{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9573958831977023,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011967448539971278,
      "grad_norm": 16.159290313720703,
      "learning_rate": 2.964e-05,
      "loss": 2.393221130371094,
      "step": 25
    },
    {
      "epoch": 0.023934897079942556,
      "grad_norm": 11.983283996582031,
      "learning_rate": 2.9265000000000002e-05,
      "loss": 1.6306124877929689,
      "step": 50
    },
    {
      "epoch": 0.03590234561991384,
      "grad_norm": 10.964775085449219,
      "learning_rate": 2.889e-05,
      "loss": 1.488197021484375,
      "step": 75
    },
    {
      "epoch": 0.04786979415988511,
      "grad_norm": 10.419496536254883,
      "learning_rate": 2.8515e-05,
      "loss": 1.3718760681152344,
      "step": 100
    },
    {
      "epoch": 0.059837242699856394,
      "grad_norm": 9.781177520751953,
      "learning_rate": 2.8139999999999998e-05,
      "loss": 1.2721688079833984,
      "step": 125
    },
    {
      "epoch": 0.07180469123982768,
      "grad_norm": 8.892899513244629,
      "learning_rate": 2.7765e-05,
      "loss": 1.212474594116211,
      "step": 150
    },
    {
      "epoch": 0.08377213977979894,
      "grad_norm": 8.198054313659668,
      "learning_rate": 2.739e-05,
      "loss": 1.1640670776367188,
      "step": 175
    },
    {
      "epoch": 0.09573958831977022,
      "grad_norm": 14.760664939880371,
      "learning_rate": 2.7015e-05,
      "loss": 1.122880630493164,
      "step": 200
    },
    {
      "epoch": 0.1077070368597415,
      "grad_norm": 8.657957077026367,
      "learning_rate": 2.6640000000000002e-05,
      "loss": 1.0792572784423828,
      "step": 225
    },
    {
      "epoch": 0.11967448539971279,
      "grad_norm": 9.582183837890625,
      "learning_rate": 2.6265e-05,
      "loss": 0.946361083984375,
      "step": 250
    },
    {
      "epoch": 0.13164193393968407,
      "grad_norm": 9.90124225616455,
      "learning_rate": 2.589e-05,
      "loss": 0.7015521240234375,
      "step": 275
    },
    {
      "epoch": 0.14360938247965535,
      "grad_norm": 6.0904927253723145,
      "learning_rate": 2.5515000000000002e-05,
      "loss": 0.5619692611694336,
      "step": 300
    },
    {
      "epoch": 0.1555768310196266,
      "grad_norm": 6.307363510131836,
      "learning_rate": 2.514e-05,
      "loss": 0.5397976303100586,
      "step": 325
    },
    {
      "epoch": 0.1675442795595979,
      "grad_norm": 6.347323417663574,
      "learning_rate": 2.4765e-05,
      "loss": 0.45329193115234373,
      "step": 350
    },
    {
      "epoch": 0.17951172809956917,
      "grad_norm": 4.2150092124938965,
      "learning_rate": 2.439e-05,
      "loss": 0.43831916809082033,
      "step": 375
    },
    {
      "epoch": 0.19147917663954045,
      "grad_norm": 6.442485332489014,
      "learning_rate": 2.4015e-05,
      "loss": 0.4092135238647461,
      "step": 400
    },
    {
      "epoch": 0.20344662517951173,
      "grad_norm": 6.235575199127197,
      "learning_rate": 2.364e-05,
      "loss": 0.41996471405029295,
      "step": 425
    },
    {
      "epoch": 0.215414073719483,
      "grad_norm": 4.805295944213867,
      "learning_rate": 2.3265e-05,
      "loss": 0.37865653991699216,
      "step": 450
    },
    {
      "epoch": 0.2273815222594543,
      "grad_norm": 4.641193389892578,
      "learning_rate": 2.289e-05,
      "loss": 0.38615558624267576,
      "step": 475
    },
    {
      "epoch": 0.23934897079942558,
      "grad_norm": 4.975593566894531,
      "learning_rate": 2.2515e-05,
      "loss": 0.3595850372314453,
      "step": 500
    },
    {
      "epoch": 0.25131641933939686,
      "grad_norm": 4.641961574554443,
      "learning_rate": 2.214e-05,
      "loss": 0.3625198745727539,
      "step": 525
    },
    {
      "epoch": 0.26328386787936814,
      "grad_norm": 3.975968837738037,
      "learning_rate": 2.1765000000000003e-05,
      "loss": 0.41111274719238283,
      "step": 550
    },
    {
      "epoch": 0.2752513164193394,
      "grad_norm": 2.668240547180176,
      "learning_rate": 2.139e-05,
      "loss": 0.32781185150146486,
      "step": 575
    },
    {
      "epoch": 0.2872187649593107,
      "grad_norm": 3.3640079498291016,
      "learning_rate": 2.1015e-05,
      "loss": 0.31779170989990235,
      "step": 600
    },
    {
      "epoch": 0.29918621349928193,
      "grad_norm": 4.217093467712402,
      "learning_rate": 2.064e-05,
      "loss": 0.3358059310913086,
      "step": 625
    },
    {
      "epoch": 0.3111536620392532,
      "grad_norm": 8.076043128967285,
      "learning_rate": 2.0265e-05,
      "loss": 0.3440943908691406,
      "step": 650
    },
    {
      "epoch": 0.3231211105792245,
      "grad_norm": 4.453291416168213,
      "learning_rate": 1.989e-05,
      "loss": 0.3261558151245117,
      "step": 675
    },
    {
      "epoch": 0.3350885591191958,
      "grad_norm": 5.208756923675537,
      "learning_rate": 1.9515e-05,
      "loss": 0.32787994384765623,
      "step": 700
    },
    {
      "epoch": 0.34705600765916705,
      "grad_norm": 4.408796310424805,
      "learning_rate": 1.914e-05,
      "loss": 0.30166456222534177,
      "step": 725
    },
    {
      "epoch": 0.35902345619913834,
      "grad_norm": 3.7778923511505127,
      "learning_rate": 1.8764999999999997e-05,
      "loss": 0.33025398254394533,
      "step": 750
    },
    {
      "epoch": 0.3709909047391096,
      "grad_norm": 3.9224133491516113,
      "learning_rate": 1.8390000000000002e-05,
      "loss": 0.30546653747558594,
      "step": 775
    },
    {
      "epoch": 0.3829583532790809,
      "grad_norm": 4.24598503112793,
      "learning_rate": 1.8015000000000003e-05,
      "loss": 0.3084229278564453,
      "step": 800
    },
    {
      "epoch": 0.3949258018190522,
      "grad_norm": 3.883857250213623,
      "learning_rate": 1.764e-05,
      "loss": 0.30587684631347656,
      "step": 825
    },
    {
      "epoch": 0.40689325035902346,
      "grad_norm": 2.9970357418060303,
      "learning_rate": 1.7265e-05,
      "loss": 0.26069087982177735,
      "step": 850
    },
    {
      "epoch": 0.41886069889899474,
      "grad_norm": 3.904029130935669,
      "learning_rate": 1.689e-05,
      "loss": 0.3135500717163086,
      "step": 875
    },
    {
      "epoch": 0.430828147438966,
      "grad_norm": 4.558609962463379,
      "learning_rate": 1.6515e-05,
      "loss": 0.30924333572387697,
      "step": 900
    },
    {
      "epoch": 0.4427955959789373,
      "grad_norm": 2.483649253845215,
      "learning_rate": 1.614e-05,
      "loss": 0.28861886978149415,
      "step": 925
    },
    {
      "epoch": 0.4547630445189086,
      "grad_norm": 3.368525981903076,
      "learning_rate": 1.5765e-05,
      "loss": 0.27014717102050784,
      "step": 950
    },
    {
      "epoch": 0.46673049305887987,
      "grad_norm": 4.169050216674805,
      "learning_rate": 1.539e-05,
      "loss": 0.3167378234863281,
      "step": 975
    },
    {
      "epoch": 0.47869794159885115,
      "grad_norm": 3.039638042449951,
      "learning_rate": 1.5015e-05,
      "loss": 0.30757768630981447,
      "step": 1000
    },
    {
      "epoch": 0.4906653901388224,
      "grad_norm": 3.8224575519561768,
      "learning_rate": 1.464e-05,
      "loss": 0.257368278503418,
      "step": 1025
    },
    {
      "epoch": 0.5026328386787937,
      "grad_norm": 4.447447776794434,
      "learning_rate": 1.4265e-05,
      "loss": 0.2711064910888672,
      "step": 1050
    },
    {
      "epoch": 0.5146002872187649,
      "grad_norm": 2.7556653022766113,
      "learning_rate": 1.389e-05,
      "loss": 0.29430915832519533,
      "step": 1075
    },
    {
      "epoch": 0.5265677357587363,
      "grad_norm": 3.6120786666870117,
      "learning_rate": 1.3515e-05,
      "loss": 0.25948652267456057,
      "step": 1100
    },
    {
      "epoch": 0.5385351842987075,
      "grad_norm": 3.0165789127349854,
      "learning_rate": 1.314e-05,
      "loss": 0.2648066329956055,
      "step": 1125
    },
    {
      "epoch": 0.5505026328386788,
      "grad_norm": 2.395517349243164,
      "learning_rate": 1.2765e-05,
      "loss": 0.28498870849609376,
      "step": 1150
    },
    {
      "epoch": 0.5624700813786501,
      "grad_norm": 3.056443691253662,
      "learning_rate": 1.239e-05,
      "loss": 0.28835039138793944,
      "step": 1175
    },
    {
      "epoch": 0.5744375299186214,
      "grad_norm": 3.4160618782043457,
      "learning_rate": 1.2015000000000001e-05,
      "loss": 0.2601981735229492,
      "step": 1200
    },
    {
      "epoch": 0.5864049784585926,
      "grad_norm": 3.4843311309814453,
      "learning_rate": 1.164e-05,
      "loss": 0.25075761795043944,
      "step": 1225
    },
    {
      "epoch": 0.5983724269985639,
      "grad_norm": 2.3877573013305664,
      "learning_rate": 1.1265e-05,
      "loss": 0.2595806121826172,
      "step": 1250
    },
    {
      "epoch": 0.6103398755385352,
      "grad_norm": 3.865945339202881,
      "learning_rate": 1.089e-05,
      "loss": 0.30072870254516604,
      "step": 1275
    },
    {
      "epoch": 0.6223073240785064,
      "grad_norm": 3.270880937576294,
      "learning_rate": 1.0515e-05,
      "loss": 0.26188276290893553,
      "step": 1300
    },
    {
      "epoch": 0.6342747726184778,
      "grad_norm": 4.212886333465576,
      "learning_rate": 1.0140000000000001e-05,
      "loss": 0.2598790168762207,
      "step": 1325
    },
    {
      "epoch": 0.646242221158449,
      "grad_norm": 2.603821039199829,
      "learning_rate": 9.765e-06,
      "loss": 0.2566701126098633,
      "step": 1350
    },
    {
      "epoch": 0.6582096696984203,
      "grad_norm": 3.567640781402588,
      "learning_rate": 9.39e-06,
      "loss": 0.23227554321289062,
      "step": 1375
    },
    {
      "epoch": 0.6701771182383915,
      "grad_norm": 3.0411109924316406,
      "learning_rate": 9.015e-06,
      "loss": 0.254827938079834,
      "step": 1400
    },
    {
      "epoch": 0.6821445667783629,
      "grad_norm": 2.4146523475646973,
      "learning_rate": 8.64e-06,
      "loss": 0.24793487548828125,
      "step": 1425
    },
    {
      "epoch": 0.6941120153183341,
      "grad_norm": 3.1589515209198,
      "learning_rate": 8.265000000000001e-06,
      "loss": 0.23845375061035157,
      "step": 1450
    },
    {
      "epoch": 0.7060794638583054,
      "grad_norm": 2.8087363243103027,
      "learning_rate": 7.89e-06,
      "loss": 0.2550558662414551,
      "step": 1475
    },
    {
      "epoch": 0.7180469123982767,
      "grad_norm": 2.8838937282562256,
      "learning_rate": 7.515e-06,
      "loss": 0.25409133911132814,
      "step": 1500
    },
    {
      "epoch": 0.730014360938248,
      "grad_norm": 2.770642042160034,
      "learning_rate": 7.14e-06,
      "loss": 0.23834611892700194,
      "step": 1525
    },
    {
      "epoch": 0.7419818094782192,
      "grad_norm": 2.3907296657562256,
      "learning_rate": 6.7650000000000005e-06,
      "loss": 0.23956525802612305,
      "step": 1550
    },
    {
      "epoch": 0.7539492580181906,
      "grad_norm": 2.288137197494507,
      "learning_rate": 6.39e-06,
      "loss": 0.23735124588012696,
      "step": 1575
    },
    {
      "epoch": 0.7659167065581618,
      "grad_norm": 3.3936712741851807,
      "learning_rate": 6.015000000000001e-06,
      "loss": 0.24709955215454102,
      "step": 1600
    },
    {
      "epoch": 0.777884155098133,
      "grad_norm": 2.605344772338867,
      "learning_rate": 5.64e-06,
      "loss": 0.23129446029663087,
      "step": 1625
    },
    {
      "epoch": 0.7898516036381044,
      "grad_norm": 2.9431045055389404,
      "learning_rate": 5.2649999999999996e-06,
      "loss": 0.241181640625,
      "step": 1650
    },
    {
      "epoch": 0.8018190521780756,
      "grad_norm": 3.2949025630950928,
      "learning_rate": 4.890000000000001e-06,
      "loss": 0.24215137481689453,
      "step": 1675
    },
    {
      "epoch": 0.8137865007180469,
      "grad_norm": 3.0328359603881836,
      "learning_rate": 4.515e-06,
      "loss": 0.2238747787475586,
      "step": 1700
    },
    {
      "epoch": 0.8257539492580181,
      "grad_norm": 3.025641679763794,
      "learning_rate": 4.14e-06,
      "loss": 0.2663035774230957,
      "step": 1725
    },
    {
      "epoch": 0.8377213977979895,
      "grad_norm": 2.0968775749206543,
      "learning_rate": 3.765e-06,
      "loss": 0.22664173126220702,
      "step": 1750
    },
    {
      "epoch": 0.8496888463379607,
      "grad_norm": 2.3551278114318848,
      "learning_rate": 3.39e-06,
      "loss": 0.24346946716308593,
      "step": 1775
    },
    {
      "epoch": 0.861656294877932,
      "grad_norm": 2.2398862838745117,
      "learning_rate": 3.0150000000000004e-06,
      "loss": 0.22162725448608397,
      "step": 1800
    },
    {
      "epoch": 0.8736237434179033,
      "grad_norm": 2.8981614112854004,
      "learning_rate": 2.6399999999999997e-06,
      "loss": 0.2262067985534668,
      "step": 1825
    },
    {
      "epoch": 0.8855911919578746,
      "grad_norm": 2.4004294872283936,
      "learning_rate": 2.265e-06,
      "loss": 0.26730960845947266,
      "step": 1850
    },
    {
      "epoch": 0.8975586404978458,
      "grad_norm": 2.969921112060547,
      "learning_rate": 1.8900000000000001e-06,
      "loss": 0.21616565704345703,
      "step": 1875
    },
    {
      "epoch": 0.9095260890378172,
      "grad_norm": 2.837693452835083,
      "learning_rate": 1.5150000000000001e-06,
      "loss": 0.23662687301635743,
      "step": 1900
    },
    {
      "epoch": 0.9214935375777884,
      "grad_norm": 2.973127841949463,
      "learning_rate": 1.14e-06,
      "loss": 0.22590934753417968,
      "step": 1925
    },
    {
      "epoch": 0.9334609861177597,
      "grad_norm": 3.1667377948760986,
      "learning_rate": 7.65e-07,
      "loss": 0.2051544952392578,
      "step": 1950
    },
    {
      "epoch": 0.945428434657731,
      "grad_norm": 2.8789992332458496,
      "learning_rate": 3.8999999999999997e-07,
      "loss": 0.22102611541748046,
      "step": 1975
    },
    {
      "epoch": 0.9573958831977023,
      "grad_norm": 2.393117904663086,
      "learning_rate": 1.5000000000000002e-08,
      "loss": 0.21713571548461913,
      "step": 2000
    }
  ],
  "logging_steps": 25,
  "max_steps": 2000,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.61736640512e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}