 6.3627,
      "mean_token_accuracy": 0.11612597554922104,
      "num_tokens": 1938865.0,
      "step": 1085
    },
    {
      "entropy": 6.6627490520477295,
      "epoch": 0.05606563279582337,
      "grad_norm": 1.140625,
      "learning_rate": 0.0004990234929580494,
      "loss": 6.3018,
      "mean_token_accuracy": 0.11800351217389107,
      "num_tokens": 1947979.0,
      "step": 1090
    },
    {
      "entropy": 6.705393505096436,
      "epoch": 0.05632281459763907,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0004989107821416609,
      "loss": 6.4207,
      "mean_token_accuracy": 0.11706310212612152,
      "num_tokens": 1957012.0,
      "step": 1095
    },
    {
      "entropy": 6.785688734054565,
      "epoch": 0.056579996399454775,
      "grad_norm": 1.078125,
      "learning_rate": 0.0004987919326980723,
      "loss": 6.5063,
      "mean_token_accuracy": 0.11153422519564629,
      "num_tokens": 1966613.0,
      "step": 1100
    },
    {
      "entropy": 6.662994146347046,
      "epoch": 0.05683717820127048,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0004986669478856011,
      "loss": 6.4567,
      "mean_token_accuracy": 0.11049317792057992,
      "num_tokens": 1975878.0,
      "step": 1105
    },
    {
      "entropy": 6.703376007080078,
      "epoch": 0.05709436000308618,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0004985358311307688,
      "loss": 6.3858,
      "mean_token_accuracy": 0.12022560909390449,
      "num_tokens": 1984828.0,
      "step": 1110
    },
    {
      "entropy": 6.687681436538696,
      "epoch": 0.05735154180490189,
      "grad_norm": 1.25,
      "learning_rate": 0.0004983985860282081,
      "loss": 6.3282,
      "mean_token_accuracy": 0.11830979585647583,
      "num_tokens": 1992706.0,
      "step": 1115
    },
    {
      "entropy": 6.691852474212647,
      "epoch": 0.057608723606717586,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0004982552163405623,
      "loss": 6.3836,
      "mean_token_accuracy": 0.11681668907403946,
      "num_tokens": 2001461.0,
      "step": 1120
    },
    {
      "entropy": 6.5880796909332275,
      "epoch": 0.05786590540853329,
      "grad_norm": 1.09375,
      "learning_rate": 0.0004981057259983839,
      "loss": 6.3809,
      "mean_token_accuracy": 0.11749306172132493,
      "num_tokens": 2011029.0,
      "step": 1125
    },
    {
      "entropy": 6.7658202171325685,
      "epoch": 0.058123087210349,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0004979501191000262,
      "loss": 6.4011,
      "mean_token_accuracy": 0.11484191119670868,
      "num_tokens": 2019712.0,
      "step": 1130
    },
    {
      "entropy": 6.552847003936767,
      "epoch": 0.0583802690121647,
      "grad_norm": 1.140625,
      "learning_rate": 0.0004977883999115311,
      "loss": 6.2373,
      "mean_token_accuracy": 0.12176965028047562,
      "num_tokens": 2028411.0,
      "step": 1135
    },
    {
      "entropy": 6.681560611724853,
      "epoch": 0.058637450813980405,
      "grad_norm": 1.0625,
      "learning_rate": 0.0004976205728665113,
      "loss": 6.395,
      "mean_token_accuracy": 0.11524997726082802,
      "num_tokens": 2037874.0,
      "step": 1140
    },
    {
      "entropy": 6.68039722442627,
      "epoch": 0.058894632615796104,
      "grad_norm": 1.171875,
      "learning_rate": 0.0004974466425660307,
      "loss": 6.3971,
      "mean_token_accuracy": 0.11318053975701332,
      "num_tokens": 2046752.0,
      "step": 1145
    },
    {
      "entropy": 6.605433797836303,
      "epoch": 0.05915181441761181,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0004972666137784759,
      "loss": 6.3035,
      "mean_token_accuracy": 0.12526411563158035,
      "num_tokens": 2054893.0,
      "step": 1150
    },
    {
      "entropy": 6.69100604057312,
      "epoch": 0.059408996219427516,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0004970804914394271,
      "loss": 6.2801,
      "mean_token_accuracy": 0.12134814634919167,
      "num_tokens": 2062794.0,
      "step": 1155
    },
    {
      "entropy": 6.600447416305542,
      "epoch": 0.059666178021243216,
      "grad_norm": 1.171875,
      "learning_rate": 0.0004968882806515225,
      "loss": 6.4006,
      "mean_token_accuracy": 0.11898823902010917,
      "num_tokens": 2072225.0,
      "step": 1160
    },
    {
      "entropy": 6.584507894515991,
      "epoch": 0.05992335982305892,
      "grad_norm": 1.2109375,
      "learning_rate": 0.0004966899866843177,
      "loss": 6.3768,
      "mean_token_accuracy": 0.11224907487630845,
      "num_tokens": 2080521.0,
      "step": 1165
    },
    {
      "entropy": 6.6145092964172365,
      "epoch": 0.06018054162487462,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000496485614974142,
      "loss": 6.2801,
      "mean_token_accuracy": 0.1179177112877369,
      "num_tokens": 2090633.0,
      "step": 1170
    },
    {
      "entropy": 6.679648780822754,
      "epoch": 0.06043772342669033,
      "grad_norm": 1.1875,
      "learning_rate": 0.0004962751711239492,
      "loss": 6.4617,
      "mean_token_accuracy": 0.1087147168815136,
      "num_tokens": 2100284.0,
      "step": 1175
    },
    {
      "entropy": 6.599804067611695,
      "epoch": 0.060694905228506034,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0004960586609031636,
      "loss": 6.2978,
      "mean_token_accuracy": 0.11903873831033707,
      "num_tokens": 2109612.0,
      "step": 1180
    },
    {
      "entropy": 6.658626890182495,
      "epoch": 0.06095208703032173,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0004958360902475224,
      "loss": 6.3076,
      "mean_token_accuracy": 0.1250632882118225,
      "num_tokens": 2117817.0,
      "step": 1185
    },
    {
      "entropy": 6.6112429141998295,
      "epoch": 0.06120926883213744,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0004956074652589125,
      "loss": 6.4007,
      "mean_token_accuracy": 0.1222650684416294,
      "num_tokens": 2126283.0,
      "step": 1190
    },
    {
      "entropy": 6.64881386756897,
      "epoch": 0.06146645063395314,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0004953727922052035,
      "loss": 6.3017,
      "mean_token_accuracy": 0.11719283163547516,
      "num_tokens": 2134361.0,
      "step": 1195
    },
    {
      "entropy": 6.705007314682007,
      "epoch": 0.061723632435768845,
      "grad_norm": 1.09375,
      "learning_rate": 0.0004951320775200756,
      "loss": 6.389,
      "mean_token_accuracy": 0.11199460625648498,
      "num_tokens": 2143304.0,
      "step": 1200
    },
    {
      "entropy": 6.519802904129028,
      "epoch": 0.06198081423758455,
      "grad_norm": 1.234375,
      "learning_rate": 0.0004948853278028436,
      "loss": 6.2467,
      "mean_token_accuracy": 0.11709044873714447,
      "num_tokens": 2151650.0,
      "step": 1205
    },
    {
      "entropy": 6.573320007324218,
      "epoch": 0.06223799603940025,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0004946325498182755,
      "loss": 6.3113,
      "mean_token_accuracy": 0.11818666979670525,
      "num_tokens": 2161139.0,
      "step": 1210
    },
    {
      "entropy": 6.78554859161377,
      "epoch": 0.06249517784121596,
      "grad_norm": 1.046875,
      "learning_rate": 0.0004943737504964076,
      "loss": 6.4733,
      "mean_token_accuracy": 0.11637833341956139,
      "num_tokens": 2170606.0,
      "step": 1215
    },
    {
      "entropy": 6.549322175979614,
      "epoch": 0.06275235964303166,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000494108936932354,
      "loss": 6.3382,
      "mean_token_accuracy": 0.11747744753956794,
      "num_tokens": 2180284.0,
      "step": 1220
    },
    {
      "entropy": 6.6795018196105955,
      "epoch": 0.06300954144484737,
      "grad_norm": 1.125,
      "learning_rate": 0.0004938381163861124,
      "loss": 6.3362,
      "mean_token_accuracy": 0.12103840410709381,
      "num_tokens": 2189130.0,
      "step": 1225
    },
    {
      "entropy": 6.5853265762329105,
      "epoch": 0.06326672324666306,
      "grad_norm": 1.15625,
      "learning_rate": 0.0004935612962823645,
      "loss": 6.3564,
      "mean_token_accuracy": 0.11555552780628205,
      "num_tokens": 2198083.0,
      "step": 1230
    },
    {
      "entropy": 6.717031812667846,
      "epoch": 0.06352390504847877,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0004932784842102739,
      "loss": 6.3463,
      "mean_token_accuracy": 0.12118180245161056,
      "num_tokens": 2206470.0,
      "step": 1235
    },
    {
      "entropy": 6.5396645069122314,
      "epoch": 0.06378108685029447,
      "grad_norm": 1.109375,
      "learning_rate": 0.0004929896879232758,
      "loss": 6.3004,
      "mean_token_accuracy": 0.12020415365695954,
      "num_tokens": 2215241.0,
      "step": 1240
    },
    {
      "entropy": 6.611561393737793,
      "epoch": 0.06403826865211018,
      "grad_norm": 1.15625,
      "learning_rate": 0.0004926949153388668,
      "loss": 6.3158,
      "mean_token_accuracy": 0.12042762041091919,
      "num_tokens": 2224047.0,
      "step": 1245
    },
    {
      "entropy": 6.717500877380371,
      "epoch": 0.06429545045392589,
      "grad_norm": 1.109375,
      "learning_rate": 0.0004923941745383859,
      "loss": 6.4761,
      "mean_token_accuracy": 0.11400299072265625,
      "num_tokens": 2234030.0,
      "step": 1250
    },
    {
      "entropy": 6.551206016540528,
      "epoch": 0.06455263225574158,
      "grad_norm": 1.09375,
      "learning_rate": 0.000492087473766794,
      "loss": 6.2506,
      "mean_token_accuracy": 0.12165699452161789,
      "num_tokens": 2243123.0,
      "step": 1255
    },
    {
      "entropy": 6.559505128860474,
      "epoch": 0.06480981405755729,
      "grad_norm": 1.046875,
      "learning_rate": 0.000491774821432448,
      "loss": 6.2329,
      "mean_token_accuracy": 0.12427677810192109,
      "num_tokens": 2251778.0,
      "step": 1260
    },
    {
      "entropy": 6.605167245864868,
      "epoch": 0.06506699585937299,
      "grad_norm": 1.078125,
      "learning_rate": 0.0004914562261068693,
      "loss": 6.2228,
      "mean_token_accuracy": 0.12148385569453239,
      "num_tokens": 2261552.0,
      "step": 1265
    },
    {
      "entropy": 6.4509941101074215,
      "epoch": 0.0653241776611887,
      "grad_norm": 1.03125,
      "learning_rate": 0.0004911316965245098,
      "loss": 6.2464,
      "mean_token_accuracy": 0.12392940372228622,
      "num_tokens": 2270543.0,
      "step": 1270
    },
    {
      "entropy": 6.684006547927856,
      "epoch": 0.0655813594630044,
      "grad_norm": 1.2421875,
      "learning_rate": 0.000490801241582512,
      "loss": 6.2811,
      "mean_token_accuracy": 0.12095867022871971,
      "num_tokens": 2278856.0,
      "step": 1275
    },
    {
      "entropy": 6.489159202575683,
      "epoch": 0.0658385412648201,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000490464870340465,
      "loss": 6.2578,
      "mean_token_accuracy": 0.12322199791669845,
      "num_tokens": 2287208.0,
      "step": 1280
    },
    {
      "entropy": 6.573577213287353,
      "epoch": 0.0660957230666358,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0004901225920201563,
      "loss": 6.3295,
      "mean_token_accuracy": 0.11680645272135734,
      "num_tokens": 2296947.0,
      "step": 1285
    },
    {
      "entropy": 6.5740087032318115,
      "epoch": 0.06635290486845151,
      "grad_norm": 1.03125,
      "learning_rate": 0.000489774416005319,
      "loss": 6.2783,
      "mean_token_accuracy": 0.12419264763593674,
      "num_tokens": 2305853.0,
      "step": 1290
    },
    {
      "entropy": 6.506151580810547,
      "epoch": 0.06661008667026722,
      "grad_norm": 1.0625,
      "learning_rate": 0.0004894203518413742,
      "loss": 6.2311,
      "mean_token_accuracy": 0.11923173069953918,
      "num_tokens": 2315344.0,
      "step": 1295
    },
    {
      "entropy": 6.499106740951538,
      "epoch": 0.06686726847208292,
      "grad_norm": 1.03125,
      "learning_rate": 0.0004890604092351701,
      "loss": 6.2209,
      "mean_token_accuracy": 0.1210881769657135,
      "num_tokens": 2324007.0,
      "step": 1300
    },
    {
      "entropy": 6.517620944976807,
      "epoch": 0.06712445027389861,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000488694598054715,
      "loss": 6.2672,
      "mean_token_accuracy": 0.11856792867183685,
      "num_tokens": 2332613.0,
      "step": 1305
    },
    {
      "entropy": 6.554975318908691,
      "epoch": 0.06738163207571432,
      "grad_norm": 1.078125,
      "learning_rate": 0.0004883229283289071,
      "loss": 6.2676,
      "mean_token_accuracy": 0.12289687469601632,
      "num_tokens": 2342019.0,
      "step": 1310
    },
    {
      "entropy": 6.47722110748291,
      "epoch": 0.06763881387753003,
      "grad_norm": 1.125,
      "learning_rate": 0.00048794541024725993,
      "loss": 6.2182,
      "mean_token_accuracy": 0.12205516248941421,
      "num_tokens": 2350715.0,
      "step": 1315
    },
    {
      "entropy": 6.656716966629029,
      "epoch": 0.06789599567934573,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0004875620541596221,
      "loss": 6.3923,
      "mean_token_accuracy": 0.12098478376865388,
      "num_tokens": 2359699.0,
      "step": 1320
    },
    {
      "entropy": 6.4792803764343265,
      "epoch": 0.06815317748116144,
      "grad_norm": 1.125,
      "learning_rate": 0.00048717287057589454,
      "loss": 6.1595,
      "mean_token_accuracy": 0.12839691638946532,
      "num_tokens": 2368782.0,
      "step": 1325
    },
    {
      "entropy": 6.383249664306641,
      "epoch": 0.06841035928297713,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0004867778701657417,
      "loss": 6.0096,
      "mean_token_accuracy": 0.13362448140978814,
      "num_tokens": 2377235.0,
      "step": 1330
    },
    {
      "entropy": 6.409832763671875,
      "epoch": 0.06866754108479284,
      "grad_norm": 1.046875,
      "learning_rate": 0.00048637706375829955,
      "loss": 6.2013,
      "mean_token_accuracy": 0.12747161388397216,
      "num_tokens": 2386265.0,
      "step": 1335
    },
    {
      "entropy": 6.527412176132202,
      "epoch": 0.06892472288660854,
      "grad_norm": 1.140625,
      "learning_rate": 0.000485970462341878,
      "loss": 6.1131,
      "mean_token_accuracy": 0.1332041934132576,
      "num_tokens": 2394953.0,
      "step": 1340
    },
    {
      "entropy": 6.503418636322022,
      "epoch": 0.06918190468842425,
      "grad_norm": 1.03125,
      "learning_rate": 0.00048555807706366044,
      "loss": 6.3003,
      "mean_token_accuracy": 0.11948163360357285,
      "num_tokens": 2403792.0,
      "step": 1345
    },
    {
      "entropy": 6.4240118026733395,
      "epoch": 0.06943908649023996,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00048513991922939756,
      "loss": 6.1478,
      "mean_token_accuracy": 0.1259373866021633,
      "num_tokens": 2412252.0,
      "step": 1350
    },
    {
      "entropy": 6.6844557762146,
      "epoch": 0.06969626829205565,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00048471600030309744,
      "loss": 6.2847,
      "mean_token_accuracy": 0.1220081552863121,
      "num_tokens": 2420364.0,
      "step": 1355
    },
    {
      "entropy": 6.442555618286133,
      "epoch": 0.06995345009387136,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00048428633190671186,
      "loss": 6.1597,
      "mean_token_accuracy": 0.12498654872179031,
      "num_tokens": 2429333.0,
      "step": 1360
    },
    {
      "entropy": 6.515508556365967,
      "epoch": 0.07021063189568706,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0004838509258198167,
      "loss": 6.2702,
      "mean_token_accuracy": 0.12291633188724518,
      "num_tokens": 2437439.0,
      "step": 1365
    },
    {
      "entropy": 6.4559262752532955,
      "epoch": 0.07046781369750277,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00048340979397929,
      "loss": 6.2392,
      "mean_token_accuracy": 0.12877265959978104,
      "num_tokens": 2446084.0,
      "step": 1370
    },
    {
      "entropy": 6.574571943283081,
      "epoch": 0.07072499549931847,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00048296294847898386,
      "loss": 6.2038,
      "mean_token_accuracy": 0.11378729492425918,
      "num_tokens": 2455613.0,
      "step": 1375
    },
    {
      "entropy": 6.547432279586792,
      "epoch": 0.07098217730113417,
      "grad_norm": 1.1875,
      "learning_rate": 0.0004825104015693934,
      "loss": 6.336,
      "mean_token_accuracy": 0.12563420534133912,
      "num_tokens": 2464123.0,
      "step": 1380
    },
    {
      "entropy": 6.496583318710327,
      "epoch": 0.07123935910294987,
      "grad_norm": 1.140625,
      "learning_rate": 0.0004820521656573208,
      "loss": 6.2003,
      "mean_token_accuracy": 0.12900396287441254,
      "num_tokens": 2472972.0,
      "step": 1385
    },
    {
      "entropy": 6.55055980682373,
      "epoch": 0.07149654090476558,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00048158825330553505,
      "loss": 6.3127,
      "mean_token_accuracy": 0.12014695033431053,
      "num_tokens": 2482017.0,
      "step": 1390
    },
    {
      "entropy": 6.498235702514648,
      "epoch": 0.07175372270658129,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00048111867723242763,
      "loss": 6.1993,
      "mean_token_accuracy": 0.12744636759161948,
      "num_tokens": 2490771.0,
      "step": 1395
    },
    {
      "entropy": 6.492023563385009,
      "epoch": 0.07201090450839699,
      "grad_norm": 1.0,
      "learning_rate": 0.0004806434503116637,
      "loss": 6.2633,
      "mean_token_accuracy": 0.12012107148766518,
      "num_tokens": 2501047.0,
      "step": 1400
    },
    {
      "entropy": 6.459356260299683,
      "epoch": 0.07226808631021268,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0004801625855718296,
      "loss": 6.2797,
      "mean_token_accuracy": 0.12193729802966118,
      "num_tokens": 2509689.0,
      "step": 1405
    },
    {
      "entropy": 6.523634672164917,
      "epoch": 0.07252526811202839,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00047967609619607477,
      "loss": 6.2162,
      "mean_token_accuracy": 0.1272864632308483,
      "num_tokens": 2519067.0,
      "step": 1410
    },
    {
      "entropy": 6.3656079292297365,
      "epoch": 0.0727824499138441,
      "grad_norm": 1.078125,
      "learning_rate": 0.0004791839955217513,
      "loss": 6.1233,
      "mean_token_accuracy": 0.12799235731363295,
      "num_tokens": 2527921.0,
      "step": 1415
    },
    {
      "entropy": 6.555266809463501,
      "epoch": 0.0730396317156598,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00047868629704004786,
      "loss": 6.2048,
      "mean_token_accuracy": 0.12755087167024612,
      "num_tokens": 2536424.0,
      "step": 1420
    },
    {
      "entropy": 6.4298278331756595,
      "epoch": 0.07329681351747551,
      "grad_norm": 1.109375,
      "learning_rate": 0.00047818301439561965,
      "loss": 6.1967,
      "mean_token_accuracy": 0.12071703523397445,
      "num_tokens": 2546029.0,
      "step": 1425
    },
    {
      "entropy": 6.526437473297119,
      "epoch": 0.0735539953192912,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00047767416138621454,
      "loss": 6.2481,
      "mean_token_accuracy": 0.12410413399338723,
      "num_tokens": 2554861.0,
      "step": 1430
    },
    {
      "entropy": 6.460501337051392,
      "epoch": 0.07381117712110691,
      "grad_norm": 1.140625,
      "learning_rate": 0.000477159751962295,
      "loss": 6.1015,
      "mean_token_accuracy": 0.12634221836924553,
      "num_tokens": 2563405.0,
      "step": 1435
    },
    {
      "entropy": 6.288591575622559,
      "epoch": 0.07406835892292261,
      "grad_norm": 1.125,
      "learning_rate": 0.00047663980022665507,
      "loss": 6.0832,
      "mean_token_accuracy": 0.1300654336810112,
      "num_tokens": 2571409.0,
      "step": 1440
    },
    {
      "entropy": 6.524644994735718,
      "epoch": 0.07432554072473832,
      "grad_norm": 1.140625,
      "learning_rate": 0.00047611432043403437,
      "loss": 6.323,
      "mean_token_accuracy": 0.11622402295470238,
      "num_tokens": 2581233.0,
      "step": 1445
    },
    {
      "entropy": 6.429956722259521,
      "epoch": 0.07458272252655403,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0004755833269907267,
      "loss": 6.273,
      "mean_token_accuracy": 0.11982614472508431,
      "num_tokens": 2591528.0,
      "step": 1450
    },
    {
      "entropy": 6.653250694274902,
      "epoch": 0.07483990432836972,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0004750468344541857,
      "loss": 6.2093,
      "mean_token_accuracy": 0.1260430246591568,
      "num_tokens": 2600033.0,
      "step": 1455
    },
    {
      "entropy": 6.354333925247192,
      "epoch": 0.07509708613018543,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00047450485753262525,
      "loss": 6.1861,
      "mean_token_accuracy": 0.12549542263150215,
      "num_tokens": 2608648.0,
      "step": 1460
    },
    {
      "entropy": 6.368370294570923,
      "epoch": 0.07535426793200113,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00047395741108461633,
      "loss": 6.0852,
      "mean_token_accuracy": 0.13009310886263847,
      "num_tokens": 2617727.0,
      "step": 1465
    },
    {
      "entropy": 6.389603805541992,
      "epoch": 0.07561144973381684,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00047340451011867985,
      "loss": 6.0666,
      "mean_token_accuracy": 0.13752511888742447,
      "num_tokens": 2625463.0,
      "step": 1470
    },
    {
      "entropy": 6.439476728439331,
      "epoch": 0.07586863153563254,
      "grad_norm": 1.09375,
      "learning_rate": 0.00047284616979287515,
      "loss": 6.1768,
      "mean_token_accuracy": 0.12700055465102195,
      "num_tokens": 2635050.0,
      "step": 1475
    },
    {
      "entropy": 6.452608394622803,
      "epoch": 0.07612581333744824,
      "grad_norm": 1.078125,
      "learning_rate": 0.00047228240541438433,
      "loss": 6.2373,
      "mean_token_accuracy": 0.1270735152065754,
      "num_tokens": 2645129.0,
      "step": 1480
    },
    {
      "entropy": 6.402850103378296,
      "epoch": 0.07638299513926394,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00047171323243909257,
      "loss": 6.1132,
      "mean_token_accuracy": 0.12463590428233147,
      "num_tokens": 2653966.0,
      "step": 1485
    },
    {
      "entropy": 6.413847303390503,
      "epoch": 0.07664017694107965,
      "grad_norm": 1.09375,
      "learning_rate": 0.00047113866647116457,
      "loss": 6.1521,
      "mean_token_accuracy": 0.1268475502729416,
      "num_tokens": 2663219.0,
      "step": 1490
    },
    {
      "entropy": 6.427061939239502,
      "epoch": 0.07689735874289536,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0004705587232626164,
      "loss": 6.0832,
      "mean_token_accuracy": 0.1297985441982746,
      "num_tokens": 2671468.0,
      "step": 1495
    },
    {
      "entropy": 6.292563104629517,
      "epoch": 0.07715454054471106,
      "grad_norm": 1.0625,
      "learning_rate": 0.00046997341871288424,
      "loss": 6.036,
      "mean_token_accuracy": 0.1342359036207199,
      "num_tokens": 2680380.0,
      "step": 1500
    },
    {
      "entropy": 6.436664009094239,
      "epoch": 0.07741172234652675,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0004693827688683879,
      "loss": 6.1687,
      "mean_token_accuracy": 0.12308031022548675,
      "num_tokens": 2689976.0,
      "step": 1505
    },
    {
      "entropy": 6.508772373199463,
      "epoch": 0.07766890414834246,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0004687867899220914,
      "loss": 6.1793,
      "mean_token_accuracy": 0.12510153502225876,
      "num_tokens": 2698780.0,
      "step": 1510
    },
    {
      "entropy": 6.226078796386719,
      "epoch": 0.07792608595015817,
      "grad_norm": 1.078125,
      "learning_rate": 0.00046818549821305846,
      "loss": 6.03,
      "mean_token_accuracy": 0.13029744401574134,
      "num_tokens": 2706887.0,
      "step": 1515
    },
    {
      "entropy": 6.41196641921997,
      "epoch": 0.07818326775197387,
      "grad_norm": 1.125,
      "learning_rate": 0.00046757891022600494,
      "loss": 6.0603,
      "mean_token_accuracy": 0.1270065888762474,
      "num_tokens": 2715484.0,
      "step": 1520
    },
    {
      "entropy": 6.334155130386352,
      "epoch": 0.07844044955378958,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0004669670425908471,
      "loss": 6.1788,
      "mean_token_accuracy": 0.12362223640084266,
      "num_tokens": 2724272.0,
      "step": 1525
    },
    {
      "entropy": 6.397065687179565,
      "epoch": 0.07869763135560527,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0004663499120822451,
      "loss": 6.0992,
      "mean_token_accuracy": 0.13246706426143645,
      "num_tokens": 2733379.0,
      "step": 1530
    },
    {
      "entropy": 6.365872526168824,
      "epoch": 0.07895481315742098,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0004657275356191437,
      "loss": 6.0708,
      "mean_token_accuracy": 0.13027092143893243,
      "num_tokens": 2742584.0,
      "step": 1535
    },
    {
      "entropy": 6.467748212814331,
      "epoch": 0.07921199495923668,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00046509993026430804,
      "loss": 6.2481,
      "mean_token_accuracy": 0.12418549954891205,
      "num_tokens": 2751491.0,
      "step": 1540
    },
    {
      "entropy": 6.414959955215454,
      "epoch": 0.07946917676105239,
      "grad_norm": 1.09375,
      "learning_rate": 0.0004644671132238558,
      "loss": 6.0621,
      "mean_token_accuracy": 0.1291202872991562,
      "num_tokens": 2760320.0,
      "step": 1545
    },
    {
      "entropy": 6.405585384368896,
      "epoch": 0.0797263585628681,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00046382910184678585,
      "loss": 6.2345,
      "mean_token_accuracy": 0.11954343914985657,
      "num_tokens": 2770247.0,
      "step": 1550
    },
    {
      "entropy": 6.431417655944824,
      "epoch": 0.07998354036468379,
      "grad_norm": 1.109375,
      "learning_rate": 0.0004631859136245025,
      "loss": 6.0881,
      "mean_token_accuracy": 0.13392823338508605,
      "num_tokens": 2779969.0,
      "step": 1555
    },
    {
      "entropy": 6.324232196807861,
      "epoch": 0.0802407221664995,
      "grad_norm": 1.125,
      "learning_rate": 0.0004625375661903357,
      "loss": 6.1817,
      "mean_token_accuracy": 0.13248204365372657,
      "num_tokens": 2788584.0,
      "step": 1560
    },
    {
      "entropy": 6.307961273193359,
      "epoch": 0.0804979039683152,
      "grad_norm": 1.140625,
      "learning_rate": 0.00046188407731905787,
      "loss": 6.0618,
      "mean_token_accuracy": 0.13163200318813323,
      "num_tokens": 2796982.0,
      "step": 1565
    },
    {
      "entropy": 6.487869310379028,
      "epoch": 0.08075508577013091,
      "grad_norm": 1.078125,
      "learning_rate": 0.00046122546492639643,
      "loss": 6.2135,
      "mean_token_accuracy": 0.12365017086267471,
      "num_tokens": 2806788.0,
      "step": 1570
    },
    {
      "entropy": 6.321759557723999,
      "epoch": 0.08101226757194661,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000460561747068543,
      "loss": 6.0832,
      "mean_token_accuracy": 0.12752610817551613,
      "num_tokens": 2816086.0,
      "step": 1575
    },
    {
      "entropy": 6.285551452636719,
      "epoch": 0.0812694493737623,
      "grad_norm": 1.125,
      "learning_rate": 0.0004598929419416578,
      "loss": 6.084,
      "mean_token_accuracy": 0.12898513302206993,
      "num_tokens": 2825623.0,
      "step": 1580
    },
    {
      "entropy": 6.406826734542847,
      "epoch": 0.08152663117557801,
      "grad_norm": 1.015625,
      "learning_rate": 0.00045921906788137123,
      "loss": 6.229,
      "mean_token_accuracy": 0.1251101866364479,
      "num_tokens": 2835241.0,
      "step": 1585
    },
    {
      "entropy": 6.380240058898925,
      "epoch": 0.08178381297739372,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00045854014336228115,
      "loss": 6.0826,
      "mean_token_accuracy": 0.1333278901875019,
      "num_tokens": 2843428.0,
      "step": 1590
    },
    {
      "entropy": 6.348821783065796,
      "epoch": 0.08204099477920943,
      "grad_norm": 1.03125,
      "learning_rate": 0.00045785618699744615,
      "loss": 6.0808,
      "mean_token_accuracy": 0.1321525380015373,
      "num_tokens": 2852662.0,
      "step": 1595
    },
    {
      "entropy": 6.395787191390991,
      "epoch": 0.08229817658102513,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00045716721753787543,
      "loss": 6.0908,
      "mean_token_accuracy": 0.13208872005343436,
      "num_tokens": 2861094.0,
      "step": 1600
    },
    {
      "entropy": 6.31074743270874,
      "epoch": 0.08255535838284082,
      "grad_norm": 1.09375,
      "learning_rate": 0.0004564732538720148,
      "loss": 5.9817,
      "mean_token_accuracy": 0.1272851899266243,
      "num_tokens": 2870214.0,
      "step": 1605
    },
    {
      "entropy": 6.283258056640625,
      "epoch": 0.08281254018465653,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00045577431502522877,
      "loss": 6.1137,
      "mean_token_accuracy": 0.1351046971976757,
      "num_tokens": 2878876.0,
      "step": 1610
    },
    {
      "entropy": 6.478934669494629,
      "epoch": 0.08306972198647224,
      "grad_norm": 1.046875,
      "learning_rate": 0.0004550704201592787,
      "loss": 6.1111,
      "mean_token_accuracy": 0.12919269502162933,
      "num_tokens": 2888111.0,
      "step": 1615
    },
    {
      "entropy": 6.340307664871216,
      "epoch": 0.08332690378828794,
      "grad_norm": 1.09375,
      "learning_rate": 0.0004543615885717981,
      "loss": 6.1395,
      "mean_token_accuracy": 0.13248469904065133,
      "num_tokens": 2897589.0,
      "step": 1620
    },
    {
      "entropy": 6.388657903671264,
      "epoch": 0.08358408559010365,
      "grad_norm": 1.09375,
      "learning_rate": 0.00045364783969576296,
      "loss": 6.0822,
      "mean_token_accuracy": 0.1332689106464386,
      "num_tokens": 2906803.0,
      "step": 1625
    },
    {
      "entropy": 6.2963072776794435,
      "epoch": 0.08384126739191934,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0004529291930989592,
      "loss": 5.9716,
      "mean_token_accuracy": 0.13755856528878213,
      "num_tokens": 2916903.0,
      "step": 1630
    },
    {
      "entropy": 6.342654514312744,
      "epoch": 0.08409844919373505,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0004522056684834464,
      "loss": 6.0949,
      "mean_token_accuracy": 0.13052690103650094,
      "num_tokens": 2925952.0,
      "step": 1635
    },
    {
      "entropy": 6.325797176361084,
      "epoch": 0.08435563099555075,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0004514772856850173,
      "loss": 6.0416,
      "mean_token_accuracy": 0.12649609819054602,
      "num_tokens": 2934538.0,
      "step": 1640
    },
    {
      "entropy": 6.3612961769104,
      "epoch": 0.08461281279736646,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0004507440646726542,
      "loss": 6.1471,
      "mean_token_accuracy": 0.132496327906847,
      "num_tokens": 2943553.0,
      "step": 1645
    },
    {
      "entropy": 6.292884588241577,
      "epoch": 0.08486999459918217,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0004500060255479818,
      "loss": 6.031,
      "mean_token_accuracy": 0.1341935083270073,
      "num_tokens": 2951854.0,
      "step": 1650
    },
    {
      "entropy": 6.448796558380127,
      "epoch": 0.08512717640099786,
      "grad_norm": 1.125,
      "learning_rate": 0.0004492631885447151,
      "loss": 6.1977,
      "mean_token_accuracy": 0.12419203296303749,
      "num_tokens": 2961684.0,
      "step": 1655
    },
    {
      "entropy": 6.379677057266235,
      "epoch": 0.08538435820281357,
      "grad_norm": 1.046875,
      "learning_rate": 0.00044851557402810616,
      "loss": 6.0526,
      "mean_token_accuracy": 0.12697965502738953,
      "num_tokens": 2970984.0,
      "step": 1660
    },
    {
      "entropy": 6.304157495498657,
      "epoch": 0.08564154000462927,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00044776320249438444,
      "loss": 6.0435,
      "mean_token_accuracy": 0.12820193246006967,
      "num_tokens": 2979319.0,
      "step": 1665
    },
    {
      "entropy": 6.231897449493408,
      "epoch": 0.08589872180644498,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00044700609457019565,
      "loss": 5.9506,
      "mean_token_accuracy": 0.1356399580836296,
      "num_tokens": 2987780.0,
      "step": 1670
    },
    {
      "entropy": 6.239076566696167,
      "epoch": 0.08615590360826068,
      "grad_norm": 0.96875,
      "learning_rate": 0.0004462442710120359,
      "loss": 6.0657,
      "mean_token_accuracy": 0.12994374260306357,
      "num_tokens": 2996890.0,
      "step": 1675
    },
    {
      "entropy": 6.530197525024414,
      "epoch": 0.08641308541007638,
      "grad_norm": 1.09375,
      "learning_rate": 0.000445477752705683,
      "loss": 6.1939,
      "mean_token_accuracy": 0.12460953146219253,
      "num_tokens": 3005736.0,
      "step": 1680
    },
    {
      "entropy": 6.189916801452637,
      "epoch": 0.08667026721189208,
      "grad_norm": 1.125,
      "learning_rate": 0.00044470656066562336,
      "loss": 5.9827,
      "mean_token_accuracy": 0.13694657981395722,
      "num_tokens": 3014167.0,
      "step": 1685
    },
    {
      "entropy": 6.1757958889007565,
      "epoch": 0.08692744901370779,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0004439307160344765,
      "loss": 5.9809,
      "mean_token_accuracy": 0.140267164260149,
      "num_tokens": 3023018.0,
      "step": 1690
    },
    {
      "entropy": 6.499619054794311,
      "epoch": 0.0871846308155235,
      "grad_norm": 0.97265625,
      "learning_rate": 0.00044315024008241473,
      "loss": 6.1587,
      "mean_token_accuracy": 0.12271130084991455,
      "num_tokens": 3032659.0,
      "step": 1695
    },
    {
      "entropy": 6.313583087921143,
      "epoch": 0.0874418126173392,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0004423651542065806,
      "loss": 5.9887,
      "mean_token_accuracy": 0.13750137612223626,
      "num_tokens": 3040882.0,
      "step": 1700
    },
    {
      "entropy": 6.182634162902832,
      "epoch": 0.0876989944191549,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00044157547993050006,
      "loss": 5.9244,
      "mean_token_accuracy": 0.13822244331240655,
      "num_tokens": 3050242.0,
      "step": 1705
    },
    {
      "entropy": 6.321706867218017,
      "epoch": 0.0879561762209706,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00044078123890349227,
      "loss": 6.0384,
      "mean_token_accuracy": 0.12941291332244872,
      "num_tokens": 3059928.0,
      "step": 1710
    },
    {
      "entropy": 6.401517152786255,
      "epoch": 0.0882133580227863,
      "grad_norm": 0.98046875,
      "learning_rate": 0.00043998245290007606,
      "loss": 6.2233,
      "mean_token_accuracy": 0.12163035720586776,
      "num_tokens": 3069787.0,
      "step": 1715
    },
    {
      "entropy": 6.403897905349732,
      "epoch": 0.08847053982460201,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00043917914381937323,
      "loss": 6.1021,
      "mean_token_accuracy": 0.12949455678462982,
      "num_tokens": 3079171.0,
      "step": 1720
    },
    {
      "entropy": 6.267082691192627,
      "epoch": 0.08872772162641772,
      "grad_norm": 1.078125,
      "learning_rate": 0.00043837133368450815,
      "loss": 6.0348,
      "mean_token_accuracy": 0.13504951894283296,
      "num_tokens": 3088371.0,
      "step": 1725
    },
    {
      "entropy": 6.264813995361328,
      "epoch": 0.08898490342823343,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0004375590446420037,
      "loss": 6.0367,
      "mean_token_accuracy": 0.13473087251186372,
      "num_tokens": 3098489.0,
      "step": 1730
    },
    {
      "entropy": 6.363276672363281,
      "epoch": 0.08924208523004912,
      "grad_norm": 1.171875,
      "learning_rate": 0.0004367422989611743,
      "loss": 6.1169,
      "mean_token_accuracy": 0.12966250479221345,
      "num_tokens": 3107161.0,
      "step": 1735
    },
    {
      "entropy": 6.385274219512939,
      "epoch": 0.08949926703186482,
      "grad_norm": 1.0625,
      "learning_rate": 0.0004359211190335153,
      "loss": 6.0351,
      "mean_token_accuracy": 0.13608441054821013,
      "num_tokens": 3115435.0,
      "step": 1740
    },
    {
      "entropy": 6.3607177734375,
      "epoch": 0.08975644883368053,
      "grad_norm": 1.046875,
      "learning_rate": 0.00043509552737208923,
      "loss": 6.1034,
      "mean_token_accuracy": 0.13773850798606874,
      "num_tokens": 3124543.0,
      "step": 1745
    },
    {
      "entropy": 6.311847782135009,
      "epoch": 0.09001363063549624,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00043426554661090853,
      "loss": 5.9807,
      "mean_token_accuracy": 0.12751075103878975,
      "num_tokens": 3133856.0,
      "step": 1750
    },
    {
      "entropy": 6.20699553489685,
      "epoch": 0.09027081243731194,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00043343119950431516,
      "loss": 6.0226,
      "mean_token_accuracy": 0.13111255168914795,
      "num_tokens": 3143643.0,
      "step": 1755
    },
    {
      "entropy": 6.388123416900635,
      "epoch": 0.09052799423912763,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00043259250892635644,
      "loss": 6.0525,
      "mean_token_accuracy": 0.13792511597275733,
      "num_tokens": 3152084.0,
      "step": 1760
    },
    {
      "entropy": 6.389042806625366,
      "epoch": 0.09078517604094334,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0004317494978701582,
      "loss": 6.0266,
      "mean_token_accuracy": 0.13580404818058014,
      "num_tokens": 3160091.0,
      "step": 1765
    },
    {
      "entropy": 6.2101809024810795,
      "epoch": 0.09104235784275905,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0004309021894472943,
      "loss": 6.014,
      "mean_token_accuracy": 0.12847821563482284,
      "num_tokens": 3169569.0,
      "step": 1770
    },
    {
      "entropy": 6.378039360046387,
      "epoch": 0.09129953964457475,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0004300506068871534,
      "loss": 6.1253,
      "mean_token_accuracy": 0.12418064251542091,
      "num_tokens": 3179974.0,
      "step": 1775
    },
    {
      "entropy": 6.311042928695679,
      "epoch": 0.09155672144639046,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00042919477353630135,
      "loss": 6.0914,
      "mean_token_accuracy": 0.13122028410434722,
      "num_tokens": 3189489.0,
      "step": 1780
    },
    {
      "entropy": 6.401360130310058,
      "epoch": 0.09181390324820615,
      "grad_norm": 1.0703125,
      "learning_rate": 0.000428334712857842,
      "loss": 6.1483,
      "mean_token_accuracy": 0.1267679288983345,
      "num_tokens": 3198335.0,
      "step": 1785
    },
    {
      "entropy": 6.154367589950562,
      "epoch": 0.09207108505002186,
      "grad_norm": 1.109375,
      "learning_rate": 0.00042747044843077304,
      "loss": 5.8831,
      "mean_token_accuracy": 0.1401224859058857,
      "num_tokens": 3206400.0,
      "step": 1790
    },
    {
      "entropy": 6.391241455078125,
      "epoch": 0.09232826685183756,
      "grad_norm": 1.21875,
      "learning_rate": 0.00042660200394934047,
      "loss": 5.9885,
      "mean_token_accuracy": 0.1355439156293869,
      "num_tokens": 3214480.0,
      "step": 1795
    },
    {
      "entropy": 6.293077850341797,
      "epoch": 0.09258544865365327,
      "grad_norm": 1.09375,
      "learning_rate": 0.00042572940322238844,
      "loss": 6.0104,
      "mean_token_accuracy": 0.13572105020284653,
      "num_tokens": 3222386.0,
      "step": 1800
    },
    {
      "entropy": 6.25052399635315,
      "epoch": 0.09284263045546898,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00042485267017270664,
      "loss": 5.9602,
      "mean_token_accuracy": 0.13466379642486573,
      "num_tokens": 3231203.0,
      "step": 1805
    },
    {
      "entropy": 6.233933353424073,
      "epoch": 0.09309981225728467,
      "grad_norm": 1.0625,
      "learning_rate": 0.0004239718288363745,
      "loss": 6.0089,
      "mean_token_accuracy": 0.1300691097974777,
      "num_tokens": 3240693.0,
      "step": 1810
    },
    {
      "entropy": 6.2747550964355465,
      "epoch": 0.09335699405910038,
      "grad_norm": 1.078125,
      "learning_rate": 0.0004230869033621023,
      "loss": 6.0764,
      "mean_token_accuracy": 0.13697424307465553,
      "num_tokens": 3249518.0,
      "step": 1815
    },
    {
      "entropy": 6.3998106002807615,
      "epoch": 0.09361417586091608,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0004221979180105688,
      "loss": 6.0622,
      "mean_token_accuracy": 0.1327414371073246,
      "num_tokens": 3258712.0,
      "step": 1820
    },
    {
      "entropy": 6.279940986633301,
      "epoch": 0.09387135766273179,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00042130489715375645,
      "loss": 5.9342,
      "mean_token_accuracy": 0.140862063318491,
      "num_tokens": 3266797.0,
      "step": 1825
    },
    {
      "entropy": 6.2281848907470705,
      "epoch": 0.0941285394645475,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00042040786527428335,
      "loss": 6.0584,
      "mean_token_accuracy": 0.13048559799790382,
      "num_tokens": 3275811.0,
      "step": 1830
    },
    {
      "entropy": 6.248003005981445,
      "epoch": 0.09438572126636319,
      "grad_norm": 1.109375,
      "learning_rate": 0.0004195068469647315,
      "loss": 5.9652,
      "mean_token_accuracy": 0.13584049865603448,
      "num_tokens": 3284813.0,
      "step": 1835
    },
    {
      "entropy": 6.284520101547241,
      "epoch": 0.0946429030681789,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00041860186692697297,
      "loss": 6.0291,
      "mean_token_accuracy": 0.1311030738055706,
      "num_tokens": 3293509.0,
      "step": 1840
    },
    {
      "entropy": 6.319161224365234,
      "epoch": 0.0949000848699946,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00041769294997149264,
      "loss": 5.9418,
      "mean_token_accuracy": 0.1394168458878994,
      "num_tokens": 3302010.0,
      "step": 1845
    },
    {
      "entropy": 6.28194146156311,
      "epoch": 0.0951572666718103,
      "grad_norm": 0.984375,
      "learning_rate": 0.0004167801210167081,
      "loss": 6.0737,
      "mean_token_accuracy": 0.13149803429841994,
      "num_tokens": 3312307.0,
      "step": 1850
    },
    {
      "entropy": 6.298348474502563,
      "epoch": 0.09541444847362601,
      "grad_norm": 1.03125,
      "learning_rate": 0.0004158634050882861,
      "loss": 6.0619,
      "mean_token_accuracy": 0.12632458582520484,
      "num_tokens": 3321859.0,
      "step": 1855
    },
    {
      "entropy": 6.352298450469971,
      "epoch": 0.0956716302754417,
      "grad_norm": 0.99609375,
      "learning_rate": 0.0004149428273184569,
      "loss": 6.0642,
      "mean_token_accuracy": 0.13412729203701018,
      "num_tokens": 3331727.0,
      "step": 1860
    },
    {
      "entropy": 6.263995742797851,
      "epoch": 0.09592881207725741,
      "grad_norm": 1.078125,
      "learning_rate": 0.0004140184129453253,
      "loss": 5.9321,
      "mean_token_accuracy": 0.13026233464479448,
      "num_tokens": 3340449.0,
      "step": 1865
    },
    {
      "entropy": 6.30117506980896,
      "epoch": 0.09618599387907312,
      "grad_norm": 1.0390625,
      "learning_rate": 0.000413090187312178,
      "loss": 5.9886,
      "mean_token_accuracy": 0.13512412831187248,
      "num_tokens": 3349374.0,
      "step": 1870
    },
    {
      "entropy": 6.266588401794434,
      "epoch": 0.09644317568088882,
      "grad_norm": 0.98828125,
      "learning_rate": 0.0004121581758667898,
      "loss": 6.0195,
      "mean_token_accuracy": 0.13124436065554618,
      "num_tokens": 3358792.0,
      "step": 1875
    },
    {
      "entropy": 6.184923267364502,
      "epoch": 0.09670035748270453,
      "grad_norm": 0.98828125,
      "learning_rate": 0.00041122240416072533,
      "loss": 5.9184,
      "mean_token_accuracy": 0.13883327171206475,
      "num_tokens": 3368066.0,
      "step": 1880
    },
    {
      "entropy": 6.24156346321106,
      "epoch": 0.09695753928452022,
      "grad_norm": 1.09375,
      "learning_rate": 0.0004102828978486385,
      "loss": 5.954,
      "mean_token_accuracy": 0.13969675824046135,
      "num_tokens": 3376872.0,
      "step": 1885
    },
    {
      "entropy": 6.241713762283325,
      "epoch": 0.09721472108633593,
      "grad_norm": 1.09375,
      "learning_rate": 0.0004093396826875695,
      "loss": 5.9471,
      "mean_token_accuracy": 0.13266203328967094,
      "num_tokens": 3385851.0,
      "step": 1890
    },
    {
      "entropy": 6.231948804855347,
      "epoch": 0.09747190288815163,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00040839278453623837,
      "loss": 6.0056,
      "mean_token_accuracy": 0.1346826121211052,
      "num_tokens": 3395263.0,
      "step": 1895
    },
    {
      "entropy": 6.228415203094483,
      "epoch": 0.09772908468996734,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0004074422293543363,
      "loss": 6.0445,
      "mean_token_accuracy": 0.13088179305195807,
      "num_tokens": 3404814.0,
      "step": 1900
    },
    {
      "entropy": 6.329216241836548,
      "epoch": 0.09798626649178305,
      "grad_norm": 1.046875,
      "learning_rate": 0.0004064880432018137,
      "loss": 6.1074,
      "mean_token_accuracy": 0.1315300315618515,
      "num_tokens": 3413822.0,
      "step": 1905
    },
    {
      "entropy": 6.301573801040649,
      "epoch": 0.09824344829359874,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00040553025223816615,
      "loss": 6.0124,
      "mean_token_accuracy": 0.13628942891955376,
      "num_tokens": 3422318.0,
      "step": 1910
    },
    {
      "entropy": 6.206828165054321,
      "epoch": 0.09850063009541445,
      "grad_norm": 1.0625,
      "learning_rate": 0.00040456888272171653,
      "loss": 5.9329,
      "mean_token_accuracy": 0.13764095306396484,
      "num_tokens": 3431066.0,
      "step": 1915
    },
    {
      "entropy": 6.251052141189575,
      "epoch": 0.09875781189723015,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00040360396100889577,
      "loss": 5.9485,
      "mean_token_accuracy": 0.1366151362657547,
      "num_tokens": 3439822.0,
      "step": 1920
    },
    {
      "entropy": 6.248995113372803,
      "epoch": 0.09901499369904586,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0004026355135535202,
      "loss": 6.0449,
      "mean_token_accuracy": 0.13020109459757806,
      "num_tokens": 3449430.0,
      "step": 1925
    },
    {
      "entropy": 6.266049480438232,
      "epoch": 0.09927217550086156,
      "grad_norm": 1.125,
      "learning_rate": 0.000401663566906066,
      "loss": 5.9646,
      "mean_token_accuracy": 0.13827199935913087,
      "num_tokens": 3457519.0,
      "step": 1930
    },
    {
      "entropy": 6.185720539093017,
      "epoch": 0.09952935730267726,
      "grad_norm": 1.09375,
      "learning_rate": 0.00040068814771294134,
      "loss": 5.8726,
      "mean_token_accuracy": 0.13870462104678155,
      "num_tokens": 3466328.0,
      "step": 1935
    },
    {
      "entropy": 6.133827590942383,
      "epoch": 0.09978653910449296,
      "grad_norm": 1.03125,
      "learning_rate": 0.0003997092827157562,
      "loss": 5.8982,
      "mean_token_accuracy": 0.1401980772614479,
      "num_tokens": 3475821.0,
      "step": 1940
    },
    {
      "entropy": 6.2277813911437985,
      "epoch": 0.10004372090630867,
      "grad_norm": 1.109375,
      "learning_rate": 0.000398726998750589,
      "loss": 5.9881,
      "mean_token_accuracy": 0.1336817152798176,
      "num_tokens": 3484902.0,
      "step": 1945
    },
    {
      "entropy": 6.296745872497558,
      "epoch": 0.10030090270812438,
      "grad_norm": 1.109375,
      "learning_rate": 0.00039774132274725076,
      "loss": 6.0906,
      "mean_token_accuracy": 0.12511072233319281,
      "num_tokens": 3494951.0,
      "step": 1950
    },
    {
      "entropy": 6.261813402175903,
      "epoch": 0.10055808450994008,
      "grad_norm": 1.03125,
      "learning_rate": 0.00039675228172854707,
      "loss": 5.9523,
      "mean_token_accuracy": 0.14045180454850198,
      "num_tokens": 3503688.0,
      "step": 1955
    },
    {
      "entropy": 6.224357604980469,
      "epoch": 0.10081526631175577,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0003957599028095371,
      "loss": 5.9971,
      "mean_token_accuracy": 0.13452794998884202,
      "num_tokens": 3512337.0,
      "step": 1960
    },
    {
      "entropy": 6.310317754745483,
      "epoch": 0.10107244811357148,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00039476421319679017,
      "loss": 6.0837,
      "mean_token_accuracy": 0.1328693710267544,
      "num_tokens": 3521370.0,
      "step": 1965
    },
    {
      "entropy": 6.193576526641846,
      "epoch": 0.10132962991538719,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00039376524018764,
      "loss": 5.8877,
      "mean_token_accuracy": 0.14604497849941253,
      "num_tokens": 3530225.0,
      "step": 1970
    },
    {
      "entropy": 6.205514764785766,
      "epoch": 0.1015868117172029,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00039276301116943616,
      "loss": 5.9687,
      "mean_token_accuracy": 0.14247402623295785,
      "num_tokens": 3538843.0,
      "step": 1975
    },
    {
      "entropy": 6.286650371551514,
      "epoch": 0.1018439935190186,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0003917575536187936,
      "loss": 5.9858,
      "mean_token_accuracy": 0.1346484936773777,
      "num_tokens": 3547833.0,
      "step": 1980
    },
    {
      "entropy": 6.177884578704834,
      "epoch": 0.10210117532083429,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00039074889510083894,
      "loss": 5.9072,
      "mean_token_accuracy": 0.1447339817881584,
      "num_tokens": 3556021.0,
      "step": 1985
    },
    {
      "entropy": 6.251054954528809,
      "epoch": 0.10235835712265,
      "grad_norm": 0.99609375,
      "learning_rate": 0.00038973706326845495,
      "loss": 5.8984,
      "mean_token_accuracy": 0.13767489194869995,
      "num_tokens": 3564483.0,
      "step": 1990
    },
    {
      "entropy": 6.208160734176635,
      "epoch": 0.1026155389244657,
      "grad_norm": 1.03125,
      "learning_rate": 0.0003887220858615225,
      "loss": 5.9995,
      "mean_token_accuracy": 0.12966525331139564,
      "num_tokens": 3574761.0,
      "step": 1995
    },
    {
      "entropy": 6.26411509513855,
      "epoch": 0.10287272072628141,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0003877039907061597,
      "loss": 6.0126,
      "mean_token_accuracy": 0.13828732147812844,
      "num_tokens": 3583401.0,
      "step": 2000
    }
  ],
  "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": 717815269785600.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}