{
  "best_metric": 0.784,
  "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-ovq62xze/checkpoint-1000",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 2.8580408096313477,
      "learning_rate": 7.324907510001364e-05,
      "loss": 0.5558,
      "step": 10
    },
    {
      "epoch": 0.1,
      "grad_norm": 4.629230976104736,
      "learning_rate": 7.250918545253876e-05,
      "loss": 0.5753,
      "step": 20
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.6798982620239258,
      "learning_rate": 7.176929580506387e-05,
      "loss": 0.5007,
      "step": 30
    },
    {
      "epoch": 0.2,
      "grad_norm": 4.710047245025635,
      "learning_rate": 7.1029406157589e-05,
      "loss": 0.5568,
      "step": 40
    },
    {
      "epoch": 0.25,
      "grad_norm": 16.165040969848633,
      "learning_rate": 7.02895165101141e-05,
      "loss": 0.5409,
      "step": 50
    },
    {
      "epoch": 0.3,
      "grad_norm": 3.3471007347106934,
      "learning_rate": 6.954962686263921e-05,
      "loss": 0.3631,
      "step": 60
    },
    {
      "epoch": 0.35,
      "grad_norm": 2.770080089569092,
      "learning_rate": 6.880973721516433e-05,
      "loss": 0.1851,
      "step": 70
    },
    {
      "epoch": 0.4,
      "grad_norm": 10.271796226501465,
      "learning_rate": 6.806984756768946e-05,
      "loss": 0.7488,
      "step": 80
    },
    {
      "epoch": 0.45,
      "grad_norm": 3.5753231048583984,
      "learning_rate": 6.732995792021456e-05,
      "loss": 0.5854,
      "step": 90
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.666292905807495,
      "learning_rate": 6.659006827273969e-05,
      "loss": 0.412,
      "step": 100
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.2799642086029053,
      "learning_rate": 6.58501786252648e-05,
      "loss": 0.557,
      "step": 110
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.7298201322555542,
      "learning_rate": 6.51102889777899e-05,
      "loss": 0.4918,
      "step": 120
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.6464192271232605,
      "learning_rate": 6.437039933031503e-05,
      "loss": 0.4231,
      "step": 130
    },
    {
      "epoch": 0.7,
      "grad_norm": 4.867911338806152,
      "learning_rate": 6.363050968284013e-05,
      "loss": 0.4482,
      "step": 140
    },
    {
      "epoch": 0.75,
      "grad_norm": 6.947429656982422,
      "learning_rate": 6.289062003536524e-05,
      "loss": 0.3369,
      "step": 150
    },
    {
      "epoch": 0.8,
      "grad_norm": 6.325223445892334,
      "learning_rate": 6.215073038789037e-05,
      "loss": 0.6414,
      "step": 160
    },
    {
      "epoch": 0.85,
      "grad_norm": 4.6585001945495605,
      "learning_rate": 6.141084074041547e-05,
      "loss": 0.488,
      "step": 170
    },
    {
      "epoch": 0.9,
      "grad_norm": 8.477282524108887,
      "learning_rate": 6.067095109294059e-05,
      "loss": 0.2685,
      "step": 180
    },
    {
      "epoch": 0.95,
      "grad_norm": 2.3661060333251953,
      "learning_rate": 5.993106144546571e-05,
      "loss": 0.4817,
      "step": 190
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6013305187225342,
      "learning_rate": 5.919117179799083e-05,
      "loss": 0.351,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.805,
      "eval_f1": 0.743421052631579,
      "eval_loss": 0.5347685813903809,
      "eval_precision": 0.6243093922651933,
      "eval_recall": 0.9186991869918699,
      "eval_runtime": 1.5641,
      "eval_samples_per_second": 255.745,
      "eval_steps_per_second": 15.984,
      "step": 200
    },
    {
      "epoch": 1.05,
      "grad_norm": 3.003253698348999,
      "learning_rate": 5.8451282150515943e-05,
      "loss": 0.5513,
      "step": 210
    },
    {
      "epoch": 1.1,
      "grad_norm": 2.9436538219451904,
      "learning_rate": 5.771139250304106e-05,
      "loss": 0.4827,
      "step": 220
    },
    {
      "epoch": 1.15,
      "grad_norm": 4.9929656982421875,
      "learning_rate": 5.697150285556617e-05,
      "loss": 0.3016,
      "step": 230
    },
    {
      "epoch": 1.2,
      "grad_norm": 10.904691696166992,
      "learning_rate": 5.623161320809128e-05,
      "loss": 0.2161,
      "step": 240
    },
    {
      "epoch": 1.25,
      "grad_norm": 5.562251567840576,
      "learning_rate": 5.54917235606164e-05,
      "loss": 0.2296,
      "step": 250
    },
    {
      "epoch": 1.3,
      "grad_norm": 21.09694480895996,
      "learning_rate": 5.4751833913141514e-05,
      "loss": 0.3892,
      "step": 260
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.3990909457206726,
      "learning_rate": 5.401194426566663e-05,
      "loss": 0.3668,
      "step": 270
    },
    {
      "epoch": 1.4,
      "grad_norm": 2.7531650066375732,
      "learning_rate": 5.327205461819174e-05,
      "loss": 0.2828,
      "step": 280
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.6674296259880066,
      "learning_rate": 5.2532164970716854e-05,
      "loss": 0.3773,
      "step": 290
    },
    {
      "epoch": 1.5,
      "grad_norm": 16.001766204833984,
      "learning_rate": 5.179227532324197e-05,
      "loss": 0.2175,
      "step": 300
    },
    {
      "epoch": 1.55,
      "grad_norm": 6.789841651916504,
      "learning_rate": 5.1052385675767085e-05,
      "loss": 0.3477,
      "step": 310
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.3401732444763184,
      "learning_rate": 5.031249602829221e-05,
      "loss": 0.2424,
      "step": 320
    },
    {
      "epoch": 1.65,
      "grad_norm": 7.187565326690674,
      "learning_rate": 4.9572606380817316e-05,
      "loss": 0.2964,
      "step": 330
    },
    {
      "epoch": 1.7,
      "grad_norm": 1.6464786529541016,
      "learning_rate": 4.883271673334243e-05,
      "loss": 0.3348,
      "step": 340
    },
    {
      "epoch": 1.75,
      "grad_norm": 7.238956451416016,
      "learning_rate": 4.809282708586755e-05,
      "loss": 0.3278,
      "step": 350
    },
    {
      "epoch": 1.8,
      "grad_norm": 2.914743423461914,
      "learning_rate": 4.735293743839266e-05,
      "loss": 0.2056,
      "step": 360
    },
    {
      "epoch": 1.85,
      "grad_norm": 13.46723747253418,
      "learning_rate": 4.661304779091778e-05,
      "loss": 0.5176,
      "step": 370
    },
    {
      "epoch": 1.9,
      "grad_norm": 6.557673931121826,
      "learning_rate": 4.5873158143442887e-05,
      "loss": 0.3953,
      "step": 380
    },
    {
      "epoch": 1.95,
      "grad_norm": 2.1576859951019287,
      "learning_rate": 4.5133268495968e-05,
      "loss": 0.2685,
      "step": 390
    },
    {
      "epoch": 2.0,
      "grad_norm": 14.825181007385254,
      "learning_rate": 4.439337884849312e-05,
      "loss": 0.4442,
      "step": 400
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.83,
      "eval_f1": 0.7536231884057971,
      "eval_loss": 0.4959351420402527,
      "eval_precision": 0.6797385620915033,
      "eval_recall": 0.8455284552845529,
      "eval_runtime": 1.509,
      "eval_samples_per_second": 265.069,
      "eval_steps_per_second": 16.567,
      "step": 400
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.3849884271621704,
      "learning_rate": 4.365348920101823e-05,
      "loss": 0.0339,
      "step": 410
    },
    {
      "epoch": 2.1,
      "grad_norm": 15.426344871520996,
      "learning_rate": 4.291359955354335e-05,
      "loss": 0.3828,
      "step": 420
    },
    {
      "epoch": 2.15,
      "grad_norm": 3.521732807159424,
      "learning_rate": 4.217370990606846e-05,
      "loss": 0.2092,
      "step": 430
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.6053170561790466,
      "learning_rate": 4.143382025859358e-05,
      "loss": 0.15,
      "step": 440
    },
    {
      "epoch": 2.25,
      "grad_norm": 2.9728167057037354,
      "learning_rate": 4.0693930611118695e-05,
      "loss": 0.1983,
      "step": 450
    },
    {
      "epoch": 2.3,
      "grad_norm": 1.158972978591919,
      "learning_rate": 3.995404096364381e-05,
      "loss": 0.1547,
      "step": 460
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.08352199196815491,
      "learning_rate": 3.9214151316168926e-05,
      "loss": 0.3832,
      "step": 470
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.16624656319618225,
      "learning_rate": 3.8474261668694035e-05,
      "loss": 0.1125,
      "step": 480
    },
    {
      "epoch": 2.45,
      "grad_norm": 13.895761489868164,
      "learning_rate": 3.773437202121915e-05,
      "loss": 0.1891,
      "step": 490
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.07783038169145584,
      "learning_rate": 3.6994482373744266e-05,
      "loss": 0.1845,
      "step": 500
    },
    {
      "epoch": 2.55,
      "grad_norm": 5.39270544052124,
      "learning_rate": 3.625459272626938e-05,
      "loss": 0.3712,
      "step": 510
    },
    {
      "epoch": 2.6,
      "grad_norm": 8.580484390258789,
      "learning_rate": 3.55147030787945e-05,
      "loss": 0.2922,
      "step": 520
    },
    {
      "epoch": 2.65,
      "grad_norm": 5.49284553527832,
      "learning_rate": 3.4774813431319605e-05,
      "loss": 0.0888,
      "step": 530
    },
    {
      "epoch": 2.7,
      "grad_norm": 2.509190559387207,
      "learning_rate": 3.403492378384473e-05,
      "loss": 0.2952,
      "step": 540
    },
    {
      "epoch": 2.75,
      "grad_norm": 1.1146562099456787,
      "learning_rate": 3.329503413636984e-05,
      "loss": 0.2025,
      "step": 550
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.5424324870109558,
      "learning_rate": 3.255514448889495e-05,
      "loss": 0.3394,
      "step": 560
    },
    {
      "epoch": 2.85,
      "grad_norm": 1.1997493505477905,
      "learning_rate": 3.181525484142007e-05,
      "loss": 0.2041,
      "step": 570
    },
    {
      "epoch": 2.9,
      "grad_norm": 18.82257080078125,
      "learning_rate": 3.107536519394518e-05,
      "loss": 0.5699,
      "step": 580
    },
    {
      "epoch": 2.95,
      "grad_norm": 11.223532676696777,
      "learning_rate": 3.0335475546470295e-05,
      "loss": 0.2722,
      "step": 590
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.048981666564941,
      "learning_rate": 2.9595585898995414e-05,
      "loss": 0.1852,
      "step": 600
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8625,
      "eval_f1": 0.7773279352226721,
      "eval_loss": 0.45909401774406433,
      "eval_precision": 0.7741935483870968,
      "eval_recall": 0.7804878048780488,
      "eval_runtime": 1.5277,
      "eval_samples_per_second": 261.826,
      "eval_steps_per_second": 16.364,
      "step": 600
    },
    {
      "epoch": 3.05,
      "grad_norm": 2.716031074523926,
      "learning_rate": 2.885569625152053e-05,
      "loss": 0.0911,
      "step": 610
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.11326009035110474,
      "learning_rate": 2.811580660404564e-05,
      "loss": 0.0525,
      "step": 620
    },
    {
      "epoch": 3.15,
      "grad_norm": 67.94048309326172,
      "learning_rate": 2.7375916956570757e-05,
      "loss": 0.1708,
      "step": 630
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.16798238456249237,
      "learning_rate": 2.663602730909587e-05,
      "loss": 0.1027,
      "step": 640
    },
    {
      "epoch": 3.25,
      "grad_norm": 8.024996757507324,
      "learning_rate": 2.5896137661620985e-05,
      "loss": 0.3075,
      "step": 650
    },
    {
      "epoch": 3.3,
      "grad_norm": 0.16531293094158173,
      "learning_rate": 2.5156248014146104e-05,
      "loss": 0.1509,
      "step": 660
    },
    {
      "epoch": 3.35,
      "grad_norm": 0.06556364893913269,
      "learning_rate": 2.4416358366671216e-05,
      "loss": 0.2373,
      "step": 670
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.1460653692483902,
      "learning_rate": 2.367646871919633e-05,
      "loss": 0.0401,
      "step": 680
    },
    {
      "epoch": 3.45,
      "grad_norm": 0.07078050822019577,
      "learning_rate": 2.2936579071721443e-05,
      "loss": 0.0538,
      "step": 690
    },
    {
      "epoch": 3.5,
      "grad_norm": 5.139517307281494,
      "learning_rate": 2.219668942424656e-05,
      "loss": 0.3995,
      "step": 700
    },
    {
      "epoch": 3.55,
      "grad_norm": 0.08660732954740524,
      "learning_rate": 2.1456799776771674e-05,
      "loss": 0.0592,
      "step": 710
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.20419315993785858,
      "learning_rate": 2.071691012929679e-05,
      "loss": 0.1184,
      "step": 720
    },
    {
      "epoch": 3.65,
      "grad_norm": 0.03444228321313858,
      "learning_rate": 1.9977020481821905e-05,
      "loss": 0.0935,
      "step": 730
    },
    {
      "epoch": 3.7,
      "grad_norm": 0.4479585587978363,
      "learning_rate": 1.9237130834347017e-05,
      "loss": 0.0884,
      "step": 740
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.24001504480838776,
      "learning_rate": 1.8497241186872133e-05,
      "loss": 0.0098,
      "step": 750
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.12233974784612656,
      "learning_rate": 1.775735153939725e-05,
      "loss": 0.0209,
      "step": 760
    },
    {
      "epoch": 3.85,
      "grad_norm": 3.510254383087158,
      "learning_rate": 1.7017461891922364e-05,
      "loss": 0.3062,
      "step": 770
    },
    {
      "epoch": 3.9,
      "grad_norm": 0.15961907804012299,
      "learning_rate": 1.6277572244447476e-05,
      "loss": 0.1364,
      "step": 780
    },
    {
      "epoch": 3.95,
      "grad_norm": 0.13841329514980316,
      "learning_rate": 1.553768259697259e-05,
      "loss": 0.0952,
      "step": 790
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.308049440383911,
      "learning_rate": 1.4797792949497707e-05,
      "loss": 0.1577,
      "step": 800
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.84,
      "eval_f1": 0.7697841726618705,
      "eval_loss": 0.6505396366119385,
      "eval_precision": 0.6903225806451613,
      "eval_recall": 0.8699186991869918,
      "eval_runtime": 1.5135,
      "eval_samples_per_second": 264.29,
      "eval_steps_per_second": 16.518,
      "step": 800
    },
    {
      "epoch": 4.05,
      "grad_norm": 0.12980560958385468,
      "learning_rate": 1.405790330202282e-05,
      "loss": 0.0537,
      "step": 810
    },
    {
      "epoch": 4.1,
      "grad_norm": 15.213448524475098,
      "learning_rate": 1.3318013654547935e-05,
      "loss": 0.0635,
      "step": 820
    },
    {
      "epoch": 4.15,
      "grad_norm": 0.13449443876743317,
      "learning_rate": 1.2578124007073052e-05,
      "loss": 0.0357,
      "step": 830
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.11500319093465805,
      "learning_rate": 1.1838234359598166e-05,
      "loss": 0.2038,
      "step": 840
    },
    {
      "epoch": 4.25,
      "grad_norm": 0.05510816350579262,
      "learning_rate": 1.109834471212328e-05,
      "loss": 0.0265,
      "step": 850
    },
    {
      "epoch": 4.3,
      "grad_norm": 0.11758866161108017,
      "learning_rate": 1.0358455064648395e-05,
      "loss": 0.0069,
      "step": 860
    },
    {
      "epoch": 4.35,
      "grad_norm": 5.604867935180664,
      "learning_rate": 9.618565417173509e-06,
      "loss": 0.1583,
      "step": 870
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.17312869429588318,
      "learning_rate": 8.878675769698624e-06,
      "loss": 0.2303,
      "step": 880
    },
    {
      "epoch": 4.45,
      "grad_norm": 0.10631933808326721,
      "learning_rate": 8.138786122223738e-06,
      "loss": 0.005,
      "step": 890
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.11875050514936447,
      "learning_rate": 7.3988964747488535e-06,
      "loss": 0.0861,
      "step": 900
    },
    {
      "epoch": 4.55,
      "grad_norm": 0.25447019934654236,
      "learning_rate": 6.659006827273967e-06,
      "loss": 0.0067,
      "step": 910
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.15403024852275848,
      "learning_rate": 5.919117179799083e-06,
      "loss": 0.1064,
      "step": 920
    },
    {
      "epoch": 4.65,
      "grad_norm": 0.10930292308330536,
      "learning_rate": 5.1792275323241974e-06,
      "loss": 0.0978,
      "step": 930
    },
    {
      "epoch": 4.7,
      "grad_norm": 2.734524726867676,
      "learning_rate": 4.439337884849312e-06,
      "loss": 0.1193,
      "step": 940
    },
    {
      "epoch": 4.75,
      "grad_norm": 3.565016746520996,
      "learning_rate": 3.6994482373744267e-06,
      "loss": 0.1922,
      "step": 950
    },
    {
      "epoch": 4.8,
      "grad_norm": 2.8288533687591553,
      "learning_rate": 2.9595585898995414e-06,
      "loss": 0.058,
      "step": 960
    },
    {
      "epoch": 4.85,
      "grad_norm": 3.0187721252441406,
      "learning_rate": 2.219668942424656e-06,
      "loss": 0.16,
      "step": 970
    },
    {
      "epoch": 4.9,
      "grad_norm": 0.1212492510676384,
      "learning_rate": 1.4797792949497707e-06,
      "loss": 0.076,
      "step": 980
    },
    {
      "epoch": 4.95,
      "grad_norm": 0.08606864511966705,
      "learning_rate": 7.398896474748853e-07,
      "loss": 0.0058,
      "step": 990
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0966118648648262,
      "learning_rate": 0.0,
      "loss": 0.0051,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.865,
      "eval_f1": 0.784,
      "eval_loss": 0.5539087057113647,
      "eval_precision": 0.7716535433070866,
      "eval_recall": 0.7967479674796748,
      "eval_runtime": 1.5704,
      "eval_samples_per_second": 254.715,
      "eval_steps_per_second": 15.92,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 1059076852254720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "_wandb": {},
    "assignments": {},
    "learning_rate": 7.398896474748853e-05,
    "metric": "eval/loss",
    "num_train_epochs": 5,
    "per_device_train_batch_size": 8,
    "seed": 14
  }
}