{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 1,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 134.0,
      "learning_rate": 2.5e-05,
      "loss": 1.7222,
      "step": 1
    },
    {
      "epoch": 0.14285714285714285,
      "eval_loss": 2.0196499824523926,
      "eval_matthews_correlation": -0.0882903551594539,
      "eval_runtime": 2.3684,
      "eval_samples_per_second": 93.311,
      "eval_steps_per_second": 1.689,
      "step": 1
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 122.0,
      "learning_rate": 5e-05,
      "loss": 1.6075,
      "step": 2
    },
    {
      "epoch": 0.2857142857142857,
      "eval_loss": 1.6619428396224976,
      "eval_matthews_correlation": -0.1403852883926243,
      "eval_runtime": 2.3754,
      "eval_samples_per_second": 93.037,
      "eval_steps_per_second": 1.684,
      "step": 2
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 100.5,
      "learning_rate": 4.9264705882352944e-05,
      "loss": 1.3669,
      "step": 3
    },
    {
      "epoch": 0.42857142857142855,
      "eval_loss": 2.0540988445281982,
      "eval_matthews_correlation": -0.028683275619690942,
      "eval_runtime": 2.3537,
      "eval_samples_per_second": 93.895,
      "eval_steps_per_second": 1.699,
      "step": 3
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 215.0,
      "learning_rate": 4.8529411764705885e-05,
      "loss": 2.6067,
      "step": 4
    },
    {
      "epoch": 0.5714285714285714,
      "eval_loss": 2.177433967590332,
      "eval_matthews_correlation": -0.09348482549375706,
      "eval_runtime": 2.309,
      "eval_samples_per_second": 95.712,
      "eval_steps_per_second": 1.732,
      "step": 4
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 239.0,
      "learning_rate": 4.7794117647058826e-05,
      "loss": 2.4986,
      "step": 5
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 1.6899642944335938,
      "eval_matthews_correlation": 0.11327087190726348,
      "eval_runtime": 2.3522,
      "eval_samples_per_second": 93.953,
      "eval_steps_per_second": 1.701,
      "step": 5
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 230.0,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.8216,
      "step": 6
    },
    {
      "epoch": 0.8571428571428571,
      "eval_loss": 1.2177472114562988,
      "eval_matthews_correlation": 0.1806865287742912,
      "eval_runtime": 2.3529,
      "eval_samples_per_second": 93.928,
      "eval_steps_per_second": 1.7,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 65.5,
      "learning_rate": 4.632352941176471e-05,
      "loss": 0.9659,
      "step": 7
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.278491497039795,
      "eval_matthews_correlation": 0.23437433589326412,
      "eval_runtime": 2.3584,
      "eval_samples_per_second": 93.706,
      "eval_steps_per_second": 1.696,
      "step": 7
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 39.0,
      "learning_rate": 4.558823529411765e-05,
      "loss": 0.7348,
      "step": 8
    },
    {
      "epoch": 1.1428571428571428,
      "eval_loss": 1.3604048490524292,
      "eval_matthews_correlation": 0.22346441232318143,
      "eval_runtime": 2.391,
      "eval_samples_per_second": 92.43,
      "eval_steps_per_second": 1.673,
      "step": 8
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 179.0,
      "learning_rate": 4.485294117647059e-05,
      "loss": 0.9459,
      "step": 9
    },
    {
      "epoch": 1.2857142857142856,
      "eval_loss": 1.2725896835327148,
      "eval_matthews_correlation": 0.19367888050743545,
      "eval_runtime": 2.3108,
      "eval_samples_per_second": 95.638,
      "eval_steps_per_second": 1.731,
      "step": 9
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 185.0,
      "learning_rate": 4.411764705882353e-05,
      "loss": 1.0113,
      "step": 10
    },
    {
      "epoch": 1.4285714285714286,
      "eval_loss": 1.0940734148025513,
      "eval_matthews_correlation": 0.1758229359256884,
      "eval_runtime": 2.3561,
      "eval_samples_per_second": 93.8,
      "eval_steps_per_second": 1.698,
      "step": 10
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 121.5,
      "learning_rate": 4.3382352941176474e-05,
      "loss": 0.8862,
      "step": 11
    },
    {
      "epoch": 1.5714285714285714,
      "eval_loss": 1.0103245973587036,
      "eval_matthews_correlation": 0.18607215373306313,
      "eval_runtime": 2.3044,
      "eval_samples_per_second": 95.905,
      "eval_steps_per_second": 1.736,
      "step": 11
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 66.0,
      "learning_rate": 4.2647058823529415e-05,
      "loss": 0.6671,
      "step": 12
    },
    {
      "epoch": 1.7142857142857144,
      "eval_loss": 1.0150161981582642,
      "eval_matthews_correlation": 0.16295492928043517,
      "eval_runtime": 2.354,
      "eval_samples_per_second": 93.883,
      "eval_steps_per_second": 1.699,
      "step": 12
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 76.5,
      "learning_rate": 4.1911764705882356e-05,
      "loss": 0.6993,
      "step": 13
    },
    {
      "epoch": 1.8571428571428572,
      "eval_loss": 0.9942739009857178,
      "eval_matthews_correlation": 0.190143522496192,
      "eval_runtime": 2.4001,
      "eval_samples_per_second": 92.079,
      "eval_steps_per_second": 1.667,
      "step": 13
    },
    {
      "epoch": 2.0,
      "grad_norm": 78.5,
      "learning_rate": 4.11764705882353e-05,
      "loss": 0.5687,
      "step": 14
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.957594633102417,
      "eval_matthews_correlation": 0.23288000159518374,
      "eval_runtime": 2.3857,
      "eval_samples_per_second": 92.635,
      "eval_steps_per_second": 1.677,
      "step": 14
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 53.75,
      "learning_rate": 4.044117647058824e-05,
      "loss": 0.5374,
      "step": 15
    },
    {
      "epoch": 2.142857142857143,
      "eval_loss": 0.9628612399101257,
      "eval_matthews_correlation": 0.23529060477256988,
      "eval_runtime": 2.3516,
      "eval_samples_per_second": 93.978,
      "eval_steps_per_second": 1.701,
      "step": 15
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 61.5,
      "learning_rate": 3.970588235294117e-05,
      "loss": 0.4614,
      "step": 16
    },
    {
      "epoch": 2.2857142857142856,
      "eval_loss": 0.9808283448219299,
      "eval_matthews_correlation": 0.2299970498991641,
      "eval_runtime": 2.3687,
      "eval_samples_per_second": 93.299,
      "eval_steps_per_second": 1.689,
      "step": 16
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 64.0,
      "learning_rate": 3.897058823529412e-05,
      "loss": 0.2969,
      "step": 17
    },
    {
      "epoch": 2.4285714285714284,
      "eval_loss": 0.973484992980957,
      "eval_matthews_correlation": 0.22569029439717253,
      "eval_runtime": 2.3678,
      "eval_samples_per_second": 93.334,
      "eval_steps_per_second": 1.689,
      "step": 17
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 53.75,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 0.3818,
      "step": 18
    },
    {
      "epoch": 2.571428571428571,
      "eval_loss": 0.9494228363037109,
      "eval_matthews_correlation": 0.26534632115143664,
      "eval_runtime": 2.3924,
      "eval_samples_per_second": 92.376,
      "eval_steps_per_second": 1.672,
      "step": 18
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 51.25,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.423,
      "step": 19
    },
    {
      "epoch": 2.7142857142857144,
      "eval_loss": 0.9362727999687195,
      "eval_matthews_correlation": 0.30245501970006394,
      "eval_runtime": 2.3067,
      "eval_samples_per_second": 95.806,
      "eval_steps_per_second": 1.734,
      "step": 19
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 36.75,
      "learning_rate": 3.6764705882352945e-05,
      "loss": 0.3591,
      "step": 20
    },
    {
      "epoch": 2.857142857142857,
      "eval_loss": 0.9422338604927063,
      "eval_matthews_correlation": 0.3196729082856838,
      "eval_runtime": 2.3608,
      "eval_samples_per_second": 93.613,
      "eval_steps_per_second": 1.694,
      "step": 20
    },
    {
      "epoch": 3.0,
      "grad_norm": 55.0,
      "learning_rate": 3.6029411764705886e-05,
      "loss": 0.3845,
      "step": 21
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.9473302364349365,
      "eval_matthews_correlation": 0.3308386147154527,
      "eval_runtime": 2.4007,
      "eval_samples_per_second": 92.056,
      "eval_steps_per_second": 1.666,
      "step": 21
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 5.71875,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.2146,
      "step": 22
    },
    {
      "epoch": 3.142857142857143,
      "eval_loss": 0.9474514126777649,
      "eval_matthews_correlation": 0.31898693930331706,
      "eval_runtime": 2.368,
      "eval_samples_per_second": 93.328,
      "eval_steps_per_second": 1.689,
      "step": 22
    },
    {
      "epoch": 3.2857142857142856,
      "grad_norm": 21.75,
      "learning_rate": 3.455882352941177e-05,
      "loss": 0.3002,
      "step": 23
    },
    {
      "epoch": 3.2857142857142856,
      "eval_loss": 0.9657209515571594,
      "eval_matthews_correlation": 0.2849062574112851,
      "eval_runtime": 2.3966,
      "eval_samples_per_second": 92.214,
      "eval_steps_per_second": 1.669,
      "step": 23
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 22.0,
      "learning_rate": 3.382352941176471e-05,
      "loss": 0.221,
      "step": 24
    },
    {
      "epoch": 3.4285714285714284,
      "eval_loss": 1.020974040031433,
      "eval_matthews_correlation": 0.24865002165245412,
      "eval_runtime": 2.3934,
      "eval_samples_per_second": 92.339,
      "eval_steps_per_second": 1.671,
      "step": 24
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 30.125,
      "learning_rate": 3.308823529411765e-05,
      "loss": 0.1452,
      "step": 25
    },
    {
      "epoch": 3.571428571428571,
      "eval_loss": 1.0698134899139404,
      "eval_matthews_correlation": 0.20606044506573787,
      "eval_runtime": 2.3098,
      "eval_samples_per_second": 95.678,
      "eval_steps_per_second": 1.732,
      "step": 25
    },
    {
      "epoch": 3.7142857142857144,
      "grad_norm": 74.0,
      "learning_rate": 3.235294117647059e-05,
      "loss": 0.3834,
      "step": 26
    },
    {
      "epoch": 3.7142857142857144,
      "eval_loss": 1.0729013681411743,
      "eval_matthews_correlation": 0.21311359700013865,
      "eval_runtime": 2.363,
      "eval_samples_per_second": 93.527,
      "eval_steps_per_second": 1.693,
      "step": 26
    },
    {
      "epoch": 3.857142857142857,
      "grad_norm": 92.5,
      "learning_rate": 3.161764705882353e-05,
      "loss": 0.3992,
      "step": 27
    },
    {
      "epoch": 3.857142857142857,
      "eval_loss": 1.044179916381836,
      "eval_matthews_correlation": 0.2415008164529655,
      "eval_runtime": 2.3563,
      "eval_samples_per_second": 93.79,
      "eval_steps_per_second": 1.698,
      "step": 27
    },
    {
      "epoch": 4.0,
      "grad_norm": 38.25,
      "learning_rate": 3.0882352941176475e-05,
      "loss": 0.1927,
      "step": 28
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0118021965026855,
      "eval_matthews_correlation": 0.2616725300472798,
      "eval_runtime": 2.3537,
      "eval_samples_per_second": 93.894,
      "eval_steps_per_second": 1.699,
      "step": 28
    },
    {
      "epoch": 4.142857142857143,
      "grad_norm": 38.0,
      "learning_rate": 3.0147058823529413e-05,
      "loss": 0.1826,
      "step": 29
    },
    {
      "epoch": 4.142857142857143,
      "eval_loss": 1.0196139812469482,
      "eval_matthews_correlation": 0.2882423971908362,
      "eval_runtime": 2.3607,
      "eval_samples_per_second": 93.616,
      "eval_steps_per_second": 1.694,
      "step": 29
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 29.0,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 0.1725,
      "step": 30
    },
    {
      "epoch": 4.285714285714286,
      "eval_loss": 1.0478262901306152,
      "eval_matthews_correlation": 0.26838255978295894,
      "eval_runtime": 2.3532,
      "eval_samples_per_second": 93.916,
      "eval_steps_per_second": 1.7,
      "step": 30
    },
    {
      "epoch": 4.428571428571429,
      "grad_norm": 36.5,
      "learning_rate": 2.8676470588235295e-05,
      "loss": 0.1338,
      "step": 31
    },
    {
      "epoch": 4.428571428571429,
      "eval_loss": 1.048422932624817,
      "eval_matthews_correlation": 0.28586872588000406,
      "eval_runtime": 2.3545,
      "eval_samples_per_second": 93.863,
      "eval_steps_per_second": 1.699,
      "step": 31
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 60.75,
      "learning_rate": 2.7941176470588236e-05,
      "loss": 0.2333,
      "step": 32
    },
    {
      "epoch": 4.571428571428571,
      "eval_loss": 1.036675214767456,
      "eval_matthews_correlation": 0.31094869799833763,
      "eval_runtime": 2.4915,
      "eval_samples_per_second": 88.702,
      "eval_steps_per_second": 1.605,
      "step": 32
    },
    {
      "epoch": 4.714285714285714,
      "grad_norm": 24.5,
      "learning_rate": 2.7205882352941174e-05,
      "loss": 0.1153,
      "step": 33
    },
    {
      "epoch": 4.714285714285714,
      "eval_loss": 1.0192501544952393,
      "eval_matthews_correlation": 0.296589480247221,
      "eval_runtime": 2.2597,
      "eval_samples_per_second": 97.802,
      "eval_steps_per_second": 1.77,
      "step": 33
    },
    {
      "epoch": 4.857142857142857,
      "grad_norm": 12.625,
      "learning_rate": 2.647058823529412e-05,
      "loss": 0.1415,
      "step": 34
    },
    {
      "epoch": 4.857142857142857,
      "eval_loss": 1.0157463550567627,
      "eval_matthews_correlation": 0.270246784845325,
      "eval_runtime": 2.3043,
      "eval_samples_per_second": 95.906,
      "eval_steps_per_second": 1.736,
      "step": 34
    },
    {
      "epoch": 5.0,
      "grad_norm": 12.625,
      "learning_rate": 2.5735294117647057e-05,
      "loss": 0.1722,
      "step": 35
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.0183305740356445,
      "eval_matthews_correlation": 0.2806455054870596,
      "eval_runtime": 2.3,
      "eval_samples_per_second": 96.089,
      "eval_steps_per_second": 1.739,
      "step": 35
    },
    {
      "epoch": 5.142857142857143,
      "grad_norm": 24.125,
      "learning_rate": 2.5e-05,
      "loss": 0.1116,
      "step": 36
    },
    {
      "epoch": 5.142857142857143,
      "eval_loss": 1.0078963041305542,
      "eval_matthews_correlation": 0.2919122663402188,
      "eval_runtime": 2.299,
      "eval_samples_per_second": 96.128,
      "eval_steps_per_second": 1.74,
      "step": 36
    },
    {
      "epoch": 5.285714285714286,
      "grad_norm": 17.875,
      "learning_rate": 2.4264705882352942e-05,
      "loss": 0.0814,
      "step": 37
    },
    {
      "epoch": 5.285714285714286,
      "eval_loss": 0.9962896704673767,
      "eval_matthews_correlation": 0.2961504855156075,
      "eval_runtime": 2.2968,
      "eval_samples_per_second": 96.219,
      "eval_steps_per_second": 1.742,
      "step": 37
    },
    {
      "epoch": 5.428571428571429,
      "grad_norm": 20.75,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 0.1022,
      "step": 38
    },
    {
      "epoch": 5.428571428571429,
      "eval_loss": 0.9801982641220093,
      "eval_matthews_correlation": 0.2974487800233713,
      "eval_runtime": 2.2484,
      "eval_samples_per_second": 98.292,
      "eval_steps_per_second": 1.779,
      "step": 38
    },
    {
      "epoch": 5.571428571428571,
      "grad_norm": 22.125,
      "learning_rate": 2.2794117647058825e-05,
      "loss": 0.0924,
      "step": 39
    },
    {
      "epoch": 5.571428571428571,
      "eval_loss": 0.9746297001838684,
      "eval_matthews_correlation": 0.324706174020757,
      "eval_runtime": 2.347,
      "eval_samples_per_second": 94.162,
      "eval_steps_per_second": 1.704,
      "step": 39
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 7.875,
      "learning_rate": 2.2058823529411766e-05,
      "loss": 0.0598,
      "step": 40
    },
    {
      "epoch": 5.714285714285714,
      "eval_loss": 0.9695372581481934,
      "eval_matthews_correlation": 0.3396355284414159,
      "eval_runtime": 2.3472,
      "eval_samples_per_second": 94.154,
      "eval_steps_per_second": 1.704,
      "step": 40
    },
    {
      "epoch": 5.857142857142857,
      "grad_norm": 3.640625,
      "learning_rate": 2.1323529411764707e-05,
      "loss": 0.0979,
      "step": 41
    },
    {
      "epoch": 5.857142857142857,
      "eval_loss": 0.9763937592506409,
      "eval_matthews_correlation": 0.35072853143256777,
      "eval_runtime": 2.3485,
      "eval_samples_per_second": 94.104,
      "eval_steps_per_second": 1.703,
      "step": 41
    },
    {
      "epoch": 6.0,
      "grad_norm": 31.75,
      "learning_rate": 2.058823529411765e-05,
      "loss": 0.0845,
      "step": 42
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.9772699475288391,
      "eval_matthews_correlation": 0.36177927116990083,
      "eval_runtime": 2.3468,
      "eval_samples_per_second": 94.172,
      "eval_steps_per_second": 1.704,
      "step": 42
    },
    {
      "epoch": 6.142857142857143,
      "grad_norm": 9.5625,
      "learning_rate": 1.9852941176470586e-05,
      "loss": 0.0577,
      "step": 43
    },
    {
      "epoch": 6.142857142857143,
      "eval_loss": 0.9829764366149902,
      "eval_matthews_correlation": 0.3530389654491601,
      "eval_runtime": 2.3472,
      "eval_samples_per_second": 94.155,
      "eval_steps_per_second": 1.704,
      "step": 43
    },
    {
      "epoch": 6.285714285714286,
      "grad_norm": 2.484375,
      "learning_rate": 1.9117647058823528e-05,
      "loss": 0.0489,
      "step": 44
    },
    {
      "epoch": 6.285714285714286,
      "eval_loss": 1.0145213603973389,
      "eval_matthews_correlation": 0.3218521640278974,
      "eval_runtime": 2.3461,
      "eval_samples_per_second": 94.199,
      "eval_steps_per_second": 1.705,
      "step": 44
    },
    {
      "epoch": 6.428571428571429,
      "grad_norm": 7.0625,
      "learning_rate": 1.8382352941176472e-05,
      "loss": 0.0472,
      "step": 45
    },
    {
      "epoch": 6.428571428571429,
      "eval_loss": 1.050150990486145,
      "eval_matthews_correlation": 0.3055129963090533,
      "eval_runtime": 2.3458,
      "eval_samples_per_second": 94.212,
      "eval_steps_per_second": 1.705,
      "step": 45
    },
    {
      "epoch": 6.571428571428571,
      "grad_norm": 4.96875,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.0514,
      "step": 46
    },
    {
      "epoch": 6.571428571428571,
      "eval_loss": 1.0775320529937744,
      "eval_matthews_correlation": 0.3151930392831226,
      "eval_runtime": 2.3482,
      "eval_samples_per_second": 94.115,
      "eval_steps_per_second": 1.703,
      "step": 46
    },
    {
      "epoch": 6.714285714285714,
      "grad_norm": 9.625,
      "learning_rate": 1.6911764705882355e-05,
      "loss": 0.0946,
      "step": 47
    },
    {
      "epoch": 6.714285714285714,
      "eval_loss": 1.0962245464324951,
      "eval_matthews_correlation": 0.3198378162607766,
      "eval_runtime": 2.3462,
      "eval_samples_per_second": 94.196,
      "eval_steps_per_second": 1.705,
      "step": 47
    },
    {
      "epoch": 6.857142857142857,
      "grad_norm": 11.0,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.064,
      "step": 48
    },
    {
      "epoch": 6.857142857142857,
      "eval_loss": 1.1000041961669922,
      "eval_matthews_correlation": 0.33299219513436445,
      "eval_runtime": 2.3477,
      "eval_samples_per_second": 94.133,
      "eval_steps_per_second": 1.704,
      "step": 48
    },
    {
      "epoch": 7.0,
      "grad_norm": 4.90625,
      "learning_rate": 1.5441176470588237e-05,
      "loss": 0.0377,
      "step": 49
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.0983600616455078,
      "eval_matthews_correlation": 0.33849333487222494,
      "eval_runtime": 2.2962,
      "eval_samples_per_second": 96.248,
      "eval_steps_per_second": 1.742,
      "step": 49
    },
    {
      "epoch": 7.142857142857143,
      "grad_norm": 1.6640625,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 0.0316,
      "step": 50
    },
    {
      "epoch": 7.142857142857143,
      "eval_loss": 1.0886433124542236,
      "eval_matthews_correlation": 0.33849333487222494,
      "eval_runtime": 2.3464,
      "eval_samples_per_second": 94.187,
      "eval_steps_per_second": 1.705,
      "step": 50
    },
    {
      "epoch": 7.285714285714286,
      "grad_norm": 9.625,
      "learning_rate": 1.3970588235294118e-05,
      "loss": 0.0442,
      "step": 51
    },
    {
      "epoch": 7.285714285714286,
      "eval_loss": 1.0777003765106201,
      "eval_matthews_correlation": 0.34693548973921595,
      "eval_runtime": 2.296,
      "eval_samples_per_second": 96.256,
      "eval_steps_per_second": 1.742,
      "step": 51
    },
    {
      "epoch": 7.428571428571429,
      "grad_norm": 6.40625,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.0266,
      "step": 52
    },
    {
      "epoch": 7.428571428571429,
      "eval_loss": 1.0702271461486816,
      "eval_matthews_correlation": 0.34693548973921595,
      "eval_runtime": 2.3463,
      "eval_samples_per_second": 94.189,
      "eval_steps_per_second": 1.705,
      "step": 52
    },
    {
      "epoch": 7.571428571428571,
      "grad_norm": 2.234375,
      "learning_rate": 1.25e-05,
      "loss": 0.0373,
      "step": 53
    },
    {
      "epoch": 7.571428571428571,
      "eval_loss": 1.0644919872283936,
      "eval_matthews_correlation": 0.34693548973921595,
      "eval_runtime": 2.2974,
      "eval_samples_per_second": 96.197,
      "eval_steps_per_second": 1.741,
      "step": 53
    },
    {
      "epoch": 7.714285714285714,
      "grad_norm": 2.671875,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.0312,
      "step": 54
    },
    {
      "epoch": 7.714285714285714,
      "eval_loss": 1.0710008144378662,
      "eval_matthews_correlation": 0.33849333487222494,
      "eval_runtime": 2.2965,
      "eval_samples_per_second": 96.232,
      "eval_steps_per_second": 1.742,
      "step": 54
    },
    {
      "epoch": 7.857142857142857,
      "grad_norm": 1.5703125,
      "learning_rate": 1.1029411764705883e-05,
      "loss": 0.0182,
      "step": 55
    },
    {
      "epoch": 7.857142857142857,
      "eval_loss": 1.0716383457183838,
      "eval_matthews_correlation": 0.35546338006875017,
      "eval_runtime": 2.2985,
      "eval_samples_per_second": 96.15,
      "eval_steps_per_second": 1.74,
      "step": 55
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.15625,
      "learning_rate": 1.0294117647058824e-05,
      "loss": 0.0307,
      "step": 56
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.0811822414398193,
      "eval_matthews_correlation": 0.3606464526835643,
      "eval_runtime": 2.3471,
      "eval_samples_per_second": 94.159,
      "eval_steps_per_second": 1.704,
      "step": 56
    },
    {
      "epoch": 8.142857142857142,
      "grad_norm": 1.1796875,
      "learning_rate": 9.558823529411764e-06,
      "loss": 0.0141,
      "step": 57
    },
    {
      "epoch": 8.142857142857142,
      "eval_loss": 1.089095115661621,
      "eval_matthews_correlation": 0.3606464526835643,
      "eval_runtime": 2.295,
      "eval_samples_per_second": 96.295,
      "eval_steps_per_second": 1.743,
      "step": 57
    },
    {
      "epoch": 8.285714285714286,
      "grad_norm": 1.515625,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.019,
      "step": 58
    },
    {
      "epoch": 8.285714285714286,
      "eval_loss": 1.1000548601150513,
      "eval_matthews_correlation": 0.3634024265899628,
      "eval_runtime": 2.3565,
      "eval_samples_per_second": 93.784,
      "eval_steps_per_second": 1.697,
      "step": 58
    },
    {
      "epoch": 8.428571428571429,
      "grad_norm": 1.21875,
      "learning_rate": 8.088235294117648e-06,
      "loss": 0.0137,
      "step": 59
    },
    {
      "epoch": 8.428571428571429,
      "eval_loss": 1.1046100854873657,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.2959,
      "eval_samples_per_second": 96.257,
      "eval_steps_per_second": 1.742,
      "step": 59
    },
    {
      "epoch": 8.571428571428571,
      "grad_norm": 2.265625,
      "learning_rate": 7.3529411764705884e-06,
      "loss": 0.0192,
      "step": 60
    },
    {
      "epoch": 8.571428571428571,
      "eval_loss": 1.1252989768981934,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.3452,
      "eval_samples_per_second": 94.235,
      "eval_steps_per_second": 1.706,
      "step": 60
    },
    {
      "epoch": 8.714285714285714,
      "grad_norm": 3.953125,
      "learning_rate": 6.61764705882353e-06,
      "loss": 0.0266,
      "step": 61
    },
    {
      "epoch": 8.714285714285714,
      "eval_loss": 1.1373261213302612,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.3438,
      "eval_samples_per_second": 94.293,
      "eval_steps_per_second": 1.707,
      "step": 61
    },
    {
      "epoch": 8.857142857142858,
      "grad_norm": 2.921875,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.0236,
      "step": 62
    },
    {
      "epoch": 8.857142857142858,
      "eval_loss": 1.1461013555526733,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.3042,
      "eval_samples_per_second": 95.911,
      "eval_steps_per_second": 1.736,
      "step": 62
    },
    {
      "epoch": 9.0,
      "grad_norm": 2.703125,
      "learning_rate": 5.147058823529412e-06,
      "loss": 0.0096,
      "step": 63
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.1585053205490112,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.3511,
      "eval_samples_per_second": 93.997,
      "eval_steps_per_second": 1.701,
      "step": 63
    },
    {
      "epoch": 9.142857142857142,
      "grad_norm": 4.9375,
      "learning_rate": 4.411764705882353e-06,
      "loss": 0.0266,
      "step": 64
    },
    {
      "epoch": 9.142857142857142,
      "eval_loss": 1.1639437675476074,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.3753,
      "eval_samples_per_second": 93.042,
      "eval_steps_per_second": 1.684,
      "step": 64
    },
    {
      "epoch": 9.285714285714286,
      "grad_norm": 1.4140625,
      "learning_rate": 3.6764705882352942e-06,
      "loss": 0.0081,
      "step": 65
    },
    {
      "epoch": 9.285714285714286,
      "eval_loss": 1.166314721107483,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.5404,
      "eval_samples_per_second": 86.993,
      "eval_steps_per_second": 1.575,
      "step": 65
    },
    {
      "epoch": 9.428571428571429,
      "grad_norm": 1.5390625,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 0.0142,
      "step": 66
    },
    {
      "epoch": 9.428571428571429,
      "eval_loss": 1.1685423851013184,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.3958,
      "eval_samples_per_second": 92.245,
      "eval_steps_per_second": 1.67,
      "step": 66
    },
    {
      "epoch": 9.571428571428571,
      "grad_norm": 0.455078125,
      "learning_rate": 2.2058823529411767e-06,
      "loss": 0.0064,
      "step": 67
    },
    {
      "epoch": 9.571428571428571,
      "eval_loss": 1.17280912399292,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.4299,
      "eval_samples_per_second": 90.951,
      "eval_steps_per_second": 1.646,
      "step": 67
    },
    {
      "epoch": 9.714285714285714,
      "grad_norm": 1.90625,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 0.0157,
      "step": 68
    },
    {
      "epoch": 9.714285714285714,
      "eval_loss": 1.1688233613967896,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.3577,
      "eval_samples_per_second": 93.734,
      "eval_steps_per_second": 1.697,
      "step": 68
    },
    {
      "epoch": 9.857142857142858,
      "grad_norm": 1.0703125,
      "learning_rate": 7.352941176470589e-07,
      "loss": 0.0102,
      "step": 69
    },
    {
      "epoch": 9.857142857142858,
      "eval_loss": 1.1763280630111694,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.352,
      "eval_samples_per_second": 93.963,
      "eval_steps_per_second": 1.701,
      "step": 69
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.98828125,
      "learning_rate": 0.0,
      "loss": 0.0042,
      "step": 70
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.1750054359436035,
      "eval_matthews_correlation": 0.3716837172819431,
      "eval_runtime": 2.3562,
      "eval_samples_per_second": 93.794,
      "eval_steps_per_second": 1.698,
      "step": 70
    },
    {
      "epoch": 10.0,
      "step": 70,
      "total_flos": 3.820098642614682e+16,
      "train_loss": 0.36309749615777814,
      "train_runtime": 435.4776,
      "train_samples_per_second": 20.277,
      "train_steps_per_second": 0.161
    }
  ],
  "logging_steps": 1,
  "max_steps": 70,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.820098642614682e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}