{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0253164556962027,
  "eval_steps": 20,
  "global_step": 243,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 0.6625,
      "step": 1
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.9669284820556641,
      "eval_runtime": 22.2599,
      "eval_samples_per_second": 11.231,
      "eval_steps_per_second": 2.83,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.666666e-07,
      "loss": 0.7012,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.3333332e-06,
      "loss": 0.6954,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9999997999999996e-06,
      "loss": 0.6383,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.6666664e-06,
      "loss": 0.6993,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 3.3333329999999998e-06,
      "loss": 0.6388,
      "step": 6
    },
    {
      "epoch": 0.09,
      "learning_rate": 3.999999599999999e-06,
      "loss": 0.6847,
      "step": 7
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.6666662e-06,
      "loss": 0.6973,
      "step": 8
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.3333328e-06,
      "loss": 0.703,
      "step": 9
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.999999399999999e-06,
      "loss": 0.6826,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 6.6666659999999995e-06,
      "loss": 0.6939,
      "step": 11
    },
    {
      "epoch": 0.15,
      "learning_rate": 7.333332599999999e-06,
      "loss": 0.6879,
      "step": 12
    },
    {
      "epoch": 0.16,
      "learning_rate": 7.999999199999998e-06,
      "loss": 0.687,
      "step": 13
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.6666658e-06,
      "loss": 0.6471,
      "step": 14
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.3333324e-06,
      "loss": 0.6658,
      "step": 15
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.999998999999998e-06,
      "loss": 0.6669,
      "step": 16
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.06666656e-05,
      "loss": 0.6451,
      "step": 17
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.13333322e-05,
      "loss": 0.6558,
      "step": 18
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.1999998799999998e-05,
      "loss": 0.6714,
      "step": 19
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.26666654e-05,
      "loss": 0.7123,
      "step": 20
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.9579811096191406,
      "eval_runtime": 22.7924,
      "eval_samples_per_second": 10.969,
      "eval_steps_per_second": 2.764,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.3333331999999999e-05,
      "loss": 0.6388,
      "step": 21
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.3999998599999999e-05,
      "loss": 0.6355,
      "step": 22
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.4666665199999999e-05,
      "loss": 0.6237,
      "step": 23
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.53333318e-05,
      "loss": 0.6214,
      "step": 24
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.5999998399999997e-05,
      "loss": 0.6045,
      "step": 25
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.6666665e-05,
      "loss": 0.671,
      "step": 26
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.73333316e-05,
      "loss": 0.6042,
      "step": 27
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.7999998199999998e-05,
      "loss": 0.6722,
      "step": 28
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.86666648e-05,
      "loss": 0.6132,
      "step": 29
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.9333331399999998e-05,
      "loss": 0.5651,
      "step": 30
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.9999997999999996e-05,
      "loss": 0.6525,
      "step": 31
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.0666664599999998e-05,
      "loss": 0.6532,
      "step": 32
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.13333312e-05,
      "loss": 0.6167,
      "step": 33
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.1999997799999997e-05,
      "loss": 0.607,
      "step": 34
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.26666644e-05,
      "loss": 0.5843,
      "step": 35
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.3333330999999997e-05,
      "loss": 0.6093,
      "step": 36
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.3999997599999995e-05,
      "loss": 0.5967,
      "step": 37
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.4666664199999997e-05,
      "loss": 0.6015,
      "step": 38
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.53333308e-05,
      "loss": 0.6263,
      "step": 39
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.59999974e-05,
      "loss": 0.5923,
      "step": 40
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.9467829465866089,
      "eval_runtime": 22.6276,
      "eval_samples_per_second": 11.048,
      "eval_steps_per_second": 2.784,
      "step": 40
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.6666663999999998e-05,
      "loss": 0.5801,
      "step": 41
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.7333330599999996e-05,
      "loss": 0.576,
      "step": 42
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.7999997199999998e-05,
      "loss": 0.6317,
      "step": 43
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.8666663799999996e-05,
      "loss": 0.5874,
      "step": 44
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.9333330399999998e-05,
      "loss": 0.6109,
      "step": 45
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.9999997e-05,
      "loss": 0.5274,
      "step": 46
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.06666636e-05,
      "loss": 0.5698,
      "step": 47
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.133333019999999e-05,
      "loss": 0.544,
      "step": 48
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.1999996799999994e-05,
      "loss": 0.5586,
      "step": 49
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.2666663399999995e-05,
      "loss": 0.5666,
      "step": 50
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.333333e-05,
      "loss": 0.586,
      "step": 51
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.39999966e-05,
      "loss": 0.6225,
      "step": 52
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.46666632e-05,
      "loss": 0.5588,
      "step": 53
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.53333298e-05,
      "loss": 0.5705,
      "step": 54
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.5999996399999996e-05,
      "loss": 0.5628,
      "step": 55
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.6666663e-05,
      "loss": 0.5868,
      "step": 56
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.73333296e-05,
      "loss": 0.5583,
      "step": 57
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.7999996199999994e-05,
      "loss": 0.5858,
      "step": 58
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.8666662799999996e-05,
      "loss": 0.5756,
      "step": 59
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.93333294e-05,
      "loss": 0.5822,
      "step": 60
    },
    {
      "epoch": 0.76,
      "eval_loss": 0.9389348030090332,
      "eval_runtime": 22.5892,
      "eval_samples_per_second": 11.067,
      "eval_steps_per_second": 2.789,
      "step": 60
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.999999599999999e-05,
      "loss": 0.5667,
      "step": 61
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.0666662599999994e-05,
      "loss": 0.5616,
      "step": 62
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.1333329199999995e-05,
      "loss": 0.5678,
      "step": 63
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.19999958e-05,
      "loss": 0.5514,
      "step": 64
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.26666624e-05,
      "loss": 0.5732,
      "step": 65
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.3333329e-05,
      "loss": 0.5794,
      "step": 66
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.3999995599999995e-05,
      "loss": 0.5582,
      "step": 67
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.4666662199999996e-05,
      "loss": 0.5575,
      "step": 68
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.53333288e-05,
      "loss": 0.5558,
      "step": 69
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.599999539999999e-05,
      "loss": 0.5707,
      "step": 70
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.6666661999999994e-05,
      "loss": 0.54,
      "step": 71
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.7333328599999996e-05,
      "loss": 0.5435,
      "step": 72
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.799999519999999e-05,
      "loss": 0.5649,
      "step": 73
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.866666179999999e-05,
      "loss": 0.5617,
      "step": 74
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.9333328399999994e-05,
      "loss": 0.5651,
      "step": 75
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.9999994999999995e-05,
      "loss": 0.5113,
      "step": 76
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.06666616e-05,
      "loss": 0.5389,
      "step": 77
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.13333282e-05,
      "loss": 0.5162,
      "step": 78
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.19999948e-05,
      "loss": 0.5397,
      "step": 79
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.2666661399999995e-05,
      "loss": 0.5794,
      "step": 80
    },
    {
      "epoch": 1.01,
      "eval_loss": 0.9314417839050293,
      "eval_runtime": 22.7753,
      "eval_samples_per_second": 10.977,
      "eval_steps_per_second": 2.766,
      "step": 80
    },
    {
      "epoch": 1.03,
      "learning_rate": 5.3333327999999996e-05,
      "loss": 0.5263,
      "step": 81
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.39999946e-05,
      "loss": 0.5141,
      "step": 82
    },
    {
      "epoch": 1.03,
      "learning_rate": 5.466666119999999e-05,
      "loss": 0.5573,
      "step": 83
    },
    {
      "epoch": 1.04,
      "learning_rate": 5.5333327799999994e-05,
      "loss": 0.5629,
      "step": 84
    },
    {
      "epoch": 1.05,
      "learning_rate": 5.5999994399999996e-05,
      "loss": 0.5043,
      "step": 85
    },
    {
      "epoch": 1.06,
      "learning_rate": 5.666666099999999e-05,
      "loss": 0.562,
      "step": 86
    },
    {
      "epoch": 1.08,
      "learning_rate": 5.733332759999999e-05,
      "loss": 0.4978,
      "step": 87
    },
    {
      "epoch": 1.09,
      "learning_rate": 5.7999994199999994e-05,
      "loss": 0.5502,
      "step": 88
    },
    {
      "epoch": 1.1,
      "learning_rate": 5.8666660799999995e-05,
      "loss": 0.5499,
      "step": 89
    },
    {
      "epoch": 1.11,
      "learning_rate": 5.93333274e-05,
      "loss": 0.5547,
      "step": 90
    },
    {
      "epoch": 1.13,
      "learning_rate": 5.9999994e-05,
      "loss": 0.5452,
      "step": 91
    },
    {
      "epoch": 1.14,
      "learning_rate": 6.066666059999999e-05,
      "loss": 0.5544,
      "step": 92
    },
    {
      "epoch": 1.15,
      "learning_rate": 6.13333272e-05,
      "loss": 0.5483,
      "step": 93
    },
    {
      "epoch": 1.16,
      "learning_rate": 6.19999938e-05,
      "loss": 0.5641,
      "step": 94
    },
    {
      "epoch": 1.18,
      "learning_rate": 6.266666039999998e-05,
      "loss": 0.5316,
      "step": 95
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.333332699999999e-05,
      "loss": 0.526,
      "step": 96
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.399999359999999e-05,
      "loss": 0.5443,
      "step": 97
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.46666602e-05,
      "loss": 0.5111,
      "step": 98
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.533332679999999e-05,
      "loss": 0.5298,
      "step": 99
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.59999934e-05,
      "loss": 0.5431,
      "step": 100
    },
    {
      "epoch": 1.24,
      "eval_loss": 0.9199196100234985,
      "eval_runtime": 22.8496,
      "eval_samples_per_second": 10.941,
      "eval_steps_per_second": 2.757,
      "step": 100
    },
    {
      "epoch": 1.25,
      "learning_rate": 6.666666e-05,
      "loss": 0.585,
      "step": 101
    },
    {
      "epoch": 1.27,
      "learning_rate": 6.64406713220339e-05,
      "loss": 0.5143,
      "step": 102
    },
    {
      "epoch": 1.28,
      "learning_rate": 6.621468264406779e-05,
      "loss": 0.5061,
      "step": 103
    },
    {
      "epoch": 1.29,
      "learning_rate": 6.59886939661017e-05,
      "loss": 0.5098,
      "step": 104
    },
    {
      "epoch": 1.3,
      "learning_rate": 6.576270528813559e-05,
      "loss": 0.5188,
      "step": 105
    },
    {
      "epoch": 1.32,
      "learning_rate": 6.553671661016948e-05,
      "loss": 0.5005,
      "step": 106
    },
    {
      "epoch": 1.33,
      "learning_rate": 6.531072793220339e-05,
      "loss": 0.5709,
      "step": 107
    },
    {
      "epoch": 1.34,
      "learning_rate": 6.508473925423728e-05,
      "loss": 0.4985,
      "step": 108
    },
    {
      "epoch": 1.35,
      "learning_rate": 6.485875057627117e-05,
      "loss": 0.5767,
      "step": 109
    },
    {
      "epoch": 1.37,
      "learning_rate": 6.463276189830508e-05,
      "loss": 0.517,
      "step": 110
    },
    {
      "epoch": 1.38,
      "learning_rate": 6.440677322033897e-05,
      "loss": 0.4759,
      "step": 111
    },
    {
      "epoch": 1.39,
      "learning_rate": 6.418078454237288e-05,
      "loss": 0.5536,
      "step": 112
    },
    {
      "epoch": 1.41,
      "learning_rate": 6.395479586440677e-05,
      "loss": 0.5657,
      "step": 113
    },
    {
      "epoch": 1.42,
      "learning_rate": 6.372880718644068e-05,
      "loss": 0.525,
      "step": 114
    },
    {
      "epoch": 1.43,
      "learning_rate": 6.350281850847457e-05,
      "loss": 0.5113,
      "step": 115
    },
    {
      "epoch": 1.44,
      "learning_rate": 6.327682983050848e-05,
      "loss": 0.4869,
      "step": 116
    },
    {
      "epoch": 1.46,
      "learning_rate": 6.305084115254237e-05,
      "loss": 0.5074,
      "step": 117
    },
    {
      "epoch": 1.47,
      "learning_rate": 6.282485247457626e-05,
      "loss": 0.5043,
      "step": 118
    },
    {
      "epoch": 1.48,
      "learning_rate": 6.259886379661017e-05,
      "loss": 0.5116,
      "step": 119
    },
    {
      "epoch": 1.49,
      "learning_rate": 6.237287511864406e-05,
      "loss": 0.5317,
      "step": 120
    },
    {
      "epoch": 1.49,
      "eval_loss": 0.9122854471206665,
      "eval_runtime": 22.8969,
      "eval_samples_per_second": 10.919,
      "eval_steps_per_second": 2.751,
      "step": 120
    },
    {
      "epoch": 1.51,
      "learning_rate": 6.214688644067795e-05,
      "loss": 0.5049,
      "step": 121
    },
    {
      "epoch": 1.52,
      "learning_rate": 6.192089776271186e-05,
      "loss": 0.496,
      "step": 122
    },
    {
      "epoch": 1.53,
      "learning_rate": 6.169490908474575e-05,
      "loss": 0.4951,
      "step": 123
    },
    {
      "epoch": 1.54,
      "learning_rate": 6.146892040677966e-05,
      "loss": 0.5489,
      "step": 124
    },
    {
      "epoch": 1.56,
      "learning_rate": 6.124293172881355e-05,
      "loss": 0.5071,
      "step": 125
    },
    {
      "epoch": 1.57,
      "learning_rate": 6.1016943050847455e-05,
      "loss": 0.5312,
      "step": 126
    },
    {
      "epoch": 1.58,
      "learning_rate": 6.079095437288135e-05,
      "loss": 0.4442,
      "step": 127
    },
    {
      "epoch": 1.59,
      "learning_rate": 6.056496569491525e-05,
      "loss": 0.4944,
      "step": 128
    },
    {
      "epoch": 1.61,
      "learning_rate": 6.033897701694915e-05,
      "loss": 0.4615,
      "step": 129
    },
    {
      "epoch": 1.62,
      "learning_rate": 6.0112988338983045e-05,
      "loss": 0.4855,
      "step": 130
    },
    {
      "epoch": 1.63,
      "learning_rate": 5.9886999661016945e-05,
      "loss": 0.4862,
      "step": 131
    },
    {
      "epoch": 1.65,
      "learning_rate": 5.9661010983050844e-05,
      "loss": 0.521,
      "step": 132
    },
    {
      "epoch": 1.66,
      "learning_rate": 5.943502230508474e-05,
      "loss": 0.5537,
      "step": 133
    },
    {
      "epoch": 1.67,
      "learning_rate": 5.9209033627118636e-05,
      "loss": 0.4828,
      "step": 134
    },
    {
      "epoch": 1.68,
      "learning_rate": 5.898304494915254e-05,
      "loss": 0.4932,
      "step": 135
    },
    {
      "epoch": 1.7,
      "learning_rate": 5.8757056271186434e-05,
      "loss": 0.4909,
      "step": 136
    },
    {
      "epoch": 1.71,
      "learning_rate": 5.8531067593220333e-05,
      "loss": 0.5211,
      "step": 137
    },
    {
      "epoch": 1.72,
      "learning_rate": 5.830507891525423e-05,
      "loss": 0.4851,
      "step": 138
    },
    {
      "epoch": 1.73,
      "learning_rate": 5.807909023728813e-05,
      "loss": 0.5172,
      "step": 139
    },
    {
      "epoch": 1.75,
      "learning_rate": 5.7853101559322024e-05,
      "loss": 0.5038,
      "step": 140
    },
    {
      "epoch": 1.75,
      "eval_loss": 0.9127333760261536,
      "eval_runtime": 22.9168,
      "eval_samples_per_second": 10.909,
      "eval_steps_per_second": 2.749,
      "step": 140
    },
    {
      "epoch": 1.76,
      "learning_rate": 5.762711288135593e-05,
      "loss": 0.5116,
      "step": 141
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.740112420338982e-05,
      "loss": 0.5009,
      "step": 142
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.717513552542372e-05,
      "loss": 0.4835,
      "step": 143
    },
    {
      "epoch": 1.8,
      "learning_rate": 5.694914684745762e-05,
      "loss": 0.4917,
      "step": 144
    },
    {
      "epoch": 1.81,
      "learning_rate": 5.672315816949152e-05,
      "loss": 0.4873,
      "step": 145
    },
    {
      "epoch": 1.82,
      "learning_rate": 5.649716949152541e-05,
      "loss": 0.5094,
      "step": 146
    },
    {
      "epoch": 1.84,
      "learning_rate": 5.627118081355932e-05,
      "loss": 0.5193,
      "step": 147
    },
    {
      "epoch": 1.85,
      "learning_rate": 5.604519213559321e-05,
      "loss": 0.4921,
      "step": 148
    },
    {
      "epoch": 1.86,
      "learning_rate": 5.581920345762711e-05,
      "loss": 0.4978,
      "step": 149
    },
    {
      "epoch": 1.87,
      "learning_rate": 5.559321477966101e-05,
      "loss": 0.4901,
      "step": 150
    },
    {
      "epoch": 1.89,
      "learning_rate": 5.536722610169491e-05,
      "loss": 0.5042,
      "step": 151
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.51412374237288e-05,
      "loss": 0.4838,
      "step": 152
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.491524874576271e-05,
      "loss": 0.485,
      "step": 153
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.46892600677966e-05,
      "loss": 0.4967,
      "step": 154
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.44632713898305e-05,
      "loss": 0.4943,
      "step": 155
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.4237282711864406e-05,
      "loss": 0.4999,
      "step": 156
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.40112940338983e-05,
      "loss": 0.4456,
      "step": 157
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.3785305355932205e-05,
      "loss": 0.4787,
      "step": 158
    },
    {
      "epoch": 1.99,
      "learning_rate": 5.35593166779661e-05,
      "loss": 0.4594,
      "step": 159
    },
    {
      "epoch": 2.0,
      "learning_rate": 5.3333327999999996e-05,
      "loss": 0.4744,
      "step": 160
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9105737805366516,
      "eval_runtime": 22.9129,
      "eval_samples_per_second": 10.911,
      "eval_steps_per_second": 2.75,
      "step": 160
    },
    {
      "epoch": 2.01,
      "learning_rate": 5.3107339322033896e-05,
      "loss": 0.5174,
      "step": 161
    },
    {
      "epoch": 2.03,
      "learning_rate": 5.2881350644067795e-05,
      "loss": 0.46,
      "step": 162
    },
    {
      "epoch": 2.01,
      "learning_rate": 5.265536196610169e-05,
      "loss": 0.4549,
      "step": 163
    },
    {
      "epoch": 2.03,
      "learning_rate": 5.242937328813559e-05,
      "loss": 0.4873,
      "step": 164
    },
    {
      "epoch": 2.04,
      "learning_rate": 5.2203384610169486e-05,
      "loss": 0.4969,
      "step": 165
    },
    {
      "epoch": 2.05,
      "learning_rate": 5.1977395932203385e-05,
      "loss": 0.4467,
      "step": 166
    },
    {
      "epoch": 2.06,
      "learning_rate": 5.1751407254237284e-05,
      "loss": 0.5028,
      "step": 167
    },
    {
      "epoch": 2.08,
      "learning_rate": 5.1525418576271184e-05,
      "loss": 0.4369,
      "step": 168
    },
    {
      "epoch": 2.09,
      "learning_rate": 5.1299429898305076e-05,
      "loss": 0.494,
      "step": 169
    },
    {
      "epoch": 2.1,
      "learning_rate": 5.107344122033898e-05,
      "loss": 0.4871,
      "step": 170
    },
    {
      "epoch": 2.11,
      "learning_rate": 5.0847452542372875e-05,
      "loss": 0.4981,
      "step": 171
    },
    {
      "epoch": 2.13,
      "learning_rate": 5.0621463864406774e-05,
      "loss": 0.4813,
      "step": 172
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.039547518644067e-05,
      "loss": 0.4956,
      "step": 173
    },
    {
      "epoch": 2.15,
      "learning_rate": 5.016948650847457e-05,
      "loss": 0.4892,
      "step": 174
    },
    {
      "epoch": 2.16,
      "learning_rate": 4.9943497830508465e-05,
      "loss": 0.509,
      "step": 175
    },
    {
      "epoch": 2.18,
      "learning_rate": 4.971750915254237e-05,
      "loss": 0.4824,
      "step": 176
    },
    {
      "epoch": 2.19,
      "learning_rate": 4.9491520474576264e-05,
      "loss": 0.4673,
      "step": 177
    },
    {
      "epoch": 2.2,
      "learning_rate": 4.926553179661016e-05,
      "loss": 0.4846,
      "step": 178
    },
    {
      "epoch": 2.22,
      "learning_rate": 4.903954311864406e-05,
      "loss": 0.4539,
      "step": 179
    },
    {
      "epoch": 2.23,
      "learning_rate": 4.881355444067796e-05,
      "loss": 0.4754,
      "step": 180
    },
    {
      "epoch": 2.23,
      "eval_loss": 0.9124670028686523,
      "eval_runtime": 22.9259,
      "eval_samples_per_second": 10.905,
      "eval_steps_per_second": 2.748,
      "step": 180
    },
    {
      "epoch": 2.24,
      "learning_rate": 4.8587565762711854e-05,
      "loss": 0.4843,
      "step": 181
    },
    {
      "epoch": 2.25,
      "learning_rate": 4.836157708474576e-05,
      "loss": 0.5252,
      "step": 182
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.813558840677966e-05,
      "loss": 0.4538,
      "step": 183
    },
    {
      "epoch": 2.28,
      "learning_rate": 4.790959972881355e-05,
      "loss": 0.4474,
      "step": 184
    },
    {
      "epoch": 2.29,
      "learning_rate": 4.768361105084746e-05,
      "loss": 0.4524,
      "step": 185
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.745762237288135e-05,
      "loss": 0.4619,
      "step": 186
    },
    {
      "epoch": 2.32,
      "learning_rate": 4.723163369491525e-05,
      "loss": 0.445,
      "step": 187
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.700564501694915e-05,
      "loss": 0.5182,
      "step": 188
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.677965633898305e-05,
      "loss": 0.4416,
      "step": 189
    },
    {
      "epoch": 2.35,
      "learning_rate": 4.655366766101694e-05,
      "loss": 0.5239,
      "step": 190
    },
    {
      "epoch": 2.37,
      "learning_rate": 4.6327678983050847e-05,
      "loss": 0.4654,
      "step": 191
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.610169030508474e-05,
      "loss": 0.4281,
      "step": 192
    },
    {
      "epoch": 2.39,
      "learning_rate": 4.5875701627118645e-05,
      "loss": 0.4956,
      "step": 193
    },
    {
      "epoch": 2.41,
      "learning_rate": 4.564971294915254e-05,
      "loss": 0.5188,
      "step": 194
    },
    {
      "epoch": 2.42,
      "learning_rate": 4.542372427118644e-05,
      "loss": 0.4761,
      "step": 195
    },
    {
      "epoch": 2.43,
      "learning_rate": 4.5197735593220336e-05,
      "loss": 0.4582,
      "step": 196
    },
    {
      "epoch": 2.44,
      "learning_rate": 4.4971746915254235e-05,
      "loss": 0.4361,
      "step": 197
    },
    {
      "epoch": 2.46,
      "learning_rate": 4.474575823728813e-05,
      "loss": 0.456,
      "step": 198
    },
    {
      "epoch": 2.47,
      "learning_rate": 4.4519769559322034e-05,
      "loss": 0.4532,
      "step": 199
    },
    {
      "epoch": 2.48,
      "learning_rate": 4.4293780881355926e-05,
      "loss": 0.4614,
      "step": 200
    },
    {
      "epoch": 2.48,
      "eval_loss": 0.9134233593940735,
      "eval_runtime": 22.8657,
      "eval_samples_per_second": 10.933,
      "eval_steps_per_second": 2.755,
      "step": 200
    },
    {
      "epoch": 2.49,
      "learning_rate": 4.4067792203389826e-05,
      "loss": 0.4809,
      "step": 201
    },
    {
      "epoch": 2.51,
      "learning_rate": 4.3841803525423725e-05,
      "loss": 0.4577,
      "step": 202
    },
    {
      "epoch": 2.52,
      "learning_rate": 4.3615814847457624e-05,
      "loss": 0.4501,
      "step": 203
    },
    {
      "epoch": 2.53,
      "learning_rate": 4.338982616949152e-05,
      "loss": 0.4478,
      "step": 204
    },
    {
      "epoch": 2.54,
      "learning_rate": 4.316383749152542e-05,
      "loss": 0.5011,
      "step": 205
    },
    {
      "epoch": 2.56,
      "learning_rate": 4.2937848813559315e-05,
      "loss": 0.4597,
      "step": 206
    },
    {
      "epoch": 2.57,
      "learning_rate": 4.2711860135593214e-05,
      "loss": 0.4816,
      "step": 207
    },
    {
      "epoch": 2.58,
      "learning_rate": 4.2485871457627114e-05,
      "loss": 0.3946,
      "step": 208
    },
    {
      "epoch": 2.59,
      "learning_rate": 4.225988277966101e-05,
      "loss": 0.451,
      "step": 209
    },
    {
      "epoch": 2.61,
      "learning_rate": 4.203389410169491e-05,
      "loss": 0.415,
      "step": 210
    },
    {
      "epoch": 2.62,
      "learning_rate": 4.180790542372881e-05,
      "loss": 0.4413,
      "step": 211
    },
    {
      "epoch": 2.63,
      "learning_rate": 4.158191674576271e-05,
      "loss": 0.4418,
      "step": 212
    },
    {
      "epoch": 2.65,
      "learning_rate": 4.13559280677966e-05,
      "loss": 0.4796,
      "step": 213
    },
    {
      "epoch": 2.66,
      "learning_rate": 4.112993938983051e-05,
      "loss": 0.5089,
      "step": 214
    },
    {
      "epoch": 2.67,
      "learning_rate": 4.09039507118644e-05,
      "loss": 0.4384,
      "step": 215
    },
    {
      "epoch": 2.68,
      "learning_rate": 4.06779620338983e-05,
      "loss": 0.4489,
      "step": 216
    },
    {
      "epoch": 2.7,
      "learning_rate": 4.04519733559322e-05,
      "loss": 0.4466,
      "step": 217
    },
    {
      "epoch": 2.71,
      "learning_rate": 4.02259846779661e-05,
      "loss": 0.4785,
      "step": 218
    },
    {
      "epoch": 2.72,
      "learning_rate": 3.999999599999999e-05,
      "loss": 0.4429,
      "step": 219
    },
    {
      "epoch": 2.73,
      "learning_rate": 3.97740073220339e-05,
      "loss": 0.4749,
      "step": 220
    },
    {
      "epoch": 2.73,
      "eval_loss": 0.9150541424751282,
      "eval_runtime": 22.6679,
      "eval_samples_per_second": 11.029,
      "eval_steps_per_second": 2.779,
      "step": 220
    },
    {
      "epoch": 2.75,
      "learning_rate": 3.954801864406779e-05,
      "loss": 0.4631,
      "step": 221
    },
    {
      "epoch": 2.76,
      "learning_rate": 3.932202996610169e-05,
      "loss": 0.4686,
      "step": 222
    },
    {
      "epoch": 2.77,
      "learning_rate": 3.909604128813559e-05,
      "loss": 0.4602,
      "step": 223
    },
    {
      "epoch": 2.78,
      "learning_rate": 3.887005261016949e-05,
      "loss": 0.4361,
      "step": 224
    },
    {
      "epoch": 2.8,
      "learning_rate": 3.864406393220338e-05,
      "loss": 0.4453,
      "step": 225
    },
    {
      "epoch": 2.81,
      "learning_rate": 3.841807525423729e-05,
      "loss": 0.4475,
      "step": 226
    },
    {
      "epoch": 2.82,
      "learning_rate": 3.819208657627118e-05,
      "loss": 0.4687,
      "step": 227
    },
    {
      "epoch": 2.84,
      "learning_rate": 3.796609789830508e-05,
      "loss": 0.4799,
      "step": 228
    },
    {
      "epoch": 2.85,
      "learning_rate": 3.774010922033898e-05,
      "loss": 0.45,
      "step": 229
    },
    {
      "epoch": 2.86,
      "learning_rate": 3.751412054237288e-05,
      "loss": 0.4617,
      "step": 230
    },
    {
      "epoch": 2.87,
      "learning_rate": 3.728813186440677e-05,
      "loss": 0.4459,
      "step": 231
    },
    {
      "epoch": 2.89,
      "learning_rate": 3.7062143186440676e-05,
      "loss": 0.465,
      "step": 232
    },
    {
      "epoch": 2.9,
      "learning_rate": 3.683615450847457e-05,
      "loss": 0.4461,
      "step": 233
    },
    {
      "epoch": 2.91,
      "learning_rate": 3.6610165830508474e-05,
      "loss": 0.448,
      "step": 234
    },
    {
      "epoch": 2.92,
      "learning_rate": 3.638417715254237e-05,
      "loss": 0.4571,
      "step": 235
    },
    {
      "epoch": 2.94,
      "learning_rate": 3.6158188474576266e-05,
      "loss": 0.4535,
      "step": 236
    },
    {
      "epoch": 2.95,
      "learning_rate": 3.593219979661017e-05,
      "loss": 0.4569,
      "step": 237
    },
    {
      "epoch": 2.96,
      "learning_rate": 3.5706211118644065e-05,
      "loss": 0.4056,
      "step": 238
    },
    {
      "epoch": 2.97,
      "learning_rate": 3.5480222440677964e-05,
      "loss": 0.4402,
      "step": 239
    },
    {
      "epoch": 2.99,
      "learning_rate": 3.525423376271186e-05,
      "loss": 0.423,
      "step": 240
    },
    {
      "epoch": 2.99,
      "eval_loss": 0.9124926328659058,
      "eval_runtime": 22.5733,
      "eval_samples_per_second": 11.075,
      "eval_steps_per_second": 2.791,
      "step": 240
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.502824508474576e-05,
      "loss": 0.4351,
      "step": 241
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.4802256406779655e-05,
      "loss": 0.4771,
      "step": 242
    },
    {
      "epoch": 3.03,
      "learning_rate": 3.457626772881356e-05,
      "loss": 0.4203,
      "step": 243
    }
  ],
  "logging_steps": 1,
  "max_steps": 395,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.3748991852030198e+18,
  "trial_name": null,
  "trial_params": null
}