{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018026137899954935,
      "grad_norm": 37.54188919067383,
      "learning_rate": 4.981949458483755e-05,
      "loss": 0.8911,
      "step": 10
    },
    {
      "epoch": 0.03605227579990987,
      "grad_norm": 15.440231323242188,
      "learning_rate": 4.963898916967509e-05,
      "loss": 0.6165,
      "step": 20
    },
    {
      "epoch": 0.054078413699864804,
      "grad_norm": 226.8269500732422,
      "learning_rate": 4.945848375451264e-05,
      "loss": 0.5151,
      "step": 30
    },
    {
      "epoch": 0.07210455159981974,
      "grad_norm": 21.70491600036621,
      "learning_rate": 4.927797833935018e-05,
      "loss": 0.5669,
      "step": 40
    },
    {
      "epoch": 0.09013068949977468,
      "grad_norm": 79.27781677246094,
      "learning_rate": 4.909747292418773e-05,
      "loss": 0.5119,
      "step": 50
    },
    {
      "epoch": 0.10815682739972961,
      "grad_norm": 15.314950942993164,
      "learning_rate": 4.891696750902527e-05,
      "loss": 0.474,
      "step": 60
    },
    {
      "epoch": 0.12618296529968454,
      "grad_norm": 25.575763702392578,
      "learning_rate": 4.873646209386282e-05,
      "loss": 0.478,
      "step": 70
    },
    {
      "epoch": 0.14420910319963948,
      "grad_norm": 27.453636169433594,
      "learning_rate": 4.855595667870036e-05,
      "loss": 0.4285,
      "step": 80
    },
    {
      "epoch": 0.16223524109959442,
      "grad_norm": 34.88062286376953,
      "learning_rate": 4.837545126353791e-05,
      "loss": 0.4317,
      "step": 90
    },
    {
      "epoch": 0.18026137899954936,
      "grad_norm": 46.823577880859375,
      "learning_rate": 4.819494584837546e-05,
      "loss": 0.4899,
      "step": 100
    },
    {
      "epoch": 0.19828751689950427,
      "grad_norm": 36.73914337158203,
      "learning_rate": 4.8014440433213e-05,
      "loss": 0.4839,
      "step": 110
    },
    {
      "epoch": 0.21631365479945922,
      "grad_norm": 102.61051940917969,
      "learning_rate": 4.783393501805055e-05,
      "loss": 0.4795,
      "step": 120
    },
    {
      "epoch": 0.23433979269941416,
      "grad_norm": 24.9108829498291,
      "learning_rate": 4.765342960288809e-05,
      "loss": 0.4332,
      "step": 130
    },
    {
      "epoch": 0.25236593059936907,
      "grad_norm": 14.366719245910645,
      "learning_rate": 4.747292418772563e-05,
      "loss": 0.4811,
      "step": 140
    },
    {
      "epoch": 0.270392068499324,
      "grad_norm": 19.95521354675293,
      "learning_rate": 4.7292418772563177e-05,
      "loss": 0.4544,
      "step": 150
    },
    {
      "epoch": 0.28841820639927895,
      "grad_norm": 20.914020538330078,
      "learning_rate": 4.711191335740072e-05,
      "loss": 0.4646,
      "step": 160
    },
    {
      "epoch": 0.3064443442992339,
      "grad_norm": 154.6277313232422,
      "learning_rate": 4.693140794223827e-05,
      "loss": 0.47,
      "step": 170
    },
    {
      "epoch": 0.32447048219918884,
      "grad_norm": 30.73076820373535,
      "learning_rate": 4.675090252707581e-05,
      "loss": 0.4341,
      "step": 180
    },
    {
      "epoch": 0.3424966200991438,
      "grad_norm": 14.621489524841309,
      "learning_rate": 4.657039711191336e-05,
      "loss": 0.5163,
      "step": 190
    },
    {
      "epoch": 0.3605227579990987,
      "grad_norm": 25.546030044555664,
      "learning_rate": 4.63898916967509e-05,
      "loss": 0.4601,
      "step": 200
    },
    {
      "epoch": 0.3785488958990536,
      "grad_norm": 18.222177505493164,
      "learning_rate": 4.620938628158845e-05,
      "loss": 0.4398,
      "step": 210
    },
    {
      "epoch": 0.39657503379900855,
      "grad_norm": 20.1109676361084,
      "learning_rate": 4.602888086642599e-05,
      "loss": 0.432,
      "step": 220
    },
    {
      "epoch": 0.4146011716989635,
      "grad_norm": 13.729535102844238,
      "learning_rate": 4.584837545126354e-05,
      "loss": 0.4327,
      "step": 230
    },
    {
      "epoch": 0.43262730959891843,
      "grad_norm": 32.50856018066406,
      "learning_rate": 4.566787003610109e-05,
      "loss": 0.4208,
      "step": 240
    },
    {
      "epoch": 0.45065344749887337,
      "grad_norm": 15.05933666229248,
      "learning_rate": 4.548736462093863e-05,
      "loss": 0.4451,
      "step": 250
    },
    {
      "epoch": 0.4686795853988283,
      "grad_norm": 31.787078857421875,
      "learning_rate": 4.530685920577618e-05,
      "loss": 0.4376,
      "step": 260
    },
    {
      "epoch": 0.48670572329878325,
      "grad_norm": 25.446210861206055,
      "learning_rate": 4.5126353790613716e-05,
      "loss": 0.4131,
      "step": 270
    },
    {
      "epoch": 0.5047318611987381,
      "grad_norm": 31.328969955444336,
      "learning_rate": 4.494584837545127e-05,
      "loss": 0.4194,
      "step": 280
    },
    {
      "epoch": 0.5227579990986931,
      "grad_norm": 255.53672790527344,
      "learning_rate": 4.4765342960288806e-05,
      "loss": 0.4984,
      "step": 290
    },
    {
      "epoch": 0.540784136998648,
      "grad_norm": 14.31953239440918,
      "learning_rate": 4.458483754512636e-05,
      "loss": 0.4417,
      "step": 300
    },
    {
      "epoch": 0.558810274898603,
      "grad_norm": 26.942129135131836,
      "learning_rate": 4.44043321299639e-05,
      "loss": 0.4527,
      "step": 310
    },
    {
      "epoch": 0.5768364127985579,
      "grad_norm": 36.217586517333984,
      "learning_rate": 4.422382671480145e-05,
      "loss": 0.4485,
      "step": 320
    },
    {
      "epoch": 0.5948625506985128,
      "grad_norm": 38.54646682739258,
      "learning_rate": 4.404332129963899e-05,
      "loss": 0.4579,
      "step": 330
    },
    {
      "epoch": 0.6128886885984678,
      "grad_norm": 21.504106521606445,
      "learning_rate": 4.386281588447654e-05,
      "loss": 0.4117,
      "step": 340
    },
    {
      "epoch": 0.6309148264984227,
      "grad_norm": 16.283788681030273,
      "learning_rate": 4.368231046931408e-05,
      "loss": 0.438,
      "step": 350
    },
    {
      "epoch": 0.6489409643983777,
      "grad_norm": 33.57164001464844,
      "learning_rate": 4.350180505415163e-05,
      "loss": 0.4043,
      "step": 360
    },
    {
      "epoch": 0.6669671022983326,
      "grad_norm": 12.821700096130371,
      "learning_rate": 4.332129963898917e-05,
      "loss": 0.4119,
      "step": 370
    },
    {
      "epoch": 0.6849932401982876,
      "grad_norm": 23.477996826171875,
      "learning_rate": 4.314079422382672e-05,
      "loss": 0.3783,
      "step": 380
    },
    {
      "epoch": 0.7030193780982424,
      "grad_norm": 18.2862548828125,
      "learning_rate": 4.296028880866426e-05,
      "loss": 0.4023,
      "step": 390
    },
    {
      "epoch": 0.7210455159981974,
      "grad_norm": 19.799530029296875,
      "learning_rate": 4.277978339350181e-05,
      "loss": 0.419,
      "step": 400
    },
    {
      "epoch": 0.7390716538981523,
      "grad_norm": 17.081830978393555,
      "learning_rate": 4.259927797833935e-05,
      "loss": 0.467,
      "step": 410
    },
    {
      "epoch": 0.7570977917981072,
      "grad_norm": 24.008344650268555,
      "learning_rate": 4.24187725631769e-05,
      "loss": 0.4302,
      "step": 420
    },
    {
      "epoch": 0.7751239296980622,
      "grad_norm": 40.07936477661133,
      "learning_rate": 4.223826714801444e-05,
      "loss": 0.3622,
      "step": 430
    },
    {
      "epoch": 0.7931500675980171,
      "grad_norm": 19.614171981811523,
      "learning_rate": 4.205776173285199e-05,
      "loss": 0.4645,
      "step": 440
    },
    {
      "epoch": 0.8111762054979721,
      "grad_norm": 32.0594596862793,
      "learning_rate": 4.187725631768953e-05,
      "loss": 0.3755,
      "step": 450
    },
    {
      "epoch": 0.829202343397927,
      "grad_norm": 15.177023887634277,
      "learning_rate": 4.169675090252708e-05,
      "loss": 0.4275,
      "step": 460
    },
    {
      "epoch": 0.847228481297882,
      "grad_norm": 11.258400917053223,
      "learning_rate": 4.151624548736462e-05,
      "loss": 0.4137,
      "step": 470
    },
    {
      "epoch": 0.8652546191978369,
      "grad_norm": 13.211421012878418,
      "learning_rate": 4.1335740072202167e-05,
      "loss": 0.4337,
      "step": 480
    },
    {
      "epoch": 0.8832807570977917,
      "grad_norm": 14.50296401977539,
      "learning_rate": 4.115523465703972e-05,
      "loss": 0.4318,
      "step": 490
    },
    {
      "epoch": 0.9013068949977467,
      "grad_norm": 21.239362716674805,
      "learning_rate": 4.0974729241877256e-05,
      "loss": 0.3939,
      "step": 500
    },
    {
      "epoch": 0.9193330328977016,
      "grad_norm": 18.6204891204834,
      "learning_rate": 4.079422382671481e-05,
      "loss": 0.3838,
      "step": 510
    },
    {
      "epoch": 0.9373591707976566,
      "grad_norm": 21.722551345825195,
      "learning_rate": 4.0613718411552346e-05,
      "loss": 0.4236,
      "step": 520
    },
    {
      "epoch": 0.9553853086976115,
      "grad_norm": 23.824357986450195,
      "learning_rate": 4.043321299638989e-05,
      "loss": 0.4062,
      "step": 530
    },
    {
      "epoch": 0.9734114465975665,
      "grad_norm": 18.93727684020996,
      "learning_rate": 4.0252707581227436e-05,
      "loss": 0.4412,
      "step": 540
    },
    {
      "epoch": 0.9914375844975214,
      "grad_norm": 16.050817489624023,
      "learning_rate": 4.007220216606498e-05,
      "loss": 0.4142,
      "step": 550
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.8390086641144469,
      "eval_fn": 205,
      "eval_fp": 594,
      "eval_loss": 0.3744712173938751,
      "eval_precision": 0.7780269058295964,
      "eval_recall": 0.910362920857018,
      "eval_runtime": 73.1391,
      "eval_samples_per_second": 63.892,
      "eval_steps_per_second": 7.998,
      "eval_tn": 1792,
      "eval_tp": 2082,
      "step": 555
    },
    {
      "epoch": 1.0090130689499774,
      "grad_norm": 26.528642654418945,
      "learning_rate": 3.989169675090253e-05,
      "loss": 0.3474,
      "step": 560
    },
    {
      "epoch": 1.0270392068499323,
      "grad_norm": 18.92278289794922,
      "learning_rate": 3.971119133574007e-05,
      "loss": 0.2881,
      "step": 570
    },
    {
      "epoch": 1.0450653447498874,
      "grad_norm": 15.88642406463623,
      "learning_rate": 3.953068592057762e-05,
      "loss": 0.3399,
      "step": 580
    },
    {
      "epoch": 1.0630914826498423,
      "grad_norm": 27.55136489868164,
      "learning_rate": 3.935018050541516e-05,
      "loss": 0.3125,
      "step": 590
    },
    {
      "epoch": 1.0811176205497972,
      "grad_norm": 18.58675765991211,
      "learning_rate": 3.916967509025271e-05,
      "loss": 0.3626,
      "step": 600
    },
    {
      "epoch": 1.099143758449752,
      "grad_norm": 22.22069549560547,
      "learning_rate": 3.898916967509025e-05,
      "loss": 0.2978,
      "step": 610
    },
    {
      "epoch": 1.117169896349707,
      "grad_norm": 29.50828742980957,
      "learning_rate": 3.88086642599278e-05,
      "loss": 0.3334,
      "step": 620
    },
    {
      "epoch": 1.135196034249662,
      "grad_norm": 18.485353469848633,
      "learning_rate": 3.862815884476535e-05,
      "loss": 0.3025,
      "step": 630
    },
    {
      "epoch": 1.153222172149617,
      "grad_norm": 16.8847599029541,
      "learning_rate": 3.844765342960289e-05,
      "loss": 0.329,
      "step": 640
    },
    {
      "epoch": 1.1712483100495719,
      "grad_norm": 25.133949279785156,
      "learning_rate": 3.826714801444044e-05,
      "loss": 0.2712,
      "step": 650
    },
    {
      "epoch": 1.1892744479495267,
      "grad_norm": 15.687613487243652,
      "learning_rate": 3.8086642599277976e-05,
      "loss": 0.345,
      "step": 660
    },
    {
      "epoch": 1.2073005858494819,
      "grad_norm": 18.612354278564453,
      "learning_rate": 3.790613718411553e-05,
      "loss": 0.3101,
      "step": 670
    },
    {
      "epoch": 1.2253267237494367,
      "grad_norm": 23.197965621948242,
      "learning_rate": 3.7725631768953066e-05,
      "loss": 0.3023,
      "step": 680
    },
    {
      "epoch": 1.2433528616493916,
      "grad_norm": 20.018022537231445,
      "learning_rate": 3.754512635379062e-05,
      "loss": 0.3302,
      "step": 690
    },
    {
      "epoch": 1.2613789995493465,
      "grad_norm": 55.68796157836914,
      "learning_rate": 3.7364620938628155e-05,
      "loss": 0.3265,
      "step": 700
    },
    {
      "epoch": 1.2794051374493014,
      "grad_norm": 18.61658477783203,
      "learning_rate": 3.718411552346571e-05,
      "loss": 0.2827,
      "step": 710
    },
    {
      "epoch": 1.2974312753492563,
      "grad_norm": 20.81103515625,
      "learning_rate": 3.700361010830325e-05,
      "loss": 0.3427,
      "step": 720
    },
    {
      "epoch": 1.3154574132492114,
      "grad_norm": 20.623382568359375,
      "learning_rate": 3.68231046931408e-05,
      "loss": 0.3241,
      "step": 730
    },
    {
      "epoch": 1.3334835511491663,
      "grad_norm": 18.186420440673828,
      "learning_rate": 3.664259927797834e-05,
      "loss": 0.3692,
      "step": 740
    },
    {
      "epoch": 1.3515096890491212,
      "grad_norm": 19.591402053833008,
      "learning_rate": 3.646209386281589e-05,
      "loss": 0.3237,
      "step": 750
    },
    {
      "epoch": 1.3695358269490763,
      "grad_norm": 29.652109146118164,
      "learning_rate": 3.628158844765343e-05,
      "loss": 0.3223,
      "step": 760
    },
    {
      "epoch": 1.3875619648490312,
      "grad_norm": 13.557708740234375,
      "learning_rate": 3.610108303249098e-05,
      "loss": 0.3534,
      "step": 770
    },
    {
      "epoch": 1.405588102748986,
      "grad_norm": 32.48282241821289,
      "learning_rate": 3.592057761732852e-05,
      "loss": 0.3476,
      "step": 780
    },
    {
      "epoch": 1.423614240648941,
      "grad_norm": 18.360185623168945,
      "learning_rate": 3.574007220216607e-05,
      "loss": 0.3506,
      "step": 790
    },
    {
      "epoch": 1.4416403785488958,
      "grad_norm": 18.72186279296875,
      "learning_rate": 3.555956678700361e-05,
      "loss": 0.3169,
      "step": 800
    },
    {
      "epoch": 1.4596665164488507,
      "grad_norm": 20.742034912109375,
      "learning_rate": 3.537906137184116e-05,
      "loss": 0.2974,
      "step": 810
    },
    {
      "epoch": 1.4776926543488058,
      "grad_norm": 27.217145919799805,
      "learning_rate": 3.51985559566787e-05,
      "loss": 0.3038,
      "step": 820
    },
    {
      "epoch": 1.4957187922487607,
      "grad_norm": 27.99778175354004,
      "learning_rate": 3.5018050541516247e-05,
      "loss": 0.3197,
      "step": 830
    },
    {
      "epoch": 1.5137449301487156,
      "grad_norm": 18.663578033447266,
      "learning_rate": 3.483754512635379e-05,
      "loss": 0.2899,
      "step": 840
    },
    {
      "epoch": 1.5317710680486707,
      "grad_norm": 19.825780868530273,
      "learning_rate": 3.4657039711191336e-05,
      "loss": 0.3086,
      "step": 850
    },
    {
      "epoch": 1.5497972059486256,
      "grad_norm": 25.401752471923828,
      "learning_rate": 3.447653429602888e-05,
      "loss": 0.3261,
      "step": 860
    },
    {
      "epoch": 1.5678233438485805,
      "grad_norm": 25.98396110534668,
      "learning_rate": 3.4296028880866426e-05,
      "loss": 0.3437,
      "step": 870
    },
    {
      "epoch": 1.5858494817485354,
      "grad_norm": 21.777820587158203,
      "learning_rate": 3.411552346570397e-05,
      "loss": 0.3243,
      "step": 880
    },
    {
      "epoch": 1.6038756196484902,
      "grad_norm": 12.681973457336426,
      "learning_rate": 3.3935018050541516e-05,
      "loss": 0.301,
      "step": 890
    },
    {
      "epoch": 1.6219017575484451,
      "grad_norm": 15.141433715820312,
      "learning_rate": 3.375451263537907e-05,
      "loss": 0.3557,
      "step": 900
    },
    {
      "epoch": 1.6399278954484002,
      "grad_norm": 24.14081382751465,
      "learning_rate": 3.3574007220216606e-05,
      "loss": 0.315,
      "step": 910
    },
    {
      "epoch": 1.6579540333483551,
      "grad_norm": 17.701383590698242,
      "learning_rate": 3.339350180505416e-05,
      "loss": 0.2934,
      "step": 920
    },
    {
      "epoch": 1.67598017124831,
      "grad_norm": 15.166337013244629,
      "learning_rate": 3.3212996389891696e-05,
      "loss": 0.3339,
      "step": 930
    },
    {
      "epoch": 1.694006309148265,
      "grad_norm": 19.966903686523438,
      "learning_rate": 3.303249097472924e-05,
      "loss": 0.3499,
      "step": 940
    },
    {
      "epoch": 1.71203244704822,
      "grad_norm": 44.75580596923828,
      "learning_rate": 3.2851985559566786e-05,
      "loss": 0.3243,
      "step": 950
    },
    {
      "epoch": 1.7300585849481749,
      "grad_norm": 20.718111038208008,
      "learning_rate": 3.267148014440433e-05,
      "loss": 0.3045,
      "step": 960
    },
    {
      "epoch": 1.7480847228481298,
      "grad_norm": 22.213359832763672,
      "learning_rate": 3.249097472924188e-05,
      "loss": 0.3172,
      "step": 970
    },
    {
      "epoch": 1.7661108607480847,
      "grad_norm": 26.86611557006836,
      "learning_rate": 3.231046931407942e-05,
      "loss": 0.3018,
      "step": 980
    },
    {
      "epoch": 1.7841369986480395,
      "grad_norm": 17.582984924316406,
      "learning_rate": 3.212996389891697e-05,
      "loss": 0.3658,
      "step": 990
    },
    {
      "epoch": 1.8021631365479944,
      "grad_norm": 35.41366958618164,
      "learning_rate": 3.194945848375451e-05,
      "loss": 0.295,
      "step": 1000
    },
    {
      "epoch": 1.8201892744479495,
      "grad_norm": 29.620559692382812,
      "learning_rate": 3.176895306859206e-05,
      "loss": 0.3218,
      "step": 1010
    },
    {
      "epoch": 1.8382154123479044,
      "grad_norm": 26.717348098754883,
      "learning_rate": 3.15884476534296e-05,
      "loss": 0.2965,
      "step": 1020
    },
    {
      "epoch": 1.8562415502478595,
      "grad_norm": 32.59479522705078,
      "learning_rate": 3.140794223826715e-05,
      "loss": 0.3378,
      "step": 1030
    },
    {
      "epoch": 1.8742676881478144,
      "grad_norm": 17.58369255065918,
      "learning_rate": 3.12274368231047e-05,
      "loss": 0.323,
      "step": 1040
    },
    {
      "epoch": 1.8922938260477693,
      "grad_norm": 30.458721160888672,
      "learning_rate": 3.104693140794224e-05,
      "loss": 0.3001,
      "step": 1050
    },
    {
      "epoch": 1.9103199639477242,
      "grad_norm": 21.08568000793457,
      "learning_rate": 3.086642599277979e-05,
      "loss": 0.2869,
      "step": 1060
    },
    {
      "epoch": 1.928346101847679,
      "grad_norm": 27.382286071777344,
      "learning_rate": 3.0685920577617325e-05,
      "loss": 0.2954,
      "step": 1070
    },
    {
      "epoch": 1.946372239747634,
      "grad_norm": 18.023101806640625,
      "learning_rate": 3.0505415162454877e-05,
      "loss": 0.3475,
      "step": 1080
    },
    {
      "epoch": 1.9643983776475888,
      "grad_norm": 21.446565628051758,
      "learning_rate": 3.032490974729242e-05,
      "loss": 0.3167,
      "step": 1090
    },
    {
      "epoch": 1.982424515547544,
      "grad_norm": 27.844911575317383,
      "learning_rate": 3.0144404332129967e-05,
      "loss": 0.321,
      "step": 1100
    },
    {
      "epoch": 2.0,
      "grad_norm": 23.883480072021484,
      "learning_rate": 2.996389891696751e-05,
      "loss": 0.2806,
      "step": 1110
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.8423625254582485,
      "eval_fn": 219,
      "eval_fp": 555,
      "eval_loss": 0.38451844453811646,
      "eval_precision": 0.7884102173084254,
      "eval_recall": 0.9042413642326191,
      "eval_runtime": 61.8973,
      "eval_samples_per_second": 75.496,
      "eval_steps_per_second": 9.451,
      "eval_tn": 1831,
      "eval_tp": 2068,
      "step": 1110
    }
  ],
  "logging_steps": 10,
  "max_steps": 2770,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 3.858514256176742e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}