{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4972650422675286,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.69195852279663,
      "epoch": 0.004972650422675286,
      "grad_norm": 13.0,
      "learning_rate": 2e-06,
      "loss": 10.8154,
      "mean_token_accuracy": 0.0,
      "num_tokens": 9089.0,
      "step": 5
    },
    {
      "entropy": 10.69191370010376,
      "epoch": 0.009945300845350571,
      "grad_norm": 12.4375,
      "learning_rate": 4.5e-06,
      "loss": 10.8258,
      "mean_token_accuracy": 0.0,
      "num_tokens": 21650.0,
      "step": 10
    },
    {
      "entropy": 10.69098253250122,
      "epoch": 0.014917951268025857,
      "grad_norm": 9.625,
      "learning_rate": 7e-06,
      "loss": 10.5784,
      "mean_token_accuracy": 0.020547608099877834,
      "num_tokens": 31067.0,
      "step": 15
    },
    {
      "entropy": 10.673026275634765,
      "epoch": 0.019890601690701143,
      "grad_norm": 6.40625,
      "learning_rate": 9.5e-06,
      "loss": 10.3334,
      "mean_token_accuracy": 0.041073380038142204,
      "num_tokens": 40816.0,
      "step": 20
    },
    {
      "entropy": 10.540556049346923,
      "epoch": 0.02486325211337643,
      "grad_norm": 4.28125,
      "learning_rate": 1.2e-05,
      "loss": 10.1325,
      "mean_token_accuracy": 0.0424393804743886,
      "num_tokens": 51065.0,
      "step": 25
    },
    {
      "entropy": 10.523736000061035,
      "epoch": 0.029835902536051714,
      "grad_norm": 3.359375,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 9.9451,
      "mean_token_accuracy": 0.044780130684375766,
      "num_tokens": 60539.0,
      "step": 30
    },
    {
      "entropy": 10.482940578460694,
      "epoch": 0.034808552958727,
      "grad_norm": 2.484375,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.9267,
      "mean_token_accuracy": 0.04583238400518894,
      "num_tokens": 71010.0,
      "step": 35
    },
    {
      "entropy": 10.497202396392822,
      "epoch": 0.039781203381402286,
      "grad_norm": 2.453125,
      "learning_rate": 1.95e-05,
      "loss": 9.8766,
      "mean_token_accuracy": 0.04677955023944378,
      "num_tokens": 81394.0,
      "step": 40
    },
    {
      "entropy": 10.495645523071289,
      "epoch": 0.04475385380407757,
      "grad_norm": 2.390625,
      "learning_rate": 2.2e-05,
      "loss": 9.9242,
      "mean_token_accuracy": 0.04332513865083456,
      "num_tokens": 92491.0,
      "step": 45
    },
    {
      "entropy": 10.476744461059571,
      "epoch": 0.04972650422675286,
      "grad_norm": 2.265625,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.8095,
      "mean_token_accuracy": 0.045694665610790254,
      "num_tokens": 102113.0,
      "step": 50
    },
    {
      "entropy": 10.468534755706788,
      "epoch": 0.05469915464942814,
      "grad_norm": 3.109375,
      "learning_rate": 2.7e-05,
      "loss": 9.8159,
      "mean_token_accuracy": 0.051046956703066824,
      "num_tokens": 112211.0,
      "step": 55
    },
    {
      "entropy": 10.431697177886964,
      "epoch": 0.05967180507210343,
      "grad_norm": 1.8203125,
      "learning_rate": 2.95e-05,
      "loss": 9.7102,
      "mean_token_accuracy": 0.05394814908504486,
      "num_tokens": 122166.0,
      "step": 60
    },
    {
      "entropy": 10.248080635070801,
      "epoch": 0.06464445549477872,
      "grad_norm": 2.125,
      "learning_rate": 3.2e-05,
      "loss": 9.6181,
      "mean_token_accuracy": 0.059726152941584586,
      "num_tokens": 131016.0,
      "step": 65
    },
    {
      "entropy": 10.313014602661132,
      "epoch": 0.069617105917454,
      "grad_norm": 1.984375,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.587,
      "mean_token_accuracy": 0.06370560713112354,
      "num_tokens": 141369.0,
      "step": 70
    },
    {
      "entropy": 10.329190254211426,
      "epoch": 0.07458975634012929,
      "grad_norm": 1.9296875,
      "learning_rate": 3.7e-05,
      "loss": 9.5355,
      "mean_token_accuracy": 0.058842772617936134,
      "num_tokens": 150939.0,
      "step": 75
    },
    {
      "entropy": 10.338141822814942,
      "epoch": 0.07956240676280457,
      "grad_norm": 1.890625,
      "learning_rate": 3.95e-05,
      "loss": 9.478,
      "mean_token_accuracy": 0.05786029174923897,
      "num_tokens": 159981.0,
      "step": 80
    },
    {
      "entropy": 10.291361045837402,
      "epoch": 0.08453505718547986,
      "grad_norm": 1.765625,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.4043,
      "mean_token_accuracy": 0.05959840677678585,
      "num_tokens": 170139.0,
      "step": 85
    },
    {
      "entropy": 10.275171947479247,
      "epoch": 0.08950770760815514,
      "grad_norm": 1.8046875,
      "learning_rate": 4.45e-05,
      "loss": 9.3294,
      "mean_token_accuracy": 0.06485622599720955,
      "num_tokens": 180746.0,
      "step": 90
    },
    {
      "entropy": 10.15320930480957,
      "epoch": 0.09448035803083044,
      "grad_norm": 1.6328125,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.1862,
      "mean_token_accuracy": 0.06401227861642837,
      "num_tokens": 190250.0,
      "step": 95
    },
    {
      "entropy": 10.223065280914307,
      "epoch": 0.09945300845350571,
      "grad_norm": 1.8046875,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.2406,
      "mean_token_accuracy": 0.061084074527025224,
      "num_tokens": 201185.0,
      "step": 100
    },
    {
      "entropy": 10.13264331817627,
      "epoch": 0.10442565887618101,
      "grad_norm": 1.46875,
      "learning_rate": 5.2e-05,
      "loss": 9.16,
      "mean_token_accuracy": 0.05885303355753422,
      "num_tokens": 211476.0,
      "step": 105
    },
    {
      "entropy": 10.12833375930786,
      "epoch": 0.10939830929885629,
      "grad_norm": 1.4140625,
      "learning_rate": 5.45e-05,
      "loss": 9.0533,
      "mean_token_accuracy": 0.062058281153440475,
      "num_tokens": 220965.0,
      "step": 110
    },
    {
      "entropy": 10.080890655517578,
      "epoch": 0.11437095972153158,
      "grad_norm": 1.4140625,
      "learning_rate": 5.7e-05,
      "loss": 8.9846,
      "mean_token_accuracy": 0.05859192833304405,
      "num_tokens": 231539.0,
      "step": 115
    },
    {
      "entropy": 9.94415922164917,
      "epoch": 0.11934361014420686,
      "grad_norm": 1.3671875,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.881,
      "mean_token_accuracy": 0.06372438780963421,
      "num_tokens": 241206.0,
      "step": 120
    },
    {
      "entropy": 9.881352806091309,
      "epoch": 0.12431626056688215,
      "grad_norm": 1.2109375,
      "learning_rate": 6.2e-05,
      "loss": 8.7735,
      "mean_token_accuracy": 0.06269489601254463,
      "num_tokens": 250629.0,
      "step": 125
    },
    {
      "entropy": 9.732184791564942,
      "epoch": 0.12928891098955744,
      "grad_norm": 1.2734375,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.7496,
      "mean_token_accuracy": 0.05945408381521702,
      "num_tokens": 260705.0,
      "step": 130
    },
    {
      "entropy": 9.715274715423584,
      "epoch": 0.13426156141223272,
      "grad_norm": 1.5234375,
      "learning_rate": 6.7e-05,
      "loss": 8.6842,
      "mean_token_accuracy": 0.05957487896084786,
      "num_tokens": 270499.0,
      "step": 135
    },
    {
      "entropy": 9.532818031311034,
      "epoch": 0.139234211834908,
      "grad_norm": 1.2265625,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.6647,
      "mean_token_accuracy": 0.05812281183898449,
      "num_tokens": 279998.0,
      "step": 140
    },
    {
      "entropy": 9.431089496612548,
      "epoch": 0.14420686225758328,
      "grad_norm": 1.4140625,
      "learning_rate": 7.2e-05,
      "loss": 8.5342,
      "mean_token_accuracy": 0.06715737730264663,
      "num_tokens": 290322.0,
      "step": 145
    },
    {
      "entropy": 9.28282127380371,
      "epoch": 0.14917951268025859,
      "grad_norm": 1.109375,
      "learning_rate": 7.45e-05,
      "loss": 8.4927,
      "mean_token_accuracy": 0.06783988289535045,
      "num_tokens": 299893.0,
      "step": 150
    },
    {
      "entropy": 9.202215671539307,
      "epoch": 0.15415216310293386,
      "grad_norm": 1.2890625,
      "learning_rate": 7.7e-05,
      "loss": 8.4742,
      "mean_token_accuracy": 0.06662740968167782,
      "num_tokens": 309191.0,
      "step": 155
    },
    {
      "entropy": 9.073563289642333,
      "epoch": 0.15912481352560914,
      "grad_norm": 1.1953125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 8.4087,
      "mean_token_accuracy": 0.06572333909571171,
      "num_tokens": 318494.0,
      "step": 160
    },
    {
      "entropy": 9.005878067016601,
      "epoch": 0.16409746394828442,
      "grad_norm": 1.1171875,
      "learning_rate": 8.2e-05,
      "loss": 8.3906,
      "mean_token_accuracy": 0.06560419239103794,
      "num_tokens": 328299.0,
      "step": 165
    },
    {
      "entropy": 8.962747955322266,
      "epoch": 0.16907011437095973,
      "grad_norm": 1.203125,
      "learning_rate": 8.450000000000001e-05,
      "loss": 8.4667,
      "mean_token_accuracy": 0.06214671768248081,
      "num_tokens": 338878.0,
      "step": 170
    },
    {
      "entropy": 8.892442321777343,
      "epoch": 0.174042764793635,
      "grad_norm": 1.4921875,
      "learning_rate": 8.7e-05,
      "loss": 8.3855,
      "mean_token_accuracy": 0.06676384881138801,
      "num_tokens": 348508.0,
      "step": 175
    },
    {
      "entropy": 8.82924509048462,
      "epoch": 0.1790154152163103,
      "grad_norm": 1.1796875,
      "learning_rate": 8.95e-05,
      "loss": 8.3408,
      "mean_token_accuracy": 0.06486317589879036,
      "num_tokens": 358233.0,
      "step": 180
    },
    {
      "entropy": 8.784028911590577,
      "epoch": 0.1839880656389856,
      "grad_norm": 1.3125,
      "learning_rate": 9.2e-05,
      "loss": 8.2883,
      "mean_token_accuracy": 0.06572877354919911,
      "num_tokens": 367297.0,
      "step": 185
    },
    {
      "entropy": 8.75277099609375,
      "epoch": 0.18896071606166087,
      "grad_norm": 1.109375,
      "learning_rate": 9.45e-05,
      "loss": 8.2958,
      "mean_token_accuracy": 0.06614930555224419,
      "num_tokens": 376880.0,
      "step": 190
    },
    {
      "entropy": 8.710809421539306,
      "epoch": 0.19393336648433615,
      "grad_norm": 1.25,
      "learning_rate": 9.7e-05,
      "loss": 8.2937,
      "mean_token_accuracy": 0.06907838135957718,
      "num_tokens": 386806.0,
      "step": 195
    },
    {
      "entropy": 8.63250789642334,
      "epoch": 0.19890601690701143,
      "grad_norm": 1.3671875,
      "learning_rate": 9.95e-05,
      "loss": 8.257,
      "mean_token_accuracy": 0.07009859867393971,
      "num_tokens": 396161.0,
      "step": 200
    },
    {
      "entropy": 8.667188930511475,
      "epoch": 0.20387866732968674,
      "grad_norm": 1.25,
      "learning_rate": 0.000102,
      "loss": 8.2966,
      "mean_token_accuracy": 0.0686015360057354,
      "num_tokens": 405643.0,
      "step": 205
    },
    {
      "entropy": 8.586182785034179,
      "epoch": 0.20885131775236201,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00010449999999999999,
      "loss": 8.249,
      "mean_token_accuracy": 0.07686658278107643,
      "num_tokens": 414367.0,
      "step": 210
    },
    {
      "entropy": 8.671557807922364,
      "epoch": 0.2138239681750373,
      "grad_norm": 1.2109375,
      "learning_rate": 0.000107,
      "loss": 8.3009,
      "mean_token_accuracy": 0.07021823003888131,
      "num_tokens": 424430.0,
      "step": 215
    },
    {
      "entropy": 8.60766077041626,
      "epoch": 0.21879661859771257,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001095,
      "loss": 8.2723,
      "mean_token_accuracy": 0.07040721997618675,
      "num_tokens": 435176.0,
      "step": 220
    },
    {
      "entropy": 8.483222579956054,
      "epoch": 0.22376926902038788,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000112,
      "loss": 8.2963,
      "mean_token_accuracy": 0.07160340994596481,
      "num_tokens": 445611.0,
      "step": 225
    },
    {
      "entropy": 8.615241146087646,
      "epoch": 0.22874191944306316,
      "grad_norm": 1.109375,
      "learning_rate": 0.0001145,
      "loss": 8.2193,
      "mean_token_accuracy": 0.07408608645200729,
      "num_tokens": 455143.0,
      "step": 230
    },
    {
      "entropy": 8.600674724578857,
      "epoch": 0.23371456986573844,
      "grad_norm": 1.796875,
      "learning_rate": 0.00011700000000000001,
      "loss": 8.2898,
      "mean_token_accuracy": 0.07503409050405026,
      "num_tokens": 465507.0,
      "step": 235
    },
    {
      "entropy": 8.539074230194093,
      "epoch": 0.23868722028841372,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00011949999999999999,
      "loss": 8.3078,
      "mean_token_accuracy": 0.0719807006418705,
      "num_tokens": 476152.0,
      "step": 240
    },
    {
      "entropy": 8.533562564849854,
      "epoch": 0.24365987071108902,
      "grad_norm": 0.98046875,
      "learning_rate": 0.000122,
      "loss": 8.1356,
      "mean_token_accuracy": 0.07810752168297767,
      "num_tokens": 486341.0,
      "step": 245
    },
    {
      "entropy": 8.470274734497071,
      "epoch": 0.2486325211337643,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0001245,
      "loss": 8.0909,
      "mean_token_accuracy": 0.07914422042667865,
      "num_tokens": 495915.0,
      "step": 250
    },
    {
      "entropy": 8.434992504119872,
      "epoch": 0.2536051715564396,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000127,
      "loss": 8.1795,
      "mean_token_accuracy": 0.07838663607835769,
      "num_tokens": 505666.0,
      "step": 255
    },
    {
      "entropy": 8.52521858215332,
      "epoch": 0.2585778219791149,
      "grad_norm": 1.234375,
      "learning_rate": 0.0001295,
      "loss": 8.0848,
      "mean_token_accuracy": 0.07590681686997414,
      "num_tokens": 515411.0,
      "step": 260
    },
    {
      "entropy": 8.440220355987549,
      "epoch": 0.26355047240179014,
      "grad_norm": 1.140625,
      "learning_rate": 0.000132,
      "loss": 8.1808,
      "mean_token_accuracy": 0.07005526758730411,
      "num_tokens": 525018.0,
      "step": 265
    },
    {
      "entropy": 8.485704612731933,
      "epoch": 0.26852312282446544,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00013450000000000002,
      "loss": 8.132,
      "mean_token_accuracy": 0.07571323961019516,
      "num_tokens": 535056.0,
      "step": 270
    },
    {
      "entropy": 8.444093799591064,
      "epoch": 0.27349577324714075,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00013700000000000002,
      "loss": 8.0943,
      "mean_token_accuracy": 0.07863550931215287,
      "num_tokens": 545115.0,
      "step": 275
    },
    {
      "entropy": 8.46326379776001,
      "epoch": 0.278468423669816,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0001395,
      "loss": 8.1362,
      "mean_token_accuracy": 0.07623238041996956,
      "num_tokens": 554429.0,
      "step": 280
    },
    {
      "entropy": 8.404027462005615,
      "epoch": 0.2834410740924913,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00014199999999999998,
      "loss": 8.0743,
      "mean_token_accuracy": 0.0847582258284092,
      "num_tokens": 563357.0,
      "step": 285
    },
    {
      "entropy": 8.44946584701538,
      "epoch": 0.28841372451516656,
      "grad_norm": 1.015625,
      "learning_rate": 0.0001445,
      "loss": 8.114,
      "mean_token_accuracy": 0.07873134687542915,
      "num_tokens": 574480.0,
      "step": 290
    },
    {
      "entropy": 8.350453853607178,
      "epoch": 0.29338637493784187,
      "grad_norm": 1.15625,
      "learning_rate": 0.000147,
      "loss": 8.1023,
      "mean_token_accuracy": 0.07694951295852662,
      "num_tokens": 583722.0,
      "step": 295
    },
    {
      "entropy": 8.420344829559326,
      "epoch": 0.29835902536051717,
      "grad_norm": 1.046875,
      "learning_rate": 0.0001495,
      "loss": 8.0479,
      "mean_token_accuracy": 0.08190468847751617,
      "num_tokens": 593644.0,
      "step": 300
    },
    {
      "entropy": 8.371365547180176,
      "epoch": 0.3033316757831924,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000152,
      "loss": 8.1017,
      "mean_token_accuracy": 0.07948060184717179,
      "num_tokens": 603547.0,
      "step": 305
    },
    {
      "entropy": 8.302706527709962,
      "epoch": 0.30830432620586773,
      "grad_norm": 1.109375,
      "learning_rate": 0.00015450000000000001,
      "loss": 8.1257,
      "mean_token_accuracy": 0.07789697460830211,
      "num_tokens": 613880.0,
      "step": 310
    },
    {
      "entropy": 8.415989398956299,
      "epoch": 0.31327697662854304,
      "grad_norm": 1.328125,
      "learning_rate": 0.000157,
      "loss": 8.0974,
      "mean_token_accuracy": 0.07658020406961441,
      "num_tokens": 624213.0,
      "step": 315
    },
    {
      "entropy": 8.416389560699463,
      "epoch": 0.3182496270512183,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0001595,
      "loss": 8.128,
      "mean_token_accuracy": 0.08172445297241211,
      "num_tokens": 634350.0,
      "step": 320
    },
    {
      "entropy": 8.42117624282837,
      "epoch": 0.3232222774738936,
      "grad_norm": 1.390625,
      "learning_rate": 0.000162,
      "loss": 8.1272,
      "mean_token_accuracy": 0.08092540055513382,
      "num_tokens": 644040.0,
      "step": 325
    },
    {
      "entropy": 8.33439235687256,
      "epoch": 0.32819492789656884,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00016450000000000001,
      "loss": 8.0773,
      "mean_token_accuracy": 0.0839149996638298,
      "num_tokens": 652915.0,
      "step": 330
    },
    {
      "entropy": 8.363460159301757,
      "epoch": 0.33316757831924415,
      "grad_norm": 1.015625,
      "learning_rate": 0.00016700000000000002,
      "loss": 8.0669,
      "mean_token_accuracy": 0.07783392369747162,
      "num_tokens": 662665.0,
      "step": 335
    },
    {
      "entropy": 8.326759719848633,
      "epoch": 0.33814022874191946,
      "grad_norm": 1.078125,
      "learning_rate": 0.00016950000000000003,
      "loss": 8.0773,
      "mean_token_accuracy": 0.08024705946445465,
      "num_tokens": 671667.0,
      "step": 340
    },
    {
      "entropy": 8.384268760681152,
      "epoch": 0.3431128791645947,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00017199999999999998,
      "loss": 8.0868,
      "mean_token_accuracy": 0.0760427363216877,
      "num_tokens": 680432.0,
      "step": 345
    },
    {
      "entropy": 8.345528602600098,
      "epoch": 0.34808552958727,
      "grad_norm": 1.171875,
      "learning_rate": 0.00017449999999999999,
      "loss": 8.0811,
      "mean_token_accuracy": 0.08016384020447731,
      "num_tokens": 690184.0,
      "step": 350
    },
    {
      "entropy": 8.333233165740968,
      "epoch": 0.3530581800099453,
      "grad_norm": 1.34375,
      "learning_rate": 0.000177,
      "loss": 7.9808,
      "mean_token_accuracy": 0.08433079347014427,
      "num_tokens": 699147.0,
      "step": 355
    },
    {
      "entropy": 8.210507869720459,
      "epoch": 0.3580308304326206,
      "grad_norm": 1.015625,
      "learning_rate": 0.0001795,
      "loss": 7.9962,
      "mean_token_accuracy": 0.08303841575980186,
      "num_tokens": 708696.0,
      "step": 360
    },
    {
      "entropy": 8.333552265167237,
      "epoch": 0.3630034808552959,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000182,
      "loss": 7.9812,
      "mean_token_accuracy": 0.08292912170290948,
      "num_tokens": 718438.0,
      "step": 365
    },
    {
      "entropy": 8.339497661590576,
      "epoch": 0.3679761312779712,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0001845,
      "loss": 8.1143,
      "mean_token_accuracy": 0.07707406133413315,
      "num_tokens": 728157.0,
      "step": 370
    },
    {
      "entropy": 8.221984767913819,
      "epoch": 0.37294878170064644,
      "grad_norm": 1.40625,
      "learning_rate": 0.000187,
      "loss": 8.0113,
      "mean_token_accuracy": 0.083165742456913,
      "num_tokens": 737007.0,
      "step": 375
    },
    {
      "entropy": 8.301848316192627,
      "epoch": 0.37792143212332174,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0001895,
      "loss": 7.9361,
      "mean_token_accuracy": 0.08524221666157246,
      "num_tokens": 746873.0,
      "step": 380
    },
    {
      "entropy": 8.174521112442017,
      "epoch": 0.382894082545997,
      "grad_norm": 1.109375,
      "learning_rate": 0.000192,
      "loss": 7.856,
      "mean_token_accuracy": 0.08981255739927292,
      "num_tokens": 755486.0,
      "step": 385
    },
    {
      "entropy": 8.252612590789795,
      "epoch": 0.3878667329686723,
      "grad_norm": 1.2109375,
      "learning_rate": 0.0001945,
      "loss": 7.9822,
      "mean_token_accuracy": 0.07825585678219796,
      "num_tokens": 765481.0,
      "step": 390
    },
    {
      "entropy": 8.236901569366456,
      "epoch": 0.3928393833913476,
      "grad_norm": 1.328125,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.937,
      "mean_token_accuracy": 0.08628773540258408,
      "num_tokens": 774335.0,
      "step": 395
    },
    {
      "entropy": 8.332719326019287,
      "epoch": 0.39781203381402286,
      "grad_norm": 1.296875,
      "learning_rate": 0.00019950000000000002,
      "loss": 8.0001,
      "mean_token_accuracy": 0.08222218602895737,
      "num_tokens": 784307.0,
      "step": 400
    },
    {
      "entropy": 8.230411338806153,
      "epoch": 0.40278468423669817,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000202,
      "loss": 8.0406,
      "mean_token_accuracy": 0.07930415198206901,
      "num_tokens": 795058.0,
      "step": 405
    },
    {
      "entropy": 8.313278293609619,
      "epoch": 0.40775733465937347,
      "grad_norm": 1.703125,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.9507,
      "mean_token_accuracy": 0.08477597758173942,
      "num_tokens": 805687.0,
      "step": 410
    },
    {
      "entropy": 8.19376473426819,
      "epoch": 0.4127299850820487,
      "grad_norm": 1.1875,
      "learning_rate": 0.000207,
      "loss": 7.989,
      "mean_token_accuracy": 0.08413419276475906,
      "num_tokens": 815138.0,
      "step": 415
    },
    {
      "entropy": 8.226968097686768,
      "epoch": 0.41770263550472403,
      "grad_norm": 1.3125,
      "learning_rate": 0.0002095,
      "loss": 7.9451,
      "mean_token_accuracy": 0.08170225620269775,
      "num_tokens": 825009.0,
      "step": 420
    },
    {
      "entropy": 8.161935615539551,
      "epoch": 0.4226752859273993,
      "grad_norm": 1.21875,
      "learning_rate": 0.000212,
      "loss": 7.9202,
      "mean_token_accuracy": 0.0900972880423069,
      "num_tokens": 834708.0,
      "step": 425
    },
    {
      "entropy": 8.352538585662842,
      "epoch": 0.4276479363500746,
      "grad_norm": 1.296875,
      "learning_rate": 0.0002145,
      "loss": 7.9872,
      "mean_token_accuracy": 0.08343984819948673,
      "num_tokens": 843888.0,
      "step": 430
    },
    {
      "entropy": 8.144132709503173,
      "epoch": 0.4326205867727499,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.9481,
      "mean_token_accuracy": 0.08321668803691865,
      "num_tokens": 853057.0,
      "step": 435
    },
    {
      "entropy": 8.240882396697998,
      "epoch": 0.43759323719542514,
      "grad_norm": 1.359375,
      "learning_rate": 0.0002195,
      "loss": 8.0054,
      "mean_token_accuracy": 0.07688518613576889,
      "num_tokens": 862701.0,
      "step": 440
    },
    {
      "entropy": 8.124331283569337,
      "epoch": 0.44256588761810045,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000222,
      "loss": 7.8978,
      "mean_token_accuracy": 0.0850852258503437,
      "num_tokens": 872129.0,
      "step": 445
    },
    {
      "entropy": 8.162071371078492,
      "epoch": 0.44753853804077576,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0002245,
      "loss": 7.9163,
      "mean_token_accuracy": 0.08625531122088433,
      "num_tokens": 883166.0,
      "step": 450
    },
    {
      "entropy": 8.160173559188843,
      "epoch": 0.452511188463451,
      "grad_norm": 1.2890625,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.7103,
      "mean_token_accuracy": 0.10269899219274521,
      "num_tokens": 894159.0,
      "step": 455
    },
    {
      "entropy": 8.14470615386963,
      "epoch": 0.4574838388861263,
      "grad_norm": 1.046875,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.9094,
      "mean_token_accuracy": 0.08693445995450019,
      "num_tokens": 904588.0,
      "step": 460
    },
    {
      "entropy": 8.188994216918946,
      "epoch": 0.46245648930880157,
      "grad_norm": 1.34375,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.8764,
      "mean_token_accuracy": 0.08472439050674438,
      "num_tokens": 915554.0,
      "step": 465
    },
    {
      "entropy": 8.080974769592284,
      "epoch": 0.4674291397314769,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.9153,
      "mean_token_accuracy": 0.08615779727697373,
      "num_tokens": 925546.0,
      "step": 470
    },
    {
      "entropy": 8.106526470184326,
      "epoch": 0.4724017901541522,
      "grad_norm": 1.234375,
      "learning_rate": 0.000237,
      "loss": 7.8827,
      "mean_token_accuracy": 0.08863506764173508,
      "num_tokens": 936615.0,
      "step": 475
    },
    {
      "entropy": 8.171993637084961,
      "epoch": 0.47737444057682743,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0002395,
      "loss": 7.9148,
      "mean_token_accuracy": 0.08405414745211601,
      "num_tokens": 947374.0,
      "step": 480
    },
    {
      "entropy": 8.07227544784546,
      "epoch": 0.48234709099950274,
      "grad_norm": 0.9765625,
      "learning_rate": 0.000242,
      "loss": 7.8263,
      "mean_token_accuracy": 0.0881466455757618,
      "num_tokens": 957772.0,
      "step": 485
    },
    {
      "entropy": 8.149549674987792,
      "epoch": 0.48731974142217804,
      "grad_norm": 1.1875,
      "learning_rate": 0.0002445,
      "loss": 7.9265,
      "mean_token_accuracy": 0.08613847866654396,
      "num_tokens": 967724.0,
      "step": 490
    },
    {
      "entropy": 8.014617347717286,
      "epoch": 0.4922923918448533,
      "grad_norm": 1.21875,
      "learning_rate": 0.000247,
      "loss": 7.821,
      "mean_token_accuracy": 0.08873307779431343,
      "num_tokens": 976497.0,
      "step": 495
    },
    {
      "entropy": 8.061779451370239,
      "epoch": 0.4972650422675286,
      "grad_norm": 1.203125,
      "learning_rate": 0.0002495,
      "loss": 7.8061,
      "mean_token_accuracy": 0.08952893353998662,
      "num_tokens": 986207.0,
      "step": 500
    },
    {
      "epoch": 0.4972650422675286,
      "eval_entropy": 8.12199338789909,
      "eval_loss": 7.925317764282227,
      "eval_mean_token_accuracy": 0.0847069110511051,
      "eval_num_tokens": 986207.0,
      "eval_runtime": 11.3595,
      "eval_samples_per_second": 305.031,
      "eval_steps_per_second": 38.206,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 10050,
  "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": 1606088632320000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}