{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02603922548927705,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002603922548927705,
      "grad_norm": 0.8521247506141663,
      "learning_rate": 5.194805194805195e-06,
      "loss": 0.7412,
      "step": 10
    },
    {
      "epoch": 0.000520784509785541,
      "grad_norm": 0.6229312419891357,
      "learning_rate": 1.038961038961039e-05,
      "loss": 0.7138,
      "step": 20
    },
    {
      "epoch": 0.0007811767646783114,
      "grad_norm": 0.4566498100757599,
      "learning_rate": 1.5584415584415583e-05,
      "loss": 0.7079,
      "step": 30
    },
    {
      "epoch": 0.001041569019571082,
      "grad_norm": 0.4316692650318146,
      "learning_rate": 2.077922077922078e-05,
      "loss": 0.6988,
      "step": 40
    },
    {
      "epoch": 0.0013019612744638524,
      "grad_norm": 0.615436315536499,
      "learning_rate": 2.5974025974025972e-05,
      "loss": 0.6937,
      "step": 50
    },
    {
      "epoch": 0.0015623535293566228,
      "grad_norm": 0.48698583245277405,
      "learning_rate": 3.1168831168831166e-05,
      "loss": 0.7043,
      "step": 60
    },
    {
      "epoch": 0.0018227457842493933,
      "grad_norm": 0.3984021544456482,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.6563,
      "step": 70
    },
    {
      "epoch": 0.002083138039142164,
      "grad_norm": 0.37576180696487427,
      "learning_rate": 4.155844155844156e-05,
      "loss": 0.6462,
      "step": 80
    },
    {
      "epoch": 0.0023435302940349343,
      "grad_norm": 0.35269680619239807,
      "learning_rate": 4.675324675324675e-05,
      "loss": 0.6656,
      "step": 90
    },
    {
      "epoch": 0.0026039225489277048,
      "grad_norm": 0.31541451811790466,
      "learning_rate": 5.1948051948051944e-05,
      "loss": 0.6547,
      "step": 100
    },
    {
      "epoch": 0.002864314803820475,
      "grad_norm": 0.3462330400943756,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.6621,
      "step": 110
    },
    {
      "epoch": 0.0031247070587132456,
      "grad_norm": 0.3465985953807831,
      "learning_rate": 6.233766233766233e-05,
      "loss": 0.6273,
      "step": 120
    },
    {
      "epoch": 0.003385099313606016,
      "grad_norm": 0.3297797441482544,
      "learning_rate": 6.753246753246754e-05,
      "loss": 0.6559,
      "step": 130
    },
    {
      "epoch": 0.0036454915684987865,
      "grad_norm": 0.3888818621635437,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.6756,
      "step": 140
    },
    {
      "epoch": 0.003905883823391557,
      "grad_norm": 0.3542368710041046,
      "learning_rate": 7.792207792207793e-05,
      "loss": 0.6506,
      "step": 150
    },
    {
      "epoch": 0.004166276078284328,
      "grad_norm": 0.37369370460510254,
      "learning_rate": 8.311688311688312e-05,
      "loss": 0.6645,
      "step": 160
    },
    {
      "epoch": 0.004426668333177098,
      "grad_norm": 0.3700549900531769,
      "learning_rate": 8.831168831168831e-05,
      "loss": 0.6727,
      "step": 170
    },
    {
      "epoch": 0.004687060588069869,
      "grad_norm": 0.32032889127731323,
      "learning_rate": 9.35064935064935e-05,
      "loss": 0.6529,
      "step": 180
    },
    {
      "epoch": 0.004947452842962639,
      "grad_norm": 0.3331650495529175,
      "learning_rate": 9.870129870129871e-05,
      "loss": 0.6627,
      "step": 190
    },
    {
      "epoch": 0.0052078450978554095,
      "grad_norm": 0.3300645351409912,
      "learning_rate": 0.00010389610389610389,
      "loss": 0.676,
      "step": 200
    },
    {
      "epoch": 0.0054682373527481795,
      "grad_norm": 0.350356787443161,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.6564,
      "step": 210
    },
    {
      "epoch": 0.00572862960764095,
      "grad_norm": 0.382756769657135,
      "learning_rate": 0.00011428571428571428,
      "loss": 0.6243,
      "step": 220
    },
    {
      "epoch": 0.00598902186253372,
      "grad_norm": 0.34450188279151917,
      "learning_rate": 0.00011948051948051949,
      "loss": 0.6611,
      "step": 230
    },
    {
      "epoch": 0.006249414117426491,
      "grad_norm": 0.3705821633338928,
      "learning_rate": 0.00012467532467532467,
      "loss": 0.6384,
      "step": 240
    },
    {
      "epoch": 0.006509806372319262,
      "grad_norm": 0.36822304129600525,
      "learning_rate": 0.00012987012987012987,
      "loss": 0.6415,
      "step": 250
    },
    {
      "epoch": 0.006770198627212032,
      "grad_norm": 0.32358303666114807,
      "learning_rate": 0.00013506493506493507,
      "loss": 0.6584,
      "step": 260
    },
    {
      "epoch": 0.007030590882104803,
      "grad_norm": 0.33386844396591187,
      "learning_rate": 0.00014025974025974028,
      "loss": 0.6702,
      "step": 270
    },
    {
      "epoch": 0.007290983136997573,
      "grad_norm": 0.32447949051856995,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.6519,
      "step": 280
    },
    {
      "epoch": 0.007551375391890344,
      "grad_norm": 0.3388073146343231,
      "learning_rate": 0.00015064935064935066,
      "loss": 0.6735,
      "step": 290
    },
    {
      "epoch": 0.007811767646783114,
      "grad_norm": 0.39655518531799316,
      "learning_rate": 0.00015584415584415587,
      "loss": 0.672,
      "step": 300
    },
    {
      "epoch": 0.008072159901675884,
      "grad_norm": 0.41258928179740906,
      "learning_rate": 0.00016103896103896104,
      "loss": 0.6626,
      "step": 310
    },
    {
      "epoch": 0.008332552156568656,
      "grad_norm": 0.3963010311126709,
      "learning_rate": 0.00016623376623376625,
      "loss": 0.6653,
      "step": 320
    },
    {
      "epoch": 0.008592944411461426,
      "grad_norm": 0.3641106188297272,
      "learning_rate": 0.00017142857142857143,
      "loss": 0.6389,
      "step": 330
    },
    {
      "epoch": 0.008853336666354196,
      "grad_norm": 0.38745763897895813,
      "learning_rate": 0.00017662337662337663,
      "loss": 0.6928,
      "step": 340
    },
    {
      "epoch": 0.009113728921246966,
      "grad_norm": 0.4573372006416321,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.6679,
      "step": 350
    },
    {
      "epoch": 0.009374121176139737,
      "grad_norm": 0.45714282989501953,
      "learning_rate": 0.000187012987012987,
      "loss": 0.6453,
      "step": 360
    },
    {
      "epoch": 0.009634513431032507,
      "grad_norm": 0.37631818652153015,
      "learning_rate": 0.00019220779220779222,
      "loss": 0.6467,
      "step": 370
    },
    {
      "epoch": 0.009894905685925277,
      "grad_norm": 0.3658345639705658,
      "learning_rate": 0.00019740259740259742,
      "loss": 0.6631,
      "step": 380
    },
    {
      "epoch": 0.010155297940818049,
      "grad_norm": 0.3953540623188019,
      "learning_rate": 0.00019999996515752773,
      "loss": 0.6573,
      "step": 390
    },
    {
      "epoch": 0.010415690195710819,
      "grad_norm": 0.377763569355011,
      "learning_rate": 0.00019999968641789507,
      "loss": 0.6664,
      "step": 400
    },
    {
      "epoch": 0.010676082450603589,
      "grad_norm": 0.37128835916519165,
      "learning_rate": 0.0001999991289394067,
      "loss": 0.6342,
      "step": 410
    },
    {
      "epoch": 0.010936474705496359,
      "grad_norm": 0.33881694078445435,
      "learning_rate": 0.00019999829272361654,
      "loss": 0.6476,
      "step": 420
    },
    {
      "epoch": 0.01119686696038913,
      "grad_norm": 0.39774075150489807,
      "learning_rate": 0.00019999717777285545,
      "loss": 0.633,
      "step": 430
    },
    {
      "epoch": 0.0114572592152819,
      "grad_norm": 0.41350051760673523,
      "learning_rate": 0.00019999578409023126,
      "loss": 0.6541,
      "step": 440
    },
    {
      "epoch": 0.01171765147017467,
      "grad_norm": 0.47954171895980835,
      "learning_rate": 0.00019999411167962868,
      "loss": 0.6545,
      "step": 450
    },
    {
      "epoch": 0.01197804372506744,
      "grad_norm": 0.46860000491142273,
      "learning_rate": 0.00019999216054570942,
      "loss": 0.6512,
      "step": 460
    },
    {
      "epoch": 0.012238435979960213,
      "grad_norm": 0.4395809471607208,
      "learning_rate": 0.00019998993069391205,
      "loss": 0.6587,
      "step": 470
    },
    {
      "epoch": 0.012498828234852983,
      "grad_norm": 0.43222516775131226,
      "learning_rate": 0.00019998742213045206,
      "loss": 0.6292,
      "step": 480
    },
    {
      "epoch": 0.012759220489745753,
      "grad_norm": 0.39363613724708557,
      "learning_rate": 0.00019998463486232179,
      "loss": 0.6319,
      "step": 490
    },
    {
      "epoch": 0.013019612744638524,
      "grad_norm": 0.4984697699546814,
      "learning_rate": 0.0001999815688972905,
      "loss": 0.6488,
      "step": 500
    },
    {
      "epoch": 0.013280004999531294,
      "grad_norm": 0.4710462689399719,
      "learning_rate": 0.00019997822424390422,
      "loss": 0.6633,
      "step": 510
    },
    {
      "epoch": 0.013540397254424064,
      "grad_norm": 0.4141169786453247,
      "learning_rate": 0.00019997460091148586,
      "loss": 0.6471,
      "step": 520
    },
    {
      "epoch": 0.013800789509316834,
      "grad_norm": 0.39957430958747864,
      "learning_rate": 0.00019997069891013503,
      "loss": 0.6226,
      "step": 530
    },
    {
      "epoch": 0.014061181764209606,
      "grad_norm": 0.4508794844150543,
      "learning_rate": 0.00019996651825072826,
      "loss": 0.6559,
      "step": 540
    },
    {
      "epoch": 0.014321574019102376,
      "grad_norm": 0.4256739020347595,
      "learning_rate": 0.00019996205894491856,
      "loss": 0.6551,
      "step": 550
    },
    {
      "epoch": 0.014581966273995146,
      "grad_norm": 0.43204987049102783,
      "learning_rate": 0.00019995732100513592,
      "loss": 0.6254,
      "step": 560
    },
    {
      "epoch": 0.014842358528887916,
      "grad_norm": 0.37589946389198303,
      "learning_rate": 0.00019995230444458682,
      "loss": 0.6543,
      "step": 570
    },
    {
      "epoch": 0.015102750783780688,
      "grad_norm": 0.40850168466567993,
      "learning_rate": 0.0001999470092772544,
      "loss": 0.6474,
      "step": 580
    },
    {
      "epoch": 0.015363143038673458,
      "grad_norm": 0.3754895031452179,
      "learning_rate": 0.00019994143551789839,
      "loss": 0.6502,
      "step": 590
    },
    {
      "epoch": 0.015623535293566228,
      "grad_norm": 0.3857438266277313,
      "learning_rate": 0.00019993558318205507,
      "loss": 0.6544,
      "step": 600
    },
    {
      "epoch": 0.015883927548459,
      "grad_norm": 0.4063841998577118,
      "learning_rate": 0.00019992945228603724,
      "loss": 0.639,
      "step": 610
    },
    {
      "epoch": 0.016144319803351768,
      "grad_norm": 0.35183581709861755,
      "learning_rate": 0.0001999230428469341,
      "loss": 0.6442,
      "step": 620
    },
    {
      "epoch": 0.01640471205824454,
      "grad_norm": 0.4158167243003845,
      "learning_rate": 0.00019991635488261138,
      "loss": 0.6586,
      "step": 630
    },
    {
      "epoch": 0.01666510431313731,
      "grad_norm": 0.45118188858032227,
      "learning_rate": 0.00019990938841171104,
      "loss": 0.6581,
      "step": 640
    },
    {
      "epoch": 0.01692549656803008,
      "grad_norm": 0.39950400590896606,
      "learning_rate": 0.0001999021434536514,
      "loss": 0.6712,
      "step": 650
    },
    {
      "epoch": 0.01718588882292285,
      "grad_norm": 0.35208678245544434,
      "learning_rate": 0.00019989462002862704,
      "loss": 0.6398,
      "step": 660
    },
    {
      "epoch": 0.017446281077815623,
      "grad_norm": 0.38008975982666016,
      "learning_rate": 0.0001998868181576088,
      "loss": 0.6479,
      "step": 670
    },
    {
      "epoch": 0.01770667333270839,
      "grad_norm": 0.4314909875392914,
      "learning_rate": 0.00019987873786234348,
      "loss": 0.6358,
      "step": 680
    },
    {
      "epoch": 0.017967065587601163,
      "grad_norm": 0.3982577323913574,
      "learning_rate": 0.00019987037916535417,
      "loss": 0.6361,
      "step": 690
    },
    {
      "epoch": 0.01822745784249393,
      "grad_norm": 0.3529202342033386,
      "learning_rate": 0.0001998617420899398,
      "loss": 0.64,
      "step": 700
    },
    {
      "epoch": 0.018487850097386703,
      "grad_norm": 0.41149991750717163,
      "learning_rate": 0.0001998528266601754,
      "loss": 0.6684,
      "step": 710
    },
    {
      "epoch": 0.018748242352279475,
      "grad_norm": 0.42630311846733093,
      "learning_rate": 0.0001998436329009118,
      "loss": 0.6429,
      "step": 720
    },
    {
      "epoch": 0.019008634607172243,
      "grad_norm": 0.4028918147087097,
      "learning_rate": 0.00019983416083777563,
      "loss": 0.6573,
      "step": 730
    },
    {
      "epoch": 0.019269026862065015,
      "grad_norm": 0.3785901963710785,
      "learning_rate": 0.0001998244104971693,
      "loss": 0.6132,
      "step": 740
    },
    {
      "epoch": 0.019529419116957786,
      "grad_norm": 0.39018985629081726,
      "learning_rate": 0.0001998143819062709,
      "loss": 0.6287,
      "step": 750
    },
    {
      "epoch": 0.019789811371850555,
      "grad_norm": 0.4268128573894501,
      "learning_rate": 0.00019980407509303413,
      "loss": 0.6585,
      "step": 760
    },
    {
      "epoch": 0.020050203626743326,
      "grad_norm": 0.4293033480644226,
      "learning_rate": 0.00019979349008618808,
      "loss": 0.6843,
      "step": 770
    },
    {
      "epoch": 0.020310595881636098,
      "grad_norm": 0.38943207263946533,
      "learning_rate": 0.00019978262691523743,
      "loss": 0.6265,
      "step": 780
    },
    {
      "epoch": 0.020570988136528866,
      "grad_norm": 0.40528395771980286,
      "learning_rate": 0.00019977148561046217,
      "loss": 0.6392,
      "step": 790
    },
    {
      "epoch": 0.020831380391421638,
      "grad_norm": 0.4273380935192108,
      "learning_rate": 0.0001997600662029175,
      "loss": 0.6615,
      "step": 800
    },
    {
      "epoch": 0.021091772646314406,
      "grad_norm": 0.4269028306007385,
      "learning_rate": 0.00019974836872443388,
      "loss": 0.6412,
      "step": 810
    },
    {
      "epoch": 0.021352164901207178,
      "grad_norm": 0.3542031943798065,
      "learning_rate": 0.0001997363932076168,
      "loss": 0.6606,
      "step": 820
    },
    {
      "epoch": 0.02161255715609995,
      "grad_norm": 0.36826202273368835,
      "learning_rate": 0.00019972413968584682,
      "loss": 0.6387,
      "step": 830
    },
    {
      "epoch": 0.021872949410992718,
      "grad_norm": 0.4278506338596344,
      "learning_rate": 0.0001997116081932793,
      "loss": 0.6544,
      "step": 840
    },
    {
      "epoch": 0.02213334166588549,
      "grad_norm": 0.467886358499527,
      "learning_rate": 0.0001996987987648446,
      "loss": 0.6524,
      "step": 850
    },
    {
      "epoch": 0.02239373392077826,
      "grad_norm": 0.36823606491088867,
      "learning_rate": 0.0001996857114362476,
      "loss": 0.6553,
      "step": 860
    },
    {
      "epoch": 0.02265412617567103,
      "grad_norm": 0.42569059133529663,
      "learning_rate": 0.00019967234624396793,
      "loss": 0.6484,
      "step": 870
    },
    {
      "epoch": 0.0229145184305638,
      "grad_norm": 0.36995476484298706,
      "learning_rate": 0.00019965870322525965,
      "loss": 0.6626,
      "step": 880
    },
    {
      "epoch": 0.023174910685456573,
      "grad_norm": 0.4284444749355316,
      "learning_rate": 0.0001996447824181513,
      "loss": 0.6579,
      "step": 890
    },
    {
      "epoch": 0.02343530294034934,
      "grad_norm": 0.36263275146484375,
      "learning_rate": 0.0001996305838614457,
      "loss": 0.6466,
      "step": 900
    },
    {
      "epoch": 0.023695695195242113,
      "grad_norm": 0.43936702609062195,
      "learning_rate": 0.00019961610759471984,
      "loss": 0.6534,
      "step": 910
    },
    {
      "epoch": 0.02395608745013488,
      "grad_norm": 0.37757524847984314,
      "learning_rate": 0.00019960135365832486,
      "loss": 0.6344,
      "step": 920
    },
    {
      "epoch": 0.024216479705027653,
      "grad_norm": 0.40086570382118225,
      "learning_rate": 0.00019958632209338587,
      "loss": 0.6265,
      "step": 930
    },
    {
      "epoch": 0.024476871959920425,
      "grad_norm": 0.3435315489768982,
      "learning_rate": 0.00019957101294180174,
      "loss": 0.6479,
      "step": 940
    },
    {
      "epoch": 0.024737264214813193,
      "grad_norm": 0.34466204047203064,
      "learning_rate": 0.00019955542624624522,
      "loss": 0.641,
      "step": 950
    },
    {
      "epoch": 0.024997656469705965,
      "grad_norm": 0.46282994747161865,
      "learning_rate": 0.00019953956205016256,
      "loss": 0.6389,
      "step": 960
    },
    {
      "epoch": 0.025258048724598737,
      "grad_norm": 0.3815780580043793,
      "learning_rate": 0.00019952342039777362,
      "loss": 0.6472,
      "step": 970
    },
    {
      "epoch": 0.025518440979491505,
      "grad_norm": 0.43121904134750366,
      "learning_rate": 0.00019950700133407163,
      "loss": 0.6314,
      "step": 980
    },
    {
      "epoch": 0.025778833234384277,
      "grad_norm": 0.41635170578956604,
      "learning_rate": 0.00019949030490482296,
      "loss": 0.6483,
      "step": 990
    },
    {
      "epoch": 0.02603922548927705,
      "grad_norm": 0.3946804106235504,
      "learning_rate": 0.0001994733311565673,
      "loss": 0.6383,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 19202,
  "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": 5.6580410179584e+17,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}