{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.051436360363140705,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.7425612449646,
      "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
    }
  ],
  "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": 354171108556800.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}