{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5042864346949067,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 4.910352373123169,
      "epoch": 0.005042864346949067,
      "grad_norm": 21.125,
      "learning_rate": 2e-06,
      "loss": 14.2192,
      "mean_token_accuracy": 0.0,
      "num_tokens": 11445.0,
      "step": 5
    },
    {
      "entropy": 4.904936599731445,
      "epoch": 0.010085728693898134,
      "grad_norm": 21.875,
      "learning_rate": 4.5e-06,
      "loss": 14.1143,
      "mean_token_accuracy": 6.73400645609945e-05,
      "num_tokens": 22095.0,
      "step": 10
    },
    {
      "entropy": 4.916885423660278,
      "epoch": 0.015128593040847202,
      "grad_norm": 22.875,
      "learning_rate": 7e-06,
      "loss": 14.1034,
      "mean_token_accuracy": 0.00013709709164686502,
      "num_tokens": 33847.0,
      "step": 15
    },
    {
      "entropy": 5.0439094543457035,
      "epoch": 0.020171457387796268,
      "grad_norm": 27.75,
      "learning_rate": 9.5e-06,
      "loss": 13.7381,
      "mean_token_accuracy": 0.0,
      "num_tokens": 44495.0,
      "step": 20
    },
    {
      "entropy": 5.412609577178955,
      "epoch": 0.025214321734745335,
      "grad_norm": 37.25,
      "learning_rate": 1.2e-05,
      "loss": 13.0504,
      "mean_token_accuracy": 0.0,
      "num_tokens": 55298.0,
      "step": 25
    },
    {
      "entropy": 6.753208303451538,
      "epoch": 0.030257186081694403,
      "grad_norm": 31.25,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 12.0538,
      "mean_token_accuracy": 0.0,
      "num_tokens": 66391.0,
      "step": 30
    },
    {
      "entropy": 9.891419410705566,
      "epoch": 0.03530005042864347,
      "grad_norm": 3.484375,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.9607,
      "mean_token_accuracy": 0.00013166556600481273,
      "num_tokens": 77624.0,
      "step": 35
    },
    {
      "entropy": 10.698719787597657,
      "epoch": 0.040342914775592535,
      "grad_norm": 3.5625,
      "learning_rate": 1.95e-05,
      "loss": 10.7344,
      "mean_token_accuracy": 0.00032866199035197496,
      "num_tokens": 89426.0,
      "step": 40
    },
    {
      "entropy": 10.726075839996337,
      "epoch": 0.0453857791225416,
      "grad_norm": 2.8125,
      "learning_rate": 2.2e-05,
      "loss": 10.5926,
      "mean_token_accuracy": 0.00417199133662507,
      "num_tokens": 100252.0,
      "step": 45
    },
    {
      "entropy": 10.712922477722168,
      "epoch": 0.05042864346949067,
      "grad_norm": 2.328125,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 10.3898,
      "mean_token_accuracy": 0.014383823238313198,
      "num_tokens": 110578.0,
      "step": 50
    },
    {
      "entropy": 10.644971942901611,
      "epoch": 0.05547150781643974,
      "grad_norm": 2.265625,
      "learning_rate": 2.7e-05,
      "loss": 10.2471,
      "mean_token_accuracy": 0.015645577292889356,
      "num_tokens": 121631.0,
      "step": 55
    },
    {
      "entropy": 10.69424057006836,
      "epoch": 0.060514372163388806,
      "grad_norm": 2.078125,
      "learning_rate": 2.95e-05,
      "loss": 10.1162,
      "mean_token_accuracy": 0.01469698864966631,
      "num_tokens": 134254.0,
      "step": 60
    },
    {
      "entropy": 10.732514667510987,
      "epoch": 0.06555723651033787,
      "grad_norm": 1.6796875,
      "learning_rate": 3.2e-05,
      "loss": 10.0187,
      "mean_token_accuracy": 0.021757309418171646,
      "num_tokens": 144928.0,
      "step": 65
    },
    {
      "entropy": 10.716106986999511,
      "epoch": 0.07060010085728693,
      "grad_norm": 1.8046875,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.8923,
      "mean_token_accuracy": 0.03248250037431717,
      "num_tokens": 155518.0,
      "step": 70
    },
    {
      "entropy": 10.709668159484863,
      "epoch": 0.07564296520423601,
      "grad_norm": 1.8984375,
      "learning_rate": 3.7e-05,
      "loss": 9.8081,
      "mean_token_accuracy": 0.032918563671410085,
      "num_tokens": 165850.0,
      "step": 75
    },
    {
      "entropy": 10.714706993103027,
      "epoch": 0.08068582955118507,
      "grad_norm": 1.8359375,
      "learning_rate": 3.95e-05,
      "loss": 9.7875,
      "mean_token_accuracy": 0.03219325188547373,
      "num_tokens": 176787.0,
      "step": 80
    },
    {
      "entropy": 10.714124965667725,
      "epoch": 0.08572869389813415,
      "grad_norm": 1.7265625,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.7108,
      "mean_token_accuracy": 0.035928618907928464,
      "num_tokens": 188345.0,
      "step": 85
    },
    {
      "entropy": 10.705197811126709,
      "epoch": 0.0907715582450832,
      "grad_norm": 1.7421875,
      "learning_rate": 4.45e-05,
      "loss": 9.6412,
      "mean_token_accuracy": 0.0326865192502737,
      "num_tokens": 199315.0,
      "step": 90
    },
    {
      "entropy": 10.699298572540282,
      "epoch": 0.09581442259203228,
      "grad_norm": 1.6875,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.4768,
      "mean_token_accuracy": 0.03807435855269432,
      "num_tokens": 209627.0,
      "step": 95
    },
    {
      "entropy": 10.682019710540771,
      "epoch": 0.10085728693898134,
      "grad_norm": 1.8046875,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.3915,
      "mean_token_accuracy": 0.036197875253856183,
      "num_tokens": 220872.0,
      "step": 100
    },
    {
      "entropy": 10.66194772720337,
      "epoch": 0.1059001512859304,
      "grad_norm": 1.7890625,
      "learning_rate": 5.2e-05,
      "loss": 9.2819,
      "mean_token_accuracy": 0.04516553804278374,
      "num_tokens": 233272.0,
      "step": 105
    },
    {
      "entropy": 10.633659744262696,
      "epoch": 0.11094301563287948,
      "grad_norm": 1.765625,
      "learning_rate": 5.45e-05,
      "loss": 9.1755,
      "mean_token_accuracy": 0.05018138997256756,
      "num_tokens": 243529.0,
      "step": 110
    },
    {
      "entropy": 10.592283630371094,
      "epoch": 0.11598587997982854,
      "grad_norm": 1.609375,
      "learning_rate": 5.7e-05,
      "loss": 9.0954,
      "mean_token_accuracy": 0.04114586636424065,
      "num_tokens": 254942.0,
      "step": 115
    },
    {
      "entropy": 10.565635299682617,
      "epoch": 0.12102874432677761,
      "grad_norm": 1.6796875,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.9839,
      "mean_token_accuracy": 0.048531080782413485,
      "num_tokens": 266552.0,
      "step": 120
    },
    {
      "entropy": 10.520887851715088,
      "epoch": 0.1260716086737267,
      "grad_norm": 1.546875,
      "learning_rate": 6.2e-05,
      "loss": 8.8489,
      "mean_token_accuracy": 0.048508816957473756,
      "num_tokens": 277906.0,
      "step": 125
    },
    {
      "entropy": 10.44383192062378,
      "epoch": 0.13111447302067575,
      "grad_norm": 1.59375,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.7307,
      "mean_token_accuracy": 0.05025425441563129,
      "num_tokens": 289079.0,
      "step": 130
    },
    {
      "entropy": 10.368312740325928,
      "epoch": 0.1361573373676248,
      "grad_norm": 1.4375,
      "learning_rate": 6.7e-05,
      "loss": 8.6518,
      "mean_token_accuracy": 0.04377192948013544,
      "num_tokens": 300107.0,
      "step": 135
    },
    {
      "entropy": 10.284347629547119,
      "epoch": 0.14120020171457387,
      "grad_norm": 1.46875,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.4993,
      "mean_token_accuracy": 0.050150758028030394,
      "num_tokens": 310779.0,
      "step": 140
    },
    {
      "entropy": 10.191308975219727,
      "epoch": 0.14624306606152296,
      "grad_norm": 1.453125,
      "learning_rate": 7.2e-05,
      "loss": 8.453,
      "mean_token_accuracy": 0.04963008016347885,
      "num_tokens": 323478.0,
      "step": 145
    },
    {
      "entropy": 10.073376941680909,
      "epoch": 0.15128593040847202,
      "grad_norm": 1.296875,
      "learning_rate": 7.45e-05,
      "loss": 8.2947,
      "mean_token_accuracy": 0.052390134707093236,
      "num_tokens": 335255.0,
      "step": 150
    },
    {
      "entropy": 9.928036785125732,
      "epoch": 0.15632879475542108,
      "grad_norm": 1.25,
      "learning_rate": 7.7e-05,
      "loss": 8.1781,
      "mean_token_accuracy": 0.050037645548582074,
      "num_tokens": 344824.0,
      "step": 155
    },
    {
      "entropy": 9.778972053527832,
      "epoch": 0.16137165910237014,
      "grad_norm": 1.140625,
      "learning_rate": 7.950000000000001e-05,
      "loss": 8.1288,
      "mean_token_accuracy": 0.04721053130924702,
      "num_tokens": 356283.0,
      "step": 160
    },
    {
      "entropy": 9.597450828552246,
      "epoch": 0.1664145234493192,
      "grad_norm": 0.9140625,
      "learning_rate": 8.2e-05,
      "loss": 8.0566,
      "mean_token_accuracy": 0.04783501923084259,
      "num_tokens": 368098.0,
      "step": 165
    },
    {
      "entropy": 9.383034706115723,
      "epoch": 0.1714573877962683,
      "grad_norm": 0.94140625,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.9436,
      "mean_token_accuracy": 0.048526646196842195,
      "num_tokens": 380948.0,
      "step": 170
    },
    {
      "entropy": 9.10937566757202,
      "epoch": 0.17650025214321735,
      "grad_norm": 0.87890625,
      "learning_rate": 8.7e-05,
      "loss": 7.8313,
      "mean_token_accuracy": 0.050237832218408586,
      "num_tokens": 390392.0,
      "step": 175
    },
    {
      "entropy": 8.893278980255127,
      "epoch": 0.1815431164901664,
      "grad_norm": 0.953125,
      "learning_rate": 8.95e-05,
      "loss": 7.8307,
      "mean_token_accuracy": 0.050915177911520004,
      "num_tokens": 400328.0,
      "step": 180
    },
    {
      "entropy": 8.709152698516846,
      "epoch": 0.18658598083711547,
      "grad_norm": 0.71875,
      "learning_rate": 9.2e-05,
      "loss": 7.8375,
      "mean_token_accuracy": 0.04621901027858257,
      "num_tokens": 410909.0,
      "step": 185
    },
    {
      "entropy": 8.523740673065186,
      "epoch": 0.19162884518406456,
      "grad_norm": 0.58984375,
      "learning_rate": 9.45e-05,
      "loss": 7.7759,
      "mean_token_accuracy": 0.047038092836737634,
      "num_tokens": 422726.0,
      "step": 190
    },
    {
      "entropy": 8.369872570037842,
      "epoch": 0.19667170953101362,
      "grad_norm": 0.69921875,
      "learning_rate": 9.7e-05,
      "loss": 7.6757,
      "mean_token_accuracy": 0.05148980468511581,
      "num_tokens": 433376.0,
      "step": 195
    },
    {
      "entropy": 8.261030673980713,
      "epoch": 0.20171457387796268,
      "grad_norm": 0.80078125,
      "learning_rate": 9.95e-05,
      "loss": 7.7332,
      "mean_token_accuracy": 0.04960624761879444,
      "num_tokens": 443940.0,
      "step": 200
    },
    {
      "entropy": 8.258826065063477,
      "epoch": 0.20675743822491174,
      "grad_norm": 0.58984375,
      "learning_rate": 0.000102,
      "loss": 7.6401,
      "mean_token_accuracy": 0.048060222342610356,
      "num_tokens": 455016.0,
      "step": 205
    },
    {
      "entropy": 8.232400035858154,
      "epoch": 0.2118003025718608,
      "grad_norm": 0.68359375,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.6756,
      "mean_token_accuracy": 0.05087458901107311,
      "num_tokens": 466380.0,
      "step": 210
    },
    {
      "entropy": 8.21111011505127,
      "epoch": 0.2168431669188099,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000107,
      "loss": 7.5595,
      "mean_token_accuracy": 0.049945533461868766,
      "num_tokens": 476915.0,
      "step": 215
    },
    {
      "entropy": 8.243093967437744,
      "epoch": 0.22188603126575895,
      "grad_norm": 1.4921875,
      "learning_rate": 0.0001095,
      "loss": 7.6386,
      "mean_token_accuracy": 0.057695179060101506,
      "num_tokens": 488924.0,
      "step": 220
    },
    {
      "entropy": 8.072712755203247,
      "epoch": 0.22692889561270801,
      "grad_norm": 1.109375,
      "learning_rate": 0.000112,
      "loss": 7.5785,
      "mean_token_accuracy": 0.05549042522907257,
      "num_tokens": 498965.0,
      "step": 225
    },
    {
      "entropy": 8.176321601867675,
      "epoch": 0.23197175995965708,
      "grad_norm": 1.6640625,
      "learning_rate": 0.0001145,
      "loss": 7.5965,
      "mean_token_accuracy": 0.056973418965935704,
      "num_tokens": 509755.0,
      "step": 230
    },
    {
      "entropy": 8.122655010223388,
      "epoch": 0.23701462430660616,
      "grad_norm": 0.8046875,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.5713,
      "mean_token_accuracy": 0.05634952038526535,
      "num_tokens": 521221.0,
      "step": 235
    },
    {
      "entropy": 8.139823246002198,
      "epoch": 0.24205748865355523,
      "grad_norm": 0.9609375,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.6557,
      "mean_token_accuracy": 0.054410668835043904,
      "num_tokens": 533595.0,
      "step": 240
    },
    {
      "entropy": 8.137359714508056,
      "epoch": 0.24710035300050429,
      "grad_norm": 1.03125,
      "learning_rate": 0.000122,
      "loss": 7.5856,
      "mean_token_accuracy": 0.05684904344379902,
      "num_tokens": 543672.0,
      "step": 245
    },
    {
      "entropy": 8.149091720581055,
      "epoch": 0.2521432173474534,
      "grad_norm": 0.81640625,
      "learning_rate": 0.0001245,
      "loss": 7.4872,
      "mean_token_accuracy": 0.06253227479755878,
      "num_tokens": 554906.0,
      "step": 250
    },
    {
      "entropy": 8.084903669357299,
      "epoch": 0.25718608169440244,
      "grad_norm": 0.765625,
      "learning_rate": 0.000127,
      "loss": 7.5417,
      "mean_token_accuracy": 0.06494161449372768,
      "num_tokens": 566419.0,
      "step": 255
    },
    {
      "entropy": 8.07434377670288,
      "epoch": 0.2622289460413515,
      "grad_norm": 1.3125,
      "learning_rate": 0.0001295,
      "loss": 7.5279,
      "mean_token_accuracy": 0.062463199719786644,
      "num_tokens": 578848.0,
      "step": 260
    },
    {
      "entropy": 8.002639818191529,
      "epoch": 0.26727181038830056,
      "grad_norm": 0.9375,
      "learning_rate": 0.000132,
      "loss": 7.4524,
      "mean_token_accuracy": 0.06691358126699924,
      "num_tokens": 590601.0,
      "step": 265
    },
    {
      "entropy": 8.033667945861817,
      "epoch": 0.2723146747352496,
      "grad_norm": 1.25,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.4989,
      "mean_token_accuracy": 0.06721620820462704,
      "num_tokens": 602021.0,
      "step": 270
    },
    {
      "entropy": 7.998079681396485,
      "epoch": 0.2773575390821987,
      "grad_norm": 1.0625,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.5903,
      "mean_token_accuracy": 0.06254490688443184,
      "num_tokens": 613966.0,
      "step": 275
    },
    {
      "entropy": 8.071601390838623,
      "epoch": 0.28240040342914774,
      "grad_norm": 1.09375,
      "learning_rate": 0.0001395,
      "loss": 7.4139,
      "mean_token_accuracy": 0.06817254088819028,
      "num_tokens": 624851.0,
      "step": 280
    },
    {
      "entropy": 7.997099876403809,
      "epoch": 0.2874432677760968,
      "grad_norm": 1.7578125,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.4835,
      "mean_token_accuracy": 0.0678780272603035,
      "num_tokens": 635580.0,
      "step": 285
    },
    {
      "entropy": 7.94349856376648,
      "epoch": 0.2924861321230459,
      "grad_norm": 0.8828125,
      "learning_rate": 0.0001445,
      "loss": 7.5534,
      "mean_token_accuracy": 0.06504139304161072,
      "num_tokens": 646927.0,
      "step": 290
    },
    {
      "entropy": 8.021345949172973,
      "epoch": 0.297528996469995,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000147,
      "loss": 7.4053,
      "mean_token_accuracy": 0.0697047770023346,
      "num_tokens": 658116.0,
      "step": 295
    },
    {
      "entropy": 7.9564056396484375,
      "epoch": 0.30257186081694404,
      "grad_norm": 1.1875,
      "learning_rate": 0.0001495,
      "loss": 7.3887,
      "mean_token_accuracy": 0.06593849398195743,
      "num_tokens": 669054.0,
      "step": 300
    },
    {
      "entropy": 7.9183282375335695,
      "epoch": 0.3076147251638931,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000152,
      "loss": 7.4247,
      "mean_token_accuracy": 0.07052628844976425,
      "num_tokens": 680439.0,
      "step": 305
    },
    {
      "entropy": 7.927852010726928,
      "epoch": 0.31265758951084216,
      "grad_norm": 0.984375,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.3485,
      "mean_token_accuracy": 0.0716003067791462,
      "num_tokens": 690909.0,
      "step": 310
    },
    {
      "entropy": 7.843877267837525,
      "epoch": 0.3177004538577912,
      "grad_norm": 1.109375,
      "learning_rate": 0.000157,
      "loss": 7.3335,
      "mean_token_accuracy": 0.0685461949557066,
      "num_tokens": 701744.0,
      "step": 315
    },
    {
      "entropy": 7.78822283744812,
      "epoch": 0.3227433182047403,
      "grad_norm": 0.92578125,
      "learning_rate": 0.0001595,
      "loss": 7.3599,
      "mean_token_accuracy": 0.07047874368727207,
      "num_tokens": 712268.0,
      "step": 320
    },
    {
      "entropy": 7.879432201385498,
      "epoch": 0.32778618255168934,
      "grad_norm": 1.15625,
      "learning_rate": 0.000162,
      "loss": 7.3937,
      "mean_token_accuracy": 0.06803249828517437,
      "num_tokens": 722978.0,
      "step": 325
    },
    {
      "entropy": 7.837024545669555,
      "epoch": 0.3328290468986384,
      "grad_norm": 0.86328125,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.3977,
      "mean_token_accuracy": 0.06485099494457244,
      "num_tokens": 734278.0,
      "step": 330
    },
    {
      "entropy": 7.870750522613525,
      "epoch": 0.3378719112455875,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.3428,
      "mean_token_accuracy": 0.06625398620963097,
      "num_tokens": 746109.0,
      "step": 335
    },
    {
      "entropy": 7.815386438369751,
      "epoch": 0.3429147755925366,
      "grad_norm": 1.4140625,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.2712,
      "mean_token_accuracy": 0.0703127596527338,
      "num_tokens": 757519.0,
      "step": 340
    },
    {
      "entropy": 7.838667201995849,
      "epoch": 0.34795763993948564,
      "grad_norm": 0.88671875,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.2327,
      "mean_token_accuracy": 0.06976432576775551,
      "num_tokens": 767665.0,
      "step": 345
    },
    {
      "entropy": 7.770452690124512,
      "epoch": 0.3530005042864347,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.2605,
      "mean_token_accuracy": 0.07452492453157902,
      "num_tokens": 778880.0,
      "step": 350
    },
    {
      "entropy": 7.671797084808349,
      "epoch": 0.35804336863338376,
      "grad_norm": 0.87890625,
      "learning_rate": 0.000177,
      "loss": 7.2654,
      "mean_token_accuracy": 0.07736610174179077,
      "num_tokens": 790360.0,
      "step": 355
    },
    {
      "entropy": 7.728646850585937,
      "epoch": 0.3630862329803328,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0001795,
      "loss": 7.2348,
      "mean_token_accuracy": 0.07338146939873695,
      "num_tokens": 800889.0,
      "step": 360
    },
    {
      "entropy": 7.675601196289063,
      "epoch": 0.3681290973272819,
      "grad_norm": 1.4921875,
      "learning_rate": 0.000182,
      "loss": 7.2333,
      "mean_token_accuracy": 0.07188612334430218,
      "num_tokens": 811414.0,
      "step": 365
    },
    {
      "entropy": 7.728438234329223,
      "epoch": 0.37317196167423095,
      "grad_norm": 0.98046875,
      "learning_rate": 0.0001845,
      "loss": 7.2265,
      "mean_token_accuracy": 0.07272094301879406,
      "num_tokens": 822822.0,
      "step": 370
    },
    {
      "entropy": 7.590001153945923,
      "epoch": 0.37821482602118,
      "grad_norm": 0.96484375,
      "learning_rate": 0.000187,
      "loss": 7.1402,
      "mean_token_accuracy": 0.07824505940079689,
      "num_tokens": 833145.0,
      "step": 375
    },
    {
      "entropy": 7.747368717193604,
      "epoch": 0.3832576903681291,
      "grad_norm": 1.34375,
      "learning_rate": 0.0001895,
      "loss": 7.2475,
      "mean_token_accuracy": 0.0740690290927887,
      "num_tokens": 844015.0,
      "step": 380
    },
    {
      "entropy": 7.641835784912109,
      "epoch": 0.3883005547150782,
      "grad_norm": 0.7578125,
      "learning_rate": 0.000192,
      "loss": 7.1787,
      "mean_token_accuracy": 0.07636387497186661,
      "num_tokens": 855806.0,
      "step": 385
    },
    {
      "entropy": 7.64897780418396,
      "epoch": 0.39334341906202724,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0001945,
      "loss": 7.098,
      "mean_token_accuracy": 0.07710095196962356,
      "num_tokens": 865750.0,
      "step": 390
    },
    {
      "entropy": 7.62802677154541,
      "epoch": 0.3983862834089763,
      "grad_norm": 1.4296875,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.2246,
      "mean_token_accuracy": 0.07233364507555962,
      "num_tokens": 877630.0,
      "step": 395
    },
    {
      "entropy": 7.64155797958374,
      "epoch": 0.40342914775592537,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.1193,
      "mean_token_accuracy": 0.07785095870494843,
      "num_tokens": 888667.0,
      "step": 400
    },
    {
      "entropy": 7.625726747512817,
      "epoch": 0.4084720121028744,
      "grad_norm": 0.9140625,
      "learning_rate": 0.000202,
      "loss": 7.197,
      "mean_token_accuracy": 0.07570679485797882,
      "num_tokens": 900989.0,
      "step": 405
    },
    {
      "entropy": 7.635288333892822,
      "epoch": 0.4135148764498235,
      "grad_norm": 0.92578125,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.0775,
      "mean_token_accuracy": 0.07197484150528907,
      "num_tokens": 911479.0,
      "step": 410
    },
    {
      "entropy": 7.58501181602478,
      "epoch": 0.41855774079677255,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000207,
      "loss": 7.1204,
      "mean_token_accuracy": 0.07360159009695053,
      "num_tokens": 922434.0,
      "step": 415
    },
    {
      "entropy": 7.5460936546325685,
      "epoch": 0.4236006051437216,
      "grad_norm": 1.265625,
      "learning_rate": 0.0002095,
      "loss": 7.1144,
      "mean_token_accuracy": 0.07529124468564988,
      "num_tokens": 933405.0,
      "step": 420
    },
    {
      "entropy": 7.6064252853393555,
      "epoch": 0.4286434694906707,
      "grad_norm": 0.94921875,
      "learning_rate": 0.000212,
      "loss": 7.0975,
      "mean_token_accuracy": 0.07624291330575943,
      "num_tokens": 943567.0,
      "step": 425
    },
    {
      "entropy": 7.480703639984131,
      "epoch": 0.4336863338376198,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0002145,
      "loss": 7.136,
      "mean_token_accuracy": 0.07384473346173763,
      "num_tokens": 955123.0,
      "step": 430
    },
    {
      "entropy": 7.631748962402344,
      "epoch": 0.43872919818456885,
      "grad_norm": 1.5,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.1533,
      "mean_token_accuracy": 0.07767361216247082,
      "num_tokens": 965565.0,
      "step": 435
    },
    {
      "entropy": 7.526004362106323,
      "epoch": 0.4437720625315179,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0002195,
      "loss": 7.1039,
      "mean_token_accuracy": 0.07384410724043847,
      "num_tokens": 977101.0,
      "step": 440
    },
    {
      "entropy": 7.576969480514526,
      "epoch": 0.44881492687846697,
      "grad_norm": 1.2890625,
      "learning_rate": 0.000222,
      "loss": 7.1376,
      "mean_token_accuracy": 0.07549539841711521,
      "num_tokens": 987445.0,
      "step": 445
    },
    {
      "entropy": 7.526590204238891,
      "epoch": 0.45385779122541603,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0002245,
      "loss": 7.0196,
      "mean_token_accuracy": 0.08274288028478623,
      "num_tokens": 999379.0,
      "step": 450
    },
    {
      "entropy": 7.471691417694092,
      "epoch": 0.4589006555723651,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.968,
      "mean_token_accuracy": 0.08329149559140206,
      "num_tokens": 1010744.0,
      "step": 455
    },
    {
      "entropy": 7.54520697593689,
      "epoch": 0.46394351991931415,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.0416,
      "mean_token_accuracy": 0.07827929966151714,
      "num_tokens": 1021808.0,
      "step": 460
    },
    {
      "entropy": 7.477932929992676,
      "epoch": 0.4689863842662632,
      "grad_norm": 1.015625,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.0811,
      "mean_token_accuracy": 0.07999052368104458,
      "num_tokens": 1033694.0,
      "step": 465
    },
    {
      "entropy": 7.520880126953125,
      "epoch": 0.47402924861321233,
      "grad_norm": 1.09375,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.0456,
      "mean_token_accuracy": 0.07764143832027912,
      "num_tokens": 1044690.0,
      "step": 470
    },
    {
      "entropy": 7.542422342300415,
      "epoch": 0.4790721129601614,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000237,
      "loss": 7.0482,
      "mean_token_accuracy": 0.07791347205638885,
      "num_tokens": 1055557.0,
      "step": 475
    },
    {
      "entropy": 7.409520292282105,
      "epoch": 0.48411497730711045,
      "grad_norm": 1.015625,
      "learning_rate": 0.0002395,
      "loss": 6.9957,
      "mean_token_accuracy": 0.08100500479340553,
      "num_tokens": 1067304.0,
      "step": 480
    },
    {
      "entropy": 7.459061002731323,
      "epoch": 0.4891578416540595,
      "grad_norm": 1.0625,
      "learning_rate": 0.000242,
      "loss": 7.021,
      "mean_token_accuracy": 0.0783581517636776,
      "num_tokens": 1078955.0,
      "step": 485
    },
    {
      "entropy": 7.449764680862427,
      "epoch": 0.49420070600100857,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0002445,
      "loss": 7.0517,
      "mean_token_accuracy": 0.08230436109006405,
      "num_tokens": 1091405.0,
      "step": 490
    },
    {
      "entropy": 7.463499355316162,
      "epoch": 0.49924357034795763,
      "grad_norm": 1.2734375,
      "learning_rate": 0.000247,
      "loss": 7.0248,
      "mean_token_accuracy": 0.08033888339996338,
      "num_tokens": 1103227.0,
      "step": 495
    },
    {
      "entropy": 7.433458662033081,
      "epoch": 0.5042864346949067,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0002495,
      "loss": 6.9657,
      "mean_token_accuracy": 0.0861723892390728,
      "num_tokens": 1114485.0,
      "step": 500
    },
    {
      "epoch": 0.5042864346949067,
      "eval_entropy": 7.395277802270788,
      "eval_loss": 7.067502975463867,
      "eval_mean_token_accuracy": 0.08697184946852482,
      "eval_num_tokens": 1114485.0,
      "eval_runtime": 2.1239,
      "eval_samples_per_second": 1477.45,
      "eval_steps_per_second": 185.034,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 9910,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 276978743377920.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}