{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 30.0,
  "eval_steps": 80,
  "global_step": 975,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 2.5e-07,
      "loss": 1.8362,
      "step": 1
    },
    {
      "epoch": 0.03,
      "eval_loss": 1.7487908601760864,
      "eval_runtime": 1.7201,
      "eval_samples_per_second": 4.07,
      "eval_steps_per_second": 2.326,
      "step": 1
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.5e-07,
      "loss": 1.7387,
      "step": 2
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.5e-07,
      "loss": 1.9194,
      "step": 3
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.5e-07,
      "loss": 1.8898,
      "step": 4
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.5e-07,
      "loss": 1.7892,
      "step": 5
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.5e-07,
      "loss": 1.9383,
      "step": 6
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.5e-07,
      "loss": 1.6433,
      "step": 7
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.5e-07,
      "loss": 1.9912,
      "step": 8
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.5e-07,
      "loss": 1.967,
      "step": 9
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.5e-07,
      "loss": 1.8385,
      "step": 10
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.5e-07,
      "loss": 2.0755,
      "step": 11
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.5e-07,
      "loss": 1.852,
      "step": 12
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.5e-07,
      "loss": 2.0098,
      "step": 13
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.5e-07,
      "loss": 1.8534,
      "step": 14
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.5e-07,
      "loss": 2.2001,
      "step": 15
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.5e-07,
      "loss": 1.7698,
      "step": 16
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.5e-07,
      "loss": 1.9215,
      "step": 17
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.5e-07,
      "loss": 1.8275,
      "step": 18
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.5e-07,
      "loss": 1.8526,
      "step": 19
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.5e-07,
      "loss": 1.8421,
      "step": 20
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.5e-07,
      "loss": 1.7406,
      "step": 21
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.5e-07,
      "loss": 1.8343,
      "step": 22
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.5e-07,
      "loss": 1.8616,
      "step": 23
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.5e-07,
      "loss": 1.6493,
      "step": 24
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5e-07,
      "loss": 1.931,
      "step": 25
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.5e-07,
      "loss": 1.9538,
      "step": 26
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.5e-07,
      "loss": 2.013,
      "step": 27
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.5e-07,
      "loss": 2.0858,
      "step": 28
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.5e-07,
      "loss": 2.0456,
      "step": 29
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.5e-07,
      "loss": 1.7464,
      "step": 30
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.5e-07,
      "loss": 1.8876,
      "step": 31
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.5e-07,
      "loss": 1.7079,
      "step": 32
    },
    {
      "epoch": 1.02,
      "learning_rate": 2.5e-07,
      "loss": 1.8358,
      "step": 33
    },
    {
      "epoch": 1.05,
      "learning_rate": 2.5e-07,
      "loss": 2.0894,
      "step": 34
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.5e-07,
      "loss": 1.8563,
      "step": 35
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.5e-07,
      "loss": 1.893,
      "step": 36
    },
    {
      "epoch": 1.14,
      "learning_rate": 2.5e-07,
      "loss": 1.9089,
      "step": 37
    },
    {
      "epoch": 1.17,
      "learning_rate": 2.5e-07,
      "loss": 1.7537,
      "step": 38
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.5e-07,
      "loss": 1.8376,
      "step": 39
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.5e-07,
      "loss": 1.7036,
      "step": 40
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.5e-07,
      "loss": 1.8212,
      "step": 41
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.5e-07,
      "loss": 1.8071,
      "step": 42
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.5e-07,
      "loss": 1.8911,
      "step": 43
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.5e-07,
      "loss": 1.88,
      "step": 44
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.5e-07,
      "loss": 1.7136,
      "step": 45
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.5e-07,
      "loss": 1.6818,
      "step": 46
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.5e-07,
      "loss": 1.9645,
      "step": 47
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.5e-07,
      "loss": 1.9903,
      "step": 48
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.5e-07,
      "loss": 1.8368,
      "step": 49
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.5e-07,
      "loss": 1.7862,
      "step": 50
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.5e-07,
      "loss": 1.9217,
      "step": 51
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.5e-07,
      "loss": 1.8417,
      "step": 52
    },
    {
      "epoch": 1.63,
      "learning_rate": 2.5e-07,
      "loss": 1.8408,
      "step": 53
    },
    {
      "epoch": 1.66,
      "learning_rate": 2.5e-07,
      "loss": 1.8922,
      "step": 54
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.5e-07,
      "loss": 1.7651,
      "step": 55
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.5e-07,
      "loss": 1.7586,
      "step": 56
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.5e-07,
      "loss": 1.9452,
      "step": 57
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.5e-07,
      "loss": 1.7795,
      "step": 58
    },
    {
      "epoch": 1.82,
      "learning_rate": 2.5e-07,
      "loss": 1.875,
      "step": 59
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.5e-07,
      "loss": 1.8503,
      "step": 60
    },
    {
      "epoch": 1.88,
      "learning_rate": 2.5e-07,
      "loss": 1.7522,
      "step": 61
    },
    {
      "epoch": 1.91,
      "learning_rate": 2.5e-07,
      "loss": 1.7527,
      "step": 62
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.5e-07,
      "loss": 1.8297,
      "step": 63
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.5e-07,
      "loss": 1.7751,
      "step": 64
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.5e-07,
      "loss": 1.9007,
      "step": 65
    },
    {
      "epoch": 2.03,
      "learning_rate": 2.5e-07,
      "loss": 1.829,
      "step": 66
    },
    {
      "epoch": 2.06,
      "learning_rate": 2.5e-07,
      "loss": 1.7726,
      "step": 67
    },
    {
      "epoch": 2.09,
      "learning_rate": 2.5e-07,
      "loss": 1.8103,
      "step": 68
    },
    {
      "epoch": 2.12,
      "learning_rate": 2.5e-07,
      "loss": 1.8264,
      "step": 69
    },
    {
      "epoch": 2.15,
      "learning_rate": 2.5e-07,
      "loss": 1.7188,
      "step": 70
    },
    {
      "epoch": 2.18,
      "learning_rate": 2.5e-07,
      "loss": 1.8933,
      "step": 71
    },
    {
      "epoch": 2.22,
      "learning_rate": 2.5e-07,
      "loss": 1.6881,
      "step": 72
    },
    {
      "epoch": 2.25,
      "learning_rate": 2.5e-07,
      "loss": 1.6726,
      "step": 73
    },
    {
      "epoch": 2.28,
      "learning_rate": 2.5e-07,
      "loss": 1.8541,
      "step": 74
    },
    {
      "epoch": 2.31,
      "learning_rate": 2.5e-07,
      "loss": 1.8042,
      "step": 75
    },
    {
      "epoch": 2.34,
      "learning_rate": 2.5e-07,
      "loss": 1.7049,
      "step": 76
    },
    {
      "epoch": 2.37,
      "learning_rate": 2.5e-07,
      "loss": 1.6737,
      "step": 77
    },
    {
      "epoch": 2.4,
      "learning_rate": 2.5e-07,
      "loss": 1.6985,
      "step": 78
    },
    {
      "epoch": 2.43,
      "learning_rate": 2.5e-07,
      "loss": 1.7261,
      "step": 79
    },
    {
      "epoch": 2.46,
      "learning_rate": 2.5e-07,
      "loss": 2.035,
      "step": 80
    },
    {
      "epoch": 2.46,
      "eval_loss": 1.646209955215454,
      "eval_runtime": 1.7493,
      "eval_samples_per_second": 4.002,
      "eval_steps_per_second": 2.287,
      "step": 80
    },
    {
      "epoch": 2.49,
      "learning_rate": 2.5e-07,
      "loss": 1.7559,
      "step": 81
    },
    {
      "epoch": 2.52,
      "learning_rate": 2.5e-07,
      "loss": 1.6864,
      "step": 82
    },
    {
      "epoch": 2.55,
      "learning_rate": 2.5e-07,
      "loss": 1.8974,
      "step": 83
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.5e-07,
      "loss": 1.822,
      "step": 84
    },
    {
      "epoch": 2.62,
      "learning_rate": 2.5e-07,
      "loss": 1.6783,
      "step": 85
    },
    {
      "epoch": 2.65,
      "learning_rate": 2.5e-07,
      "loss": 1.8375,
      "step": 86
    },
    {
      "epoch": 2.68,
      "learning_rate": 2.5e-07,
      "loss": 1.7302,
      "step": 87
    },
    {
      "epoch": 2.71,
      "learning_rate": 2.5e-07,
      "loss": 1.7164,
      "step": 88
    },
    {
      "epoch": 2.74,
      "learning_rate": 2.5e-07,
      "loss": 1.6118,
      "step": 89
    },
    {
      "epoch": 2.77,
      "learning_rate": 2.5e-07,
      "loss": 1.7528,
      "step": 90
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.5e-07,
      "loss": 1.9012,
      "step": 91
    },
    {
      "epoch": 2.83,
      "learning_rate": 2.5e-07,
      "loss": 1.6869,
      "step": 92
    },
    {
      "epoch": 2.86,
      "learning_rate": 2.5e-07,
      "loss": 1.7648,
      "step": 93
    },
    {
      "epoch": 2.89,
      "learning_rate": 2.5e-07,
      "loss": 1.6151,
      "step": 94
    },
    {
      "epoch": 2.92,
      "learning_rate": 2.5e-07,
      "loss": 1.7853,
      "step": 95
    },
    {
      "epoch": 2.95,
      "learning_rate": 2.5e-07,
      "loss": 1.7481,
      "step": 96
    },
    {
      "epoch": 2.98,
      "learning_rate": 2.5e-07,
      "loss": 1.7218,
      "step": 97
    },
    {
      "epoch": 3.02,
      "learning_rate": 2.5e-07,
      "loss": 1.8767,
      "step": 98
    },
    {
      "epoch": 3.05,
      "learning_rate": 2.5e-07,
      "loss": 1.7954,
      "step": 99
    },
    {
      "epoch": 3.08,
      "learning_rate": 2.5e-07,
      "loss": 1.6822,
      "step": 100
    },
    {
      "epoch": 3.11,
      "learning_rate": 2.5e-07,
      "loss": 1.821,
      "step": 101
    },
    {
      "epoch": 3.14,
      "learning_rate": 2.5e-07,
      "loss": 1.6984,
      "step": 102
    },
    {
      "epoch": 3.17,
      "learning_rate": 2.5e-07,
      "loss": 1.7225,
      "step": 103
    },
    {
      "epoch": 3.2,
      "learning_rate": 2.5e-07,
      "loss": 1.6312,
      "step": 104
    },
    {
      "epoch": 3.23,
      "learning_rate": 2.5e-07,
      "loss": 1.7467,
      "step": 105
    },
    {
      "epoch": 3.26,
      "learning_rate": 2.5e-07,
      "loss": 1.679,
      "step": 106
    },
    {
      "epoch": 3.29,
      "learning_rate": 2.5e-07,
      "loss": 1.791,
      "step": 107
    },
    {
      "epoch": 3.32,
      "learning_rate": 2.5e-07,
      "loss": 1.7233,
      "step": 108
    },
    {
      "epoch": 3.35,
      "learning_rate": 2.5e-07,
      "loss": 1.8198,
      "step": 109
    },
    {
      "epoch": 3.38,
      "learning_rate": 2.5e-07,
      "loss": 1.6536,
      "step": 110
    },
    {
      "epoch": 3.42,
      "learning_rate": 2.5e-07,
      "loss": 1.6672,
      "step": 111
    },
    {
      "epoch": 3.45,
      "learning_rate": 2.5e-07,
      "loss": 1.8259,
      "step": 112
    },
    {
      "epoch": 3.48,
      "learning_rate": 2.5e-07,
      "loss": 1.7671,
      "step": 113
    },
    {
      "epoch": 3.51,
      "learning_rate": 2.5e-07,
      "loss": 1.5717,
      "step": 114
    },
    {
      "epoch": 3.54,
      "learning_rate": 2.5e-07,
      "loss": 1.7491,
      "step": 115
    },
    {
      "epoch": 3.57,
      "learning_rate": 2.5e-07,
      "loss": 1.4921,
      "step": 116
    },
    {
      "epoch": 3.6,
      "learning_rate": 2.5e-07,
      "loss": 1.7512,
      "step": 117
    },
    {
      "epoch": 3.63,
      "learning_rate": 2.5e-07,
      "loss": 1.5921,
      "step": 118
    },
    {
      "epoch": 3.66,
      "learning_rate": 2.5e-07,
      "loss": 1.6179,
      "step": 119
    },
    {
      "epoch": 3.69,
      "learning_rate": 2.5e-07,
      "loss": 1.7484,
      "step": 120
    },
    {
      "epoch": 3.72,
      "learning_rate": 2.5e-07,
      "loss": 1.6551,
      "step": 121
    },
    {
      "epoch": 3.75,
      "learning_rate": 2.5e-07,
      "loss": 1.6753,
      "step": 122
    },
    {
      "epoch": 3.78,
      "learning_rate": 2.5e-07,
      "loss": 1.816,
      "step": 123
    },
    {
      "epoch": 3.82,
      "learning_rate": 2.5e-07,
      "loss": 1.7982,
      "step": 124
    },
    {
      "epoch": 3.85,
      "learning_rate": 2.5e-07,
      "loss": 1.5347,
      "step": 125
    },
    {
      "epoch": 3.88,
      "learning_rate": 2.5e-07,
      "loss": 1.6895,
      "step": 126
    },
    {
      "epoch": 3.91,
      "learning_rate": 2.5e-07,
      "loss": 1.6968,
      "step": 127
    },
    {
      "epoch": 3.94,
      "learning_rate": 2.5e-07,
      "loss": 1.6039,
      "step": 128
    },
    {
      "epoch": 3.97,
      "learning_rate": 2.5e-07,
      "loss": 1.6148,
      "step": 129
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.5e-07,
      "loss": 1.6244,
      "step": 130
    },
    {
      "epoch": 4.03,
      "learning_rate": 2.5e-07,
      "loss": 1.5743,
      "step": 131
    },
    {
      "epoch": 4.06,
      "learning_rate": 2.5e-07,
      "loss": 1.5876,
      "step": 132
    },
    {
      "epoch": 4.09,
      "learning_rate": 2.5e-07,
      "loss": 1.7865,
      "step": 133
    },
    {
      "epoch": 4.12,
      "learning_rate": 2.5e-07,
      "loss": 1.731,
      "step": 134
    },
    {
      "epoch": 4.15,
      "learning_rate": 2.5e-07,
      "loss": 1.6661,
      "step": 135
    },
    {
      "epoch": 4.18,
      "learning_rate": 2.5e-07,
      "loss": 1.6231,
      "step": 136
    },
    {
      "epoch": 4.22,
      "learning_rate": 2.5e-07,
      "loss": 1.5479,
      "step": 137
    },
    {
      "epoch": 4.25,
      "learning_rate": 2.5e-07,
      "loss": 1.7758,
      "step": 138
    },
    {
      "epoch": 4.28,
      "learning_rate": 2.5e-07,
      "loss": 1.6865,
      "step": 139
    },
    {
      "epoch": 4.31,
      "learning_rate": 2.5e-07,
      "loss": 1.6355,
      "step": 140
    },
    {
      "epoch": 4.34,
      "learning_rate": 2.5e-07,
      "loss": 1.6922,
      "step": 141
    },
    {
      "epoch": 4.37,
      "learning_rate": 2.5e-07,
      "loss": 1.5235,
      "step": 142
    },
    {
      "epoch": 4.4,
      "learning_rate": 2.5e-07,
      "loss": 1.6388,
      "step": 143
    },
    {
      "epoch": 4.43,
      "learning_rate": 2.5e-07,
      "loss": 1.536,
      "step": 144
    },
    {
      "epoch": 4.46,
      "learning_rate": 2.5e-07,
      "loss": 1.6105,
      "step": 145
    },
    {
      "epoch": 4.49,
      "learning_rate": 2.5e-07,
      "loss": 1.6795,
      "step": 146
    },
    {
      "epoch": 4.52,
      "learning_rate": 2.5e-07,
      "loss": 1.5493,
      "step": 147
    },
    {
      "epoch": 4.55,
      "learning_rate": 2.5e-07,
      "loss": 1.6987,
      "step": 148
    },
    {
      "epoch": 4.58,
      "learning_rate": 2.5e-07,
      "loss": 1.529,
      "step": 149
    },
    {
      "epoch": 4.62,
      "learning_rate": 2.5e-07,
      "loss": 1.5458,
      "step": 150
    },
    {
      "epoch": 4.65,
      "learning_rate": 2.5e-07,
      "loss": 1.5496,
      "step": 151
    },
    {
      "epoch": 4.68,
      "learning_rate": 2.5e-07,
      "loss": 1.6442,
      "step": 152
    },
    {
      "epoch": 4.71,
      "learning_rate": 2.5e-07,
      "loss": 1.727,
      "step": 153
    },
    {
      "epoch": 4.74,
      "learning_rate": 2.5e-07,
      "loss": 1.6884,
      "step": 154
    },
    {
      "epoch": 4.77,
      "learning_rate": 2.5e-07,
      "loss": 1.5979,
      "step": 155
    },
    {
      "epoch": 4.8,
      "learning_rate": 2.5e-07,
      "loss": 1.5635,
      "step": 156
    },
    {
      "epoch": 4.83,
      "learning_rate": 2.5e-07,
      "loss": 1.805,
      "step": 157
    },
    {
      "epoch": 4.86,
      "learning_rate": 2.5e-07,
      "loss": 1.565,
      "step": 158
    },
    {
      "epoch": 4.89,
      "learning_rate": 2.5e-07,
      "loss": 1.5836,
      "step": 159
    },
    {
      "epoch": 4.92,
      "learning_rate": 2.5e-07,
      "loss": 1.5489,
      "step": 160
    },
    {
      "epoch": 4.92,
      "eval_loss": 1.490054965019226,
      "eval_runtime": 1.7397,
      "eval_samples_per_second": 4.024,
      "eval_steps_per_second": 2.299,
      "step": 160
    },
    {
      "epoch": 4.95,
      "learning_rate": 2.5e-07,
      "loss": 1.6744,
      "step": 161
    },
    {
      "epoch": 4.98,
      "learning_rate": 2.5e-07,
      "loss": 1.5578,
      "step": 162
    },
    {
      "epoch": 5.02,
      "learning_rate": 2.5e-07,
      "loss": 1.5033,
      "step": 163
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.5e-07,
      "loss": 1.701,
      "step": 164
    },
    {
      "epoch": 5.08,
      "learning_rate": 2.5e-07,
      "loss": 1.5297,
      "step": 165
    },
    {
      "epoch": 5.11,
      "learning_rate": 2.5e-07,
      "loss": 1.5086,
      "step": 166
    },
    {
      "epoch": 5.14,
      "learning_rate": 2.5e-07,
      "loss": 1.5426,
      "step": 167
    },
    {
      "epoch": 5.17,
      "learning_rate": 2.5e-07,
      "loss": 1.5224,
      "step": 168
    },
    {
      "epoch": 5.2,
      "learning_rate": 2.5e-07,
      "loss": 1.4174,
      "step": 169
    },
    {
      "epoch": 5.23,
      "learning_rate": 2.5e-07,
      "loss": 1.5665,
      "step": 170
    },
    {
      "epoch": 5.26,
      "learning_rate": 2.5e-07,
      "loss": 1.5093,
      "step": 171
    },
    {
      "epoch": 5.29,
      "learning_rate": 2.5e-07,
      "loss": 1.4894,
      "step": 172
    },
    {
      "epoch": 5.32,
      "learning_rate": 2.5e-07,
      "loss": 1.7075,
      "step": 173
    },
    {
      "epoch": 5.35,
      "learning_rate": 2.5e-07,
      "loss": 1.5987,
      "step": 174
    },
    {
      "epoch": 5.38,
      "learning_rate": 2.5e-07,
      "loss": 1.5064,
      "step": 175
    },
    {
      "epoch": 5.42,
      "learning_rate": 2.5e-07,
      "loss": 1.5896,
      "step": 176
    },
    {
      "epoch": 5.45,
      "learning_rate": 2.5e-07,
      "loss": 1.5435,
      "step": 177
    },
    {
      "epoch": 5.48,
      "learning_rate": 2.5e-07,
      "loss": 1.5764,
      "step": 178
    },
    {
      "epoch": 5.51,
      "learning_rate": 2.5e-07,
      "loss": 1.6604,
      "step": 179
    },
    {
      "epoch": 5.54,
      "learning_rate": 2.5e-07,
      "loss": 1.6184,
      "step": 180
    },
    {
      "epoch": 5.57,
      "learning_rate": 2.5e-07,
      "loss": 1.6953,
      "step": 181
    },
    {
      "epoch": 5.6,
      "learning_rate": 2.5e-07,
      "loss": 1.5764,
      "step": 182
    },
    {
      "epoch": 5.63,
      "learning_rate": 2.5e-07,
      "loss": 1.4756,
      "step": 183
    },
    {
      "epoch": 5.66,
      "learning_rate": 2.5e-07,
      "loss": 1.6062,
      "step": 184
    },
    {
      "epoch": 5.69,
      "learning_rate": 2.5e-07,
      "loss": 1.5978,
      "step": 185
    },
    {
      "epoch": 5.72,
      "learning_rate": 2.5e-07,
      "loss": 1.4222,
      "step": 186
    },
    {
      "epoch": 5.75,
      "learning_rate": 2.5e-07,
      "loss": 1.5142,
      "step": 187
    },
    {
      "epoch": 5.78,
      "learning_rate": 2.5e-07,
      "loss": 1.4466,
      "step": 188
    },
    {
      "epoch": 5.82,
      "learning_rate": 2.5e-07,
      "loss": 1.5513,
      "step": 189
    },
    {
      "epoch": 5.85,
      "learning_rate": 2.5e-07,
      "loss": 1.4656,
      "step": 190
    },
    {
      "epoch": 5.88,
      "learning_rate": 2.5e-07,
      "loss": 1.5972,
      "step": 191
    },
    {
      "epoch": 5.91,
      "learning_rate": 2.5e-07,
      "loss": 1.4809,
      "step": 192
    },
    {
      "epoch": 5.94,
      "learning_rate": 2.5e-07,
      "loss": 1.6644,
      "step": 193
    },
    {
      "epoch": 5.97,
      "learning_rate": 2.5e-07,
      "loss": 1.5554,
      "step": 194
    },
    {
      "epoch": 6.0,
      "learning_rate": 2.5e-07,
      "loss": 1.5099,
      "step": 195
    },
    {
      "epoch": 6.03,
      "learning_rate": 2.5e-07,
      "loss": 1.5775,
      "step": 196
    },
    {
      "epoch": 6.06,
      "learning_rate": 2.5e-07,
      "loss": 1.4642,
      "step": 197
    },
    {
      "epoch": 6.09,
      "learning_rate": 2.5e-07,
      "loss": 1.4549,
      "step": 198
    },
    {
      "epoch": 6.12,
      "learning_rate": 2.5e-07,
      "loss": 1.4262,
      "step": 199
    },
    {
      "epoch": 6.15,
      "learning_rate": 2.5e-07,
      "loss": 1.3087,
      "step": 200
    },
    {
      "epoch": 6.18,
      "learning_rate": 2.5e-07,
      "loss": 1.4069,
      "step": 201
    },
    {
      "epoch": 6.22,
      "learning_rate": 2.5e-07,
      "loss": 1.5301,
      "step": 202
    },
    {
      "epoch": 6.25,
      "learning_rate": 2.5e-07,
      "loss": 1.4505,
      "step": 203
    },
    {
      "epoch": 6.28,
      "learning_rate": 2.5e-07,
      "loss": 1.5708,
      "step": 204
    },
    {
      "epoch": 6.31,
      "learning_rate": 2.5e-07,
      "loss": 1.5237,
      "step": 205
    },
    {
      "epoch": 6.34,
      "learning_rate": 2.5e-07,
      "loss": 1.6189,
      "step": 206
    },
    {
      "epoch": 6.37,
      "learning_rate": 2.5e-07,
      "loss": 1.3563,
      "step": 207
    },
    {
      "epoch": 6.4,
      "learning_rate": 2.5e-07,
      "loss": 1.6897,
      "step": 208
    },
    {
      "epoch": 6.43,
      "learning_rate": 2.5e-07,
      "loss": 1.4593,
      "step": 209
    },
    {
      "epoch": 6.46,
      "learning_rate": 2.5e-07,
      "loss": 1.6024,
      "step": 210
    },
    {
      "epoch": 6.49,
      "learning_rate": 2.5e-07,
      "loss": 1.4543,
      "step": 211
    },
    {
      "epoch": 6.52,
      "learning_rate": 2.5e-07,
      "loss": 1.5193,
      "step": 212
    },
    {
      "epoch": 6.55,
      "learning_rate": 2.5e-07,
      "loss": 1.3936,
      "step": 213
    },
    {
      "epoch": 6.58,
      "learning_rate": 2.5e-07,
      "loss": 1.5552,
      "step": 214
    },
    {
      "epoch": 6.62,
      "learning_rate": 2.5e-07,
      "loss": 1.453,
      "step": 215
    },
    {
      "epoch": 6.65,
      "learning_rate": 2.5e-07,
      "loss": 1.4554,
      "step": 216
    },
    {
      "epoch": 6.68,
      "learning_rate": 2.5e-07,
      "loss": 1.6442,
      "step": 217
    },
    {
      "epoch": 6.71,
      "learning_rate": 2.5e-07,
      "loss": 1.439,
      "step": 218
    },
    {
      "epoch": 6.74,
      "learning_rate": 2.5e-07,
      "loss": 1.4309,
      "step": 219
    },
    {
      "epoch": 6.77,
      "learning_rate": 2.5e-07,
      "loss": 1.4857,
      "step": 220
    },
    {
      "epoch": 6.8,
      "learning_rate": 2.5e-07,
      "loss": 1.5154,
      "step": 221
    },
    {
      "epoch": 6.83,
      "learning_rate": 2.5e-07,
      "loss": 1.3941,
      "step": 222
    },
    {
      "epoch": 6.86,
      "learning_rate": 2.5e-07,
      "loss": 1.5596,
      "step": 223
    },
    {
      "epoch": 6.89,
      "learning_rate": 2.5e-07,
      "loss": 1.4859,
      "step": 224
    },
    {
      "epoch": 6.92,
      "learning_rate": 2.5e-07,
      "loss": 1.4801,
      "step": 225
    },
    {
      "epoch": 6.95,
      "learning_rate": 2.5e-07,
      "loss": 1.5035,
      "step": 226
    },
    {
      "epoch": 6.98,
      "learning_rate": 2.5e-07,
      "loss": 1.6068,
      "step": 227
    },
    {
      "epoch": 7.02,
      "learning_rate": 2.5e-07,
      "loss": 1.4447,
      "step": 228
    },
    {
      "epoch": 7.05,
      "learning_rate": 2.5e-07,
      "loss": 1.5094,
      "step": 229
    },
    {
      "epoch": 7.08,
      "learning_rate": 2.5e-07,
      "loss": 1.5474,
      "step": 230
    },
    {
      "epoch": 7.11,
      "learning_rate": 2.5e-07,
      "loss": 1.4545,
      "step": 231
    },
    {
      "epoch": 7.14,
      "learning_rate": 2.5e-07,
      "loss": 1.4672,
      "step": 232
    },
    {
      "epoch": 7.17,
      "learning_rate": 2.5e-07,
      "loss": 1.6396,
      "step": 233
    },
    {
      "epoch": 7.2,
      "learning_rate": 2.5e-07,
      "loss": 1.374,
      "step": 234
    },
    {
      "epoch": 7.23,
      "learning_rate": 2.5e-07,
      "loss": 1.4521,
      "step": 235
    },
    {
      "epoch": 7.26,
      "learning_rate": 2.5e-07,
      "loss": 1.2984,
      "step": 236
    },
    {
      "epoch": 7.29,
      "learning_rate": 2.5e-07,
      "loss": 1.4511,
      "step": 237
    },
    {
      "epoch": 7.32,
      "learning_rate": 2.5e-07,
      "loss": 1.405,
      "step": 238
    },
    {
      "epoch": 7.35,
      "learning_rate": 2.5e-07,
      "loss": 1.296,
      "step": 239
    },
    {
      "epoch": 7.38,
      "learning_rate": 2.5e-07,
      "loss": 1.4392,
      "step": 240
    },
    {
      "epoch": 7.38,
      "eval_loss": 1.3567150831222534,
      "eval_runtime": 1.7364,
      "eval_samples_per_second": 4.031,
      "eval_steps_per_second": 2.304,
      "step": 240
    },
    {
      "epoch": 7.42,
      "learning_rate": 2.5e-07,
      "loss": 1.5595,
      "step": 241
    },
    {
      "epoch": 7.45,
      "learning_rate": 2.5e-07,
      "loss": 1.5671,
      "step": 242
    },
    {
      "epoch": 7.48,
      "learning_rate": 2.5e-07,
      "loss": 1.4832,
      "step": 243
    },
    {
      "epoch": 7.51,
      "learning_rate": 2.5e-07,
      "loss": 1.4415,
      "step": 244
    },
    {
      "epoch": 7.54,
      "learning_rate": 2.5e-07,
      "loss": 1.4649,
      "step": 245
    },
    {
      "epoch": 7.57,
      "learning_rate": 2.5e-07,
      "loss": 1.5053,
      "step": 246
    },
    {
      "epoch": 7.6,
      "learning_rate": 2.5e-07,
      "loss": 1.5084,
      "step": 247
    },
    {
      "epoch": 7.63,
      "learning_rate": 2.5e-07,
      "loss": 1.4543,
      "step": 248
    },
    {
      "epoch": 7.66,
      "learning_rate": 2.5e-07,
      "loss": 1.3008,
      "step": 249
    },
    {
      "epoch": 7.69,
      "learning_rate": 2.5e-07,
      "loss": 1.324,
      "step": 250
    },
    {
      "epoch": 7.72,
      "learning_rate": 2.5e-07,
      "loss": 1.5586,
      "step": 251
    },
    {
      "epoch": 7.75,
      "learning_rate": 2.5e-07,
      "loss": 1.4245,
      "step": 252
    },
    {
      "epoch": 7.78,
      "learning_rate": 2.5e-07,
      "loss": 1.4361,
      "step": 253
    },
    {
      "epoch": 7.82,
      "learning_rate": 2.5e-07,
      "loss": 1.4301,
      "step": 254
    },
    {
      "epoch": 7.85,
      "learning_rate": 2.5e-07,
      "loss": 1.5183,
      "step": 255
    },
    {
      "epoch": 7.88,
      "learning_rate": 2.5e-07,
      "loss": 1.46,
      "step": 256
    },
    {
      "epoch": 7.91,
      "learning_rate": 2.5e-07,
      "loss": 1.2602,
      "step": 257
    },
    {
      "epoch": 7.94,
      "learning_rate": 2.5e-07,
      "loss": 1.358,
      "step": 258
    },
    {
      "epoch": 7.97,
      "learning_rate": 2.5e-07,
      "loss": 1.2598,
      "step": 259
    },
    {
      "epoch": 8.0,
      "learning_rate": 2.5e-07,
      "loss": 1.3058,
      "step": 260
    },
    {
      "epoch": 8.03,
      "learning_rate": 2.5e-07,
      "loss": 1.4428,
      "step": 261
    },
    {
      "epoch": 8.06,
      "learning_rate": 2.5e-07,
      "loss": 1.4506,
      "step": 262
    },
    {
      "epoch": 8.09,
      "learning_rate": 2.5e-07,
      "loss": 1.4627,
      "step": 263
    },
    {
      "epoch": 8.12,
      "learning_rate": 2.5e-07,
      "loss": 1.4584,
      "step": 264
    },
    {
      "epoch": 8.15,
      "learning_rate": 2.5e-07,
      "loss": 1.356,
      "step": 265
    },
    {
      "epoch": 8.18,
      "learning_rate": 2.5e-07,
      "loss": 1.4304,
      "step": 266
    },
    {
      "epoch": 8.22,
      "learning_rate": 2.5e-07,
      "loss": 1.2296,
      "step": 267
    },
    {
      "epoch": 8.25,
      "learning_rate": 2.5e-07,
      "loss": 1.4255,
      "step": 268
    },
    {
      "epoch": 8.28,
      "learning_rate": 2.5e-07,
      "loss": 1.4978,
      "step": 269
    },
    {
      "epoch": 8.31,
      "learning_rate": 2.5e-07,
      "loss": 1.4115,
      "step": 270
    },
    {
      "epoch": 8.34,
      "learning_rate": 2.5e-07,
      "loss": 1.4366,
      "step": 271
    },
    {
      "epoch": 8.37,
      "learning_rate": 2.5e-07,
      "loss": 1.2477,
      "step": 272
    },
    {
      "epoch": 8.4,
      "learning_rate": 2.5e-07,
      "loss": 1.453,
      "step": 273
    },
    {
      "epoch": 8.43,
      "learning_rate": 2.5e-07,
      "loss": 1.3008,
      "step": 274
    },
    {
      "epoch": 8.46,
      "learning_rate": 2.5e-07,
      "loss": 1.2511,
      "step": 275
    },
    {
      "epoch": 8.49,
      "learning_rate": 2.5e-07,
      "loss": 1.4864,
      "step": 276
    },
    {
      "epoch": 8.52,
      "learning_rate": 2.5e-07,
      "loss": 1.4733,
      "step": 277
    },
    {
      "epoch": 8.55,
      "learning_rate": 2.5e-07,
      "loss": 1.4998,
      "step": 278
    },
    {
      "epoch": 8.58,
      "learning_rate": 2.5e-07,
      "loss": 1.4771,
      "step": 279
    },
    {
      "epoch": 8.62,
      "learning_rate": 2.5e-07,
      "loss": 1.4164,
      "step": 280
    },
    {
      "epoch": 8.65,
      "learning_rate": 2.5e-07,
      "loss": 1.2803,
      "step": 281
    },
    {
      "epoch": 8.68,
      "learning_rate": 2.5e-07,
      "loss": 1.3673,
      "step": 282
    },
    {
      "epoch": 8.71,
      "learning_rate": 2.5e-07,
      "loss": 1.3849,
      "step": 283
    },
    {
      "epoch": 8.74,
      "learning_rate": 2.5e-07,
      "loss": 1.4484,
      "step": 284
    },
    {
      "epoch": 8.77,
      "learning_rate": 2.5e-07,
      "loss": 1.397,
      "step": 285
    },
    {
      "epoch": 8.8,
      "learning_rate": 2.5e-07,
      "loss": 1.5398,
      "step": 286
    },
    {
      "epoch": 8.83,
      "learning_rate": 2.5e-07,
      "loss": 1.2841,
      "step": 287
    },
    {
      "epoch": 8.86,
      "learning_rate": 2.5e-07,
      "loss": 1.2991,
      "step": 288
    },
    {
      "epoch": 8.89,
      "learning_rate": 2.5e-07,
      "loss": 1.3,
      "step": 289
    },
    {
      "epoch": 8.92,
      "learning_rate": 2.5e-07,
      "loss": 1.413,
      "step": 290
    },
    {
      "epoch": 8.95,
      "learning_rate": 2.5e-07,
      "loss": 1.3346,
      "step": 291
    },
    {
      "epoch": 8.98,
      "learning_rate": 2.5e-07,
      "loss": 1.3362,
      "step": 292
    },
    {
      "epoch": 9.02,
      "learning_rate": 2.5e-07,
      "loss": 1.1674,
      "step": 293
    },
    {
      "epoch": 9.05,
      "learning_rate": 2.5e-07,
      "loss": 1.4128,
      "step": 294
    },
    {
      "epoch": 9.08,
      "learning_rate": 2.5e-07,
      "loss": 1.461,
      "step": 295
    },
    {
      "epoch": 9.11,
      "learning_rate": 2.5e-07,
      "loss": 1.3092,
      "step": 296
    },
    {
      "epoch": 9.14,
      "learning_rate": 2.5e-07,
      "loss": 1.2157,
      "step": 297
    },
    {
      "epoch": 9.17,
      "learning_rate": 2.5e-07,
      "loss": 1.3718,
      "step": 298
    },
    {
      "epoch": 9.2,
      "learning_rate": 2.5e-07,
      "loss": 1.4823,
      "step": 299
    },
    {
      "epoch": 9.23,
      "learning_rate": 2.5e-07,
      "loss": 1.4398,
      "step": 300
    },
    {
      "epoch": 9.26,
      "learning_rate": 2.5e-07,
      "loss": 1.3343,
      "step": 301
    },
    {
      "epoch": 9.29,
      "learning_rate": 2.5e-07,
      "loss": 1.1481,
      "step": 302
    },
    {
      "epoch": 9.32,
      "learning_rate": 2.5e-07,
      "loss": 1.3867,
      "step": 303
    },
    {
      "epoch": 9.35,
      "learning_rate": 2.5e-07,
      "loss": 1.3983,
      "step": 304
    },
    {
      "epoch": 9.38,
      "learning_rate": 2.5e-07,
      "loss": 1.3382,
      "step": 305
    },
    {
      "epoch": 9.42,
      "learning_rate": 2.5e-07,
      "loss": 1.4251,
      "step": 306
    },
    {
      "epoch": 9.45,
      "learning_rate": 2.5e-07,
      "loss": 1.2907,
      "step": 307
    },
    {
      "epoch": 9.48,
      "learning_rate": 2.5e-07,
      "loss": 1.2584,
      "step": 308
    },
    {
      "epoch": 9.51,
      "learning_rate": 2.5e-07,
      "loss": 1.3281,
      "step": 309
    },
    {
      "epoch": 9.54,
      "learning_rate": 2.5e-07,
      "loss": 1.4022,
      "step": 310
    },
    {
      "epoch": 9.57,
      "learning_rate": 2.5e-07,
      "loss": 1.3523,
      "step": 311
    },
    {
      "epoch": 9.6,
      "learning_rate": 2.5e-07,
      "loss": 1.5241,
      "step": 312
    },
    {
      "epoch": 9.63,
      "learning_rate": 2.5e-07,
      "loss": 1.1701,
      "step": 313
    },
    {
      "epoch": 9.66,
      "learning_rate": 2.5e-07,
      "loss": 1.194,
      "step": 314
    },
    {
      "epoch": 9.69,
      "learning_rate": 2.5e-07,
      "loss": 1.4622,
      "step": 315
    },
    {
      "epoch": 9.72,
      "learning_rate": 2.5e-07,
      "loss": 1.1747,
      "step": 316
    },
    {
      "epoch": 9.75,
      "learning_rate": 2.5e-07,
      "loss": 1.4286,
      "step": 317
    },
    {
      "epoch": 9.78,
      "learning_rate": 2.5e-07,
      "loss": 1.3895,
      "step": 318
    },
    {
      "epoch": 9.82,
      "learning_rate": 2.5e-07,
      "loss": 1.3746,
      "step": 319
    },
    {
      "epoch": 9.85,
      "learning_rate": 2.5e-07,
      "loss": 1.2196,
      "step": 320
    },
    {
      "epoch": 9.85,
      "eval_loss": 1.2475242614746094,
      "eval_runtime": 1.7503,
      "eval_samples_per_second": 3.999,
      "eval_steps_per_second": 2.285,
      "step": 320
    },
    {
      "epoch": 9.88,
      "learning_rate": 2.5e-07,
      "loss": 1.2543,
      "step": 321
    },
    {
      "epoch": 9.91,
      "learning_rate": 2.5e-07,
      "loss": 1.239,
      "step": 322
    },
    {
      "epoch": 9.94,
      "learning_rate": 2.5e-07,
      "loss": 1.3088,
      "step": 323
    },
    {
      "epoch": 9.97,
      "learning_rate": 2.5e-07,
      "loss": 1.299,
      "step": 324
    },
    {
      "epoch": 10.0,
      "learning_rate": 2.5e-07,
      "loss": 1.3273,
      "step": 325
    },
    {
      "epoch": 10.03,
      "learning_rate": 2.5e-07,
      "loss": 1.3335,
      "step": 326
    },
    {
      "epoch": 10.06,
      "learning_rate": 2.5e-07,
      "loss": 1.317,
      "step": 327
    },
    {
      "epoch": 10.09,
      "learning_rate": 2.5e-07,
      "loss": 1.3048,
      "step": 328
    },
    {
      "epoch": 10.12,
      "learning_rate": 2.5e-07,
      "loss": 1.429,
      "step": 329
    },
    {
      "epoch": 10.15,
      "learning_rate": 2.5e-07,
      "loss": 1.2001,
      "step": 330
    },
    {
      "epoch": 10.18,
      "learning_rate": 2.5e-07,
      "loss": 1.3512,
      "step": 331
    },
    {
      "epoch": 10.22,
      "learning_rate": 2.5e-07,
      "loss": 1.2161,
      "step": 332
    },
    {
      "epoch": 10.25,
      "learning_rate": 2.5e-07,
      "loss": 1.2098,
      "step": 333
    },
    {
      "epoch": 10.28,
      "learning_rate": 2.5e-07,
      "loss": 1.3637,
      "step": 334
    },
    {
      "epoch": 10.31,
      "learning_rate": 2.5e-07,
      "loss": 1.3788,
      "step": 335
    },
    {
      "epoch": 10.34,
      "learning_rate": 2.5e-07,
      "loss": 1.2368,
      "step": 336
    },
    {
      "epoch": 10.37,
      "learning_rate": 2.5e-07,
      "loss": 1.348,
      "step": 337
    },
    {
      "epoch": 10.4,
      "learning_rate": 2.5e-07,
      "loss": 1.0986,
      "step": 338
    },
    {
      "epoch": 10.43,
      "learning_rate": 2.5e-07,
      "loss": 1.3233,
      "step": 339
    },
    {
      "epoch": 10.46,
      "learning_rate": 2.5e-07,
      "loss": 1.3613,
      "step": 340
    },
    {
      "epoch": 10.49,
      "learning_rate": 2.5e-07,
      "loss": 1.3211,
      "step": 341
    },
    {
      "epoch": 10.52,
      "learning_rate": 2.5e-07,
      "loss": 1.5044,
      "step": 342
    },
    {
      "epoch": 10.55,
      "learning_rate": 2.5e-07,
      "loss": 1.3033,
      "step": 343
    },
    {
      "epoch": 10.58,
      "learning_rate": 2.5e-07,
      "loss": 1.4222,
      "step": 344
    },
    {
      "epoch": 10.62,
      "learning_rate": 2.5e-07,
      "loss": 1.4241,
      "step": 345
    },
    {
      "epoch": 10.65,
      "learning_rate": 2.5e-07,
      "loss": 1.3264,
      "step": 346
    },
    {
      "epoch": 10.68,
      "learning_rate": 2.5e-07,
      "loss": 1.4957,
      "step": 347
    },
    {
      "epoch": 10.71,
      "learning_rate": 2.5e-07,
      "loss": 1.1016,
      "step": 348
    },
    {
      "epoch": 10.74,
      "learning_rate": 2.5e-07,
      "loss": 1.2492,
      "step": 349
    },
    {
      "epoch": 10.77,
      "learning_rate": 2.5e-07,
      "loss": 1.1237,
      "step": 350
    },
    {
      "epoch": 10.8,
      "learning_rate": 2.5e-07,
      "loss": 1.4371,
      "step": 351
    },
    {
      "epoch": 10.83,
      "learning_rate": 2.5e-07,
      "loss": 1.438,
      "step": 352
    },
    {
      "epoch": 10.86,
      "learning_rate": 2.5e-07,
      "loss": 1.2182,
      "step": 353
    },
    {
      "epoch": 10.89,
      "learning_rate": 2.5e-07,
      "loss": 1.2577,
      "step": 354
    },
    {
      "epoch": 10.92,
      "learning_rate": 2.5e-07,
      "loss": 1.2687,
      "step": 355
    },
    {
      "epoch": 10.95,
      "learning_rate": 2.5e-07,
      "loss": 1.3387,
      "step": 356
    },
    {
      "epoch": 10.98,
      "learning_rate": 2.5e-07,
      "loss": 1.3571,
      "step": 357
    },
    {
      "epoch": 11.02,
      "learning_rate": 2.5e-07,
      "loss": 1.2289,
      "step": 358
    },
    {
      "epoch": 11.05,
      "learning_rate": 2.5e-07,
      "loss": 1.2925,
      "step": 359
    },
    {
      "epoch": 11.08,
      "learning_rate": 2.5e-07,
      "loss": 1.3187,
      "step": 360
    },
    {
      "epoch": 11.11,
      "learning_rate": 2.5e-07,
      "loss": 1.3628,
      "step": 361
    },
    {
      "epoch": 11.14,
      "learning_rate": 2.5e-07,
      "loss": 1.2547,
      "step": 362
    },
    {
      "epoch": 11.17,
      "learning_rate": 2.5e-07,
      "loss": 1.3169,
      "step": 363
    },
    {
      "epoch": 11.2,
      "learning_rate": 2.5e-07,
      "loss": 1.2921,
      "step": 364
    },
    {
      "epoch": 11.23,
      "learning_rate": 2.5e-07,
      "loss": 1.3426,
      "step": 365
    },
    {
      "epoch": 11.26,
      "learning_rate": 2.5e-07,
      "loss": 1.4212,
      "step": 366
    },
    {
      "epoch": 11.29,
      "learning_rate": 2.5e-07,
      "loss": 1.2466,
      "step": 367
    },
    {
      "epoch": 11.32,
      "learning_rate": 2.5e-07,
      "loss": 1.3367,
      "step": 368
    },
    {
      "epoch": 11.35,
      "learning_rate": 2.5e-07,
      "loss": 1.3179,
      "step": 369
    },
    {
      "epoch": 11.38,
      "learning_rate": 2.5e-07,
      "loss": 1.2568,
      "step": 370
    },
    {
      "epoch": 11.42,
      "learning_rate": 2.5e-07,
      "loss": 1.1769,
      "step": 371
    },
    {
      "epoch": 11.45,
      "learning_rate": 2.5e-07,
      "loss": 1.3068,
      "step": 372
    },
    {
      "epoch": 11.48,
      "learning_rate": 2.5e-07,
      "loss": 1.1623,
      "step": 373
    },
    {
      "epoch": 11.51,
      "learning_rate": 2.5e-07,
      "loss": 1.2147,
      "step": 374
    },
    {
      "epoch": 11.54,
      "learning_rate": 2.5e-07,
      "loss": 1.4786,
      "step": 375
    },
    {
      "epoch": 11.57,
      "learning_rate": 2.5e-07,
      "loss": 1.3387,
      "step": 376
    },
    {
      "epoch": 11.6,
      "learning_rate": 2.5e-07,
      "loss": 1.261,
      "step": 377
    },
    {
      "epoch": 11.63,
      "learning_rate": 2.5e-07,
      "loss": 1.2758,
      "step": 378
    },
    {
      "epoch": 11.66,
      "learning_rate": 2.5e-07,
      "loss": 1.2917,
      "step": 379
    },
    {
      "epoch": 11.69,
      "learning_rate": 2.5e-07,
      "loss": 1.3428,
      "step": 380
    },
    {
      "epoch": 11.72,
      "learning_rate": 2.5e-07,
      "loss": 1.4322,
      "step": 381
    },
    {
      "epoch": 11.75,
      "learning_rate": 2.5e-07,
      "loss": 1.2796,
      "step": 382
    },
    {
      "epoch": 11.78,
      "learning_rate": 2.5e-07,
      "loss": 1.318,
      "step": 383
    },
    {
      "epoch": 11.82,
      "learning_rate": 2.5e-07,
      "loss": 1.2229,
      "step": 384
    },
    {
      "epoch": 11.85,
      "learning_rate": 2.5e-07,
      "loss": 1.1542,
      "step": 385
    },
    {
      "epoch": 11.88,
      "learning_rate": 2.5e-07,
      "loss": 1.3305,
      "step": 386
    },
    {
      "epoch": 11.91,
      "learning_rate": 2.5e-07,
      "loss": 1.3448,
      "step": 387
    },
    {
      "epoch": 11.94,
      "learning_rate": 2.5e-07,
      "loss": 1.2508,
      "step": 388
    },
    {
      "epoch": 11.97,
      "learning_rate": 2.5e-07,
      "loss": 1.3033,
      "step": 389
    },
    {
      "epoch": 12.0,
      "learning_rate": 2.5e-07,
      "loss": 1.1879,
      "step": 390
    },
    {
      "epoch": 12.03,
      "learning_rate": 2.5e-07,
      "loss": 1.3695,
      "step": 391
    },
    {
      "epoch": 12.06,
      "learning_rate": 2.5e-07,
      "loss": 1.278,
      "step": 392
    },
    {
      "epoch": 12.09,
      "learning_rate": 2.5e-07,
      "loss": 1.4726,
      "step": 393
    },
    {
      "epoch": 12.12,
      "learning_rate": 2.5e-07,
      "loss": 1.142,
      "step": 394
    },
    {
      "epoch": 12.15,
      "learning_rate": 2.5e-07,
      "loss": 1.2075,
      "step": 395
    },
    {
      "epoch": 12.18,
      "learning_rate": 2.5e-07,
      "loss": 1.4716,
      "step": 396
    },
    {
      "epoch": 12.22,
      "learning_rate": 2.5e-07,
      "loss": 1.336,
      "step": 397
    },
    {
      "epoch": 12.25,
      "learning_rate": 2.5e-07,
      "loss": 1.0818,
      "step": 398
    },
    {
      "epoch": 12.28,
      "learning_rate": 2.5e-07,
      "loss": 1.3366,
      "step": 399
    },
    {
      "epoch": 12.31,
      "learning_rate": 2.5e-07,
      "loss": 1.3219,
      "step": 400
    },
    {
      "epoch": 12.31,
      "eval_loss": 1.2088563442230225,
      "eval_runtime": 1.7541,
      "eval_samples_per_second": 3.991,
      "eval_steps_per_second": 2.28,
      "step": 400
    },
    {
      "epoch": 12.34,
      "learning_rate": 2.5e-07,
      "loss": 1.4101,
      "step": 401
    },
    {
      "epoch": 12.37,
      "learning_rate": 2.5e-07,
      "loss": 1.2773,
      "step": 402
    },
    {
      "epoch": 12.4,
      "learning_rate": 2.5e-07,
      "loss": 1.3575,
      "step": 403
    },
    {
      "epoch": 12.43,
      "learning_rate": 2.5e-07,
      "loss": 1.089,
      "step": 404
    },
    {
      "epoch": 12.46,
      "learning_rate": 2.5e-07,
      "loss": 1.4164,
      "step": 405
    },
    {
      "epoch": 12.49,
      "learning_rate": 2.5e-07,
      "loss": 1.3292,
      "step": 406
    },
    {
      "epoch": 12.52,
      "learning_rate": 2.5e-07,
      "loss": 1.3447,
      "step": 407
    },
    {
      "epoch": 12.55,
      "learning_rate": 2.5e-07,
      "loss": 1.4455,
      "step": 408
    },
    {
      "epoch": 12.58,
      "learning_rate": 2.5e-07,
      "loss": 1.3716,
      "step": 409
    },
    {
      "epoch": 12.62,
      "learning_rate": 2.5e-07,
      "loss": 1.338,
      "step": 410
    },
    {
      "epoch": 12.65,
      "learning_rate": 2.5e-07,
      "loss": 1.2842,
      "step": 411
    },
    {
      "epoch": 12.68,
      "learning_rate": 2.5e-07,
      "loss": 1.0655,
      "step": 412
    },
    {
      "epoch": 12.71,
      "learning_rate": 2.5e-07,
      "loss": 1.1405,
      "step": 413
    },
    {
      "epoch": 12.74,
      "learning_rate": 2.5e-07,
      "loss": 1.3488,
      "step": 414
    },
    {
      "epoch": 12.77,
      "learning_rate": 2.5e-07,
      "loss": 1.1401,
      "step": 415
    },
    {
      "epoch": 12.8,
      "learning_rate": 2.5e-07,
      "loss": 1.2261,
      "step": 416
    },
    {
      "epoch": 12.83,
      "learning_rate": 2.5e-07,
      "loss": 1.2211,
      "step": 417
    },
    {
      "epoch": 12.86,
      "learning_rate": 2.5e-07,
      "loss": 1.235,
      "step": 418
    },
    {
      "epoch": 12.89,
      "learning_rate": 2.5e-07,
      "loss": 1.2779,
      "step": 419
    },
    {
      "epoch": 12.92,
      "learning_rate": 2.5e-07,
      "loss": 1.228,
      "step": 420
    },
    {
      "epoch": 12.95,
      "learning_rate": 2.5e-07,
      "loss": 1.3058,
      "step": 421
    },
    {
      "epoch": 12.98,
      "learning_rate": 2.5e-07,
      "loss": 1.2325,
      "step": 422
    },
    {
      "epoch": 13.02,
      "learning_rate": 2.5e-07,
      "loss": 1.3127,
      "step": 423
    },
    {
      "epoch": 13.05,
      "learning_rate": 2.5e-07,
      "loss": 1.382,
      "step": 424
    },
    {
      "epoch": 13.08,
      "learning_rate": 2.5e-07,
      "loss": 1.3625,
      "step": 425
    },
    {
      "epoch": 13.11,
      "learning_rate": 2.5e-07,
      "loss": 1.3533,
      "step": 426
    },
    {
      "epoch": 13.14,
      "learning_rate": 2.5e-07,
      "loss": 1.2046,
      "step": 427
    },
    {
      "epoch": 13.17,
      "learning_rate": 2.5e-07,
      "loss": 1.2991,
      "step": 428
    },
    {
      "epoch": 13.2,
      "learning_rate": 2.5e-07,
      "loss": 1.1785,
      "step": 429
    },
    {
      "epoch": 13.23,
      "learning_rate": 2.5e-07,
      "loss": 1.2795,
      "step": 430
    },
    {
      "epoch": 13.26,
      "learning_rate": 2.5e-07,
      "loss": 1.248,
      "step": 431
    },
    {
      "epoch": 13.29,
      "learning_rate": 2.5e-07,
      "loss": 1.3476,
      "step": 432
    },
    {
      "epoch": 13.32,
      "learning_rate": 2.5e-07,
      "loss": 1.277,
      "step": 433
    },
    {
      "epoch": 13.35,
      "learning_rate": 2.5e-07,
      "loss": 1.2044,
      "step": 434
    },
    {
      "epoch": 13.38,
      "learning_rate": 2.5e-07,
      "loss": 1.1909,
      "step": 435
    },
    {
      "epoch": 13.42,
      "learning_rate": 2.5e-07,
      "loss": 1.2544,
      "step": 436
    },
    {
      "epoch": 13.45,
      "learning_rate": 2.5e-07,
      "loss": 1.2036,
      "step": 437
    },
    {
      "epoch": 13.48,
      "learning_rate": 2.5e-07,
      "loss": 1.2141,
      "step": 438
    },
    {
      "epoch": 13.51,
      "learning_rate": 2.5e-07,
      "loss": 1.2086,
      "step": 439
    },
    {
      "epoch": 13.54,
      "learning_rate": 2.5e-07,
      "loss": 1.3863,
      "step": 440
    },
    {
      "epoch": 13.57,
      "learning_rate": 2.5e-07,
      "loss": 1.2435,
      "step": 441
    },
    {
      "epoch": 13.6,
      "learning_rate": 2.5e-07,
      "loss": 1.3655,
      "step": 442
    },
    {
      "epoch": 13.63,
      "learning_rate": 2.5e-07,
      "loss": 1.3562,
      "step": 443
    },
    {
      "epoch": 13.66,
      "learning_rate": 2.5e-07,
      "loss": 1.3441,
      "step": 444
    },
    {
      "epoch": 13.69,
      "learning_rate": 2.5e-07,
      "loss": 1.342,
      "step": 445
    },
    {
      "epoch": 13.72,
      "learning_rate": 2.5e-07,
      "loss": 1.0318,
      "step": 446
    },
    {
      "epoch": 13.75,
      "learning_rate": 2.5e-07,
      "loss": 1.3068,
      "step": 447
    },
    {
      "epoch": 13.78,
      "learning_rate": 2.5e-07,
      "loss": 1.4054,
      "step": 448
    },
    {
      "epoch": 13.82,
      "learning_rate": 2.5e-07,
      "loss": 1.1914,
      "step": 449
    },
    {
      "epoch": 13.85,
      "learning_rate": 2.5e-07,
      "loss": 1.3734,
      "step": 450
    },
    {
      "epoch": 13.88,
      "learning_rate": 2.5e-07,
      "loss": 1.3705,
      "step": 451
    },
    {
      "epoch": 13.91,
      "learning_rate": 2.5e-07,
      "loss": 1.2954,
      "step": 452
    },
    {
      "epoch": 13.94,
      "learning_rate": 2.5e-07,
      "loss": 1.2625,
      "step": 453
    },
    {
      "epoch": 13.97,
      "learning_rate": 2.5e-07,
      "loss": 1.0147,
      "step": 454
    },
    {
      "epoch": 14.0,
      "learning_rate": 2.5e-07,
      "loss": 1.2888,
      "step": 455
    },
    {
      "epoch": 14.03,
      "learning_rate": 2.5e-07,
      "loss": 1.1156,
      "step": 456
    },
    {
      "epoch": 14.06,
      "learning_rate": 2.5e-07,
      "loss": 1.421,
      "step": 457
    },
    {
      "epoch": 14.09,
      "learning_rate": 2.5e-07,
      "loss": 1.2285,
      "step": 458
    },
    {
      "epoch": 14.12,
      "learning_rate": 2.5e-07,
      "loss": 1.2881,
      "step": 459
    },
    {
      "epoch": 14.15,
      "learning_rate": 2.5e-07,
      "loss": 1.2028,
      "step": 460
    },
    {
      "epoch": 14.18,
      "learning_rate": 2.5e-07,
      "loss": 1.2213,
      "step": 461
    },
    {
      "epoch": 14.22,
      "learning_rate": 2.5e-07,
      "loss": 1.2455,
      "step": 462
    },
    {
      "epoch": 14.25,
      "learning_rate": 2.5e-07,
      "loss": 1.2788,
      "step": 463
    },
    {
      "epoch": 14.28,
      "learning_rate": 2.5e-07,
      "loss": 1.1349,
      "step": 464
    },
    {
      "epoch": 14.31,
      "learning_rate": 2.5e-07,
      "loss": 1.3234,
      "step": 465
    },
    {
      "epoch": 14.34,
      "learning_rate": 2.5e-07,
      "loss": 1.2652,
      "step": 466
    },
    {
      "epoch": 14.37,
      "learning_rate": 2.5e-07,
      "loss": 1.3123,
      "step": 467
    },
    {
      "epoch": 14.4,
      "learning_rate": 2.5e-07,
      "loss": 1.3447,
      "step": 468
    },
    {
      "epoch": 14.43,
      "learning_rate": 2.5e-07,
      "loss": 1.2818,
      "step": 469
    },
    {
      "epoch": 14.46,
      "learning_rate": 2.5e-07,
      "loss": 1.1331,
      "step": 470
    },
    {
      "epoch": 14.49,
      "learning_rate": 2.5e-07,
      "loss": 1.2309,
      "step": 471
    },
    {
      "epoch": 14.52,
      "learning_rate": 2.5e-07,
      "loss": 1.2867,
      "step": 472
    },
    {
      "epoch": 14.55,
      "learning_rate": 2.5e-07,
      "loss": 1.3339,
      "step": 473
    },
    {
      "epoch": 14.58,
      "learning_rate": 2.5e-07,
      "loss": 1.4158,
      "step": 474
    },
    {
      "epoch": 14.62,
      "learning_rate": 2.5e-07,
      "loss": 1.529,
      "step": 475
    },
    {
      "epoch": 14.65,
      "learning_rate": 2.5e-07,
      "loss": 1.258,
      "step": 476
    },
    {
      "epoch": 14.68,
      "learning_rate": 2.5e-07,
      "loss": 1.3033,
      "step": 477
    },
    {
      "epoch": 14.71,
      "learning_rate": 2.5e-07,
      "loss": 1.147,
      "step": 478
    },
    {
      "epoch": 14.74,
      "learning_rate": 2.5e-07,
      "loss": 1.3166,
      "step": 479
    },
    {
      "epoch": 14.77,
      "learning_rate": 2.5e-07,
      "loss": 1.2171,
      "step": 480
    },
    {
      "epoch": 14.77,
      "eval_loss": 1.1870461702346802,
      "eval_runtime": 1.7297,
      "eval_samples_per_second": 4.047,
      "eval_steps_per_second": 2.312,
      "step": 480
    },
    {
      "epoch": 14.8,
      "learning_rate": 2.5e-07,
      "loss": 1.18,
      "step": 481
    },
    {
      "epoch": 14.83,
      "learning_rate": 2.5e-07,
      "loss": 1.2117,
      "step": 482
    },
    {
      "epoch": 14.86,
      "learning_rate": 2.5e-07,
      "loss": 1.148,
      "step": 483
    },
    {
      "epoch": 14.89,
      "learning_rate": 2.5e-07,
      "loss": 1.3961,
      "step": 484
    },
    {
      "epoch": 14.92,
      "learning_rate": 2.5e-07,
      "loss": 1.3331,
      "step": 485
    },
    {
      "epoch": 14.95,
      "learning_rate": 2.5e-07,
      "loss": 1.3485,
      "step": 486
    },
    {
      "epoch": 14.98,
      "learning_rate": 2.5e-07,
      "loss": 1.0999,
      "step": 487
    },
    {
      "epoch": 15.02,
      "learning_rate": 2.5e-07,
      "loss": 1.2521,
      "step": 488
    },
    {
      "epoch": 15.05,
      "learning_rate": 2.5e-07,
      "loss": 1.2097,
      "step": 489
    },
    {
      "epoch": 15.08,
      "learning_rate": 2.5e-07,
      "loss": 1.2557,
      "step": 490
    },
    {
      "epoch": 15.11,
      "learning_rate": 2.5e-07,
      "loss": 1.2638,
      "step": 491
    },
    {
      "epoch": 15.14,
      "learning_rate": 2.5e-07,
      "loss": 1.3549,
      "step": 492
    },
    {
      "epoch": 15.17,
      "learning_rate": 2.5e-07,
      "loss": 1.2417,
      "step": 493
    },
    {
      "epoch": 15.2,
      "learning_rate": 2.5e-07,
      "loss": 1.2861,
      "step": 494
    },
    {
      "epoch": 15.23,
      "learning_rate": 2.5e-07,
      "loss": 1.2428,
      "step": 495
    },
    {
      "epoch": 15.26,
      "learning_rate": 2.5e-07,
      "loss": 1.1561,
      "step": 496
    },
    {
      "epoch": 15.29,
      "learning_rate": 2.5e-07,
      "loss": 1.2641,
      "step": 497
    },
    {
      "epoch": 15.32,
      "learning_rate": 2.5e-07,
      "loss": 1.3073,
      "step": 498
    },
    {
      "epoch": 15.35,
      "learning_rate": 2.5e-07,
      "loss": 1.2227,
      "step": 499
    },
    {
      "epoch": 15.38,
      "learning_rate": 2.5e-07,
      "loss": 1.3311,
      "step": 500
    },
    {
      "epoch": 15.42,
      "learning_rate": 2.5e-07,
      "loss": 1.2581,
      "step": 501
    },
    {
      "epoch": 15.45,
      "learning_rate": 2.5e-07,
      "loss": 1.2751,
      "step": 502
    },
    {
      "epoch": 15.48,
      "learning_rate": 2.5e-07,
      "loss": 1.4222,
      "step": 503
    },
    {
      "epoch": 15.51,
      "learning_rate": 2.5e-07,
      "loss": 1.3263,
      "step": 504
    },
    {
      "epoch": 15.54,
      "learning_rate": 2.5e-07,
      "loss": 1.2236,
      "step": 505
    },
    {
      "epoch": 15.57,
      "learning_rate": 2.5e-07,
      "loss": 1.3125,
      "step": 506
    },
    {
      "epoch": 15.6,
      "learning_rate": 2.5e-07,
      "loss": 1.424,
      "step": 507
    },
    {
      "epoch": 15.63,
      "learning_rate": 2.5e-07,
      "loss": 1.2231,
      "step": 508
    },
    {
      "epoch": 15.66,
      "learning_rate": 2.5e-07,
      "loss": 1.2089,
      "step": 509
    },
    {
      "epoch": 15.69,
      "learning_rate": 2.5e-07,
      "loss": 1.4663,
      "step": 510
    },
    {
      "epoch": 15.72,
      "learning_rate": 2.5e-07,
      "loss": 1.3236,
      "step": 511
    },
    {
      "epoch": 15.75,
      "learning_rate": 2.5e-07,
      "loss": 1.2133,
      "step": 512
    },
    {
      "epoch": 15.78,
      "learning_rate": 2.5e-07,
      "loss": 1.1598,
      "step": 513
    },
    {
      "epoch": 15.82,
      "learning_rate": 2.5e-07,
      "loss": 1.3023,
      "step": 514
    },
    {
      "epoch": 15.85,
      "learning_rate": 2.5e-07,
      "loss": 1.139,
      "step": 515
    },
    {
      "epoch": 15.88,
      "learning_rate": 2.5e-07,
      "loss": 1.1881,
      "step": 516
    },
    {
      "epoch": 15.91,
      "learning_rate": 2.5e-07,
      "loss": 1.1448,
      "step": 517
    },
    {
      "epoch": 15.94,
      "learning_rate": 2.5e-07,
      "loss": 1.2321,
      "step": 518
    },
    {
      "epoch": 15.97,
      "learning_rate": 2.5e-07,
      "loss": 1.2134,
      "step": 519
    },
    {
      "epoch": 16.0,
      "learning_rate": 2.5e-07,
      "loss": 1.3268,
      "step": 520
    },
    {
      "epoch": 16.03,
      "learning_rate": 2.5e-07,
      "loss": 1.3858,
      "step": 521
    },
    {
      "epoch": 16.06,
      "learning_rate": 2.5e-07,
      "loss": 1.3358,
      "step": 522
    },
    {
      "epoch": 16.09,
      "learning_rate": 2.5e-07,
      "loss": 1.2051,
      "step": 523
    },
    {
      "epoch": 16.12,
      "learning_rate": 2.5e-07,
      "loss": 1.1431,
      "step": 524
    },
    {
      "epoch": 16.15,
      "learning_rate": 2.5e-07,
      "loss": 1.2539,
      "step": 525
    },
    {
      "epoch": 16.18,
      "learning_rate": 2.5e-07,
      "loss": 1.3096,
      "step": 526
    },
    {
      "epoch": 16.22,
      "learning_rate": 2.5e-07,
      "loss": 1.1879,
      "step": 527
    },
    {
      "epoch": 16.25,
      "learning_rate": 2.5e-07,
      "loss": 1.3215,
      "step": 528
    },
    {
      "epoch": 16.28,
      "learning_rate": 2.5e-07,
      "loss": 1.2835,
      "step": 529
    },
    {
      "epoch": 16.31,
      "learning_rate": 2.5e-07,
      "loss": 1.2596,
      "step": 530
    },
    {
      "epoch": 16.34,
      "learning_rate": 2.5e-07,
      "loss": 1.2635,
      "step": 531
    },
    {
      "epoch": 16.37,
      "learning_rate": 2.5e-07,
      "loss": 1.4138,
      "step": 532
    },
    {
      "epoch": 16.4,
      "learning_rate": 2.5e-07,
      "loss": 1.2552,
      "step": 533
    },
    {
      "epoch": 16.43,
      "learning_rate": 2.5e-07,
      "loss": 1.337,
      "step": 534
    },
    {
      "epoch": 16.46,
      "learning_rate": 2.5e-07,
      "loss": 1.1408,
      "step": 535
    },
    {
      "epoch": 16.49,
      "learning_rate": 2.5e-07,
      "loss": 1.2962,
      "step": 536
    },
    {
      "epoch": 16.52,
      "learning_rate": 2.5e-07,
      "loss": 1.3547,
      "step": 537
    },
    {
      "epoch": 16.55,
      "learning_rate": 2.5e-07,
      "loss": 1.2199,
      "step": 538
    },
    {
      "epoch": 16.58,
      "learning_rate": 2.5e-07,
      "loss": 1.2924,
      "step": 539
    },
    {
      "epoch": 16.62,
      "learning_rate": 2.5e-07,
      "loss": 1.1342,
      "step": 540
    },
    {
      "epoch": 16.65,
      "learning_rate": 2.5e-07,
      "loss": 1.2628,
      "step": 541
    },
    {
      "epoch": 16.68,
      "learning_rate": 2.5e-07,
      "loss": 0.9506,
      "step": 542
    },
    {
      "epoch": 16.71,
      "learning_rate": 2.5e-07,
      "loss": 1.3052,
      "step": 543
    },
    {
      "epoch": 16.74,
      "learning_rate": 2.5e-07,
      "loss": 1.3089,
      "step": 544
    },
    {
      "epoch": 16.77,
      "learning_rate": 2.5e-07,
      "loss": 1.3776,
      "step": 545
    },
    {
      "epoch": 16.8,
      "learning_rate": 2.5e-07,
      "loss": 1.0516,
      "step": 546
    },
    {
      "epoch": 16.83,
      "learning_rate": 2.5e-07,
      "loss": 1.1433,
      "step": 547
    },
    {
      "epoch": 16.86,
      "learning_rate": 2.5e-07,
      "loss": 1.3056,
      "step": 548
    },
    {
      "epoch": 16.89,
      "learning_rate": 2.5e-07,
      "loss": 1.2652,
      "step": 549
    },
    {
      "epoch": 16.92,
      "learning_rate": 2.5e-07,
      "loss": 1.2002,
      "step": 550
    },
    {
      "epoch": 16.95,
      "learning_rate": 2.5e-07,
      "loss": 1.181,
      "step": 551
    },
    {
      "epoch": 16.98,
      "learning_rate": 2.5e-07,
      "loss": 1.0902,
      "step": 552
    },
    {
      "epoch": 17.02,
      "learning_rate": 2.5e-07,
      "loss": 1.2845,
      "step": 553
    },
    {
      "epoch": 17.05,
      "learning_rate": 2.5e-07,
      "loss": 1.2646,
      "step": 554
    },
    {
      "epoch": 17.08,
      "learning_rate": 2.5e-07,
      "loss": 1.0982,
      "step": 555
    },
    {
      "epoch": 17.11,
      "learning_rate": 2.5e-07,
      "loss": 1.1109,
      "step": 556
    },
    {
      "epoch": 17.14,
      "learning_rate": 2.5e-07,
      "loss": 1.2508,
      "step": 557
    },
    {
      "epoch": 17.17,
      "learning_rate": 2.5e-07,
      "loss": 1.2859,
      "step": 558
    },
    {
      "epoch": 17.2,
      "learning_rate": 2.5e-07,
      "loss": 0.9845,
      "step": 559
    },
    {
      "epoch": 17.23,
      "learning_rate": 2.5e-07,
      "loss": 1.1686,
      "step": 560
    },
    {
      "epoch": 17.23,
      "eval_loss": 1.173031210899353,
      "eval_runtime": 1.7371,
      "eval_samples_per_second": 4.03,
      "eval_steps_per_second": 2.303,
      "step": 560
    },
    {
      "epoch": 17.26,
      "learning_rate": 2.5e-07,
      "loss": 1.2483,
      "step": 561
    },
    {
      "epoch": 17.29,
      "learning_rate": 2.5e-07,
      "loss": 1.3438,
      "step": 562
    },
    {
      "epoch": 17.32,
      "learning_rate": 2.5e-07,
      "loss": 1.2862,
      "step": 563
    },
    {
      "epoch": 17.35,
      "learning_rate": 2.5e-07,
      "loss": 1.2464,
      "step": 564
    },
    {
      "epoch": 17.38,
      "learning_rate": 2.5e-07,
      "loss": 1.3084,
      "step": 565
    },
    {
      "epoch": 17.42,
      "learning_rate": 2.5e-07,
      "loss": 1.2382,
      "step": 566
    },
    {
      "epoch": 17.45,
      "learning_rate": 2.5e-07,
      "loss": 1.2763,
      "step": 567
    },
    {
      "epoch": 17.48,
      "learning_rate": 2.5e-07,
      "loss": 1.1901,
      "step": 568
    },
    {
      "epoch": 17.51,
      "learning_rate": 2.5e-07,
      "loss": 1.0708,
      "step": 569
    },
    {
      "epoch": 17.54,
      "learning_rate": 2.5e-07,
      "loss": 1.2879,
      "step": 570
    },
    {
      "epoch": 17.57,
      "learning_rate": 2.5e-07,
      "loss": 1.2257,
      "step": 571
    },
    {
      "epoch": 17.6,
      "learning_rate": 2.5e-07,
      "loss": 1.06,
      "step": 572
    },
    {
      "epoch": 17.63,
      "learning_rate": 2.5e-07,
      "loss": 1.3583,
      "step": 573
    },
    {
      "epoch": 17.66,
      "learning_rate": 2.5e-07,
      "loss": 1.2269,
      "step": 574
    },
    {
      "epoch": 17.69,
      "learning_rate": 2.5e-07,
      "loss": 1.3294,
      "step": 575
    },
    {
      "epoch": 17.72,
      "learning_rate": 2.5e-07,
      "loss": 1.3498,
      "step": 576
    },
    {
      "epoch": 17.75,
      "learning_rate": 2.5e-07,
      "loss": 1.0898,
      "step": 577
    },
    {
      "epoch": 17.78,
      "learning_rate": 2.5e-07,
      "loss": 1.2676,
      "step": 578
    },
    {
      "epoch": 17.82,
      "learning_rate": 2.5e-07,
      "loss": 1.3162,
      "step": 579
    },
    {
      "epoch": 17.85,
      "learning_rate": 2.5e-07,
      "loss": 1.3982,
      "step": 580
    },
    {
      "epoch": 17.88,
      "learning_rate": 2.5e-07,
      "loss": 1.3926,
      "step": 581
    },
    {
      "epoch": 17.91,
      "learning_rate": 2.5e-07,
      "loss": 1.1394,
      "step": 582
    },
    {
      "epoch": 17.94,
      "learning_rate": 2.5e-07,
      "loss": 1.2473,
      "step": 583
    },
    {
      "epoch": 17.97,
      "learning_rate": 2.5e-07,
      "loss": 1.1476,
      "step": 584
    },
    {
      "epoch": 18.0,
      "learning_rate": 2.5e-07,
      "loss": 1.226,
      "step": 585
    },
    {
      "epoch": 18.03,
      "learning_rate": 2.5e-07,
      "loss": 1.2704,
      "step": 586
    },
    {
      "epoch": 18.06,
      "learning_rate": 2.5e-07,
      "loss": 0.9477,
      "step": 587
    },
    {
      "epoch": 18.09,
      "learning_rate": 2.5e-07,
      "loss": 1.3465,
      "step": 588
    },
    {
      "epoch": 18.12,
      "learning_rate": 2.5e-07,
      "loss": 1.3294,
      "step": 589
    },
    {
      "epoch": 18.15,
      "learning_rate": 2.5e-07,
      "loss": 1.057,
      "step": 590
    },
    {
      "epoch": 18.18,
      "learning_rate": 2.5e-07,
      "loss": 1.2434,
      "step": 591
    },
    {
      "epoch": 18.22,
      "learning_rate": 2.5e-07,
      "loss": 1.2729,
      "step": 592
    },
    {
      "epoch": 18.25,
      "learning_rate": 2.5e-07,
      "loss": 1.1356,
      "step": 593
    },
    {
      "epoch": 18.28,
      "learning_rate": 2.5e-07,
      "loss": 1.1587,
      "step": 594
    },
    {
      "epoch": 18.31,
      "learning_rate": 2.5e-07,
      "loss": 1.1197,
      "step": 595
    },
    {
      "epoch": 18.34,
      "learning_rate": 2.5e-07,
      "loss": 1.1778,
      "step": 596
    },
    {
      "epoch": 18.37,
      "learning_rate": 2.5e-07,
      "loss": 1.1198,
      "step": 597
    },
    {
      "epoch": 18.4,
      "learning_rate": 2.5e-07,
      "loss": 1.3865,
      "step": 598
    },
    {
      "epoch": 18.43,
      "learning_rate": 2.5e-07,
      "loss": 1.2218,
      "step": 599
    },
    {
      "epoch": 18.46,
      "learning_rate": 2.5e-07,
      "loss": 1.0191,
      "step": 600
    },
    {
      "epoch": 18.49,
      "learning_rate": 2.5e-07,
      "loss": 1.3666,
      "step": 601
    },
    {
      "epoch": 18.52,
      "learning_rate": 2.5e-07,
      "loss": 1.3141,
      "step": 602
    },
    {
      "epoch": 18.55,
      "learning_rate": 2.5e-07,
      "loss": 1.279,
      "step": 603
    },
    {
      "epoch": 18.58,
      "learning_rate": 2.5e-07,
      "loss": 1.32,
      "step": 604
    },
    {
      "epoch": 18.62,
      "learning_rate": 2.5e-07,
      "loss": 1.3216,
      "step": 605
    },
    {
      "epoch": 18.65,
      "learning_rate": 2.5e-07,
      "loss": 1.1378,
      "step": 606
    },
    {
      "epoch": 18.68,
      "learning_rate": 2.5e-07,
      "loss": 1.174,
      "step": 607
    },
    {
      "epoch": 18.71,
      "learning_rate": 2.5e-07,
      "loss": 1.1897,
      "step": 608
    },
    {
      "epoch": 18.74,
      "learning_rate": 2.5e-07,
      "loss": 1.2227,
      "step": 609
    },
    {
      "epoch": 18.77,
      "learning_rate": 2.5e-07,
      "loss": 1.2315,
      "step": 610
    },
    {
      "epoch": 18.8,
      "learning_rate": 2.5e-07,
      "loss": 1.1637,
      "step": 611
    },
    {
      "epoch": 18.83,
      "learning_rate": 2.5e-07,
      "loss": 1.2978,
      "step": 612
    },
    {
      "epoch": 18.86,
      "learning_rate": 2.5e-07,
      "loss": 1.2103,
      "step": 613
    },
    {
      "epoch": 18.89,
      "learning_rate": 2.5e-07,
      "loss": 1.3145,
      "step": 614
    },
    {
      "epoch": 18.92,
      "learning_rate": 2.5e-07,
      "loss": 1.2807,
      "step": 615
    },
    {
      "epoch": 18.95,
      "learning_rate": 2.5e-07,
      "loss": 1.2668,
      "step": 616
    },
    {
      "epoch": 18.98,
      "learning_rate": 2.5e-07,
      "loss": 1.2986,
      "step": 617
    },
    {
      "epoch": 19.02,
      "learning_rate": 2.5e-07,
      "loss": 1.1996,
      "step": 618
    },
    {
      "epoch": 19.05,
      "learning_rate": 2.5e-07,
      "loss": 0.9905,
      "step": 619
    },
    {
      "epoch": 19.08,
      "learning_rate": 2.5e-07,
      "loss": 1.3338,
      "step": 620
    },
    {
      "epoch": 19.11,
      "learning_rate": 2.5e-07,
      "loss": 1.0955,
      "step": 621
    },
    {
      "epoch": 19.14,
      "learning_rate": 2.5e-07,
      "loss": 1.1721,
      "step": 622
    },
    {
      "epoch": 19.17,
      "learning_rate": 2.5e-07,
      "loss": 1.2088,
      "step": 623
    },
    {
      "epoch": 19.2,
      "learning_rate": 2.5e-07,
      "loss": 1.3623,
      "step": 624
    },
    {
      "epoch": 19.23,
      "learning_rate": 2.5e-07,
      "loss": 1.0578,
      "step": 625
    },
    {
      "epoch": 19.26,
      "learning_rate": 2.5e-07,
      "loss": 1.0765,
      "step": 626
    },
    {
      "epoch": 19.29,
      "learning_rate": 2.5e-07,
      "loss": 1.3624,
      "step": 627
    },
    {
      "epoch": 19.32,
      "learning_rate": 2.5e-07,
      "loss": 1.1778,
      "step": 628
    },
    {
      "epoch": 19.35,
      "learning_rate": 2.5e-07,
      "loss": 1.2267,
      "step": 629
    },
    {
      "epoch": 19.38,
      "learning_rate": 2.5e-07,
      "loss": 1.2311,
      "step": 630
    },
    {
      "epoch": 19.42,
      "learning_rate": 2.5e-07,
      "loss": 1.3226,
      "step": 631
    },
    {
      "epoch": 19.45,
      "learning_rate": 2.5e-07,
      "loss": 1.2294,
      "step": 632
    },
    {
      "epoch": 19.48,
      "learning_rate": 2.5e-07,
      "loss": 1.0192,
      "step": 633
    },
    {
      "epoch": 19.51,
      "learning_rate": 2.5e-07,
      "loss": 1.2559,
      "step": 634
    },
    {
      "epoch": 19.54,
      "learning_rate": 2.5e-07,
      "loss": 1.2497,
      "step": 635
    },
    {
      "epoch": 19.57,
      "learning_rate": 2.5e-07,
      "loss": 1.4026,
      "step": 636
    },
    {
      "epoch": 19.6,
      "learning_rate": 2.5e-07,
      "loss": 1.2551,
      "step": 637
    },
    {
      "epoch": 19.63,
      "learning_rate": 2.5e-07,
      "loss": 1.2695,
      "step": 638
    },
    {
      "epoch": 19.66,
      "learning_rate": 2.5e-07,
      "loss": 1.2047,
      "step": 639
    },
    {
      "epoch": 19.69,
      "learning_rate": 2.5e-07,
      "loss": 1.1506,
      "step": 640
    },
    {
      "epoch": 19.69,
      "eval_loss": 1.161481261253357,
      "eval_runtime": 1.7425,
      "eval_samples_per_second": 4.017,
      "eval_steps_per_second": 2.296,
      "step": 640
    },
    {
      "epoch": 19.72,
      "learning_rate": 2.5e-07,
      "loss": 1.2597,
      "step": 641
    },
    {
      "epoch": 19.75,
      "learning_rate": 2.5e-07,
      "loss": 1.1908,
      "step": 642
    },
    {
      "epoch": 19.78,
      "learning_rate": 2.5e-07,
      "loss": 1.2338,
      "step": 643
    },
    {
      "epoch": 19.82,
      "learning_rate": 2.5e-07,
      "loss": 1.31,
      "step": 644
    },
    {
      "epoch": 19.85,
      "learning_rate": 2.5e-07,
      "loss": 1.0713,
      "step": 645
    },
    {
      "epoch": 19.88,
      "learning_rate": 2.5e-07,
      "loss": 1.2727,
      "step": 646
    },
    {
      "epoch": 19.91,
      "learning_rate": 2.5e-07,
      "loss": 1.2029,
      "step": 647
    },
    {
      "epoch": 19.94,
      "learning_rate": 2.5e-07,
      "loss": 1.3007,
      "step": 648
    },
    {
      "epoch": 19.97,
      "learning_rate": 2.5e-07,
      "loss": 1.3173,
      "step": 649
    },
    {
      "epoch": 20.0,
      "learning_rate": 2.5e-07,
      "loss": 1.2024,
      "step": 650
    },
    {
      "epoch": 20.03,
      "learning_rate": 2.5e-07,
      "loss": 1.1753,
      "step": 651
    },
    {
      "epoch": 20.06,
      "learning_rate": 2.5e-07,
      "loss": 1.273,
      "step": 652
    },
    {
      "epoch": 20.09,
      "learning_rate": 2.5e-07,
      "loss": 1.2252,
      "step": 653
    },
    {
      "epoch": 20.12,
      "learning_rate": 2.5e-07,
      "loss": 1.2582,
      "step": 654
    },
    {
      "epoch": 20.15,
      "learning_rate": 2.5e-07,
      "loss": 1.2634,
      "step": 655
    },
    {
      "epoch": 20.18,
      "learning_rate": 2.5e-07,
      "loss": 1.2168,
      "step": 656
    },
    {
      "epoch": 20.22,
      "learning_rate": 2.5e-07,
      "loss": 1.2868,
      "step": 657
    },
    {
      "epoch": 20.25,
      "learning_rate": 2.5e-07,
      "loss": 1.2229,
      "step": 658
    },
    {
      "epoch": 20.28,
      "learning_rate": 2.5e-07,
      "loss": 1.0799,
      "step": 659
    },
    {
      "epoch": 20.31,
      "learning_rate": 2.5e-07,
      "loss": 1.187,
      "step": 660
    },
    {
      "epoch": 20.34,
      "learning_rate": 2.5e-07,
      "loss": 1.3681,
      "step": 661
    },
    {
      "epoch": 20.37,
      "learning_rate": 2.5e-07,
      "loss": 1.1951,
      "step": 662
    },
    {
      "epoch": 20.4,
      "learning_rate": 2.5e-07,
      "loss": 1.0643,
      "step": 663
    },
    {
      "epoch": 20.43,
      "learning_rate": 2.5e-07,
      "loss": 1.2073,
      "step": 664
    },
    {
      "epoch": 20.46,
      "learning_rate": 2.5e-07,
      "loss": 1.2797,
      "step": 665
    },
    {
      "epoch": 20.49,
      "learning_rate": 2.5e-07,
      "loss": 1.3999,
      "step": 666
    },
    {
      "epoch": 20.52,
      "learning_rate": 2.5e-07,
      "loss": 1.2501,
      "step": 667
    },
    {
      "epoch": 20.55,
      "learning_rate": 2.5e-07,
      "loss": 1.2163,
      "step": 668
    },
    {
      "epoch": 20.58,
      "learning_rate": 2.5e-07,
      "loss": 1.3067,
      "step": 669
    },
    {
      "epoch": 20.62,
      "learning_rate": 2.5e-07,
      "loss": 1.1854,
      "step": 670
    },
    {
      "epoch": 20.65,
      "learning_rate": 2.5e-07,
      "loss": 1.1188,
      "step": 671
    },
    {
      "epoch": 20.68,
      "learning_rate": 2.5e-07,
      "loss": 1.2344,
      "step": 672
    },
    {
      "epoch": 20.71,
      "learning_rate": 2.5e-07,
      "loss": 1.2431,
      "step": 673
    },
    {
      "epoch": 20.74,
      "learning_rate": 2.5e-07,
      "loss": 1.1848,
      "step": 674
    },
    {
      "epoch": 20.77,
      "learning_rate": 2.5e-07,
      "loss": 1.3042,
      "step": 675
    },
    {
      "epoch": 20.8,
      "learning_rate": 2.5e-07,
      "loss": 1.121,
      "step": 676
    },
    {
      "epoch": 20.83,
      "learning_rate": 2.5e-07,
      "loss": 1.1777,
      "step": 677
    },
    {
      "epoch": 20.86,
      "learning_rate": 2.5e-07,
      "loss": 1.2183,
      "step": 678
    },
    {
      "epoch": 20.89,
      "learning_rate": 2.5e-07,
      "loss": 1.1327,
      "step": 679
    },
    {
      "epoch": 20.92,
      "learning_rate": 2.5e-07,
      "loss": 1.1136,
      "step": 680
    },
    {
      "epoch": 20.95,
      "learning_rate": 2.5e-07,
      "loss": 1.2761,
      "step": 681
    },
    {
      "epoch": 20.98,
      "learning_rate": 2.5e-07,
      "loss": 1.079,
      "step": 682
    },
    {
      "epoch": 21.02,
      "learning_rate": 2.5e-07,
      "loss": 1.2263,
      "step": 683
    },
    {
      "epoch": 21.05,
      "learning_rate": 2.5e-07,
      "loss": 1.2507,
      "step": 684
    },
    {
      "epoch": 21.08,
      "learning_rate": 2.5e-07,
      "loss": 1.1574,
      "step": 685
    },
    {
      "epoch": 21.11,
      "learning_rate": 2.5e-07,
      "loss": 1.0829,
      "step": 686
    },
    {
      "epoch": 21.14,
      "learning_rate": 2.5e-07,
      "loss": 1.2645,
      "step": 687
    },
    {
      "epoch": 21.17,
      "learning_rate": 2.5e-07,
      "loss": 1.2632,
      "step": 688
    },
    {
      "epoch": 21.2,
      "learning_rate": 2.5e-07,
      "loss": 1.2332,
      "step": 689
    },
    {
      "epoch": 21.23,
      "learning_rate": 2.5e-07,
      "loss": 1.2069,
      "step": 690
    },
    {
      "epoch": 21.26,
      "learning_rate": 2.5e-07,
      "loss": 1.2087,
      "step": 691
    },
    {
      "epoch": 21.29,
      "learning_rate": 2.5e-07,
      "loss": 1.1768,
      "step": 692
    },
    {
      "epoch": 21.32,
      "learning_rate": 2.5e-07,
      "loss": 1.0126,
      "step": 693
    },
    {
      "epoch": 21.35,
      "learning_rate": 2.5e-07,
      "loss": 1.3168,
      "step": 694
    },
    {
      "epoch": 21.38,
      "learning_rate": 2.5e-07,
      "loss": 1.0629,
      "step": 695
    },
    {
      "epoch": 21.42,
      "learning_rate": 2.5e-07,
      "loss": 1.1156,
      "step": 696
    },
    {
      "epoch": 21.45,
      "learning_rate": 2.5e-07,
      "loss": 1.2308,
      "step": 697
    },
    {
      "epoch": 21.48,
      "learning_rate": 2.5e-07,
      "loss": 1.2688,
      "step": 698
    },
    {
      "epoch": 21.51,
      "learning_rate": 2.5e-07,
      "loss": 1.1114,
      "step": 699
    },
    {
      "epoch": 21.54,
      "learning_rate": 2.5e-07,
      "loss": 1.0432,
      "step": 700
    },
    {
      "epoch": 21.57,
      "learning_rate": 2.5e-07,
      "loss": 1.2938,
      "step": 701
    },
    {
      "epoch": 21.6,
      "learning_rate": 2.5e-07,
      "loss": 1.2673,
      "step": 702
    },
    {
      "epoch": 21.63,
      "learning_rate": 2.5e-07,
      "loss": 1.2795,
      "step": 703
    },
    {
      "epoch": 21.66,
      "learning_rate": 2.5e-07,
      "loss": 1.1992,
      "step": 704
    },
    {
      "epoch": 21.69,
      "learning_rate": 2.5e-07,
      "loss": 1.2114,
      "step": 705
    },
    {
      "epoch": 21.72,
      "learning_rate": 2.5e-07,
      "loss": 1.1559,
      "step": 706
    },
    {
      "epoch": 21.75,
      "learning_rate": 2.5e-07,
      "loss": 1.1923,
      "step": 707
    },
    {
      "epoch": 21.78,
      "learning_rate": 2.5e-07,
      "loss": 1.135,
      "step": 708
    },
    {
      "epoch": 21.82,
      "learning_rate": 2.5e-07,
      "loss": 1.1937,
      "step": 709
    },
    {
      "epoch": 21.85,
      "learning_rate": 2.5e-07,
      "loss": 1.3328,
      "step": 710
    },
    {
      "epoch": 21.88,
      "learning_rate": 2.5e-07,
      "loss": 1.2513,
      "step": 711
    },
    {
      "epoch": 21.91,
      "learning_rate": 2.5e-07,
      "loss": 1.197,
      "step": 712
    },
    {
      "epoch": 21.94,
      "learning_rate": 2.5e-07,
      "loss": 1.0483,
      "step": 713
    },
    {
      "epoch": 21.97,
      "learning_rate": 2.5e-07,
      "loss": 1.3072,
      "step": 714
    },
    {
      "epoch": 22.0,
      "learning_rate": 2.5e-07,
      "loss": 1.2929,
      "step": 715
    },
    {
      "epoch": 22.03,
      "learning_rate": 2.5e-07,
      "loss": 1.2504,
      "step": 716
    },
    {
      "epoch": 22.06,
      "learning_rate": 2.5e-07,
      "loss": 1.0944,
      "step": 717
    },
    {
      "epoch": 22.09,
      "learning_rate": 2.5e-07,
      "loss": 1.2897,
      "step": 718
    },
    {
      "epoch": 22.12,
      "learning_rate": 2.5e-07,
      "loss": 1.1668,
      "step": 719
    },
    {
      "epoch": 22.15,
      "learning_rate": 2.5e-07,
      "loss": 1.1829,
      "step": 720
    },
    {
      "epoch": 22.15,
      "eval_loss": 1.151276707649231,
      "eval_runtime": 1.757,
      "eval_samples_per_second": 3.984,
      "eval_steps_per_second": 2.277,
      "step": 720
    },
    {
      "epoch": 22.18,
      "learning_rate": 2.5e-07,
      "loss": 1.1646,
      "step": 721
    },
    {
      "epoch": 22.22,
      "learning_rate": 2.5e-07,
      "loss": 1.2432,
      "step": 722
    },
    {
      "epoch": 22.25,
      "learning_rate": 2.5e-07,
      "loss": 1.3598,
      "step": 723
    },
    {
      "epoch": 22.28,
      "learning_rate": 2.5e-07,
      "loss": 0.9391,
      "step": 724
    },
    {
      "epoch": 22.31,
      "learning_rate": 2.5e-07,
      "loss": 1.2974,
      "step": 725
    },
    {
      "epoch": 22.34,
      "learning_rate": 2.5e-07,
      "loss": 1.2225,
      "step": 726
    },
    {
      "epoch": 22.37,
      "learning_rate": 2.5e-07,
      "loss": 1.2099,
      "step": 727
    },
    {
      "epoch": 22.4,
      "learning_rate": 2.5e-07,
      "loss": 1.1805,
      "step": 728
    },
    {
      "epoch": 22.43,
      "learning_rate": 2.5e-07,
      "loss": 1.1195,
      "step": 729
    },
    {
      "epoch": 22.46,
      "learning_rate": 2.5e-07,
      "loss": 1.1393,
      "step": 730
    },
    {
      "epoch": 22.49,
      "learning_rate": 2.5e-07,
      "loss": 1.0755,
      "step": 731
    },
    {
      "epoch": 22.52,
      "learning_rate": 2.5e-07,
      "loss": 1.299,
      "step": 732
    },
    {
      "epoch": 22.55,
      "learning_rate": 2.5e-07,
      "loss": 1.2319,
      "step": 733
    },
    {
      "epoch": 22.58,
      "learning_rate": 2.5e-07,
      "loss": 1.1846,
      "step": 734
    },
    {
      "epoch": 22.62,
      "learning_rate": 2.5e-07,
      "loss": 1.3545,
      "step": 735
    },
    {
      "epoch": 22.65,
      "learning_rate": 2.5e-07,
      "loss": 1.1044,
      "step": 736
    },
    {
      "epoch": 22.68,
      "learning_rate": 2.5e-07,
      "loss": 1.1402,
      "step": 737
    },
    {
      "epoch": 22.71,
      "learning_rate": 2.5e-07,
      "loss": 1.2412,
      "step": 738
    },
    {
      "epoch": 22.74,
      "learning_rate": 2.5e-07,
      "loss": 1.2066,
      "step": 739
    },
    {
      "epoch": 22.77,
      "learning_rate": 2.5e-07,
      "loss": 1.243,
      "step": 740
    },
    {
      "epoch": 22.8,
      "learning_rate": 2.5e-07,
      "loss": 1.037,
      "step": 741
    },
    {
      "epoch": 22.83,
      "learning_rate": 2.5e-07,
      "loss": 1.1585,
      "step": 742
    },
    {
      "epoch": 22.86,
      "learning_rate": 2.5e-07,
      "loss": 1.2563,
      "step": 743
    },
    {
      "epoch": 22.89,
      "learning_rate": 2.5e-07,
      "loss": 1.2223,
      "step": 744
    },
    {
      "epoch": 22.92,
      "learning_rate": 2.5e-07,
      "loss": 1.1915,
      "step": 745
    },
    {
      "epoch": 22.95,
      "learning_rate": 2.5e-07,
      "loss": 1.2192,
      "step": 746
    },
    {
      "epoch": 22.98,
      "learning_rate": 2.5e-07,
      "loss": 1.0116,
      "step": 747
    },
    {
      "epoch": 23.02,
      "learning_rate": 2.5e-07,
      "loss": 1.3601,
      "step": 748
    },
    {
      "epoch": 23.05,
      "learning_rate": 2.5e-07,
      "loss": 0.9849,
      "step": 749
    },
    {
      "epoch": 23.08,
      "learning_rate": 2.5e-07,
      "loss": 1.238,
      "step": 750
    },
    {
      "epoch": 23.11,
      "learning_rate": 2.5e-07,
      "loss": 1.1157,
      "step": 751
    },
    {
      "epoch": 23.14,
      "learning_rate": 2.5e-07,
      "loss": 1.1531,
      "step": 752
    },
    {
      "epoch": 23.17,
      "learning_rate": 2.5e-07,
      "loss": 1.2322,
      "step": 753
    },
    {
      "epoch": 23.2,
      "learning_rate": 2.5e-07,
      "loss": 1.1656,
      "step": 754
    },
    {
      "epoch": 23.23,
      "learning_rate": 2.5e-07,
      "loss": 1.1579,
      "step": 755
    },
    {
      "epoch": 23.26,
      "learning_rate": 2.5e-07,
      "loss": 1.1663,
      "step": 756
    },
    {
      "epoch": 23.29,
      "learning_rate": 2.5e-07,
      "loss": 1.2587,
      "step": 757
    },
    {
      "epoch": 23.32,
      "learning_rate": 2.5e-07,
      "loss": 1.2768,
      "step": 758
    },
    {
      "epoch": 23.35,
      "learning_rate": 2.5e-07,
      "loss": 1.1416,
      "step": 759
    },
    {
      "epoch": 23.38,
      "learning_rate": 2.5e-07,
      "loss": 1.2223,
      "step": 760
    },
    {
      "epoch": 23.42,
      "learning_rate": 2.5e-07,
      "loss": 1.2657,
      "step": 761
    },
    {
      "epoch": 23.45,
      "learning_rate": 2.5e-07,
      "loss": 1.0958,
      "step": 762
    },
    {
      "epoch": 23.48,
      "learning_rate": 2.5e-07,
      "loss": 1.1521,
      "step": 763
    },
    {
      "epoch": 23.51,
      "learning_rate": 2.5e-07,
      "loss": 1.0966,
      "step": 764
    },
    {
      "epoch": 23.54,
      "learning_rate": 2.5e-07,
      "loss": 1.1623,
      "step": 765
    },
    {
      "epoch": 23.57,
      "learning_rate": 2.5e-07,
      "loss": 1.2151,
      "step": 766
    },
    {
      "epoch": 23.6,
      "learning_rate": 2.5e-07,
      "loss": 1.163,
      "step": 767
    },
    {
      "epoch": 23.63,
      "learning_rate": 2.5e-07,
      "loss": 1.1975,
      "step": 768
    },
    {
      "epoch": 23.66,
      "learning_rate": 2.5e-07,
      "loss": 1.3573,
      "step": 769
    },
    {
      "epoch": 23.69,
      "learning_rate": 2.5e-07,
      "loss": 1.2025,
      "step": 770
    },
    {
      "epoch": 23.72,
      "learning_rate": 2.5e-07,
      "loss": 1.2213,
      "step": 771
    },
    {
      "epoch": 23.75,
      "learning_rate": 2.5e-07,
      "loss": 1.3908,
      "step": 772
    },
    {
      "epoch": 23.78,
      "learning_rate": 2.5e-07,
      "loss": 1.2604,
      "step": 773
    },
    {
      "epoch": 23.82,
      "learning_rate": 2.5e-07,
      "loss": 1.1152,
      "step": 774
    },
    {
      "epoch": 23.85,
      "learning_rate": 2.5e-07,
      "loss": 1.2275,
      "step": 775
    },
    {
      "epoch": 23.88,
      "learning_rate": 2.5e-07,
      "loss": 1.0982,
      "step": 776
    },
    {
      "epoch": 23.91,
      "learning_rate": 2.5e-07,
      "loss": 1.2497,
      "step": 777
    },
    {
      "epoch": 23.94,
      "learning_rate": 2.5e-07,
      "loss": 1.2903,
      "step": 778
    },
    {
      "epoch": 23.97,
      "learning_rate": 2.5e-07,
      "loss": 1.3096,
      "step": 779
    },
    {
      "epoch": 24.0,
      "learning_rate": 2.5e-07,
      "loss": 1.2009,
      "step": 780
    },
    {
      "epoch": 24.03,
      "learning_rate": 2.5e-07,
      "loss": 1.2357,
      "step": 781
    },
    {
      "epoch": 24.06,
      "learning_rate": 2.5e-07,
      "loss": 1.2579,
      "step": 782
    },
    {
      "epoch": 24.09,
      "learning_rate": 2.5e-07,
      "loss": 1.2434,
      "step": 783
    },
    {
      "epoch": 24.12,
      "learning_rate": 2.5e-07,
      "loss": 1.198,
      "step": 784
    },
    {
      "epoch": 24.15,
      "learning_rate": 2.5e-07,
      "loss": 1.1289,
      "step": 785
    },
    {
      "epoch": 24.18,
      "learning_rate": 2.5e-07,
      "loss": 1.2248,
      "step": 786
    },
    {
      "epoch": 24.22,
      "learning_rate": 2.5e-07,
      "loss": 1.2352,
      "step": 787
    },
    {
      "epoch": 24.25,
      "learning_rate": 2.5e-07,
      "loss": 1.1982,
      "step": 788
    },
    {
      "epoch": 24.28,
      "learning_rate": 2.5e-07,
      "loss": 1.2262,
      "step": 789
    },
    {
      "epoch": 24.31,
      "learning_rate": 2.5e-07,
      "loss": 1.2906,
      "step": 790
    },
    {
      "epoch": 24.34,
      "learning_rate": 2.5e-07,
      "loss": 1.1845,
      "step": 791
    },
    {
      "epoch": 24.37,
      "learning_rate": 2.5e-07,
      "loss": 1.2187,
      "step": 792
    },
    {
      "epoch": 24.4,
      "learning_rate": 2.5e-07,
      "loss": 1.1024,
      "step": 793
    },
    {
      "epoch": 24.43,
      "learning_rate": 2.5e-07,
      "loss": 1.3153,
      "step": 794
    },
    {
      "epoch": 24.46,
      "learning_rate": 2.5e-07,
      "loss": 1.0233,
      "step": 795
    },
    {
      "epoch": 24.49,
      "learning_rate": 2.5e-07,
      "loss": 1.1543,
      "step": 796
    },
    {
      "epoch": 24.52,
      "learning_rate": 2.5e-07,
      "loss": 1.1003,
      "step": 797
    },
    {
      "epoch": 24.55,
      "learning_rate": 2.5e-07,
      "loss": 1.212,
      "step": 798
    },
    {
      "epoch": 24.58,
      "learning_rate": 2.5e-07,
      "loss": 1.1479,
      "step": 799
    },
    {
      "epoch": 24.62,
      "learning_rate": 2.5e-07,
      "loss": 1.267,
      "step": 800
    },
    {
      "epoch": 24.62,
      "eval_loss": 1.1453821659088135,
      "eval_runtime": 1.7358,
      "eval_samples_per_second": 4.033,
      "eval_steps_per_second": 2.304,
      "step": 800
    },
    {
      "epoch": 24.65,
      "learning_rate": 2.5e-07,
      "loss": 1.0811,
      "step": 801
    },
    {
      "epoch": 24.68,
      "learning_rate": 2.5e-07,
      "loss": 1.318,
      "step": 802
    },
    {
      "epoch": 24.71,
      "learning_rate": 2.5e-07,
      "loss": 1.2086,
      "step": 803
    },
    {
      "epoch": 24.74,
      "learning_rate": 2.5e-07,
      "loss": 1.288,
      "step": 804
    },
    {
      "epoch": 24.77,
      "learning_rate": 2.5e-07,
      "loss": 1.1407,
      "step": 805
    },
    {
      "epoch": 24.8,
      "learning_rate": 2.5e-07,
      "loss": 0.9671,
      "step": 806
    },
    {
      "epoch": 24.83,
      "learning_rate": 2.5e-07,
      "loss": 1.1035,
      "step": 807
    },
    {
      "epoch": 24.86,
      "learning_rate": 2.5e-07,
      "loss": 1.0981,
      "step": 808
    },
    {
      "epoch": 24.89,
      "learning_rate": 2.5e-07,
      "loss": 1.3622,
      "step": 809
    },
    {
      "epoch": 24.92,
      "learning_rate": 2.5e-07,
      "loss": 1.2952,
      "step": 810
    },
    {
      "epoch": 24.95,
      "learning_rate": 2.5e-07,
      "loss": 1.3048,
      "step": 811
    },
    {
      "epoch": 24.98,
      "learning_rate": 2.5e-07,
      "loss": 1.258,
      "step": 812
    },
    {
      "epoch": 25.02,
      "learning_rate": 2.5e-07,
      "loss": 1.0539,
      "step": 813
    },
    {
      "epoch": 25.05,
      "learning_rate": 2.5e-07,
      "loss": 1.2292,
      "step": 814
    },
    {
      "epoch": 25.08,
      "learning_rate": 2.5e-07,
      "loss": 1.174,
      "step": 815
    },
    {
      "epoch": 25.11,
      "learning_rate": 2.5e-07,
      "loss": 1.2923,
      "step": 816
    },
    {
      "epoch": 25.14,
      "learning_rate": 2.5e-07,
      "loss": 1.0353,
      "step": 817
    },
    {
      "epoch": 25.17,
      "learning_rate": 2.5e-07,
      "loss": 1.2647,
      "step": 818
    },
    {
      "epoch": 25.2,
      "learning_rate": 2.5e-07,
      "loss": 1.2257,
      "step": 819
    },
    {
      "epoch": 25.23,
      "learning_rate": 2.5e-07,
      "loss": 1.125,
      "step": 820
    },
    {
      "epoch": 25.26,
      "learning_rate": 2.5e-07,
      "loss": 1.2659,
      "step": 821
    },
    {
      "epoch": 25.29,
      "learning_rate": 2.5e-07,
      "loss": 1.0275,
      "step": 822
    },
    {
      "epoch": 25.32,
      "learning_rate": 2.5e-07,
      "loss": 1.2631,
      "step": 823
    },
    {
      "epoch": 25.35,
      "learning_rate": 2.5e-07,
      "loss": 1.1905,
      "step": 824
    },
    {
      "epoch": 25.38,
      "learning_rate": 2.5e-07,
      "loss": 1.1871,
      "step": 825
    },
    {
      "epoch": 25.42,
      "learning_rate": 2.5e-07,
      "loss": 1.0288,
      "step": 826
    },
    {
      "epoch": 25.45,
      "learning_rate": 2.5e-07,
      "loss": 1.0998,
      "step": 827
    },
    {
      "epoch": 25.48,
      "learning_rate": 2.5e-07,
      "loss": 1.1128,
      "step": 828
    },
    {
      "epoch": 25.51,
      "learning_rate": 2.5e-07,
      "loss": 1.1058,
      "step": 829
    },
    {
      "epoch": 25.54,
      "learning_rate": 2.5e-07,
      "loss": 0.9362,
      "step": 830
    },
    {
      "epoch": 25.57,
      "learning_rate": 2.5e-07,
      "loss": 1.1587,
      "step": 831
    },
    {
      "epoch": 25.6,
      "learning_rate": 2.5e-07,
      "loss": 1.1345,
      "step": 832
    },
    {
      "epoch": 25.63,
      "learning_rate": 2.5e-07,
      "loss": 1.269,
      "step": 833
    },
    {
      "epoch": 25.66,
      "learning_rate": 2.5e-07,
      "loss": 1.1619,
      "step": 834
    },
    {
      "epoch": 25.69,
      "learning_rate": 2.5e-07,
      "loss": 1.2199,
      "step": 835
    },
    {
      "epoch": 25.72,
      "learning_rate": 2.5e-07,
      "loss": 1.2374,
      "step": 836
    },
    {
      "epoch": 25.75,
      "learning_rate": 2.5e-07,
      "loss": 1.2568,
      "step": 837
    },
    {
      "epoch": 25.78,
      "learning_rate": 2.5e-07,
      "loss": 1.1374,
      "step": 838
    },
    {
      "epoch": 25.82,
      "learning_rate": 2.5e-07,
      "loss": 1.32,
      "step": 839
    },
    {
      "epoch": 25.85,
      "learning_rate": 2.5e-07,
      "loss": 1.2681,
      "step": 840
    },
    {
      "epoch": 25.88,
      "learning_rate": 2.5e-07,
      "loss": 1.0749,
      "step": 841
    },
    {
      "epoch": 25.91,
      "learning_rate": 2.5e-07,
      "loss": 1.325,
      "step": 842
    },
    {
      "epoch": 25.94,
      "learning_rate": 2.5e-07,
      "loss": 1.2718,
      "step": 843
    },
    {
      "epoch": 25.97,
      "learning_rate": 2.5e-07,
      "loss": 1.2822,
      "step": 844
    },
    {
      "epoch": 26.0,
      "learning_rate": 2.5e-07,
      "loss": 1.2542,
      "step": 845
    },
    {
      "epoch": 26.03,
      "learning_rate": 2.5e-07,
      "loss": 1.094,
      "step": 846
    },
    {
      "epoch": 26.06,
      "learning_rate": 2.5e-07,
      "loss": 1.1741,
      "step": 847
    },
    {
      "epoch": 26.09,
      "learning_rate": 2.5e-07,
      "loss": 0.9948,
      "step": 848
    },
    {
      "epoch": 26.12,
      "learning_rate": 2.5e-07,
      "loss": 0.9381,
      "step": 849
    },
    {
      "epoch": 26.15,
      "learning_rate": 2.5e-07,
      "loss": 1.2547,
      "step": 850
    },
    {
      "epoch": 26.18,
      "learning_rate": 2.5e-07,
      "loss": 1.3896,
      "step": 851
    },
    {
      "epoch": 26.22,
      "learning_rate": 2.5e-07,
      "loss": 1.2587,
      "step": 852
    },
    {
      "epoch": 26.25,
      "learning_rate": 2.5e-07,
      "loss": 1.2572,
      "step": 853
    },
    {
      "epoch": 26.28,
      "learning_rate": 2.5e-07,
      "loss": 1.1927,
      "step": 854
    },
    {
      "epoch": 26.31,
      "learning_rate": 2.5e-07,
      "loss": 0.9622,
      "step": 855
    },
    {
      "epoch": 26.34,
      "learning_rate": 2.5e-07,
      "loss": 1.192,
      "step": 856
    },
    {
      "epoch": 26.37,
      "learning_rate": 2.5e-07,
      "loss": 0.9601,
      "step": 857
    },
    {
      "epoch": 26.4,
      "learning_rate": 2.5e-07,
      "loss": 1.1648,
      "step": 858
    },
    {
      "epoch": 26.43,
      "learning_rate": 2.5e-07,
      "loss": 1.2387,
      "step": 859
    },
    {
      "epoch": 26.46,
      "learning_rate": 2.5e-07,
      "loss": 1.2444,
      "step": 860
    },
    {
      "epoch": 26.49,
      "learning_rate": 2.5e-07,
      "loss": 1.1718,
      "step": 861
    },
    {
      "epoch": 26.52,
      "learning_rate": 2.5e-07,
      "loss": 1.3051,
      "step": 862
    },
    {
      "epoch": 26.55,
      "learning_rate": 2.5e-07,
      "loss": 1.3384,
      "step": 863
    },
    {
      "epoch": 26.58,
      "learning_rate": 2.5e-07,
      "loss": 1.1536,
      "step": 864
    },
    {
      "epoch": 26.62,
      "learning_rate": 2.5e-07,
      "loss": 1.1541,
      "step": 865
    },
    {
      "epoch": 26.65,
      "learning_rate": 2.5e-07,
      "loss": 1.2604,
      "step": 866
    },
    {
      "epoch": 26.68,
      "learning_rate": 2.5e-07,
      "loss": 1.1687,
      "step": 867
    },
    {
      "epoch": 26.71,
      "learning_rate": 2.5e-07,
      "loss": 1.0095,
      "step": 868
    },
    {
      "epoch": 26.74,
      "learning_rate": 2.5e-07,
      "loss": 1.2004,
      "step": 869
    },
    {
      "epoch": 26.77,
      "learning_rate": 2.5e-07,
      "loss": 1.3289,
      "step": 870
    },
    {
      "epoch": 26.8,
      "learning_rate": 2.5e-07,
      "loss": 1.2065,
      "step": 871
    },
    {
      "epoch": 26.83,
      "learning_rate": 2.5e-07,
      "loss": 1.1295,
      "step": 872
    },
    {
      "epoch": 26.86,
      "learning_rate": 2.5e-07,
      "loss": 1.2577,
      "step": 873
    },
    {
      "epoch": 26.89,
      "learning_rate": 2.5e-07,
      "loss": 1.1807,
      "step": 874
    },
    {
      "epoch": 26.92,
      "learning_rate": 2.5e-07,
      "loss": 1.1881,
      "step": 875
    },
    {
      "epoch": 26.95,
      "learning_rate": 2.5e-07,
      "loss": 1.2618,
      "step": 876
    },
    {
      "epoch": 26.98,
      "learning_rate": 2.5e-07,
      "loss": 1.3067,
      "step": 877
    },
    {
      "epoch": 27.02,
      "learning_rate": 2.5e-07,
      "loss": 0.8701,
      "step": 878
    },
    {
      "epoch": 27.05,
      "learning_rate": 2.5e-07,
      "loss": 1.1478,
      "step": 879
    },
    {
      "epoch": 27.08,
      "learning_rate": 2.5e-07,
      "loss": 1.0857,
      "step": 880
    },
    {
      "epoch": 27.08,
      "eval_loss": 1.1367146968841553,
      "eval_runtime": 1.7401,
      "eval_samples_per_second": 4.023,
      "eval_steps_per_second": 2.299,
      "step": 880
    },
    {
      "epoch": 27.11,
      "learning_rate": 2.5e-07,
      "loss": 1.2706,
      "step": 881
    },
    {
      "epoch": 27.14,
      "learning_rate": 2.5e-07,
      "loss": 1.151,
      "step": 882
    },
    {
      "epoch": 27.17,
      "learning_rate": 2.5e-07,
      "loss": 1.2352,
      "step": 883
    },
    {
      "epoch": 27.2,
      "learning_rate": 2.5e-07,
      "loss": 1.0755,
      "step": 884
    },
    {
      "epoch": 27.23,
      "learning_rate": 2.5e-07,
      "loss": 0.9987,
      "step": 885
    },
    {
      "epoch": 27.26,
      "learning_rate": 2.5e-07,
      "loss": 1.3896,
      "step": 886
    },
    {
      "epoch": 27.29,
      "learning_rate": 2.5e-07,
      "loss": 1.047,
      "step": 887
    },
    {
      "epoch": 27.32,
      "learning_rate": 2.5e-07,
      "loss": 1.2163,
      "step": 888
    },
    {
      "epoch": 27.35,
      "learning_rate": 2.5e-07,
      "loss": 1.1826,
      "step": 889
    },
    {
      "epoch": 27.38,
      "learning_rate": 2.5e-07,
      "loss": 1.0939,
      "step": 890
    },
    {
      "epoch": 27.42,
      "learning_rate": 2.5e-07,
      "loss": 1.0561,
      "step": 891
    },
    {
      "epoch": 27.45,
      "learning_rate": 2.5e-07,
      "loss": 1.1888,
      "step": 892
    },
    {
      "epoch": 27.48,
      "learning_rate": 2.5e-07,
      "loss": 1.2385,
      "step": 893
    },
    {
      "epoch": 27.51,
      "learning_rate": 2.5e-07,
      "loss": 1.1719,
      "step": 894
    },
    {
      "epoch": 27.54,
      "learning_rate": 2.5e-07,
      "loss": 1.2768,
      "step": 895
    },
    {
      "epoch": 27.57,
      "learning_rate": 2.5e-07,
      "loss": 1.2474,
      "step": 896
    },
    {
      "epoch": 27.6,
      "learning_rate": 2.5e-07,
      "loss": 1.3374,
      "step": 897
    },
    {
      "epoch": 27.63,
      "learning_rate": 2.5e-07,
      "loss": 1.2982,
      "step": 898
    },
    {
      "epoch": 27.66,
      "learning_rate": 2.5e-07,
      "loss": 1.0727,
      "step": 899
    },
    {
      "epoch": 27.69,
      "learning_rate": 2.5e-07,
      "loss": 1.2495,
      "step": 900
    },
    {
      "epoch": 27.72,
      "learning_rate": 2.5e-07,
      "loss": 1.1306,
      "step": 901
    },
    {
      "epoch": 27.75,
      "learning_rate": 2.5e-07,
      "loss": 1.2784,
      "step": 902
    },
    {
      "epoch": 27.78,
      "learning_rate": 2.5e-07,
      "loss": 1.1225,
      "step": 903
    },
    {
      "epoch": 27.82,
      "learning_rate": 2.5e-07,
      "loss": 1.2542,
      "step": 904
    },
    {
      "epoch": 27.85,
      "learning_rate": 2.5e-07,
      "loss": 1.1575,
      "step": 905
    },
    {
      "epoch": 27.88,
      "learning_rate": 2.5e-07,
      "loss": 1.1425,
      "step": 906
    },
    {
      "epoch": 27.91,
      "learning_rate": 2.5e-07,
      "loss": 1.1282,
      "step": 907
    },
    {
      "epoch": 27.94,
      "learning_rate": 2.5e-07,
      "loss": 1.223,
      "step": 908
    },
    {
      "epoch": 27.97,
      "learning_rate": 2.5e-07,
      "loss": 1.1326,
      "step": 909
    },
    {
      "epoch": 28.0,
      "learning_rate": 2.5e-07,
      "loss": 1.2255,
      "step": 910
    },
    {
      "epoch": 28.03,
      "learning_rate": 2.5e-07,
      "loss": 1.1362,
      "step": 911
    },
    {
      "epoch": 28.06,
      "learning_rate": 2.5e-07,
      "loss": 1.1001,
      "step": 912
    },
    {
      "epoch": 28.09,
      "learning_rate": 2.5e-07,
      "loss": 1.2152,
      "step": 913
    },
    {
      "epoch": 28.12,
      "learning_rate": 2.5e-07,
      "loss": 1.1168,
      "step": 914
    },
    {
      "epoch": 28.15,
      "learning_rate": 2.5e-07,
      "loss": 1.2479,
      "step": 915
    },
    {
      "epoch": 28.18,
      "learning_rate": 2.5e-07,
      "loss": 1.1956,
      "step": 916
    },
    {
      "epoch": 28.22,
      "learning_rate": 2.5e-07,
      "loss": 1.1865,
      "step": 917
    },
    {
      "epoch": 28.25,
      "learning_rate": 2.5e-07,
      "loss": 1.1982,
      "step": 918
    },
    {
      "epoch": 28.28,
      "learning_rate": 2.5e-07,
      "loss": 1.0791,
      "step": 919
    },
    {
      "epoch": 28.31,
      "learning_rate": 2.5e-07,
      "loss": 1.1691,
      "step": 920
    },
    {
      "epoch": 28.34,
      "learning_rate": 2.5e-07,
      "loss": 1.2283,
      "step": 921
    },
    {
      "epoch": 28.37,
      "learning_rate": 2.5e-07,
      "loss": 1.2687,
      "step": 922
    },
    {
      "epoch": 28.4,
      "learning_rate": 2.5e-07,
      "loss": 0.9531,
      "step": 923
    },
    {
      "epoch": 28.43,
      "learning_rate": 2.5e-07,
      "loss": 1.0041,
      "step": 924
    },
    {
      "epoch": 28.46,
      "learning_rate": 2.5e-07,
      "loss": 0.9897,
      "step": 925
    },
    {
      "epoch": 28.49,
      "learning_rate": 2.5e-07,
      "loss": 1.1019,
      "step": 926
    },
    {
      "epoch": 28.52,
      "learning_rate": 2.5e-07,
      "loss": 1.2045,
      "step": 927
    },
    {
      "epoch": 28.55,
      "learning_rate": 2.5e-07,
      "loss": 1.1838,
      "step": 928
    },
    {
      "epoch": 28.58,
      "learning_rate": 2.5e-07,
      "loss": 1.1894,
      "step": 929
    },
    {
      "epoch": 28.62,
      "learning_rate": 2.5e-07,
      "loss": 1.1054,
      "step": 930
    },
    {
      "epoch": 28.65,
      "learning_rate": 2.5e-07,
      "loss": 1.3175,
      "step": 931
    },
    {
      "epoch": 28.68,
      "learning_rate": 2.5e-07,
      "loss": 1.2877,
      "step": 932
    },
    {
      "epoch": 28.71,
      "learning_rate": 2.5e-07,
      "loss": 1.2615,
      "step": 933
    },
    {
      "epoch": 28.74,
      "learning_rate": 2.5e-07,
      "loss": 1.1079,
      "step": 934
    },
    {
      "epoch": 28.77,
      "learning_rate": 2.5e-07,
      "loss": 1.264,
      "step": 935
    },
    {
      "epoch": 28.8,
      "learning_rate": 2.5e-07,
      "loss": 1.3003,
      "step": 936
    },
    {
      "epoch": 28.83,
      "learning_rate": 2.5e-07,
      "loss": 1.0865,
      "step": 937
    },
    {
      "epoch": 28.86,
      "learning_rate": 2.5e-07,
      "loss": 1.1714,
      "step": 938
    },
    {
      "epoch": 28.89,
      "learning_rate": 2.5e-07,
      "loss": 1.0339,
      "step": 939
    },
    {
      "epoch": 28.92,
      "learning_rate": 2.5e-07,
      "loss": 1.3118,
      "step": 940
    },
    {
      "epoch": 28.95,
      "learning_rate": 2.5e-07,
      "loss": 1.2253,
      "step": 941
    },
    {
      "epoch": 28.98,
      "learning_rate": 2.5e-07,
      "loss": 1.1665,
      "step": 942
    },
    {
      "epoch": 29.02,
      "learning_rate": 2.5e-07,
      "loss": 1.3285,
      "step": 943
    },
    {
      "epoch": 29.05,
      "learning_rate": 2.5e-07,
      "loss": 1.2553,
      "step": 944
    },
    {
      "epoch": 29.08,
      "learning_rate": 2.5e-07,
      "loss": 1.2341,
      "step": 945
    },
    {
      "epoch": 29.11,
      "learning_rate": 2.5e-07,
      "loss": 1.257,
      "step": 946
    },
    {
      "epoch": 29.14,
      "learning_rate": 2.5e-07,
      "loss": 1.1492,
      "step": 947
    },
    {
      "epoch": 29.17,
      "learning_rate": 2.5e-07,
      "loss": 1.0962,
      "step": 948
    },
    {
      "epoch": 29.2,
      "learning_rate": 2.5e-07,
      "loss": 1.1208,
      "step": 949
    },
    {
      "epoch": 29.23,
      "learning_rate": 2.5e-07,
      "loss": 1.2373,
      "step": 950
    },
    {
      "epoch": 29.26,
      "learning_rate": 2.5e-07,
      "loss": 1.2133,
      "step": 951
    },
    {
      "epoch": 29.29,
      "learning_rate": 2.5e-07,
      "loss": 1.1271,
      "step": 952
    },
    {
      "epoch": 29.32,
      "learning_rate": 2.5e-07,
      "loss": 1.2082,
      "step": 953
    },
    {
      "epoch": 29.35,
      "learning_rate": 2.5e-07,
      "loss": 1.1464,
      "step": 954
    },
    {
      "epoch": 29.38,
      "learning_rate": 2.5e-07,
      "loss": 1.2751,
      "step": 955
    },
    {
      "epoch": 29.42,
      "learning_rate": 2.5e-07,
      "loss": 1.1938,
      "step": 956
    },
    {
      "epoch": 29.45,
      "learning_rate": 2.5e-07,
      "loss": 0.8369,
      "step": 957
    },
    {
      "epoch": 29.48,
      "learning_rate": 2.5e-07,
      "loss": 1.0691,
      "step": 958
    },
    {
      "epoch": 29.51,
      "learning_rate": 2.5e-07,
      "loss": 1.2111,
      "step": 959
    },
    {
      "epoch": 29.54,
      "learning_rate": 2.5e-07,
      "loss": 1.0795,
      "step": 960
    },
    {
      "epoch": 29.54,
      "eval_loss": 1.1345065832138062,
      "eval_runtime": 1.7373,
      "eval_samples_per_second": 4.029,
      "eval_steps_per_second": 2.302,
      "step": 960
    },
    {
      "epoch": 29.57,
      "learning_rate": 2.5e-07,
      "loss": 1.1129,
      "step": 961
    },
    {
      "epoch": 29.6,
      "learning_rate": 2.5e-07,
      "loss": 1.1189,
      "step": 962
    },
    {
      "epoch": 29.63,
      "learning_rate": 2.5e-07,
      "loss": 0.9281,
      "step": 963
    },
    {
      "epoch": 29.66,
      "learning_rate": 2.5e-07,
      "loss": 1.3352,
      "step": 964
    },
    {
      "epoch": 29.69,
      "learning_rate": 2.5e-07,
      "loss": 1.2835,
      "step": 965
    },
    {
      "epoch": 29.72,
      "learning_rate": 2.5e-07,
      "loss": 1.1693,
      "step": 966
    },
    {
      "epoch": 29.75,
      "learning_rate": 2.5e-07,
      "loss": 1.18,
      "step": 967
    },
    {
      "epoch": 29.78,
      "learning_rate": 2.5e-07,
      "loss": 1.3506,
      "step": 968
    },
    {
      "epoch": 29.82,
      "learning_rate": 2.5e-07,
      "loss": 1.2388,
      "step": 969
    },
    {
      "epoch": 29.85,
      "learning_rate": 2.5e-07,
      "loss": 1.1186,
      "step": 970
    },
    {
      "epoch": 29.88,
      "learning_rate": 2.5e-07,
      "loss": 1.0852,
      "step": 971
    },
    {
      "epoch": 29.91,
      "learning_rate": 2.5e-07,
      "loss": 1.1784,
      "step": 972
    },
    {
      "epoch": 29.94,
      "learning_rate": 2.5e-07,
      "loss": 1.1734,
      "step": 973
    },
    {
      "epoch": 29.97,
      "learning_rate": 2.5e-07,
      "loss": 1.1523,
      "step": 974
    },
    {
      "epoch": 30.0,
      "learning_rate": 2.5e-07,
      "loss": 1.2161,
      "step": 975
    }
  ],
  "logging_steps": 1,
  "max_steps": 1600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 65,
  "total_flos": 1.5462810055213056e+17,
  "trial_name": null,
  "trial_params": null
}