{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029055408664322865,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.742584228515625,
      "epoch": 0.0002905540866432286,
      "grad_norm": 4.90625,
      "learning_rate": 2e-06,
      "loss": 10.7837,
      "mean_token_accuracy": 0.0,
      "num_tokens": 10156.0,
      "step": 5
    },
    {
      "entropy": 10.742587471008301,
      "epoch": 0.0005811081732864572,
      "grad_norm": 4.8125,
      "learning_rate": 4.5e-06,
      "loss": 10.7753,
      "mean_token_accuracy": 9.267840650863945e-05,
      "num_tokens": 20933.0,
      "step": 10
    },
    {
      "entropy": 10.74257869720459,
      "epoch": 0.0008716622599296859,
      "grad_norm": 4.375,
      "learning_rate": 7e-06,
      "loss": 10.7508,
      "mean_token_accuracy": 0.0,
      "num_tokens": 31298.0,
      "step": 15
    },
    {
      "entropy": 10.742635726928711,
      "epoch": 0.0011622163465729145,
      "grad_norm": 4.875,
      "learning_rate": 9.5e-06,
      "loss": 10.697,
      "mean_token_accuracy": 0.0,
      "num_tokens": 40913.0,
      "step": 20
    },
    {
      "entropy": 10.742652702331544,
      "epoch": 0.0014527704332161432,
      "grad_norm": 4.28125,
      "learning_rate": 1.2e-05,
      "loss": 10.5798,
      "mean_token_accuracy": 0.0007269373920280487,
      "num_tokens": 49901.0,
      "step": 25
    },
    {
      "entropy": 10.742454719543456,
      "epoch": 0.0017433245198593718,
      "grad_norm": 4.0625,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.4688,
      "mean_token_accuracy": 0.01560134175233543,
      "num_tokens": 59328.0,
      "step": 30
    },
    {
      "entropy": 10.741775226593017,
      "epoch": 0.0020338786065026006,
      "grad_norm": 3.25,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.3287,
      "mean_token_accuracy": 0.037073963694274424,
      "num_tokens": 68405.0,
      "step": 35
    },
    {
      "entropy": 10.740037631988525,
      "epoch": 0.002324432693145829,
      "grad_norm": 2.578125,
      "learning_rate": 1.95e-05,
      "loss": 10.2203,
      "mean_token_accuracy": 0.037133642472326756,
      "num_tokens": 77591.0,
      "step": 40
    },
    {
      "entropy": 10.73731575012207,
      "epoch": 0.0026149867797890577,
      "grad_norm": 2.359375,
      "learning_rate": 2.2e-05,
      "loss": 10.1202,
      "mean_token_accuracy": 0.03901108838617802,
      "num_tokens": 88186.0,
      "step": 45
    },
    {
      "entropy": 10.734606838226318,
      "epoch": 0.0029055408664322865,
      "grad_norm": 2.09375,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 10.0211,
      "mean_token_accuracy": 0.04241710864007473,
      "num_tokens": 97594.0,
      "step": 50
    },
    {
      "entropy": 10.73211612701416,
      "epoch": 0.003196094953075515,
      "grad_norm": 1.9921875,
      "learning_rate": 2.7e-05,
      "loss": 9.9871,
      "mean_token_accuracy": 0.03826836366206408,
      "num_tokens": 107386.0,
      "step": 55
    },
    {
      "entropy": 10.73102445602417,
      "epoch": 0.0034866490397187436,
      "grad_norm": 1.9140625,
      "learning_rate": 2.95e-05,
      "loss": 9.9132,
      "mean_token_accuracy": 0.03943221494555473,
      "num_tokens": 116742.0,
      "step": 60
    },
    {
      "entropy": 10.729645252227783,
      "epoch": 0.0037772031263619723,
      "grad_norm": 1.859375,
      "learning_rate": 3.2e-05,
      "loss": 9.8519,
      "mean_token_accuracy": 0.03962419871240854,
      "num_tokens": 126520.0,
      "step": 65
    },
    {
      "entropy": 10.727834033966065,
      "epoch": 0.004067757213005201,
      "grad_norm": 1.7734375,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.7907,
      "mean_token_accuracy": 0.03989919070154428,
      "num_tokens": 136382.0,
      "step": 70
    },
    {
      "entropy": 10.724947452545166,
      "epoch": 0.0043583112996484295,
      "grad_norm": 1.7421875,
      "learning_rate": 3.7e-05,
      "loss": 9.7212,
      "mean_token_accuracy": 0.03671109899878502,
      "num_tokens": 146435.0,
      "step": 75
    },
    {
      "entropy": 10.72182493209839,
      "epoch": 0.004648865386291658,
      "grad_norm": 1.8359375,
      "learning_rate": 3.95e-05,
      "loss": 9.6591,
      "mean_token_accuracy": 0.037667426839470865,
      "num_tokens": 156174.0,
      "step": 80
    },
    {
      "entropy": 10.71723222732544,
      "epoch": 0.004939419472934887,
      "grad_norm": 1.765625,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.5783,
      "mean_token_accuracy": 0.04142397493124008,
      "num_tokens": 165118.0,
      "step": 85
    },
    {
      "entropy": 10.708585739135742,
      "epoch": 0.005229973559578115,
      "grad_norm": 1.875,
      "learning_rate": 4.45e-05,
      "loss": 9.5252,
      "mean_token_accuracy": 0.04036426953971386,
      "num_tokens": 174401.0,
      "step": 90
    },
    {
      "entropy": 10.697160243988037,
      "epoch": 0.005520527646221344,
      "grad_norm": 1.765625,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.443,
      "mean_token_accuracy": 0.04118307866156101,
      "num_tokens": 183533.0,
      "step": 95
    },
    {
      "entropy": 10.683875274658202,
      "epoch": 0.005811081732864573,
      "grad_norm": 1.7734375,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.3596,
      "mean_token_accuracy": 0.045602331310510634,
      "num_tokens": 193296.0,
      "step": 100
    },
    {
      "entropy": 10.665638542175293,
      "epoch": 0.006101635819507801,
      "grad_norm": 1.75,
      "learning_rate": 5.2e-05,
      "loss": 9.2242,
      "mean_token_accuracy": 0.055989645794034,
      "num_tokens": 202741.0,
      "step": 105
    },
    {
      "entropy": 10.637047958374023,
      "epoch": 0.00639218990615103,
      "grad_norm": 1.703125,
      "learning_rate": 5.45e-05,
      "loss": 9.1359,
      "mean_token_accuracy": 0.05134495124220848,
      "num_tokens": 212441.0,
      "step": 110
    },
    {
      "entropy": 10.61000461578369,
      "epoch": 0.006682743992794259,
      "grad_norm": 1.6875,
      "learning_rate": 5.7e-05,
      "loss": 8.9868,
      "mean_token_accuracy": 0.04918566383421421,
      "num_tokens": 220671.0,
      "step": 115
    },
    {
      "entropy": 10.56931962966919,
      "epoch": 0.006973298079437487,
      "grad_norm": 1.7578125,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.9878,
      "mean_token_accuracy": 0.04560479037463665,
      "num_tokens": 231390.0,
      "step": 120
    },
    {
      "entropy": 10.515452098846435,
      "epoch": 0.007263852166080716,
      "grad_norm": 1.5859375,
      "learning_rate": 6.2e-05,
      "loss": 8.8241,
      "mean_token_accuracy": 0.05023673102259636,
      "num_tokens": 241137.0,
      "step": 125
    },
    {
      "entropy": 10.430156230926514,
      "epoch": 0.007554406252723945,
      "grad_norm": 1.578125,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.6778,
      "mean_token_accuracy": 0.05138532817363739,
      "num_tokens": 250627.0,
      "step": 130
    },
    {
      "entropy": 10.353140926361084,
      "epoch": 0.007844960339367173,
      "grad_norm": 1.5859375,
      "learning_rate": 6.7e-05,
      "loss": 8.5255,
      "mean_token_accuracy": 0.05529710613191128,
      "num_tokens": 259564.0,
      "step": 135
    },
    {
      "entropy": 10.262280082702636,
      "epoch": 0.008135514426010402,
      "grad_norm": 1.453125,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.4168,
      "mean_token_accuracy": 0.05102897398173809,
      "num_tokens": 268997.0,
      "step": 140
    },
    {
      "entropy": 10.17268762588501,
      "epoch": 0.00842606851265363,
      "grad_norm": 1.40625,
      "learning_rate": 7.2e-05,
      "loss": 8.402,
      "mean_token_accuracy": 0.04707291163504124,
      "num_tokens": 278989.0,
      "step": 145
    },
    {
      "entropy": 10.068906784057617,
      "epoch": 0.008716622599296859,
      "grad_norm": 1.3828125,
      "learning_rate": 7.45e-05,
      "loss": 8.2195,
      "mean_token_accuracy": 0.04823922924697399,
      "num_tokens": 288770.0,
      "step": 150
    },
    {
      "entropy": 9.884156227111816,
      "epoch": 0.009007176685940088,
      "grad_norm": 1.234375,
      "learning_rate": 7.7e-05,
      "loss": 8.1604,
      "mean_token_accuracy": 0.05296766012907028,
      "num_tokens": 298368.0,
      "step": 155
    },
    {
      "entropy": 9.749515438079834,
      "epoch": 0.009297730772583316,
      "grad_norm": 1.125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.9887,
      "mean_token_accuracy": 0.054083061218261716,
      "num_tokens": 307437.0,
      "step": 160
    },
    {
      "entropy": 9.539670753479005,
      "epoch": 0.009588284859226545,
      "grad_norm": 1.3828125,
      "learning_rate": 8.2e-05,
      "loss": 7.931,
      "mean_token_accuracy": 0.05368399284780025,
      "num_tokens": 317842.0,
      "step": 165
    },
    {
      "entropy": 9.367785167694091,
      "epoch": 0.009878838945869774,
      "grad_norm": 0.984375,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.7746,
      "mean_token_accuracy": 0.056211471930146216,
      "num_tokens": 327455.0,
      "step": 170
    },
    {
      "entropy": 9.106531143188477,
      "epoch": 0.010169393032513002,
      "grad_norm": 0.96484375,
      "learning_rate": 8.7e-05,
      "loss": 7.7023,
      "mean_token_accuracy": 0.059121083468198776,
      "num_tokens": 338593.0,
      "step": 175
    },
    {
      "entropy": 8.891216564178468,
      "epoch": 0.01045994711915623,
      "grad_norm": 1.0,
      "learning_rate": 8.95e-05,
      "loss": 7.6717,
      "mean_token_accuracy": 0.060001150518655774,
      "num_tokens": 348278.0,
      "step": 180
    },
    {
      "entropy": 8.690237522125244,
      "epoch": 0.01075050120579946,
      "grad_norm": 0.91796875,
      "learning_rate": 9.2e-05,
      "loss": 7.5848,
      "mean_token_accuracy": 0.060652027279138564,
      "num_tokens": 358293.0,
      "step": 185
    },
    {
      "entropy": 8.500970458984375,
      "epoch": 0.011041055292442687,
      "grad_norm": 0.70703125,
      "learning_rate": 9.45e-05,
      "loss": 7.6462,
      "mean_token_accuracy": 0.06345079019665718,
      "num_tokens": 368177.0,
      "step": 190
    },
    {
      "entropy": 8.432841682434082,
      "epoch": 0.011331609379085917,
      "grad_norm": 0.87890625,
      "learning_rate": 9.7e-05,
      "loss": 7.5041,
      "mean_token_accuracy": 0.06438801400363445,
      "num_tokens": 377258.0,
      "step": 195
    },
    {
      "entropy": 8.328762531280518,
      "epoch": 0.011622163465729146,
      "grad_norm": 0.79296875,
      "learning_rate": 9.95e-05,
      "loss": 7.515,
      "mean_token_accuracy": 0.06462946832180023,
      "num_tokens": 385931.0,
      "step": 200
    },
    {
      "entropy": 8.228355598449706,
      "epoch": 0.011912717552372373,
      "grad_norm": 0.984375,
      "learning_rate": 0.000102,
      "loss": 7.4262,
      "mean_token_accuracy": 0.06731356121599674,
      "num_tokens": 394370.0,
      "step": 205
    },
    {
      "entropy": 8.163572025299072,
      "epoch": 0.012203271639015602,
      "grad_norm": 0.765625,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.5127,
      "mean_token_accuracy": 0.06187250129878521,
      "num_tokens": 405167.0,
      "step": 210
    },
    {
      "entropy": 8.144425964355468,
      "epoch": 0.012493825725658832,
      "grad_norm": 0.90234375,
      "learning_rate": 0.000107,
      "loss": 7.4823,
      "mean_token_accuracy": 0.06424942426383495,
      "num_tokens": 414954.0,
      "step": 215
    },
    {
      "entropy": 8.074434852600097,
      "epoch": 0.01278437981230206,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0001095,
      "loss": 7.4379,
      "mean_token_accuracy": 0.07021872885525227,
      "num_tokens": 423806.0,
      "step": 220
    },
    {
      "entropy": 8.100719451904297,
      "epoch": 0.013074933898945288,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000112,
      "loss": 7.4049,
      "mean_token_accuracy": 0.07006631046533585,
      "num_tokens": 433416.0,
      "step": 225
    },
    {
      "entropy": 8.068440341949463,
      "epoch": 0.013365487985588518,
      "grad_norm": 1.015625,
      "learning_rate": 0.0001145,
      "loss": 7.4086,
      "mean_token_accuracy": 0.0656484205275774,
      "num_tokens": 443237.0,
      "step": 230
    },
    {
      "entropy": 8.008077144622803,
      "epoch": 0.013656042072231747,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.3811,
      "mean_token_accuracy": 0.07138268202543259,
      "num_tokens": 452334.0,
      "step": 235
    },
    {
      "entropy": 7.95733003616333,
      "epoch": 0.013946596158874974,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.451,
      "mean_token_accuracy": 0.07069577798247337,
      "num_tokens": 462604.0,
      "step": 240
    },
    {
      "entropy": 7.985943031311035,
      "epoch": 0.014237150245518203,
      "grad_norm": 1.109375,
      "learning_rate": 0.000122,
      "loss": 7.3342,
      "mean_token_accuracy": 0.07418472990393639,
      "num_tokens": 472105.0,
      "step": 245
    },
    {
      "entropy": 7.985353708267212,
      "epoch": 0.014527704332161433,
      "grad_norm": 0.89453125,
      "learning_rate": 0.0001245,
      "loss": 7.3573,
      "mean_token_accuracy": 0.07192124761641025,
      "num_tokens": 481873.0,
      "step": 250
    },
    {
      "entropy": 7.852858924865723,
      "epoch": 0.01481825841880466,
      "grad_norm": 0.9140625,
      "learning_rate": 0.000127,
      "loss": 7.3134,
      "mean_token_accuracy": 0.07094009146094322,
      "num_tokens": 490776.0,
      "step": 255
    },
    {
      "entropy": 7.97090711593628,
      "epoch": 0.01510881250544789,
      "grad_norm": 0.97265625,
      "learning_rate": 0.0001295,
      "loss": 7.3459,
      "mean_token_accuracy": 0.06945950090885163,
      "num_tokens": 500237.0,
      "step": 260
    },
    {
      "entropy": 7.988322401046753,
      "epoch": 0.015399366592091119,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000132,
      "loss": 7.3569,
      "mean_token_accuracy": 0.0719369538128376,
      "num_tokens": 509449.0,
      "step": 265
    },
    {
      "entropy": 7.863973140716553,
      "epoch": 0.015689920678734346,
      "grad_norm": 0.9296875,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.3463,
      "mean_token_accuracy": 0.07629362866282463,
      "num_tokens": 519335.0,
      "step": 270
    },
    {
      "entropy": 7.850080347061157,
      "epoch": 0.015980474765377575,
      "grad_norm": 0.828125,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.269,
      "mean_token_accuracy": 0.07348301075398922,
      "num_tokens": 529108.0,
      "step": 275
    },
    {
      "entropy": 7.803001642227173,
      "epoch": 0.016271028852020804,
      "grad_norm": 0.9609375,
      "learning_rate": 0.0001395,
      "loss": 7.3421,
      "mean_token_accuracy": 0.07442944496870041,
      "num_tokens": 539409.0,
      "step": 280
    },
    {
      "entropy": 7.8401947021484375,
      "epoch": 0.016561582938664034,
      "grad_norm": 0.98828125,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.269,
      "mean_token_accuracy": 0.07476447969675064,
      "num_tokens": 549790.0,
      "step": 285
    },
    {
      "entropy": 7.773062610626221,
      "epoch": 0.01685213702530726,
      "grad_norm": 0.90234375,
      "learning_rate": 0.0001445,
      "loss": 7.2597,
      "mean_token_accuracy": 0.07743276208639145,
      "num_tokens": 559343.0,
      "step": 290
    },
    {
      "entropy": 7.833370351791382,
      "epoch": 0.01714269111195049,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000147,
      "loss": 7.306,
      "mean_token_accuracy": 0.07507650516927242,
      "num_tokens": 568806.0,
      "step": 295
    },
    {
      "entropy": 7.692620134353637,
      "epoch": 0.017433245198593718,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0001495,
      "loss": 7.1532,
      "mean_token_accuracy": 0.07671754881739616,
      "num_tokens": 578988.0,
      "step": 300
    },
    {
      "entropy": 7.840510559082031,
      "epoch": 0.017723799285236947,
      "grad_norm": 1.015625,
      "learning_rate": 0.000152,
      "loss": 7.258,
      "mean_token_accuracy": 0.0767325557768345,
      "num_tokens": 588588.0,
      "step": 305
    },
    {
      "entropy": 7.740892934799194,
      "epoch": 0.018014353371880176,
      "grad_norm": 0.9453125,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.2385,
      "mean_token_accuracy": 0.07767370343208313,
      "num_tokens": 597957.0,
      "step": 310
    },
    {
      "entropy": 7.761815309524536,
      "epoch": 0.018304907458523405,
      "grad_norm": 0.8671875,
      "learning_rate": 0.000157,
      "loss": 7.2168,
      "mean_token_accuracy": 0.07732245922088624,
      "num_tokens": 607446.0,
      "step": 315
    },
    {
      "entropy": 7.723113679885865,
      "epoch": 0.01859546154516663,
      "grad_norm": 0.8359375,
      "learning_rate": 0.0001595,
      "loss": 7.1559,
      "mean_token_accuracy": 0.07753840312361718,
      "num_tokens": 617064.0,
      "step": 320
    },
    {
      "entropy": 7.695508337020874,
      "epoch": 0.01888601563180986,
      "grad_norm": 1.03125,
      "learning_rate": 0.000162,
      "loss": 7.2008,
      "mean_token_accuracy": 0.08057244047522545,
      "num_tokens": 625927.0,
      "step": 325
    },
    {
      "entropy": 7.717827177047729,
      "epoch": 0.01917656971845309,
      "grad_norm": 0.97265625,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.1152,
      "mean_token_accuracy": 0.07994545996189117,
      "num_tokens": 635341.0,
      "step": 330
    },
    {
      "entropy": 7.675025224685669,
      "epoch": 0.01946712380509632,
      "grad_norm": 2.171875,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.1106,
      "mean_token_accuracy": 0.08988085016608238,
      "num_tokens": 645095.0,
      "step": 335
    },
    {
      "entropy": 7.714554166793823,
      "epoch": 0.019757677891739548,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.1558,
      "mean_token_accuracy": 0.0730321068316698,
      "num_tokens": 654754.0,
      "step": 340
    },
    {
      "entropy": 7.60111026763916,
      "epoch": 0.020048231978382777,
      "grad_norm": 0.8671875,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.1266,
      "mean_token_accuracy": 0.07690966166555882,
      "num_tokens": 664589.0,
      "step": 345
    },
    {
      "entropy": 7.6628223896026615,
      "epoch": 0.020338786065026003,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.1425,
      "mean_token_accuracy": 0.07918459475040436,
      "num_tokens": 673870.0,
      "step": 350
    },
    {
      "entropy": 7.577814197540283,
      "epoch": 0.020629340151669232,
      "grad_norm": 1.03125,
      "learning_rate": 0.000177,
      "loss": 7.1137,
      "mean_token_accuracy": 0.07997918874025345,
      "num_tokens": 684309.0,
      "step": 355
    },
    {
      "entropy": 7.6769345760345455,
      "epoch": 0.02091989423831246,
      "grad_norm": 1.359375,
      "learning_rate": 0.0001795,
      "loss": 7.1629,
      "mean_token_accuracy": 0.07469077445566655,
      "num_tokens": 693702.0,
      "step": 360
    },
    {
      "entropy": 7.534895896911621,
      "epoch": 0.02121044832495569,
      "grad_norm": 0.94140625,
      "learning_rate": 0.000182,
      "loss": 7.0599,
      "mean_token_accuracy": 0.07970957532525062,
      "num_tokens": 702951.0,
      "step": 365
    },
    {
      "entropy": 7.588031339645386,
      "epoch": 0.02150100241159892,
      "grad_norm": 1.25,
      "learning_rate": 0.0001845,
      "loss": 7.0677,
      "mean_token_accuracy": 0.08218754455447197,
      "num_tokens": 712481.0,
      "step": 370
    },
    {
      "entropy": 7.600922870635986,
      "epoch": 0.02179155649824215,
      "grad_norm": 1.046875,
      "learning_rate": 0.000187,
      "loss": 7.0683,
      "mean_token_accuracy": 0.08380770459771156,
      "num_tokens": 721579.0,
      "step": 375
    },
    {
      "entropy": 7.572713327407837,
      "epoch": 0.022082110584885375,
      "grad_norm": 1.03125,
      "learning_rate": 0.0001895,
      "loss": 7.0774,
      "mean_token_accuracy": 0.07982454895973205,
      "num_tokens": 731404.0,
      "step": 380
    },
    {
      "entropy": 7.548839807510376,
      "epoch": 0.022372664671528604,
      "grad_norm": 0.93359375,
      "learning_rate": 0.000192,
      "loss": 7.0556,
      "mean_token_accuracy": 0.07496214136481286,
      "num_tokens": 740751.0,
      "step": 385
    },
    {
      "entropy": 7.523876476287842,
      "epoch": 0.022663218758171833,
      "grad_norm": 0.9765625,
      "learning_rate": 0.0001945,
      "loss": 7.0247,
      "mean_token_accuracy": 0.08082472011446953,
      "num_tokens": 751171.0,
      "step": 390
    },
    {
      "entropy": 7.552808237075806,
      "epoch": 0.022953772844815062,
      "grad_norm": 1.078125,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.0823,
      "mean_token_accuracy": 0.07615064568817616,
      "num_tokens": 760874.0,
      "step": 395
    },
    {
      "entropy": 7.583486127853393,
      "epoch": 0.02324432693145829,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.0585,
      "mean_token_accuracy": 0.08326990716159344,
      "num_tokens": 769652.0,
      "step": 400
    },
    {
      "entropy": 7.488273334503174,
      "epoch": 0.02353488101810152,
      "grad_norm": 0.98828125,
      "learning_rate": 0.000202,
      "loss": 7.0421,
      "mean_token_accuracy": 0.07620194889605045,
      "num_tokens": 779591.0,
      "step": 405
    },
    {
      "entropy": 7.564187002182007,
      "epoch": 0.023825435104744747,
      "grad_norm": 0.94921875,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.156,
      "mean_token_accuracy": 0.08098742663860321,
      "num_tokens": 789582.0,
      "step": 410
    },
    {
      "entropy": 7.506245565414429,
      "epoch": 0.024115989191387976,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000207,
      "loss": 7.0546,
      "mean_token_accuracy": 0.07765479311347008,
      "num_tokens": 799146.0,
      "step": 415
    },
    {
      "entropy": 7.4926127910614015,
      "epoch": 0.024406543278031205,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0002095,
      "loss": 7.0246,
      "mean_token_accuracy": 0.0782523088157177,
      "num_tokens": 808934.0,
      "step": 420
    },
    {
      "entropy": 7.532363748550415,
      "epoch": 0.024697097364674434,
      "grad_norm": 0.87109375,
      "learning_rate": 0.000212,
      "loss": 7.0821,
      "mean_token_accuracy": 0.07597277015447616,
      "num_tokens": 819280.0,
      "step": 425
    },
    {
      "entropy": 7.457432746887207,
      "epoch": 0.024987651451317663,
      "grad_norm": 0.97265625,
      "learning_rate": 0.0002145,
      "loss": 6.9892,
      "mean_token_accuracy": 0.0840725652873516,
      "num_tokens": 828818.0,
      "step": 430
    },
    {
      "entropy": 7.463752698898316,
      "epoch": 0.025278205537960893,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.9816,
      "mean_token_accuracy": 0.08661384396255016,
      "num_tokens": 839175.0,
      "step": 435
    },
    {
      "entropy": 7.5449175357818605,
      "epoch": 0.02556875962460412,
      "grad_norm": 1.125,
      "learning_rate": 0.0002195,
      "loss": 7.0777,
      "mean_token_accuracy": 0.07947314418852329,
      "num_tokens": 849965.0,
      "step": 440
    },
    {
      "entropy": 7.392349624633789,
      "epoch": 0.025859313711247348,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000222,
      "loss": 6.9968,
      "mean_token_accuracy": 0.08229465186595916,
      "num_tokens": 859229.0,
      "step": 445
    },
    {
      "entropy": 7.4397971630096436,
      "epoch": 0.026149867797890577,
      "grad_norm": 1.28125,
      "learning_rate": 0.0002245,
      "loss": 6.9708,
      "mean_token_accuracy": 0.0816520519554615,
      "num_tokens": 869199.0,
      "step": 450
    },
    {
      "entropy": 7.399962043762207,
      "epoch": 0.026440421884533806,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.9666,
      "mean_token_accuracy": 0.09285714998841285,
      "num_tokens": 879470.0,
      "step": 455
    },
    {
      "entropy": 7.4366514682769775,
      "epoch": 0.026730975971177035,
      "grad_norm": 0.921875,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.9274,
      "mean_token_accuracy": 0.0792453158646822,
      "num_tokens": 888397.0,
      "step": 460
    },
    {
      "entropy": 7.370485734939575,
      "epoch": 0.027021530057820264,
      "grad_norm": 0.953125,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.8202,
      "mean_token_accuracy": 0.0855403620749712,
      "num_tokens": 898321.0,
      "step": 465
    },
    {
      "entropy": 7.4845947265625,
      "epoch": 0.027312084144463494,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.0856,
      "mean_token_accuracy": 0.0808610200881958,
      "num_tokens": 907947.0,
      "step": 470
    },
    {
      "entropy": 7.327203702926636,
      "epoch": 0.02760263823110672,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000237,
      "loss": 6.9103,
      "mean_token_accuracy": 0.0954340323805809,
      "num_tokens": 916842.0,
      "step": 475
    },
    {
      "entropy": 7.380954456329346,
      "epoch": 0.02789319231774995,
      "grad_norm": 1.046875,
      "learning_rate": 0.0002395,
      "loss": 7.0098,
      "mean_token_accuracy": 0.08165798112750053,
      "num_tokens": 926431.0,
      "step": 480
    },
    {
      "entropy": 7.412681722640992,
      "epoch": 0.028183746404393178,
      "grad_norm": 0.98828125,
      "learning_rate": 0.000242,
      "loss": 6.9162,
      "mean_token_accuracy": 0.08133741281926632,
      "num_tokens": 935819.0,
      "step": 485
    },
    {
      "entropy": 7.44426212310791,
      "epoch": 0.028474300491036407,
      "grad_norm": 1.15625,
      "learning_rate": 0.0002445,
      "loss": 6.9418,
      "mean_token_accuracy": 0.08402741849422454,
      "num_tokens": 944198.0,
      "step": 490
    },
    {
      "entropy": 7.264917373657227,
      "epoch": 0.028764854577679636,
      "grad_norm": 0.88671875,
      "learning_rate": 0.000247,
      "loss": 6.9628,
      "mean_token_accuracy": 0.08352083042263984,
      "num_tokens": 954972.0,
      "step": 495
    },
    {
      "entropy": 7.385922384262085,
      "epoch": 0.029055408664322865,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0002495,
      "loss": 6.9018,
      "mean_token_accuracy": 0.08520250022411346,
      "num_tokens": 964532.0,
      "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": 210168601804800.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}