{
  "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": 1.1953125,
      "learning_rate": 2.5e-05,
      "loss": 0.6913,
      "step": 1
    },
    {
      "epoch": 0.14285714285714285,
      "eval_loss": 0.675564169883728,
      "eval_matthews_correlation": 0.039478056766886455,
      "eval_runtime": 1.9051,
      "eval_samples_per_second": 116.006,
      "eval_steps_per_second": 2.1,
      "step": 1
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 3.6875,
      "learning_rate": 5e-05,
      "loss": 0.7041,
      "step": 2
    },
    {
      "epoch": 0.2857142857142857,
      "eval_loss": 0.6751559972763062,
      "eval_matthews_correlation": 0.018836815775184944,
      "eval_runtime": 1.9021,
      "eval_samples_per_second": 116.189,
      "eval_steps_per_second": 2.103,
      "step": 2
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 3.25,
      "learning_rate": 4.9264705882352944e-05,
      "loss": 0.6404,
      "step": 3
    },
    {
      "epoch": 0.42857142857142855,
      "eval_loss": 0.672702431678772,
      "eval_matthews_correlation": 0.02597419770482644,
      "eval_runtime": 1.8999,
      "eval_samples_per_second": 116.32,
      "eval_steps_per_second": 2.105,
      "step": 3
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.84375,
      "learning_rate": 4.8529411764705885e-05,
      "loss": 0.7011,
      "step": 4
    },
    {
      "epoch": 0.5714285714285714,
      "eval_loss": 0.6732006669044495,
      "eval_matthews_correlation": 0.011067888344390708,
      "eval_runtime": 1.9011,
      "eval_samples_per_second": 116.248,
      "eval_steps_per_second": 2.104,
      "step": 4
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 2.8125,
      "learning_rate": 4.7794117647058826e-05,
      "loss": 0.7219,
      "step": 5
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 0.6730763912200928,
      "eval_matthews_correlation": -0.0029297843623512934,
      "eval_runtime": 1.901,
      "eval_samples_per_second": 116.252,
      "eval_steps_per_second": 2.104,
      "step": 5
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 6.1875,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.7232,
      "step": 6
    },
    {
      "epoch": 0.8571428571428571,
      "eval_loss": 0.673651397228241,
      "eval_matthews_correlation": 0.011067888344390708,
      "eval_runtime": 1.9003,
      "eval_samples_per_second": 116.297,
      "eval_steps_per_second": 2.105,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.53125,
      "learning_rate": 4.632352941176471e-05,
      "loss": 0.7109,
      "step": 7
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6717435121536255,
      "eval_matthews_correlation": 0.011067888344390708,
      "eval_runtime": 1.9013,
      "eval_samples_per_second": 116.234,
      "eval_steps_per_second": 2.104,
      "step": 7
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 6.28125,
      "learning_rate": 4.558823529411765e-05,
      "loss": 0.6897,
      "step": 8
    },
    {
      "epoch": 1.1428571428571428,
      "eval_loss": 0.6718308329582214,
      "eval_matthews_correlation": 0.011067888344390708,
      "eval_runtime": 1.9012,
      "eval_samples_per_second": 116.241,
      "eval_steps_per_second": 2.104,
      "step": 8
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 3.09375,
      "learning_rate": 4.485294117647059e-05,
      "loss": 0.6994,
      "step": 9
    },
    {
      "epoch": 1.2857142857142856,
      "eval_loss": 0.672776460647583,
      "eval_matthews_correlation": 0.011067888344390708,
      "eval_runtime": 1.9005,
      "eval_samples_per_second": 116.288,
      "eval_steps_per_second": 2.105,
      "step": 9
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 8.5,
      "learning_rate": 4.411764705882353e-05,
      "loss": 0.6598,
      "step": 10
    },
    {
      "epoch": 1.4285714285714286,
      "eval_loss": 0.6726637482643127,
      "eval_matthews_correlation": -0.0029297843623512934,
      "eval_runtime": 1.9,
      "eval_samples_per_second": 116.317,
      "eval_steps_per_second": 2.105,
      "step": 10
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 1.203125,
      "learning_rate": 4.3382352941176474e-05,
      "loss": 0.6885,
      "step": 11
    },
    {
      "epoch": 1.5714285714285714,
      "eval_loss": 0.675143837928772,
      "eval_matthews_correlation": -0.028683275619690942,
      "eval_runtime": 1.8994,
      "eval_samples_per_second": 116.351,
      "eval_steps_per_second": 2.106,
      "step": 11
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 4.59375,
      "learning_rate": 4.2647058823529415e-05,
      "loss": 0.708,
      "step": 12
    },
    {
      "epoch": 1.7142857142857144,
      "eval_loss": 0.6781198978424072,
      "eval_matthews_correlation": -0.028683275619690942,
      "eval_runtime": 1.9007,
      "eval_samples_per_second": 116.275,
      "eval_steps_per_second": 2.105,
      "step": 12
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 2.640625,
      "learning_rate": 4.1911764705882356e-05,
      "loss": 0.6756,
      "step": 13
    },
    {
      "epoch": 1.8571428571428572,
      "eval_loss": 0.6830955147743225,
      "eval_matthews_correlation": 0.03840151481124831,
      "eval_runtime": 1.9014,
      "eval_samples_per_second": 116.231,
      "eval_steps_per_second": 2.104,
      "step": 13
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1015625,
      "learning_rate": 4.11764705882353e-05,
      "loss": 0.6827,
      "step": 14
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6893890500068665,
      "eval_matthews_correlation": 0.02099447073916433,
      "eval_runtime": 1.901,
      "eval_samples_per_second": 116.255,
      "eval_steps_per_second": 2.104,
      "step": 14
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 2.015625,
      "learning_rate": 4.044117647058824e-05,
      "loss": 0.7033,
      "step": 15
    },
    {
      "epoch": 2.142857142857143,
      "eval_loss": 0.6950197815895081,
      "eval_matthews_correlation": -0.000624626584919963,
      "eval_runtime": 1.8984,
      "eval_samples_per_second": 116.414,
      "eval_steps_per_second": 2.107,
      "step": 15
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 1.4921875,
      "learning_rate": 3.970588235294117e-05,
      "loss": 0.7001,
      "step": 16
    },
    {
      "epoch": 2.2857142857142856,
      "eval_loss": 0.6963896155357361,
      "eval_matthews_correlation": -0.000624626584919963,
      "eval_runtime": 1.8999,
      "eval_samples_per_second": 116.323,
      "eval_steps_per_second": 2.105,
      "step": 16
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 5.15625,
      "learning_rate": 3.897058823529412e-05,
      "loss": 0.6424,
      "step": 17
    },
    {
      "epoch": 2.4285714285714284,
      "eval_loss": 0.6982244849205017,
      "eval_matthews_correlation": -0.000624626584919963,
      "eval_runtime": 1.8994,
      "eval_samples_per_second": 116.352,
      "eval_steps_per_second": 2.106,
      "step": 17
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 3.78125,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 0.6598,
      "step": 18
    },
    {
      "epoch": 2.571428571428571,
      "eval_loss": 0.701633632183075,
      "eval_matthews_correlation": -0.010960055896189614,
      "eval_runtime": 1.8505,
      "eval_samples_per_second": 119.425,
      "eval_steps_per_second": 2.162,
      "step": 18
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 4.375,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.7053,
      "step": 19
    },
    {
      "epoch": 2.7142857142857144,
      "eval_loss": 0.7011630535125732,
      "eval_matthews_correlation": -0.010960055896189614,
      "eval_runtime": 1.8994,
      "eval_samples_per_second": 116.35,
      "eval_steps_per_second": 2.106,
      "step": 19
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 1.296875,
      "learning_rate": 3.6764705882352945e-05,
      "loss": 0.6959,
      "step": 20
    },
    {
      "epoch": 2.857142857142857,
      "eval_loss": 0.695502519607544,
      "eval_matthews_correlation": -0.000624626584919963,
      "eval_runtime": 1.8499,
      "eval_samples_per_second": 119.465,
      "eval_steps_per_second": 2.162,
      "step": 20
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.515625,
      "learning_rate": 3.6029411764705886e-05,
      "loss": 0.7014,
      "step": 21
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6924899816513062,
      "eval_matthews_correlation": -0.000624626584919963,
      "eval_runtime": 1.9,
      "eval_samples_per_second": 116.318,
      "eval_steps_per_second": 2.105,
      "step": 21
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 6.34375,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.7011,
      "step": 22
    },
    {
      "epoch": 3.142857142857143,
      "eval_loss": 0.6877518892288208,
      "eval_matthews_correlation": 0.01001773397191543,
      "eval_runtime": 1.8999,
      "eval_samples_per_second": 116.325,
      "eval_steps_per_second": 2.105,
      "step": 22
    },
    {
      "epoch": 3.2857142857142856,
      "grad_norm": 2.984375,
      "learning_rate": 3.455882352941177e-05,
      "loss": 0.6765,
      "step": 23
    },
    {
      "epoch": 3.2857142857142856,
      "eval_loss": 0.682935357093811,
      "eval_matthews_correlation": 0.007873691885759546,
      "eval_runtime": 1.9014,
      "eval_samples_per_second": 116.233,
      "eval_steps_per_second": 2.104,
      "step": 23
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 3.171875,
      "learning_rate": 3.382352941176471e-05,
      "loss": 0.7059,
      "step": 24
    },
    {
      "epoch": 3.4285714285714284,
      "eval_loss": 0.6817290186882019,
      "eval_matthews_correlation": 0.0005753543746001685,
      "eval_runtime": 1.9018,
      "eval_samples_per_second": 116.208,
      "eval_steps_per_second": 2.103,
      "step": 24
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 1.1953125,
      "learning_rate": 3.308823529411765e-05,
      "loss": 0.6734,
      "step": 25
    },
    {
      "epoch": 3.571428571428571,
      "eval_loss": 0.6798145174980164,
      "eval_matthews_correlation": 0.012938076628071615,
      "eval_runtime": 1.9008,
      "eval_samples_per_second": 116.265,
      "eval_steps_per_second": 2.104,
      "step": 25
    },
    {
      "epoch": 3.7142857142857144,
      "grad_norm": 1.3203125,
      "learning_rate": 3.235294117647059e-05,
      "loss": 0.6776,
      "step": 26
    },
    {
      "epoch": 3.7142857142857144,
      "eval_loss": 0.6806607246398926,
      "eval_matthews_correlation": 0.012938076628071615,
      "eval_runtime": 1.9014,
      "eval_samples_per_second": 116.231,
      "eval_steps_per_second": 2.104,
      "step": 26
    },
    {
      "epoch": 3.857142857142857,
      "grad_norm": 7.5,
      "learning_rate": 3.161764705882353e-05,
      "loss": 0.6379,
      "step": 27
    },
    {
      "epoch": 3.857142857142857,
      "eval_loss": 0.6790522933006287,
      "eval_matthews_correlation": 0.012938076628071615,
      "eval_runtime": 1.9049,
      "eval_samples_per_second": 116.015,
      "eval_steps_per_second": 2.1,
      "step": 27
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.1484375,
      "learning_rate": 3.0882352941176475e-05,
      "loss": 0.6882,
      "step": 28
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6815522313117981,
      "eval_matthews_correlation": 0.012938076628071615,
      "eval_runtime": 1.8987,
      "eval_samples_per_second": 116.395,
      "eval_steps_per_second": 2.107,
      "step": 28
    },
    {
      "epoch": 4.142857142857143,
      "grad_norm": 7.75,
      "learning_rate": 3.0147058823529413e-05,
      "loss": 0.6601,
      "step": 29
    },
    {
      "epoch": 4.142857142857143,
      "eval_loss": 0.6804011464118958,
      "eval_matthews_correlation": 0.012938076628071615,
      "eval_runtime": 1.9011,
      "eval_samples_per_second": 116.251,
      "eval_steps_per_second": 2.104,
      "step": 29
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 4.0,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 0.6992,
      "step": 30
    },
    {
      "epoch": 4.285714285714286,
      "eval_loss": 0.6818273067474365,
      "eval_matthews_correlation": 0.012938076628071615,
      "eval_runtime": 1.8995,
      "eval_samples_per_second": 116.345,
      "eval_steps_per_second": 2.106,
      "step": 30
    },
    {
      "epoch": 4.428571428571429,
      "grad_norm": 4.125,
      "learning_rate": 2.8676470588235295e-05,
      "loss": 0.6962,
      "step": 31
    },
    {
      "epoch": 4.428571428571429,
      "eval_loss": 0.6815787553787231,
      "eval_matthews_correlation": 0.012938076628071615,
      "eval_runtime": 1.8495,
      "eval_samples_per_second": 119.492,
      "eval_steps_per_second": 2.163,
      "step": 31
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 1.0234375,
      "learning_rate": 2.7941176470588236e-05,
      "loss": 0.7036,
      "step": 32
    },
    {
      "epoch": 4.571428571428571,
      "eval_loss": 0.6793671250343323,
      "eval_matthews_correlation": 0.012938076628071615,
      "eval_runtime": 1.8986,
      "eval_samples_per_second": 116.404,
      "eval_steps_per_second": 2.107,
      "step": 32
    },
    {
      "epoch": 4.714285714285714,
      "grad_norm": 1.6484375,
      "learning_rate": 2.7205882352941174e-05,
      "loss": 0.6784,
      "step": 33
    },
    {
      "epoch": 4.714285714285714,
      "eval_loss": 0.6809413433074951,
      "eval_matthews_correlation": 0.012938076628071615,
      "eval_runtime": 1.9012,
      "eval_samples_per_second": 116.245,
      "eval_steps_per_second": 2.104,
      "step": 33
    },
    {
      "epoch": 4.857142857142857,
      "grad_norm": 2.515625,
      "learning_rate": 2.647058823529412e-05,
      "loss": 0.67,
      "step": 34
    },
    {
      "epoch": 4.857142857142857,
      "eval_loss": 0.6806762218475342,
      "eval_matthews_correlation": 0.012938076628071615,
      "eval_runtime": 1.9026,
      "eval_samples_per_second": 116.155,
      "eval_steps_per_second": 2.102,
      "step": 34
    },
    {
      "epoch": 5.0,
      "grad_norm": 5.25,
      "learning_rate": 2.5735294117647057e-05,
      "loss": 0.6671,
      "step": 35
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6812605857849121,
      "eval_matthews_correlation": 0.03236368357125948,
      "eval_runtime": 1.9017,
      "eval_samples_per_second": 116.211,
      "eval_steps_per_second": 2.103,
      "step": 35
    },
    {
      "epoch": 5.142857142857143,
      "grad_norm": 1.6796875,
      "learning_rate": 2.5e-05,
      "loss": 0.6736,
      "step": 36
    },
    {
      "epoch": 5.142857142857143,
      "eval_loss": 0.6816417574882507,
      "eval_matthews_correlation": 0.03840151481124831,
      "eval_runtime": 1.8517,
      "eval_samples_per_second": 119.347,
      "eval_steps_per_second": 2.16,
      "step": 36
    },
    {
      "epoch": 5.285714285714286,
      "grad_norm": 2.421875,
      "learning_rate": 2.4264705882352942e-05,
      "loss": 0.6884,
      "step": 37
    },
    {
      "epoch": 5.285714285714286,
      "eval_loss": 0.6835285425186157,
      "eval_matthews_correlation": 0.014648552723664804,
      "eval_runtime": 1.9003,
      "eval_samples_per_second": 116.298,
      "eval_steps_per_second": 2.105,
      "step": 37
    },
    {
      "epoch": 5.428571428571429,
      "grad_norm": 3.6875,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 0.7176,
      "step": 38
    },
    {
      "epoch": 5.428571428571429,
      "eval_loss": 0.6828601956367493,
      "eval_matthews_correlation": 0.014648552723664804,
      "eval_runtime": 1.8971,
      "eval_samples_per_second": 116.495,
      "eval_steps_per_second": 2.109,
      "step": 38
    },
    {
      "epoch": 5.571428571428571,
      "grad_norm": 1.4375,
      "learning_rate": 2.2794117647058825e-05,
      "loss": 0.6654,
      "step": 39
    },
    {
      "epoch": 5.571428571428571,
      "eval_loss": 0.6825487017631531,
      "eval_matthews_correlation": 0.014648552723664804,
      "eval_runtime": 1.8513,
      "eval_samples_per_second": 119.373,
      "eval_steps_per_second": 2.161,
      "step": 39
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 6.125,
      "learning_rate": 2.2058823529411766e-05,
      "loss": 0.6557,
      "step": 40
    },
    {
      "epoch": 5.714285714285714,
      "eval_loss": 0.6816793084144592,
      "eval_matthews_correlation": 0.03840151481124831,
      "eval_runtime": 1.8502,
      "eval_samples_per_second": 119.448,
      "eval_steps_per_second": 2.162,
      "step": 40
    },
    {
      "epoch": 5.857142857142857,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1323529411764707e-05,
      "loss": 0.6842,
      "step": 41
    },
    {
      "epoch": 5.857142857142857,
      "eval_loss": 0.6825309991836548,
      "eval_matthews_correlation": 0.014648552723664804,
      "eval_runtime": 1.8521,
      "eval_samples_per_second": 119.327,
      "eval_steps_per_second": 2.16,
      "step": 41
    },
    {
      "epoch": 6.0,
      "grad_norm": 5.3125,
      "learning_rate": 2.058823529411765e-05,
      "loss": 0.6744,
      "step": 42
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.683228075504303,
      "eval_matthews_correlation": 0.014648552723664804,
      "eval_runtime": 1.8994,
      "eval_samples_per_second": 116.35,
      "eval_steps_per_second": 2.106,
      "step": 42
    },
    {
      "epoch": 6.142857142857143,
      "grad_norm": 1.90625,
      "learning_rate": 1.9852941176470586e-05,
      "loss": 0.7252,
      "step": 43
    },
    {
      "epoch": 6.142857142857143,
      "eval_loss": 0.6838776469230652,
      "eval_matthews_correlation": 0.014648552723664804,
      "eval_runtime": 1.8046,
      "eval_samples_per_second": 122.467,
      "eval_steps_per_second": 2.217,
      "step": 43
    },
    {
      "epoch": 6.285714285714286,
      "grad_norm": 1.21875,
      "learning_rate": 1.9117647058823528e-05,
      "loss": 0.6785,
      "step": 44
    },
    {
      "epoch": 6.285714285714286,
      "eval_loss": 0.6839317679405212,
      "eval_matthews_correlation": 0.014648552723664804,
      "eval_runtime": 1.901,
      "eval_samples_per_second": 116.253,
      "eval_steps_per_second": 2.104,
      "step": 44
    },
    {
      "epoch": 6.428571428571429,
      "grad_norm": 1.3515625,
      "learning_rate": 1.8382352941176472e-05,
      "loss": 0.6793,
      "step": 45
    },
    {
      "epoch": 6.428571428571429,
      "eval_loss": 0.6828281879425049,
      "eval_matthews_correlation": 0.014648552723664804,
      "eval_runtime": 1.9004,
      "eval_samples_per_second": 116.294,
      "eval_steps_per_second": 2.105,
      "step": 45
    },
    {
      "epoch": 6.571428571428571,
      "grad_norm": 6.5625,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.6521,
      "step": 46
    },
    {
      "epoch": 6.571428571428571,
      "eval_loss": 0.6809899806976318,
      "eval_matthews_correlation": 0.026300443342391174,
      "eval_runtime": 1.901,
      "eval_samples_per_second": 116.257,
      "eval_steps_per_second": 2.104,
      "step": 46
    },
    {
      "epoch": 6.714285714285714,
      "grad_norm": 2.0625,
      "learning_rate": 1.6911764705882355e-05,
      "loss": 0.6568,
      "step": 47
    },
    {
      "epoch": 6.714285714285714,
      "eval_loss": 0.6805745959281921,
      "eval_matthews_correlation": 0.03840151481124831,
      "eval_runtime": 1.8994,
      "eval_samples_per_second": 116.353,
      "eval_steps_per_second": 2.106,
      "step": 47
    },
    {
      "epoch": 6.857142857142857,
      "grad_norm": 1.1875,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.6669,
      "step": 48
    },
    {
      "epoch": 6.857142857142857,
      "eval_loss": 0.6794301271438599,
      "eval_matthews_correlation": 0.03840151481124831,
      "eval_runtime": 1.8992,
      "eval_samples_per_second": 116.364,
      "eval_steps_per_second": 2.106,
      "step": 48
    },
    {
      "epoch": 7.0,
      "grad_norm": 3.0625,
      "learning_rate": 1.5441176470588237e-05,
      "loss": 0.7096,
      "step": 49
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.6792279481887817,
      "eval_matthews_correlation": 0.03840151481124831,
      "eval_runtime": 1.8999,
      "eval_samples_per_second": 116.322,
      "eval_steps_per_second": 2.105,
      "step": 49
    },
    {
      "epoch": 7.142857142857143,
      "grad_norm": 3.5,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 0.698,
      "step": 50
    },
    {
      "epoch": 7.142857142857143,
      "eval_loss": 0.6769732236862183,
      "eval_matthews_correlation": 0.019864667834482774,
      "eval_runtime": 1.8984,
      "eval_samples_per_second": 116.413,
      "eval_steps_per_second": 2.107,
      "step": 50
    },
    {
      "epoch": 7.285714285714286,
      "grad_norm": 2.140625,
      "learning_rate": 1.3970588235294118e-05,
      "loss": 0.6773,
      "step": 51
    },
    {
      "epoch": 7.285714285714286,
      "eval_loss": 0.6770384311676025,
      "eval_matthews_correlation": 0.03236368357125948,
      "eval_runtime": 1.9001,
      "eval_samples_per_second": 116.311,
      "eval_steps_per_second": 2.105,
      "step": 51
    },
    {
      "epoch": 7.428571428571429,
      "grad_norm": 1.9453125,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.6603,
      "step": 52
    },
    {
      "epoch": 7.428571428571429,
      "eval_loss": 0.6764286160469055,
      "eval_matthews_correlation": 0.03236368357125948,
      "eval_runtime": 1.9031,
      "eval_samples_per_second": 116.127,
      "eval_steps_per_second": 2.102,
      "step": 52
    },
    {
      "epoch": 7.571428571428571,
      "grad_norm": 1.203125,
      "learning_rate": 1.25e-05,
      "loss": 0.6804,
      "step": 53
    },
    {
      "epoch": 7.571428571428571,
      "eval_loss": 0.6764540076255798,
      "eval_matthews_correlation": 0.03236368357125948,
      "eval_runtime": 1.9008,
      "eval_samples_per_second": 116.264,
      "eval_steps_per_second": 2.104,
      "step": 53
    },
    {
      "epoch": 7.714285714285714,
      "grad_norm": 2.171875,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.681,
      "step": 54
    },
    {
      "epoch": 7.714285714285714,
      "eval_loss": 0.6770803928375244,
      "eval_matthews_correlation": 0.03236368357125948,
      "eval_runtime": 1.8515,
      "eval_samples_per_second": 119.364,
      "eval_steps_per_second": 2.16,
      "step": 54
    },
    {
      "epoch": 7.857142857142857,
      "grad_norm": 4.34375,
      "learning_rate": 1.1029411764705883e-05,
      "loss": 0.6653,
      "step": 55
    },
    {
      "epoch": 7.857142857142857,
      "eval_loss": 0.6761192679405212,
      "eval_matthews_correlation": 0.03236368357125948,
      "eval_runtime": 1.8528,
      "eval_samples_per_second": 119.281,
      "eval_steps_per_second": 2.159,
      "step": 55
    },
    {
      "epoch": 8.0,
      "grad_norm": 5.4375,
      "learning_rate": 1.0294117647058824e-05,
      "loss": 0.6527,
      "step": 56
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.6764020919799805,
      "eval_matthews_correlation": 0.04543029179629692,
      "eval_runtime": 1.9014,
      "eval_samples_per_second": 116.233,
      "eval_steps_per_second": 2.104,
      "step": 56
    },
    {
      "epoch": 8.142857142857142,
      "grad_norm": 5.96875,
      "learning_rate": 9.558823529411764e-06,
      "loss": 0.661,
      "step": 57
    },
    {
      "epoch": 8.142857142857142,
      "eval_loss": 0.6761281490325928,
      "eval_matthews_correlation": 0.04543029179629692,
      "eval_runtime": 1.8981,
      "eval_samples_per_second": 116.432,
      "eval_steps_per_second": 2.107,
      "step": 57
    },
    {
      "epoch": 8.285714285714286,
      "grad_norm": 3.625,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.6332,
      "step": 58
    },
    {
      "epoch": 8.285714285714286,
      "eval_loss": 0.6764816641807556,
      "eval_matthews_correlation": 0.04543029179629692,
      "eval_runtime": 1.9012,
      "eval_samples_per_second": 116.24,
      "eval_steps_per_second": 2.104,
      "step": 58
    },
    {
      "epoch": 8.428571428571429,
      "grad_norm": 3.328125,
      "learning_rate": 8.088235294117648e-06,
      "loss": 0.6971,
      "step": 59
    },
    {
      "epoch": 8.428571428571429,
      "eval_loss": 0.6764915585517883,
      "eval_matthews_correlation": 0.03236368357125948,
      "eval_runtime": 1.9012,
      "eval_samples_per_second": 116.243,
      "eval_steps_per_second": 2.104,
      "step": 59
    },
    {
      "epoch": 8.571428571428571,
      "grad_norm": 1.7890625,
      "learning_rate": 7.3529411764705884e-06,
      "loss": 0.6819,
      "step": 60
    },
    {
      "epoch": 8.571428571428571,
      "eval_loss": 0.6767964959144592,
      "eval_matthews_correlation": 0.04543029179629692,
      "eval_runtime": 1.9009,
      "eval_samples_per_second": 116.261,
      "eval_steps_per_second": 2.104,
      "step": 60
    },
    {
      "epoch": 8.714285714285714,
      "grad_norm": 4.0625,
      "learning_rate": 6.61764705882353e-06,
      "loss": 0.6832,
      "step": 61
    },
    {
      "epoch": 8.714285714285714,
      "eval_loss": 0.6778514981269836,
      "eval_matthews_correlation": 0.03236368357125948,
      "eval_runtime": 1.8991,
      "eval_samples_per_second": 116.37,
      "eval_steps_per_second": 2.106,
      "step": 61
    },
    {
      "epoch": 8.857142857142858,
      "grad_norm": 1.203125,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.6673,
      "step": 62
    },
    {
      "epoch": 8.857142857142858,
      "eval_loss": 0.6788612008094788,
      "eval_matthews_correlation": 0.019864667834482774,
      "eval_runtime": 1.9007,
      "eval_samples_per_second": 116.27,
      "eval_steps_per_second": 2.104,
      "step": 62
    },
    {
      "epoch": 9.0,
      "grad_norm": 6.65625,
      "learning_rate": 5.147058823529412e-06,
      "loss": 0.6472,
      "step": 63
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.6786766648292542,
      "eval_matthews_correlation": 0.019864667834482774,
      "eval_runtime": 1.8996,
      "eval_samples_per_second": 116.34,
      "eval_steps_per_second": 2.106,
      "step": 63
    },
    {
      "epoch": 9.142857142857142,
      "grad_norm": 2.78125,
      "learning_rate": 4.411764705882353e-06,
      "loss": 0.6997,
      "step": 64
    },
    {
      "epoch": 9.142857142857142,
      "eval_loss": 0.6784170866012573,
      "eval_matthews_correlation": 0.03236368357125948,
      "eval_runtime": 1.8989,
      "eval_samples_per_second": 116.385,
      "eval_steps_per_second": 2.107,
      "step": 64
    },
    {
      "epoch": 9.285714285714286,
      "grad_norm": 7.28125,
      "learning_rate": 3.6764705882352942e-06,
      "loss": 0.6486,
      "step": 65
    },
    {
      "epoch": 9.285714285714286,
      "eval_loss": 0.6794090867042542,
      "eval_matthews_correlation": 0.019864667834482774,
      "eval_runtime": 1.9,
      "eval_samples_per_second": 116.314,
      "eval_steps_per_second": 2.105,
      "step": 65
    },
    {
      "epoch": 9.428571428571429,
      "grad_norm": 0.83984375,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 0.6702,
      "step": 66
    },
    {
      "epoch": 9.428571428571429,
      "eval_loss": 0.6790147423744202,
      "eval_matthews_correlation": 0.019864667834482774,
      "eval_runtime": 1.8501,
      "eval_samples_per_second": 119.451,
      "eval_steps_per_second": 2.162,
      "step": 66
    },
    {
      "epoch": 9.571428571428571,
      "grad_norm": 8.625,
      "learning_rate": 2.2058823529411767e-06,
      "loss": 0.7147,
      "step": 67
    },
    {
      "epoch": 9.571428571428571,
      "eval_loss": 0.6785043478012085,
      "eval_matthews_correlation": 0.03840151481124831,
      "eval_runtime": 1.8499,
      "eval_samples_per_second": 119.469,
      "eval_steps_per_second": 2.162,
      "step": 67
    },
    {
      "epoch": 9.714285714285714,
      "grad_norm": 6.0,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 0.6492,
      "step": 68
    },
    {
      "epoch": 9.714285714285714,
      "eval_loss": 0.6781408786773682,
      "eval_matthews_correlation": 0.03840151481124831,
      "eval_runtime": 1.9005,
      "eval_samples_per_second": 116.283,
      "eval_steps_per_second": 2.105,
      "step": 68
    },
    {
      "epoch": 9.857142857142858,
      "grad_norm": 1.9140625,
      "learning_rate": 7.352941176470589e-07,
      "loss": 0.6741,
      "step": 69
    },
    {
      "epoch": 9.857142857142858,
      "eval_loss": 0.6785739660263062,
      "eval_matthews_correlation": 0.03840151481124831,
      "eval_runtime": 1.9018,
      "eval_samples_per_second": 116.205,
      "eval_steps_per_second": 2.103,
      "step": 69
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.4921875,
      "learning_rate": 0.0,
      "loss": 0.6885,
      "step": 70
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.6790357232093811,
      "eval_matthews_correlation": 0.019864667834482774,
      "eval_runtime": 1.9009,
      "eval_samples_per_second": 116.259,
      "eval_steps_per_second": 2.104,
      "step": 70
    },
    {
      "epoch": 10.0,
      "step": 70,
      "total_flos": 3.203834021989581e+16,
      "train_loss": 0.6814145530973162,
      "train_runtime": 351.2516,
      "train_samples_per_second": 25.139,
      "train_steps_per_second": 0.199
    }
  ],
  "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": 3.203834021989581e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}