{
  "best_metric": 0.3755741665997943,
  "best_model_checkpoint": "/content/drive/MyDrive/model_outputs/trial_9/checkpoint-1764",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1764,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011337868480725623,
      "grad_norm": 9.890141487121582,
      "learning_rate": 9.346480722758123e-07,
      "loss": 2.2337,
      "step": 10
    },
    {
      "epoch": 0.022675736961451247,
      "grad_norm": 10.97945785522461,
      "learning_rate": 1.8692961445516245e-06,
      "loss": 2.2359,
      "step": 20
    },
    {
      "epoch": 0.034013605442176874,
      "grad_norm": 10.244830131530762,
      "learning_rate": 2.8039442168274367e-06,
      "loss": 2.2034,
      "step": 30
    },
    {
      "epoch": 0.045351473922902494,
      "grad_norm": 11.170487403869629,
      "learning_rate": 3.738592289103249e-06,
      "loss": 2.2238,
      "step": 40
    },
    {
      "epoch": 0.05668934240362812,
      "grad_norm": 8.994032859802246,
      "learning_rate": 4.673240361379061e-06,
      "loss": 2.143,
      "step": 50
    },
    {
      "epoch": 0.06802721088435375,
      "grad_norm": 11.781458854675293,
      "learning_rate": 5.607888433654873e-06,
      "loss": 2.1299,
      "step": 60
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 10.54732894897461,
      "learning_rate": 6.542536505930685e-06,
      "loss": 2.102,
      "step": 70
    },
    {
      "epoch": 0.09070294784580499,
      "grad_norm": 8.15542221069336,
      "learning_rate": 7.477184578206498e-06,
      "loss": 2.0436,
      "step": 80
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 12.086600303649902,
      "learning_rate": 8.41183265048231e-06,
      "loss": 2.0417,
      "step": 90
    },
    {
      "epoch": 0.11337868480725624,
      "grad_norm": 10.285418510437012,
      "learning_rate": 9.346480722758123e-06,
      "loss": 2.0767,
      "step": 100
    },
    {
      "epoch": 0.12471655328798185,
      "grad_norm": 10.342191696166992,
      "learning_rate": 1.0281128795033934e-05,
      "loss": 2.0401,
      "step": 110
    },
    {
      "epoch": 0.1360544217687075,
      "grad_norm": 9.20302677154541,
      "learning_rate": 1.1215776867309747e-05,
      "loss": 1.99,
      "step": 120
    },
    {
      "epoch": 0.1473922902494331,
      "grad_norm": 9.420401573181152,
      "learning_rate": 1.215042493958556e-05,
      "loss": 1.9867,
      "step": 130
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 7.75075101852417,
      "learning_rate": 1.308507301186137e-05,
      "loss": 1.9988,
      "step": 140
    },
    {
      "epoch": 0.17006802721088435,
      "grad_norm": 8.807808876037598,
      "learning_rate": 1.4019721084137183e-05,
      "loss": 1.9886,
      "step": 150
    },
    {
      "epoch": 0.18140589569160998,
      "grad_norm": 10.291740417480469,
      "learning_rate": 1.4954369156412996e-05,
      "loss": 1.9393,
      "step": 160
    },
    {
      "epoch": 0.1927437641723356,
      "grad_norm": 8.806387901306152,
      "learning_rate": 1.588901722868881e-05,
      "loss": 1.9602,
      "step": 170
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 7.684463977813721,
      "learning_rate": 1.682366530096462e-05,
      "loss": 2.0044,
      "step": 180
    },
    {
      "epoch": 0.21541950113378686,
      "grad_norm": 8.645553588867188,
      "learning_rate": 1.7758313373240435e-05,
      "loss": 2.0519,
      "step": 190
    },
    {
      "epoch": 0.22675736961451248,
      "grad_norm": 9.162885665893555,
      "learning_rate": 1.8692961445516246e-05,
      "loss": 2.0516,
      "step": 200
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 7.536770343780518,
      "learning_rate": 1.9627609517792057e-05,
      "loss": 2.0299,
      "step": 210
    },
    {
      "epoch": 0.2494331065759637,
      "grad_norm": 8.47108268737793,
      "learning_rate": 2.0562257590067868e-05,
      "loss": 2.0816,
      "step": 220
    },
    {
      "epoch": 0.26077097505668934,
      "grad_norm": 6.5353498458862305,
      "learning_rate": 2.1496905662343682e-05,
      "loss": 2.0053,
      "step": 230
    },
    {
      "epoch": 0.272108843537415,
      "grad_norm": 7.390655994415283,
      "learning_rate": 2.2431553734619493e-05,
      "loss": 1.956,
      "step": 240
    },
    {
      "epoch": 0.2834467120181406,
      "grad_norm": 11.590116500854492,
      "learning_rate": 2.3366201806895304e-05,
      "loss": 1.9745,
      "step": 250
    },
    {
      "epoch": 0.2947845804988662,
      "grad_norm": 7.277239799499512,
      "learning_rate": 2.430084987917112e-05,
      "loss": 2.0846,
      "step": 260
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 7.210775375366211,
      "learning_rate": 2.523549795144693e-05,
      "loss": 1.9379,
      "step": 270
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 9.101860046386719,
      "learning_rate": 2.617014602372274e-05,
      "loss": 1.9774,
      "step": 280
    },
    {
      "epoch": 0.3287981859410431,
      "grad_norm": 8.541576385498047,
      "learning_rate": 2.7104794095998556e-05,
      "loss": 1.9359,
      "step": 290
    },
    {
      "epoch": 0.3401360544217687,
      "grad_norm": 9.097405433654785,
      "learning_rate": 2.8039442168274367e-05,
      "loss": 1.9943,
      "step": 300
    },
    {
      "epoch": 0.35147392290249435,
      "grad_norm": 10.134627342224121,
      "learning_rate": 2.8551341727859275e-05,
      "loss": 1.9935,
      "step": 310
    },
    {
      "epoch": 0.36281179138321995,
      "grad_norm": 9.275653839111328,
      "learning_rate": 2.842911851840782e-05,
      "loss": 1.9708,
      "step": 320
    },
    {
      "epoch": 0.3741496598639456,
      "grad_norm": 10.57584285736084,
      "learning_rate": 2.830689530895637e-05,
      "loss": 1.8931,
      "step": 330
    },
    {
      "epoch": 0.3854875283446712,
      "grad_norm": 8.968500137329102,
      "learning_rate": 2.818467209950492e-05,
      "loss": 2.0358,
      "step": 340
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 7.630152702331543,
      "learning_rate": 2.806244889005346e-05,
      "loss": 1.9313,
      "step": 350
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 10.709409713745117,
      "learning_rate": 2.794022568060201e-05,
      "loss": 1.8677,
      "step": 360
    },
    {
      "epoch": 0.41950113378684806,
      "grad_norm": 8.903763771057129,
      "learning_rate": 2.781800247115056e-05,
      "loss": 1.9309,
      "step": 370
    },
    {
      "epoch": 0.4308390022675737,
      "grad_norm": 11.22157096862793,
      "learning_rate": 2.769577926169911e-05,
      "loss": 1.9434,
      "step": 380
    },
    {
      "epoch": 0.4421768707482993,
      "grad_norm": 13.553994178771973,
      "learning_rate": 2.7573556052247655e-05,
      "loss": 1.9612,
      "step": 390
    },
    {
      "epoch": 0.45351473922902497,
      "grad_norm": 10.572993278503418,
      "learning_rate": 2.7451332842796204e-05,
      "loss": 1.9312,
      "step": 400
    },
    {
      "epoch": 0.46485260770975056,
      "grad_norm": 10.051871299743652,
      "learning_rate": 2.7329109633344753e-05,
      "loss": 2.0256,
      "step": 410
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 8.120019912719727,
      "learning_rate": 2.7206886423893295e-05,
      "loss": 1.8118,
      "step": 420
    },
    {
      "epoch": 0.4875283446712018,
      "grad_norm": 8.908893585205078,
      "learning_rate": 2.7084663214441844e-05,
      "loss": 1.9479,
      "step": 430
    },
    {
      "epoch": 0.4988662131519274,
      "grad_norm": 9.484359741210938,
      "learning_rate": 2.6962440004990394e-05,
      "loss": 1.9766,
      "step": 440
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 9.914438247680664,
      "learning_rate": 2.684021679553894e-05,
      "loss": 1.9492,
      "step": 450
    },
    {
      "epoch": 0.5215419501133787,
      "grad_norm": 10.76697063446045,
      "learning_rate": 2.671799358608749e-05,
      "loss": 1.9384,
      "step": 460
    },
    {
      "epoch": 0.5328798185941043,
      "grad_norm": 11.358717918395996,
      "learning_rate": 2.6595770376636038e-05,
      "loss": 1.8805,
      "step": 470
    },
    {
      "epoch": 0.54421768707483,
      "grad_norm": 10.204866409301758,
      "learning_rate": 2.6473547167184583e-05,
      "loss": 1.7569,
      "step": 480
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 9.388846397399902,
      "learning_rate": 2.635132395773313e-05,
      "loss": 1.9267,
      "step": 490
    },
    {
      "epoch": 0.5668934240362812,
      "grad_norm": 10.731882095336914,
      "learning_rate": 2.6229100748281678e-05,
      "loss": 1.9189,
      "step": 500
    },
    {
      "epoch": 0.5782312925170068,
      "grad_norm": 17.54758644104004,
      "learning_rate": 2.6106877538830227e-05,
      "loss": 1.9435,
      "step": 510
    },
    {
      "epoch": 0.5895691609977324,
      "grad_norm": 16.29359245300293,
      "learning_rate": 2.5984654329378773e-05,
      "loss": 1.9415,
      "step": 520
    },
    {
      "epoch": 0.6009070294784581,
      "grad_norm": 12.303582191467285,
      "learning_rate": 2.5862431119927322e-05,
      "loss": 1.9217,
      "step": 530
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 11.611120223999023,
      "learning_rate": 2.574020791047587e-05,
      "loss": 1.9101,
      "step": 540
    },
    {
      "epoch": 0.6235827664399093,
      "grad_norm": 8.830730438232422,
      "learning_rate": 2.5617984701024417e-05,
      "loss": 1.7771,
      "step": 550
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 17.929471969604492,
      "learning_rate": 2.5495761491572966e-05,
      "loss": 1.9179,
      "step": 560
    },
    {
      "epoch": 0.6462585034013606,
      "grad_norm": 10.709088325500488,
      "learning_rate": 2.5373538282121512e-05,
      "loss": 1.9077,
      "step": 570
    },
    {
      "epoch": 0.6575963718820862,
      "grad_norm": 11.527586936950684,
      "learning_rate": 2.5251315072670058e-05,
      "loss": 1.8224,
      "step": 580
    },
    {
      "epoch": 0.6689342403628118,
      "grad_norm": 10.246384620666504,
      "learning_rate": 2.5129091863218607e-05,
      "loss": 1.8023,
      "step": 590
    },
    {
      "epoch": 0.6802721088435374,
      "grad_norm": 16.176572799682617,
      "learning_rate": 2.5006868653767156e-05,
      "loss": 1.9447,
      "step": 600
    },
    {
      "epoch": 0.691609977324263,
      "grad_norm": 13.913769721984863,
      "learning_rate": 2.4884645444315702e-05,
      "loss": 1.8641,
      "step": 610
    },
    {
      "epoch": 0.7029478458049887,
      "grad_norm": 12.541318893432617,
      "learning_rate": 2.476242223486425e-05,
      "loss": 1.9395,
      "step": 620
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 12.410688400268555,
      "learning_rate": 2.46401990254128e-05,
      "loss": 1.9303,
      "step": 630
    },
    {
      "epoch": 0.7256235827664399,
      "grad_norm": 9.643453598022461,
      "learning_rate": 2.4517975815961346e-05,
      "loss": 1.9703,
      "step": 640
    },
    {
      "epoch": 0.7369614512471655,
      "grad_norm": 19.51215934753418,
      "learning_rate": 2.439575260650989e-05,
      "loss": 1.8502,
      "step": 650
    },
    {
      "epoch": 0.7482993197278912,
      "grad_norm": 16.120214462280273,
      "learning_rate": 2.427352939705844e-05,
      "loss": 1.8644,
      "step": 660
    },
    {
      "epoch": 0.7596371882086168,
      "grad_norm": 9.631799697875977,
      "learning_rate": 2.415130618760699e-05,
      "loss": 1.7562,
      "step": 670
    },
    {
      "epoch": 0.7709750566893424,
      "grad_norm": 11.26856803894043,
      "learning_rate": 2.4029082978155535e-05,
      "loss": 1.9283,
      "step": 680
    },
    {
      "epoch": 0.782312925170068,
      "grad_norm": 14.097902297973633,
      "learning_rate": 2.3906859768704085e-05,
      "loss": 1.8127,
      "step": 690
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 10.835921287536621,
      "learning_rate": 2.3784636559252634e-05,
      "loss": 1.6211,
      "step": 700
    },
    {
      "epoch": 0.8049886621315193,
      "grad_norm": 13.751789093017578,
      "learning_rate": 2.3662413349801176e-05,
      "loss": 1.7555,
      "step": 710
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 14.243096351623535,
      "learning_rate": 2.3540190140349725e-05,
      "loss": 1.6117,
      "step": 720
    },
    {
      "epoch": 0.8276643990929705,
      "grad_norm": 15.838502883911133,
      "learning_rate": 2.3417966930898274e-05,
      "loss": 1.7722,
      "step": 730
    },
    {
      "epoch": 0.8390022675736961,
      "grad_norm": 12.460963249206543,
      "learning_rate": 2.329574372144682e-05,
      "loss": 1.7567,
      "step": 740
    },
    {
      "epoch": 0.8503401360544217,
      "grad_norm": 17.053138732910156,
      "learning_rate": 2.317352051199537e-05,
      "loss": 1.907,
      "step": 750
    },
    {
      "epoch": 0.8616780045351474,
      "grad_norm": 12.155874252319336,
      "learning_rate": 2.305129730254392e-05,
      "loss": 1.9573,
      "step": 760
    },
    {
      "epoch": 0.873015873015873,
      "grad_norm": 9.946329116821289,
      "learning_rate": 2.2929074093092468e-05,
      "loss": 1.7964,
      "step": 770
    },
    {
      "epoch": 0.8843537414965986,
      "grad_norm": 13.480246543884277,
      "learning_rate": 2.2806850883641013e-05,
      "loss": 1.9251,
      "step": 780
    },
    {
      "epoch": 0.8956916099773242,
      "grad_norm": 9.594596862792969,
      "learning_rate": 2.268462767418956e-05,
      "loss": 1.6834,
      "step": 790
    },
    {
      "epoch": 0.9070294784580499,
      "grad_norm": 11.284895896911621,
      "learning_rate": 2.2562404464738108e-05,
      "loss": 1.7469,
      "step": 800
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 13.537227630615234,
      "learning_rate": 2.2440181255286654e-05,
      "loss": 1.6632,
      "step": 810
    },
    {
      "epoch": 0.9297052154195011,
      "grad_norm": 11.549741744995117,
      "learning_rate": 2.2317958045835203e-05,
      "loss": 1.788,
      "step": 820
    },
    {
      "epoch": 0.9410430839002267,
      "grad_norm": 53.76149368286133,
      "learning_rate": 2.2195734836383752e-05,
      "loss": 1.8974,
      "step": 830
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 9.953411102294922,
      "learning_rate": 2.2073511626932298e-05,
      "loss": 1.8805,
      "step": 840
    },
    {
      "epoch": 0.963718820861678,
      "grad_norm": 18.290058135986328,
      "learning_rate": 2.1951288417480847e-05,
      "loss": 1.6644,
      "step": 850
    },
    {
      "epoch": 0.9750566893424036,
      "grad_norm": 12.544032096862793,
      "learning_rate": 2.1829065208029393e-05,
      "loss": 1.6205,
      "step": 860
    },
    {
      "epoch": 0.9863945578231292,
      "grad_norm": 20.213836669921875,
      "learning_rate": 2.170684199857794e-05,
      "loss": 1.8964,
      "step": 870
    },
    {
      "epoch": 0.9977324263038548,
      "grad_norm": 17.492652893066406,
      "learning_rate": 2.1584618789126488e-05,
      "loss": 1.7601,
      "step": 880
    },
    {
      "epoch": 1.0,
      "eval_classification_report": {
        "accuracy": 0.3479986768111148,
        "ar": {
          "f1-score": 0.36553524804177545,
          "precision": 0.358974358974359,
          "recall": 0.3723404255319149,
          "support": 376.0
        },
        "cl": {
          "f1-score": 0.2568250758341759,
          "precision": 0.3075060532687651,
          "recall": 0.2204861111111111,
          "support": 576.0
        },
        "co": {
          "f1-score": 0.25892857142857145,
          "precision": 0.5576923076923077,
          "recall": 0.1686046511627907,
          "support": 344.0
        },
        "es": {
          "f1-score": 0.41894353369763204,
          "precision": 0.4144144144144144,
          "recall": 0.42357274401473294,
          "support": 543.0
        },
        "macro avg": {
          "f1-score": 0.3142646730168648,
          "precision": 0.3640216920469342,
          "recall": 0.3175752127167582,
          "support": 3023.0
        },
        "mx": {
          "f1-score": 0.38181818181818183,
          "precision": 0.2786729857819905,
          "recall": 0.6061855670103092,
          "support": 485.0
        },
        "pe": {
          "f1-score": 0.3090909090909091,
          "precision": 0.3269230769230769,
          "recall": 0.29310344827586204,
          "support": 348.0
        },
        "pr": {
          "f1-score": 0.5769230769230769,
          "precision": 0.5607476635514018,
          "recall": 0.594059405940594,
          "support": 101.0
        },
        "uy": {
          "f1-score": 0.26031746031746034,
          "precision": 0.47126436781609193,
          "recall": 0.17982456140350878,
          "support": 228.0
        },
        "ve": {
          "f1-score": 0.0,
          "precision": 0.0,
          "recall": 0.0,
          "support": 22.0
        },
        "weighted avg": {
          "f1-score": 0.3348651440888197,
          "precision": 0.37776395808289953,
          "recall": 0.3479986768111148,
          "support": 3023.0
        }
      },
      "eval_f1": 0.3142646730168648,
      "eval_loss": 1.7349679470062256,
      "eval_runtime": 4.5054,
      "eval_samples_per_second": 670.979,
      "eval_steps_per_second": 83.9,
      "step": 882
    },
    {
      "epoch": 1.0090702947845804,
      "grad_norm": 15.810832023620605,
      "learning_rate": 2.1462395579675037e-05,
      "loss": 1.6151,
      "step": 890
    },
    {
      "epoch": 1.0204081632653061,
      "grad_norm": 13.969820022583008,
      "learning_rate": 2.1340172370223586e-05,
      "loss": 1.6903,
      "step": 900
    },
    {
      "epoch": 1.0317460317460316,
      "grad_norm": 10.878263473510742,
      "learning_rate": 2.1217949160772132e-05,
      "loss": 1.3787,
      "step": 910
    },
    {
      "epoch": 1.0430839002267573,
      "grad_norm": 13.959477424621582,
      "learning_rate": 2.109572595132068e-05,
      "loss": 1.6575,
      "step": 920
    },
    {
      "epoch": 1.054421768707483,
      "grad_norm": 17.30800437927246,
      "learning_rate": 2.0973502741869227e-05,
      "loss": 1.5016,
      "step": 930
    },
    {
      "epoch": 1.0657596371882085,
      "grad_norm": 14.826261520385742,
      "learning_rate": 2.0851279532417772e-05,
      "loss": 1.6254,
      "step": 940
    },
    {
      "epoch": 1.0770975056689343,
      "grad_norm": 15.56223201751709,
      "learning_rate": 2.072905632296632e-05,
      "loss": 1.5939,
      "step": 950
    },
    {
      "epoch": 1.08843537414966,
      "grad_norm": 26.888315200805664,
      "learning_rate": 2.060683311351487e-05,
      "loss": 1.521,
      "step": 960
    },
    {
      "epoch": 1.0997732426303855,
      "grad_norm": 15.208369255065918,
      "learning_rate": 2.0484609904063416e-05,
      "loss": 1.601,
      "step": 970
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 20.432218551635742,
      "learning_rate": 2.0362386694611965e-05,
      "loss": 1.5258,
      "step": 980
    },
    {
      "epoch": 1.1224489795918366,
      "grad_norm": 16.719057083129883,
      "learning_rate": 2.0240163485160515e-05,
      "loss": 1.4809,
      "step": 990
    },
    {
      "epoch": 1.1337868480725624,
      "grad_norm": 20.315963745117188,
      "learning_rate": 2.011794027570906e-05,
      "loss": 1.4214,
      "step": 1000
    },
    {
      "epoch": 1.145124716553288,
      "grad_norm": 17.45546531677246,
      "learning_rate": 1.9995717066257606e-05,
      "loss": 1.5853,
      "step": 1010
    },
    {
      "epoch": 1.1564625850340136,
      "grad_norm": 16.830751419067383,
      "learning_rate": 1.9873493856806155e-05,
      "loss": 1.3777,
      "step": 1020
    },
    {
      "epoch": 1.1678004535147393,
      "grad_norm": 19.829317092895508,
      "learning_rate": 1.9751270647354704e-05,
      "loss": 1.3531,
      "step": 1030
    },
    {
      "epoch": 1.179138321995465,
      "grad_norm": 23.709720611572266,
      "learning_rate": 1.962904743790325e-05,
      "loss": 1.485,
      "step": 1040
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 14.404341697692871,
      "learning_rate": 1.95068242284518e-05,
      "loss": 1.2469,
      "step": 1050
    },
    {
      "epoch": 1.2018140589569162,
      "grad_norm": 26.16022300720215,
      "learning_rate": 1.938460101900035e-05,
      "loss": 1.5754,
      "step": 1060
    },
    {
      "epoch": 1.2131519274376417,
      "grad_norm": 20.90950584411621,
      "learning_rate": 1.9262377809548894e-05,
      "loss": 1.7132,
      "step": 1070
    },
    {
      "epoch": 1.2244897959183674,
      "grad_norm": 20.9376220703125,
      "learning_rate": 1.914015460009744e-05,
      "loss": 1.5629,
      "step": 1080
    },
    {
      "epoch": 1.235827664399093,
      "grad_norm": 18.35310935974121,
      "learning_rate": 1.901793139064599e-05,
      "loss": 1.4152,
      "step": 1090
    },
    {
      "epoch": 1.2471655328798186,
      "grad_norm": 18.69922637939453,
      "learning_rate": 1.8895708181194535e-05,
      "loss": 1.3757,
      "step": 1100
    },
    {
      "epoch": 1.2585034013605443,
      "grad_norm": 15.565815925598145,
      "learning_rate": 1.8773484971743084e-05,
      "loss": 1.3995,
      "step": 1110
    },
    {
      "epoch": 1.2698412698412698,
      "grad_norm": 20.754438400268555,
      "learning_rate": 1.8651261762291633e-05,
      "loss": 1.5485,
      "step": 1120
    },
    {
      "epoch": 1.2811791383219955,
      "grad_norm": 31.195865631103516,
      "learning_rate": 1.852903855284018e-05,
      "loss": 1.4945,
      "step": 1130
    },
    {
      "epoch": 1.2925170068027212,
      "grad_norm": 22.87392234802246,
      "learning_rate": 1.8406815343388728e-05,
      "loss": 1.5909,
      "step": 1140
    },
    {
      "epoch": 1.3038548752834467,
      "grad_norm": 16.350553512573242,
      "learning_rate": 1.8284592133937274e-05,
      "loss": 1.3411,
      "step": 1150
    },
    {
      "epoch": 1.3151927437641724,
      "grad_norm": 18.95813751220703,
      "learning_rate": 1.8162368924485823e-05,
      "loss": 1.5416,
      "step": 1160
    },
    {
      "epoch": 1.3265306122448979,
      "grad_norm": 21.95383071899414,
      "learning_rate": 1.804014571503437e-05,
      "loss": 1.4762,
      "step": 1170
    },
    {
      "epoch": 1.3378684807256236,
      "grad_norm": 22.101272583007812,
      "learning_rate": 1.7917922505582918e-05,
      "loss": 1.4737,
      "step": 1180
    },
    {
      "epoch": 1.3492063492063493,
      "grad_norm": 21.4808406829834,
      "learning_rate": 1.7795699296131467e-05,
      "loss": 1.2548,
      "step": 1190
    },
    {
      "epoch": 1.3605442176870748,
      "grad_norm": 17.070913314819336,
      "learning_rate": 1.7673476086680013e-05,
      "loss": 1.438,
      "step": 1200
    },
    {
      "epoch": 1.3718820861678005,
      "grad_norm": 23.818998336791992,
      "learning_rate": 1.7551252877228562e-05,
      "loss": 1.4455,
      "step": 1210
    },
    {
      "epoch": 1.383219954648526,
      "grad_norm": 25.911645889282227,
      "learning_rate": 1.742902966777711e-05,
      "loss": 1.4403,
      "step": 1220
    },
    {
      "epoch": 1.3945578231292517,
      "grad_norm": 16.849903106689453,
      "learning_rate": 1.7306806458325653e-05,
      "loss": 1.3663,
      "step": 1230
    },
    {
      "epoch": 1.4058956916099774,
      "grad_norm": 16.710933685302734,
      "learning_rate": 1.7184583248874202e-05,
      "loss": 1.3915,
      "step": 1240
    },
    {
      "epoch": 1.417233560090703,
      "grad_norm": 22.40735626220703,
      "learning_rate": 1.706236003942275e-05,
      "loss": 1.472,
      "step": 1250
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 23.049968719482422,
      "learning_rate": 1.6940136829971297e-05,
      "loss": 1.3523,
      "step": 1260
    },
    {
      "epoch": 1.439909297052154,
      "grad_norm": 12.89521598815918,
      "learning_rate": 1.6817913620519846e-05,
      "loss": 1.5376,
      "step": 1270
    },
    {
      "epoch": 1.4512471655328798,
      "grad_norm": 19.498533248901367,
      "learning_rate": 1.6695690411068396e-05,
      "loss": 1.5389,
      "step": 1280
    },
    {
      "epoch": 1.4625850340136055,
      "grad_norm": 18.624237060546875,
      "learning_rate": 1.657346720161694e-05,
      "loss": 1.4731,
      "step": 1290
    },
    {
      "epoch": 1.473922902494331,
      "grad_norm": 21.690345764160156,
      "learning_rate": 1.6451243992165487e-05,
      "loss": 1.3718,
      "step": 1300
    },
    {
      "epoch": 1.4852607709750567,
      "grad_norm": 21.58686065673828,
      "learning_rate": 1.6329020782714036e-05,
      "loss": 1.6325,
      "step": 1310
    },
    {
      "epoch": 1.4965986394557822,
      "grad_norm": 17.337610244750977,
      "learning_rate": 1.6206797573262585e-05,
      "loss": 1.5196,
      "step": 1320
    },
    {
      "epoch": 1.507936507936508,
      "grad_norm": 22.74974822998047,
      "learning_rate": 1.608457436381113e-05,
      "loss": 1.6169,
      "step": 1330
    },
    {
      "epoch": 1.5192743764172336,
      "grad_norm": 24.127099990844727,
      "learning_rate": 1.596235115435968e-05,
      "loss": 1.3358,
      "step": 1340
    },
    {
      "epoch": 1.5306122448979593,
      "grad_norm": 18.630477905273438,
      "learning_rate": 1.584012794490823e-05,
      "loss": 1.2559,
      "step": 1350
    },
    {
      "epoch": 1.5419501133786848,
      "grad_norm": 22.353515625,
      "learning_rate": 1.5717904735456775e-05,
      "loss": 1.3693,
      "step": 1360
    },
    {
      "epoch": 1.5532879818594103,
      "grad_norm": 25.24136734008789,
      "learning_rate": 1.559568152600532e-05,
      "loss": 1.4876,
      "step": 1370
    },
    {
      "epoch": 1.564625850340136,
      "grad_norm": 13.99299144744873,
      "learning_rate": 1.547345831655387e-05,
      "loss": 1.3684,
      "step": 1380
    },
    {
      "epoch": 1.5759637188208617,
      "grad_norm": 17.318729400634766,
      "learning_rate": 1.5351235107102416e-05,
      "loss": 1.2686,
      "step": 1390
    },
    {
      "epoch": 1.5873015873015874,
      "grad_norm": 16.49215316772461,
      "learning_rate": 1.5229011897650965e-05,
      "loss": 1.3287,
      "step": 1400
    },
    {
      "epoch": 1.598639455782313,
      "grad_norm": 17.993852615356445,
      "learning_rate": 1.5106788688199514e-05,
      "loss": 1.3661,
      "step": 1410
    },
    {
      "epoch": 1.6099773242630384,
      "grad_norm": 17.669912338256836,
      "learning_rate": 1.4984565478748061e-05,
      "loss": 1.4371,
      "step": 1420
    },
    {
      "epoch": 1.6213151927437641,
      "grad_norm": 32.347835540771484,
      "learning_rate": 1.4862342269296609e-05,
      "loss": 1.5957,
      "step": 1430
    },
    {
      "epoch": 1.6326530612244898,
      "grad_norm": 15.98144245147705,
      "learning_rate": 1.4740119059845155e-05,
      "loss": 1.3895,
      "step": 1440
    },
    {
      "epoch": 1.6439909297052155,
      "grad_norm": 15.446006774902344,
      "learning_rate": 1.4617895850393702e-05,
      "loss": 1.4985,
      "step": 1450
    },
    {
      "epoch": 1.655328798185941,
      "grad_norm": 20.650182723999023,
      "learning_rate": 1.4495672640942251e-05,
      "loss": 1.3036,
      "step": 1460
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 18.82501220703125,
      "learning_rate": 1.4373449431490799e-05,
      "loss": 1.3777,
      "step": 1470
    },
    {
      "epoch": 1.6780045351473922,
      "grad_norm": 24.08733558654785,
      "learning_rate": 1.4251226222039346e-05,
      "loss": 1.4847,
      "step": 1480
    },
    {
      "epoch": 1.689342403628118,
      "grad_norm": 15.655111312866211,
      "learning_rate": 1.4129003012587895e-05,
      "loss": 1.6208,
      "step": 1490
    },
    {
      "epoch": 1.7006802721088436,
      "grad_norm": 14.29283618927002,
      "learning_rate": 1.4006779803136441e-05,
      "loss": 1.4783,
      "step": 1500
    },
    {
      "epoch": 1.7120181405895691,
      "grad_norm": 27.245153427124023,
      "learning_rate": 1.388455659368499e-05,
      "loss": 1.3621,
      "step": 1510
    },
    {
      "epoch": 1.7233560090702946,
      "grad_norm": 17.18270492553711,
      "learning_rate": 1.3762333384233537e-05,
      "loss": 1.4615,
      "step": 1520
    },
    {
      "epoch": 1.7346938775510203,
      "grad_norm": 30.546113967895508,
      "learning_rate": 1.3640110174782085e-05,
      "loss": 1.4101,
      "step": 1530
    },
    {
      "epoch": 1.746031746031746,
      "grad_norm": 27.630264282226562,
      "learning_rate": 1.3517886965330632e-05,
      "loss": 1.5457,
      "step": 1540
    },
    {
      "epoch": 1.7573696145124718,
      "grad_norm": 24.351619720458984,
      "learning_rate": 1.339566375587918e-05,
      "loss": 1.4364,
      "step": 1550
    },
    {
      "epoch": 1.7687074829931972,
      "grad_norm": 22.478717803955078,
      "learning_rate": 1.3273440546427727e-05,
      "loss": 1.5078,
      "step": 1560
    },
    {
      "epoch": 1.780045351473923,
      "grad_norm": 33.06885528564453,
      "learning_rate": 1.3151217336976275e-05,
      "loss": 1.3344,
      "step": 1570
    },
    {
      "epoch": 1.7913832199546484,
      "grad_norm": 25.309829711914062,
      "learning_rate": 1.3028994127524822e-05,
      "loss": 1.4234,
      "step": 1580
    },
    {
      "epoch": 1.8027210884353742,
      "grad_norm": 26.68161392211914,
      "learning_rate": 1.2906770918073371e-05,
      "loss": 1.326,
      "step": 1590
    },
    {
      "epoch": 1.8140589569160999,
      "grad_norm": 24.11896324157715,
      "learning_rate": 1.2784547708621919e-05,
      "loss": 1.5031,
      "step": 1600
    },
    {
      "epoch": 1.8253968253968254,
      "grad_norm": 19.29245948791504,
      "learning_rate": 1.2662324499170464e-05,
      "loss": 1.3132,
      "step": 1610
    },
    {
      "epoch": 1.836734693877551,
      "grad_norm": 18.402624130249023,
      "learning_rate": 1.2540101289719014e-05,
      "loss": 1.359,
      "step": 1620
    },
    {
      "epoch": 1.8480725623582765,
      "grad_norm": 22.64293670654297,
      "learning_rate": 1.2417878080267561e-05,
      "loss": 1.6493,
      "step": 1630
    },
    {
      "epoch": 1.8594104308390023,
      "grad_norm": 20.680465698242188,
      "learning_rate": 1.2295654870816108e-05,
      "loss": 1.3705,
      "step": 1640
    },
    {
      "epoch": 1.870748299319728,
      "grad_norm": 21.203262329101562,
      "learning_rate": 1.2173431661364656e-05,
      "loss": 1.4593,
      "step": 1650
    },
    {
      "epoch": 1.8820861678004537,
      "grad_norm": 19.054349899291992,
      "learning_rate": 1.2051208451913203e-05,
      "loss": 1.316,
      "step": 1660
    },
    {
      "epoch": 1.8934240362811792,
      "grad_norm": 18.196651458740234,
      "learning_rate": 1.1928985242461752e-05,
      "loss": 1.4121,
      "step": 1670
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 14.884149551391602,
      "learning_rate": 1.1806762033010298e-05,
      "loss": 1.2392,
      "step": 1680
    },
    {
      "epoch": 1.9160997732426304,
      "grad_norm": 21.171005249023438,
      "learning_rate": 1.1684538823558846e-05,
      "loss": 1.3379,
      "step": 1690
    },
    {
      "epoch": 1.927437641723356,
      "grad_norm": 18.805988311767578,
      "learning_rate": 1.1562315614107395e-05,
      "loss": 1.3454,
      "step": 1700
    },
    {
      "epoch": 1.9387755102040818,
      "grad_norm": 19.397449493408203,
      "learning_rate": 1.1440092404655942e-05,
      "loss": 1.4548,
      "step": 1710
    },
    {
      "epoch": 1.9501133786848073,
      "grad_norm": 20.647939682006836,
      "learning_rate": 1.131786919520449e-05,
      "loss": 1.4206,
      "step": 1720
    },
    {
      "epoch": 1.9614512471655328,
      "grad_norm": 22.62149429321289,
      "learning_rate": 1.1195645985753037e-05,
      "loss": 1.3777,
      "step": 1730
    },
    {
      "epoch": 1.9727891156462585,
      "grad_norm": 27.34062385559082,
      "learning_rate": 1.1073422776301585e-05,
      "loss": 1.3447,
      "step": 1740
    },
    {
      "epoch": 1.9841269841269842,
      "grad_norm": 29.27070426940918,
      "learning_rate": 1.0951199566850134e-05,
      "loss": 1.3864,
      "step": 1750
    },
    {
      "epoch": 1.99546485260771,
      "grad_norm": 16.5633487701416,
      "learning_rate": 1.082897635739868e-05,
      "loss": 1.2893,
      "step": 1760
    },
    {
      "epoch": 2.0,
      "eval_classification_report": {
        "accuracy": 0.3989414488918293,
        "ar": {
          "f1-score": 0.3793103448275862,
          "precision": 0.4618320610687023,
          "recall": 0.32180851063829785,
          "support": 376.0
        },
        "cl": {
          "f1-score": 0.37325038880248834,
          "precision": 0.3380281690140845,
          "recall": 0.4166666666666667,
          "support": 576.0
        },
        "co": {
          "f1-score": 0.3398230088495575,
          "precision": 0.4343891402714932,
          "recall": 0.27906976744186046,
          "support": 344.0
        },
        "es": {
          "f1-score": 0.4501323918799647,
          "precision": 0.4322033898305085,
          "recall": 0.4696132596685083,
          "support": 543.0
        },
        "macro avg": {
          "f1-score": 0.3755741665997943,
          "precision": 0.4098704182426044,
          "recall": 0.3639331480997811,
          "support": 3023.0
        },
        "mx": {
          "f1-score": 0.4408888888888889,
          "precision": 0.3875,
          "recall": 0.511340206185567,
          "support": 485.0
        },
        "pe": {
          "f1-score": 0.35097493036211697,
          "precision": 0.34054054054054056,
          "recall": 0.3620689655172414,
          "support": 348.0
        },
        "pr": {
          "f1-score": 0.6666666666666666,
          "precision": 0.7159090909090909,
          "recall": 0.6237623762376238,
          "support": 101.0
        },
        "uy": {
          "f1-score": 0.3076923076923077,
          "precision": 0.4117647058823529,
          "recall": 0.24561403508771928,
          "support": 228.0
        },
        "ve": {
          "f1-score": 0.07142857142857142,
          "precision": 0.16666666666666666,
          "recall": 0.045454545454545456,
          "support": 22.0
        },
        "weighted avg": {
          "f1-score": 0.3949596137532948,
          "precision": 0.40647397656072576,
          "recall": 0.3989414488918293,
          "support": 3023.0
        }
      },
      "eval_f1": 0.3755741665997943,
      "eval_loss": 1.6900478601455688,
      "eval_runtime": 4.3866,
      "eval_samples_per_second": 689.137,
      "eval_steps_per_second": 86.171,
      "step": 1764
    }
  ],
  "logging_steps": 10,
  "max_steps": 2646,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 463959726481152.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}