{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 1,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 78.1366195678711,
      "learning_rate": 2.5e-05,
      "loss": 1.9894,
      "step": 1
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.55,
      "eval_loss": 1.7598272562026978,
      "eval_runtime": 1.0005,
      "eval_samples_per_second": 99.95,
      "eval_steps_per_second": 2.999,
      "step": 1
    },
    {
      "epoch": 0.4,
      "grad_norm": 73.63365936279297,
      "learning_rate": 5e-05,
      "loss": 1.8056,
      "step": 2
    },
    {
      "epoch": 0.4,
      "eval_accuracy": 0.55,
      "eval_loss": 1.6865791082382202,
      "eval_runtime": 0.9969,
      "eval_samples_per_second": 100.314,
      "eval_steps_per_second": 3.009,
      "step": 2
    },
    {
      "epoch": 0.6,
      "grad_norm": 85.16033172607422,
      "learning_rate": 4.8958333333333335e-05,
      "loss": 1.9709,
      "step": 3
    },
    {
      "epoch": 0.6,
      "eval_accuracy": 0.55,
      "eval_loss": 1.3770341873168945,
      "eval_runtime": 1.0002,
      "eval_samples_per_second": 99.978,
      "eval_steps_per_second": 2.999,
      "step": 3
    },
    {
      "epoch": 0.8,
      "grad_norm": 69.2215347290039,
      "learning_rate": 4.791666666666667e-05,
      "loss": 1.4335,
      "step": 4
    },
    {
      "epoch": 0.8,
      "eval_accuracy": 0.54,
      "eval_loss": 1.0766552686691284,
      "eval_runtime": 0.9982,
      "eval_samples_per_second": 100.18,
      "eval_steps_per_second": 3.005,
      "step": 4
    },
    {
      "epoch": 1.0,
      "grad_norm": 69.37948608398438,
      "learning_rate": 4.6875e-05,
      "loss": 1.3065,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.49,
      "eval_loss": 0.8532812595367432,
      "eval_runtime": 0.9986,
      "eval_samples_per_second": 100.144,
      "eval_steps_per_second": 3.004,
      "step": 5
    },
    {
      "epoch": 1.2,
      "grad_norm": 15.690597534179688,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 0.8055,
      "step": 6
    },
    {
      "epoch": 1.2,
      "eval_accuracy": 0.43,
      "eval_loss": 0.8792579174041748,
      "eval_runtime": 0.9976,
      "eval_samples_per_second": 100.242,
      "eval_steps_per_second": 3.007,
      "step": 6
    },
    {
      "epoch": 1.4,
      "grad_norm": 20.13286018371582,
      "learning_rate": 4.4791666666666673e-05,
      "loss": 0.7901,
      "step": 7
    },
    {
      "epoch": 1.4,
      "eval_accuracy": 0.44,
      "eval_loss": 0.9624806046485901,
      "eval_runtime": 0.9981,
      "eval_samples_per_second": 100.193,
      "eval_steps_per_second": 3.006,
      "step": 7
    },
    {
      "epoch": 1.6,
      "grad_norm": 5.53256893157959,
      "learning_rate": 4.375e-05,
      "loss": 0.7524,
      "step": 8
    },
    {
      "epoch": 1.6,
      "eval_accuracy": 0.45,
      "eval_loss": 0.9771338105201721,
      "eval_runtime": 0.997,
      "eval_samples_per_second": 100.301,
      "eval_steps_per_second": 3.009,
      "step": 8
    },
    {
      "epoch": 1.8,
      "grad_norm": 29.057296752929688,
      "learning_rate": 4.270833333333333e-05,
      "loss": 0.7744,
      "step": 9
    },
    {
      "epoch": 1.8,
      "eval_accuracy": 0.41,
      "eval_loss": 0.9202635884284973,
      "eval_runtime": 0.997,
      "eval_samples_per_second": 100.301,
      "eval_steps_per_second": 3.009,
      "step": 9
    },
    {
      "epoch": 2.0,
      "grad_norm": 23.430646896362305,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.7863,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.44,
      "eval_loss": 0.8504493832588196,
      "eval_runtime": 0.9988,
      "eval_samples_per_second": 100.118,
      "eval_steps_per_second": 3.004,
      "step": 10
    },
    {
      "epoch": 2.2,
      "grad_norm": 17.951738357543945,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 0.6977,
      "step": 11
    },
    {
      "epoch": 2.2,
      "eval_accuracy": 0.43,
      "eval_loss": 0.8065915703773499,
      "eval_runtime": 0.9996,
      "eval_samples_per_second": 100.035,
      "eval_steps_per_second": 3.001,
      "step": 11
    },
    {
      "epoch": 2.4,
      "grad_norm": 16.09232521057129,
      "learning_rate": 3.958333333333333e-05,
      "loss": 0.75,
      "step": 12
    },
    {
      "epoch": 2.4,
      "eval_accuracy": 0.43,
      "eval_loss": 0.7995800971984863,
      "eval_runtime": 0.9964,
      "eval_samples_per_second": 100.364,
      "eval_steps_per_second": 3.011,
      "step": 12
    },
    {
      "epoch": 2.6,
      "grad_norm": 16.51948356628418,
      "learning_rate": 3.854166666666667e-05,
      "loss": 0.8325,
      "step": 13
    },
    {
      "epoch": 2.6,
      "eval_accuracy": 0.44,
      "eval_loss": 0.7968456745147705,
      "eval_runtime": 0.9962,
      "eval_samples_per_second": 100.386,
      "eval_steps_per_second": 3.012,
      "step": 13
    },
    {
      "epoch": 2.8,
      "grad_norm": 18.92729949951172,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.7324,
      "step": 14
    },
    {
      "epoch": 2.8,
      "eval_accuracy": 0.46,
      "eval_loss": 0.792890727519989,
      "eval_runtime": 0.9961,
      "eval_samples_per_second": 100.395,
      "eval_steps_per_second": 3.012,
      "step": 14
    },
    {
      "epoch": 3.0,
      "grad_norm": 8.970295906066895,
      "learning_rate": 3.6458333333333336e-05,
      "loss": 0.7882,
      "step": 15
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.43,
      "eval_loss": 0.786152184009552,
      "eval_runtime": 0.999,
      "eval_samples_per_second": 100.104,
      "eval_steps_per_second": 3.003,
      "step": 15
    },
    {
      "epoch": 3.2,
      "grad_norm": 7.676571369171143,
      "learning_rate": 3.541666666666667e-05,
      "loss": 0.7451,
      "step": 16
    },
    {
      "epoch": 3.2,
      "eval_accuracy": 0.44,
      "eval_loss": 0.785478413105011,
      "eval_runtime": 0.9973,
      "eval_samples_per_second": 100.272,
      "eval_steps_per_second": 3.008,
      "step": 16
    },
    {
      "epoch": 3.4,
      "grad_norm": 17.803117752075195,
      "learning_rate": 3.4375e-05,
      "loss": 0.7071,
      "step": 17
    },
    {
      "epoch": 3.4,
      "eval_accuracy": 0.44,
      "eval_loss": 0.7892186045646667,
      "eval_runtime": 1.0007,
      "eval_samples_per_second": 99.933,
      "eval_steps_per_second": 2.998,
      "step": 17
    },
    {
      "epoch": 3.6,
      "grad_norm": 16.301389694213867,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7665,
      "step": 18
    },
    {
      "epoch": 3.6,
      "eval_accuracy": 0.44,
      "eval_loss": 0.8022948503494263,
      "eval_runtime": 0.9993,
      "eval_samples_per_second": 100.071,
      "eval_steps_per_second": 3.002,
      "step": 18
    },
    {
      "epoch": 3.8,
      "grad_norm": 9.103254318237305,
      "learning_rate": 3.229166666666667e-05,
      "loss": 0.7503,
      "step": 19
    },
    {
      "epoch": 3.8,
      "eval_accuracy": 0.44,
      "eval_loss": 0.8114063739776611,
      "eval_runtime": 0.9942,
      "eval_samples_per_second": 100.58,
      "eval_steps_per_second": 3.017,
      "step": 19
    },
    {
      "epoch": 4.0,
      "grad_norm": 14.845060348510742,
      "learning_rate": 3.125e-05,
      "loss": 0.6844,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.47,
      "eval_loss": 0.8062010407447815,
      "eval_runtime": 0.9971,
      "eval_samples_per_second": 100.295,
      "eval_steps_per_second": 3.009,
      "step": 20
    },
    {
      "epoch": 4.2,
      "grad_norm": 19.840051651000977,
      "learning_rate": 3.0208333333333334e-05,
      "loss": 0.7454,
      "step": 21
    },
    {
      "epoch": 4.2,
      "eval_accuracy": 0.44,
      "eval_loss": 0.7904101610183716,
      "eval_runtime": 0.9973,
      "eval_samples_per_second": 100.271,
      "eval_steps_per_second": 3.008,
      "step": 21
    },
    {
      "epoch": 4.4,
      "grad_norm": 3.92164945602417,
      "learning_rate": 2.916666666666667e-05,
      "loss": 0.6977,
      "step": 22
    },
    {
      "epoch": 4.4,
      "eval_accuracy": 0.45,
      "eval_loss": 0.7847166657447815,
      "eval_runtime": 0.9986,
      "eval_samples_per_second": 100.142,
      "eval_steps_per_second": 3.004,
      "step": 22
    },
    {
      "epoch": 4.6,
      "grad_norm": 7.615128040313721,
      "learning_rate": 2.8125000000000003e-05,
      "loss": 0.7374,
      "step": 23
    },
    {
      "epoch": 4.6,
      "eval_accuracy": 0.46,
      "eval_loss": 0.7748146057128906,
      "eval_runtime": 0.9975,
      "eval_samples_per_second": 100.247,
      "eval_steps_per_second": 3.007,
      "step": 23
    },
    {
      "epoch": 4.8,
      "grad_norm": 7.336858749389648,
      "learning_rate": 2.7083333333333332e-05,
      "loss": 0.6703,
      "step": 24
    },
    {
      "epoch": 4.8,
      "eval_accuracy": 0.48,
      "eval_loss": 0.7589452266693115,
      "eval_runtime": 0.9975,
      "eval_samples_per_second": 100.247,
      "eval_steps_per_second": 3.007,
      "step": 24
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.808582305908203,
      "learning_rate": 2.604166666666667e-05,
      "loss": 0.6783,
      "step": 25
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.49,
      "eval_loss": 0.7491601705551147,
      "eval_runtime": 0.9972,
      "eval_samples_per_second": 100.279,
      "eval_steps_per_second": 3.008,
      "step": 25
    },
    {
      "epoch": 5.2,
      "grad_norm": 3.35099720954895,
      "learning_rate": 2.5e-05,
      "loss": 0.6878,
      "step": 26
    },
    {
      "epoch": 5.2,
      "eval_accuracy": 0.47,
      "eval_loss": 0.7470411062240601,
      "eval_runtime": 0.9968,
      "eval_samples_per_second": 100.316,
      "eval_steps_per_second": 3.009,
      "step": 26
    },
    {
      "epoch": 5.4,
      "grad_norm": 6.638521194458008,
      "learning_rate": 2.3958333333333334e-05,
      "loss": 0.6909,
      "step": 27
    },
    {
      "epoch": 5.4,
      "eval_accuracy": 0.48,
      "eval_loss": 0.74560546875,
      "eval_runtime": 0.9981,
      "eval_samples_per_second": 100.19,
      "eval_steps_per_second": 3.006,
      "step": 27
    },
    {
      "epoch": 5.6,
      "grad_norm": 11.796442031860352,
      "learning_rate": 2.2916666666666667e-05,
      "loss": 0.6564,
      "step": 28
    },
    {
      "epoch": 5.6,
      "eval_accuracy": 0.5,
      "eval_loss": 0.750224769115448,
      "eval_runtime": 1.0001,
      "eval_samples_per_second": 99.987,
      "eval_steps_per_second": 3.0,
      "step": 28
    },
    {
      "epoch": 5.8,
      "grad_norm": 10.697065353393555,
      "learning_rate": 2.1875e-05,
      "loss": 0.7397,
      "step": 29
    },
    {
      "epoch": 5.8,
      "eval_accuracy": 0.5,
      "eval_loss": 0.7502343654632568,
      "eval_runtime": 0.9996,
      "eval_samples_per_second": 100.035,
      "eval_steps_per_second": 3.001,
      "step": 29
    },
    {
      "epoch": 6.0,
      "grad_norm": 16.58921241760254,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 0.641,
      "step": 30
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.51,
      "eval_loss": 0.7463575601577759,
      "eval_runtime": 0.9995,
      "eval_samples_per_second": 100.051,
      "eval_steps_per_second": 3.002,
      "step": 30
    },
    {
      "epoch": 6.2,
      "grad_norm": 7.851564407348633,
      "learning_rate": 1.9791666666666665e-05,
      "loss": 0.6272,
      "step": 31
    },
    {
      "epoch": 6.2,
      "eval_accuracy": 0.52,
      "eval_loss": 0.7356445789337158,
      "eval_runtime": 0.9987,
      "eval_samples_per_second": 100.129,
      "eval_steps_per_second": 3.004,
      "step": 31
    },
    {
      "epoch": 6.4,
      "grad_norm": 11.272120475769043,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.6667,
      "step": 32
    },
    {
      "epoch": 6.4,
      "eval_accuracy": 0.51,
      "eval_loss": 0.7220800518989563,
      "eval_runtime": 0.9996,
      "eval_samples_per_second": 100.044,
      "eval_steps_per_second": 3.001,
      "step": 32
    },
    {
      "epoch": 6.6,
      "grad_norm": 4.333158493041992,
      "learning_rate": 1.7708333333333335e-05,
      "loss": 0.6604,
      "step": 33
    },
    {
      "epoch": 6.6,
      "eval_accuracy": 0.5,
      "eval_loss": 0.7124804854393005,
      "eval_runtime": 0.997,
      "eval_samples_per_second": 100.298,
      "eval_steps_per_second": 3.009,
      "step": 33
    },
    {
      "epoch": 6.8,
      "grad_norm": 4.1158127784729,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.6196,
      "step": 34
    },
    {
      "epoch": 6.8,
      "eval_accuracy": 0.51,
      "eval_loss": 0.7032715082168579,
      "eval_runtime": 0.9988,
      "eval_samples_per_second": 100.122,
      "eval_steps_per_second": 3.004,
      "step": 34
    },
    {
      "epoch": 7.0,
      "grad_norm": 12.1450834274292,
      "learning_rate": 1.5625e-05,
      "loss": 0.6995,
      "step": 35
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.52,
      "eval_loss": 0.6988573670387268,
      "eval_runtime": 0.9973,
      "eval_samples_per_second": 100.27,
      "eval_steps_per_second": 3.008,
      "step": 35
    },
    {
      "epoch": 7.2,
      "grad_norm": 5.940031051635742,
      "learning_rate": 1.4583333333333335e-05,
      "loss": 0.6227,
      "step": 36
    },
    {
      "epoch": 7.2,
      "eval_accuracy": 0.52,
      "eval_loss": 0.6967969536781311,
      "eval_runtime": 0.9976,
      "eval_samples_per_second": 100.24,
      "eval_steps_per_second": 3.007,
      "step": 36
    },
    {
      "epoch": 7.4,
      "grad_norm": 17.160533905029297,
      "learning_rate": 1.3541666666666666e-05,
      "loss": 0.6482,
      "step": 37
    },
    {
      "epoch": 7.4,
      "eval_accuracy": 0.54,
      "eval_loss": 0.6968165636062622,
      "eval_runtime": 0.9978,
      "eval_samples_per_second": 100.221,
      "eval_steps_per_second": 3.007,
      "step": 37
    },
    {
      "epoch": 7.6,
      "grad_norm": 2.506211757659912,
      "learning_rate": 1.25e-05,
      "loss": 0.6068,
      "step": 38
    },
    {
      "epoch": 7.6,
      "eval_accuracy": 0.57,
      "eval_loss": 0.6994236707687378,
      "eval_runtime": 0.9998,
      "eval_samples_per_second": 100.024,
      "eval_steps_per_second": 3.001,
      "step": 38
    },
    {
      "epoch": 7.8,
      "grad_norm": 4.562036991119385,
      "learning_rate": 1.1458333333333333e-05,
      "loss": 0.6346,
      "step": 39
    },
    {
      "epoch": 7.8,
      "eval_accuracy": 0.59,
      "eval_loss": 0.6964159607887268,
      "eval_runtime": 0.9979,
      "eval_samples_per_second": 100.214,
      "eval_steps_per_second": 3.006,
      "step": 39
    },
    {
      "epoch": 8.0,
      "grad_norm": 19.430461883544922,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 0.6444,
      "step": 40
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.59,
      "eval_loss": 0.691386878490448,
      "eval_runtime": 0.9975,
      "eval_samples_per_second": 100.251,
      "eval_steps_per_second": 3.008,
      "step": 40
    },
    {
      "epoch": 8.2,
      "grad_norm": 12.345283508300781,
      "learning_rate": 9.375000000000001e-06,
      "loss": 0.6287,
      "step": 41
    },
    {
      "epoch": 8.2,
      "eval_accuracy": 0.6,
      "eval_loss": 0.6884568929672241,
      "eval_runtime": 0.9962,
      "eval_samples_per_second": 100.38,
      "eval_steps_per_second": 3.011,
      "step": 41
    },
    {
      "epoch": 8.4,
      "grad_norm": 14.297842025756836,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.6198,
      "step": 42
    },
    {
      "epoch": 8.4,
      "eval_accuracy": 0.58,
      "eval_loss": 0.6812109351158142,
      "eval_runtime": 0.998,
      "eval_samples_per_second": 100.196,
      "eval_steps_per_second": 3.006,
      "step": 42
    },
    {
      "epoch": 8.6,
      "grad_norm": 4.835755825042725,
      "learning_rate": 7.2916666666666674e-06,
      "loss": 0.6104,
      "step": 43
    },
    {
      "epoch": 8.6,
      "eval_accuracy": 0.59,
      "eval_loss": 0.6766307353973389,
      "eval_runtime": 1.0003,
      "eval_samples_per_second": 99.967,
      "eval_steps_per_second": 2.999,
      "step": 43
    },
    {
      "epoch": 8.8,
      "grad_norm": 7.960282325744629,
      "learning_rate": 6.25e-06,
      "loss": 0.6007,
      "step": 44
    },
    {
      "epoch": 8.8,
      "eval_accuracy": 0.6,
      "eval_loss": 0.6741991639137268,
      "eval_runtime": 0.9973,
      "eval_samples_per_second": 100.273,
      "eval_steps_per_second": 3.008,
      "step": 44
    },
    {
      "epoch": 9.0,
      "grad_norm": 6.917936325073242,
      "learning_rate": 5.208333333333334e-06,
      "loss": 0.6092,
      "step": 45
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.61,
      "eval_loss": 0.6733300685882568,
      "eval_runtime": 0.9989,
      "eval_samples_per_second": 100.109,
      "eval_steps_per_second": 3.003,
      "step": 45
    },
    {
      "epoch": 9.2,
      "grad_norm": 2.6899542808532715,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.6177,
      "step": 46
    },
    {
      "epoch": 9.2,
      "eval_accuracy": 0.6,
      "eval_loss": 0.6735841631889343,
      "eval_runtime": 1.0001,
      "eval_samples_per_second": 99.991,
      "eval_steps_per_second": 3.0,
      "step": 46
    },
    {
      "epoch": 9.4,
      "grad_norm": 3.7043120861053467,
      "learning_rate": 3.125e-06,
      "loss": 0.6172,
      "step": 47
    },
    {
      "epoch": 9.4,
      "eval_accuracy": 0.6,
      "eval_loss": 0.673154354095459,
      "eval_runtime": 0.9971,
      "eval_samples_per_second": 100.293,
      "eval_steps_per_second": 3.009,
      "step": 47
    },
    {
      "epoch": 9.6,
      "grad_norm": 4.5208659172058105,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 0.6193,
      "step": 48
    },
    {
      "epoch": 9.6,
      "eval_accuracy": 0.61,
      "eval_loss": 0.6734569072723389,
      "eval_runtime": 0.9958,
      "eval_samples_per_second": 100.42,
      "eval_steps_per_second": 3.013,
      "step": 48
    },
    {
      "epoch": 9.8,
      "grad_norm": 10.0933837890625,
      "learning_rate": 1.0416666666666667e-06,
      "loss": 0.5712,
      "step": 49
    },
    {
      "epoch": 9.8,
      "eval_accuracy": 0.61,
      "eval_loss": 0.6726464629173279,
      "eval_runtime": 0.9963,
      "eval_samples_per_second": 100.375,
      "eval_steps_per_second": 3.011,
      "step": 49
    },
    {
      "epoch": 10.0,
      "grad_norm": 3.2562851905822754,
      "learning_rate": 0.0,
      "loss": 0.5908,
      "step": 50
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.6,
      "eval_loss": 0.6712987422943115,
      "eval_runtime": 0.9969,
      "eval_samples_per_second": 100.308,
      "eval_steps_per_second": 3.009,
      "step": 50
    },
    {
      "epoch": 10.0,
      "step": 50,
      "total_flos": 27858578374656.0,
      "train_loss": 0.7865762293338776,
      "train_runtime": 193.0614,
      "train_samples_per_second": 20.719,
      "train_steps_per_second": 0.259
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 27858578374656.0,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}