{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03304583457255213,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.69155969619751,
      "epoch": 0.0003304583457255213,
      "grad_norm": 12.8125,
      "learning_rate": 2e-06,
      "loss": 10.8103,
      "mean_token_accuracy": 0.0,
      "num_tokens": 10836.0,
      "step": 5
    },
    {
      "entropy": 10.69160442352295,
      "epoch": 0.0006609166914510426,
      "grad_norm": 10.9375,
      "learning_rate": 4.5e-06,
      "loss": 10.7287,
      "mean_token_accuracy": 0.00010266940807923675,
      "num_tokens": 20708.0,
      "step": 10
    },
    {
      "entropy": 10.691381645202636,
      "epoch": 0.000991375037176564,
      "grad_norm": 9.375,
      "learning_rate": 7e-06,
      "loss": 10.556,
      "mean_token_accuracy": 0.012630514975171536,
      "num_tokens": 32651.0,
      "step": 15
    },
    {
      "entropy": 10.685187435150146,
      "epoch": 0.0013218333829020852,
      "grad_norm": 6.25,
      "learning_rate": 9.5e-06,
      "loss": 10.2559,
      "mean_token_accuracy": 0.04093300513923168,
      "num_tokens": 43844.0,
      "step": 20
    },
    {
      "entropy": 10.628204250335694,
      "epoch": 0.0016522917286276066,
      "grad_norm": 3.9375,
      "learning_rate": 1.2e-05,
      "loss": 10.0415,
      "mean_token_accuracy": 0.038726492412388326,
      "num_tokens": 55019.0,
      "step": 25
    },
    {
      "entropy": 10.554113483428955,
      "epoch": 0.001982750074353128,
      "grad_norm": 3.140625,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 9.8257,
      "mean_token_accuracy": 0.048476964607834815,
      "num_tokens": 66746.0,
      "step": 30
    },
    {
      "entropy": 10.590810203552246,
      "epoch": 0.002313208420078649,
      "grad_norm": 2.765625,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.8306,
      "mean_token_accuracy": 0.03930025473237038,
      "num_tokens": 78821.0,
      "step": 35
    },
    {
      "entropy": 10.605837535858154,
      "epoch": 0.0026436667658041703,
      "grad_norm": 2.5,
      "learning_rate": 1.95e-05,
      "loss": 9.7593,
      "mean_token_accuracy": 0.037112961150705816,
      "num_tokens": 89051.0,
      "step": 40
    },
    {
      "entropy": 10.587123107910156,
      "epoch": 0.0029741251115296915,
      "grad_norm": 2.390625,
      "learning_rate": 2.2e-05,
      "loss": 9.6663,
      "mean_token_accuracy": 0.040811435878276826,
      "num_tokens": 99691.0,
      "step": 45
    },
    {
      "entropy": 10.559133148193359,
      "epoch": 0.003304583457255213,
      "grad_norm": 2.3125,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.7075,
      "mean_token_accuracy": 0.03913131728768349,
      "num_tokens": 110614.0,
      "step": 50
    },
    {
      "entropy": 10.571648788452148,
      "epoch": 0.0036350418029807343,
      "grad_norm": 2.203125,
      "learning_rate": 2.7e-05,
      "loss": 9.7135,
      "mean_token_accuracy": 0.03680916838347912,
      "num_tokens": 122915.0,
      "step": 55
    },
    {
      "entropy": 10.579666042327881,
      "epoch": 0.003965500148706256,
      "grad_norm": 2.28125,
      "learning_rate": 2.95e-05,
      "loss": 9.5367,
      "mean_token_accuracy": 0.040818646922707556,
      "num_tokens": 132627.0,
      "step": 60
    },
    {
      "entropy": 10.55205478668213,
      "epoch": 0.004295958494431777,
      "grad_norm": 2.125,
      "learning_rate": 3.2e-05,
      "loss": 9.5003,
      "mean_token_accuracy": 0.044149795174598695,
      "num_tokens": 144317.0,
      "step": 65
    },
    {
      "entropy": 10.516563987731933,
      "epoch": 0.004626416840157298,
      "grad_norm": 2.28125,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.3204,
      "mean_token_accuracy": 0.04889754429459572,
      "num_tokens": 152798.0,
      "step": 70
    },
    {
      "entropy": 10.421174716949462,
      "epoch": 0.00495687518588282,
      "grad_norm": 2.171875,
      "learning_rate": 3.7e-05,
      "loss": 9.2668,
      "mean_token_accuracy": 0.04544033259153366,
      "num_tokens": 162656.0,
      "step": 75
    },
    {
      "entropy": 10.396770095825195,
      "epoch": 0.005287333531608341,
      "grad_norm": 2.234375,
      "learning_rate": 3.95e-05,
      "loss": 9.226,
      "mean_token_accuracy": 0.050432728976011275,
      "num_tokens": 173784.0,
      "step": 80
    },
    {
      "entropy": 10.419888401031494,
      "epoch": 0.005617791877333862,
      "grad_norm": 1.921875,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.1258,
      "mean_token_accuracy": 0.0568363256752491,
      "num_tokens": 184681.0,
      "step": 85
    },
    {
      "entropy": 10.358776760101318,
      "epoch": 0.005948250223059383,
      "grad_norm": 2.109375,
      "learning_rate": 4.45e-05,
      "loss": 9.0169,
      "mean_token_accuracy": 0.053509436920285224,
      "num_tokens": 195307.0,
      "step": 90
    },
    {
      "entropy": 10.326674938201904,
      "epoch": 0.006278708568784905,
      "grad_norm": 2.15625,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 8.8921,
      "mean_token_accuracy": 0.060885720700025556,
      "num_tokens": 206857.0,
      "step": 95
    },
    {
      "entropy": 10.2583758354187,
      "epoch": 0.006609166914510426,
      "grad_norm": 2.421875,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 8.8016,
      "mean_token_accuracy": 0.05900029614567757,
      "num_tokens": 217291.0,
      "step": 100
    },
    {
      "entropy": 10.172372817993164,
      "epoch": 0.006939625260235947,
      "grad_norm": 2.203125,
      "learning_rate": 5.2e-05,
      "loss": 8.6847,
      "mean_token_accuracy": 0.0601776622235775,
      "num_tokens": 227184.0,
      "step": 105
    },
    {
      "entropy": 10.142582893371582,
      "epoch": 0.007270083605961469,
      "grad_norm": 2.421875,
      "learning_rate": 5.45e-05,
      "loss": 8.5856,
      "mean_token_accuracy": 0.062167299538850786,
      "num_tokens": 237928.0,
      "step": 110
    },
    {
      "entropy": 9.992514324188232,
      "epoch": 0.00760054195168699,
      "grad_norm": 1.6484375,
      "learning_rate": 5.7e-05,
      "loss": 8.4541,
      "mean_token_accuracy": 0.07033347450196743,
      "num_tokens": 250073.0,
      "step": 115
    },
    {
      "entropy": 9.925767707824708,
      "epoch": 0.007931000297412512,
      "grad_norm": 1.7421875,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.3133,
      "mean_token_accuracy": 0.07063820958137512,
      "num_tokens": 261191.0,
      "step": 120
    },
    {
      "entropy": 9.826898574829102,
      "epoch": 0.008261458643138032,
      "grad_norm": 1.7421875,
      "learning_rate": 6.2e-05,
      "loss": 8.2501,
      "mean_token_accuracy": 0.0650045171380043,
      "num_tokens": 271226.0,
      "step": 125
    },
    {
      "entropy": 9.688051795959472,
      "epoch": 0.008591916988863553,
      "grad_norm": 1.7421875,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.1108,
      "mean_token_accuracy": 0.07041079625487327,
      "num_tokens": 282632.0,
      "step": 130
    },
    {
      "entropy": 9.554755210876465,
      "epoch": 0.008922375334589075,
      "grad_norm": 1.640625,
      "learning_rate": 6.7e-05,
      "loss": 8.0812,
      "mean_token_accuracy": 0.06935585699975491,
      "num_tokens": 294119.0,
      "step": 135
    },
    {
      "entropy": 9.3393235206604,
      "epoch": 0.009252833680314597,
      "grad_norm": 1.5546875,
      "learning_rate": 6.950000000000001e-05,
      "loss": 7.9154,
      "mean_token_accuracy": 0.06800433918833733,
      "num_tokens": 304725.0,
      "step": 140
    },
    {
      "entropy": 9.183171463012695,
      "epoch": 0.009583292026040118,
      "grad_norm": 1.1953125,
      "learning_rate": 7.2e-05,
      "loss": 7.8272,
      "mean_token_accuracy": 0.06738981902599335,
      "num_tokens": 315260.0,
      "step": 145
    },
    {
      "entropy": 9.023473262786865,
      "epoch": 0.00991375037176564,
      "grad_norm": 1.1953125,
      "learning_rate": 7.45e-05,
      "loss": 7.816,
      "mean_token_accuracy": 0.0658723335713148,
      "num_tokens": 326228.0,
      "step": 150
    },
    {
      "entropy": 8.789591312408447,
      "epoch": 0.01024420871749116,
      "grad_norm": 1.25,
      "learning_rate": 7.7e-05,
      "loss": 7.6682,
      "mean_token_accuracy": 0.07138085626065731,
      "num_tokens": 336974.0,
      "step": 155
    },
    {
      "entropy": 8.713123226165772,
      "epoch": 0.010574667063216681,
      "grad_norm": 1.5546875,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.6937,
      "mean_token_accuracy": 0.06671310998499394,
      "num_tokens": 347380.0,
      "step": 160
    },
    {
      "entropy": 8.564159774780274,
      "epoch": 0.010905125408942203,
      "grad_norm": 1.484375,
      "learning_rate": 8.2e-05,
      "loss": 7.5414,
      "mean_token_accuracy": 0.06911698617041111,
      "num_tokens": 358159.0,
      "step": 165
    },
    {
      "entropy": 8.391338634490968,
      "epoch": 0.011235583754667725,
      "grad_norm": 1.28125,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.6154,
      "mean_token_accuracy": 0.06779548972845077,
      "num_tokens": 369224.0,
      "step": 170
    },
    {
      "entropy": 8.317761039733886,
      "epoch": 0.011566042100393246,
      "grad_norm": 1.1953125,
      "learning_rate": 8.7e-05,
      "loss": 7.5342,
      "mean_token_accuracy": 0.0646525926887989,
      "num_tokens": 380973.0,
      "step": 175
    },
    {
      "entropy": 8.257954692840576,
      "epoch": 0.011896500446118766,
      "grad_norm": 1.3359375,
      "learning_rate": 8.95e-05,
      "loss": 7.6128,
      "mean_token_accuracy": 0.06305343359708786,
      "num_tokens": 393367.0,
      "step": 180
    },
    {
      "entropy": 8.156609535217285,
      "epoch": 0.012226958791844288,
      "grad_norm": 1.203125,
      "learning_rate": 9.2e-05,
      "loss": 7.5075,
      "mean_token_accuracy": 0.07255993783473969,
      "num_tokens": 405104.0,
      "step": 185
    },
    {
      "entropy": 8.167465686798096,
      "epoch": 0.01255741713756981,
      "grad_norm": 1.1796875,
      "learning_rate": 9.45e-05,
      "loss": 7.5335,
      "mean_token_accuracy": 0.06890368461608887,
      "num_tokens": 415734.0,
      "step": 190
    },
    {
      "entropy": 8.079139995574952,
      "epoch": 0.01288787548329533,
      "grad_norm": 1.421875,
      "learning_rate": 9.7e-05,
      "loss": 7.5476,
      "mean_token_accuracy": 0.06830249056220054,
      "num_tokens": 425949.0,
      "step": 195
    },
    {
      "entropy": 8.103539848327637,
      "epoch": 0.013218333829020852,
      "grad_norm": 1.6328125,
      "learning_rate": 9.95e-05,
      "loss": 7.3962,
      "mean_token_accuracy": 0.06818307042121888,
      "num_tokens": 436083.0,
      "step": 200
    },
    {
      "entropy": 7.987107515335083,
      "epoch": 0.013548792174746372,
      "grad_norm": 1.484375,
      "learning_rate": 0.000102,
      "loss": 7.4,
      "mean_token_accuracy": 0.0744843065738678,
      "num_tokens": 446731.0,
      "step": 205
    },
    {
      "entropy": 7.954383039474488,
      "epoch": 0.013879250520471894,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.392,
      "mean_token_accuracy": 0.0729294192045927,
      "num_tokens": 456630.0,
      "step": 210
    },
    {
      "entropy": 7.964882946014404,
      "epoch": 0.014209708866197416,
      "grad_norm": 1.8203125,
      "learning_rate": 0.000107,
      "loss": 7.406,
      "mean_token_accuracy": 0.06909749209880829,
      "num_tokens": 468804.0,
      "step": 215
    },
    {
      "entropy": 7.789395570755005,
      "epoch": 0.014540167211922937,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0001095,
      "loss": 7.3496,
      "mean_token_accuracy": 0.07542757764458656,
      "num_tokens": 479321.0,
      "step": 220
    },
    {
      "entropy": 7.850273847579956,
      "epoch": 0.014870625557648459,
      "grad_norm": 1.25,
      "learning_rate": 0.000112,
      "loss": 7.3846,
      "mean_token_accuracy": 0.0726801447570324,
      "num_tokens": 490788.0,
      "step": 225
    },
    {
      "entropy": 7.854997777938843,
      "epoch": 0.01520108390337398,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0001145,
      "loss": 7.3583,
      "mean_token_accuracy": 0.07561610527336597,
      "num_tokens": 501992.0,
      "step": 230
    },
    {
      "entropy": 7.8472926139831545,
      "epoch": 0.0155315422490995,
      "grad_norm": 1.21875,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.2768,
      "mean_token_accuracy": 0.08250004723668099,
      "num_tokens": 511927.0,
      "step": 235
    },
    {
      "entropy": 7.760110378265381,
      "epoch": 0.015862000594825024,
      "grad_norm": 1.0625,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.2478,
      "mean_token_accuracy": 0.08096232078969479,
      "num_tokens": 521874.0,
      "step": 240
    },
    {
      "entropy": 7.749714708328247,
      "epoch": 0.016192458940550544,
      "grad_norm": 1.0625,
      "learning_rate": 0.000122,
      "loss": 7.3405,
      "mean_token_accuracy": 0.07609539777040482,
      "num_tokens": 532913.0,
      "step": 245
    },
    {
      "entropy": 7.832424545288086,
      "epoch": 0.016522917286276063,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0001245,
      "loss": 7.2888,
      "mean_token_accuracy": 0.07482444941997528,
      "num_tokens": 544195.0,
      "step": 250
    },
    {
      "entropy": 7.710200643539428,
      "epoch": 0.016853375632001587,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000127,
      "loss": 7.2822,
      "mean_token_accuracy": 0.07511841356754304,
      "num_tokens": 555555.0,
      "step": 255
    },
    {
      "entropy": 7.723060989379883,
      "epoch": 0.017183833977727107,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0001295,
      "loss": 7.3017,
      "mean_token_accuracy": 0.06918322369456291,
      "num_tokens": 566446.0,
      "step": 260
    },
    {
      "entropy": 7.735864305496216,
      "epoch": 0.01751429232345263,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000132,
      "loss": 7.1435,
      "mean_token_accuracy": 0.08523371145129204,
      "num_tokens": 576138.0,
      "step": 265
    },
    {
      "entropy": 7.7571961879730225,
      "epoch": 0.01784475066917815,
      "grad_norm": 1.7109375,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.4068,
      "mean_token_accuracy": 0.07323086895048618,
      "num_tokens": 587559.0,
      "step": 270
    },
    {
      "entropy": 7.637564659118652,
      "epoch": 0.01817520901490367,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.2492,
      "mean_token_accuracy": 0.07899717763066291,
      "num_tokens": 598704.0,
      "step": 275
    },
    {
      "entropy": 7.6305924415588375,
      "epoch": 0.018505667360629193,
      "grad_norm": 1.203125,
      "learning_rate": 0.0001395,
      "loss": 7.2202,
      "mean_token_accuracy": 0.08230236917734146,
      "num_tokens": 609992.0,
      "step": 280
    },
    {
      "entropy": 7.777820110321045,
      "epoch": 0.018836125706354713,
      "grad_norm": 1.375,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.2906,
      "mean_token_accuracy": 0.0766009196639061,
      "num_tokens": 620756.0,
      "step": 285
    },
    {
      "entropy": 7.612432479858398,
      "epoch": 0.019166584052080236,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001445,
      "loss": 7.1494,
      "mean_token_accuracy": 0.08179529085755348,
      "num_tokens": 630335.0,
      "step": 290
    },
    {
      "entropy": 7.54581618309021,
      "epoch": 0.019497042397805756,
      "grad_norm": 1.1875,
      "learning_rate": 0.000147,
      "loss": 7.2277,
      "mean_token_accuracy": 0.07613298408687115,
      "num_tokens": 641176.0,
      "step": 295
    },
    {
      "entropy": 7.677836608886719,
      "epoch": 0.01982750074353128,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0001495,
      "loss": 7.1341,
      "mean_token_accuracy": 0.0822694730013609,
      "num_tokens": 652144.0,
      "step": 300
    },
    {
      "entropy": 7.5951337814331055,
      "epoch": 0.0201579590892568,
      "grad_norm": 1.328125,
      "learning_rate": 0.000152,
      "loss": 7.1135,
      "mean_token_accuracy": 0.07866659983992577,
      "num_tokens": 663040.0,
      "step": 305
    },
    {
      "entropy": 7.540827846527099,
      "epoch": 0.02048841743498232,
      "grad_norm": 1.078125,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.1588,
      "mean_token_accuracy": 0.08099368289113044,
      "num_tokens": 674407.0,
      "step": 310
    },
    {
      "entropy": 7.606076622009278,
      "epoch": 0.020818875780707843,
      "grad_norm": 1.0390625,
      "learning_rate": 0.000157,
      "loss": 7.1684,
      "mean_token_accuracy": 0.07814301066100597,
      "num_tokens": 686575.0,
      "step": 315
    },
    {
      "entropy": 7.528010988235474,
      "epoch": 0.021149334126433363,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0001595,
      "loss": 7.1044,
      "mean_token_accuracy": 0.08741299659013749,
      "num_tokens": 697404.0,
      "step": 320
    },
    {
      "entropy": 7.685597991943359,
      "epoch": 0.021479792472158886,
      "grad_norm": 1.078125,
      "learning_rate": 0.000162,
      "loss": 7.2433,
      "mean_token_accuracy": 0.07762166783213616,
      "num_tokens": 708462.0,
      "step": 325
    },
    {
      "entropy": 7.546236228942871,
      "epoch": 0.021810250817884406,
      "grad_norm": 1.140625,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.1297,
      "mean_token_accuracy": 0.08397110104560852,
      "num_tokens": 719485.0,
      "step": 330
    },
    {
      "entropy": 7.449752140045166,
      "epoch": 0.022140709163609926,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.1155,
      "mean_token_accuracy": 0.08090364784002305,
      "num_tokens": 730417.0,
      "step": 335
    },
    {
      "entropy": 7.544217443466186,
      "epoch": 0.02247116750933545,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.0674,
      "mean_token_accuracy": 0.08530745506286622,
      "num_tokens": 740644.0,
      "step": 340
    },
    {
      "entropy": 7.413099479675293,
      "epoch": 0.02280162585506097,
      "grad_norm": 1.2890625,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.0263,
      "mean_token_accuracy": 0.0855514369904995,
      "num_tokens": 751843.0,
      "step": 345
    },
    {
      "entropy": 7.519398832321167,
      "epoch": 0.023132084200786492,
      "grad_norm": 1.125,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.0071,
      "mean_token_accuracy": 0.08101744726300239,
      "num_tokens": 763193.0,
      "step": 350
    },
    {
      "entropy": 7.416529798507691,
      "epoch": 0.023462542546512012,
      "grad_norm": 1.109375,
      "learning_rate": 0.000177,
      "loss": 7.088,
      "mean_token_accuracy": 0.07980120629072189,
      "num_tokens": 775393.0,
      "step": 355
    },
    {
      "entropy": 7.473480892181397,
      "epoch": 0.023793000892237532,
      "grad_norm": 1.28125,
      "learning_rate": 0.0001795,
      "loss": 6.9638,
      "mean_token_accuracy": 0.08316674306988717,
      "num_tokens": 786292.0,
      "step": 360
    },
    {
      "entropy": 7.4191234588623045,
      "epoch": 0.024123459237963055,
      "grad_norm": 1.109375,
      "learning_rate": 0.000182,
      "loss": 7.0293,
      "mean_token_accuracy": 0.07673819884657859,
      "num_tokens": 798344.0,
      "step": 365
    },
    {
      "entropy": 7.390763473510742,
      "epoch": 0.024453917583688575,
      "grad_norm": 1.265625,
      "learning_rate": 0.0001845,
      "loss": 7.0266,
      "mean_token_accuracy": 0.08823682218790055,
      "num_tokens": 809058.0,
      "step": 370
    },
    {
      "entropy": 7.3451203346252445,
      "epoch": 0.0247843759294141,
      "grad_norm": 1.0625,
      "learning_rate": 0.000187,
      "loss": 6.9562,
      "mean_token_accuracy": 0.08663681447505951,
      "num_tokens": 820848.0,
      "step": 375
    },
    {
      "entropy": 7.416850471496582,
      "epoch": 0.02511483427513962,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001895,
      "loss": 7.0447,
      "mean_token_accuracy": 0.08994424119591712,
      "num_tokens": 833361.0,
      "step": 380
    },
    {
      "entropy": 7.370834159851074,
      "epoch": 0.02544529262086514,
      "grad_norm": 1.09375,
      "learning_rate": 0.000192,
      "loss": 6.9881,
      "mean_token_accuracy": 0.08523149564862251,
      "num_tokens": 843801.0,
      "step": 385
    },
    {
      "entropy": 7.4036249160766605,
      "epoch": 0.02577575096659066,
      "grad_norm": 1.125,
      "learning_rate": 0.0001945,
      "loss": 6.9772,
      "mean_token_accuracy": 0.08082735612988472,
      "num_tokens": 854477.0,
      "step": 390
    },
    {
      "entropy": 7.330833148956299,
      "epoch": 0.02610620931231618,
      "grad_norm": 1.203125,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.0413,
      "mean_token_accuracy": 0.08312294557690621,
      "num_tokens": 863380.0,
      "step": 395
    },
    {
      "entropy": 7.37300477027893,
      "epoch": 0.026436667658041705,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00019950000000000002,
      "loss": 6.9635,
      "mean_token_accuracy": 0.08273139744997024,
      "num_tokens": 874215.0,
      "step": 400
    },
    {
      "entropy": 7.265693616867066,
      "epoch": 0.026767126003767225,
      "grad_norm": 1.296875,
      "learning_rate": 0.000202,
      "loss": 7.0215,
      "mean_token_accuracy": 0.09335545673966408,
      "num_tokens": 885928.0,
      "step": 405
    },
    {
      "entropy": 7.470329475402832,
      "epoch": 0.027097584349492745,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.036,
      "mean_token_accuracy": 0.08615454584360123,
      "num_tokens": 896349.0,
      "step": 410
    },
    {
      "entropy": 7.282833099365234,
      "epoch": 0.027428042695218268,
      "grad_norm": 1.109375,
      "learning_rate": 0.000207,
      "loss": 6.9012,
      "mean_token_accuracy": 0.0931041918694973,
      "num_tokens": 907126.0,
      "step": 415
    },
    {
      "entropy": 7.305163431167602,
      "epoch": 0.027758501040943788,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0002095,
      "loss": 7.0214,
      "mean_token_accuracy": 0.08308781683444977,
      "num_tokens": 918021.0,
      "step": 420
    },
    {
      "entropy": 7.268058013916016,
      "epoch": 0.02808895938666931,
      "grad_norm": 1.171875,
      "learning_rate": 0.000212,
      "loss": 6.8958,
      "mean_token_accuracy": 0.08962870463728904,
      "num_tokens": 929321.0,
      "step": 425
    },
    {
      "entropy": 7.27590012550354,
      "epoch": 0.02841941773239483,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0002145,
      "loss": 6.9289,
      "mean_token_accuracy": 0.08679753243923187,
      "num_tokens": 940196.0,
      "step": 430
    },
    {
      "entropy": 7.284714984893799,
      "epoch": 0.028749876078120355,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.9195,
      "mean_token_accuracy": 0.09327666312456132,
      "num_tokens": 950600.0,
      "step": 435
    },
    {
      "entropy": 7.263758373260498,
      "epoch": 0.029080334423845874,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0002195,
      "loss": 6.9498,
      "mean_token_accuracy": 0.08754595220088959,
      "num_tokens": 961447.0,
      "step": 440
    },
    {
      "entropy": 7.194220161437988,
      "epoch": 0.029410792769571394,
      "grad_norm": 1.171875,
      "learning_rate": 0.000222,
      "loss": 6.8597,
      "mean_token_accuracy": 0.08954929485917092,
      "num_tokens": 973264.0,
      "step": 445
    },
    {
      "entropy": 7.355491304397583,
      "epoch": 0.029741251115296918,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0002245,
      "loss": 7.0987,
      "mean_token_accuracy": 0.07984722442924977,
      "num_tokens": 985123.0,
      "step": 450
    },
    {
      "entropy": 7.258900594711304,
      "epoch": 0.030071709461022438,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.935,
      "mean_token_accuracy": 0.08211459219455719,
      "num_tokens": 996037.0,
      "step": 455
    },
    {
      "entropy": 7.292104005813599,
      "epoch": 0.03040216780674796,
      "grad_norm": 1.34375,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.9936,
      "mean_token_accuracy": 0.0812192477285862,
      "num_tokens": 1006940.0,
      "step": 460
    },
    {
      "entropy": 7.212660837173462,
      "epoch": 0.03073262615247348,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.8055,
      "mean_token_accuracy": 0.08365916460752487,
      "num_tokens": 1017259.0,
      "step": 465
    },
    {
      "entropy": 7.161711931228638,
      "epoch": 0.031063084498199,
      "grad_norm": 1.015625,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.8381,
      "mean_token_accuracy": 0.08933527991175652,
      "num_tokens": 1028477.0,
      "step": 470
    },
    {
      "entropy": 7.197433996200561,
      "epoch": 0.031393542843924524,
      "grad_norm": 1.0390625,
      "learning_rate": 0.000237,
      "loss": 6.8515,
      "mean_token_accuracy": 0.0891186311841011,
      "num_tokens": 1039812.0,
      "step": 475
    },
    {
      "entropy": 7.1398866176605225,
      "epoch": 0.03172400118965005,
      "grad_norm": 1.109375,
      "learning_rate": 0.0002395,
      "loss": 6.8207,
      "mean_token_accuracy": 0.09132780060172081,
      "num_tokens": 1050856.0,
      "step": 480
    },
    {
      "entropy": 7.054386281967163,
      "epoch": 0.032054459535375564,
      "grad_norm": 1.15625,
      "learning_rate": 0.000242,
      "loss": 6.6937,
      "mean_token_accuracy": 0.09542593285441399,
      "num_tokens": 1061491.0,
      "step": 485
    },
    {
      "entropy": 7.081818532943726,
      "epoch": 0.03238491788110109,
      "grad_norm": 1.03125,
      "learning_rate": 0.0002445,
      "loss": 6.7775,
      "mean_token_accuracy": 0.08975680768489838,
      "num_tokens": 1071986.0,
      "step": 490
    },
    {
      "entropy": 7.154221773147583,
      "epoch": 0.03271537622682661,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000247,
      "loss": 6.8332,
      "mean_token_accuracy": 0.08331749886274338,
      "num_tokens": 1084174.0,
      "step": 495
    },
    {
      "entropy": 7.191654109954834,
      "epoch": 0.03304583457255213,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0002495,
      "loss": 6.8399,
      "mean_token_accuracy": 0.08998439535498619,
      "num_tokens": 1094267.0,
      "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": 1859060146176000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}