{
  "best_metric": 1.0,
  "best_model_checkpoint": "./results/checkpoint-10",
  "epoch": 1.9607843137254903,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.9950980392156866e-05,
      "loss": 0.0247,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9901960784313726e-05,
      "loss": 0.0265,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.985294117647059e-05,
      "loss": 0.0243,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9803921568627454e-05,
      "loss": 0.0233,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9754901960784318e-05,
      "loss": 0.025,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9705882352941178e-05,
      "loss": 0.0247,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.965686274509804e-05,
      "loss": 0.0242,
      "step": 7
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9607843137254903e-05,
      "loss": 0.0243,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9558823529411766e-05,
      "loss": 0.0235,
      "step": 9
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.950980392156863e-05,
      "loss": 0.0237,
      "step": 10
    },
    {
      "epoch": 0.05,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.023951606824994087,
      "eval_runtime": 45.985,
      "eval_samples_per_second": 9.046,
      "eval_steps_per_second": 0.565,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.946078431372549e-05,
      "loss": 0.0242,
      "step": 11
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9411764705882355e-05,
      "loss": 0.0243,
      "step": 12
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.936274509803922e-05,
      "loss": 0.0258,
      "step": 13
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.931372549019608e-05,
      "loss": 0.0239,
      "step": 14
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9264705882352943e-05,
      "loss": 0.0215,
      "step": 15
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9215686274509807e-05,
      "loss": 0.0239,
      "step": 16
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.916666666666667e-05,
      "loss": 0.0218,
      "step": 17
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.911764705882353e-05,
      "loss": 0.0213,
      "step": 18
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9068627450980395e-05,
      "loss": 0.0224,
      "step": 19
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9019607843137255e-05,
      "loss": 0.0224,
      "step": 20
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.022203562781214714,
      "eval_runtime": 45.6095,
      "eval_samples_per_second": 9.121,
      "eval_steps_per_second": 0.57,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.897058823529412e-05,
      "loss": 0.0223,
      "step": 21
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.892156862745098e-05,
      "loss": 0.0226,
      "step": 22
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.8872549019607844e-05,
      "loss": 0.0207,
      "step": 23
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 0.021,
      "step": 24
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.877450980392157e-05,
      "loss": 0.0216,
      "step": 25
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.8725490196078432e-05,
      "loss": 0.0219,
      "step": 26
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.8676470588235296e-05,
      "loss": 0.0206,
      "step": 27
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.862745098039216e-05,
      "loss": 0.0218,
      "step": 28
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.857843137254902e-05,
      "loss": 0.021,
      "step": 29
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.8529411764705884e-05,
      "loss": 0.0214,
      "step": 30
    },
    {
      "epoch": 0.15,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.020884361118078232,
      "eval_runtime": 44.0709,
      "eval_samples_per_second": 9.439,
      "eval_steps_per_second": 0.59,
      "step": 30
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.8480392156862748e-05,
      "loss": 0.0215,
      "step": 31
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.843137254901961e-05,
      "loss": 0.0209,
      "step": 32
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.8382352941176472e-05,
      "loss": 0.0202,
      "step": 33
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 0.0208,
      "step": 34
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.8284313725490197e-05,
      "loss": 0.0202,
      "step": 35
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.823529411764706e-05,
      "loss": 0.0205,
      "step": 36
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8186274509803924e-05,
      "loss": 0.0203,
      "step": 37
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8137254901960785e-05,
      "loss": 0.0204,
      "step": 38
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.808823529411765e-05,
      "loss": 0.02,
      "step": 39
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8039215686274513e-05,
      "loss": 0.019,
      "step": 40
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.019802309572696686,
      "eval_runtime": 43.7053,
      "eval_samples_per_second": 9.518,
      "eval_steps_per_second": 0.595,
      "step": 40
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.7990196078431373e-05,
      "loss": 0.0204,
      "step": 41
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.7941176470588237e-05,
      "loss": 0.0193,
      "step": 42
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.78921568627451e-05,
      "loss": 0.0202,
      "step": 43
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.7843137254901965e-05,
      "loss": 0.0199,
      "step": 44
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.7794117647058825e-05,
      "loss": 0.0186,
      "step": 45
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.7745098039215686e-05,
      "loss": 0.0187,
      "step": 46
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.769607843137255e-05,
      "loss": 0.019,
      "step": 47
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.0191,
      "step": 48
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.7598039215686274e-05,
      "loss": 0.0195,
      "step": 49
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7549019607843138e-05,
      "loss": 0.0187,
      "step": 50
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.018848298117518425,
      "eval_runtime": 44.1124,
      "eval_samples_per_second": 9.43,
      "eval_steps_per_second": 0.589,
      "step": 50
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 0.0185,
      "step": 51
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7450980392156866e-05,
      "loss": 0.0184,
      "step": 52
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.7401960784313726e-05,
      "loss": 0.0193,
      "step": 53
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.735294117647059e-05,
      "loss": 0.0187,
      "step": 54
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.7303921568627454e-05,
      "loss": 0.0167,
      "step": 55
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.7254901960784314e-05,
      "loss": 0.0182,
      "step": 56
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.720588235294118e-05,
      "loss": 0.0182,
      "step": 57
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.715686274509804e-05,
      "loss": 0.0192,
      "step": 58
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.7107843137254903e-05,
      "loss": 0.0185,
      "step": 59
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.7058823529411767e-05,
      "loss": 0.0181,
      "step": 60
    },
    {
      "epoch": 0.29,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.01803619973361492,
      "eval_runtime": 44.0611,
      "eval_samples_per_second": 9.441,
      "eval_steps_per_second": 0.59,
      "step": 60
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.7009803921568627e-05,
      "loss": 0.0184,
      "step": 61
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.696078431372549e-05,
      "loss": 0.0194,
      "step": 62
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.6911764705882355e-05,
      "loss": 0.0182,
      "step": 63
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.686274509803922e-05,
      "loss": 0.0185,
      "step": 64
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.681372549019608e-05,
      "loss": 0.0173,
      "step": 65
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.6764705882352943e-05,
      "loss": 0.0173,
      "step": 66
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.6715686274509807e-05,
      "loss": 0.0176,
      "step": 67
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0181,
      "step": 68
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.661764705882353e-05,
      "loss": 0.0177,
      "step": 69
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.6568627450980395e-05,
      "loss": 0.0181,
      "step": 70
    },
    {
      "epoch": 0.34,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0173654742538929,
      "eval_runtime": 43.9898,
      "eval_samples_per_second": 9.457,
      "eval_steps_per_second": 0.591,
      "step": 70
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.6519607843137256e-05,
      "loss": 0.0174,
      "step": 71
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.647058823529412e-05,
      "loss": 0.017,
      "step": 72
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.642156862745098e-05,
      "loss": 0.016,
      "step": 73
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.6372549019607844e-05,
      "loss": 0.0167,
      "step": 74
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.6323529411764708e-05,
      "loss": 0.0167,
      "step": 75
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.627450980392157e-05,
      "loss": 0.0176,
      "step": 76
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.6225490196078432e-05,
      "loss": 0.0172,
      "step": 77
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.0165,
      "step": 78
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.612745098039216e-05,
      "loss": 0.0169,
      "step": 79
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.607843137254902e-05,
      "loss": 0.0164,
      "step": 80
    },
    {
      "epoch": 0.39,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.016724321991205215,
      "eval_runtime": 45.333,
      "eval_samples_per_second": 9.177,
      "eval_steps_per_second": 0.574,
      "step": 80
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.6029411764705884e-05,
      "loss": 0.0163,
      "step": 81
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.5980392156862748e-05,
      "loss": 0.0169,
      "step": 82
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.593137254901961e-05,
      "loss": 0.0161,
      "step": 83
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.5882352941176473e-05,
      "loss": 0.0173,
      "step": 84
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.5833333333333333e-05,
      "loss": 0.0173,
      "step": 85
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.5784313725490197e-05,
      "loss": 0.0162,
      "step": 86
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.573529411764706e-05,
      "loss": 0.0158,
      "step": 87
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.568627450980392e-05,
      "loss": 0.016,
      "step": 88
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.5637254901960785e-05,
      "loss": 0.0162,
      "step": 89
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.558823529411765e-05,
      "loss": 0.0167,
      "step": 90
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.016224848106503487,
      "eval_runtime": 44.042,
      "eval_samples_per_second": 9.446,
      "eval_steps_per_second": 0.59,
      "step": 90
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.5539215686274513e-05,
      "loss": 0.017,
      "step": 91
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.5490196078431373e-05,
      "loss": 0.0162,
      "step": 92
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.5441176470588237e-05,
      "loss": 0.0162,
      "step": 93
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.53921568627451e-05,
      "loss": 0.016,
      "step": 94
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.5343137254901962e-05,
      "loss": 0.0159,
      "step": 95
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.5294117647058822e-05,
      "loss": 0.0165,
      "step": 96
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.5245098039215686e-05,
      "loss": 0.0155,
      "step": 97
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.519607843137255e-05,
      "loss": 0.0162,
      "step": 98
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.5147058823529412e-05,
      "loss": 0.016,
      "step": 99
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.5098039215686276e-05,
      "loss": 0.0153,
      "step": 100
    },
    {
      "epoch": 0.49,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.015692483633756638,
      "eval_runtime": 285.5108,
      "eval_samples_per_second": 1.457,
      "eval_steps_per_second": 0.091,
      "step": 100
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.5049019607843138e-05,
      "loss": 0.0165,
      "step": 101
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0156,
      "step": 102
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.4950980392156864e-05,
      "loss": 0.0151,
      "step": 103
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.4901960784313726e-05,
      "loss": 0.0155,
      "step": 104
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.485294117647059e-05,
      "loss": 0.0159,
      "step": 105
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.4803921568627453e-05,
      "loss": 0.0156,
      "step": 106
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.4754901960784316e-05,
      "loss": 0.0152,
      "step": 107
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 0.0155,
      "step": 108
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.4656862745098039e-05,
      "loss": 0.015,
      "step": 109
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.4607843137254903e-05,
      "loss": 0.0156,
      "step": 110
    },
    {
      "epoch": 0.54,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.01523014809936285,
      "eval_runtime": 43.8475,
      "eval_samples_per_second": 9.487,
      "eval_steps_per_second": 0.593,
      "step": 110
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.4558823529411765e-05,
      "loss": 0.0152,
      "step": 111
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.4509803921568629e-05,
      "loss": 0.0149,
      "step": 112
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.4460784313725491e-05,
      "loss": 0.015,
      "step": 113
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.4411764705882353e-05,
      "loss": 0.0146,
      "step": 114
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.4362745098039217e-05,
      "loss": 0.0143,
      "step": 115
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.431372549019608e-05,
      "loss": 0.0148,
      "step": 116
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.4264705882352943e-05,
      "loss": 0.0159,
      "step": 117
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.4215686274509805e-05,
      "loss": 0.0147,
      "step": 118
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.416666666666667e-05,
      "loss": 0.015,
      "step": 119
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.4117647058823532e-05,
      "loss": 0.0153,
      "step": 120
    },
    {
      "epoch": 0.59,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.014789704233407974,
      "eval_runtime": 85.7951,
      "eval_samples_per_second": 4.849,
      "eval_steps_per_second": 0.303,
      "step": 120
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.4068627450980394e-05,
      "loss": 0.0148,
      "step": 121
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.4019607843137256e-05,
      "loss": 0.0164,
      "step": 122
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.3970588235294118e-05,
      "loss": 0.0148,
      "step": 123
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.392156862745098e-05,
      "loss": 0.0159,
      "step": 124
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.3872549019607844e-05,
      "loss": 0.0152,
      "step": 125
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.3823529411764706e-05,
      "loss": 0.0144,
      "step": 126
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.377450980392157e-05,
      "loss": 0.015,
      "step": 127
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.3725490196078432e-05,
      "loss": 0.0146,
      "step": 128
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.3676470588235296e-05,
      "loss": 0.0141,
      "step": 129
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.3627450980392158e-05,
      "loss": 0.0142,
      "step": 130
    },
    {
      "epoch": 0.64,
      "eval_accuracy": 0.9855769230769231,
      "eval_f1": 0.9872564935064935,
      "eval_loss": 0.0629911869764328,
      "eval_runtime": 34.9932,
      "eval_samples_per_second": 11.888,
      "eval_steps_per_second": 0.743,
      "step": 130
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.357843137254902e-05,
      "loss": 0.0837,
      "step": 131
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.3529411764705885e-05,
      "loss": 0.0145,
      "step": 132
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.3480392156862747e-05,
      "loss": 0.0141,
      "step": 133
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.3431372549019607e-05,
      "loss": 0.0138,
      "step": 134
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.3382352941176471e-05,
      "loss": 0.0147,
      "step": 135
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.3277,
      "step": 136
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.3284313725490197e-05,
      "loss": 0.0142,
      "step": 137
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.0139,
      "step": 138
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.3186274509803923e-05,
      "loss": 0.0149,
      "step": 139
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.3137254901960785e-05,
      "loss": 0.0965,
      "step": 140
    },
    {
      "epoch": 0.69,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.01508896891027689,
      "eval_runtime": 41.1613,
      "eval_samples_per_second": 10.107,
      "eval_steps_per_second": 0.632,
      "step": 140
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.3088235294117648e-05,
      "loss": 0.0151,
      "step": 141
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.3039215686274511e-05,
      "loss": 0.0152,
      "step": 142
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.2990196078431374e-05,
      "loss": 0.015,
      "step": 143
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.2941176470588238e-05,
      "loss": 0.0152,
      "step": 144
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.28921568627451e-05,
      "loss": 0.015,
      "step": 145
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.2843137254901964e-05,
      "loss": 0.0151,
      "step": 146
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.2794117647058824e-05,
      "loss": 0.0151,
      "step": 147
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.2745098039215686e-05,
      "loss": 0.0155,
      "step": 148
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.269607843137255e-05,
      "loss": 0.0146,
      "step": 149
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.2647058823529412e-05,
      "loss": 0.0152,
      "step": 150
    },
    {
      "epoch": 0.74,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.014995763078331947,
      "eval_runtime": 44.3071,
      "eval_samples_per_second": 9.389,
      "eval_steps_per_second": 0.587,
      "step": 150
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.2598039215686275e-05,
      "loss": 0.0148,
      "step": 151
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.2549019607843138e-05,
      "loss": 0.0145,
      "step": 152
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.25e-05,
      "loss": 0.0145,
      "step": 153
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.2450980392156864e-05,
      "loss": 0.015,
      "step": 154
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.2401960784313727e-05,
      "loss": 0.0135,
      "step": 155
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.235294117647059e-05,
      "loss": 0.014,
      "step": 156
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.2303921568627453e-05,
      "loss": 0.0142,
      "step": 157
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.2254901960784315e-05,
      "loss": 0.0137,
      "step": 158
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.2205882352941179e-05,
      "loss": 0.0137,
      "step": 159
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.215686274509804e-05,
      "loss": 0.0144,
      "step": 160
    },
    {
      "epoch": 0.78,
      "eval_accuracy": 0.9951923076923077,
      "eval_f1": 0.9957494043751355,
      "eval_loss": 0.021605193614959717,
      "eval_runtime": 44.8691,
      "eval_samples_per_second": 9.271,
      "eval_steps_per_second": 0.579,
      "step": 160
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.2107843137254901e-05,
      "loss": 0.0139,
      "step": 161
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.2058823529411765e-05,
      "loss": 0.0146,
      "step": 162
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.2009803921568628e-05,
      "loss": 0.0132,
      "step": 163
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.1960784313725491e-05,
      "loss": 0.214,
      "step": 164
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.1911764705882354e-05,
      "loss": 0.0129,
      "step": 165
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.1862745098039217e-05,
      "loss": 0.014,
      "step": 166
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.181372549019608e-05,
      "loss": 0.0138,
      "step": 167
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.0139,
      "step": 168
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.1715686274509806e-05,
      "loss": 0.0137,
      "step": 169
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 0.014,
      "step": 170
    },
    {
      "epoch": 0.83,
      "eval_accuracy": 0.9975961538461539,
      "eval_f1": 0.9978732122960841,
      "eval_loss": 0.022373327985405922,
      "eval_runtime": 44.8886,
      "eval_samples_per_second": 9.267,
      "eval_steps_per_second": 0.579,
      "step": 170
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.1617647058823532e-05,
      "loss": 0.0133,
      "step": 171
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.1568627450980394e-05,
      "loss": 0.0143,
      "step": 172
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1519607843137254e-05,
      "loss": 0.0136,
      "step": 173
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1470588235294118e-05,
      "loss": 0.0139,
      "step": 174
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.142156862745098e-05,
      "loss": 0.0136,
      "step": 175
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1372549019607844e-05,
      "loss": 0.0136,
      "step": 176
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.1323529411764707e-05,
      "loss": 0.0147,
      "step": 177
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.1274509803921569e-05,
      "loss": 0.0136,
      "step": 178
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.1225490196078433e-05,
      "loss": 0.0131,
      "step": 179
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.1176470588235295e-05,
      "loss": 0.014,
      "step": 180
    },
    {
      "epoch": 0.88,
      "eval_accuracy": 0.9855769230769231,
      "eval_f1": 0.9872191468577011,
      "eval_loss": 0.06219267472624779,
      "eval_runtime": 44.8444,
      "eval_samples_per_second": 9.277,
      "eval_steps_per_second": 0.58,
      "step": 180
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.1127450980392159e-05,
      "loss": 0.0134,
      "step": 181
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.1078431372549021e-05,
      "loss": 0.0131,
      "step": 182
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.1029411764705885e-05,
      "loss": 0.2791,
      "step": 183
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.0980392156862747e-05,
      "loss": 0.0133,
      "step": 184
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.0931372549019607e-05,
      "loss": 0.0131,
      "step": 185
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.0882352941176471e-05,
      "loss": 0.0135,
      "step": 186
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.0833333333333334e-05,
      "loss": 0.0133,
      "step": 187
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.0784313725490196e-05,
      "loss": 0.0135,
      "step": 188
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.073529411764706e-05,
      "loss": 0.0136,
      "step": 189
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.0686274509803922e-05,
      "loss": 0.0128,
      "step": 190
    },
    {
      "epoch": 0.93,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.013310183770954609,
      "eval_runtime": 45.3674,
      "eval_samples_per_second": 9.17,
      "eval_steps_per_second": 0.573,
      "step": 190
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.0637254901960786e-05,
      "loss": 0.0132,
      "step": 191
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.0588235294117648e-05,
      "loss": 0.0136,
      "step": 192
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0539215686274512e-05,
      "loss": 0.0133,
      "step": 193
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0490196078431374e-05,
      "loss": 0.0132,
      "step": 194
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0441176470588236e-05,
      "loss": 0.0128,
      "step": 195
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.03921568627451e-05,
      "loss": 0.1327,
      "step": 196
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.0343137254901962e-05,
      "loss": 0.0129,
      "step": 197
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.0294117647058823e-05,
      "loss": 0.0128,
      "step": 198
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0245098039215687e-05,
      "loss": 0.0134,
      "step": 199
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0196078431372549e-05,
      "loss": 0.013,
      "step": 200
    },
    {
      "epoch": 0.98,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.013462849892675877,
      "eval_runtime": 44.5104,
      "eval_samples_per_second": 9.346,
      "eval_steps_per_second": 0.584,
      "step": 200
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0147058823529413e-05,
      "loss": 0.0132,
      "step": 201
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0098039215686275e-05,
      "loss": 0.0133,
      "step": 202
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0049019607843139e-05,
      "loss": 0.0133,
      "step": 203
    },
    {
      "epoch": 1.0,
      "learning_rate": 1e-05,
      "loss": 0.0129,
      "step": 204
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.950980392156863e-06,
      "loss": 0.0121,
      "step": 205
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.901960784313727e-06,
      "loss": 0.0132,
      "step": 206
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.852941176470589e-06,
      "loss": 0.0128,
      "step": 207
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.803921568627451e-06,
      "loss": 0.013,
      "step": 208
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.754901960784315e-06,
      "loss": 0.0129,
      "step": 209
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.705882352941177e-06,
      "loss": 0.0127,
      "step": 210
    },
    {
      "epoch": 1.03,
      "eval_accuracy": 0.9975961538461539,
      "eval_f1": 0.9973483427141964,
      "eval_loss": 0.023964770138263702,
      "eval_runtime": 44.9115,
      "eval_samples_per_second": 9.263,
      "eval_steps_per_second": 0.579,
      "step": 210
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.65686274509804e-06,
      "loss": 0.0127,
      "step": 211
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.607843137254903e-06,
      "loss": 0.0138,
      "step": 212
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.558823529411766e-06,
      "loss": 0.013,
      "step": 213
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.509803921568628e-06,
      "loss": 0.0127,
      "step": 214
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.46078431372549e-06,
      "loss": 0.0123,
      "step": 215
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.411764705882354e-06,
      "loss": 0.0126,
      "step": 216
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.362745098039216e-06,
      "loss": 0.0128,
      "step": 217
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.31372549019608e-06,
      "loss": 0.0126,
      "step": 218
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.264705882352942e-06,
      "loss": 0.0127,
      "step": 219
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.215686274509804e-06,
      "loss": 0.0127,
      "step": 220
    },
    {
      "epoch": 1.08,
      "eval_accuracy": 0.9975961538461539,
      "eval_f1": 0.9973483427141964,
      "eval_loss": 0.025055842474102974,
      "eval_runtime": 46.6357,
      "eval_samples_per_second": 8.92,
      "eval_steps_per_second": 0.558,
      "step": 220
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.166666666666666e-06,
      "loss": 0.0125,
      "step": 221
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.11764705882353e-06,
      "loss": 0.0126,
      "step": 222
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.068627450980392e-06,
      "loss": 0.0118,
      "step": 223
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.019607843137256e-06,
      "loss": 0.0123,
      "step": 224
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.970588235294119e-06,
      "loss": 0.0126,
      "step": 225
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.921568627450982e-06,
      "loss": 0.0127,
      "step": 226
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.872549019607843e-06,
      "loss": 0.0126,
      "step": 227
    },
    {
      "epoch": 1.12,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.0121,
      "step": 228
    },
    {
      "epoch": 1.12,
      "learning_rate": 8.774509803921569e-06,
      "loss": 0.0124,
      "step": 229
    },
    {
      "epoch": 1.13,
      "learning_rate": 8.725490196078433e-06,
      "loss": 0.0123,
      "step": 230
    },
    {
      "epoch": 1.13,
      "eval_accuracy": 0.9951923076923077,
      "eval_f1": 0.9946306933075956,
      "eval_loss": 0.023868300020694733,
      "eval_runtime": 44.7504,
      "eval_samples_per_second": 9.296,
      "eval_steps_per_second": 0.581,
      "step": 230
    },
    {
      "epoch": 1.13,
      "learning_rate": 8.676470588235295e-06,
      "loss": 0.0126,
      "step": 231
    },
    {
      "epoch": 1.14,
      "learning_rate": 8.627450980392157e-06,
      "loss": 0.0118,
      "step": 232
    },
    {
      "epoch": 1.14,
      "learning_rate": 8.57843137254902e-06,
      "loss": 0.0124,
      "step": 233
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.529411764705883e-06,
      "loss": 0.0125,
      "step": 234
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.480392156862745e-06,
      "loss": 0.0119,
      "step": 235
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.43137254901961e-06,
      "loss": 0.0122,
      "step": 236
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.382352941176472e-06,
      "loss": 0.0124,
      "step": 237
    },
    {
      "epoch": 1.17,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.012,
      "step": 238
    },
    {
      "epoch": 1.17,
      "learning_rate": 8.284313725490198e-06,
      "loss": 0.0123,
      "step": 239
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.23529411764706e-06,
      "loss": 0.012,
      "step": 240
    },
    {
      "epoch": 1.18,
      "eval_accuracy": 0.9975961538461539,
      "eval_f1": 0.9973483427141964,
      "eval_loss": 0.01997234672307968,
      "eval_runtime": 36.0151,
      "eval_samples_per_second": 11.551,
      "eval_steps_per_second": 0.722,
      "step": 240
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.186274509803922e-06,
      "loss": 0.0122,
      "step": 241
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.137254901960784e-06,
      "loss": 0.0119,
      "step": 242
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.088235294117648e-06,
      "loss": 0.0125,
      "step": 243
    },
    {
      "epoch": 1.2,
      "learning_rate": 8.03921568627451e-06,
      "loss": 0.0118,
      "step": 244
    },
    {
      "epoch": 1.2,
      "learning_rate": 7.990196078431374e-06,
      "loss": 0.0119,
      "step": 245
    },
    {
      "epoch": 1.21,
      "learning_rate": 7.941176470588236e-06,
      "loss": 0.0115,
      "step": 246
    },
    {
      "epoch": 1.21,
      "learning_rate": 7.892156862745098e-06,
      "loss": 0.012,
      "step": 247
    },
    {
      "epoch": 1.22,
      "learning_rate": 7.84313725490196e-06,
      "loss": 0.012,
      "step": 248
    },
    {
      "epoch": 1.22,
      "learning_rate": 7.794117647058825e-06,
      "loss": 0.0119,
      "step": 249
    },
    {
      "epoch": 1.23,
      "learning_rate": 7.745098039215687e-06,
      "loss": 0.0117,
      "step": 250
    },
    {
      "epoch": 1.23,
      "eval_accuracy": 0.9975961538461539,
      "eval_f1": 0.9973483427141964,
      "eval_loss": 0.017237048596143723,
      "eval_runtime": 35.9546,
      "eval_samples_per_second": 11.57,
      "eval_steps_per_second": 0.723,
      "step": 250
    },
    {
      "epoch": 1.23,
      "learning_rate": 7.69607843137255e-06,
      "loss": 0.0113,
      "step": 251
    },
    {
      "epoch": 1.24,
      "learning_rate": 7.647058823529411e-06,
      "loss": 0.0116,
      "step": 252
    },
    {
      "epoch": 1.24,
      "learning_rate": 7.598039215686275e-06,
      "loss": 0.0125,
      "step": 253
    },
    {
      "epoch": 1.25,
      "learning_rate": 7.549019607843138e-06,
      "loss": 0.0118,
      "step": 254
    },
    {
      "epoch": 1.25,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.0123,
      "step": 255
    },
    {
      "epoch": 1.25,
      "learning_rate": 7.450980392156863e-06,
      "loss": 0.012,
      "step": 256
    },
    {
      "epoch": 1.26,
      "learning_rate": 7.401960784313726e-06,
      "loss": 0.1191,
      "step": 257
    },
    {
      "epoch": 1.26,
      "learning_rate": 7.352941176470589e-06,
      "loss": 0.012,
      "step": 258
    },
    {
      "epoch": 1.27,
      "learning_rate": 7.3039215686274515e-06,
      "loss": 0.0117,
      "step": 259
    },
    {
      "epoch": 1.27,
      "learning_rate": 7.2549019607843145e-06,
      "loss": 0.0121,
      "step": 260
    },
    {
      "epoch": 1.27,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.01184043474495411,
      "eval_runtime": 36.6675,
      "eval_samples_per_second": 11.345,
      "eval_steps_per_second": 0.709,
      "step": 260
    },
    {
      "epoch": 1.28,
      "learning_rate": 7.205882352941177e-06,
      "loss": 0.0123,
      "step": 261
    },
    {
      "epoch": 1.28,
      "learning_rate": 7.15686274509804e-06,
      "loss": 0.0117,
      "step": 262
    },
    {
      "epoch": 1.29,
      "learning_rate": 7.107843137254903e-06,
      "loss": 0.0118,
      "step": 263
    },
    {
      "epoch": 1.29,
      "learning_rate": 7.058823529411766e-06,
      "loss": 0.0118,
      "step": 264
    },
    {
      "epoch": 1.3,
      "learning_rate": 7.009803921568628e-06,
      "loss": 0.0121,
      "step": 265
    },
    {
      "epoch": 1.3,
      "learning_rate": 6.96078431372549e-06,
      "loss": 0.0122,
      "step": 266
    },
    {
      "epoch": 1.31,
      "learning_rate": 6.911764705882353e-06,
      "loss": 0.0117,
      "step": 267
    },
    {
      "epoch": 1.31,
      "learning_rate": 6.862745098039216e-06,
      "loss": 0.0115,
      "step": 268
    },
    {
      "epoch": 1.32,
      "learning_rate": 6.813725490196079e-06,
      "loss": 0.0116,
      "step": 269
    },
    {
      "epoch": 1.32,
      "learning_rate": 6.764705882352942e-06,
      "loss": 0.0113,
      "step": 270
    },
    {
      "epoch": 1.32,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.011712317354977131,
      "eval_runtime": 36.4009,
      "eval_samples_per_second": 11.428,
      "eval_steps_per_second": 0.714,
      "step": 270
    },
    {
      "epoch": 1.33,
      "learning_rate": 6.715686274509804e-06,
      "loss": 0.0116,
      "step": 271
    },
    {
      "epoch": 1.33,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.0118,
      "step": 272
    },
    {
      "epoch": 1.34,
      "learning_rate": 6.61764705882353e-06,
      "loss": 0.0114,
      "step": 273
    },
    {
      "epoch": 1.34,
      "learning_rate": 6.568627450980393e-06,
      "loss": 0.0118,
      "step": 274
    },
    {
      "epoch": 1.35,
      "learning_rate": 6.519607843137256e-06,
      "loss": 0.0113,
      "step": 275
    },
    {
      "epoch": 1.35,
      "learning_rate": 6.470588235294119e-06,
      "loss": 0.0112,
      "step": 276
    },
    {
      "epoch": 1.36,
      "learning_rate": 6.421568627450982e-06,
      "loss": 0.0116,
      "step": 277
    },
    {
      "epoch": 1.36,
      "learning_rate": 6.372549019607843e-06,
      "loss": 0.0114,
      "step": 278
    },
    {
      "epoch": 1.37,
      "learning_rate": 6.323529411764706e-06,
      "loss": 0.0114,
      "step": 279
    },
    {
      "epoch": 1.37,
      "learning_rate": 6.274509803921569e-06,
      "loss": 0.012,
      "step": 280
    },
    {
      "epoch": 1.37,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.012247053906321526,
      "eval_runtime": 36.9279,
      "eval_samples_per_second": 11.265,
      "eval_steps_per_second": 0.704,
      "step": 280
    },
    {
      "epoch": 1.38,
      "learning_rate": 6.225490196078432e-06,
      "loss": 0.0116,
      "step": 281
    },
    {
      "epoch": 1.38,
      "learning_rate": 6.176470588235295e-06,
      "loss": 0.0115,
      "step": 282
    },
    {
      "epoch": 1.39,
      "learning_rate": 6.1274509803921575e-06,
      "loss": 0.0114,
      "step": 283
    },
    {
      "epoch": 1.39,
      "learning_rate": 6.07843137254902e-06,
      "loss": 0.0116,
      "step": 284
    },
    {
      "epoch": 1.4,
      "learning_rate": 6.029411764705883e-06,
      "loss": 0.0111,
      "step": 285
    },
    {
      "epoch": 1.4,
      "learning_rate": 5.980392156862746e-06,
      "loss": 0.0109,
      "step": 286
    },
    {
      "epoch": 1.41,
      "learning_rate": 5.931372549019609e-06,
      "loss": 0.0115,
      "step": 287
    },
    {
      "epoch": 1.41,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.0113,
      "step": 288
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.833333333333334e-06,
      "loss": 0.0113,
      "step": 289
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.784313725490197e-06,
      "loss": 0.0121,
      "step": 290
    },
    {
      "epoch": 1.42,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.012648958712816238,
      "eval_runtime": 43.1975,
      "eval_samples_per_second": 9.63,
      "eval_steps_per_second": 0.602,
      "step": 290
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.735294117647059e-06,
      "loss": 0.0111,
      "step": 291
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.686274509803922e-06,
      "loss": 0.0115,
      "step": 292
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.637254901960784e-06,
      "loss": 0.0109,
      "step": 293
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.588235294117647e-06,
      "loss": 0.0111,
      "step": 294
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.5392156862745104e-06,
      "loss": 0.0109,
      "step": 295
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.4901960784313735e-06,
      "loss": 0.0115,
      "step": 296
    },
    {
      "epoch": 1.46,
      "learning_rate": 5.441176470588236e-06,
      "loss": 0.0115,
      "step": 297
    },
    {
      "epoch": 1.46,
      "learning_rate": 5.392156862745098e-06,
      "loss": 0.0115,
      "step": 298
    },
    {
      "epoch": 1.47,
      "learning_rate": 5.343137254901961e-06,
      "loss": 0.0111,
      "step": 299
    },
    {
      "epoch": 1.47,
      "learning_rate": 5.294117647058824e-06,
      "loss": 0.0111,
      "step": 300
    },
    {
      "epoch": 1.47,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.012613965198397636,
      "eval_runtime": 44.8985,
      "eval_samples_per_second": 9.265,
      "eval_steps_per_second": 0.579,
      "step": 300
    },
    {
      "epoch": 1.48,
      "learning_rate": 5.245098039215687e-06,
      "loss": 0.0115,
      "step": 301
    },
    {
      "epoch": 1.48,
      "learning_rate": 5.19607843137255e-06,
      "loss": 0.0113,
      "step": 302
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.147058823529411e-06,
      "loss": 0.0109,
      "step": 303
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.098039215686274e-06,
      "loss": 0.0112,
      "step": 304
    },
    {
      "epoch": 1.5,
      "learning_rate": 5.049019607843137e-06,
      "loss": 0.0111,
      "step": 305
    },
    {
      "epoch": 1.5,
      "learning_rate": 5e-06,
      "loss": 0.0116,
      "step": 306
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.9509803921568634e-06,
      "loss": 0.0112,
      "step": 307
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.901960784313726e-06,
      "loss": 0.0113,
      "step": 308
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.852941176470589e-06,
      "loss": 0.011,
      "step": 309
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.803921568627452e-06,
      "loss": 0.0105,
      "step": 310
    },
    {
      "epoch": 1.52,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.012045690789818764,
      "eval_runtime": 45.2182,
      "eval_samples_per_second": 9.2,
      "eval_steps_per_second": 0.575,
      "step": 310
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.754901960784314e-06,
      "loss": 0.0105,
      "step": 311
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.705882352941177e-06,
      "loss": 0.0113,
      "step": 312
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.65686274509804e-06,
      "loss": 0.011,
      "step": 313
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.607843137254902e-06,
      "loss": 0.0113,
      "step": 314
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.558823529411765e-06,
      "loss": 0.011,
      "step": 315
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.509803921568628e-06,
      "loss": 0.011,
      "step": 316
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.460784313725491e-06,
      "loss": 0.0105,
      "step": 317
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.411764705882353e-06,
      "loss": 0.0111,
      "step": 318
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.3627450980392164e-06,
      "loss": 0.0113,
      "step": 319
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.313725490196079e-06,
      "loss": 0.0113,
      "step": 320
    },
    {
      "epoch": 1.57,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.011651783250272274,
      "eval_runtime": 45.4996,
      "eval_samples_per_second": 9.143,
      "eval_steps_per_second": 0.571,
      "step": 320
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.264705882352942e-06,
      "loss": 0.011,
      "step": 321
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.215686274509805e-06,
      "loss": 0.3293,
      "step": 322
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.0109,
      "step": 323
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.11764705882353e-06,
      "loss": 0.0112,
      "step": 324
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.068627450980392e-06,
      "loss": 0.0109,
      "step": 325
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.019607843137255e-06,
      "loss": 0.011,
      "step": 326
    },
    {
      "epoch": 1.6,
      "learning_rate": 3.970588235294118e-06,
      "loss": 0.0113,
      "step": 327
    },
    {
      "epoch": 1.61,
      "learning_rate": 3.92156862745098e-06,
      "loss": 0.0108,
      "step": 328
    },
    {
      "epoch": 1.61,
      "learning_rate": 3.872549019607843e-06,
      "loss": 0.0114,
      "step": 329
    },
    {
      "epoch": 1.62,
      "learning_rate": 3.8235294117647055e-06,
      "loss": 0.011,
      "step": 330
    },
    {
      "epoch": 1.62,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.01183410082012415,
      "eval_runtime": 45.2181,
      "eval_samples_per_second": 9.2,
      "eval_steps_per_second": 0.575,
      "step": 330
    },
    {
      "epoch": 1.62,
      "learning_rate": 3.774509803921569e-06,
      "loss": 0.0111,
      "step": 331
    },
    {
      "epoch": 1.63,
      "learning_rate": 3.7254901960784316e-06,
      "loss": 0.0114,
      "step": 332
    },
    {
      "epoch": 1.63,
      "learning_rate": 3.6764705882352946e-06,
      "loss": 0.0115,
      "step": 333
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.6274509803921573e-06,
      "loss": 0.0111,
      "step": 334
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.57843137254902e-06,
      "loss": 0.0112,
      "step": 335
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.529411764705883e-06,
      "loss": 0.0109,
      "step": 336
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.480392156862745e-06,
      "loss": 0.0108,
      "step": 337
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.431372549019608e-06,
      "loss": 0.0111,
      "step": 338
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.382352941176471e-06,
      "loss": 0.011,
      "step": 339
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0106,
      "step": 340
    },
    {
      "epoch": 1.67,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.011788716539740562,
      "eval_runtime": 45.3933,
      "eval_samples_per_second": 9.164,
      "eval_steps_per_second": 0.573,
      "step": 340
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.2843137254901964e-06,
      "loss": 0.0111,
      "step": 341
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.2352941176470594e-06,
      "loss": 0.0114,
      "step": 342
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.1862745098039216e-06,
      "loss": 0.0109,
      "step": 343
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.1372549019607846e-06,
      "loss": 0.0112,
      "step": 344
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.0882352941176476e-06,
      "loss": 0.011,
      "step": 345
    },
    {
      "epoch": 1.7,
      "learning_rate": 3.03921568627451e-06,
      "loss": 0.0109,
      "step": 346
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.990196078431373e-06,
      "loss": 0.011,
      "step": 347
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 0.0112,
      "step": 348
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.8921568627450985e-06,
      "loss": 0.0109,
      "step": 349
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.843137254901961e-06,
      "loss": 0.0114,
      "step": 350
    },
    {
      "epoch": 1.72,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.01162599679082632,
      "eval_runtime": 44.2014,
      "eval_samples_per_second": 9.411,
      "eval_steps_per_second": 0.588,
      "step": 350
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.7941176470588237e-06,
      "loss": 0.0106,
      "step": 351
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.7450980392156867e-06,
      "loss": 0.0109,
      "step": 352
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.696078431372549e-06,
      "loss": 0.0105,
      "step": 353
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.647058823529412e-06,
      "loss": 0.0113,
      "step": 354
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.598039215686275e-06,
      "loss": 0.0114,
      "step": 355
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.549019607843137e-06,
      "loss": 0.0108,
      "step": 356
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.5e-06,
      "loss": 0.0113,
      "step": 357
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.450980392156863e-06,
      "loss": 0.0111,
      "step": 358
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.401960784313726e-06,
      "loss": 0.0109,
      "step": 359
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 0.011,
      "step": 360
    },
    {
      "epoch": 1.76,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.011486674658954144,
      "eval_runtime": 45.5187,
      "eval_samples_per_second": 9.139,
      "eval_steps_per_second": 0.571,
      "step": 360
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.303921568627451e-06,
      "loss": 0.0107,
      "step": 361
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.254901960784314e-06,
      "loss": 0.011,
      "step": 362
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.2058823529411767e-06,
      "loss": 0.0104,
      "step": 363
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.1568627450980393e-06,
      "loss": 0.0111,
      "step": 364
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.1078431372549023e-06,
      "loss": 0.0108,
      "step": 365
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.058823529411765e-06,
      "loss": 0.0111,
      "step": 366
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.0098039215686276e-06,
      "loss": 0.0111,
      "step": 367
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.96078431372549e-06,
      "loss": 0.0114,
      "step": 368
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.9117647058823528e-06,
      "loss": 0.0107,
      "step": 369
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.8627450980392158e-06,
      "loss": 0.011,
      "step": 370
    },
    {
      "epoch": 1.81,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.011367387138307095,
      "eval_runtime": 45.9461,
      "eval_samples_per_second": 9.054,
      "eval_steps_per_second": 0.566,
      "step": 370
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.8137254901960786e-06,
      "loss": 0.0108,
      "step": 371
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.7647058823529414e-06,
      "loss": 0.0109,
      "step": 372
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.715686274509804e-06,
      "loss": 0.0106,
      "step": 373
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.0109,
      "step": 374
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.6176470588235297e-06,
      "loss": 0.0108,
      "step": 375
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.5686274509803923e-06,
      "loss": 0.0112,
      "step": 376
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.519607843137255e-06,
      "loss": 0.0111,
      "step": 377
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 0.0109,
      "step": 378
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.4215686274509805e-06,
      "loss": 0.0112,
      "step": 379
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.3725490196078434e-06,
      "loss": 0.0108,
      "step": 380
    },
    {
      "epoch": 1.86,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.011174076236784458,
      "eval_runtime": 44.8162,
      "eval_samples_per_second": 9.282,
      "eval_steps_per_second": 0.58,
      "step": 380
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.323529411764706e-06,
      "loss": 0.0111,
      "step": 381
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.2745098039215686e-06,
      "loss": 0.0111,
      "step": 382
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.2254901960784314e-06,
      "loss": 0.0112,
      "step": 383
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 0.0111,
      "step": 384
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.127450980392157e-06,
      "loss": 0.0107,
      "step": 385
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.0784313725490197e-06,
      "loss": 0.011,
      "step": 386
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.0294117647058825e-06,
      "loss": 0.0107,
      "step": 387
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.80392156862745e-07,
      "loss": 0.0107,
      "step": 388
    },
    {
      "epoch": 1.91,
      "learning_rate": 9.313725490196079e-07,
      "loss": 0.0107,
      "step": 389
    },
    {
      "epoch": 1.91,
      "learning_rate": 8.823529411764707e-07,
      "loss": 0.0106,
      "step": 390
    },
    {
      "epoch": 1.91,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.011054928414523602,
      "eval_runtime": 44.7524,
      "eval_samples_per_second": 9.296,
      "eval_steps_per_second": 0.581,
      "step": 390
    },
    {
      "epoch": 1.92,
      "learning_rate": 8.333333333333333e-07,
      "loss": 0.0108,
      "step": 391
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.843137254901962e-07,
      "loss": 0.0106,
      "step": 392
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.352941176470589e-07,
      "loss": 0.0106,
      "step": 393
    },
    {
      "epoch": 1.93,
      "learning_rate": 6.862745098039217e-07,
      "loss": 0.0113,
      "step": 394
    },
    {
      "epoch": 1.94,
      "learning_rate": 6.372549019607843e-07,
      "loss": 0.0105,
      "step": 395
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.882352941176471e-07,
      "loss": 0.0104,
      "step": 396
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.392156862745098e-07,
      "loss": 0.0108,
      "step": 397
    },
    {
      "epoch": 1.95,
      "learning_rate": 4.901960784313725e-07,
      "loss": 0.0107,
      "step": 398
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.4117647058823536e-07,
      "loss": 0.0111,
      "step": 399
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.921568627450981e-07,
      "loss": 0.0103,
      "step": 400
    },
    {
      "epoch": 1.96,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.011022184044122696,
      "eval_runtime": 44.104,
      "eval_samples_per_second": 9.432,
      "eval_steps_per_second": 0.59,
      "step": 400
    }
  ],
  "max_steps": 408,
  "num_train_epochs": 2,
  "total_flos": 4.949457736710574e+17,
  "trial_name": null,
  "trial_params": null
}