{
  "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,
      "eval_f1": 0.6562770562770562,
      "eval_loss": 0.7476533651351929,
      "eval_precision": 0.48976954555244456,
      "eval_recall": 0.9943156974202011,
      "eval_runtime": 16.4688,
      "eval_samples_per_second": 283.749,
      "eval_steps_per_second": 35.522,
      "step": 0
    },
    {
      "epoch": 0.018026137899954935,
      "grad_norm": 14.20566463470459,
      "learning_rate": 4.981949458483755e-05,
      "loss": 0.6876,
      "step": 10
    },
    {
      "epoch": 0.03605227579990987,
      "grad_norm": 27.79998016357422,
      "learning_rate": 4.963898916967509e-05,
      "loss": 0.5988,
      "step": 20
    },
    {
      "epoch": 0.054078413699864804,
      "grad_norm": 39.63682556152344,
      "learning_rate": 4.945848375451264e-05,
      "loss": 0.5677,
      "step": 30
    },
    {
      "epoch": 0.07210455159981974,
      "grad_norm": 38.49867630004883,
      "learning_rate": 4.927797833935018e-05,
      "loss": 0.5922,
      "step": 40
    },
    {
      "epoch": 0.09013068949977468,
      "grad_norm": 52.28614044189453,
      "learning_rate": 4.909747292418773e-05,
      "loss": 0.5506,
      "step": 50
    },
    {
      "epoch": 0.10815682739972961,
      "grad_norm": 29.180490493774414,
      "learning_rate": 4.891696750902527e-05,
      "loss": 0.5173,
      "step": 60
    },
    {
      "epoch": 0.12618296529968454,
      "grad_norm": 33.55237579345703,
      "learning_rate": 4.873646209386282e-05,
      "loss": 0.4931,
      "step": 70
    },
    {
      "epoch": 0.14420910319963948,
      "grad_norm": 32.063228607177734,
      "learning_rate": 4.855595667870036e-05,
      "loss": 0.483,
      "step": 80
    },
    {
      "epoch": 0.16223524109959442,
      "grad_norm": 24.234926223754883,
      "learning_rate": 4.837545126353791e-05,
      "loss": 0.47,
      "step": 90
    },
    {
      "epoch": 0.18026137899954936,
      "grad_norm": 33.66775894165039,
      "learning_rate": 4.819494584837546e-05,
      "loss": 0.4564,
      "step": 100
    },
    {
      "epoch": 0.19828751689950427,
      "grad_norm": 53.322574615478516,
      "learning_rate": 4.8014440433213e-05,
      "loss": 0.5083,
      "step": 110
    },
    {
      "epoch": 0.21631365479945922,
      "grad_norm": 29.443470001220703,
      "learning_rate": 4.783393501805055e-05,
      "loss": 0.463,
      "step": 120
    },
    {
      "epoch": 0.23433979269941416,
      "grad_norm": 33.13877487182617,
      "learning_rate": 4.765342960288809e-05,
      "loss": 0.4626,
      "step": 130
    },
    {
      "epoch": 0.25236593059936907,
      "grad_norm": 25.509536743164062,
      "learning_rate": 4.747292418772563e-05,
      "loss": 0.5113,
      "step": 140
    },
    {
      "epoch": 0.270392068499324,
      "grad_norm": 21.015031814575195,
      "learning_rate": 4.7292418772563177e-05,
      "loss": 0.4611,
      "step": 150
    },
    {
      "epoch": 0.28841820639927895,
      "grad_norm": 28.079387664794922,
      "learning_rate": 4.711191335740072e-05,
      "loss": 0.4783,
      "step": 160
    },
    {
      "epoch": 0.3064443442992339,
      "grad_norm": 19.978599548339844,
      "learning_rate": 4.693140794223827e-05,
      "loss": 0.5026,
      "step": 170
    },
    {
      "epoch": 0.32447048219918884,
      "grad_norm": 29.316265106201172,
      "learning_rate": 4.675090252707581e-05,
      "loss": 0.4906,
      "step": 180
    },
    {
      "epoch": 0.3424966200991438,
      "grad_norm": 18.79282569885254,
      "learning_rate": 4.657039711191336e-05,
      "loss": 0.5016,
      "step": 190
    },
    {
      "epoch": 0.3605227579990987,
      "grad_norm": 18.66801643371582,
      "learning_rate": 4.63898916967509e-05,
      "loss": 0.4502,
      "step": 200
    },
    {
      "epoch": 0.3785488958990536,
      "grad_norm": 27.929332733154297,
      "learning_rate": 4.620938628158845e-05,
      "loss": 0.4302,
      "step": 210
    },
    {
      "epoch": 0.39657503379900855,
      "grad_norm": 20.541879653930664,
      "learning_rate": 4.602888086642599e-05,
      "loss": 0.4496,
      "step": 220
    },
    {
      "epoch": 0.4146011716989635,
      "grad_norm": 19.034873962402344,
      "learning_rate": 4.584837545126354e-05,
      "loss": 0.4541,
      "step": 230
    },
    {
      "epoch": 0.43262730959891843,
      "grad_norm": 32.077945709228516,
      "learning_rate": 4.566787003610109e-05,
      "loss": 0.4562,
      "step": 240
    },
    {
      "epoch": 0.45065344749887337,
      "grad_norm": 25.475997924804688,
      "learning_rate": 4.548736462093863e-05,
      "loss": 0.4456,
      "step": 250
    },
    {
      "epoch": 0.4686795853988283,
      "grad_norm": 17.132720947265625,
      "learning_rate": 4.530685920577618e-05,
      "loss": 0.4629,
      "step": 260
    },
    {
      "epoch": 0.48670572329878325,
      "grad_norm": 22.313941955566406,
      "learning_rate": 4.5126353790613716e-05,
      "loss": 0.4444,
      "step": 270
    },
    {
      "epoch": 0.5047318611987381,
      "grad_norm": 22.373477935791016,
      "learning_rate": 4.494584837545127e-05,
      "loss": 0.4404,
      "step": 280
    },
    {
      "epoch": 0.5227579990986931,
      "grad_norm": 16.72430992126465,
      "learning_rate": 4.4765342960288806e-05,
      "loss": 0.4611,
      "step": 290
    },
    {
      "epoch": 0.540784136998648,
      "grad_norm": 27.037927627563477,
      "learning_rate": 4.458483754512636e-05,
      "loss": 0.4272,
      "step": 300
    },
    {
      "epoch": 0.558810274898603,
      "grad_norm": 31.637985229492188,
      "learning_rate": 4.44043321299639e-05,
      "loss": 0.448,
      "step": 310
    },
    {
      "epoch": 0.5768364127985579,
      "grad_norm": 35.010459899902344,
      "learning_rate": 4.422382671480145e-05,
      "loss": 0.4215,
      "step": 320
    },
    {
      "epoch": 0.5948625506985128,
      "grad_norm": 26.25156021118164,
      "learning_rate": 4.404332129963899e-05,
      "loss": 0.4396,
      "step": 330
    },
    {
      "epoch": 0.6128886885984678,
      "grad_norm": 19.4619083404541,
      "learning_rate": 4.386281588447654e-05,
      "loss": 0.4378,
      "step": 340
    },
    {
      "epoch": 0.6309148264984227,
      "grad_norm": 19.16460609436035,
      "learning_rate": 4.368231046931408e-05,
      "loss": 0.4366,
      "step": 350
    },
    {
      "epoch": 0.6489409643983777,
      "grad_norm": 30.745384216308594,
      "learning_rate": 4.350180505415163e-05,
      "loss": 0.4062,
      "step": 360
    },
    {
      "epoch": 0.6669671022983326,
      "grad_norm": 16.873245239257812,
      "learning_rate": 4.332129963898917e-05,
      "loss": 0.439,
      "step": 370
    },
    {
      "epoch": 0.6849932401982876,
      "grad_norm": 25.771486282348633,
      "learning_rate": 4.314079422382672e-05,
      "loss": 0.4053,
      "step": 380
    },
    {
      "epoch": 0.7030193780982424,
      "grad_norm": 14.48513412475586,
      "learning_rate": 4.296028880866426e-05,
      "loss": 0.4164,
      "step": 390
    },
    {
      "epoch": 0.7210455159981974,
      "grad_norm": 34.993465423583984,
      "learning_rate": 4.277978339350181e-05,
      "loss": 0.4438,
      "step": 400
    },
    {
      "epoch": 0.7390716538981523,
      "grad_norm": 22.576608657836914,
      "learning_rate": 4.259927797833935e-05,
      "loss": 0.4518,
      "step": 410
    },
    {
      "epoch": 0.7570977917981072,
      "grad_norm": 19.088132858276367,
      "learning_rate": 4.24187725631769e-05,
      "loss": 0.4495,
      "step": 420
    },
    {
      "epoch": 0.7751239296980622,
      "grad_norm": 35.2998046875,
      "learning_rate": 4.223826714801444e-05,
      "loss": 0.3897,
      "step": 430
    },
    {
      "epoch": 0.7931500675980171,
      "grad_norm": 20.395572662353516,
      "learning_rate": 4.205776173285199e-05,
      "loss": 0.4818,
      "step": 440
    },
    {
      "epoch": 0.8111762054979721,
      "grad_norm": 21.174386978149414,
      "learning_rate": 4.187725631768953e-05,
      "loss": 0.4103,
      "step": 450
    },
    {
      "epoch": 0.829202343397927,
      "grad_norm": 32.97265625,
      "learning_rate": 4.169675090252708e-05,
      "loss": 0.4036,
      "step": 460
    },
    {
      "epoch": 0.847228481297882,
      "grad_norm": 23.78690528869629,
      "learning_rate": 4.151624548736462e-05,
      "loss": 0.4079,
      "step": 470
    },
    {
      "epoch": 0.8652546191978369,
      "grad_norm": 17.087247848510742,
      "learning_rate": 4.1335740072202167e-05,
      "loss": 0.4371,
      "step": 480
    },
    {
      "epoch": 0.8832807570977917,
      "grad_norm": 13.810160636901855,
      "learning_rate": 4.115523465703972e-05,
      "loss": 0.4249,
      "step": 490
    },
    {
      "epoch": 0.9013068949977467,
      "grad_norm": 20.197996139526367,
      "learning_rate": 4.0974729241877256e-05,
      "loss": 0.3991,
      "step": 500
    },
    {
      "epoch": 0.9193330328977016,
      "grad_norm": 33.1153564453125,
      "learning_rate": 4.079422382671481e-05,
      "loss": 0.3994,
      "step": 510
    },
    {
      "epoch": 0.9373591707976566,
      "grad_norm": 18.20081901550293,
      "learning_rate": 4.0613718411552346e-05,
      "loss": 0.4176,
      "step": 520
    },
    {
      "epoch": 0.9553853086976115,
      "grad_norm": 20.09193992614746,
      "learning_rate": 4.043321299638989e-05,
      "loss": 0.4297,
      "step": 530
    },
    {
      "epoch": 0.9734114465975665,
      "grad_norm": 15.939692497253418,
      "learning_rate": 4.0252707581227436e-05,
      "loss": 0.4309,
      "step": 540
    },
    {
      "epoch": 0.9914375844975214,
      "grad_norm": 24.811601638793945,
      "learning_rate": 4.007220216606498e-05,
      "loss": 0.3908,
      "step": 550
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.8367177786987153,
      "eval_loss": 0.37827184796333313,
      "eval_precision": 0.7951949586451359,
      "eval_recall": 0.8828159160472234,
      "eval_runtime": 15.9582,
      "eval_samples_per_second": 292.827,
      "eval_steps_per_second": 36.658,
      "step": 555
    },
    {
      "epoch": 1.0090130689499774,
      "grad_norm": 16.960424423217773,
      "learning_rate": 3.989169675090253e-05,
      "loss": 0.3719,
      "step": 560
    },
    {
      "epoch": 1.0270392068499323,
      "grad_norm": 15.816173553466797,
      "learning_rate": 3.971119133574007e-05,
      "loss": 0.3238,
      "step": 570
    },
    {
      "epoch": 1.0450653447498874,
      "grad_norm": 19.375043869018555,
      "learning_rate": 3.953068592057762e-05,
      "loss": 0.3516,
      "step": 580
    },
    {
      "epoch": 1.0630914826498423,
      "grad_norm": 36.740943908691406,
      "learning_rate": 3.935018050541516e-05,
      "loss": 0.3329,
      "step": 590
    },
    {
      "epoch": 1.0811176205497972,
      "grad_norm": 23.23931884765625,
      "learning_rate": 3.916967509025271e-05,
      "loss": 0.345,
      "step": 600
    },
    {
      "epoch": 1.099143758449752,
      "grad_norm": 23.009553909301758,
      "learning_rate": 3.898916967509025e-05,
      "loss": 0.3054,
      "step": 610
    },
    {
      "epoch": 1.117169896349707,
      "grad_norm": 18.865903854370117,
      "learning_rate": 3.88086642599278e-05,
      "loss": 0.3236,
      "step": 620
    },
    {
      "epoch": 1.135196034249662,
      "grad_norm": 21.043642044067383,
      "learning_rate": 3.862815884476535e-05,
      "loss": 0.3092,
      "step": 630
    },
    {
      "epoch": 1.153222172149617,
      "grad_norm": 22.50505256652832,
      "learning_rate": 3.844765342960289e-05,
      "loss": 0.3274,
      "step": 640
    },
    {
      "epoch": 1.1712483100495719,
      "grad_norm": 20.4163818359375,
      "learning_rate": 3.826714801444044e-05,
      "loss": 0.2459,
      "step": 650
    },
    {
      "epoch": 1.1892744479495267,
      "grad_norm": 21.210535049438477,
      "learning_rate": 3.8086642599277976e-05,
      "loss": 0.3365,
      "step": 660
    },
    {
      "epoch": 1.2073005858494819,
      "grad_norm": 21.084487915039062,
      "learning_rate": 3.790613718411553e-05,
      "loss": 0.3242,
      "step": 670
    },
    {
      "epoch": 1.2253267237494367,
      "grad_norm": 22.721454620361328,
      "learning_rate": 3.7725631768953066e-05,
      "loss": 0.2844,
      "step": 680
    },
    {
      "epoch": 1.2433528616493916,
      "grad_norm": 49.28988265991211,
      "learning_rate": 3.754512635379062e-05,
      "loss": 0.3247,
      "step": 690
    },
    {
      "epoch": 1.2613789995493465,
      "grad_norm": 48.35593795776367,
      "learning_rate": 3.7364620938628155e-05,
      "loss": 0.3217,
      "step": 700
    },
    {
      "epoch": 1.2794051374493014,
      "grad_norm": 30.997228622436523,
      "learning_rate": 3.718411552346571e-05,
      "loss": 0.2854,
      "step": 710
    },
    {
      "epoch": 1.2974312753492563,
      "grad_norm": 35.57414627075195,
      "learning_rate": 3.700361010830325e-05,
      "loss": 0.3315,
      "step": 720
    },
    {
      "epoch": 1.3154574132492114,
      "grad_norm": 27.17759895324707,
      "learning_rate": 3.68231046931408e-05,
      "loss": 0.2965,
      "step": 730
    },
    {
      "epoch": 1.3334835511491663,
      "grad_norm": 31.296627044677734,
      "learning_rate": 3.664259927797834e-05,
      "loss": 0.3396,
      "step": 740
    },
    {
      "epoch": 1.3515096890491212,
      "grad_norm": 18.639175415039062,
      "learning_rate": 3.646209386281589e-05,
      "loss": 0.3178,
      "step": 750
    },
    {
      "epoch": 1.3695358269490763,
      "grad_norm": 31.972665786743164,
      "learning_rate": 3.628158844765343e-05,
      "loss": 0.2927,
      "step": 760
    },
    {
      "epoch": 1.3875619648490312,
      "grad_norm": 14.907872200012207,
      "learning_rate": 3.610108303249098e-05,
      "loss": 0.3391,
      "step": 770
    },
    {
      "epoch": 1.405588102748986,
      "grad_norm": 33.58858871459961,
      "learning_rate": 3.592057761732852e-05,
      "loss": 0.3111,
      "step": 780
    },
    {
      "epoch": 1.423614240648941,
      "grad_norm": 17.019819259643555,
      "learning_rate": 3.574007220216607e-05,
      "loss": 0.3401,
      "step": 790
    },
    {
      "epoch": 1.4416403785488958,
      "grad_norm": 27.324296951293945,
      "learning_rate": 3.555956678700361e-05,
      "loss": 0.2917,
      "step": 800
    },
    {
      "epoch": 1.4596665164488507,
      "grad_norm": 30.170120239257812,
      "learning_rate": 3.537906137184116e-05,
      "loss": 0.2871,
      "step": 810
    },
    {
      "epoch": 1.4776926543488058,
      "grad_norm": 44.26614761352539,
      "learning_rate": 3.51985559566787e-05,
      "loss": 0.3307,
      "step": 820
    },
    {
      "epoch": 1.4957187922487607,
      "grad_norm": 28.978620529174805,
      "learning_rate": 3.5018050541516247e-05,
      "loss": 0.3207,
      "step": 830
    },
    {
      "epoch": 1.5137449301487156,
      "grad_norm": 22.961040496826172,
      "learning_rate": 3.483754512635379e-05,
      "loss": 0.3075,
      "step": 840
    },
    {
      "epoch": 1.5317710680486707,
      "grad_norm": 22.511327743530273,
      "learning_rate": 3.4657039711191336e-05,
      "loss": 0.3035,
      "step": 850
    },
    {
      "epoch": 1.5497972059486256,
      "grad_norm": 33.944190979003906,
      "learning_rate": 3.447653429602888e-05,
      "loss": 0.3243,
      "step": 860
    },
    {
      "epoch": 1.5678233438485805,
      "grad_norm": 24.72734832763672,
      "learning_rate": 3.4296028880866426e-05,
      "loss": 0.3403,
      "step": 870
    },
    {
      "epoch": 1.5858494817485354,
      "grad_norm": 31.211387634277344,
      "learning_rate": 3.411552346570397e-05,
      "loss": 0.3142,
      "step": 880
    },
    {
      "epoch": 1.6038756196484902,
      "grad_norm": 23.974918365478516,
      "learning_rate": 3.3935018050541516e-05,
      "loss": 0.3015,
      "step": 890
    },
    {
      "epoch": 1.6219017575484451,
      "grad_norm": 30.705829620361328,
      "learning_rate": 3.375451263537907e-05,
      "loss": 0.3529,
      "step": 900
    },
    {
      "epoch": 1.6399278954484002,
      "grad_norm": 20.697528839111328,
      "learning_rate": 3.3574007220216606e-05,
      "loss": 0.302,
      "step": 910
    },
    {
      "epoch": 1.6579540333483551,
      "grad_norm": 28.308101654052734,
      "learning_rate": 3.339350180505416e-05,
      "loss": 0.2735,
      "step": 920
    },
    {
      "epoch": 1.67598017124831,
      "grad_norm": 22.28900909423828,
      "learning_rate": 3.3212996389891696e-05,
      "loss": 0.3194,
      "step": 930
    },
    {
      "epoch": 1.694006309148265,
      "grad_norm": 29.04107666015625,
      "learning_rate": 3.303249097472924e-05,
      "loss": 0.3265,
      "step": 940
    },
    {
      "epoch": 1.71203244704822,
      "grad_norm": 40.08032989501953,
      "learning_rate": 3.2851985559566786e-05,
      "loss": 0.3331,
      "step": 950
    },
    {
      "epoch": 1.7300585849481749,
      "grad_norm": 29.40334129333496,
      "learning_rate": 3.267148014440433e-05,
      "loss": 0.2664,
      "step": 960
    },
    {
      "epoch": 1.7480847228481298,
      "grad_norm": 33.51088333129883,
      "learning_rate": 3.249097472924188e-05,
      "loss": 0.3031,
      "step": 970
    },
    {
      "epoch": 1.7661108607480847,
      "grad_norm": 27.003469467163086,
      "learning_rate": 3.231046931407942e-05,
      "loss": 0.3195,
      "step": 980
    },
    {
      "epoch": 1.7841369986480395,
      "grad_norm": 26.585309982299805,
      "learning_rate": 3.212996389891697e-05,
      "loss": 0.3385,
      "step": 990
    },
    {
      "epoch": 1.8021631365479944,
      "grad_norm": 36.866294860839844,
      "learning_rate": 3.194945848375451e-05,
      "loss": 0.3029,
      "step": 1000
    },
    {
      "epoch": 1.8201892744479495,
      "grad_norm": 44.910362243652344,
      "learning_rate": 3.176895306859206e-05,
      "loss": 0.3239,
      "step": 1010
    },
    {
      "epoch": 1.8382154123479044,
      "grad_norm": 20.13945198059082,
      "learning_rate": 3.15884476534296e-05,
      "loss": 0.3071,
      "step": 1020
    },
    {
      "epoch": 1.8562415502478595,
      "grad_norm": 42.44215774536133,
      "learning_rate": 3.140794223826715e-05,
      "loss": 0.3246,
      "step": 1030
    },
    {
      "epoch": 1.8742676881478144,
      "grad_norm": 31.791410446166992,
      "learning_rate": 3.12274368231047e-05,
      "loss": 0.3273,
      "step": 1040
    },
    {
      "epoch": 1.8922938260477693,
      "grad_norm": 21.244722366333008,
      "learning_rate": 3.104693140794224e-05,
      "loss": 0.3093,
      "step": 1050
    },
    {
      "epoch": 1.9103199639477242,
      "grad_norm": 27.103349685668945,
      "learning_rate": 3.086642599277979e-05,
      "loss": 0.2694,
      "step": 1060
    },
    {
      "epoch": 1.928346101847679,
      "grad_norm": 35.73145294189453,
      "learning_rate": 3.0685920577617325e-05,
      "loss": 0.2934,
      "step": 1070
    },
    {
      "epoch": 1.946372239747634,
      "grad_norm": 19.97008514404297,
      "learning_rate": 3.0505415162454877e-05,
      "loss": 0.3493,
      "step": 1080
    },
    {
      "epoch": 1.9643983776475888,
      "grad_norm": 23.084754943847656,
      "learning_rate": 3.032490974729242e-05,
      "loss": 0.3243,
      "step": 1090
    },
    {
      "epoch": 1.982424515547544,
      "grad_norm": 29.515155792236328,
      "learning_rate": 3.0144404332129967e-05,
      "loss": 0.3235,
      "step": 1100
    },
    {
      "epoch": 2.0,
      "grad_norm": 24.17915916442871,
      "learning_rate": 2.996389891696751e-05,
      "loss": 0.2751,
      "step": 1110
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.8428896708755951,
      "eval_loss": 0.3940623104572296,
      "eval_precision": 0.800314465408805,
      "eval_recall": 0.890249234805422,
      "eval_runtime": 12.3989,
      "eval_samples_per_second": 376.889,
      "eval_steps_per_second": 47.182,
      "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": 9341494909501440.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}