{
  "best_metric": 0.35031697154045105,
  "best_model_checkpoint": "deberta-sent-multi/checkpoint-1800",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 1.9551440477371216,
      "learning_rate": 2.3148148148148148e-06,
      "loss": 0.6935,
      "step": 25
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 1.187191128730774,
      "learning_rate": 4.6296296296296296e-06,
      "loss": 0.6957,
      "step": 50
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 0.9179525375366211,
      "learning_rate": 6.944444444444445e-06,
      "loss": 0.6948,
      "step": 75
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.4890326261520386,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.6827,
      "step": 100
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 7.563885688781738,
      "learning_rate": 1.1574074074074075e-05,
      "loss": 0.5348,
      "step": 125
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 5.335231781005859,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.5517,
      "step": 150
    },
    {
      "epoch": 0.09722222222222222,
      "grad_norm": 31.28253746032715,
      "learning_rate": 1.6203703703703704e-05,
      "loss": 0.4477,
      "step": 175
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 3.2105932235717773,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.5092,
      "step": 200
    },
    {
      "epoch": 0.125,
      "grad_norm": 4.380924701690674,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 0.3824,
      "step": 225
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 2.6306023597717285,
      "learning_rate": 2.314814814814815e-05,
      "loss": 0.3407,
      "step": 250
    },
    {
      "epoch": 0.1527777777777778,
      "grad_norm": 54.588436126708984,
      "learning_rate": 2.5462962962962965e-05,
      "loss": 0.6848,
      "step": 275
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 9.066441535949707,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.5151,
      "step": 300
    },
    {
      "epoch": 0.18055555555555555,
      "grad_norm": 2.912062168121338,
      "learning_rate": 3.0092592592592593e-05,
      "loss": 0.3909,
      "step": 325
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 14.664259910583496,
      "learning_rate": 3.240740740740741e-05,
      "loss": 0.4754,
      "step": 350
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 17.37154769897461,
      "learning_rate": 3.472222222222222e-05,
      "loss": 0.4067,
      "step": 375
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 7.159306049346924,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.5269,
      "step": 400
    },
    {
      "epoch": 0.2361111111111111,
      "grad_norm": 24.980106353759766,
      "learning_rate": 3.935185185185186e-05,
      "loss": 0.3985,
      "step": 425
    },
    {
      "epoch": 0.25,
      "grad_norm": 10.40503215789795,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.5491,
      "step": 450
    },
    {
      "epoch": 0.2638888888888889,
      "grad_norm": 2.9398627281188965,
      "learning_rate": 4.3981481481481486e-05,
      "loss": 0.3183,
      "step": 475
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 20.303274154663086,
      "learning_rate": 4.62962962962963e-05,
      "loss": 0.4905,
      "step": 500
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 5.474150657653809,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 0.4931,
      "step": 525
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 18.128984451293945,
      "learning_rate": 4.9897119341563785e-05,
      "loss": 0.636,
      "step": 550
    },
    {
      "epoch": 0.3194444444444444,
      "grad_norm": 41.586219787597656,
      "learning_rate": 4.963991769547325e-05,
      "loss": 0.3997,
      "step": 575
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 11.251654624938965,
      "learning_rate": 4.938271604938271e-05,
      "loss": 0.6164,
      "step": 600
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 3.6719627380371094,
      "learning_rate": 4.912551440329218e-05,
      "loss": 0.4721,
      "step": 625
    },
    {
      "epoch": 0.3611111111111111,
      "grad_norm": 6.4116435050964355,
      "learning_rate": 4.886831275720165e-05,
      "loss": 0.5444,
      "step": 650
    },
    {
      "epoch": 0.375,
      "grad_norm": 8.13191032409668,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 0.4481,
      "step": 675
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 2.3826730251312256,
      "learning_rate": 4.835390946502058e-05,
      "loss": 0.4876,
      "step": 700
    },
    {
      "epoch": 0.4027777777777778,
      "grad_norm": 9.0649995803833,
      "learning_rate": 4.809670781893004e-05,
      "loss": 0.5457,
      "step": 725
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 3.2031192779541016,
      "learning_rate": 4.783950617283951e-05,
      "loss": 0.4291,
      "step": 750
    },
    {
      "epoch": 0.4305555555555556,
      "grad_norm": 3.011695384979248,
      "learning_rate": 4.758230452674897e-05,
      "loss": 0.5681,
      "step": 775
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 17.774301528930664,
      "learning_rate": 4.732510288065844e-05,
      "loss": 0.5143,
      "step": 800
    },
    {
      "epoch": 0.4583333333333333,
      "grad_norm": 3.0613749027252197,
      "learning_rate": 4.70679012345679e-05,
      "loss": 0.603,
      "step": 825
    },
    {
      "epoch": 0.4722222222222222,
      "grad_norm": 7.315563201904297,
      "learning_rate": 4.6810699588477366e-05,
      "loss": 0.5161,
      "step": 850
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 10.456121444702148,
      "learning_rate": 4.6553497942386833e-05,
      "loss": 0.39,
      "step": 875
    },
    {
      "epoch": 0.5,
      "grad_norm": 9.36212158203125,
      "learning_rate": 4.62962962962963e-05,
      "loss": 0.4058,
      "step": 900
    },
    {
      "epoch": 0.5138888888888888,
      "grad_norm": 2.4673802852630615,
      "learning_rate": 4.603909465020577e-05,
      "loss": 0.3361,
      "step": 925
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 7.2702202796936035,
      "learning_rate": 4.578189300411523e-05,
      "loss": 0.3313,
      "step": 950
    },
    {
      "epoch": 0.5416666666666666,
      "grad_norm": 15.533823013305664,
      "learning_rate": 4.5524691358024696e-05,
      "loss": 0.4702,
      "step": 975
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 12.91049861907959,
      "learning_rate": 4.5267489711934157e-05,
      "loss": 0.4219,
      "step": 1000
    },
    {
      "epoch": 0.5694444444444444,
      "grad_norm": 8.368412017822266,
      "learning_rate": 4.5010288065843624e-05,
      "loss": 0.3685,
      "step": 1025
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 38.96614074707031,
      "learning_rate": 4.4753086419753084e-05,
      "loss": 0.4168,
      "step": 1050
    },
    {
      "epoch": 0.5972222222222222,
      "grad_norm": 5.273324489593506,
      "learning_rate": 4.449588477366255e-05,
      "loss": 0.5382,
      "step": 1075
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 9.082724571228027,
      "learning_rate": 4.423868312757202e-05,
      "loss": 0.525,
      "step": 1100
    },
    {
      "epoch": 0.625,
      "grad_norm": 12.262503623962402,
      "learning_rate": 4.3981481481481486e-05,
      "loss": 0.3931,
      "step": 1125
    },
    {
      "epoch": 0.6388888888888888,
      "grad_norm": 31.51844596862793,
      "learning_rate": 4.372427983539095e-05,
      "loss": 0.3836,
      "step": 1150
    },
    {
      "epoch": 0.6527777777777778,
      "grad_norm": 4.899830341339111,
      "learning_rate": 4.3467078189300414e-05,
      "loss": 0.4635,
      "step": 1175
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 8.966187477111816,
      "learning_rate": 4.3209876543209875e-05,
      "loss": 0.3706,
      "step": 1200
    },
    {
      "epoch": 0.6805555555555556,
      "grad_norm": 12.4137544631958,
      "learning_rate": 4.295267489711934e-05,
      "loss": 0.6281,
      "step": 1225
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 4.339605808258057,
      "learning_rate": 4.269547325102881e-05,
      "loss": 0.4616,
      "step": 1250
    },
    {
      "epoch": 0.7083333333333334,
      "grad_norm": 27.38968276977539,
      "learning_rate": 4.243827160493827e-05,
      "loss": 0.4681,
      "step": 1275
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 4.831294059753418,
      "learning_rate": 4.2181069958847744e-05,
      "loss": 0.4135,
      "step": 1300
    },
    {
      "epoch": 0.7361111111111112,
      "grad_norm": 9.18549633026123,
      "learning_rate": 4.1923868312757205e-05,
      "loss": 0.444,
      "step": 1325
    },
    {
      "epoch": 0.75,
      "grad_norm": 3.1465399265289307,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.3754,
      "step": 1350
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 16.972923278808594,
      "learning_rate": 4.140946502057613e-05,
      "loss": 0.466,
      "step": 1375
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 1.612660527229309,
      "learning_rate": 4.11522633744856e-05,
      "loss": 0.3867,
      "step": 1400
    },
    {
      "epoch": 0.7916666666666666,
      "grad_norm": 7.258045673370361,
      "learning_rate": 4.089506172839506e-05,
      "loss": 0.5741,
      "step": 1425
    },
    {
      "epoch": 0.8055555555555556,
      "grad_norm": 7.1187214851379395,
      "learning_rate": 4.063786008230453e-05,
      "loss": 0.4024,
      "step": 1450
    },
    {
      "epoch": 0.8194444444444444,
      "grad_norm": 15.787425994873047,
      "learning_rate": 4.038065843621399e-05,
      "loss": 0.4623,
      "step": 1475
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 2.3647310733795166,
      "learning_rate": 4.012345679012346e-05,
      "loss": 0.3146,
      "step": 1500
    },
    {
      "epoch": 0.8472222222222222,
      "grad_norm": 3.4890708923339844,
      "learning_rate": 3.986625514403292e-05,
      "loss": 0.3952,
      "step": 1525
    },
    {
      "epoch": 0.8611111111111112,
      "grad_norm": 17.58116912841797,
      "learning_rate": 3.960905349794239e-05,
      "loss": 0.4454,
      "step": 1550
    },
    {
      "epoch": 0.875,
      "grad_norm": 5.0533246994018555,
      "learning_rate": 3.935185185185186e-05,
      "loss": 0.4524,
      "step": 1575
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 23.176776885986328,
      "learning_rate": 3.909465020576132e-05,
      "loss": 0.401,
      "step": 1600
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 5.863523483276367,
      "learning_rate": 3.8837448559670786e-05,
      "loss": 0.4483,
      "step": 1625
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 12.402013778686523,
      "learning_rate": 3.8580246913580246e-05,
      "loss": 0.5053,
      "step": 1650
    },
    {
      "epoch": 0.9305555555555556,
      "grad_norm": 2.132073402404785,
      "learning_rate": 3.8323045267489713e-05,
      "loss": 0.3247,
      "step": 1675
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 2.4326186180114746,
      "learning_rate": 3.806584362139918e-05,
      "loss": 0.4661,
      "step": 1700
    },
    {
      "epoch": 0.9583333333333334,
      "grad_norm": 14.031126976013184,
      "learning_rate": 3.780864197530865e-05,
      "loss": 0.4249,
      "step": 1725
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 24.70652198791504,
      "learning_rate": 3.755144032921811e-05,
      "loss": 0.3789,
      "step": 1750
    },
    {
      "epoch": 0.9861111111111112,
      "grad_norm": 2.8892605304718018,
      "learning_rate": 3.7294238683127576e-05,
      "loss": 0.4248,
      "step": 1775
    },
    {
      "epoch": 1.0,
      "grad_norm": 6.622640132904053,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.3189,
      "step": 1800
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.865,
      "eval_auc": 0.9395007159925164,
      "eval_f1": 0.869073275862069,
      "eval_loss": 0.35031697154045105,
      "eval_precision": 0.8529878371232152,
      "eval_recall": 0.885777045579352,
      "eval_runtime": 1007.1559,
      "eval_samples_per_second": 3.574,
      "eval_steps_per_second": 0.223,
      "step": 1800
    }
  ],
  "logging_steps": 25,
  "max_steps": 5400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "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": 947216786227200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}