{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "global_step": 21190,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24,
      "learning_rate": 1.952807928268051e-05,
      "loss": 0.1097,
      "step": 500
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.905615856536102e-05,
      "loss": 0.0885,
      "step": 1000
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.858423784804153e-05,
      "loss": 0.1291,
      "step": 1500
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8112317130722038e-05,
      "loss": 0.1202,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_LOC": {
        "f1": 0.7736781419864931,
        "number": 12507,
        "precision": 0.7976564490107837,
        "recall": 0.751099384344767
      },
      "eval_MISC": {
        "f1": 0.7151848937844216,
        "number": 2816,
        "precision": 0.8015873015873016,
        "recall": 0.6455965909090909
      },
      "eval_NORP": {
        "f1": 0.8523970985879222,
        "number": 10969,
        "precision": 0.805352798053528,
        "recall": 0.9052785121706628
      },
      "eval_PER": {
        "f1": 0.9086936163571093,
        "number": 28256,
        "precision": 0.8909103274730507,
        "recall": 0.9272013023782559
      },
      "eval_loss": 0.11920765787363052,
      "eval_overall_accuracy": 0.967201754087,
      "eval_overall_f1": 0.8581709417202936,
      "eval_overall_precision": 0.8486787852712344,
      "eval_overall_recall": 0.8678778323678228,
      "eval_runtime": 57.7447,
      "eval_samples_per_second": 73.357,
      "eval_steps_per_second": 9.178,
      "step": 2119
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.7640396413402548e-05,
      "loss": 0.0999,
      "step": 2500
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.7168475696083062e-05,
      "loss": 0.0863,
      "step": 3000
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.669655497876357e-05,
      "loss": 0.09,
      "step": 3500
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.622463426144408e-05,
      "loss": 0.0881,
      "step": 4000
    },
    {
      "epoch": 2.0,
      "eval_LOC": {
        "f1": 0.8009789829454955,
        "number": 12507,
        "precision": 0.7789783889980354,
        "recall": 0.824258415287439
      },
      "eval_MISC": {
        "f1": 0.7636171337916445,
        "number": 2816,
        "precision": 0.7581379068953448,
        "recall": 0.7691761363636364
      },
      "eval_NORP": {
        "f1": 0.8755772529357434,
        "number": 10969,
        "precision": 0.8458531611148878,
        "recall": 0.9074664964901085
      },
      "eval_PER": {
        "f1": 0.9198921794894381,
        "number": 28256,
        "precision": 0.9158744079985968,
        "recall": 0.9239453567383918
      },
      "eval_loss": 0.1091507151722908,
      "eval_overall_accuracy": 0.9707860445565364,
      "eval_overall_f1": 0.8752163877668782,
      "eval_overall_precision": 0.8611170250514513,
      "eval_overall_recall": 0.8897851433599765,
      "eval_runtime": 59.0952,
      "eval_samples_per_second": 71.681,
      "eval_steps_per_second": 8.969,
      "step": 4238
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.575271354412459e-05,
      "loss": 0.0739,
      "step": 4500
    },
    {
      "epoch": 2.36,
      "learning_rate": 1.52807928268051e-05,
      "loss": 0.0616,
      "step": 5000
    },
    {
      "epoch": 2.6,
      "learning_rate": 1.4808872109485608e-05,
      "loss": 0.062,
      "step": 5500
    },
    {
      "epoch": 2.83,
      "learning_rate": 1.4336951392166117e-05,
      "loss": 0.0629,
      "step": 6000
    },
    {
      "epoch": 3.0,
      "eval_LOC": {
        "f1": 0.7920257336880983,
        "number": 12507,
        "precision": 0.7868076376834464,
        "recall": 0.797313504437515
      },
      "eval_MISC": {
        "f1": 0.7715430861723446,
        "number": 2816,
        "precision": 0.8854645814167433,
        "recall": 0.68359375
      },
      "eval_NORP": {
        "f1": 0.8747102811912363,
        "number": 10969,
        "precision": 0.8405614388972936,
        "recall": 0.9117512991156896
      },
      "eval_PER": {
        "f1": 0.9222061110043501,
        "number": 28256,
        "precision": 0.910608935656374,
        "recall": 0.9341024915062288
      },
      "eval_loss": 0.11280690133571625,
      "eval_overall_accuracy": 0.9706866387194256,
      "eval_overall_f1": 0.8758149783730356,
      "eval_overall_precision": 0.8665195313200912,
      "eval_overall_recall": 0.8853120187724572,
      "eval_runtime": 59.3431,
      "eval_samples_per_second": 71.381,
      "eval_steps_per_second": 8.931,
      "step": 6357
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.3865030674846627e-05,
      "loss": 0.0554,
      "step": 6500
    },
    {
      "epoch": 3.3,
      "learning_rate": 1.3393109957527137e-05,
      "loss": 0.0433,
      "step": 7000
    },
    {
      "epoch": 3.54,
      "learning_rate": 1.2921189240207645e-05,
      "loss": 0.0442,
      "step": 7500
    },
    {
      "epoch": 3.78,
      "learning_rate": 1.2449268522888157e-05,
      "loss": 0.0409,
      "step": 8000
    },
    {
      "epoch": 4.0,
      "eval_LOC": {
        "f1": 0.8152558604321939,
        "number": 12507,
        "precision": 0.8505647263249348,
        "recall": 0.7827616534740546
      },
      "eval_MISC": {
        "f1": 0.7983193277310924,
        "number": 2816,
        "precision": 0.8220466516177577,
        "recall": 0.7759232954545454
      },
      "eval_NORP": {
        "f1": 0.886389100524358,
        "number": 10969,
        "precision": 0.8717383638928068,
        "recall": 0.901540705624943
      },
      "eval_PER": {
        "f1": 0.9238697668005309,
        "number": 28256,
        "precision": 0.9004804623189867,
        "recall": 0.9485065118912798
      },
      "eval_loss": 0.11524520814418793,
      "eval_overall_accuracy": 0.9734700021585267,
      "eval_overall_f1": 0.8862442293508646,
      "eval_overall_precision": 0.8804161013116237,
      "eval_overall_recall": 0.8921500329984601,
      "eval_runtime": 59.3779,
      "eval_samples_per_second": 71.34,
      "eval_steps_per_second": 8.926,
      "step": 8476
    },
    {
      "epoch": 4.01,
      "learning_rate": 1.1977347805568667e-05,
      "loss": 0.0461,
      "step": 8500
    },
    {
      "epoch": 4.25,
      "learning_rate": 1.1505427088249175e-05,
      "loss": 0.028,
      "step": 9000
    },
    {
      "epoch": 4.48,
      "learning_rate": 1.1033506370929685e-05,
      "loss": 0.0289,
      "step": 9500
    },
    {
      "epoch": 4.72,
      "learning_rate": 1.0561585653610193e-05,
      "loss": 0.0331,
      "step": 10000
    },
    {
      "epoch": 4.96,
      "learning_rate": 1.0089664936290703e-05,
      "loss": 0.0306,
      "step": 10500
    },
    {
      "epoch": 5.0,
      "eval_LOC": {
        "f1": 0.8143539881344759,
        "number": 12507,
        "precision": 0.8400339991500213,
        "recall": 0.7901974894059327
      },
      "eval_MISC": {
        "f1": 0.8030969558331867,
        "number": 2816,
        "precision": 0.7959539588419952,
        "recall": 0.8103693181818182
      },
      "eval_NORP": {
        "f1": 0.893543068490709,
        "number": 10969,
        "precision": 0.8739539748953975,
        "recall": 0.9140304494484456
      },
      "eval_PER": {
        "f1": 0.9285937771597428,
        "number": 28256,
        "precision": 0.9124479059916649,
        "recall": 0.9453213476783692
      },
      "eval_loss": 0.1234506368637085,
      "eval_overall_accuracy": 0.9740408756802199,
      "eval_overall_f1": 0.8897258155486418,
      "eval_overall_precision": 0.8830582541803604,
      "eval_overall_recall": 0.8964948302412554,
      "eval_runtime": 58.1348,
      "eval_samples_per_second": 72.865,
      "eval_steps_per_second": 9.117,
      "step": 10595
    },
    {
      "epoch": 5.19,
      "learning_rate": 9.617744218971213e-06,
      "loss": 0.0237,
      "step": 11000
    },
    {
      "epoch": 5.43,
      "learning_rate": 9.145823501651723e-06,
      "loss": 0.023,
      "step": 11500
    },
    {
      "epoch": 5.66,
      "learning_rate": 8.673902784332233e-06,
      "loss": 0.0246,
      "step": 12000
    },
    {
      "epoch": 5.9,
      "learning_rate": 8.201982067012742e-06,
      "loss": 0.0184,
      "step": 12500
    },
    {
      "epoch": 6.0,
      "eval_LOC": {
        "f1": 0.8221609305672143,
        "number": 12507,
        "precision": 0.822062350119904,
        "recall": 0.8222595346605901
      },
      "eval_MISC": {
        "f1": 0.8192371475953565,
        "number": 2816,
        "precision": 0.8513979318268863,
        "recall": 0.7894176136363636
      },
      "eval_NORP": {
        "f1": 0.8961138379790156,
        "number": 10969,
        "precision": 0.8853888592276206,
        "recall": 0.9071018324368675
      },
      "eval_PER": {
        "f1": 0.9297248123720718,
        "number": 28256,
        "precision": 0.9192873205327798,
        "recall": 0.9404020385050963
      },
      "eval_loss": 0.1410222351551056,
      "eval_overall_accuracy": 0.9745975483680401,
      "eval_overall_f1": 0.8929625177576221,
      "eval_overall_precision": 0.8871779096699479,
      "eval_overall_recall": 0.8988230549241035,
      "eval_runtime": 60.1835,
      "eval_samples_per_second": 70.385,
      "eval_steps_per_second": 8.806,
      "step": 12714
    },
    {
      "epoch": 6.13,
      "learning_rate": 7.730061349693252e-06,
      "loss": 0.0181,
      "step": 13000
    },
    {
      "epoch": 6.37,
      "learning_rate": 7.258140632373761e-06,
      "loss": 0.014,
      "step": 13500
    },
    {
      "epoch": 6.61,
      "learning_rate": 6.786219915054272e-06,
      "loss": 0.0152,
      "step": 14000
    },
    {
      "epoch": 6.84,
      "learning_rate": 6.314299197734781e-06,
      "loss": 0.0144,
      "step": 14500
    },
    {
      "epoch": 7.0,
      "eval_LOC": {
        "f1": 0.8194483254161512,
        "number": 12507,
        "precision": 0.8182397959183674,
        "recall": 0.8206604301591109
      },
      "eval_MISC": {
        "f1": 0.8199495858840475,
        "number": 2816,
        "precision": 0.8316289262235208,
        "recall": 0.80859375
      },
      "eval_NORP": {
        "f1": 0.8962966345495228,
        "number": 10969,
        "precision": 0.8978956999085087,
        "recall": 0.8947032546266752
      },
      "eval_PER": {
        "f1": 0.9302089886069755,
        "number": 28256,
        "precision": 0.9187146210133922,
        "recall": 0.9419946206115515
      },
      "eval_loss": 0.15106713771820068,
      "eval_overall_accuracy": 0.9748702043784011,
      "eval_overall_f1": 0.8925746363868333,
      "eval_overall_precision": 0.8874311394607133,
      "eval_overall_recall": 0.8977781036884945,
      "eval_runtime": 57.4606,
      "eval_samples_per_second": 73.72,
      "eval_steps_per_second": 9.224,
      "step": 14833
    },
    {
      "epoch": 7.08,
      "learning_rate": 5.84237848041529e-06,
      "loss": 0.0142,
      "step": 15000
    },
    {
      "epoch": 7.31,
      "learning_rate": 5.3704577630958e-06,
      "loss": 0.0113,
      "step": 15500
    },
    {
      "epoch": 7.55,
      "learning_rate": 4.89853704577631e-06,
      "loss": 0.0094,
      "step": 16000
    },
    {
      "epoch": 7.79,
      "learning_rate": 4.42661632845682e-06,
      "loss": 0.0118,
      "step": 16500
    },
    {
      "epoch": 8.0,
      "eval_LOC": {
        "f1": 0.8198295522746369,
        "number": 12507,
        "precision": 0.8205189812590101,
        "recall": 0.8191412808827057
      },
      "eval_MISC": {
        "f1": 0.8218876239441792,
        "number": 2816,
        "precision": 0.8509505703422053,
        "recall": 0.7947443181818182
      },
      "eval_NORP": {
        "f1": 0.8973384030418251,
        "number": 10969,
        "precision": 0.8911264946507237,
        "recall": 0.9036375239310785
      },
      "eval_PER": {
        "f1": 0.9298639775676194,
        "number": 28256,
        "precision": 0.9154349987997669,
        "recall": 0.9447550962627407
      },
      "eval_loss": 0.16531305015087128,
      "eval_overall_accuracy": 0.9748900855458232,
      "eval_overall_f1": 0.8929675846763926,
      "eval_overall_precision": 0.886101083032491,
      "eval_overall_recall": 0.8999413360709834,
      "eval_runtime": 59.2269,
      "eval_samples_per_second": 71.522,
      "eval_steps_per_second": 8.949,
      "step": 16952
    },
    {
      "epoch": 8.02,
      "learning_rate": 3.954695611137329e-06,
      "loss": 0.009,
      "step": 17000
    },
    {
      "epoch": 8.26,
      "learning_rate": 3.482774893817839e-06,
      "loss": 0.007,
      "step": 17500
    },
    {
      "epoch": 8.49,
      "learning_rate": 3.0108541764983485e-06,
      "loss": 0.0072,
      "step": 18000
    },
    {
      "epoch": 8.73,
      "learning_rate": 2.5389334591788585e-06,
      "loss": 0.009,
      "step": 18500
    },
    {
      "epoch": 8.97,
      "learning_rate": 2.0670127418593677e-06,
      "loss": 0.0076,
      "step": 19000
    },
    {
      "epoch": 9.0,
      "eval_LOC": {
        "f1": 0.8171711433904082,
        "number": 12507,
        "precision": 0.8295576241865062,
        "recall": 0.805149116494763
      },
      "eval_MISC": {
        "f1": 0.8233618233618233,
        "number": 2816,
        "precision": 0.8257142857142857,
        "recall": 0.8210227272727273
      },
      "eval_NORP": {
        "f1": 0.8973920863309351,
        "number": 10969,
        "precision": 0.8853695324283559,
        "recall": 0.9097456468228644
      },
      "eval_PER": {
        "f1": 0.9303293743112526,
        "number": 28256,
        "precision": 0.9197592778335005,
        "recall": 0.9411452434881087
      },
      "eval_loss": 0.16768833994865417,
      "eval_overall_accuracy": 0.9747083148722493,
      "eval_overall_f1": 0.8927428399485734,
      "eval_overall_precision": 0.8880866425992779,
      "eval_overall_recall": 0.8974481190877759,
      "eval_runtime": 59.1217,
      "eval_samples_per_second": 71.649,
      "eval_steps_per_second": 8.965,
      "step": 19071
    },
    {
      "epoch": 9.2,
      "learning_rate": 1.5950920245398775e-06,
      "loss": 0.0063,
      "step": 19500
    },
    {
      "epoch": 9.44,
      "learning_rate": 1.123171307220387e-06,
      "loss": 0.005,
      "step": 20000
    },
    {
      "epoch": 9.67,
      "learning_rate": 6.512505899008966e-07,
      "loss": 0.0046,
      "step": 20500
    },
    {
      "epoch": 9.91,
      "learning_rate": 1.7932987258140632e-07,
      "loss": 0.0056,
      "step": 21000
    },
    {
      "epoch": 10.0,
      "eval_LOC": {
        "f1": 0.8228770339188861,
        "number": 12507,
        "precision": 0.833265021723092,
        "recall": 0.812744862876789
      },
      "eval_MISC": {
        "f1": 0.8222182275750494,
        "number": 2816,
        "precision": 0.8325445941026575,
        "recall": 0.8121448863636364
      },
      "eval_NORP": {
        "f1": 0.8972602739726027,
        "number": 10969,
        "precision": 0.8871068341798093,
        "recall": 0.907648828516729
      },
      "eval_PER": {
        "f1": 0.9305083267939662,
        "number": 28256,
        "precision": 0.917185190278112,
        "recall": 0.9442242355605889
      },
      "eval_loss": 0.17190925776958466,
      "eval_overall_accuracy": 0.9750008520500324,
      "eval_overall_f1": 0.8940859333734041,
      "eval_overall_precision": 0.888341959535271,
      "eval_overall_recall": 0.899904671115348,
      "eval_runtime": 57.6029,
      "eval_samples_per_second": 73.538,
      "eval_steps_per_second": 9.201,
      "step": 21190
    }
  ],
  "max_steps": 21190,
  "num_train_epochs": 10,
  "total_flos": 1.5668822780351856e+16,
  "trial_name": null,
  "trial_params": null
}