{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25,
  "eval_steps": 100.0,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025,
      "grad_norm": 0.09379793703556061,
      "learning_rate": 5.999999999999999e-06,
      "loss": 0.6799,
      "step": 5
    },
    {
      "epoch": 0.005,
      "grad_norm": 0.1399833709001541,
      "learning_rate": 1.3499999999999998e-05,
      "loss": 0.6954,
      "step": 10
    },
    {
      "epoch": 0.0075,
      "grad_norm": 0.08632303029298782,
      "learning_rate": 2.1e-05,
      "loss": 0.6921,
      "step": 15
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.10006701201200485,
      "learning_rate": 2.8499999999999998e-05,
      "loss": 0.69,
      "step": 20
    },
    {
      "epoch": 0.0125,
      "grad_norm": 0.07633858919143677,
      "learning_rate": 3.5999999999999994e-05,
      "loss": 0.6722,
      "step": 25
    },
    {
      "epoch": 0.015,
      "grad_norm": 0.09399061650037766,
      "learning_rate": 4.3499999999999993e-05,
      "loss": 0.6453,
      "step": 30
    },
    {
      "epoch": 0.0175,
      "grad_norm": 0.0843738541007042,
      "learning_rate": 5.1e-05,
      "loss": 0.6276,
      "step": 35
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.08583351224660873,
      "learning_rate": 5.85e-05,
      "loss": 0.58,
      "step": 40
    },
    {
      "epoch": 0.0225,
      "grad_norm": 0.09571370482444763,
      "learning_rate": 6.599999999999999e-05,
      "loss": 0.6355,
      "step": 45
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.1083935871720314,
      "learning_rate": 7.35e-05,
      "loss": 0.589,
      "step": 50
    },
    {
      "epoch": 0.0275,
      "grad_norm": 0.10387319326400757,
      "learning_rate": 8.1e-05,
      "loss": 0.6061,
      "step": 55
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.11083361506462097,
      "learning_rate": 8.849999999999998e-05,
      "loss": 0.572,
      "step": 60
    },
    {
      "epoch": 0.0325,
      "grad_norm": 0.12665686011314392,
      "learning_rate": 9.599999999999999e-05,
      "loss": 0.5442,
      "step": 65
    },
    {
      "epoch": 0.035,
      "grad_norm": 0.1308053582906723,
      "learning_rate": 0.00010349999999999998,
      "loss": 0.6524,
      "step": 70
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.13535510003566742,
      "learning_rate": 0.00011099999999999999,
      "loss": 0.6404,
      "step": 75
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.12833671271800995,
      "learning_rate": 0.0001185,
      "loss": 0.5717,
      "step": 80
    },
    {
      "epoch": 0.0425,
      "grad_norm": 0.11962099373340607,
      "learning_rate": 0.00012599999999999997,
      "loss": 0.6098,
      "step": 85
    },
    {
      "epoch": 0.045,
      "grad_norm": 0.13898271322250366,
      "learning_rate": 0.0001335,
      "loss": 0.6099,
      "step": 90
    },
    {
      "epoch": 0.0475,
      "grad_norm": 0.14486610889434814,
      "learning_rate": 0.00014099999999999998,
      "loss": 0.5744,
      "step": 95
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.1432138830423355,
      "learning_rate": 0.00014849999999999998,
      "loss": 0.5659,
      "step": 100
    },
    {
      "epoch": 0.0525,
      "grad_norm": 0.13487878441810608,
      "learning_rate": 0.000156,
      "loss": 0.5622,
      "step": 105
    },
    {
      "epoch": 0.055,
      "grad_norm": 0.12495309859514236,
      "learning_rate": 0.0001635,
      "loss": 0.5951,
      "step": 110
    },
    {
      "epoch": 0.0575,
      "grad_norm": 0.13011734187602997,
      "learning_rate": 0.00017099999999999998,
      "loss": 0.6249,
      "step": 115
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.13987745344638824,
      "learning_rate": 0.00017849999999999997,
      "loss": 0.559,
      "step": 120
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.13373605906963348,
      "learning_rate": 0.000186,
      "loss": 0.5475,
      "step": 125
    },
    {
      "epoch": 0.065,
      "grad_norm": 0.12433867901563644,
      "learning_rate": 0.0001935,
      "loss": 0.5274,
      "step": 130
    },
    {
      "epoch": 0.0675,
      "grad_norm": 0.11097615957260132,
      "learning_rate": 0.000201,
      "loss": 0.678,
      "step": 135
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.1155027225613594,
      "learning_rate": 0.00020849999999999997,
      "loss": 0.5611,
      "step": 140
    },
    {
      "epoch": 0.0725,
      "grad_norm": 0.11431068181991577,
      "learning_rate": 0.00021599999999999996,
      "loss": 0.6054,
      "step": 145
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.09796140342950821,
      "learning_rate": 0.00022349999999999998,
      "loss": 0.5472,
      "step": 150
    },
    {
      "epoch": 0.0775,
      "grad_norm": 0.09489257633686066,
      "learning_rate": 0.00023099999999999998,
      "loss": 0.4636,
      "step": 155
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.10787788033485413,
      "learning_rate": 0.0002385,
      "loss": 0.6164,
      "step": 160
    },
    {
      "epoch": 0.0825,
      "grad_norm": 0.10261733084917068,
      "learning_rate": 0.00024599999999999996,
      "loss": 0.5408,
      "step": 165
    },
    {
      "epoch": 0.085,
      "grad_norm": 0.11870352178812027,
      "learning_rate": 0.0002535,
      "loss": 0.5268,
      "step": 170
    },
    {
      "epoch": 0.0875,
      "grad_norm": 0.11910569667816162,
      "learning_rate": 0.000261,
      "loss": 0.5461,
      "step": 175
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.10083702206611633,
      "learning_rate": 0.00026849999999999997,
      "loss": 0.4794,
      "step": 180
    },
    {
      "epoch": 0.0925,
      "grad_norm": 0.10453511029481888,
      "learning_rate": 0.000276,
      "loss": 0.5539,
      "step": 185
    },
    {
      "epoch": 0.095,
      "grad_norm": 0.101403146982193,
      "learning_rate": 0.00028349999999999995,
      "loss": 0.5346,
      "step": 190
    },
    {
      "epoch": 0.0975,
      "grad_norm": 0.10724789649248123,
      "learning_rate": 0.00029099999999999997,
      "loss": 0.6026,
      "step": 195
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.1140277311205864,
      "learning_rate": 0.0002985,
      "loss": 0.5193,
      "step": 200
    },
    {
      "epoch": 0.1025,
      "grad_norm": 0.09706108272075653,
      "learning_rate": 0.0002999963446058092,
      "loss": 0.54,
      "step": 205
    },
    {
      "epoch": 0.105,
      "grad_norm": 0.10003062337636948,
      "learning_rate": 0.0002999814948722491,
      "loss": 0.5365,
      "step": 210
    },
    {
      "epoch": 0.1075,
      "grad_norm": 0.1078687533736229,
      "learning_rate": 0.00029995522346717746,
      "loss": 0.5889,
      "step": 215
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.10538115352392197,
      "learning_rate": 0.0002999175323912636,
      "loss": 0.5611,
      "step": 220
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.1020808294415474,
      "learning_rate": 0.00029986842451482874,
      "loss": 0.6103,
      "step": 225
    },
    {
      "epoch": 0.115,
      "grad_norm": 0.09635835886001587,
      "learning_rate": 0.0002998079035776279,
      "loss": 0.5229,
      "step": 230
    },
    {
      "epoch": 0.1175,
      "grad_norm": 0.10287190228700638,
      "learning_rate": 0.0002997359741885648,
      "loss": 0.5312,
      "step": 235
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.09160075336694717,
      "learning_rate": 0.0002996526418253408,
      "loss": 0.5673,
      "step": 240
    },
    {
      "epoch": 0.1225,
      "grad_norm": 0.08691006153821945,
      "learning_rate": 0.000299557912834038,
      "loss": 0.5326,
      "step": 245
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.10096988826990128,
      "learning_rate": 0.00029945179442863594,
      "loss": 0.6004,
      "step": 250
    },
    {
      "epoch": 0.1275,
      "grad_norm": 0.09594204276800156,
      "learning_rate": 0.000299334294690462,
      "loss": 0.5516,
      "step": 255
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.10281919687986374,
      "learning_rate": 0.00029920542256757607,
      "loss": 0.5515,
      "step": 260
    },
    {
      "epoch": 0.1325,
      "grad_norm": 0.08547840267419815,
      "learning_rate": 0.00029906518787408944,
      "loss": 0.5243,
      "step": 265
    },
    {
      "epoch": 0.135,
      "grad_norm": 0.10161560773849487,
      "learning_rate": 0.0002989136012894168,
      "loss": 0.5096,
      "step": 270
    },
    {
      "epoch": 0.1375,
      "grad_norm": 0.09101904183626175,
      "learning_rate": 0.0002987506743574635,
      "loss": 0.553,
      "step": 275
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.09769442677497864,
      "learning_rate": 0.0002985764194857463,
      "loss": 0.4953,
      "step": 280
    },
    {
      "epoch": 0.1425,
      "grad_norm": 0.10991579294204712,
      "learning_rate": 0.00029839084994444826,
      "loss": 0.5152,
      "step": 285
    },
    {
      "epoch": 0.145,
      "grad_norm": 0.09450916200876236,
      "learning_rate": 0.00029819397986540836,
      "loss": 0.5397,
      "step": 290
    },
    {
      "epoch": 0.1475,
      "grad_norm": 0.10876069217920303,
      "learning_rate": 0.0002979858242410454,
      "loss": 0.4858,
      "step": 295
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.097995825111866,
      "learning_rate": 0.00029776639892321606,
      "loss": 0.5566,
      "step": 300
    },
    {
      "epoch": 0.1525,
      "grad_norm": 0.1145048514008522,
      "learning_rate": 0.0002975357206220079,
      "loss": 0.4531,
      "step": 305
    },
    {
      "epoch": 0.155,
      "grad_norm": 0.10271880775690079,
      "learning_rate": 0.00029729380690446654,
      "loss": 0.5199,
      "step": 310
    },
    {
      "epoch": 0.1575,
      "grad_norm": 0.11095371842384338,
      "learning_rate": 0.0002970406761932583,
      "loss": 0.5416,
      "step": 315
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.09949438273906708,
      "learning_rate": 0.00029677634776526673,
      "loss": 0.4841,
      "step": 320
    },
    {
      "epoch": 0.1625,
      "grad_norm": 0.1163724958896637,
      "learning_rate": 0.00029650084175012517,
      "loss": 0.4913,
      "step": 325
    },
    {
      "epoch": 0.165,
      "grad_norm": 0.10726840049028397,
      "learning_rate": 0.00029621417912868323,
      "loss": 0.5203,
      "step": 330
    },
    {
      "epoch": 0.1675,
      "grad_norm": 0.09609931707382202,
      "learning_rate": 0.00029591638173140947,
      "loss": 0.5607,
      "step": 335
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.10824442654848099,
      "learning_rate": 0.0002956074722367286,
      "loss": 0.6004,
      "step": 340
    },
    {
      "epoch": 0.1725,
      "grad_norm": 0.10465679317712784,
      "learning_rate": 0.00029528747416929463,
      "loss": 0.5216,
      "step": 345
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.10518354922533035,
      "learning_rate": 0.0002949564118981994,
      "loss": 0.499,
      "step": 350
    },
    {
      "epoch": 0.1775,
      "grad_norm": 0.0955279991030693,
      "learning_rate": 0.0002946143106351165,
      "loss": 0.5607,
      "step": 355
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.11159654706716537,
      "learning_rate": 0.0002942611964323817,
      "loss": 0.5204,
      "step": 360
    },
    {
      "epoch": 0.1825,
      "grad_norm": 0.09571187198162079,
      "learning_rate": 0.0002938970961810086,
      "loss": 0.6113,
      "step": 365
    },
    {
      "epoch": 0.185,
      "grad_norm": 0.11854679882526398,
      "learning_rate": 0.0002935220376086411,
      "loss": 0.5639,
      "step": 370
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.1050512045621872,
      "learning_rate": 0.0002931360492774415,
      "loss": 0.548,
      "step": 375
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.1053968220949173,
      "learning_rate": 0.0002927391605819157,
      "loss": 0.5507,
      "step": 380
    },
    {
      "epoch": 0.1925,
      "grad_norm": 0.10567320138216019,
      "learning_rate": 0.00029233140174667445,
      "loss": 0.5312,
      "step": 385
    },
    {
      "epoch": 0.195,
      "grad_norm": 0.11914283782243729,
      "learning_rate": 0.0002919128038241318,
      "loss": 0.5961,
      "step": 390
    },
    {
      "epoch": 0.1975,
      "grad_norm": 0.09915795922279358,
      "learning_rate": 0.0002914833986921401,
      "loss": 0.5086,
      "step": 395
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.10796502232551575,
      "learning_rate": 0.0002910432190515628,
      "loss": 0.5585,
      "step": 400
    },
    {
      "epoch": 0.2025,
      "grad_norm": 0.10748997330665588,
      "learning_rate": 0.00029059229842378373,
      "loss": 0.5466,
      "step": 405
    },
    {
      "epoch": 0.205,
      "grad_norm": 0.10696308314800262,
      "learning_rate": 0.0002901306711481544,
      "loss": 0.5513,
      "step": 410
    },
    {
      "epoch": 0.2075,
      "grad_norm": 0.10418657958507538,
      "learning_rate": 0.0002896583723793792,
      "loss": 0.5391,
      "step": 415
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.16421550512313843,
      "learning_rate": 0.00028917543808483796,
      "loss": 0.4699,
      "step": 420
    },
    {
      "epoch": 0.2125,
      "grad_norm": 0.12929962575435638,
      "learning_rate": 0.00028868190504184696,
      "loss": 0.4984,
      "step": 425
    },
    {
      "epoch": 0.215,
      "grad_norm": 0.10469454526901245,
      "learning_rate": 0.00028817781083485816,
      "loss": 0.5119,
      "step": 430
    },
    {
      "epoch": 0.2175,
      "grad_norm": 0.0964970663189888,
      "learning_rate": 0.00028766319385259713,
      "loss": 0.5167,
      "step": 435
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.12395574152469635,
      "learning_rate": 0.00028713809328513953,
      "loss": 0.5692,
      "step": 440
    },
    {
      "epoch": 0.2225,
      "grad_norm": 0.10189738124608994,
      "learning_rate": 0.0002866025491209265,
      "loss": 0.4628,
      "step": 445
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.10433454066514969,
      "learning_rate": 0.0002860566021437197,
      "loss": 0.4869,
      "step": 450
    },
    {
      "epoch": 0.2275,
      "grad_norm": 0.13003456592559814,
      "learning_rate": 0.0002855002939294951,
      "loss": 0.5291,
      "step": 455
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.11692202836275101,
      "learning_rate": 0.000284933666843277,
      "loss": 0.5229,
      "step": 460
    },
    {
      "epoch": 0.2325,
      "grad_norm": 0.10757846385240555,
      "learning_rate": 0.0002843567640359119,
      "loss": 0.435,
      "step": 465
    },
    {
      "epoch": 0.235,
      "grad_norm": 0.10775501281023026,
      "learning_rate": 0.00028376962944078206,
      "loss": 0.4418,
      "step": 470
    },
    {
      "epoch": 0.2375,
      "grad_norm": 0.11543692648410797,
      "learning_rate": 0.00028317230777046015,
      "loss": 0.4204,
      "step": 475
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.10946698486804962,
      "learning_rate": 0.00028256484451330403,
      "loss": 0.49,
      "step": 480
    },
    {
      "epoch": 0.2425,
      "grad_norm": 0.11528221517801285,
      "learning_rate": 0.00028194728592999247,
      "loss": 0.4752,
      "step": 485
    },
    {
      "epoch": 0.245,
      "grad_norm": 0.10474205762147903,
      "learning_rate": 0.0002813196790500027,
      "loss": 0.4847,
      "step": 490
    },
    {
      "epoch": 0.2475,
      "grad_norm": 0.10768820345401764,
      "learning_rate": 0.00028068207166802837,
      "loss": 0.4664,
      "step": 495
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.12158560007810593,
      "learning_rate": 0.00028003451234034037,
      "loss": 0.4741,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 6.57394539429888e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}