{
  "best_global_step": 7245,
  "best_metric": 0.8153345585743379,
  "best_model_checkpoint": "outputs/runs/bartpho/checkpoint-7245",
  "epoch": 23.0,
  "eval_steps": 500,
  "global_step": 7245,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9968253968253968,
      "grad_norm": 5.682558536529541,
      "learning_rate": 4.999432333543028e-06,
      "loss": 0.6382,
      "step": 314
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6618786257685761,
      "eval_f1": 0.5275329196417486,
      "eval_loss": 0.623261570930481,
      "eval_precision": 0.7377902962250189,
      "eval_recall": 0.5717004519029796,
      "eval_runtime": 1.4418,
      "eval_samples_per_second": 902.363,
      "eval_steps_per_second": 28.437,
      "step": 315
    },
    {
      "epoch": 1.9936507936507937,
      "grad_norm": 1.4926543235778809,
      "learning_rate": 4.996525669931999e-06,
      "loss": 0.5683,
      "step": 628
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6871157119533122,
      "eval_f1": 0.6270341888525142,
      "eval_loss": 0.5687424540519714,
      "eval_precision": 0.6851236426126874,
      "eval_recall": 0.6290258325510966,
      "eval_runtime": 1.4493,
      "eval_samples_per_second": 897.649,
      "eval_steps_per_second": 28.289,
      "step": 630
    },
    {
      "epoch": 2.9904761904761905,
      "grad_norm": 6.10944128036499,
      "learning_rate": 4.991155236893945e-06,
      "loss": 0.5534,
      "step": 942
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6981102581026157,
      "eval_f1": 0.6686886646196348,
      "eval_loss": 0.5649789571762085,
      "eval_precision": 0.6820856346718416,
      "eval_recall": 0.6647145253749493,
      "eval_runtime": 1.4482,
      "eval_samples_per_second": 898.381,
      "eval_steps_per_second": 28.312,
      "step": 945
    },
    {
      "epoch": 3.9873015873015873,
      "grad_norm": 3.255537509918213,
      "learning_rate": 4.983326334397891e-06,
      "loss": 0.5436,
      "step": 1256
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.697224441588217,
      "eval_f1": 0.6146617747343325,
      "eval_loss": 0.5817087888717651,
      "eval_precision": 0.7360948991758735,
      "eval_recall": 0.625299233298471,
      "eval_runtime": 1.4497,
      "eval_samples_per_second": 897.453,
      "eval_steps_per_second": 28.283,
      "step": 1260
    },
    {
      "epoch": 4.984126984126984,
      "grad_norm": 4.936647891998291,
      "learning_rate": 4.97304668862541e-06,
      "loss": 0.5387,
      "step": 1570
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6994824052523708,
      "eval_f1": 0.6780463785641409,
      "eval_loss": 0.5464158654212952,
      "eval_precision": 0.6826491609942078,
      "eval_recall": 0.6754857450135558,
      "eval_runtime": 1.4501,
      "eval_samples_per_second": 897.181,
      "eval_steps_per_second": 28.274,
      "step": 1575
    },
    {
      "epoch": 5.980952380952381,
      "grad_norm": 5.54253625869751,
      "learning_rate": 4.9603264443458e-06,
      "loss": 0.5347,
      "step": 1884
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.703234098725119,
      "eval_f1": 0.658548053122289,
      "eval_loss": 0.5504359602928162,
      "eval_precision": 0.6971966581407725,
      "eval_recall": 0.6552219050544602,
      "eval_runtime": 1.4502,
      "eval_samples_per_second": 897.134,
      "eval_steps_per_second": 28.272,
      "step": 1890
    },
    {
      "epoch": 6.977777777777778,
      "grad_norm": 2.980400800704956,
      "learning_rate": 4.945178154904432e-06,
      "loss": 0.5295,
      "step": 2198
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7049188869976031,
      "eval_f1": 0.6712744945089447,
      "eval_loss": 0.5498743057250977,
      "eval_precision": 0.6921020382053092,
      "eval_recall": 0.6667597786262732,
      "eval_runtime": 1.451,
      "eval_samples_per_second": 896.602,
      "eval_steps_per_second": 28.256,
      "step": 2205
    },
    {
      "epoch": 7.974603174603175,
      "grad_norm": 1.8561100959777832,
      "learning_rate": 4.92761676983411e-06,
      "loss": 0.526,
      "step": 2512
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7058568103657901,
      "eval_f1": 0.662676465048434,
      "eval_loss": 0.5571920871734619,
      "eval_precision": 0.6997671412894451,
      "eval_recall": 0.6589087948228982,
      "eval_runtime": 1.4516,
      "eval_samples_per_second": 896.228,
      "eval_steps_per_second": 28.244,
      "step": 2520
    },
    {
      "epoch": 8.971428571428572,
      "grad_norm": 3.5451998710632324,
      "learning_rate": 4.9076596201016856e-06,
      "loss": 0.523,
      "step": 2826
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7018619515753639,
      "eval_f1": 0.625374057862767,
      "eval_loss": 0.5914136171340942,
      "eval_precision": 0.7358493036678011,
      "eval_recall": 0.6327511530635204,
      "eval_runtime": 1.4534,
      "eval_samples_per_second": 895.149,
      "eval_steps_per_second": 28.21,
      "step": 2835
    },
    {
      "epoch": 9.968253968253968,
      "grad_norm": 5.0408406257629395,
      "learning_rate": 4.88532640100449e-06,
      "loss": 0.5171,
      "step": 3140
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.7077847639559524,
      "eval_f1": 0.6786121509955985,
      "eval_loss": 0.5660568475723267,
      "eval_precision": 0.6936028147526183,
      "eval_recall": 0.6741239127178265,
      "eval_runtime": 1.4513,
      "eval_samples_per_second": 896.413,
      "eval_steps_per_second": 28.25,
      "step": 3150
    },
    {
      "epoch": 10.965079365079365,
      "grad_norm": 9.36005973815918,
      "learning_rate": 4.860639152733449e-06,
      "loss": 0.5147,
      "step": 3454
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.701914058429152,
      "eval_f1": 0.6364582078339008,
      "eval_loss": 0.5687407851219177,
      "eval_precision": 0.7180110728497148,
      "eval_recall": 0.6392313775049545,
      "eval_runtime": 1.4526,
      "eval_samples_per_second": 895.624,
      "eval_steps_per_second": 28.225,
      "step": 3465
    },
    {
      "epoch": 11.961904761904762,
      "grad_norm": 3.487974166870117,
      "learning_rate": 4.833622238622079e-06,
      "loss": 0.5095,
      "step": 3768
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.7085316288602495,
      "eval_f1": 0.6626885625948004,
      "eval_loss": 0.5603615045547485,
      "eval_precision": 0.7060931620291221,
      "eval_recall": 0.6591844125186699,
      "eval_runtime": 1.4523,
      "eval_samples_per_second": 895.797,
      "eval_steps_per_second": 28.23,
      "step": 3780
    },
    {
      "epoch": 12.958730158730159,
      "grad_norm": 5.526001930236816,
      "learning_rate": 4.804302321102816e-06,
      "loss": 0.508,
      "step": 4082
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.7037377983117379,
      "eval_f1": 0.6584786752528541,
      "eval_loss": 0.5470253229141235,
      "eval_precision": 0.6984109009927764,
      "eval_recall": 0.6552206326603638,
      "eval_runtime": 1.4537,
      "eval_samples_per_second": 894.952,
      "eval_steps_per_second": 28.204,
      "step": 4095
    },
    {
      "epoch": 13.955555555555556,
      "grad_norm": 7.560145378112793,
      "learning_rate": 4.772708335394416e-06,
      "loss": 0.5029,
      "step": 4396
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.713568624726439,
      "eval_f1": 0.6795572312733509,
      "eval_loss": 0.5456140637397766,
      "eval_precision": 0.7034572312241041,
      "eval_recall": 0.6744872926065051,
      "eval_runtime": 1.4534,
      "eval_samples_per_second": 895.17,
      "eval_steps_per_second": 28.211,
      "step": 4410
    },
    {
      "epoch": 14.952380952380953,
      "grad_norm": 5.061767578125,
      "learning_rate": 4.738871460946384e-06,
      "loss": 0.4971,
      "step": 4710
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.7147323444610414,
      "eval_f1": 0.6712151153220013,
      "eval_loss": 0.5506519675254822,
      "eval_precision": 0.7131289966118773,
      "eval_recall": 0.66683731470523,
      "eval_runtime": 1.4555,
      "eval_samples_per_second": 893.846,
      "eval_steps_per_second": 28.169,
      "step": 4725
    },
    {
      "epoch": 15.94920634920635,
      "grad_norm": 3.6310696601867676,
      "learning_rate": 4.702825090668624e-06,
      "loss": 0.4883,
      "step": 5024
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.7275853683954563,
      "eval_f1": 0.6800593771748749,
      "eval_loss": 0.5249310731887817,
      "eval_precision": 0.7385652261130415,
      "eval_recall": 0.6753129875296177,
      "eval_runtime": 1.4568,
      "eval_samples_per_second": 893.074,
      "eval_steps_per_second": 28.145,
      "step": 5040
    },
    {
      "epoch": 16.946031746031746,
      "grad_norm": 3.5576395988464355,
      "learning_rate": 4.664604797976672e-06,
      "loss": 0.4785,
      "step": 5338
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.7470733317122312,
      "eval_f1": 0.7220592428721022,
      "eval_loss": 0.5220229625701904,
      "eval_precision": 0.7393366406970809,
      "eval_recall": 0.7157473225861406,
      "eval_runtime": 1.4557,
      "eval_samples_per_second": 893.714,
      "eval_steps_per_second": 28.165,
      "step": 5355
    },
    {
      "epoch": 17.942857142857143,
      "grad_norm": 3.7962605953216553,
      "learning_rate": 4.6242483016850204e-06,
      "loss": 0.4601,
      "step": 5652
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.7800743391114044,
      "eval_f1": 0.7542114810572249,
      "eval_loss": 0.47945165634155273,
      "eval_precision": 0.7845629818690574,
      "eval_recall": 0.7447658710776668,
      "eval_runtime": 1.4542,
      "eval_samples_per_second": 894.647,
      "eval_steps_per_second": 28.194,
      "step": 5670
    },
    {
      "epoch": 18.93968253968254,
      "grad_norm": 6.58827543258667,
      "learning_rate": 4.581795428783211e-06,
      "loss": 0.438,
      "step": 5966
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.8036266370236566,
      "eval_f1": 0.7794844647965122,
      "eval_loss": 0.45785731077194214,
      "eval_precision": 0.8159505749196594,
      "eval_recall": 0.7680218463402948,
      "eval_runtime": 1.4553,
      "eval_samples_per_second": 893.958,
      "eval_steps_per_second": 28.172,
      "step": 5985
    },
    {
      "epoch": 19.936507936507937,
      "grad_norm": 5.3035383224487305,
      "learning_rate": 4.537288075131401e-06,
      "loss": 0.4133,
      "step": 6280
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.8041129676590127,
      "eval_f1": 0.797301642675663,
      "eval_loss": 0.4323329031467438,
      "eval_precision": 0.7942179843107702,
      "eval_recall": 0.8029752318176708,
      "eval_runtime": 1.452,
      "eval_samples_per_second": 895.983,
      "eval_steps_per_second": 28.236,
      "step": 6300
    },
    {
      "epoch": 20.933333333333334,
      "grad_norm": 5.589924335479736,
      "learning_rate": 4.490770164114206e-06,
      "loss": 0.3947,
      "step": 6594
    },
    {
      "epoch": 21.0,
      "eval_accuracy": 0.8210650640914302,
      "eval_f1": 0.8050070699973129,
      "eval_loss": 0.41711243987083435,
      "eval_precision": 0.821898032840692,
      "eval_recall": 0.7966116925782902,
      "eval_runtime": 1.4546,
      "eval_samples_per_second": 894.434,
      "eval_steps_per_second": 28.187,
      "step": 6615
    },
    {
      "epoch": 21.93015873015873,
      "grad_norm": 4.1770501136779785,
      "learning_rate": 4.442287603293625e-06,
      "loss": 0.3787,
      "step": 6908
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.8151943585646299,
      "eval_f1": 0.807236518842082,
      "eval_loss": 0.4175125062465668,
      "eval_precision": 0.8051094915340469,
      "eval_recall": 0.8099929034678388,
      "eval_runtime": 1.4549,
      "eval_samples_per_second": 894.205,
      "eval_steps_per_second": 28.18,
      "step": 6930
    },
    {
      "epoch": 22.926984126984127,
      "grad_norm": 6.486811637878418,
      "learning_rate": 4.391888239103818e-06,
      "loss": 0.367,
      "step": 7222
    },
    {
      "epoch": 23.0,
      "eval_accuracy": 0.8269878764720187,
      "eval_f1": 0.8153345585743379,
      "eval_loss": 0.4084073305130005,
      "eval_precision": 0.8211330177764262,
      "eval_recall": 0.8111882260202181,
      "eval_runtime": 1.4534,
      "eval_samples_per_second": 895.129,
      "eval_steps_per_second": 28.209,
      "step": 7245
    }
  ],
  "logging_steps": 314,
  "max_steps": 31500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}