{
  "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": 0.1456953642384106,
      "eval_fn": 11,
      "eval_fp": 4117,
      "eval_loss": 0.7862394452095032,
      "eval_precision": 0.07876482434549116,
      "eval_recall": 0.9696969696969697,
      "eval_runtime": 48.4563,
      "eval_samples_per_second": 96.437,
      "eval_steps_per_second": 6.047,
      "eval_tn": 193,
      "eval_tp": 352,
      "step": 0
    },
    {
      "epoch": 0.018026137899954935,
      "grad_norm": 5.399981498718262,
      "learning_rate": 4.9548736462093865e-05,
      "loss": 0.5179,
      "step": 10
    },
    {
      "epoch": 0.03605227579990987,
      "grad_norm": 1.6319377422332764,
      "learning_rate": 4.909747292418773e-05,
      "loss": 0.2969,
      "step": 20
    },
    {
      "epoch": 0.054078413699864804,
      "grad_norm": 1.8271431922912598,
      "learning_rate": 4.864620938628159e-05,
      "loss": 0.3075,
      "step": 30
    },
    {
      "epoch": 0.07210455159981974,
      "grad_norm": 2.5912694931030273,
      "learning_rate": 4.819494584837546e-05,
      "loss": 0.3096,
      "step": 40
    },
    {
      "epoch": 0.09013068949977468,
      "grad_norm": 3.3950061798095703,
      "learning_rate": 4.7743682310469314e-05,
      "loss": 0.2585,
      "step": 50
    },
    {
      "epoch": 0.10815682739972961,
      "grad_norm": 1.6037261486053467,
      "learning_rate": 4.7292418772563177e-05,
      "loss": 0.2461,
      "step": 60
    },
    {
      "epoch": 0.12618296529968454,
      "grad_norm": 3.6747143268585205,
      "learning_rate": 4.684115523465704e-05,
      "loss": 0.2803,
      "step": 70
    },
    {
      "epoch": 0.14420910319963948,
      "grad_norm": 6.330898284912109,
      "learning_rate": 4.63898916967509e-05,
      "loss": 0.2735,
      "step": 80
    },
    {
      "epoch": 0.16223524109959442,
      "grad_norm": 4.724136829376221,
      "learning_rate": 4.5938628158844764e-05,
      "loss": 0.2551,
      "step": 90
    },
    {
      "epoch": 0.18026137899954936,
      "grad_norm": 3.852949619293213,
      "learning_rate": 4.548736462093863e-05,
      "loss": 0.2286,
      "step": 100
    },
    {
      "epoch": 0.19828751689950427,
      "grad_norm": 10.743219375610352,
      "learning_rate": 4.5036101083032495e-05,
      "loss": 0.2511,
      "step": 110
    },
    {
      "epoch": 0.21631365479945922,
      "grad_norm": 24.62398910522461,
      "learning_rate": 4.458483754512636e-05,
      "loss": 0.1756,
      "step": 120
    },
    {
      "epoch": 0.23433979269941416,
      "grad_norm": 6.864269256591797,
      "learning_rate": 4.413357400722022e-05,
      "loss": 0.1947,
      "step": 130
    },
    {
      "epoch": 0.25236593059936907,
      "grad_norm": 11.810012817382812,
      "learning_rate": 4.368231046931408e-05,
      "loss": 0.1976,
      "step": 140
    },
    {
      "epoch": 0.270392068499324,
      "grad_norm": 4.794726848602295,
      "learning_rate": 4.3231046931407945e-05,
      "loss": 0.2081,
      "step": 150
    },
    {
      "epoch": 0.28841820639927895,
      "grad_norm": 7.1115875244140625,
      "learning_rate": 4.277978339350181e-05,
      "loss": 0.2055,
      "step": 160
    },
    {
      "epoch": 0.3064443442992339,
      "grad_norm": 6.199843883514404,
      "learning_rate": 4.232851985559567e-05,
      "loss": 0.1764,
      "step": 170
    },
    {
      "epoch": 0.32447048219918884,
      "grad_norm": 5.7516679763793945,
      "learning_rate": 4.187725631768953e-05,
      "loss": 0.185,
      "step": 180
    },
    {
      "epoch": 0.3424966200991438,
      "grad_norm": 17.204120635986328,
      "learning_rate": 4.1425992779783394e-05,
      "loss": 0.175,
      "step": 190
    },
    {
      "epoch": 0.3605227579990987,
      "grad_norm": 6.416110038757324,
      "learning_rate": 4.0974729241877256e-05,
      "loss": 0.1197,
      "step": 200
    },
    {
      "epoch": 0.3785488958990536,
      "grad_norm": 8.525187492370605,
      "learning_rate": 4.052346570397112e-05,
      "loss": 0.1968,
      "step": 210
    },
    {
      "epoch": 0.39657503379900855,
      "grad_norm": 42.04795455932617,
      "learning_rate": 4.007220216606498e-05,
      "loss": 0.1718,
      "step": 220
    },
    {
      "epoch": 0.4146011716989635,
      "grad_norm": 4.502872467041016,
      "learning_rate": 3.962093862815885e-05,
      "loss": 0.1442,
      "step": 230
    },
    {
      "epoch": 0.43262730959891843,
      "grad_norm": 3.215198278427124,
      "learning_rate": 3.916967509025271e-05,
      "loss": 0.1675,
      "step": 240
    },
    {
      "epoch": 0.45065344749887337,
      "grad_norm": 6.314309120178223,
      "learning_rate": 3.8718411552346575e-05,
      "loss": 0.1492,
      "step": 250
    },
    {
      "epoch": 0.4686795853988283,
      "grad_norm": 8.839702606201172,
      "learning_rate": 3.826714801444044e-05,
      "loss": 0.1399,
      "step": 260
    },
    {
      "epoch": 0.48670572329878325,
      "grad_norm": 183.9261016845703,
      "learning_rate": 3.78158844765343e-05,
      "loss": 0.1801,
      "step": 270
    },
    {
      "epoch": 0.5047318611987381,
      "grad_norm": 5.393545150756836,
      "learning_rate": 3.7364620938628155e-05,
      "loss": 0.1353,
      "step": 280
    },
    {
      "epoch": 0.5227579990986931,
      "grad_norm": 3.587885856628418,
      "learning_rate": 3.6913357400722025e-05,
      "loss": 0.1428,
      "step": 290
    },
    {
      "epoch": 0.540784136998648,
      "grad_norm": 9.456450462341309,
      "learning_rate": 3.646209386281589e-05,
      "loss": 0.1758,
      "step": 300
    },
    {
      "epoch": 0.558810274898603,
      "grad_norm": 4.051924705505371,
      "learning_rate": 3.601083032490975e-05,
      "loss": 0.1874,
      "step": 310
    },
    {
      "epoch": 0.5768364127985579,
      "grad_norm": 6.4390363693237305,
      "learning_rate": 3.555956678700361e-05,
      "loss": 0.1472,
      "step": 320
    },
    {
      "epoch": 0.5948625506985128,
      "grad_norm": 3.86102557182312,
      "learning_rate": 3.5108303249097474e-05,
      "loss": 0.1659,
      "step": 330
    },
    {
      "epoch": 0.6128886885984678,
      "grad_norm": 6.6616644859313965,
      "learning_rate": 3.4657039711191336e-05,
      "loss": 0.191,
      "step": 340
    },
    {
      "epoch": 0.6309148264984227,
      "grad_norm": 6.867959976196289,
      "learning_rate": 3.42057761732852e-05,
      "loss": 0.1343,
      "step": 350
    },
    {
      "epoch": 0.6489409643983777,
      "grad_norm": 8.724226951599121,
      "learning_rate": 3.375451263537907e-05,
      "loss": 0.145,
      "step": 360
    },
    {
      "epoch": 0.6669671022983326,
      "grad_norm": 3.5500874519348145,
      "learning_rate": 3.330324909747293e-05,
      "loss": 0.1153,
      "step": 370
    },
    {
      "epoch": 0.6849932401982876,
      "grad_norm": 9.760895729064941,
      "learning_rate": 3.2851985559566786e-05,
      "loss": 0.1362,
      "step": 380
    },
    {
      "epoch": 0.7030193780982424,
      "grad_norm": 3.9465765953063965,
      "learning_rate": 3.240072202166065e-05,
      "loss": 0.1281,
      "step": 390
    },
    {
      "epoch": 0.7210455159981974,
      "grad_norm": 3.495382070541382,
      "learning_rate": 3.194945848375451e-05,
      "loss": 0.1792,
      "step": 400
    },
    {
      "epoch": 0.7390716538981523,
      "grad_norm": 2.8898510932922363,
      "learning_rate": 3.149819494584837e-05,
      "loss": 0.1085,
      "step": 410
    },
    {
      "epoch": 0.7570977917981072,
      "grad_norm": 3.3261382579803467,
      "learning_rate": 3.104693140794224e-05,
      "loss": 0.203,
      "step": 420
    },
    {
      "epoch": 0.7751239296980622,
      "grad_norm": 3.417875051498413,
      "learning_rate": 3.0595667870036104e-05,
      "loss": 0.1491,
      "step": 430
    },
    {
      "epoch": 0.7931500675980171,
      "grad_norm": 7.868630409240723,
      "learning_rate": 3.0144404332129967e-05,
      "loss": 0.1777,
      "step": 440
    },
    {
      "epoch": 0.8111762054979721,
      "grad_norm": 2.16607403755188,
      "learning_rate": 2.969314079422383e-05,
      "loss": 0.1406,
      "step": 450
    },
    {
      "epoch": 0.829202343397927,
      "grad_norm": 5.121480464935303,
      "learning_rate": 2.924187725631769e-05,
      "loss": 0.1387,
      "step": 460
    },
    {
      "epoch": 0.847228481297882,
      "grad_norm": 6.610152244567871,
      "learning_rate": 2.879061371841155e-05,
      "loss": 0.1158,
      "step": 470
    },
    {
      "epoch": 0.8652546191978369,
      "grad_norm": 5.962329387664795,
      "learning_rate": 2.8339350180505413e-05,
      "loss": 0.127,
      "step": 480
    },
    {
      "epoch": 0.8832807570977917,
      "grad_norm": 5.11064338684082,
      "learning_rate": 2.7888086642599282e-05,
      "loss": 0.1232,
      "step": 490
    },
    {
      "epoch": 0.9013068949977467,
      "grad_norm": 5.128263473510742,
      "learning_rate": 2.7436823104693144e-05,
      "loss": 0.1084,
      "step": 500
    },
    {
      "epoch": 0.9193330328977016,
      "grad_norm": 8.249767303466797,
      "learning_rate": 2.6985559566787007e-05,
      "loss": 0.1453,
      "step": 510
    },
    {
      "epoch": 0.9373591707976566,
      "grad_norm": 14.850152969360352,
      "learning_rate": 2.6534296028880866e-05,
      "loss": 0.1102,
      "step": 520
    },
    {
      "epoch": 0.9553853086976115,
      "grad_norm": 4.934476852416992,
      "learning_rate": 2.6083032490974728e-05,
      "loss": 0.1493,
      "step": 530
    },
    {
      "epoch": 0.9734114465975665,
      "grad_norm": 6.984730243682861,
      "learning_rate": 2.563176895306859e-05,
      "loss": 0.1344,
      "step": 540
    },
    {
      "epoch": 0.9914375844975214,
      "grad_norm": 4.595370292663574,
      "learning_rate": 2.518050541516246e-05,
      "loss": 0.1246,
      "step": 550
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.7272727272727273,
      "eval_fn": 95,
      "eval_fp": 106,
      "eval_loss": 0.11311017721891403,
      "eval_precision": 0.7165775401069518,
      "eval_recall": 0.7382920110192838,
      "eval_runtime": 56.8141,
      "eval_samples_per_second": 82.251,
      "eval_steps_per_second": 5.157,
      "eval_tn": 4204,
      "eval_tp": 268,
      "step": 555
    },
    {
      "epoch": 1.0090130689499774,
      "grad_norm": 3.8490426540374756,
      "learning_rate": 2.472924187725632e-05,
      "loss": 0.131,
      "step": 560
    },
    {
      "epoch": 1.0270392068499323,
      "grad_norm": 8.608445167541504,
      "learning_rate": 2.427797833935018e-05,
      "loss": 0.0894,
      "step": 570
    },
    {
      "epoch": 1.0450653447498874,
      "grad_norm": 7.926303863525391,
      "learning_rate": 2.3826714801444043e-05,
      "loss": 0.1462,
      "step": 580
    },
    {
      "epoch": 1.0630914826498423,
      "grad_norm": 5.411970138549805,
      "learning_rate": 2.3375451263537906e-05,
      "loss": 0.1556,
      "step": 590
    },
    {
      "epoch": 1.0811176205497972,
      "grad_norm": 6.707615375518799,
      "learning_rate": 2.292418772563177e-05,
      "loss": 0.0999,
      "step": 600
    },
    {
      "epoch": 1.099143758449752,
      "grad_norm": 5.215950012207031,
      "learning_rate": 2.2472924187725634e-05,
      "loss": 0.0854,
      "step": 610
    },
    {
      "epoch": 1.117169896349707,
      "grad_norm": 1.6493467092514038,
      "learning_rate": 2.2021660649819496e-05,
      "loss": 0.0806,
      "step": 620
    },
    {
      "epoch": 1.135196034249662,
      "grad_norm": 8.559683799743652,
      "learning_rate": 2.157039711191336e-05,
      "loss": 0.1422,
      "step": 630
    },
    {
      "epoch": 1.153222172149617,
      "grad_norm": 3.0874404907226562,
      "learning_rate": 2.111913357400722e-05,
      "loss": 0.1436,
      "step": 640
    },
    {
      "epoch": 1.1712483100495719,
      "grad_norm": 13.975804328918457,
      "learning_rate": 2.0667870036101083e-05,
      "loss": 0.1294,
      "step": 650
    },
    {
      "epoch": 1.1892744479495267,
      "grad_norm": 52.61249923706055,
      "learning_rate": 2.0216606498194946e-05,
      "loss": 0.127,
      "step": 660
    },
    {
      "epoch": 1.2073005858494819,
      "grad_norm": 4.427943706512451,
      "learning_rate": 1.976534296028881e-05,
      "loss": 0.1101,
      "step": 670
    },
    {
      "epoch": 1.2253267237494367,
      "grad_norm": 3.466806411743164,
      "learning_rate": 1.9314079422382674e-05,
      "loss": 0.0733,
      "step": 680
    },
    {
      "epoch": 1.2433528616493916,
      "grad_norm": 7.252458572387695,
      "learning_rate": 1.8862815884476533e-05,
      "loss": 0.1129,
      "step": 690
    },
    {
      "epoch": 1.2613789995493465,
      "grad_norm": 7.521577835083008,
      "learning_rate": 1.84115523465704e-05,
      "loss": 0.0894,
      "step": 700
    },
    {
      "epoch": 1.2794051374493014,
      "grad_norm": 2.96766996383667,
      "learning_rate": 1.796028880866426e-05,
      "loss": 0.0828,
      "step": 710
    },
    {
      "epoch": 1.2974312753492563,
      "grad_norm": 3.5544350147247314,
      "learning_rate": 1.7509025270758123e-05,
      "loss": 0.1205,
      "step": 720
    },
    {
      "epoch": 1.3154574132492114,
      "grad_norm": 2.323742389678955,
      "learning_rate": 1.7057761732851986e-05,
      "loss": 0.1114,
      "step": 730
    },
    {
      "epoch": 1.3334835511491663,
      "grad_norm": 4.532501220703125,
      "learning_rate": 1.6606498194945848e-05,
      "loss": 0.1242,
      "step": 740
    },
    {
      "epoch": 1.3515096890491212,
      "grad_norm": 4.962907314300537,
      "learning_rate": 1.615523465703971e-05,
      "loss": 0.1222,
      "step": 750
    },
    {
      "epoch": 1.3695358269490763,
      "grad_norm": 2.745126724243164,
      "learning_rate": 1.5703971119133576e-05,
      "loss": 0.1089,
      "step": 760
    },
    {
      "epoch": 1.3875619648490312,
      "grad_norm": 1.2508844137191772,
      "learning_rate": 1.5252707581227438e-05,
      "loss": 0.086,
      "step": 770
    },
    {
      "epoch": 1.405588102748986,
      "grad_norm": 9.282389640808105,
      "learning_rate": 1.4801444043321299e-05,
      "loss": 0.1142,
      "step": 780
    },
    {
      "epoch": 1.423614240648941,
      "grad_norm": 3.1791019439697266,
      "learning_rate": 1.4350180505415165e-05,
      "loss": 0.1237,
      "step": 790
    },
    {
      "epoch": 1.4416403785488958,
      "grad_norm": 6.121169567108154,
      "learning_rate": 1.3898916967509026e-05,
      "loss": 0.1346,
      "step": 800
    },
    {
      "epoch": 1.4596665164488507,
      "grad_norm": 19.356491088867188,
      "learning_rate": 1.3447653429602888e-05,
      "loss": 0.0937,
      "step": 810
    },
    {
      "epoch": 1.4776926543488058,
      "grad_norm": 6.563851356506348,
      "learning_rate": 1.299638989169675e-05,
      "loss": 0.1136,
      "step": 820
    },
    {
      "epoch": 1.4957187922487607,
      "grad_norm": 5.794551372528076,
      "learning_rate": 1.2545126353790614e-05,
      "loss": 0.119,
      "step": 830
    },
    {
      "epoch": 1.5137449301487156,
      "grad_norm": 2.885023832321167,
      "learning_rate": 1.2093862815884477e-05,
      "loss": 0.1073,
      "step": 840
    },
    {
      "epoch": 1.5317710680486707,
      "grad_norm": 3.519407272338867,
      "learning_rate": 1.164259927797834e-05,
      "loss": 0.122,
      "step": 850
    },
    {
      "epoch": 1.5497972059486256,
      "grad_norm": 3.4222164154052734,
      "learning_rate": 1.1191335740072201e-05,
      "loss": 0.1002,
      "step": 860
    },
    {
      "epoch": 1.5678233438485805,
      "grad_norm": 8.442163467407227,
      "learning_rate": 1.0740072202166066e-05,
      "loss": 0.1301,
      "step": 870
    },
    {
      "epoch": 1.5858494817485354,
      "grad_norm": 5.987030982971191,
      "learning_rate": 1.028880866425993e-05,
      "loss": 0.1197,
      "step": 880
    },
    {
      "epoch": 1.6038756196484902,
      "grad_norm": 3.641470432281494,
      "learning_rate": 9.83754512635379e-06,
      "loss": 0.094,
      "step": 890
    },
    {
      "epoch": 1.6219017575484451,
      "grad_norm": 4.365111827850342,
      "learning_rate": 9.386281588447654e-06,
      "loss": 0.1309,
      "step": 900
    },
    {
      "epoch": 1.6399278954484002,
      "grad_norm": 6.229074478149414,
      "learning_rate": 8.935018050541517e-06,
      "loss": 0.1002,
      "step": 910
    },
    {
      "epoch": 1.6579540333483551,
      "grad_norm": 8.32435417175293,
      "learning_rate": 8.483754512635379e-06,
      "loss": 0.1155,
      "step": 920
    },
    {
      "epoch": 1.67598017124831,
      "grad_norm": 2.6587719917297363,
      "learning_rate": 8.032490974729243e-06,
      "loss": 0.1047,
      "step": 930
    },
    {
      "epoch": 1.694006309148265,
      "grad_norm": 31.095243453979492,
      "learning_rate": 7.581227436823105e-06,
      "loss": 0.0957,
      "step": 940
    },
    {
      "epoch": 1.71203244704822,
      "grad_norm": 148.5176544189453,
      "learning_rate": 7.129963898916968e-06,
      "loss": 0.1138,
      "step": 950
    },
    {
      "epoch": 1.7300585849481749,
      "grad_norm": 4.901301383972168,
      "learning_rate": 6.678700361010831e-06,
      "loss": 0.0939,
      "step": 960
    },
    {
      "epoch": 1.7480847228481298,
      "grad_norm": 4.844261646270752,
      "learning_rate": 6.227436823104693e-06,
      "loss": 0.0905,
      "step": 970
    },
    {
      "epoch": 1.7661108607480847,
      "grad_norm": 6.100379943847656,
      "learning_rate": 5.776173285198557e-06,
      "loss": 0.1169,
      "step": 980
    },
    {
      "epoch": 1.7841369986480395,
      "grad_norm": 9.385725021362305,
      "learning_rate": 5.324909747292419e-06,
      "loss": 0.0843,
      "step": 990
    },
    {
      "epoch": 1.8021631365479944,
      "grad_norm": 8.386088371276855,
      "learning_rate": 4.873646209386281e-06,
      "loss": 0.1044,
      "step": 1000
    },
    {
      "epoch": 1.8201892744479495,
      "grad_norm": 13.418025970458984,
      "learning_rate": 4.422382671480145e-06,
      "loss": 0.1351,
      "step": 1010
    },
    {
      "epoch": 1.8382154123479044,
      "grad_norm": 13.804243087768555,
      "learning_rate": 3.971119133574008e-06,
      "loss": 0.0919,
      "step": 1020
    },
    {
      "epoch": 1.8562415502478595,
      "grad_norm": 7.5179924964904785,
      "learning_rate": 3.51985559566787e-06,
      "loss": 0.1305,
      "step": 1030
    },
    {
      "epoch": 1.8742676881478144,
      "grad_norm": 4.629436016082764,
      "learning_rate": 3.068592057761733e-06,
      "loss": 0.1278,
      "step": 1040
    },
    {
      "epoch": 1.8922938260477693,
      "grad_norm": 5.896274566650391,
      "learning_rate": 2.6173285198555957e-06,
      "loss": 0.1211,
      "step": 1050
    },
    {
      "epoch": 1.9103199639477242,
      "grad_norm": 7.580524921417236,
      "learning_rate": 2.1660649819494585e-06,
      "loss": 0.0993,
      "step": 1060
    },
    {
      "epoch": 1.928346101847679,
      "grad_norm": 12.92769718170166,
      "learning_rate": 1.7148014440433215e-06,
      "loss": 0.1557,
      "step": 1070
    },
    {
      "epoch": 1.946372239747634,
      "grad_norm": 12.059624671936035,
      "learning_rate": 1.263537906137184e-06,
      "loss": 0.0929,
      "step": 1080
    },
    {
      "epoch": 1.9643983776475888,
      "grad_norm": 4.273173809051514,
      "learning_rate": 8.122743682310469e-07,
      "loss": 0.1053,
      "step": 1090
    },
    {
      "epoch": 1.982424515547544,
      "grad_norm": 7.6728596687316895,
      "learning_rate": 3.610108303249098e-07,
      "loss": 0.0997,
      "step": 1100
    },
    {
      "epoch": 1.996845425867508,
      "eval_f1": 0.7513513513513513,
      "eval_fn": 85,
      "eval_fp": 99,
      "eval_loss": 0.10865739732980728,
      "eval_precision": 0.7374005305039788,
      "eval_recall": 0.7658402203856749,
      "eval_runtime": 59.9339,
      "eval_samples_per_second": 77.969,
      "eval_steps_per_second": 4.889,
      "eval_tn": 4211,
      "eval_tp": 278,
      "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": 7.68611172962304e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}