{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.996845425867508,
  "eval_steps": 500,
  "global_step": 1108,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_f1": 0.45686228664952067,
      "eval_loss": 0.701814591884613,
      "eval_precision": 0.4909547738693467,
      "eval_recall": 0.42719720157411456,
      "eval_runtime": 72.3647,
      "eval_samples_per_second": 64.576,
      "eval_steps_per_second": 8.084,
      "step": 0
    },
    {
      "epoch": 0.018026137899954935,
      "grad_norm": 37.129154205322266,
      "learning_rate": 4.9548736462093865e-05,
      "loss": 0.8401,
      "step": 10
    },
    {
      "epoch": 0.03605227579990987,
      "grad_norm": 32.83527374267578,
      "learning_rate": 4.909747292418773e-05,
      "loss": 0.6093,
      "step": 20
    },
    {
      "epoch": 0.054078413699864804,
      "grad_norm": 48.55173873901367,
      "learning_rate": 4.864620938628159e-05,
      "loss": 0.5201,
      "step": 30
    },
    {
      "epoch": 0.07210455159981974,
      "grad_norm": 24.419078826904297,
      "learning_rate": 4.819494584837546e-05,
      "loss": 0.5847,
      "step": 40
    },
    {
      "epoch": 0.09013068949977468,
      "grad_norm": 27.96658706665039,
      "learning_rate": 4.7743682310469314e-05,
      "loss": 0.4958,
      "step": 50
    },
    {
      "epoch": 0.10815682739972961,
      "grad_norm": 28.15681266784668,
      "learning_rate": 4.7292418772563177e-05,
      "loss": 0.4754,
      "step": 60
    },
    {
      "epoch": 0.12618296529968454,
      "grad_norm": 27.729917526245117,
      "learning_rate": 4.684115523465704e-05,
      "loss": 0.4621,
      "step": 70
    },
    {
      "epoch": 0.14420910319963948,
      "grad_norm": 24.70597267150879,
      "learning_rate": 4.63898916967509e-05,
      "loss": 0.4333,
      "step": 80
    },
    {
      "epoch": 0.16223524109959442,
      "grad_norm": 30.800254821777344,
      "learning_rate": 4.5938628158844764e-05,
      "loss": 0.4425,
      "step": 90
    },
    {
      "epoch": 0.18026137899954936,
      "grad_norm": 37.59977340698242,
      "learning_rate": 4.548736462093863e-05,
      "loss": 0.4774,
      "step": 100
    },
    {
      "epoch": 0.19828751689950427,
      "grad_norm": 36.29924392700195,
      "learning_rate": 4.5036101083032495e-05,
      "loss": 0.4853,
      "step": 110
    },
    {
      "epoch": 0.21631365479945922,
      "grad_norm": 22.9832763671875,
      "learning_rate": 4.458483754512636e-05,
      "loss": 0.4419,
      "step": 120
    },
    {
      "epoch": 0.23433979269941416,
      "grad_norm": 35.384368896484375,
      "learning_rate": 4.413357400722022e-05,
      "loss": 0.4376,
      "step": 130
    },
    {
      "epoch": 0.25236593059936907,
      "grad_norm": 16.165664672851562,
      "learning_rate": 4.368231046931408e-05,
      "loss": 0.4557,
      "step": 140
    },
    {
      "epoch": 0.270392068499324,
      "grad_norm": 13.965127944946289,
      "learning_rate": 4.3231046931407945e-05,
      "loss": 0.4723,
      "step": 150
    },
    {
      "epoch": 0.28841820639927895,
      "grad_norm": 30.59395980834961,
      "learning_rate": 4.277978339350181e-05,
      "loss": 0.4656,
      "step": 160
    },
    {
      "epoch": 0.3064443442992339,
      "grad_norm": 27.32846450805664,
      "learning_rate": 4.232851985559567e-05,
      "loss": 0.4858,
      "step": 170
    },
    {
      "epoch": 0.32447048219918884,
      "grad_norm": 14.389259338378906,
      "learning_rate": 4.187725631768953e-05,
      "loss": 0.4604,
      "step": 180
    },
    {
      "epoch": 0.3424966200991438,
      "grad_norm": 17.084495544433594,
      "learning_rate": 4.1425992779783394e-05,
      "loss": 0.504,
      "step": 190
    },
    {
      "epoch": 0.3605227579990987,
      "grad_norm": 27.83977508544922,
      "learning_rate": 4.0974729241877256e-05,
      "loss": 0.4581,
      "step": 200
    },
    {
      "epoch": 0.3785488958990536,
      "grad_norm": 27.089218139648438,
      "learning_rate": 4.052346570397112e-05,
      "loss": 0.4239,
      "step": 210
    },
    {
      "epoch": 0.39657503379900855,
      "grad_norm": 22.199338912963867,
      "learning_rate": 4.007220216606498e-05,
      "loss": 0.4356,
      "step": 220
    },
    {
      "epoch": 0.4146011716989635,
      "grad_norm": 13.628811836242676,
      "learning_rate": 3.962093862815885e-05,
      "loss": 0.4363,
      "step": 230
    },
    {
      "epoch": 0.43262730959891843,
      "grad_norm": 27.136962890625,
      "learning_rate": 3.916967509025271e-05,
      "loss": 0.4419,
      "step": 240
    },
    {
      "epoch": 0.45065344749887337,
      "grad_norm": 21.228151321411133,
      "learning_rate": 3.8718411552346575e-05,
      "loss": 0.4258,
      "step": 250
    },
    {
      "epoch": 0.4686795853988283,
      "grad_norm": 21.63435935974121,
      "learning_rate": 3.826714801444044e-05,
      "loss": 0.4232,
      "step": 260
    },
    {
      "epoch": 0.48670572329878325,
      "grad_norm": 23.011816024780273,
      "learning_rate": 3.78158844765343e-05,
      "loss": 0.417,
      "step": 270
    },
    {
      "epoch": 0.5047318611987381,
      "grad_norm": 22.028409957885742,
      "learning_rate": 3.7364620938628155e-05,
      "loss": 0.3913,
      "step": 280
    },
    {
      "epoch": 0.5227579990986931,
      "grad_norm": 13.293946266174316,
      "learning_rate": 3.6913357400722025e-05,
      "loss": 0.4443,
      "step": 290
    },
    {
      "epoch": 0.540784136998648,
      "grad_norm": 16.026897430419922,
      "learning_rate": 3.646209386281589e-05,
      "loss": 0.4243,
      "step": 300
    },
    {
      "epoch": 0.558810274898603,
      "grad_norm": 22.489286422729492,
      "learning_rate": 3.601083032490975e-05,
      "loss": 0.4157,
      "step": 310
    },
    {
      "epoch": 0.5768364127985579,
      "grad_norm": 34.415470123291016,
      "learning_rate": 3.555956678700361e-05,
      "loss": 0.4159,
      "step": 320
    },
    {
      "epoch": 0.5948625506985128,
      "grad_norm": 28.348594665527344,
      "learning_rate": 3.5108303249097474e-05,
      "loss": 0.4409,
      "step": 330
    },
    {
      "epoch": 0.6128886885984678,
      "grad_norm": 16.92120933532715,
      "learning_rate": 3.4657039711191336e-05,
      "loss": 0.4034,
      "step": 340
    },
    {
      "epoch": 0.6309148264984227,
      "grad_norm": 15.073827743530273,
      "learning_rate": 3.42057761732852e-05,
      "loss": 0.4164,
      "step": 350
    },
    {
      "epoch": 0.6489409643983777,
      "grad_norm": 23.035175323486328,
      "learning_rate": 3.375451263537907e-05,
      "loss": 0.3952,
      "step": 360
    },
    {
      "epoch": 0.6669671022983326,
      "grad_norm": 19.5601806640625,
      "learning_rate": 3.330324909747293e-05,
      "loss": 0.3883,
      "step": 370
    },
    {
      "epoch": 0.6849932401982876,
      "grad_norm": 20.22748565673828,
      "learning_rate": 3.2851985559566786e-05,
      "loss": 0.3869,
      "step": 380
    },
    {
      "epoch": 0.7030193780982424,
      "grad_norm": 19.998939514160156,
      "learning_rate": 3.240072202166065e-05,
      "loss": 0.3889,
      "step": 390
    },
    {
      "epoch": 0.7210455159981974,
      "grad_norm": 27.682971954345703,
      "learning_rate": 3.194945848375451e-05,
      "loss": 0.4554,
      "step": 400
    },
    {
      "epoch": 0.7390716538981523,
      "grad_norm": 16.14117431640625,
      "learning_rate": 3.149819494584837e-05,
      "loss": 0.4202,
      "step": 410
    },
    {
      "epoch": 0.7570977917981072,
      "grad_norm": 30.020023345947266,
      "learning_rate": 3.104693140794224e-05,
      "loss": 0.4067,
      "step": 420
    },
    {
      "epoch": 0.7751239296980622,
      "grad_norm": 33.89706039428711,
      "learning_rate": 3.0595667870036104e-05,
      "loss": 0.3647,
      "step": 430
    },
    {
      "epoch": 0.7931500675980171,
      "grad_norm": 15.263274192810059,
      "learning_rate": 3.0144404332129967e-05,
      "loss": 0.4292,
      "step": 440
    },
    {
      "epoch": 0.8111762054979721,
      "grad_norm": 20.31402587890625,
      "learning_rate": 2.969314079422383e-05,
      "loss": 0.3802,
      "step": 450
    },
    {
      "epoch": 0.829202343397927,
      "grad_norm": 18.45032501220703,
      "learning_rate": 2.924187725631769e-05,
      "loss": 0.39,
      "step": 460
    },
    {
      "epoch": 0.847228481297882,
      "grad_norm": 13.733787536621094,
      "learning_rate": 2.879061371841155e-05,
      "loss": 0.3903,
      "step": 470
    },
    {
      "epoch": 0.8652546191978369,
      "grad_norm": 18.276058197021484,
      "learning_rate": 2.8339350180505413e-05,
      "loss": 0.4174,
      "step": 480
    },
    {
      "epoch": 0.8832807570977917,
      "grad_norm": 14.345264434814453,
      "learning_rate": 2.7888086642599282e-05,
      "loss": 0.4075,
      "step": 490
    },
    {
      "epoch": 0.9013068949977467,
      "grad_norm": 18.126863479614258,
      "learning_rate": 2.7436823104693144e-05,
      "loss": 0.3761,
      "step": 500
    },
    {
      "epoch": 0.9193330328977016,
      "grad_norm": 27.871076583862305,
      "learning_rate": 2.6985559566787007e-05,
      "loss": 0.3941,
      "step": 510
    },
    {
      "epoch": 0.9373591707976566,
      "grad_norm": 17.600557327270508,
      "learning_rate": 2.6534296028880866e-05,
      "loss": 0.3836,
      "step": 520
    },
    {
      "epoch": 0.9553853086976115,
      "grad_norm": 23.826416015625,
      "learning_rate": 2.6083032490974728e-05,
      "loss": 0.3882,
      "step": 530
    },
    {
      "epoch": 0.9734114465975665,
      "grad_norm": 17.19468116760254,
      "learning_rate": 2.563176895306859e-05,
      "loss": 0.4026,
      "step": 540
    },
    {
      "epoch": 0.9914375844975214,
      "grad_norm": 14.197047233581543,
      "learning_rate": 2.518050541516246e-05,
      "loss": 0.3874,
      "step": 550
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.8447773616312942,
      "eval_loss": 0.35632607340812683,
      "eval_precision": 0.8058753473600635,
      "eval_recall": 0.8876257105378225,
      "eval_runtime": 83.9871,
      "eval_samples_per_second": 55.639,
      "eval_steps_per_second": 6.965,
      "step": 555
    },
    {
      "epoch": 1.0090130689499774,
      "grad_norm": 15.379148483276367,
      "learning_rate": 2.472924187725632e-05,
      "loss": 0.336,
      "step": 560
    },
    {
      "epoch": 1.0270392068499323,
      "grad_norm": 26.69488525390625,
      "learning_rate": 2.427797833935018e-05,
      "loss": 0.2845,
      "step": 570
    },
    {
      "epoch": 1.0450653447498874,
      "grad_norm": 23.51136589050293,
      "learning_rate": 2.3826714801444043e-05,
      "loss": 0.3312,
      "step": 580
    },
    {
      "epoch": 1.0630914826498423,
      "grad_norm": 22.386554718017578,
      "learning_rate": 2.3375451263537906e-05,
      "loss": 0.287,
      "step": 590
    },
    {
      "epoch": 1.0811176205497972,
      "grad_norm": 18.04471206665039,
      "learning_rate": 2.292418772563177e-05,
      "loss": 0.3319,
      "step": 600
    },
    {
      "epoch": 1.099143758449752,
      "grad_norm": 18.214990615844727,
      "learning_rate": 2.2472924187725634e-05,
      "loss": 0.2626,
      "step": 610
    },
    {
      "epoch": 1.117169896349707,
      "grad_norm": 30.86859893798828,
      "learning_rate": 2.2021660649819496e-05,
      "loss": 0.3012,
      "step": 620
    },
    {
      "epoch": 1.135196034249662,
      "grad_norm": 20.468313217163086,
      "learning_rate": 2.157039711191336e-05,
      "loss": 0.2861,
      "step": 630
    },
    {
      "epoch": 1.153222172149617,
      "grad_norm": 13.948538780212402,
      "learning_rate": 2.111913357400722e-05,
      "loss": 0.3063,
      "step": 640
    },
    {
      "epoch": 1.1712483100495719,
      "grad_norm": 35.41230392456055,
      "learning_rate": 2.0667870036101083e-05,
      "loss": 0.2495,
      "step": 650
    },
    {
      "epoch": 1.1892744479495267,
      "grad_norm": 23.12849998474121,
      "learning_rate": 2.0216606498194946e-05,
      "loss": 0.3132,
      "step": 660
    },
    {
      "epoch": 1.2073005858494819,
      "grad_norm": 14.763388633728027,
      "learning_rate": 1.976534296028881e-05,
      "loss": 0.2822,
      "step": 670
    },
    {
      "epoch": 1.2253267237494367,
      "grad_norm": 16.697044372558594,
      "learning_rate": 1.9314079422382674e-05,
      "loss": 0.2592,
      "step": 680
    },
    {
      "epoch": 1.2433528616493916,
      "grad_norm": 39.87757873535156,
      "learning_rate": 1.8862815884476533e-05,
      "loss": 0.3114,
      "step": 690
    },
    {
      "epoch": 1.2613789995493465,
      "grad_norm": 38.50444793701172,
      "learning_rate": 1.84115523465704e-05,
      "loss": 0.2744,
      "step": 700
    },
    {
      "epoch": 1.2794051374493014,
      "grad_norm": 22.88275718688965,
      "learning_rate": 1.796028880866426e-05,
      "loss": 0.2454,
      "step": 710
    },
    {
      "epoch": 1.2974312753492563,
      "grad_norm": 24.772756576538086,
      "learning_rate": 1.7509025270758123e-05,
      "loss": 0.3065,
      "step": 720
    },
    {
      "epoch": 1.3154574132492114,
      "grad_norm": 25.954540252685547,
      "learning_rate": 1.7057761732851986e-05,
      "loss": 0.2714,
      "step": 730
    },
    {
      "epoch": 1.3334835511491663,
      "grad_norm": 19.4567928314209,
      "learning_rate": 1.6606498194945848e-05,
      "loss": 0.2797,
      "step": 740
    },
    {
      "epoch": 1.3515096890491212,
      "grad_norm": 20.511821746826172,
      "learning_rate": 1.615523465703971e-05,
      "loss": 0.2957,
      "step": 750
    },
    {
      "epoch": 1.3695358269490763,
      "grad_norm": 19.46160125732422,
      "learning_rate": 1.5703971119133576e-05,
      "loss": 0.278,
      "step": 760
    },
    {
      "epoch": 1.3875619648490312,
      "grad_norm": 17.91026496887207,
      "learning_rate": 1.5252707581227438e-05,
      "loss": 0.3295,
      "step": 770
    },
    {
      "epoch": 1.405588102748986,
      "grad_norm": 24.161779403686523,
      "learning_rate": 1.4801444043321299e-05,
      "loss": 0.3087,
      "step": 780
    },
    {
      "epoch": 1.423614240648941,
      "grad_norm": 16.5992488861084,
      "learning_rate": 1.4350180505415165e-05,
      "loss": 0.3138,
      "step": 790
    },
    {
      "epoch": 1.4416403785488958,
      "grad_norm": 19.812719345092773,
      "learning_rate": 1.3898916967509026e-05,
      "loss": 0.2671,
      "step": 800
    },
    {
      "epoch": 1.4596665164488507,
      "grad_norm": 26.38890838623047,
      "learning_rate": 1.3447653429602888e-05,
      "loss": 0.2655,
      "step": 810
    },
    {
      "epoch": 1.4776926543488058,
      "grad_norm": 25.614246368408203,
      "learning_rate": 1.299638989169675e-05,
      "loss": 0.285,
      "step": 820
    },
    {
      "epoch": 1.4957187922487607,
      "grad_norm": 23.396530151367188,
      "learning_rate": 1.2545126353790614e-05,
      "loss": 0.2871,
      "step": 830
    },
    {
      "epoch": 1.5137449301487156,
      "grad_norm": 19.622678756713867,
      "learning_rate": 1.2093862815884477e-05,
      "loss": 0.2754,
      "step": 840
    },
    {
      "epoch": 1.5317710680486707,
      "grad_norm": 17.912141799926758,
      "learning_rate": 1.164259927797834e-05,
      "loss": 0.2626,
      "step": 850
    },
    {
      "epoch": 1.5497972059486256,
      "grad_norm": 23.310211181640625,
      "learning_rate": 1.1191335740072201e-05,
      "loss": 0.2829,
      "step": 860
    },
    {
      "epoch": 1.5678233438485805,
      "grad_norm": 19.311479568481445,
      "learning_rate": 1.0740072202166066e-05,
      "loss": 0.287,
      "step": 870
    },
    {
      "epoch": 1.5858494817485354,
      "grad_norm": 25.074918746948242,
      "learning_rate": 1.028880866425993e-05,
      "loss": 0.292,
      "step": 880
    },
    {
      "epoch": 1.6038756196484902,
      "grad_norm": 18.028676986694336,
      "learning_rate": 9.83754512635379e-06,
      "loss": 0.2635,
      "step": 890
    },
    {
      "epoch": 1.6219017575484451,
      "grad_norm": 22.707019805908203,
      "learning_rate": 9.386281588447654e-06,
      "loss": 0.3303,
      "step": 900
    },
    {
      "epoch": 1.6399278954484002,
      "grad_norm": 26.213523864746094,
      "learning_rate": 8.935018050541517e-06,
      "loss": 0.2572,
      "step": 910
    },
    {
      "epoch": 1.6579540333483551,
      "grad_norm": 27.651395797729492,
      "learning_rate": 8.483754512635379e-06,
      "loss": 0.2673,
      "step": 920
    },
    {
      "epoch": 1.67598017124831,
      "grad_norm": 16.422618865966797,
      "learning_rate": 8.032490974729243e-06,
      "loss": 0.2793,
      "step": 930
    },
    {
      "epoch": 1.694006309148265,
      "grad_norm": 25.192127227783203,
      "learning_rate": 7.581227436823105e-06,
      "loss": 0.3019,
      "step": 940
    },
    {
      "epoch": 1.71203244704822,
      "grad_norm": 32.72596740722656,
      "learning_rate": 7.129963898916968e-06,
      "loss": 0.2722,
      "step": 950
    },
    {
      "epoch": 1.7300585849481749,
      "grad_norm": 20.50579833984375,
      "learning_rate": 6.678700361010831e-06,
      "loss": 0.2662,
      "step": 960
    },
    {
      "epoch": 1.7480847228481298,
      "grad_norm": 29.32863426208496,
      "learning_rate": 6.227436823104693e-06,
      "loss": 0.2576,
      "step": 970
    },
    {
      "epoch": 1.7661108607480847,
      "grad_norm": 24.872976303100586,
      "learning_rate": 5.776173285198557e-06,
      "loss": 0.2532,
      "step": 980
    },
    {
      "epoch": 1.7841369986480395,
      "grad_norm": 21.214448928833008,
      "learning_rate": 5.324909747292419e-06,
      "loss": 0.3031,
      "step": 990
    },
    {
      "epoch": 1.8021631365479944,
      "grad_norm": 23.342086791992188,
      "learning_rate": 4.873646209386281e-06,
      "loss": 0.2646,
      "step": 1000
    },
    {
      "epoch": 1.8201892744479495,
      "grad_norm": 16.437740325927734,
      "learning_rate": 4.422382671480145e-06,
      "loss": 0.275,
      "step": 1010
    },
    {
      "epoch": 1.8382154123479044,
      "grad_norm": 24.245403289794922,
      "learning_rate": 3.971119133574008e-06,
      "loss": 0.2762,
      "step": 1020
    },
    {
      "epoch": 1.8562415502478595,
      "grad_norm": 30.563308715820312,
      "learning_rate": 3.51985559566787e-06,
      "loss": 0.2667,
      "step": 1030
    },
    {
      "epoch": 1.8742676881478144,
      "grad_norm": 30.939002990722656,
      "learning_rate": 3.068592057761733e-06,
      "loss": 0.28,
      "step": 1040
    },
    {
      "epoch": 1.8922938260477693,
      "grad_norm": 24.054363250732422,
      "learning_rate": 2.6173285198555957e-06,
      "loss": 0.2451,
      "step": 1050
    },
    {
      "epoch": 1.9103199639477242,
      "grad_norm": 18.180830001831055,
      "learning_rate": 2.1660649819494585e-06,
      "loss": 0.2484,
      "step": 1060
    },
    {
      "epoch": 1.928346101847679,
      "grad_norm": 26.393966674804688,
      "learning_rate": 1.7148014440433215e-06,
      "loss": 0.2941,
      "step": 1070
    },
    {
      "epoch": 1.946372239747634,
      "grad_norm": 18.06760597229004,
      "learning_rate": 1.263537906137184e-06,
      "loss": 0.2859,
      "step": 1080
    },
    {
      "epoch": 1.9643983776475888,
      "grad_norm": 21.646621704101562,
      "learning_rate": 8.122743682310469e-07,
      "loss": 0.2654,
      "step": 1090
    },
    {
      "epoch": 1.982424515547544,
      "grad_norm": 22.391935348510742,
      "learning_rate": 3.610108303249098e-07,
      "loss": 0.27,
      "step": 1100
    },
    {
      "epoch": 1.996845425867508,
      "eval_f1": 0.8420606317574729,
      "eval_loss": 0.3596021831035614,
      "eval_precision": 0.817283950617284,
      "eval_recall": 0.8683865325754263,
      "eval_runtime": 74.0407,
      "eval_samples_per_second": 63.114,
      "eval_steps_per_second": 7.901,
      "step": 1108
    }
  ],
  "logging_steps": 10,
  "max_steps": 1108,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.852428271545549e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}