{
  "best_metric": 0.3142646730168648,
  "best_model_checkpoint": "/content/drive/MyDrive/model_outputs/trial_9/checkpoint-882",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 882,
  "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
    }
  ],
  "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": 231979863240576.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}