{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.45433893684688775,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.742555522918702,
      "epoch": 0.004543389368468878,
      "grad_norm": 5.0625,
      "learning_rate": 2e-06,
      "loss": 10.7779,
      "mean_token_accuracy": 8.431703317910433e-05,
      "num_tokens": 10156.0,
      "step": 5
    },
    {
      "entropy": 10.742563724517822,
      "epoch": 0.009086778736937756,
      "grad_norm": 5.25,
      "learning_rate": 4.5e-06,
      "loss": 10.7654,
      "mean_token_accuracy": 0.0,
      "num_tokens": 20669.0,
      "step": 10
    },
    {
      "entropy": 10.74255313873291,
      "epoch": 0.013630168105406633,
      "grad_norm": 4.9375,
      "learning_rate": 7e-06,
      "loss": 10.7397,
      "mean_token_accuracy": 0.0,
      "num_tokens": 30952.0,
      "step": 15
    },
    {
      "entropy": 10.742581939697265,
      "epoch": 0.01817355747387551,
      "grad_norm": 5.40625,
      "learning_rate": 9.5e-06,
      "loss": 10.6785,
      "mean_token_accuracy": 0.0005094278021715581,
      "num_tokens": 41429.0,
      "step": 20
    },
    {
      "entropy": 10.742574501037598,
      "epoch": 0.02271694684234439,
      "grad_norm": 4.90625,
      "learning_rate": 1.2e-05,
      "loss": 10.585,
      "mean_token_accuracy": 0.004951991699635982,
      "num_tokens": 52166.0,
      "step": 25
    },
    {
      "entropy": 10.742272472381591,
      "epoch": 0.027260336210813266,
      "grad_norm": 4.0,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.439,
      "mean_token_accuracy": 0.027590089477598667,
      "num_tokens": 61670.0,
      "step": 30
    },
    {
      "entropy": 10.741254997253417,
      "epoch": 0.03180372557928214,
      "grad_norm": 3.203125,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.2851,
      "mean_token_accuracy": 0.040197663381695746,
      "num_tokens": 71702.0,
      "step": 35
    },
    {
      "entropy": 10.738425350189209,
      "epoch": 0.03634711494775102,
      "grad_norm": 2.734375,
      "learning_rate": 1.95e-05,
      "loss": 10.129,
      "mean_token_accuracy": 0.04816498160362244,
      "num_tokens": 82840.0,
      "step": 40
    },
    {
      "entropy": 10.734417152404784,
      "epoch": 0.0408905043162199,
      "grad_norm": 2.359375,
      "learning_rate": 2.2e-05,
      "loss": 10.0098,
      "mean_token_accuracy": 0.04295867718756199,
      "num_tokens": 92290.0,
      "step": 45
    },
    {
      "entropy": 10.731618976593017,
      "epoch": 0.04543389368468878,
      "grad_norm": 2.21875,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.9604,
      "mean_token_accuracy": 0.04617781527340412,
      "num_tokens": 101842.0,
      "step": 50
    },
    {
      "entropy": 10.729147243499757,
      "epoch": 0.049977283053157656,
      "grad_norm": 1.875,
      "learning_rate": 2.7e-05,
      "loss": 9.9546,
      "mean_token_accuracy": 0.04403300806879997,
      "num_tokens": 114030.0,
      "step": 55
    },
    {
      "entropy": 10.727308368682861,
      "epoch": 0.05452067242162653,
      "grad_norm": 1.890625,
      "learning_rate": 2.95e-05,
      "loss": 9.8581,
      "mean_token_accuracy": 0.04366073869168759,
      "num_tokens": 124349.0,
      "step": 60
    },
    {
      "entropy": 10.726133060455322,
      "epoch": 0.059064061790095414,
      "grad_norm": 1.9609375,
      "learning_rate": 3.2e-05,
      "loss": 9.7412,
      "mean_token_accuracy": 0.044536291435360906,
      "num_tokens": 133534.0,
      "step": 65
    },
    {
      "entropy": 10.724782562255859,
      "epoch": 0.06360745115856428,
      "grad_norm": 2.0625,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.6971,
      "mean_token_accuracy": 0.041312586329877374,
      "num_tokens": 144383.0,
      "step": 70
    },
    {
      "entropy": 10.723019886016846,
      "epoch": 0.06815084052703317,
      "grad_norm": 1.8359375,
      "learning_rate": 3.7e-05,
      "loss": 9.6751,
      "mean_token_accuracy": 0.04508417844772339,
      "num_tokens": 155467.0,
      "step": 75
    },
    {
      "entropy": 10.717958164215087,
      "epoch": 0.07269422989550205,
      "grad_norm": 1.9609375,
      "learning_rate": 3.95e-05,
      "loss": 9.5919,
      "mean_token_accuracy": 0.045108040794730186,
      "num_tokens": 165903.0,
      "step": 80
    },
    {
      "entropy": 10.709596824645995,
      "epoch": 0.07723761926397092,
      "grad_norm": 2.125,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.511,
      "mean_token_accuracy": 0.04253413174301386,
      "num_tokens": 175812.0,
      "step": 85
    },
    {
      "entropy": 10.702213764190674,
      "epoch": 0.0817810086324398,
      "grad_norm": 1.9140625,
      "learning_rate": 4.45e-05,
      "loss": 9.4176,
      "mean_token_accuracy": 0.04180197641253471,
      "num_tokens": 186357.0,
      "step": 90
    },
    {
      "entropy": 10.6961669921875,
      "epoch": 0.08632439800090867,
      "grad_norm": 1.96875,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.3391,
      "mean_token_accuracy": 0.04544849582016468,
      "num_tokens": 196124.0,
      "step": 95
    },
    {
      "entropy": 10.684025192260743,
      "epoch": 0.09086778736937756,
      "grad_norm": 1.9609375,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.2392,
      "mean_token_accuracy": 0.05092858672142029,
      "num_tokens": 205655.0,
      "step": 100
    },
    {
      "entropy": 10.664148139953614,
      "epoch": 0.09541117673784644,
      "grad_norm": 1.875,
      "learning_rate": 5.2e-05,
      "loss": 9.1639,
      "mean_token_accuracy": 0.05325500890612602,
      "num_tokens": 215870.0,
      "step": 105
    },
    {
      "entropy": 10.64291820526123,
      "epoch": 0.09995456610631531,
      "grad_norm": 1.90625,
      "learning_rate": 5.45e-05,
      "loss": 9.0589,
      "mean_token_accuracy": 0.056853560358285905,
      "num_tokens": 225027.0,
      "step": 110
    },
    {
      "entropy": 10.60800380706787,
      "epoch": 0.10449795547478419,
      "grad_norm": 1.8515625,
      "learning_rate": 5.7e-05,
      "loss": 8.9662,
      "mean_token_accuracy": 0.05881645642220974,
      "num_tokens": 236352.0,
      "step": 115
    },
    {
      "entropy": 10.564264106750489,
      "epoch": 0.10904134484325306,
      "grad_norm": 1.8125,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.8255,
      "mean_token_accuracy": 0.06017065867781639,
      "num_tokens": 246713.0,
      "step": 120
    },
    {
      "entropy": 10.5113018989563,
      "epoch": 0.11358473421172194,
      "grad_norm": 1.7890625,
      "learning_rate": 6.2e-05,
      "loss": 8.666,
      "mean_token_accuracy": 0.06393568031489849,
      "num_tokens": 256950.0,
      "step": 125
    },
    {
      "entropy": 10.445667171478272,
      "epoch": 0.11812812358019083,
      "grad_norm": 1.671875,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.6162,
      "mean_token_accuracy": 0.06482643783092498,
      "num_tokens": 267345.0,
      "step": 130
    },
    {
      "entropy": 10.374823379516602,
      "epoch": 0.1226715129486597,
      "grad_norm": 1.9765625,
      "learning_rate": 6.7e-05,
      "loss": 8.4096,
      "mean_token_accuracy": 0.07293099723756313,
      "num_tokens": 276782.0,
      "step": 135
    },
    {
      "entropy": 10.27814416885376,
      "epoch": 0.12721490231712856,
      "grad_norm": 1.5390625,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.2813,
      "mean_token_accuracy": 0.073567845672369,
      "num_tokens": 287024.0,
      "step": 140
    },
    {
      "entropy": 10.162126541137695,
      "epoch": 0.13175829168559747,
      "grad_norm": 1.4140625,
      "learning_rate": 7.2e-05,
      "loss": 8.255,
      "mean_token_accuracy": 0.07345798872411251,
      "num_tokens": 296597.0,
      "step": 145
    },
    {
      "entropy": 10.039239120483398,
      "epoch": 0.13630168105406634,
      "grad_norm": 1.546875,
      "learning_rate": 7.45e-05,
      "loss": 8.0456,
      "mean_token_accuracy": 0.07541064321994781,
      "num_tokens": 307709.0,
      "step": 150
    },
    {
      "entropy": 9.879199600219726,
      "epoch": 0.14084507042253522,
      "grad_norm": 1.2734375,
      "learning_rate": 7.7e-05,
      "loss": 8.0019,
      "mean_token_accuracy": 0.07952367104589939,
      "num_tokens": 317976.0,
      "step": 155
    },
    {
      "entropy": 9.700241374969483,
      "epoch": 0.1453884597910041,
      "grad_norm": 1.25,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.8309,
      "mean_token_accuracy": 0.07648782916367054,
      "num_tokens": 327319.0,
      "step": 160
    },
    {
      "entropy": 9.498950004577637,
      "epoch": 0.14993184915947297,
      "grad_norm": 1.2109375,
      "learning_rate": 8.2e-05,
      "loss": 7.7494,
      "mean_token_accuracy": 0.07844193913042545,
      "num_tokens": 337337.0,
      "step": 165
    },
    {
      "entropy": 9.23708553314209,
      "epoch": 0.15447523852794184,
      "grad_norm": 1.1484375,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.7247,
      "mean_token_accuracy": 0.07220172360539437,
      "num_tokens": 347779.0,
      "step": 170
    },
    {
      "entropy": 9.071245193481445,
      "epoch": 0.15901862789641072,
      "grad_norm": 1.1484375,
      "learning_rate": 8.7e-05,
      "loss": 7.6848,
      "mean_token_accuracy": 0.07456069067120552,
      "num_tokens": 358088.0,
      "step": 175
    },
    {
      "entropy": 8.767854022979737,
      "epoch": 0.1635620172648796,
      "grad_norm": 0.95703125,
      "learning_rate": 8.95e-05,
      "loss": 7.5652,
      "mean_token_accuracy": 0.07797556966543198,
      "num_tokens": 368314.0,
      "step": 180
    },
    {
      "entropy": 8.613600921630859,
      "epoch": 0.16810540663334847,
      "grad_norm": 0.890625,
      "learning_rate": 9.2e-05,
      "loss": 7.4354,
      "mean_token_accuracy": 0.08428428322076797,
      "num_tokens": 378406.0,
      "step": 185
    },
    {
      "entropy": 8.429571628570557,
      "epoch": 0.17264879600181735,
      "grad_norm": 0.875,
      "learning_rate": 9.45e-05,
      "loss": 7.439,
      "mean_token_accuracy": 0.08039730936288833,
      "num_tokens": 388912.0,
      "step": 190
    },
    {
      "entropy": 8.273902130126952,
      "epoch": 0.17719218537028622,
      "grad_norm": 0.828125,
      "learning_rate": 9.7e-05,
      "loss": 7.4157,
      "mean_token_accuracy": 0.08314879797399044,
      "num_tokens": 399290.0,
      "step": 195
    },
    {
      "entropy": 8.167303562164307,
      "epoch": 0.18173557473875512,
      "grad_norm": 0.7421875,
      "learning_rate": 9.95e-05,
      "loss": 7.322,
      "mean_token_accuracy": 0.08215823769569397,
      "num_tokens": 409757.0,
      "step": 200
    },
    {
      "entropy": 8.126931190490723,
      "epoch": 0.186278964107224,
      "grad_norm": 1.171875,
      "learning_rate": 0.000102,
      "loss": 7.4599,
      "mean_token_accuracy": 0.08315562084317207,
      "num_tokens": 420182.0,
      "step": 205
    },
    {
      "entropy": 8.04471731185913,
      "epoch": 0.19082235347569287,
      "grad_norm": 0.875,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.3635,
      "mean_token_accuracy": 0.08014154359698296,
      "num_tokens": 429897.0,
      "step": 210
    },
    {
      "entropy": 7.973057556152344,
      "epoch": 0.19536574284416175,
      "grad_norm": 0.90234375,
      "learning_rate": 0.000107,
      "loss": 7.2597,
      "mean_token_accuracy": 0.08170034214854241,
      "num_tokens": 441131.0,
      "step": 215
    },
    {
      "entropy": 7.934465074539185,
      "epoch": 0.19990913221263062,
      "grad_norm": 0.76953125,
      "learning_rate": 0.0001095,
      "loss": 7.2285,
      "mean_token_accuracy": 0.08460488840937615,
      "num_tokens": 451894.0,
      "step": 220
    },
    {
      "entropy": 7.865971183776855,
      "epoch": 0.2044525215810995,
      "grad_norm": 0.953125,
      "learning_rate": 0.000112,
      "loss": 7.1586,
      "mean_token_accuracy": 0.08472679629921913,
      "num_tokens": 462613.0,
      "step": 225
    },
    {
      "entropy": 7.905964708328247,
      "epoch": 0.20899591094956838,
      "grad_norm": 0.9140625,
      "learning_rate": 0.0001145,
      "loss": 7.2551,
      "mean_token_accuracy": 0.08738799616694451,
      "num_tokens": 471606.0,
      "step": 230
    },
    {
      "entropy": 7.820685958862304,
      "epoch": 0.21353930031803725,
      "grad_norm": 0.984375,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.1499,
      "mean_token_accuracy": 0.08987567648291588,
      "num_tokens": 481559.0,
      "step": 235
    },
    {
      "entropy": 7.777825260162354,
      "epoch": 0.21808268968650613,
      "grad_norm": 0.96875,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.1686,
      "mean_token_accuracy": 0.0859978199005127,
      "num_tokens": 492766.0,
      "step": 240
    },
    {
      "entropy": 7.835345315933227,
      "epoch": 0.222626079054975,
      "grad_norm": 1.03125,
      "learning_rate": 0.000122,
      "loss": 7.2285,
      "mean_token_accuracy": 0.08684551119804382,
      "num_tokens": 503357.0,
      "step": 245
    },
    {
      "entropy": 7.6760852336883545,
      "epoch": 0.22716946842344388,
      "grad_norm": 1.0625,
      "learning_rate": 0.0001245,
      "loss": 7.0637,
      "mean_token_accuracy": 0.08950686678290368,
      "num_tokens": 513098.0,
      "step": 250
    },
    {
      "entropy": 7.730396175384522,
      "epoch": 0.23171285779191278,
      "grad_norm": 0.98828125,
      "learning_rate": 0.000127,
      "loss": 7.1422,
      "mean_token_accuracy": 0.08494780957698822,
      "num_tokens": 522807.0,
      "step": 255
    },
    {
      "entropy": 7.82570514678955,
      "epoch": 0.23625624716038165,
      "grad_norm": 0.890625,
      "learning_rate": 0.0001295,
      "loss": 7.1568,
      "mean_token_accuracy": 0.0862432986497879,
      "num_tokens": 532670.0,
      "step": 260
    },
    {
      "entropy": 7.713788843154907,
      "epoch": 0.24079963652885053,
      "grad_norm": 0.90625,
      "learning_rate": 0.000132,
      "loss": 7.0973,
      "mean_token_accuracy": 0.0868481919169426,
      "num_tokens": 543647.0,
      "step": 265
    },
    {
      "entropy": 7.765906810760498,
      "epoch": 0.2453430258973194,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.112,
      "mean_token_accuracy": 0.09636801481246948,
      "num_tokens": 553047.0,
      "step": 270
    },
    {
      "entropy": 7.660856294631958,
      "epoch": 0.24988641526578828,
      "grad_norm": 0.91015625,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.1678,
      "mean_token_accuracy": 0.09444689303636551,
      "num_tokens": 563413.0,
      "step": 275
    },
    {
      "entropy": 7.606683969497681,
      "epoch": 0.25442980463425713,
      "grad_norm": 0.921875,
      "learning_rate": 0.0001395,
      "loss": 7.1218,
      "mean_token_accuracy": 0.089845459908247,
      "num_tokens": 573790.0,
      "step": 280
    },
    {
      "entropy": 7.731978559494019,
      "epoch": 0.25897319400272606,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.0439,
      "mean_token_accuracy": 0.09121683463454247,
      "num_tokens": 582958.0,
      "step": 285
    },
    {
      "entropy": 7.521587800979614,
      "epoch": 0.26351658337119493,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001445,
      "loss": 6.9904,
      "mean_token_accuracy": 0.09767817184329033,
      "num_tokens": 592886.0,
      "step": 290
    },
    {
      "entropy": 7.548699855804443,
      "epoch": 0.2680599727396638,
      "grad_norm": 0.97265625,
      "learning_rate": 0.000147,
      "loss": 7.0399,
      "mean_token_accuracy": 0.09062462002038955,
      "num_tokens": 603692.0,
      "step": 295
    },
    {
      "entropy": 7.651094913482666,
      "epoch": 0.2726033621081327,
      "grad_norm": 0.9765625,
      "learning_rate": 0.0001495,
      "loss": 7.0823,
      "mean_token_accuracy": 0.0895950011909008,
      "num_tokens": 613534.0,
      "step": 300
    },
    {
      "entropy": 7.61688346862793,
      "epoch": 0.27714675147660156,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000152,
      "loss": 7.0274,
      "mean_token_accuracy": 0.09576684832572938,
      "num_tokens": 623862.0,
      "step": 305
    },
    {
      "entropy": 7.62919430732727,
      "epoch": 0.28169014084507044,
      "grad_norm": 1.171875,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.1036,
      "mean_token_accuracy": 0.09453180059790611,
      "num_tokens": 633759.0,
      "step": 310
    },
    {
      "entropy": 7.475176191329956,
      "epoch": 0.2862335302135393,
      "grad_norm": 0.9765625,
      "learning_rate": 0.000157,
      "loss": 6.9859,
      "mean_token_accuracy": 0.09430009499192238,
      "num_tokens": 643553.0,
      "step": 315
    },
    {
      "entropy": 7.528373908996582,
      "epoch": 0.2907769195820082,
      "grad_norm": 0.89453125,
      "learning_rate": 0.0001595,
      "loss": 6.9115,
      "mean_token_accuracy": 0.09864105582237244,
      "num_tokens": 653714.0,
      "step": 320
    },
    {
      "entropy": 7.604555463790893,
      "epoch": 0.29532030895047706,
      "grad_norm": 1.109375,
      "learning_rate": 0.000162,
      "loss": 6.9306,
      "mean_token_accuracy": 0.10158697441220284,
      "num_tokens": 662817.0,
      "step": 325
    },
    {
      "entropy": 7.483990573883057,
      "epoch": 0.29986369831894594,
      "grad_norm": 1.2265625,
      "learning_rate": 0.00016450000000000001,
      "loss": 6.9631,
      "mean_token_accuracy": 0.0952290877699852,
      "num_tokens": 672381.0,
      "step": 330
    },
    {
      "entropy": 7.382349872589112,
      "epoch": 0.3044070876874148,
      "grad_norm": 0.9765625,
      "learning_rate": 0.00016700000000000002,
      "loss": 6.8338,
      "mean_token_accuracy": 0.09701873064041137,
      "num_tokens": 682525.0,
      "step": 335
    },
    {
      "entropy": 7.496461296081543,
      "epoch": 0.3089504770558837,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00016950000000000003,
      "loss": 6.9359,
      "mean_token_accuracy": 0.09759294539690018,
      "num_tokens": 691826.0,
      "step": 340
    },
    {
      "entropy": 7.394898748397827,
      "epoch": 0.31349386642435256,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00017199999999999998,
      "loss": 6.9089,
      "mean_token_accuracy": 0.10296000391244889,
      "num_tokens": 701319.0,
      "step": 345
    },
    {
      "entropy": 7.4353029251098635,
      "epoch": 0.31803725579282144,
      "grad_norm": 1.28125,
      "learning_rate": 0.00017449999999999999,
      "loss": 6.998,
      "mean_token_accuracy": 0.0935439720749855,
      "num_tokens": 710888.0,
      "step": 350
    },
    {
      "entropy": 7.49090256690979,
      "epoch": 0.3225806451612903,
      "grad_norm": 0.91015625,
      "learning_rate": 0.000177,
      "loss": 6.9328,
      "mean_token_accuracy": 0.09594348818063736,
      "num_tokens": 722516.0,
      "step": 355
    },
    {
      "entropy": 7.475078916549682,
      "epoch": 0.3271240345297592,
      "grad_norm": 1.203125,
      "learning_rate": 0.0001795,
      "loss": 6.9103,
      "mean_token_accuracy": 0.09800132587552071,
      "num_tokens": 733058.0,
      "step": 360
    },
    {
      "entropy": 7.39355149269104,
      "epoch": 0.33166742389822806,
      "grad_norm": 1.0625,
      "learning_rate": 0.000182,
      "loss": 6.974,
      "mean_token_accuracy": 0.09975532218813896,
      "num_tokens": 744832.0,
      "step": 365
    },
    {
      "entropy": 7.496864604949951,
      "epoch": 0.33621081326669694,
      "grad_norm": 1.140625,
      "learning_rate": 0.0001845,
      "loss": 6.9025,
      "mean_token_accuracy": 0.09925103634595871,
      "num_tokens": 755387.0,
      "step": 370
    },
    {
      "entropy": 7.3132157802581785,
      "epoch": 0.3407542026351658,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000187,
      "loss": 6.8349,
      "mean_token_accuracy": 0.1016771987080574,
      "num_tokens": 764455.0,
      "step": 375
    },
    {
      "entropy": 7.339641284942627,
      "epoch": 0.3452975920036347,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0001895,
      "loss": 6.8903,
      "mean_token_accuracy": 0.09662013798952103,
      "num_tokens": 774513.0,
      "step": 380
    },
    {
      "entropy": 7.49444260597229,
      "epoch": 0.34984098137210357,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000192,
      "loss": 6.9771,
      "mean_token_accuracy": 0.09587227553129196,
      "num_tokens": 785540.0,
      "step": 385
    },
    {
      "entropy": 7.336615896224975,
      "epoch": 0.35438437074057244,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001945,
      "loss": 6.8417,
      "mean_token_accuracy": 0.09714982733130455,
      "num_tokens": 795233.0,
      "step": 390
    },
    {
      "entropy": 7.437350511550903,
      "epoch": 0.35892776010904137,
      "grad_norm": 1.234375,
      "learning_rate": 0.00019700000000000002,
      "loss": 6.8975,
      "mean_token_accuracy": 0.09597025141119957,
      "num_tokens": 804855.0,
      "step": 395
    },
    {
      "entropy": 7.3508072853088375,
      "epoch": 0.36347114947751025,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019950000000000002,
      "loss": 6.8581,
      "mean_token_accuracy": 0.10273054391145706,
      "num_tokens": 814818.0,
      "step": 400
    },
    {
      "entropy": 7.307885694503784,
      "epoch": 0.3680145388459791,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000202,
      "loss": 6.8737,
      "mean_token_accuracy": 0.10590235516428947,
      "num_tokens": 824622.0,
      "step": 405
    },
    {
      "entropy": 7.379908847808838,
      "epoch": 0.372557928214448,
      "grad_norm": 1.0625,
      "learning_rate": 0.00020449999999999998,
      "loss": 6.7626,
      "mean_token_accuracy": 0.10957324355840684,
      "num_tokens": 834813.0,
      "step": 410
    },
    {
      "entropy": 7.205720233917236,
      "epoch": 0.3771013175829169,
      "grad_norm": 0.98046875,
      "learning_rate": 0.000207,
      "loss": 6.8537,
      "mean_token_accuracy": 0.10128433629870415,
      "num_tokens": 844887.0,
      "step": 415
    },
    {
      "entropy": 7.279560470581055,
      "epoch": 0.38164470695138575,
      "grad_norm": 0.99609375,
      "learning_rate": 0.0002095,
      "loss": 6.8512,
      "mean_token_accuracy": 0.10131347700953483,
      "num_tokens": 855430.0,
      "step": 420
    },
    {
      "entropy": 7.237056398391724,
      "epoch": 0.3861880963198546,
      "grad_norm": 1.046875,
      "learning_rate": 0.000212,
      "loss": 6.6942,
      "mean_token_accuracy": 0.10520395040512084,
      "num_tokens": 866052.0,
      "step": 425
    },
    {
      "entropy": 7.226158237457275,
      "epoch": 0.3907314856883235,
      "grad_norm": 0.82421875,
      "learning_rate": 0.0002145,
      "loss": 6.8429,
      "mean_token_accuracy": 0.0950412966310978,
      "num_tokens": 877961.0,
      "step": 430
    },
    {
      "entropy": 7.291323947906494,
      "epoch": 0.3952748750567924,
      "grad_norm": 1.0625,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.8103,
      "mean_token_accuracy": 0.10648028403520585,
      "num_tokens": 888386.0,
      "step": 435
    },
    {
      "entropy": 7.235066747665405,
      "epoch": 0.39981826442526125,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0002195,
      "loss": 6.8563,
      "mean_token_accuracy": 0.10282102078199387,
      "num_tokens": 898272.0,
      "step": 440
    },
    {
      "entropy": 7.281696557998657,
      "epoch": 0.4043616537937301,
      "grad_norm": 0.99609375,
      "learning_rate": 0.000222,
      "loss": 6.8014,
      "mean_token_accuracy": 0.1076163724064827,
      "num_tokens": 908317.0,
      "step": 445
    },
    {
      "entropy": 7.248809957504273,
      "epoch": 0.408905043162199,
      "grad_norm": 0.91015625,
      "learning_rate": 0.0002245,
      "loss": 6.7819,
      "mean_token_accuracy": 0.10194819942116737,
      "num_tokens": 917970.0,
      "step": 450
    },
    {
      "entropy": 7.240721273422241,
      "epoch": 0.4134484325306679,
      "grad_norm": 1.203125,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.8191,
      "mean_token_accuracy": 0.09906565770506859,
      "num_tokens": 928132.0,
      "step": 455
    },
    {
      "entropy": 7.241307735443115,
      "epoch": 0.41799182189913675,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.747,
      "mean_token_accuracy": 0.1059770368039608,
      "num_tokens": 938092.0,
      "step": 460
    },
    {
      "entropy": 7.299763536453247,
      "epoch": 0.4225352112676056,
      "grad_norm": 0.96484375,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.8651,
      "mean_token_accuracy": 0.10198809579014778,
      "num_tokens": 948650.0,
      "step": 465
    },
    {
      "entropy": 7.130692863464356,
      "epoch": 0.4270786006360745,
      "grad_norm": 1.0,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.7675,
      "mean_token_accuracy": 0.10987066626548767,
      "num_tokens": 960195.0,
      "step": 470
    },
    {
      "entropy": 7.254830408096313,
      "epoch": 0.4316219900045434,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000237,
      "loss": 6.7984,
      "mean_token_accuracy": 0.10485964193940163,
      "num_tokens": 970608.0,
      "step": 475
    },
    {
      "entropy": 7.314376783370972,
      "epoch": 0.43616537937301225,
      "grad_norm": 1.34375,
      "learning_rate": 0.0002395,
      "loss": 6.7811,
      "mean_token_accuracy": 0.10285131707787513,
      "num_tokens": 981053.0,
      "step": 480
    },
    {
      "entropy": 7.066157007217408,
      "epoch": 0.4407087687414811,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000242,
      "loss": 6.703,
      "mean_token_accuracy": 0.11324564591050149,
      "num_tokens": 991560.0,
      "step": 485
    },
    {
      "entropy": 7.167983913421631,
      "epoch": 0.44525215810995,
      "grad_norm": 1.171875,
      "learning_rate": 0.0002445,
      "loss": 6.7507,
      "mean_token_accuracy": 0.1001538448035717,
      "num_tokens": 1002008.0,
      "step": 490
    },
    {
      "entropy": 7.145689487457275,
      "epoch": 0.4497955474784189,
      "grad_norm": 1.0,
      "learning_rate": 0.000247,
      "loss": 6.7502,
      "mean_token_accuracy": 0.10835718214511872,
      "num_tokens": 1012349.0,
      "step": 495
    },
    {
      "entropy": 7.15342149734497,
      "epoch": 0.45433893684688775,
      "grad_norm": 1.09375,
      "learning_rate": 0.0002495,
      "loss": 6.7273,
      "mean_token_accuracy": 0.10544943064451218,
      "num_tokens": 1022886.0,
      "step": 500
    },
    {
      "epoch": 0.45433893684688775,
      "eval_entropy": 7.164822139296421,
      "eval_loss": 6.852421760559082,
      "eval_mean_token_accuracy": 0.10633610026954218,
      "eval_num_tokens": 1022886.0,
      "eval_runtime": 2.0057,
      "eval_samples_per_second": 1712.63,
      "eval_steps_per_second": 214.39,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 11000,
  "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": 221422467317760.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}