{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.803921568627452,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 3.171875,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.8106,
      "step": 1
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 2.046875,
      "learning_rate": 4e-05,
      "loss": 2.7854,
      "step": 5
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 6.34375,
      "learning_rate": 8e-05,
      "loss": 2.7197,
      "step": 10
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 1.7734375,
      "learning_rate": 0.00012,
      "loss": 2.5034,
      "step": 15
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 2.5625,
      "learning_rate": 0.00016,
      "loss": 2.1943,
      "step": 20
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 1.5234375,
      "learning_rate": 0.0002,
      "loss": 1.9711,
      "step": 25
    },
    {
      "epoch": 0.9803921568627451,
      "eval_loss": 2.6221704483032227,
      "eval_runtime": 0.6383,
      "eval_samples_per_second": 15.667,
      "eval_steps_per_second": 1.567,
      "step": 25
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.9140625,
      "learning_rate": 0.00019975640502598244,
      "loss": 1.765,
      "step": 30
    },
    {
      "epoch": 1.3725490196078431,
      "grad_norm": 0.7109375,
      "learning_rate": 0.00019902680687415705,
      "loss": 1.5781,
      "step": 35
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 0.474609375,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.4939,
      "step": 40
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.7734375,
      "learning_rate": 0.0001961261695938319,
      "loss": 1.4032,
      "step": 45
    },
    {
      "epoch": 1.9607843137254903,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00019396926207859084,
      "loss": 1.3473,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.5571093559265137,
      "eval_runtime": 0.5378,
      "eval_samples_per_second": 18.595,
      "eval_steps_per_second": 1.86,
      "step": 51
    },
    {
      "epoch": 2.156862745098039,
      "grad_norm": 0.462890625,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.2973,
      "step": 55
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.3671875,
      "learning_rate": 0.00018829475928589271,
      "loss": 1.2645,
      "step": 60
    },
    {
      "epoch": 2.549019607843137,
      "grad_norm": 0.345703125,
      "learning_rate": 0.0001848048096156426,
      "loss": 1.2291,
      "step": 65
    },
    {
      "epoch": 2.7450980392156863,
      "grad_norm": 0.5859375,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.2081,
      "step": 70
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.427734375,
      "learning_rate": 0.0001766044443118978,
      "loss": 1.1845,
      "step": 75
    },
    {
      "epoch": 2.980392156862745,
      "eval_loss": 2.5049567222595215,
      "eval_runtime": 0.6655,
      "eval_samples_per_second": 15.026,
      "eval_steps_per_second": 1.503,
      "step": 76
    },
    {
      "epoch": 3.1372549019607843,
      "grad_norm": 0.43359375,
      "learning_rate": 0.0001719339800338651,
      "loss": 1.1781,
      "step": 80
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.48828125,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.142,
      "step": 85
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.35546875,
      "learning_rate": 0.0001615661475325658,
      "loss": 1.1494,
      "step": 90
    },
    {
      "epoch": 3.7254901960784315,
      "grad_norm": 0.33203125,
      "learning_rate": 0.0001559192903470747,
      "loss": 1.1512,
      "step": 95
    },
    {
      "epoch": 3.9215686274509802,
      "grad_norm": 0.431640625,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.1242,
      "step": 100
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.5088963508605957,
      "eval_runtime": 0.5376,
      "eval_samples_per_second": 18.602,
      "eval_steps_per_second": 1.86,
      "step": 102
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 0.390625,
      "learning_rate": 0.00014383711467890774,
      "loss": 1.1068,
      "step": 105
    },
    {
      "epoch": 4.313725490196078,
      "grad_norm": 0.470703125,
      "learning_rate": 0.00013746065934159123,
      "loss": 1.0975,
      "step": 110
    },
    {
      "epoch": 4.509803921568627,
      "grad_norm": 0.52734375,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0827,
      "step": 115
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 0.435546875,
      "learning_rate": 0.00012419218955996676,
      "loss": 1.0938,
      "step": 120
    },
    {
      "epoch": 4.901960784313726,
      "grad_norm": 0.494140625,
      "learning_rate": 0.00011736481776669306,
      "loss": 1.0937,
      "step": 125
    },
    {
      "epoch": 4.980392156862745,
      "eval_loss": 2.523869276046753,
      "eval_runtime": 0.6835,
      "eval_samples_per_second": 14.632,
      "eval_steps_per_second": 1.463,
      "step": 127
    },
    {
      "epoch": 5.098039215686274,
      "grad_norm": 0.376953125,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.0747,
      "step": 130
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 0.39453125,
      "learning_rate": 0.00010348994967025012,
      "loss": 1.0627,
      "step": 135
    },
    {
      "epoch": 5.490196078431373,
      "grad_norm": 0.453125,
      "learning_rate": 9.651005032974994e-05,
      "loss": 1.0485,
      "step": 140
    },
    {
      "epoch": 5.686274509803922,
      "grad_norm": 0.470703125,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.0543,
      "step": 145
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.431640625,
      "learning_rate": 8.263518223330697e-05,
      "loss": 1.0632,
      "step": 150
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.5274596214294434,
      "eval_runtime": 0.5589,
      "eval_samples_per_second": 17.893,
      "eval_steps_per_second": 1.789,
      "step": 153
    },
    {
      "epoch": 6.078431372549019,
      "grad_norm": 0.55078125,
      "learning_rate": 7.580781044003324e-05,
      "loss": 1.0488,
      "step": 155
    },
    {
      "epoch": 6.2745098039215685,
      "grad_norm": 0.55078125,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.0318,
      "step": 160
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 0.423828125,
      "learning_rate": 6.25393406584088e-05,
      "loss": 1.027,
      "step": 165
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.5078125,
      "learning_rate": 5.616288532109225e-05,
      "loss": 1.0391,
      "step": 170
    },
    {
      "epoch": 6.862745098039216,
      "grad_norm": 0.412109375,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.0377,
      "step": 175
    },
    {
      "epoch": 6.980392156862745,
      "eval_loss": 2.5316176414489746,
      "eval_runtime": 0.6547,
      "eval_samples_per_second": 15.274,
      "eval_steps_per_second": 1.527,
      "step": 178
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.40625,
      "learning_rate": 4.4080709652925336e-05,
      "loss": 1.0217,
      "step": 180
    },
    {
      "epoch": 7.254901960784314,
      "grad_norm": 0.462890625,
      "learning_rate": 3.843385246743417e-05,
      "loss": 1.0203,
      "step": 185
    },
    {
      "epoch": 7.450980392156863,
      "grad_norm": 0.384765625,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.0188,
      "step": 190
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 0.396484375,
      "learning_rate": 2.8066019966134904e-05,
      "loss": 1.0165,
      "step": 195
    },
    {
      "epoch": 7.8431372549019605,
      "grad_norm": 0.390625,
      "learning_rate": 2.339555568810221e-05,
      "loss": 1.0278,
      "step": 200
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.53991961479187,
      "eval_runtime": 0.5393,
      "eval_samples_per_second": 18.541,
      "eval_steps_per_second": 1.854,
      "step": 204
    },
    {
      "epoch": 8.03921568627451,
      "grad_norm": 0.40234375,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.0104,
      "step": 205
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 0.41015625,
      "learning_rate": 1.5195190384357404e-05,
      "loss": 1.0056,
      "step": 210
    },
    {
      "epoch": 8.431372549019608,
      "grad_norm": 0.392578125,
      "learning_rate": 1.1705240714107302e-05,
      "loss": 1.0218,
      "step": 215
    },
    {
      "epoch": 8.627450980392156,
      "grad_norm": 0.421875,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.0136,
      "step": 220
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 0.365234375,
      "learning_rate": 6.030737921409169e-06,
      "loss": 1.0176,
      "step": 225
    },
    {
      "epoch": 8.980392156862745,
      "eval_loss": 2.542208671569824,
      "eval_runtime": 0.6862,
      "eval_samples_per_second": 14.574,
      "eval_steps_per_second": 1.457,
      "step": 229
    },
    {
      "epoch": 9.019607843137255,
      "grad_norm": 0.3671875,
      "learning_rate": 3.873830406168111e-06,
      "loss": 1.0092,
      "step": 230
    },
    {
      "epoch": 9.215686274509803,
      "grad_norm": 0.384765625,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.0084,
      "step": 235
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 0.34765625,
      "learning_rate": 9.731931258429638e-07,
      "loss": 1.0208,
      "step": 240
    },
    {
      "epoch": 9.607843137254902,
      "grad_norm": 0.388671875,
      "learning_rate": 2.4359497401758024e-07,
      "loss": 1.0059,
      "step": 245
    },
    {
      "epoch": 9.803921568627452,
      "grad_norm": 0.435546875,
      "learning_rate": 0.0,
      "loss": 1.007,
      "step": 250
    },
    {
      "epoch": 9.803921568627452,
      "eval_loss": 2.5420966148376465,
      "eval_runtime": 0.5393,
      "eval_samples_per_second": 18.543,
      "eval_steps_per_second": 1.854,
      "step": 250
    },
    {
      "epoch": 9.803921568627452,
      "step": 250,
      "total_flos": 1.4684333472638566e+17,
      "train_loss": 1.2576467142105103,
      "train_runtime": 862.0118,
      "train_samples_per_second": 14.13,
      "train_steps_per_second": 0.29
    }
  ],
  "logging_steps": 5,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "total_flos": 1.4684333472638566e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}