{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9910044977511245,
  "eval_steps": 20,
  "global_step": 166,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1e-06,
      "loss": 2.4137,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 2e-06,
      "loss": 2.5757,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.9999999999999997e-06,
      "loss": 2.2254,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 4e-06,
      "loss": 2.3859,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 2.2279,
      "step": 5
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.999999999999999e-06,
      "loss": 2.4677,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 7e-06,
      "loss": 2.3097,
      "step": 7
    },
    {
      "epoch": 0.1,
      "learning_rate": 8e-06,
      "loss": 2.1753,
      "step": 8
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.999999999999999e-06,
      "loss": 1.9567,
      "step": 9
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.4897,
      "step": 10
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.1e-05,
      "loss": 1.3339,
      "step": 11
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.1999999999999999e-05,
      "loss": 1.2799,
      "step": 12
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.3e-05,
      "loss": 0.941,
      "step": 13
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.4e-05,
      "loss": 0.9046,
      "step": 14
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 0.8112,
      "step": 15
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.6e-05,
      "loss": 0.8297,
      "step": 16
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.6999999999999996e-05,
      "loss": 0.7657,
      "step": 17
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.7999999999999997e-05,
      "loss": 0.8527,
      "step": 18
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.9e-05,
      "loss": 0.8213,
      "step": 19
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.767,
      "step": 20
    },
    {
      "epoch": 0.24,
      "eval_loss": 0.6342860460281372,
      "eval_runtime": 35.077,
      "eval_samples_per_second": 46.441,
      "eval_steps_per_second": 11.632,
      "step": 20
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.1e-05,
      "loss": 0.8794,
      "step": 21
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.2e-05,
      "loss": 0.7471,
      "step": 22
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.2999999999999997e-05,
      "loss": 0.8795,
      "step": 23
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.3999999999999997e-05,
      "loss": 0.7741,
      "step": 24
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.4999999999999998e-05,
      "loss": 0.774,
      "step": 25
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.6e-05,
      "loss": 0.7771,
      "step": 26
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.6999999999999996e-05,
      "loss": 0.8314,
      "step": 27
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.8e-05,
      "loss": 0.6423,
      "step": 28
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.8999999999999997e-05,
      "loss": 0.8044,
      "step": 29
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.6982,
      "step": 30
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.0999999999999995e-05,
      "loss": 0.7646,
      "step": 31
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.2e-05,
      "loss": 0.7309,
      "step": 32
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.2999999999999996e-05,
      "loss": 0.7731,
      "step": 33
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.399999999999999e-05,
      "loss": 0.7677,
      "step": 34
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.5e-05,
      "loss": 0.6812,
      "step": 35
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.5999999999999994e-05,
      "loss": 0.7012,
      "step": 36
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.7e-05,
      "loss": 0.743,
      "step": 37
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.8e-05,
      "loss": 0.7018,
      "step": 38
    },
    {
      "epoch": 0.47,
      "learning_rate": 3.9e-05,
      "loss": 0.6283,
      "step": 39
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.9999999999999996e-05,
      "loss": 0.6849,
      "step": 40
    },
    {
      "epoch": 0.48,
      "eval_loss": 0.5668678283691406,
      "eval_runtime": 35.2083,
      "eval_samples_per_second": 46.268,
      "eval_steps_per_second": 11.588,
      "step": 40
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.0999999999999994e-05,
      "loss": 0.674,
      "step": 41
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.2e-05,
      "loss": 0.6649,
      "step": 42
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.3e-05,
      "loss": 0.6876,
      "step": 43
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.4e-05,
      "loss": 0.6865,
      "step": 44
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 0.7319,
      "step": 45
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.599999999999999e-05,
      "loss": 0.6688,
      "step": 46
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.7e-05,
      "loss": 0.737,
      "step": 47
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.7999999999999994e-05,
      "loss": 0.6599,
      "step": 48
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.899999999999999e-05,
      "loss": 0.6748,
      "step": 49
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 0.7997,
      "step": 50
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.1e-05,
      "loss": 0.6429,
      "step": 51
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.2e-05,
      "loss": 0.6107,
      "step": 52
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.2999999999999994e-05,
      "loss": 0.7678,
      "step": 53
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.399999999999999e-05,
      "loss": 0.686,
      "step": 54
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.499999999999999e-05,
      "loss": 0.6825,
      "step": 55
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.6e-05,
      "loss": 0.5791,
      "step": 56
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 0.7382,
      "step": 57
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.7999999999999994e-05,
      "loss": 0.6888,
      "step": 58
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.899999999999999e-05,
      "loss": 0.6067,
      "step": 59
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.6761,
      "step": 60
    },
    {
      "epoch": 0.72,
      "eval_loss": 0.5247214436531067,
      "eval_runtime": 35.3754,
      "eval_samples_per_second": 46.049,
      "eval_steps_per_second": 11.533,
      "step": 60
    },
    {
      "epoch": 0.73,
      "learning_rate": 6.1e-05,
      "loss": 0.6388,
      "step": 61
    },
    {
      "epoch": 0.74,
      "learning_rate": 6.199999999999999e-05,
      "loss": 0.5719,
      "step": 62
    },
    {
      "epoch": 0.76,
      "learning_rate": 6.299999999999999e-05,
      "loss": 0.6878,
      "step": 63
    },
    {
      "epoch": 0.77,
      "learning_rate": 6.4e-05,
      "loss": 0.6075,
      "step": 64
    },
    {
      "epoch": 0.78,
      "learning_rate": 6.5e-05,
      "loss": 0.583,
      "step": 65
    },
    {
      "epoch": 0.79,
      "learning_rate": 6.599999999999999e-05,
      "loss": 0.6215,
      "step": 66
    },
    {
      "epoch": 0.8,
      "learning_rate": 6.699999999999999e-05,
      "loss": 0.6645,
      "step": 67
    },
    {
      "epoch": 0.82,
      "learning_rate": 6.799999999999999e-05,
      "loss": 0.6785,
      "step": 68
    },
    {
      "epoch": 0.83,
      "learning_rate": 6.9e-05,
      "loss": 0.5568,
      "step": 69
    },
    {
      "epoch": 0.84,
      "learning_rate": 7e-05,
      "loss": 0.5797,
      "step": 70
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.099999999999999e-05,
      "loss": 0.6467,
      "step": 71
    },
    {
      "epoch": 0.86,
      "learning_rate": 7.199999999999999e-05,
      "loss": 0.5555,
      "step": 72
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.3e-05,
      "loss": 0.6119,
      "step": 73
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.4e-05,
      "loss": 0.6903,
      "step": 74
    },
    {
      "epoch": 0.9,
      "learning_rate": 7.5e-05,
      "loss": 0.6461,
      "step": 75
    },
    {
      "epoch": 0.91,
      "learning_rate": 7.6e-05,
      "loss": 0.5789,
      "step": 76
    },
    {
      "epoch": 0.92,
      "learning_rate": 7.699999999999999e-05,
      "loss": 0.5349,
      "step": 77
    },
    {
      "epoch": 0.94,
      "learning_rate": 7.8e-05,
      "loss": 0.5261,
      "step": 78
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.899999999999998e-05,
      "loss": 0.6659,
      "step": 79
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.999999999999999e-05,
      "loss": 0.5534,
      "step": 80
    },
    {
      "epoch": 0.96,
      "eval_loss": 0.5044009685516357,
      "eval_runtime": 35.1756,
      "eval_samples_per_second": 46.31,
      "eval_steps_per_second": 11.599,
      "step": 80
    },
    {
      "epoch": 0.97,
      "learning_rate": 8.1e-05,
      "loss": 0.5247,
      "step": 81
    },
    {
      "epoch": 0.98,
      "learning_rate": 8.199999999999999e-05,
      "loss": 0.6016,
      "step": 82
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.3e-05,
      "loss": 0.642,
      "step": 83
    },
    {
      "epoch": 1.01,
      "learning_rate": 8.4e-05,
      "loss": 0.6376,
      "step": 84
    },
    {
      "epoch": 1.02,
      "learning_rate": 8.499999999999999e-05,
      "loss": 0.6491,
      "step": 85
    },
    {
      "epoch": 1.03,
      "learning_rate": 8.6e-05,
      "loss": 0.5976,
      "step": 86
    },
    {
      "epoch": 1.04,
      "learning_rate": 8.699999999999999e-05,
      "loss": 0.6259,
      "step": 87
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.8e-05,
      "loss": 0.515,
      "step": 88
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.9e-05,
      "loss": 0.5182,
      "step": 89
    },
    {
      "epoch": 1.08,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.4986,
      "step": 90
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.099999999999999e-05,
      "loss": 0.5622,
      "step": 91
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.199999999999999e-05,
      "loss": 0.6323,
      "step": 92
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.3e-05,
      "loss": 0.5946,
      "step": 93
    },
    {
      "epoch": 1.13,
      "learning_rate": 9.4e-05,
      "loss": 0.5888,
      "step": 94
    },
    {
      "epoch": 1.14,
      "learning_rate": 9.499999999999999e-05,
      "loss": 0.526,
      "step": 95
    },
    {
      "epoch": 1.15,
      "learning_rate": 9.599999999999999e-05,
      "loss": 0.5157,
      "step": 96
    },
    {
      "epoch": 1.16,
      "learning_rate": 9.699999999999999e-05,
      "loss": 0.4719,
      "step": 97
    },
    {
      "epoch": 1.18,
      "learning_rate": 9.799999999999998e-05,
      "loss": 0.5578,
      "step": 98
    },
    {
      "epoch": 1.19,
      "learning_rate": 9.9e-05,
      "loss": 0.5357,
      "step": 99
    },
    {
      "epoch": 1.2,
      "learning_rate": 9.999999999999999e-05,
      "loss": 0.4757,
      "step": 100
    },
    {
      "epoch": 1.2,
      "eval_loss": 0.5023330450057983,
      "eval_runtime": 35.2525,
      "eval_samples_per_second": 46.21,
      "eval_steps_per_second": 11.574,
      "step": 100
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00010099999999999999,
      "loss": 0.5517,
      "step": 101
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.000102,
      "loss": 0.4868,
      "step": 102
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00010299999999999998,
      "loss": 0.5257,
      "step": 103
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.000104,
      "loss": 0.5651,
      "step": 104
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00010499999999999999,
      "loss": 0.5424,
      "step": 105
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00010599999999999999,
      "loss": 0.5472,
      "step": 106
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.000107,
      "loss": 0.5045,
      "step": 107
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00010799999999999998,
      "loss": 0.5533,
      "step": 108
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00010899999999999999,
      "loss": 0.479,
      "step": 109
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00010999999999999998,
      "loss": 0.5794,
      "step": 110
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011099999999999999,
      "loss": 0.487,
      "step": 111
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.000112,
      "loss": 0.6611,
      "step": 112
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011299999999999998,
      "loss": 0.4638,
      "step": 113
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.5047,
      "step": 114
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.000115,
      "loss": 0.4416,
      "step": 115
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011599999999999999,
      "loss": 0.4736,
      "step": 116
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.000117,
      "loss": 0.545,
      "step": 117
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011799999999999998,
      "loss": 0.502,
      "step": 118
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00011899999999999999,
      "loss": 0.5108,
      "step": 119
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.5158,
      "step": 120
    },
    {
      "epoch": 1.44,
      "eval_loss": 0.4883132874965668,
      "eval_runtime": 35.2497,
      "eval_samples_per_second": 46.213,
      "eval_steps_per_second": 11.575,
      "step": 120
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00012099999999999999,
      "loss": 0.5845,
      "step": 121
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.000122,
      "loss": 0.52,
      "step": 122
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00012299999999999998,
      "loss": 0.4885,
      "step": 123
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00012399999999999998,
      "loss": 0.4641,
      "step": 124
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.000125,
      "loss": 0.5046,
      "step": 125
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00012599999999999997,
      "loss": 0.5195,
      "step": 126
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.000127,
      "loss": 0.512,
      "step": 127
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.000128,
      "loss": 0.4458,
      "step": 128
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.000129,
      "loss": 0.5912,
      "step": 129
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00013,
      "loss": 0.4515,
      "step": 130
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00013099999999999999,
      "loss": 0.5619,
      "step": 131
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00013199999999999998,
      "loss": 0.7071,
      "step": 132
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.000133,
      "loss": 0.5515,
      "step": 133
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00013399999999999998,
      "loss": 0.4863,
      "step": 134
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.000135,
      "loss": 0.5102,
      "step": 135
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00013599999999999997,
      "loss": 0.4338,
      "step": 136
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.000137,
      "loss": 0.5132,
      "step": 137
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.000138,
      "loss": 0.5793,
      "step": 138
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.000139,
      "loss": 0.4992,
      "step": 139
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00014,
      "loss": 0.5414,
      "step": 140
    },
    {
      "epoch": 1.68,
      "eval_loss": 0.48085713386535645,
      "eval_runtime": 35.2966,
      "eval_samples_per_second": 46.152,
      "eval_steps_per_second": 11.559,
      "step": 140
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00014099999999999998,
      "loss": 0.5303,
      "step": 141
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00014199999999999998,
      "loss": 0.4456,
      "step": 142
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00014299999999999998,
      "loss": 0.5117,
      "step": 143
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00014399999999999998,
      "loss": 0.6139,
      "step": 144
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.000145,
      "loss": 0.4346,
      "step": 145
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.000146,
      "loss": 0.5148,
      "step": 146
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.000147,
      "loss": 0.4928,
      "step": 147
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.000148,
      "loss": 0.6429,
      "step": 148
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.000149,
      "loss": 0.4687,
      "step": 149
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00015,
      "loss": 0.6071,
      "step": 150
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00015099999999999998,
      "loss": 0.5215,
      "step": 151
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.000152,
      "loss": 0.5806,
      "step": 152
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00015299999999999998,
      "loss": 0.5801,
      "step": 153
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00015399999999999998,
      "loss": 0.5104,
      "step": 154
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.000155,
      "loss": 0.5002,
      "step": 155
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.000156,
      "loss": 0.508,
      "step": 156
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.000157,
      "loss": 0.5223,
      "step": 157
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00015799999999999996,
      "loss": 0.6085,
      "step": 158
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.000159,
      "loss": 0.5328,
      "step": 159
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00015999999999999999,
      "loss": 0.4715,
      "step": 160
    },
    {
      "epoch": 1.92,
      "eval_loss": 0.47481799125671387,
      "eval_runtime": 35.1736,
      "eval_samples_per_second": 46.313,
      "eval_steps_per_second": 11.6,
      "step": 160
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00016099999999999998,
      "loss": 0.4352,
      "step": 161
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.000162,
      "loss": 0.5532,
      "step": 162
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00016299999999999998,
      "loss": 0.4916,
      "step": 163
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00016399999999999997,
      "loss": 0.4879,
      "step": 164
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.000165,
      "loss": 0.5124,
      "step": 165
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.000166,
      "loss": 0.5515,
      "step": 166
    }
  ],
  "logging_steps": 1,
  "max_steps": 249,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.9089513439895224e+18,
  "trial_name": null,
  "trial_params": null
}