{
  "best_metric": 0.8754390108936493,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-121",
  "epoch": 34.0,
  "eval_steps": 500,
  "global_step": 153,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8888888888888888,
      "eval_accuracy": 0.63003663003663,
      "eval_confusion_matrix": [
        [
          53,
          0,
          16,
          3
        ],
        [
          28,
          1,
          31,
          0
        ],
        [
          13,
          0,
          62,
          1
        ],
        [
          3,
          0,
          6,
          56
        ]
      ],
      "eval_f1": 0.566693372031096,
      "eval_loss": 1.31327486038208,
      "eval_precision": 0.7361933549293478,
      "eval_recall": 0.63003663003663,
      "eval_runtime": 2.8436,
      "eval_samples_per_second": 96.005,
      "eval_steps_per_second": 1.055,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6593406593406593,
      "eval_confusion_matrix": [
        [
          41,
          10,
          16,
          5
        ],
        [
          21,
          1,
          38,
          0
        ],
        [
          1,
          2,
          73,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.595713773130153,
      "eval_loss": 0.9242589473724365,
      "eval_precision": 0.5696509512811321,
      "eval_recall": 0.6593406593406593,
      "eval_runtime": 2.8668,
      "eval_samples_per_second": 95.227,
      "eval_steps_per_second": 1.046,
      "step": 9
    },
    {
      "epoch": 2.888888888888889,
      "eval_accuracy": 0.717948717948718,
      "eval_confusion_matrix": [
        [
          52,
          8,
          7,
          5
        ],
        [
          18,
          5,
          37,
          0
        ],
        [
          1,
          0,
          75,
          0
        ],
        [
          1,
          0,
          0,
          64
        ]
      ],
      "eval_f1": 0.6621621567125869,
      "eval_loss": 0.8232662081718445,
      "eval_precision": 0.671303801513745,
      "eval_recall": 0.717948717948718,
      "eval_runtime": 2.8711,
      "eval_samples_per_second": 95.084,
      "eval_steps_per_second": 1.045,
      "step": 13
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6959706959706959,
      "eval_confusion_matrix": [
        [
          45,
          9,
          13,
          5
        ],
        [
          13,
          5,
          42,
          0
        ],
        [
          1,
          0,
          75,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.6428796900399459,
      "eval_loss": 0.951453447341919,
      "eval_precision": 0.6613447705829899,
      "eval_recall": 0.6959706959706959,
      "eval_runtime": 2.8813,
      "eval_samples_per_second": 94.75,
      "eval_steps_per_second": 1.041,
      "step": 18
    },
    {
      "epoch": 4.888888888888889,
      "eval_accuracy": 0.6666666666666666,
      "eval_confusion_matrix": [
        [
          16,
          49,
          3,
          4
        ],
        [
          1,
          26,
          33,
          0
        ],
        [
          0,
          1,
          75,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.6331541584523206,
      "eval_loss": 1.0080645084381104,
      "eval_precision": 0.7358031394913882,
      "eval_recall": 0.6666666666666666,
      "eval_runtime": 2.9108,
      "eval_samples_per_second": 93.789,
      "eval_steps_per_second": 1.031,
      "step": 22
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.652014652014652,
      "eval_confusion_matrix": [
        [
          66,
          0,
          0,
          6
        ],
        [
          36,
          16,
          8,
          0
        ],
        [
          10,
          35,
          31,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.6302407955860642,
      "eval_loss": 0.9598046541213989,
      "eval_precision": 0.6636241740077424,
      "eval_recall": 0.652014652014652,
      "eval_runtime": 2.9773,
      "eval_samples_per_second": 91.693,
      "eval_steps_per_second": 1.008,
      "step": 27
    },
    {
      "epoch": 6.888888888888889,
      "eval_accuracy": 0.7692307692307693,
      "eval_confusion_matrix": [
        [
          66,
          0,
          0,
          6
        ],
        [
          29,
          21,
          10,
          0
        ],
        [
          3,
          15,
          58,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.7527855586679116,
      "eval_loss": 0.7898163795471191,
      "eval_precision": 0.7612467677056892,
      "eval_recall": 0.7692307692307693,
      "eval_runtime": 2.8918,
      "eval_samples_per_second": 94.404,
      "eval_steps_per_second": 1.037,
      "step": 31
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7802197802197802,
      "eval_confusion_matrix": [
        [
          66,
          0,
          0,
          6
        ],
        [
          25,
          15,
          19,
          1
        ],
        [
          1,
          6,
          68,
          1
        ],
        [
          1,
          0,
          0,
          64
        ]
      ],
      "eval_f1": 0.7471179200524057,
      "eval_loss": 0.7337484359741211,
      "eval_precision": 0.7733845922309294,
      "eval_recall": 0.7802197802197802,
      "eval_runtime": 2.9006,
      "eval_samples_per_second": 94.119,
      "eval_steps_per_second": 1.034,
      "step": 36
    },
    {
      "epoch": 8.88888888888889,
      "eval_accuracy": 0.7912087912087912,
      "eval_confusion_matrix": [
        [
          57,
          8,
          3,
          4
        ],
        [
          13,
          24,
          23,
          0
        ],
        [
          0,
          5,
          71,
          0
        ],
        [
          1,
          0,
          0,
          64
        ]
      ],
      "eval_f1": 0.7766564722186922,
      "eval_loss": 0.7148727178573608,
      "eval_precision": 0.7821504483074875,
      "eval_recall": 0.7912087912087912,
      "eval_runtime": 2.8866,
      "eval_samples_per_second": 94.576,
      "eval_steps_per_second": 1.039,
      "step": 40
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8168498168498168,
      "eval_confusion_matrix": [
        [
          51,
          8,
          1,
          12
        ],
        [
          10,
          36,
          14,
          0
        ],
        [
          0,
          5,
          71,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8094336953840884,
      "eval_loss": 0.7574812173843384,
      "eval_precision": 0.8127936625684181,
      "eval_recall": 0.8168498168498168,
      "eval_runtime": 2.8967,
      "eval_samples_per_second": 94.245,
      "eval_steps_per_second": 1.036,
      "step": 45
    },
    {
      "epoch": 10.88888888888889,
      "eval_accuracy": 0.8021978021978022,
      "eval_confusion_matrix": [
        [
          48,
          18,
          2,
          4
        ],
        [
          4,
          41,
          15,
          0
        ],
        [
          0,
          7,
          69,
          0
        ],
        [
          3,
          0,
          1,
          61
        ]
      ],
      "eval_f1": 0.801525180147331,
      "eval_loss": 0.7140281200408936,
      "eval_precision": 0.8109338936925145,
      "eval_recall": 0.8021978021978022,
      "eval_runtime": 2.917,
      "eval_samples_per_second": 93.589,
      "eval_steps_per_second": 1.028,
      "step": 49
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.8534798534798534,
      "eval_confusion_matrix": [
        [
          56,
          12,
          0,
          4
        ],
        [
          6,
          43,
          11,
          0
        ],
        [
          0,
          6,
          70,
          0
        ],
        [
          1,
          0,
          0,
          64
        ]
      ],
      "eval_f1": 0.8523994617102314,
      "eval_loss": 0.6672152280807495,
      "eval_precision": 0.8540313732642031,
      "eval_recall": 0.8534798534798534,
      "eval_runtime": 2.8969,
      "eval_samples_per_second": 94.238,
      "eval_steps_per_second": 1.036,
      "step": 54
    },
    {
      "epoch": 12.88888888888889,
      "eval_accuracy": 0.8498168498168498,
      "eval_confusion_matrix": [
        [
          60,
          8,
          0,
          4
        ],
        [
          8,
          38,
          14,
          0
        ],
        [
          0,
          6,
          70,
          0
        ],
        [
          1,
          0,
          0,
          64
        ]
      ],
      "eval_f1": 0.8463270052615757,
      "eval_loss": 0.6432910561561584,
      "eval_precision": 0.8460243715014519,
      "eval_recall": 0.8498168498168498,
      "eval_runtime": 3.0281,
      "eval_samples_per_second": 90.156,
      "eval_steps_per_second": 0.991,
      "step": 58
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.8278388278388278,
      "eval_confusion_matrix": [
        [
          54,
          13,
          1,
          4
        ],
        [
          7,
          44,
          9,
          0
        ],
        [
          0,
          11,
          65,
          0
        ],
        [
          1,
          1,
          0,
          63
        ]
      ],
      "eval_f1": 0.82943590265942,
      "eval_loss": 0.7395206093788147,
      "eval_precision": 0.8350059217447382,
      "eval_recall": 0.8278388278388278,
      "eval_runtime": 2.9869,
      "eval_samples_per_second": 91.399,
      "eval_steps_per_second": 1.004,
      "step": 63
    },
    {
      "epoch": 14.88888888888889,
      "eval_accuracy": 0.8315018315018315,
      "eval_confusion_matrix": [
        [
          54,
          13,
          1,
          4
        ],
        [
          10,
          39,
          11,
          0
        ],
        [
          0,
          7,
          69,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8291811389886823,
      "eval_loss": 0.7115849852561951,
      "eval_precision": 0.829244108966536,
      "eval_recall": 0.8315018315018315,
      "eval_runtime": 2.9616,
      "eval_samples_per_second": 92.181,
      "eval_steps_per_second": 1.013,
      "step": 67
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.8315018315018315,
      "eval_confusion_matrix": [
        [
          60,
          7,
          1,
          4
        ],
        [
          10,
          39,
          11,
          0
        ],
        [
          0,
          11,
          65,
          0
        ],
        [
          1,
          1,
          0,
          63
        ]
      ],
      "eval_f1": 0.8304073820984628,
      "eval_loss": 0.7295921444892883,
      "eval_precision": 0.8295426562258641,
      "eval_recall": 0.8315018315018315,
      "eval_runtime": 2.8758,
      "eval_samples_per_second": 94.932,
      "eval_steps_per_second": 1.043,
      "step": 72
    },
    {
      "epoch": 16.88888888888889,
      "eval_accuracy": 0.8644688644688645,
      "eval_confusion_matrix": [
        [
          62,
          5,
          1,
          4
        ],
        [
          9,
          37,
          14,
          0
        ],
        [
          0,
          3,
          73,
          0
        ],
        [
          1,
          0,
          0,
          64
        ]
      ],
      "eval_f1": 0.8589767100678526,
      "eval_loss": 0.7055637240409851,
      "eval_precision": 0.8628397746044805,
      "eval_recall": 0.8644688644688645,
      "eval_runtime": 3.074,
      "eval_samples_per_second": 88.809,
      "eval_steps_per_second": 0.976,
      "step": 76
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.8644688644688645,
      "eval_confusion_matrix": [
        [
          65,
          2,
          1,
          4
        ],
        [
          13,
          42,
          5,
          0
        ],
        [
          0,
          12,
          64,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8627769756077204,
      "eval_loss": 0.7563945651054382,
      "eval_precision": 0.8634344261673453,
      "eval_recall": 0.8644688644688645,
      "eval_runtime": 3.0072,
      "eval_samples_per_second": 90.783,
      "eval_steps_per_second": 0.998,
      "step": 81
    },
    {
      "epoch": 18.88888888888889,
      "eval_accuracy": 0.8424908424908425,
      "eval_confusion_matrix": [
        [
          64,
          4,
          0,
          4
        ],
        [
          11,
          41,
          8,
          0
        ],
        [
          0,
          10,
          66,
          0
        ],
        [
          6,
          0,
          0,
          59
        ]
      ],
      "eval_f1": 0.8418306879608031,
      "eval_loss": 0.7825365662574768,
      "eval_precision": 0.8434907006335578,
      "eval_recall": 0.8424908424908425,
      "eval_runtime": 3.0343,
      "eval_samples_per_second": 89.972,
      "eval_steps_per_second": 0.989,
      "step": 85
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.8058608058608059,
      "eval_confusion_matrix": [
        [
          40,
          28,
          1,
          3
        ],
        [
          2,
          50,
          8,
          0
        ],
        [
          0,
          11,
          65,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8065760931078588,
      "eval_loss": 0.8426868915557861,
      "eval_precision": 0.8467707085637404,
      "eval_recall": 0.8058608058608059,
      "eval_runtime": 3.0783,
      "eval_samples_per_second": 88.686,
      "eval_steps_per_second": 0.975,
      "step": 90
    },
    {
      "epoch": 20.88888888888889,
      "eval_accuracy": 0.8498168498168498,
      "eval_confusion_matrix": [
        [
          63,
          4,
          0,
          5
        ],
        [
          13,
          40,
          7,
          0
        ],
        [
          0,
          12,
          64,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8477878057985963,
      "eval_loss": 0.7440442442893982,
      "eval_precision": 0.8476393351433065,
      "eval_recall": 0.8498168498168498,
      "eval_runtime": 2.9875,
      "eval_samples_per_second": 91.38,
      "eval_steps_per_second": 1.004,
      "step": 94
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.8608058608058609,
      "eval_confusion_matrix": [
        [
          66,
          1,
          1,
          4
        ],
        [
          13,
          36,
          11,
          0
        ],
        [
          0,
          5,
          71,
          0
        ],
        [
          3,
          0,
          0,
          62
        ]
      ],
      "eval_f1": 0.855194718990792,
      "eval_loss": 0.7338178753852844,
      "eval_precision": 0.8624631692093176,
      "eval_recall": 0.8608058608058609,
      "eval_runtime": 2.98,
      "eval_samples_per_second": 91.611,
      "eval_steps_per_second": 1.007,
      "step": 99
    },
    {
      "epoch": 22.88888888888889,
      "eval_accuracy": 0.8498168498168498,
      "eval_confusion_matrix": [
        [
          58,
          10,
          0,
          4
        ],
        [
          10,
          43,
          7,
          0
        ],
        [
          0,
          7,
          69,
          0
        ],
        [
          2,
          1,
          0,
          62
        ]
      ],
      "eval_f1": 0.8497737987724402,
      "eval_loss": 0.7231407761573792,
      "eval_precision": 0.8498638493954653,
      "eval_recall": 0.8498168498168498,
      "eval_runtime": 2.9272,
      "eval_samples_per_second": 93.262,
      "eval_steps_per_second": 1.025,
      "step": 103
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.8424908424908425,
      "eval_confusion_matrix": [
        [
          67,
          1,
          0,
          4
        ],
        [
          12,
          44,
          4,
          0
        ],
        [
          0,
          18,
          58,
          0
        ],
        [
          2,
          2,
          0,
          61
        ]
      ],
      "eval_f1": 0.8431607380967995,
      "eval_loss": 0.752363920211792,
      "eval_precision": 0.8507974885146101,
      "eval_recall": 0.8424908424908425,
      "eval_runtime": 3.0257,
      "eval_samples_per_second": 90.228,
      "eval_steps_per_second": 0.992,
      "step": 108
    },
    {
      "epoch": 24.88888888888889,
      "eval_accuracy": 0.8498168498168498,
      "eval_confusion_matrix": [
        [
          66,
          0,
          1,
          5
        ],
        [
          15,
          28,
          17,
          0
        ],
        [
          0,
          2,
          74,
          0
        ],
        [
          1,
          0,
          0,
          64
        ]
      ],
      "eval_f1": 0.8354928653436116,
      "eval_loss": 0.7849779725074768,
      "eval_precision": 0.8621667009790022,
      "eval_recall": 0.8498168498168498,
      "eval_runtime": 2.8819,
      "eval_samples_per_second": 94.73,
      "eval_steps_per_second": 1.041,
      "step": 112
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.8131868131868132,
      "eval_confusion_matrix": [
        [
          62,
          6,
          0,
          4
        ],
        [
          11,
          44,
          5,
          0
        ],
        [
          0,
          24,
          52,
          0
        ],
        [
          1,
          0,
          0,
          64
        ]
      ],
      "eval_f1": 0.8151598256855266,
      "eval_loss": 0.7896661162376404,
      "eval_precision": 0.8297062414709473,
      "eval_recall": 0.8131868131868132,
      "eval_runtime": 2.8953,
      "eval_samples_per_second": 94.291,
      "eval_steps_per_second": 1.036,
      "step": 117
    },
    {
      "epoch": 26.88888888888889,
      "eval_accuracy": 0.8791208791208791,
      "eval_confusion_matrix": [
        [
          66,
          1,
          1,
          4
        ],
        [
          13,
          40,
          7,
          0
        ],
        [
          1,
          6,
          69,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8754390108936493,
      "eval_loss": 0.7321063876152039,
      "eval_precision": 0.878386849630407,
      "eval_recall": 0.8791208791208791,
      "eval_runtime": 2.8941,
      "eval_samples_per_second": 94.329,
      "eval_steps_per_second": 1.037,
      "step": 121
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.8608058608058609,
      "eval_confusion_matrix": [
        [
          66,
          2,
          0,
          4
        ],
        [
          15,
          40,
          5,
          0
        ],
        [
          1,
          11,
          64,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8583938406059761,
      "eval_loss": 0.7691925168037415,
      "eval_precision": 0.8606552236676889,
      "eval_recall": 0.8608058608058609,
      "eval_runtime": 2.9043,
      "eval_samples_per_second": 93.997,
      "eval_steps_per_second": 1.033,
      "step": 126
    },
    {
      "epoch": 28.88888888888889,
      "eval_accuracy": 0.8461538461538461,
      "eval_confusion_matrix": [
        [
          60,
          8,
          0,
          4
        ],
        [
          10,
          41,
          9,
          0
        ],
        [
          0,
          11,
          65,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8453166248415355,
      "eval_loss": 0.764687716960907,
      "eval_precision": 0.8450656649414414,
      "eval_recall": 0.8461538461538461,
      "eval_runtime": 2.8898,
      "eval_samples_per_second": 94.47,
      "eval_steps_per_second": 1.038,
      "step": 130
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.8461538461538461,
      "eval_confusion_matrix": [
        [
          60,
          8,
          0,
          4
        ],
        [
          10,
          40,
          10,
          0
        ],
        [
          0,
          10,
          66,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8446254139808331,
      "eval_loss": 0.7896224856376648,
      "eval_precision": 0.8436830773519571,
      "eval_recall": 0.8461538461538461,
      "eval_runtime": 2.9051,
      "eval_samples_per_second": 93.974,
      "eval_steps_per_second": 1.033,
      "step": 135
    },
    {
      "epoch": 30.88888888888889,
      "eval_accuracy": 0.8571428571428571,
      "eval_confusion_matrix": [
        [
          62,
          6,
          0,
          4
        ],
        [
          12,
          41,
          7,
          0
        ],
        [
          0,
          10,
          66,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8556429580063329,
      "eval_loss": 0.7785082459449768,
      "eval_precision": 0.8550418750412481,
      "eval_recall": 0.8571428571428571,
      "eval_runtime": 2.9144,
      "eval_samples_per_second": 93.672,
      "eval_steps_per_second": 1.029,
      "step": 139
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.8571428571428571,
      "eval_confusion_matrix": [
        [
          62,
          6,
          0,
          4
        ],
        [
          13,
          41,
          6,
          0
        ],
        [
          0,
          10,
          66,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.855785572180052,
      "eval_loss": 0.7778924107551575,
      "eval_precision": 0.8555913753167756,
      "eval_recall": 0.8571428571428571,
      "eval_runtime": 2.8889,
      "eval_samples_per_second": 94.501,
      "eval_steps_per_second": 1.038,
      "step": 144
    },
    {
      "epoch": 32.888888888888886,
      "eval_accuracy": 0.8498168498168498,
      "eval_confusion_matrix": [
        [
          64,
          4,
          0,
          4
        ],
        [
          14,
          37,
          9,
          0
        ],
        [
          0,
          10,
          66,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8459222988470789,
      "eval_loss": 0.7852644324302673,
      "eval_precision": 0.8451216809509156,
      "eval_recall": 0.8498168498168498,
      "eval_runtime": 2.897,
      "eval_samples_per_second": 94.237,
      "eval_steps_per_second": 1.036,
      "step": 148
    },
    {
      "epoch": 34.0,
      "eval_accuracy": 0.8498168498168498,
      "eval_confusion_matrix": [
        [
          65,
          3,
          0,
          4
        ],
        [
          16,
          36,
          8,
          0
        ],
        [
          1,
          9,
          66,
          0
        ],
        [
          0,
          0,
          0,
          65
        ]
      ],
      "eval_f1": 0.8451242574057074,
      "eval_loss": 0.7895408868789673,
      "eval_precision": 0.8464792621738539,
      "eval_recall": 0.8498168498168498,
      "eval_runtime": 2.8905,
      "eval_samples_per_second": 94.447,
      "eval_steps_per_second": 1.038,
      "step": 153
    }
  ],
  "logging_steps": 500,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 45,
  "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": 8.42828363136e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}