{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.025718180181570353,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.7425612449646,
      "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
    }
  ],
  "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": 179847569571840.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}