{
  "best_global_step": 1023,
  "best_metric": 0.8101649500416815,
  "best_model_checkpoint": "./roberta-base-normclsf-wce_v07/checkpoint-1023",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1023,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02932551319648094,
      "grad_norm": 6.274427890777588,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.6739353656768798,
      "step": 10
    },
    {
      "epoch": 0.05865102639296188,
      "grad_norm": 7.410248279571533,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.7113884925842285,
      "step": 20
    },
    {
      "epoch": 0.08797653958944282,
      "grad_norm": 4.502801895141602,
      "learning_rate": 2.9e-06,
      "loss": 0.6877131462097168,
      "step": 30
    },
    {
      "epoch": 0.11730205278592376,
      "grad_norm": 3.6373634338378906,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.6994937896728516,
      "step": 40
    },
    {
      "epoch": 0.1466275659824047,
      "grad_norm": 5.270040988922119,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.6988643169403076,
      "step": 50
    },
    {
      "epoch": 0.17595307917888564,
      "grad_norm": 4.53806734085083,
      "learning_rate": 5.9e-06,
      "loss": 0.698380422592163,
      "step": 60
    },
    {
      "epoch": 0.20527859237536658,
      "grad_norm": 2.1874923706054688,
      "learning_rate": 6.9e-06,
      "loss": 0.7049017906188965,
      "step": 70
    },
    {
      "epoch": 0.23460410557184752,
      "grad_norm": 2.6310946941375732,
      "learning_rate": 7.9e-06,
      "loss": 0.6866714954376221,
      "step": 80
    },
    {
      "epoch": 0.26392961876832843,
      "grad_norm": 4.628715515136719,
      "learning_rate": 8.900000000000001e-06,
      "loss": 0.6937003135681152,
      "step": 90
    },
    {
      "epoch": 0.2932551319648094,
      "grad_norm": 1.9889392852783203,
      "learning_rate": 9.9e-06,
      "loss": 0.6852640151977539,
      "step": 100
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 3.230287551879883,
      "learning_rate": 1.0900000000000002e-05,
      "loss": 0.6885860443115235,
      "step": 110
    },
    {
      "epoch": 0.3519061583577713,
      "grad_norm": 2.2565829753875732,
      "learning_rate": 1.1900000000000001e-05,
      "loss": 0.6908163547515869,
      "step": 120
    },
    {
      "epoch": 0.3812316715542522,
      "grad_norm": 2.4631707668304443,
      "learning_rate": 1.2900000000000002e-05,
      "loss": 0.6803622245788574,
      "step": 130
    },
    {
      "epoch": 0.41055718475073316,
      "grad_norm": 8.635135650634766,
      "learning_rate": 1.39e-05,
      "loss": 0.6100090503692627,
      "step": 140
    },
    {
      "epoch": 0.4398826979472141,
      "grad_norm": 42.23886489868164,
      "learning_rate": 1.4900000000000001e-05,
      "loss": 0.4960626602172852,
      "step": 150
    },
    {
      "epoch": 0.46920821114369504,
      "grad_norm": 17.948444366455078,
      "learning_rate": 1.5900000000000004e-05,
      "loss": 0.36152377128601076,
      "step": 160
    },
    {
      "epoch": 0.49853372434017595,
      "grad_norm": 14.445870399475098,
      "learning_rate": 1.69e-05,
      "loss": 0.38893632888793944,
      "step": 170
    },
    {
      "epoch": 0.5278592375366569,
      "grad_norm": 23.278106689453125,
      "learning_rate": 1.79e-05,
      "loss": 0.47756447792053225,
      "step": 180
    },
    {
      "epoch": 0.5571847507331378,
      "grad_norm": 8.31049919128418,
      "learning_rate": 1.8900000000000002e-05,
      "loss": 0.38424367904663087,
      "step": 190
    },
    {
      "epoch": 0.5865102639296188,
      "grad_norm": 17.757457733154297,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 0.5007349491119385,
      "step": 200
    },
    {
      "epoch": 0.6158357771260997,
      "grad_norm": 24.88862419128418,
      "learning_rate": 1.9998827040856932e-05,
      "loss": 0.4304344177246094,
      "step": 210
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 50.94068145751953,
      "learning_rate": 1.9994772720547093e-05,
      "loss": 0.43378639221191406,
      "step": 220
    },
    {
      "epoch": 0.6744868035190615,
      "grad_norm": 14.23753833770752,
      "learning_rate": 1.9987823732018804e-05,
      "loss": 0.4078083515167236,
      "step": 230
    },
    {
      "epoch": 0.7038123167155426,
      "grad_norm": 14.046149253845215,
      "learning_rate": 1.9977982087825714e-05,
      "loss": 0.39012579917907714,
      "step": 240
    },
    {
      "epoch": 0.7331378299120235,
      "grad_norm": 11.86131477355957,
      "learning_rate": 1.9965250638287224e-05,
      "loss": 0.26512391567230226,
      "step": 250
    },
    {
      "epoch": 0.7624633431085044,
      "grad_norm": 22.713699340820312,
      "learning_rate": 1.994963307066301e-05,
      "loss": 0.5063480854034423,
      "step": 260
    },
    {
      "epoch": 0.7917888563049853,
      "grad_norm": 23.17565155029297,
      "learning_rate": 1.9931133908085093e-05,
      "loss": 0.549618148803711,
      "step": 270
    },
    {
      "epoch": 0.8211143695014663,
      "grad_norm": 11.513432502746582,
      "learning_rate": 1.9909758508247902e-05,
      "loss": 0.5453836917877197,
      "step": 280
    },
    {
      "epoch": 0.8504398826979472,
      "grad_norm": 31.22650718688965,
      "learning_rate": 1.988551306185654e-05,
      "loss": 0.3752528190612793,
      "step": 290
    },
    {
      "epoch": 0.8797653958944281,
      "grad_norm": 4.477701663970947,
      "learning_rate": 1.9858404590833874e-05,
      "loss": 0.396454381942749,
      "step": 300
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 4.240663528442383,
      "learning_rate": 1.9828440946286853e-05,
      "loss": 0.39183750152587893,
      "step": 310
    },
    {
      "epoch": 0.9384164222873901,
      "grad_norm": 4.501325607299805,
      "learning_rate": 1.979563080623267e-05,
      "loss": 0.439255428314209,
      "step": 320
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 5.938743591308594,
      "learning_rate": 1.9759983673085476e-05,
      "loss": 0.2729459047317505,
      "step": 330
    },
    {
      "epoch": 0.9970674486803519,
      "grad_norm": 17.144458770751953,
      "learning_rate": 1.972150987090428e-05,
      "loss": 0.39424500465393064,
      "step": 340
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9367088607594937,
      "eval_f1": 0.603448275862069,
      "eval_loss": 0.6145616173744202,
      "eval_macro_f1": 0.7845291618544794,
      "eval_precision": 0.6653992395437263,
      "eval_recall": 0.5520504731861199,
      "eval_runtime": 28.4905,
      "eval_samples_per_second": 127.551,
      "eval_steps_per_second": 2.001,
      "step": 341
    },
    {
      "epoch": 1.0263929618768328,
      "grad_norm": 5.595256805419922,
      "learning_rate": 1.968022054240293e-05,
      "loss": 0.4527877330780029,
      "step": 350
    },
    {
      "epoch": 1.0557184750733137,
      "grad_norm": 25.64937973022461,
      "learning_rate": 1.9636127645722988e-05,
      "loss": 0.3735408067703247,
      "step": 360
    },
    {
      "epoch": 1.0850439882697946,
      "grad_norm": 8.792585372924805,
      "learning_rate": 1.95892439509704e-05,
      "loss": 0.3585880041122437,
      "step": 370
    },
    {
      "epoch": 1.1143695014662756,
      "grad_norm": 43.46753692626953,
      "learning_rate": 1.953958303651709e-05,
      "loss": 0.5687558650970459,
      "step": 380
    },
    {
      "epoch": 1.1436950146627567,
      "grad_norm": 7.620843887329102,
      "learning_rate": 1.9487159285068366e-05,
      "loss": 0.380626916885376,
      "step": 390
    },
    {
      "epoch": 1.1730205278592376,
      "grad_norm": 24.21900749206543,
      "learning_rate": 1.943198787949746e-05,
      "loss": 0.27167201042175293,
      "step": 400
    },
    {
      "epoch": 1.2023460410557185,
      "grad_norm": 16.18953514099121,
      "learning_rate": 1.9374084798448294e-05,
      "loss": 0.20955939292907716,
      "step": 410
    },
    {
      "epoch": 1.2316715542521994,
      "grad_norm": 2.4854800701141357,
      "learning_rate": 1.9313466811707744e-05,
      "loss": 0.45894174575805663,
      "step": 420
    },
    {
      "epoch": 1.2609970674486803,
      "grad_norm": 14.185721397399902,
      "learning_rate": 1.925015147534883e-05,
      "loss": 0.2584639549255371,
      "step": 430
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 14.547219276428223,
      "learning_rate": 1.9184157126646144e-05,
      "loss": 0.29377260208129885,
      "step": 440
    },
    {
      "epoch": 1.3196480938416422,
      "grad_norm": 35.326332092285156,
      "learning_rate": 1.911550287876505e-05,
      "loss": 0.48297734260559083,
      "step": 450
    },
    {
      "epoch": 1.3489736070381233,
      "grad_norm": 8.512100219726562,
      "learning_rate": 1.904420861522617e-05,
      "loss": 0.3517111539840698,
      "step": 460
    },
    {
      "epoch": 1.3782991202346042,
      "grad_norm": 12.59523868560791,
      "learning_rate": 1.897029498414672e-05,
      "loss": 0.4336338996887207,
      "step": 470
    },
    {
      "epoch": 1.4076246334310851,
      "grad_norm": 6.085882186889648,
      "learning_rate": 1.8893783392260492e-05,
      "loss": 0.31885290145874023,
      "step": 480
    },
    {
      "epoch": 1.436950146627566,
      "grad_norm": 4.003190994262695,
      "learning_rate": 1.8814695998718023e-05,
      "loss": 0.23459928035736083,
      "step": 490
    },
    {
      "epoch": 1.466275659824047,
      "grad_norm": 19.78611183166504,
      "learning_rate": 1.8733055708668928e-05,
      "loss": 0.49587507247924806,
      "step": 500
    },
    {
      "epoch": 1.4956011730205279,
      "grad_norm": 12.707535743713379,
      "learning_rate": 1.8648886166628157e-05,
      "loss": 0.4021581172943115,
      "step": 510
    },
    {
      "epoch": 1.5249266862170088,
      "grad_norm": 7.153898239135742,
      "learning_rate": 1.8562211749628095e-05,
      "loss": 0.2762838125228882,
      "step": 520
    },
    {
      "epoch": 1.5542521994134897,
      "grad_norm": 3.7341670989990234,
      "learning_rate": 1.847305756015854e-05,
      "loss": 0.3147549867630005,
      "step": 530
    },
    {
      "epoch": 1.5835777126099706,
      "grad_norm": 7.168247699737549,
      "learning_rate": 1.838144941889656e-05,
      "loss": 0.5545739650726318,
      "step": 540
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 10.357027053833008,
      "learning_rate": 1.8287413857228357e-05,
      "loss": 0.28069357872009276,
      "step": 550
    },
    {
      "epoch": 1.6422287390029324,
      "grad_norm": 1.3375144004821777,
      "learning_rate": 1.81909781095653e-05,
      "loss": 0.2539283275604248,
      "step": 560
    },
    {
      "epoch": 1.6715542521994133,
      "grad_norm": 61.67247772216797,
      "learning_rate": 1.8092170105456324e-05,
      "loss": 0.8403676986694336,
      "step": 570
    },
    {
      "epoch": 1.7008797653958945,
      "grad_norm": 8.79477596282959,
      "learning_rate": 1.7991018461499054e-05,
      "loss": 0.5081100463867188,
      "step": 580
    },
    {
      "epoch": 1.7302052785923754,
      "grad_norm": 7.9283905029296875,
      "learning_rate": 1.7887552473051896e-05,
      "loss": 0.3533244371414185,
      "step": 590
    },
    {
      "epoch": 1.7595307917888563,
      "grad_norm": 15.013837814331055,
      "learning_rate": 1.7781802105749558e-05,
      "loss": 0.41324725151062014,
      "step": 600
    },
    {
      "epoch": 1.7888563049853372,
      "grad_norm": 6.264997482299805,
      "learning_rate": 1.7673797986824495e-05,
      "loss": 0.3623948335647583,
      "step": 610
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 47.5418701171875,
      "learning_rate": 1.756357139623666e-05,
      "loss": 0.5024556159973145,
      "step": 620
    },
    {
      "epoch": 1.8475073313782993,
      "grad_norm": 6.494227886199951,
      "learning_rate": 1.7451154257614287e-05,
      "loss": 0.4641399383544922,
      "step": 630
    },
    {
      "epoch": 1.8768328445747802,
      "grad_norm": 36.73579406738281,
      "learning_rate": 1.733657912900822e-05,
      "loss": 0.47899684906005857,
      "step": 640
    },
    {
      "epoch": 1.906158357771261,
      "grad_norm": 3.7244112491607666,
      "learning_rate": 1.7219879193462498e-05,
      "loss": 0.37715878486633303,
      "step": 650
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 3.3324058055877686,
      "learning_rate": 1.7101088249403957e-05,
      "loss": 0.4517849922180176,
      "step": 660
    },
    {
      "epoch": 1.964809384164223,
      "grad_norm": 3.113097667694092,
      "learning_rate": 1.6980240700853583e-05,
      "loss": 0.29823923110961914,
      "step": 670
    },
    {
      "epoch": 1.9941348973607038,
      "grad_norm": 4.621532440185547,
      "learning_rate": 1.685737154746248e-05,
      "loss": 0.3290010690689087,
      "step": 680
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9122179416620804,
      "eval_f1": 0.6037267080745342,
      "eval_loss": 0.4162055253982544,
      "eval_macro_f1": 0.777184412369311,
      "eval_precision": 0.4979508196721312,
      "eval_recall": 0.7665615141955836,
      "eval_runtime": 28.8738,
      "eval_samples_per_second": 125.858,
      "eval_steps_per_second": 1.974,
      "step": 682
    },
    {
      "epoch": 2.0234604105571847,
      "grad_norm": 39.13134765625,
      "learning_rate": 1.673251637437533e-05,
      "loss": 0.36524658203125,
      "step": 690
    },
    {
      "epoch": 2.0527859237536656,
      "grad_norm": 2.5331356525421143,
      "learning_rate": 1.660571134192429e-05,
      "loss": 0.24305994510650636,
      "step": 700
    },
    {
      "epoch": 2.0821114369501466,
      "grad_norm": 3.388939380645752,
      "learning_rate": 1.6476993175156306e-05,
      "loss": 0.2262793779373169,
      "step": 710
    },
    {
      "epoch": 2.1114369501466275,
      "grad_norm": 50.848594665527344,
      "learning_rate": 1.6346399153196873e-05,
      "loss": 0.27400689125061034,
      "step": 720
    },
    {
      "epoch": 2.1407624633431084,
      "grad_norm": 30.017822265625,
      "learning_rate": 1.621396709845331e-05,
      "loss": 0.30254995822906494,
      "step": 730
    },
    {
      "epoch": 2.1700879765395893,
      "grad_norm": 19.93187141418457,
      "learning_rate": 1.6079735365660695e-05,
      "loss": 0.3568316221237183,
      "step": 740
    },
    {
      "epoch": 2.19941348973607,
      "grad_norm": 19.21232032775879,
      "learning_rate": 1.5943742830773665e-05,
      "loss": 0.21902217864990234,
      "step": 750
    },
    {
      "epoch": 2.228739002932551,
      "grad_norm": 8.548822402954102,
      "learning_rate": 1.580602887970721e-05,
      "loss": 0.3009159564971924,
      "step": 760
    },
    {
      "epoch": 2.258064516129032,
      "grad_norm": 13.429585456848145,
      "learning_rate": 1.5666633396929787e-05,
      "loss": 0.4545457363128662,
      "step": 770
    },
    {
      "epoch": 2.2873900293255134,
      "grad_norm": 5.193440914154053,
      "learning_rate": 1.5525596753912078e-05,
      "loss": 0.23406951427459716,
      "step": 780
    },
    {
      "epoch": 2.3167155425219943,
      "grad_norm": 38.764408111572266,
      "learning_rate": 1.538295979743465e-05,
      "loss": 0.2635719537734985,
      "step": 790
    },
    {
      "epoch": 2.346041055718475,
      "grad_norm": 3.2206692695617676,
      "learning_rate": 1.5238763837758004e-05,
      "loss": 0.2099674701690674,
      "step": 800
    },
    {
      "epoch": 2.375366568914956,
      "grad_norm": 12.719015121459961,
      "learning_rate": 1.5093050636658353e-05,
      "loss": 0.3552921056747437,
      "step": 810
    },
    {
      "epoch": 2.404692082111437,
      "grad_norm": 13.831098556518555,
      "learning_rate": 1.4945862395332672e-05,
      "loss": 0.4749103546142578,
      "step": 820
    },
    {
      "epoch": 2.434017595307918,
      "grad_norm": 5.287304401397705,
      "learning_rate": 1.4797241742176433e-05,
      "loss": 0.244032883644104,
      "step": 830
    },
    {
      "epoch": 2.463343108504399,
      "grad_norm": 4.9697160720825195,
      "learning_rate": 1.4647231720437687e-05,
      "loss": 0.4007211685180664,
      "step": 840
    },
    {
      "epoch": 2.4926686217008798,
      "grad_norm": 23.01662826538086,
      "learning_rate": 1.4495875775750911e-05,
      "loss": 0.4493084907531738,
      "step": 850
    },
    {
      "epoch": 2.5219941348973607,
      "grad_norm": 7.524326324462891,
      "learning_rate": 1.434321774355439e-05,
      "loss": 0.3268959760665894,
      "step": 860
    },
    {
      "epoch": 2.5513196480938416,
      "grad_norm": 16.699954986572266,
      "learning_rate": 1.4189301836394668e-05,
      "loss": 0.3056162357330322,
      "step": 870
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 23.58338165283203,
      "learning_rate": 1.403417263112179e-05,
      "loss": 0.3211620569229126,
      "step": 880
    },
    {
      "epoch": 2.6099706744868034,
      "grad_norm": 7.736941814422607,
      "learning_rate": 1.3877875055979021e-05,
      "loss": 0.2918569087982178,
      "step": 890
    },
    {
      "epoch": 2.6392961876832843,
      "grad_norm": 12.861424446105957,
      "learning_rate": 1.3720454377590841e-05,
      "loss": 0.27423183917999266,
      "step": 900
    },
    {
      "epoch": 2.6686217008797652,
      "grad_norm": 8.398710250854492,
      "learning_rate": 1.3561956187852863e-05,
      "loss": 0.36331515312194823,
      "step": 910
    },
    {
      "epoch": 2.6979472140762466,
      "grad_norm": 17.49972152709961,
      "learning_rate": 1.340242639072763e-05,
      "loss": 0.19535980224609376,
      "step": 920
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 17.317955017089844,
      "learning_rate": 1.3241911188949962e-05,
      "loss": 0.2180016279220581,
      "step": 930
    },
    {
      "epoch": 2.7565982404692084,
      "grad_norm": 9.967617988586426,
      "learning_rate": 1.308045707064582e-05,
      "loss": 0.2760441541671753,
      "step": 940
    },
    {
      "epoch": 2.7859237536656893,
      "grad_norm": 14.349778175354004,
      "learning_rate": 1.2918110795868488e-05,
      "loss": 0.1867595672607422,
      "step": 950
    },
    {
      "epoch": 2.8152492668621703,
      "grad_norm": 36.6998405456543,
      "learning_rate": 1.2754919383056016e-05,
      "loss": 0.24778587818145753,
      "step": 960
    },
    {
      "epoch": 2.844574780058651,
      "grad_norm": 46.54512023925781,
      "learning_rate": 1.2590930095413825e-05,
      "loss": 0.20473012924194336,
      "step": 970
    },
    {
      "epoch": 2.873900293255132,
      "grad_norm": 25.6732120513916,
      "learning_rate": 1.2426190427226407e-05,
      "loss": 0.42395458221435545,
      "step": 980
    },
    {
      "epoch": 2.903225806451613,
      "grad_norm": 9.22095012664795,
      "learning_rate": 1.2260748090102143e-05,
      "loss": 0.31453471183776854,
      "step": 990
    },
    {
      "epoch": 2.932551319648094,
      "grad_norm": 4.472631931304932,
      "learning_rate": 1.209465099915513e-05,
      "loss": 0.24591920375823975,
      "step": 1000
    },
    {
      "epoch": 2.961876832844575,
      "grad_norm": 7.117494583129883,
      "learning_rate": 1.1927947259128083e-05,
      "loss": 0.19121105670928956,
      "step": 1010
    },
    {
      "epoch": 2.9912023460410557,
      "grad_norm": 1.256831169128418,
      "learning_rate": 1.1760685150460363e-05,
      "loss": 0.1457730770111084,
      "step": 1020
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9408365437534397,
      "eval_f1": 0.6526655896607432,
      "eval_loss": 0.7006177306175232,
      "eval_macro_f1": 0.8101649500416815,
      "eval_precision": 0.6688741721854304,
      "eval_recall": 0.637223974763407,
      "eval_runtime": 28.5302,
      "eval_samples_per_second": 127.374,
      "eval_steps_per_second": 1.998,
      "step": 1023
    }
  ],
  "logging_steps": 10,
  "max_steps": 2046,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4302260421719040.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}