{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01353637901861252,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.69199342727661,
      "epoch": 0.00013536379018612522,
      "grad_norm": 11.5625,
      "learning_rate": 2e-06,
      "loss": 10.8479,
      "mean_token_accuracy": 0.0,
      "num_tokens": 12791.0,
      "step": 5
    },
    {
      "entropy": 10.691878128051759,
      "epoch": 0.00027072758037225043,
      "grad_norm": 11.0,
      "learning_rate": 4.5e-06,
      "loss": 10.8142,
      "mean_token_accuracy": 0.0,
      "num_tokens": 26683.0,
      "step": 10
    },
    {
      "entropy": 10.691429710388183,
      "epoch": 0.0004060913705583756,
      "grad_norm": 9.3125,
      "learning_rate": 7e-06,
      "loss": 10.5672,
      "mean_token_accuracy": 0.011101403925567865,
      "num_tokens": 39347.0,
      "step": 15
    },
    {
      "entropy": 10.686277675628663,
      "epoch": 0.0005414551607445009,
      "grad_norm": 5.375,
      "learning_rate": 9.5e-06,
      "loss": 10.3174,
      "mean_token_accuracy": 0.030114291980862618,
      "num_tokens": 54329.0,
      "step": 20
    },
    {
      "entropy": 10.660668087005615,
      "epoch": 0.0006768189509306261,
      "grad_norm": 4.09375,
      "learning_rate": 1.2e-05,
      "loss": 10.0145,
      "mean_token_accuracy": 0.032822173461318015,
      "num_tokens": 67393.0,
      "step": 25
    },
    {
      "entropy": 10.637198734283448,
      "epoch": 0.0008121827411167512,
      "grad_norm": 3.0625,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 9.8798,
      "mean_token_accuracy": 0.03450996596366167,
      "num_tokens": 81383.0,
      "step": 30
    },
    {
      "entropy": 10.631521320343017,
      "epoch": 0.0009475465313028764,
      "grad_norm": 2.515625,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.8183,
      "mean_token_accuracy": 0.03217146322131157,
      "num_tokens": 95991.0,
      "step": 35
    },
    {
      "entropy": 10.626516151428223,
      "epoch": 0.0010829103214890017,
      "grad_norm": 2.515625,
      "learning_rate": 1.95e-05,
      "loss": 9.7088,
      "mean_token_accuracy": 0.03352573178708553,
      "num_tokens": 108504.0,
      "step": 40
    },
    {
      "entropy": 10.627447319030761,
      "epoch": 0.001218274111675127,
      "grad_norm": 2.1875,
      "learning_rate": 2.2e-05,
      "loss": 9.7785,
      "mean_token_accuracy": 0.030551478266716003,
      "num_tokens": 123286.0,
      "step": 45
    },
    {
      "entropy": 10.629091835021972,
      "epoch": 0.0013536379018612521,
      "grad_norm": 2.296875,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.6538,
      "mean_token_accuracy": 0.03104141727089882,
      "num_tokens": 135493.0,
      "step": 50
    },
    {
      "entropy": 10.618868160247803,
      "epoch": 0.0014890016920473773,
      "grad_norm": 2.078125,
      "learning_rate": 2.7e-05,
      "loss": 9.6537,
      "mean_token_accuracy": 0.03736583907157183,
      "num_tokens": 150376.0,
      "step": 55
    },
    {
      "entropy": 10.596181201934815,
      "epoch": 0.0016243654822335025,
      "grad_norm": 2.109375,
      "learning_rate": 2.95e-05,
      "loss": 9.5976,
      "mean_token_accuracy": 0.03170219026505947,
      "num_tokens": 165805.0,
      "step": 60
    },
    {
      "entropy": 10.606531143188477,
      "epoch": 0.0017597292724196277,
      "grad_norm": 2.09375,
      "learning_rate": 3.2e-05,
      "loss": 9.4608,
      "mean_token_accuracy": 0.03743585981428623,
      "num_tokens": 179043.0,
      "step": 65
    },
    {
      "entropy": 10.577856731414794,
      "epoch": 0.0018950930626057529,
      "grad_norm": 2.09375,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.3947,
      "mean_token_accuracy": 0.03445138856768608,
      "num_tokens": 191847.0,
      "step": 70
    },
    {
      "entropy": 10.561034107208252,
      "epoch": 0.0020304568527918783,
      "grad_norm": 2.125,
      "learning_rate": 3.7e-05,
      "loss": 9.2778,
      "mean_token_accuracy": 0.03577356971800327,
      "num_tokens": 207116.0,
      "step": 75
    },
    {
      "entropy": 10.546807861328125,
      "epoch": 0.0021658206429780035,
      "grad_norm": 2.03125,
      "learning_rate": 3.95e-05,
      "loss": 9.2156,
      "mean_token_accuracy": 0.03288109693676233,
      "num_tokens": 219651.0,
      "step": 80
    },
    {
      "entropy": 10.532037448883056,
      "epoch": 0.0023011844331641287,
      "grad_norm": 2.015625,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.16,
      "mean_token_accuracy": 0.03139570262283087,
      "num_tokens": 233183.0,
      "step": 85
    },
    {
      "entropy": 10.499158573150634,
      "epoch": 0.002436548223350254,
      "grad_norm": 2.0625,
      "learning_rate": 4.45e-05,
      "loss": 8.9864,
      "mean_token_accuracy": 0.0376906756311655,
      "num_tokens": 246291.0,
      "step": 90
    },
    {
      "entropy": 10.423231887817384,
      "epoch": 0.002571912013536379,
      "grad_norm": 2.15625,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 8.8533,
      "mean_token_accuracy": 0.04000245779752731,
      "num_tokens": 259606.0,
      "step": 95
    },
    {
      "entropy": 10.371912956237793,
      "epoch": 0.0027072758037225042,
      "grad_norm": 2.0,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 8.7521,
      "mean_token_accuracy": 0.04012820441275835,
      "num_tokens": 275174.0,
      "step": 100
    },
    {
      "entropy": 10.304845333099365,
      "epoch": 0.0028426395939086294,
      "grad_norm": 2.25,
      "learning_rate": 5.2e-05,
      "loss": 8.5952,
      "mean_token_accuracy": 0.04803745746612549,
      "num_tokens": 287873.0,
      "step": 105
    },
    {
      "entropy": 10.202454662322998,
      "epoch": 0.0029780033840947546,
      "grad_norm": 1.9453125,
      "learning_rate": 5.45e-05,
      "loss": 8.4264,
      "mean_token_accuracy": 0.052891625463962554,
      "num_tokens": 301243.0,
      "step": 110
    },
    {
      "entropy": 10.146648788452149,
      "epoch": 0.00311336717428088,
      "grad_norm": 2.140625,
      "learning_rate": 5.7e-05,
      "loss": 8.3599,
      "mean_token_accuracy": 0.04921769984066486,
      "num_tokens": 314246.0,
      "step": 115
    },
    {
      "entropy": 9.991413021087647,
      "epoch": 0.003248730964467005,
      "grad_norm": 1.671875,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.1824,
      "mean_token_accuracy": 0.05792190656065941,
      "num_tokens": 327131.0,
      "step": 120
    },
    {
      "entropy": 9.899451637268067,
      "epoch": 0.00338409475465313,
      "grad_norm": 1.7734375,
      "learning_rate": 6.2e-05,
      "loss": 8.0577,
      "mean_token_accuracy": 0.054864197969436646,
      "num_tokens": 340932.0,
      "step": 125
    },
    {
      "entropy": 9.722916507720948,
      "epoch": 0.0035194585448392554,
      "grad_norm": 1.671875,
      "learning_rate": 6.450000000000001e-05,
      "loss": 7.9419,
      "mean_token_accuracy": 0.05465308241546154,
      "num_tokens": 355280.0,
      "step": 130
    },
    {
      "entropy": 9.517075347900391,
      "epoch": 0.0036548223350253805,
      "grad_norm": 1.546875,
      "learning_rate": 6.7e-05,
      "loss": 7.863,
      "mean_token_accuracy": 0.06392355933785439,
      "num_tokens": 370159.0,
      "step": 135
    },
    {
      "entropy": 9.312166881561279,
      "epoch": 0.0037901861252115057,
      "grad_norm": 1.4609375,
      "learning_rate": 6.950000000000001e-05,
      "loss": 7.7284,
      "mean_token_accuracy": 0.060528535023331644,
      "num_tokens": 385660.0,
      "step": 140
    },
    {
      "entropy": 9.113211154937744,
      "epoch": 0.003925549915397631,
      "grad_norm": 1.3359375,
      "learning_rate": 7.2e-05,
      "loss": 7.6437,
      "mean_token_accuracy": 0.05836181789636612,
      "num_tokens": 401147.0,
      "step": 145
    },
    {
      "entropy": 8.787345790863037,
      "epoch": 0.0040609137055837565,
      "grad_norm": 1.5625,
      "learning_rate": 7.45e-05,
      "loss": 7.4136,
      "mean_token_accuracy": 0.07278152294456959,
      "num_tokens": 413888.0,
      "step": 150
    },
    {
      "entropy": 8.64449052810669,
      "epoch": 0.004196277495769882,
      "grad_norm": 1.40625,
      "learning_rate": 7.7e-05,
      "loss": 7.3884,
      "mean_token_accuracy": 0.06653538607060909,
      "num_tokens": 427538.0,
      "step": 155
    },
    {
      "entropy": 8.441664218902588,
      "epoch": 0.004331641285956007,
      "grad_norm": 2.125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.3251,
      "mean_token_accuracy": 0.069814383238554,
      "num_tokens": 441236.0,
      "step": 160
    },
    {
      "entropy": 8.356950950622558,
      "epoch": 0.004467005076142132,
      "grad_norm": 1.3984375,
      "learning_rate": 8.2e-05,
      "loss": 7.4254,
      "mean_token_accuracy": 0.0740208551287651,
      "num_tokens": 454231.0,
      "step": 165
    },
    {
      "entropy": 8.19385576248169,
      "epoch": 0.004602368866328257,
      "grad_norm": 1.5234375,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.2457,
      "mean_token_accuracy": 0.07566015087068081,
      "num_tokens": 468791.0,
      "step": 170
    },
    {
      "entropy": 8.173048114776611,
      "epoch": 0.0047377326565143825,
      "grad_norm": 1.6328125,
      "learning_rate": 8.7e-05,
      "loss": 7.3934,
      "mean_token_accuracy": 0.06828283667564392,
      "num_tokens": 481866.0,
      "step": 175
    },
    {
      "entropy": 8.059328603744508,
      "epoch": 0.004873096446700508,
      "grad_norm": 1.4296875,
      "learning_rate": 8.95e-05,
      "loss": 7.2376,
      "mean_token_accuracy": 0.07703411132097245,
      "num_tokens": 495060.0,
      "step": 180
    },
    {
      "entropy": 8.006558561325074,
      "epoch": 0.005008460236886633,
      "grad_norm": 1.2890625,
      "learning_rate": 9.2e-05,
      "loss": 7.1953,
      "mean_token_accuracy": 0.07884187921881676,
      "num_tokens": 508485.0,
      "step": 185
    },
    {
      "entropy": 7.988453817367554,
      "epoch": 0.005143824027072758,
      "grad_norm": 1.3984375,
      "learning_rate": 9.45e-05,
      "loss": 7.2074,
      "mean_token_accuracy": 0.07364003024995328,
      "num_tokens": 522642.0,
      "step": 190
    },
    {
      "entropy": 7.911316013336181,
      "epoch": 0.005279187817258883,
      "grad_norm": 1.234375,
      "learning_rate": 9.7e-05,
      "loss": 7.1742,
      "mean_token_accuracy": 0.07427211254835128,
      "num_tokens": 536967.0,
      "step": 195
    },
    {
      "entropy": 7.899316692352295,
      "epoch": 0.0054145516074450084,
      "grad_norm": 1.4296875,
      "learning_rate": 9.95e-05,
      "loss": 7.1728,
      "mean_token_accuracy": 0.0805082306265831,
      "num_tokens": 548389.0,
      "step": 200
    },
    {
      "entropy": 7.799197435379028,
      "epoch": 0.005549915397631134,
      "grad_norm": 1.296875,
      "learning_rate": 0.000102,
      "loss": 7.1509,
      "mean_token_accuracy": 0.07738717347383499,
      "num_tokens": 560609.0,
      "step": 205
    },
    {
      "entropy": 7.819343090057373,
      "epoch": 0.005685279187817259,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.1254,
      "mean_token_accuracy": 0.07640378400683404,
      "num_tokens": 574689.0,
      "step": 210
    },
    {
      "entropy": 7.777826452255249,
      "epoch": 0.005820642978003384,
      "grad_norm": 1.3515625,
      "learning_rate": 0.000107,
      "loss": 7.0691,
      "mean_token_accuracy": 0.07349300533533096,
      "num_tokens": 588789.0,
      "step": 215
    },
    {
      "entropy": 7.698786115646362,
      "epoch": 0.005956006768189509,
      "grad_norm": 1.3125,
      "learning_rate": 0.0001095,
      "loss": 7.1439,
      "mean_token_accuracy": 0.07730361446738243,
      "num_tokens": 603609.0,
      "step": 220
    },
    {
      "entropy": 7.7466569423675535,
      "epoch": 0.006091370558375634,
      "grad_norm": 1.4453125,
      "learning_rate": 0.000112,
      "loss": 7.0113,
      "mean_token_accuracy": 0.07942908927798271,
      "num_tokens": 616403.0,
      "step": 225
    },
    {
      "entropy": 7.682626628875733,
      "epoch": 0.00622673434856176,
      "grad_norm": 1.09375,
      "learning_rate": 0.0001145,
      "loss": 7.1202,
      "mean_token_accuracy": 0.08443130478262902,
      "num_tokens": 630831.0,
      "step": 230
    },
    {
      "entropy": 7.731028842926025,
      "epoch": 0.006362098138747885,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.0225,
      "mean_token_accuracy": 0.08779790177941323,
      "num_tokens": 646501.0,
      "step": 235
    },
    {
      "entropy": 7.661398029327392,
      "epoch": 0.00649746192893401,
      "grad_norm": 1.8671875,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.0941,
      "mean_token_accuracy": 0.08079206757247448,
      "num_tokens": 661193.0,
      "step": 240
    },
    {
      "entropy": 7.572637605667114,
      "epoch": 0.006632825719120135,
      "grad_norm": 1.734375,
      "learning_rate": 0.000122,
      "loss": 7.0787,
      "mean_token_accuracy": 0.08005881682038307,
      "num_tokens": 675523.0,
      "step": 245
    },
    {
      "entropy": 7.636332321166992,
      "epoch": 0.00676818950930626,
      "grad_norm": 1.5859375,
      "learning_rate": 0.0001245,
      "loss": 7.0674,
      "mean_token_accuracy": 0.07794632315635681,
      "num_tokens": 691106.0,
      "step": 250
    },
    {
      "entropy": 7.519766235351563,
      "epoch": 0.0069035532994923855,
      "grad_norm": 1.3671875,
      "learning_rate": 0.000127,
      "loss": 6.9381,
      "mean_token_accuracy": 0.08541512936353683,
      "num_tokens": 704312.0,
      "step": 255
    },
    {
      "entropy": 7.561954641342163,
      "epoch": 0.007038917089678511,
      "grad_norm": 1.4375,
      "learning_rate": 0.0001295,
      "loss": 6.9601,
      "mean_token_accuracy": 0.0883929617702961,
      "num_tokens": 717026.0,
      "step": 260
    },
    {
      "entropy": 7.570081567764282,
      "epoch": 0.007174280879864636,
      "grad_norm": 1.328125,
      "learning_rate": 0.000132,
      "loss": 6.9123,
      "mean_token_accuracy": 0.08829773366451263,
      "num_tokens": 729605.0,
      "step": 265
    },
    {
      "entropy": 7.463983678817749,
      "epoch": 0.007309644670050761,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00013450000000000002,
      "loss": 6.9353,
      "mean_token_accuracy": 0.09122553616762161,
      "num_tokens": 743208.0,
      "step": 270
    },
    {
      "entropy": 7.550097227096558,
      "epoch": 0.007445008460236886,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00013700000000000002,
      "loss": 6.9287,
      "mean_token_accuracy": 0.08519787713885307,
      "num_tokens": 755127.0,
      "step": 275
    },
    {
      "entropy": 7.398041200637818,
      "epoch": 0.0075803722504230115,
      "grad_norm": 1.53125,
      "learning_rate": 0.0001395,
      "loss": 6.8231,
      "mean_token_accuracy": 0.08911917060613632,
      "num_tokens": 769725.0,
      "step": 280
    },
    {
      "entropy": 7.364175844192505,
      "epoch": 0.007715736040609137,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00014199999999999998,
      "loss": 6.7527,
      "mean_token_accuracy": 0.09069294035434723,
      "num_tokens": 783788.0,
      "step": 285
    },
    {
      "entropy": 7.450532627105713,
      "epoch": 0.007851099830795263,
      "grad_norm": 1.171875,
      "learning_rate": 0.0001445,
      "loss": 6.934,
      "mean_token_accuracy": 0.08614907264709473,
      "num_tokens": 797214.0,
      "step": 290
    },
    {
      "entropy": 7.43695821762085,
      "epoch": 0.007986463620981387,
      "grad_norm": 1.6328125,
      "learning_rate": 0.000147,
      "loss": 6.897,
      "mean_token_accuracy": 0.09108028039336205,
      "num_tokens": 809731.0,
      "step": 295
    },
    {
      "entropy": 7.286933469772339,
      "epoch": 0.008121827411167513,
      "grad_norm": 1.4296875,
      "learning_rate": 0.0001495,
      "loss": 6.8591,
      "mean_token_accuracy": 0.09137310981750488,
      "num_tokens": 825021.0,
      "step": 300
    },
    {
      "entropy": 7.2696253776550295,
      "epoch": 0.008257191201353637,
      "grad_norm": 1.40625,
      "learning_rate": 0.000152,
      "loss": 6.9029,
      "mean_token_accuracy": 0.09101672545075416,
      "num_tokens": 839153.0,
      "step": 305
    },
    {
      "entropy": 7.386481237411499,
      "epoch": 0.008392554991539763,
      "grad_norm": 1.3984375,
      "learning_rate": 0.00015450000000000001,
      "loss": 6.8276,
      "mean_token_accuracy": 0.08859616219997406,
      "num_tokens": 853120.0,
      "step": 310
    },
    {
      "entropy": 7.337709522247314,
      "epoch": 0.008527918781725888,
      "grad_norm": 1.21875,
      "learning_rate": 0.000157,
      "loss": 6.8448,
      "mean_token_accuracy": 0.08571028485894203,
      "num_tokens": 867268.0,
      "step": 315
    },
    {
      "entropy": 7.340923023223877,
      "epoch": 0.008663282571912014,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001595,
      "loss": 6.8255,
      "mean_token_accuracy": 0.09267906844615936,
      "num_tokens": 879062.0,
      "step": 320
    },
    {
      "entropy": 7.282296800613404,
      "epoch": 0.008798646362098138,
      "grad_norm": 1.4140625,
      "learning_rate": 0.000162,
      "loss": 6.7932,
      "mean_token_accuracy": 0.09626845642924309,
      "num_tokens": 892178.0,
      "step": 325
    },
    {
      "entropy": 7.201563024520874,
      "epoch": 0.008934010152284264,
      "grad_norm": 1.3125,
      "learning_rate": 0.00016450000000000001,
      "loss": 6.671,
      "mean_token_accuracy": 0.09671695902943611,
      "num_tokens": 904809.0,
      "step": 330
    },
    {
      "entropy": 7.275315999984741,
      "epoch": 0.009069373942470389,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00016700000000000002,
      "loss": 6.8034,
      "mean_token_accuracy": 0.09026706293225288,
      "num_tokens": 917660.0,
      "step": 335
    },
    {
      "entropy": 7.179704904556274,
      "epoch": 0.009204737732656515,
      "grad_norm": 1.328125,
      "learning_rate": 0.00016950000000000003,
      "loss": 6.6849,
      "mean_token_accuracy": 0.09763308465480805,
      "num_tokens": 932773.0,
      "step": 340
    },
    {
      "entropy": 7.1569760799407955,
      "epoch": 0.009340101522842639,
      "grad_norm": 1.3359375,
      "learning_rate": 0.00017199999999999998,
      "loss": 6.707,
      "mean_token_accuracy": 0.09705711230635643,
      "num_tokens": 946688.0,
      "step": 345
    },
    {
      "entropy": 7.123394393920899,
      "epoch": 0.009475465313028765,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00017449999999999999,
      "loss": 6.6188,
      "mean_token_accuracy": 0.10255519598722458,
      "num_tokens": 960621.0,
      "step": 350
    },
    {
      "entropy": 7.114657831192017,
      "epoch": 0.00961082910321489,
      "grad_norm": 1.2734375,
      "learning_rate": 0.000177,
      "loss": 6.7525,
      "mean_token_accuracy": 0.0939077839255333,
      "num_tokens": 976705.0,
      "step": 355
    },
    {
      "entropy": 7.13629846572876,
      "epoch": 0.009746192893401015,
      "grad_norm": 1.234375,
      "learning_rate": 0.0001795,
      "loss": 6.6798,
      "mean_token_accuracy": 0.09904273673892021,
      "num_tokens": 989175.0,
      "step": 360
    },
    {
      "entropy": 7.18667254447937,
      "epoch": 0.00988155668358714,
      "grad_norm": 1.25,
      "learning_rate": 0.000182,
      "loss": 6.7875,
      "mean_token_accuracy": 0.095027344673872,
      "num_tokens": 1003899.0,
      "step": 365
    },
    {
      "entropy": 7.018054962158203,
      "epoch": 0.010016920473773266,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0001845,
      "loss": 6.6248,
      "mean_token_accuracy": 0.09302543699741364,
      "num_tokens": 1017823.0,
      "step": 370
    },
    {
      "entropy": 7.214749193191528,
      "epoch": 0.01015228426395939,
      "grad_norm": 1.234375,
      "learning_rate": 0.000187,
      "loss": 6.8025,
      "mean_token_accuracy": 0.0944581039249897,
      "num_tokens": 1031556.0,
      "step": 375
    },
    {
      "entropy": 7.06955304145813,
      "epoch": 0.010287648054145516,
      "grad_norm": 1.375,
      "learning_rate": 0.0001895,
      "loss": 6.6582,
      "mean_token_accuracy": 0.10281435176730155,
      "num_tokens": 1044245.0,
      "step": 380
    },
    {
      "entropy": 7.121717023849487,
      "epoch": 0.01042301184433164,
      "grad_norm": 1.3671875,
      "learning_rate": 0.000192,
      "loss": 6.6908,
      "mean_token_accuracy": 0.09887115061283111,
      "num_tokens": 1058288.0,
      "step": 385
    },
    {
      "entropy": 7.069799566268921,
      "epoch": 0.010558375634517767,
      "grad_norm": 1.546875,
      "learning_rate": 0.0001945,
      "loss": 6.623,
      "mean_token_accuracy": 0.09829980209469795,
      "num_tokens": 1072234.0,
      "step": 390
    },
    {
      "entropy": 7.062967205047608,
      "epoch": 0.010693739424703893,
      "grad_norm": 1.484375,
      "learning_rate": 0.00019700000000000002,
      "loss": 6.6287,
      "mean_token_accuracy": 0.0978606753051281,
      "num_tokens": 1085463.0,
      "step": 395
    },
    {
      "entropy": 6.952229833602905,
      "epoch": 0.010829103214890017,
      "grad_norm": 1.4375,
      "learning_rate": 0.00019950000000000002,
      "loss": 6.6629,
      "mean_token_accuracy": 0.09642241895198822,
      "num_tokens": 1101393.0,
      "step": 400
    },
    {
      "entropy": 7.105423212051392,
      "epoch": 0.010964467005076143,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000202,
      "loss": 6.6263,
      "mean_token_accuracy": 0.09685642644762993,
      "num_tokens": 1117150.0,
      "step": 405
    },
    {
      "entropy": 6.972289943695069,
      "epoch": 0.011099830795262267,
      "grad_norm": 1.3515625,
      "learning_rate": 0.00020449999999999998,
      "loss": 6.6594,
      "mean_token_accuracy": 0.10496844202280045,
      "num_tokens": 1130674.0,
      "step": 410
    },
    {
      "entropy": 7.087021827697754,
      "epoch": 0.011235194585448393,
      "grad_norm": 1.171875,
      "learning_rate": 0.000207,
      "loss": 6.6508,
      "mean_token_accuracy": 0.09535380229353904,
      "num_tokens": 1144016.0,
      "step": 415
    },
    {
      "entropy": 6.9751802444458,
      "epoch": 0.011370558375634518,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0002095,
      "loss": 6.646,
      "mean_token_accuracy": 0.09546661153435707,
      "num_tokens": 1160200.0,
      "step": 420
    },
    {
      "entropy": 7.048429536819458,
      "epoch": 0.011505922165820644,
      "grad_norm": 1.484375,
      "learning_rate": 0.000212,
      "loss": 6.5651,
      "mean_token_accuracy": 0.1022900827229023,
      "num_tokens": 1173266.0,
      "step": 425
    },
    {
      "entropy": 6.974373769760132,
      "epoch": 0.011641285956006768,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0002145,
      "loss": 6.6353,
      "mean_token_accuracy": 0.09445997178554535,
      "num_tokens": 1187977.0,
      "step": 430
    },
    {
      "entropy": 6.9971846580505375,
      "epoch": 0.011776649746192894,
      "grad_norm": 1.21875,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.6389,
      "mean_token_accuracy": 0.09972369968891144,
      "num_tokens": 1202369.0,
      "step": 435
    },
    {
      "entropy": 6.966669607162475,
      "epoch": 0.011912013536379018,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0002195,
      "loss": 6.5354,
      "mean_token_accuracy": 0.09552454426884652,
      "num_tokens": 1216956.0,
      "step": 440
    },
    {
      "entropy": 6.981910848617554,
      "epoch": 0.012047377326565144,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000222,
      "loss": 6.6403,
      "mean_token_accuracy": 0.09657183811068534,
      "num_tokens": 1230958.0,
      "step": 445
    },
    {
      "entropy": 6.972163391113281,
      "epoch": 0.012182741116751269,
      "grad_norm": 1.3671875,
      "learning_rate": 0.0002245,
      "loss": 6.5568,
      "mean_token_accuracy": 0.1032287061214447,
      "num_tokens": 1244512.0,
      "step": 450
    },
    {
      "entropy": 6.940069246292114,
      "epoch": 0.012318104906937395,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.4972,
      "mean_token_accuracy": 0.10796320661902428,
      "num_tokens": 1257469.0,
      "step": 455
    },
    {
      "entropy": 6.870718479156494,
      "epoch": 0.01245346869712352,
      "grad_norm": 1.203125,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.5861,
      "mean_token_accuracy": 0.10574530512094497,
      "num_tokens": 1273533.0,
      "step": 460
    },
    {
      "entropy": 6.932940578460693,
      "epoch": 0.012588832487309645,
      "grad_norm": 1.25,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.5387,
      "mean_token_accuracy": 0.10031782239675521,
      "num_tokens": 1288385.0,
      "step": 465
    },
    {
      "entropy": 6.920595693588257,
      "epoch": 0.01272419627749577,
      "grad_norm": 1.3203125,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.6012,
      "mean_token_accuracy": 0.10496116429567337,
      "num_tokens": 1300721.0,
      "step": 470
    },
    {
      "entropy": 6.878480577468872,
      "epoch": 0.012859560067681896,
      "grad_norm": 1.2421875,
      "learning_rate": 0.000237,
      "loss": 6.4915,
      "mean_token_accuracy": 0.1057609498500824,
      "num_tokens": 1313125.0,
      "step": 475
    },
    {
      "entropy": 6.905995321273804,
      "epoch": 0.01299492385786802,
      "grad_norm": 1.296875,
      "learning_rate": 0.0002395,
      "loss": 6.5534,
      "mean_token_accuracy": 0.09937024191021919,
      "num_tokens": 1326226.0,
      "step": 480
    },
    {
      "entropy": 6.928886890411377,
      "epoch": 0.013130287648054146,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000242,
      "loss": 6.4614,
      "mean_token_accuracy": 0.10791765451431275,
      "num_tokens": 1339932.0,
      "step": 485
    },
    {
      "entropy": 6.82708158493042,
      "epoch": 0.01326565143824027,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0002445,
      "loss": 6.5553,
      "mean_token_accuracy": 0.09961838722229004,
      "num_tokens": 1354015.0,
      "step": 490
    },
    {
      "entropy": 6.846263122558594,
      "epoch": 0.013401015228426396,
      "grad_norm": 1.2734375,
      "learning_rate": 0.000247,
      "loss": 6.5473,
      "mean_token_accuracy": 0.100076574832201,
      "num_tokens": 1369333.0,
      "step": 495
    },
    {
      "entropy": 6.777434158325195,
      "epoch": 0.01353637901861252,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0002495,
      "loss": 6.5092,
      "mean_token_accuracy": 0.10239997878670692,
      "num_tokens": 1383141.0,
      "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": 2463461277696000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}