{
  "best_metric": 1.7676039934158325,
  "best_model_checkpoint": "/dodrio/scratch/projects/2023_005/llm-finetuning/results/llama2-13b-ft-mc4_nl_cleaned_tiny/tiny-3e-4lr+1152tbs+1ep+0.1wd/checkpoint-900",
  "epoch": 0.9996554100620262,
  "global_step": 967,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 1.973,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.113851412715185e-05,
      "loss": 1.9883,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.690225224134633e-05,
      "loss": 1.9733,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001222770282543037,
      "loss": 1.9711,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014195923363150177,
      "loss": 1.9844,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015804076636849817,
      "loss": 1.9779,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001716375085621481,
      "loss": 1.9729,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001834155423814555,
      "loss": 1.9695,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019380450448269266,
      "loss": 1.9608,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00020309774775865365,
      "loss": 1.9629,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00021150450888797218,
      "loss": 1.9773,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00021917928049565002,
      "loss": 1.9642,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00022623938598424298,
      "loss": 1.9668,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00023277602268929992,
      "loss": 1.9551,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002388614858728481,
      "loss": 1.9568,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002445540565086074,
      "loss": 1.9529,
      "step": 16
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002499014046639921,
      "loss": 1.957,
      "step": 17
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002549430186098445,
      "loss": 1.9465,
      "step": 18
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002597119762917877,
      "loss": 1.9452,
      "step": 19
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00026423626188580546,
      "loss": 1.962,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00026853976080349446,
      "loss": 1.933,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000272643023015124,
      "loss": 1.9386,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002765638565554383,
      "loss": 1.939,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002803177946228019,
      "loss": 1.9285,
      "step": 24
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00028391846726300355,
      "loss": 1.9258,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002873779001113948,
      "loss": 1.938,
      "step": 26
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000290706756724039,
      "loss": 1.9287,
      "step": 27
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002939145368164518,
      "loss": 1.9237,
      "step": 28
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002970097397000423,
      "loss": 1.9264,
      "step": 29
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.9109,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.9203,
      "step": 31
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.9248,
      "step": 32
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.9271,
      "step": 33
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9103,
      "step": 34
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9077,
      "step": 35
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9152,
      "step": 36
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9152,
      "step": 37
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9065,
      "step": 38
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9114,
      "step": 39
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9169,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9135,
      "step": 41
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9028,
      "step": 42
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9021,
      "step": 43
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.9137,
      "step": 44
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.9149,
      "step": 45
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.9049,
      "step": 46
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.9038,
      "step": 47
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.9028,
      "step": 48
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.9116,
      "step": 49
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.8984,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.9131,
      "step": 51
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.9136,
      "step": 52
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.8904,
      "step": 53
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.8909,
      "step": 54
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.9005,
      "step": 55
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.8922,
      "step": 56
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.8892,
      "step": 57
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.8998,
      "step": 58
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.8905,
      "step": 59
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.9003,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.8947,
      "step": 61
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.897,
      "step": 62
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.8995,
      "step": 63
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.896,
      "step": 64
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.8988,
      "step": 65
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.8843,
      "step": 66
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.8937,
      "step": 67
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.8824,
      "step": 68
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.8898,
      "step": 69
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.8964,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.8845,
      "step": 71
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.889,
      "step": 72
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.8896,
      "step": 73
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.9022,
      "step": 74
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.8962,
      "step": 75
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.8809,
      "step": 76
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.8804,
      "step": 77
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.8752,
      "step": 78
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.8947,
      "step": 79
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.8909,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.8713,
      "step": 81
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.8918,
      "step": 82
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.8956,
      "step": 83
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.8823,
      "step": 84
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.894,
      "step": 85
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.8816,
      "step": 86
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.8888,
      "step": 87
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.8795,
      "step": 88
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.8862,
      "step": 89
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.8784,
      "step": 90
    },
    {
      "epoch": 0.09,
      "eval_loss": 1.8820199966430664,
      "eval_runtime": 2549.8335,
      "eval_samples_per_second": 22.942,
      "eval_steps_per_second": 0.12,
      "step": 90
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.8904,
      "step": 91
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.8933,
      "step": 92
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.8799,
      "step": 93
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.8879,
      "step": 94
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.874,
      "step": 95
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.8701,
      "step": 96
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.8839,
      "step": 97
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.8796,
      "step": 98
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.8816,
      "step": 99
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.8735,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.8729,
      "step": 101
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.8732,
      "step": 102
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.8846,
      "step": 103
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.884,
      "step": 104
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.8778,
      "step": 105
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.8741,
      "step": 106
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.8754,
      "step": 107
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.8586,
      "step": 108
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.88,
      "step": 109
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.877,
      "step": 110
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.8707,
      "step": 111
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 1.8805,
      "step": 112
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 1.8619,
      "step": 113
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 1.8768,
      "step": 114
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 1.8801,
      "step": 115
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 1.8782,
      "step": 116
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 1.8719,
      "step": 117
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 1.8713,
      "step": 118
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 1.8706,
      "step": 119
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 1.8726,
      "step": 120
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.8717,
      "step": 121
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.8633,
      "step": 122
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.8638,
      "step": 123
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.8802,
      "step": 124
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.8687,
      "step": 125
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.8583,
      "step": 126
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.8682,
      "step": 127
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.8611,
      "step": 128
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.8646,
      "step": 129
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.8718,
      "step": 130
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.8768,
      "step": 131
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.865,
      "step": 132
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.8831,
      "step": 133
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.8727,
      "step": 134
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.8759,
      "step": 135
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.8612,
      "step": 136
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.8612,
      "step": 137
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.8685,
      "step": 138
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.8763,
      "step": 139
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.8578,
      "step": 140
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.8602,
      "step": 141
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.8688,
      "step": 142
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.8616,
      "step": 143
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.8594,
      "step": 144
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.8671,
      "step": 145
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.8524,
      "step": 146
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.8668,
      "step": 147
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.8591,
      "step": 148
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.8615,
      "step": 149
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.8577,
      "step": 150
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.8685,
      "step": 151
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.8589,
      "step": 152
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.8762,
      "step": 153
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.8607,
      "step": 154
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.856,
      "step": 155
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.8577,
      "step": 156
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.8625,
      "step": 157
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.8589,
      "step": 158
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.8533,
      "step": 159
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.8563,
      "step": 160
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.8672,
      "step": 161
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.8671,
      "step": 162
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.8481,
      "step": 163
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.8643,
      "step": 164
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.8567,
      "step": 165
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.8678,
      "step": 166
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.8645,
      "step": 167
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.8684,
      "step": 168
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.8521,
      "step": 169
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.8682,
      "step": 170
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.8455,
      "step": 171
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.8513,
      "step": 172
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.859,
      "step": 173
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.8597,
      "step": 174
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.8519,
      "step": 175
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.844,
      "step": 176
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.8529,
      "step": 177
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.8582,
      "step": 178
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.874,
      "step": 179
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.8344,
      "step": 180
    },
    {
      "epoch": 0.19,
      "eval_loss": 1.8541951179504395,
      "eval_runtime": 2546.7927,
      "eval_samples_per_second": 22.969,
      "eval_steps_per_second": 0.12,
      "step": 180
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.8557,
      "step": 181
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.8396,
      "step": 182
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.8506,
      "step": 183
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.8683,
      "step": 184
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.8634,
      "step": 185
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.8453,
      "step": 186
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.8595,
      "step": 187
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.8472,
      "step": 188
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.8438,
      "step": 189
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.8459,
      "step": 190
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.8558,
      "step": 191
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.8474,
      "step": 192
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.8588,
      "step": 193
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.8584,
      "step": 194
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.86,
      "step": 195
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.8408,
      "step": 196
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.8569,
      "step": 197
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.8456,
      "step": 198
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 1.8577,
      "step": 199
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 1.8541,
      "step": 200
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 1.8499,
      "step": 201
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 1.8505,
      "step": 202
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 1.8491,
      "step": 203
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 1.8441,
      "step": 204
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 1.8394,
      "step": 205
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 1.8523,
      "step": 206
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 1.8553,
      "step": 207
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.8456,
      "step": 208
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.8485,
      "step": 209
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.8417,
      "step": 210
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.8438,
      "step": 211
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.8593,
      "step": 212
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.8496,
      "step": 213
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.8427,
      "step": 214
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.8475,
      "step": 215
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.8411,
      "step": 216
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.8418,
      "step": 217
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.8536,
      "step": 218
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.843,
      "step": 219
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.8385,
      "step": 220
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.8488,
      "step": 221
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.843,
      "step": 222
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.8412,
      "step": 223
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.8633,
      "step": 224
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.8483,
      "step": 225
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.8411,
      "step": 226
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.8353,
      "step": 227
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.8435,
      "step": 228
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.845,
      "step": 229
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.8553,
      "step": 230
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.8357,
      "step": 231
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.832,
      "step": 232
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.8359,
      "step": 233
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.8433,
      "step": 234
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.8416,
      "step": 235
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.8468,
      "step": 236
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.84,
      "step": 237
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.8459,
      "step": 238
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.8474,
      "step": 239
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.8295,
      "step": 240
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.8408,
      "step": 241
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.8408,
      "step": 242
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.8385,
      "step": 243
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.8425,
      "step": 244
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.8298,
      "step": 245
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.8385,
      "step": 246
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.8304,
      "step": 247
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.8326,
      "step": 248
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.8501,
      "step": 249
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.8414,
      "step": 250
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.8394,
      "step": 251
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.8387,
      "step": 252
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.8344,
      "step": 253
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.8433,
      "step": 254
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.8431,
      "step": 255
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.8372,
      "step": 256
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8464,
      "step": 257
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8517,
      "step": 258
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8384,
      "step": 259
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8356,
      "step": 260
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8362,
      "step": 261
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8381,
      "step": 262
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8224,
      "step": 263
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8418,
      "step": 264
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8374,
      "step": 265
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8416,
      "step": 266
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8423,
      "step": 267
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8442,
      "step": 268
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8291,
      "step": 269
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8351,
      "step": 270
    },
    {
      "epoch": 0.28,
      "eval_loss": 1.8355114459991455,
      "eval_runtime": 2618.0598,
      "eval_samples_per_second": 22.344,
      "eval_steps_per_second": 0.116,
      "step": 270
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8279,
      "step": 271
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8311,
      "step": 272
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8386,
      "step": 273
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8298,
      "step": 274
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8284,
      "step": 275
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.8412,
      "step": 276
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.8226,
      "step": 277
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.8312,
      "step": 278
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.8274,
      "step": 279
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.8142,
      "step": 280
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.8267,
      "step": 281
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.8276,
      "step": 282
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.8368,
      "step": 283
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.8311,
      "step": 284
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.8136,
      "step": 285
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8472,
      "step": 286
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8336,
      "step": 287
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8243,
      "step": 288
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8361,
      "step": 289
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8263,
      "step": 290
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8318,
      "step": 291
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.828,
      "step": 292
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8268,
      "step": 293
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8302,
      "step": 294
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8387,
      "step": 295
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8406,
      "step": 296
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8339,
      "step": 297
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8378,
      "step": 298
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8331,
      "step": 299
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8267,
      "step": 300
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8295,
      "step": 301
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8364,
      "step": 302
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8329,
      "step": 303
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8427,
      "step": 304
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.8348,
      "step": 305
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.8302,
      "step": 306
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.8378,
      "step": 307
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.8282,
      "step": 308
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.8344,
      "step": 309
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.8108,
      "step": 310
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.8282,
      "step": 311
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.8263,
      "step": 312
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.8213,
      "step": 313
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.828,
      "step": 314
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.835,
      "step": 315
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.839,
      "step": 316
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.8402,
      "step": 317
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.8281,
      "step": 318
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.8267,
      "step": 319
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.832,
      "step": 320
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.8257,
      "step": 321
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.834,
      "step": 322
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.8243,
      "step": 323
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.8422,
      "step": 324
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.8165,
      "step": 325
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.8241,
      "step": 326
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.8232,
      "step": 327
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.8396,
      "step": 328
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.8173,
      "step": 329
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.8162,
      "step": 330
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.814,
      "step": 331
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.8221,
      "step": 332
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.8208,
      "step": 333
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.8177,
      "step": 334
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.8157,
      "step": 335
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.8237,
      "step": 336
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.8279,
      "step": 337
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.8335,
      "step": 338
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.8319,
      "step": 339
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.8188,
      "step": 340
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.8238,
      "step": 341
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.8199,
      "step": 342
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.8186,
      "step": 343
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.8202,
      "step": 344
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.8346,
      "step": 345
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.827,
      "step": 346
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.8231,
      "step": 347
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.8295,
      "step": 348
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.8312,
      "step": 349
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.8246,
      "step": 350
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.828,
      "step": 351
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.8297,
      "step": 352
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.816,
      "step": 353
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.8191,
      "step": 354
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.8234,
      "step": 355
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.8086,
      "step": 356
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.8301,
      "step": 357
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.8257,
      "step": 358
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.8127,
      "step": 359
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.8206,
      "step": 360
    },
    {
      "epoch": 0.37,
      "eval_loss": 1.8211501836776733,
      "eval_runtime": 2779.7831,
      "eval_samples_per_second": 21.044,
      "eval_steps_per_second": 0.11,
      "step": 360
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.8215,
      "step": 361
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.8279,
      "step": 362
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.8361,
      "step": 363
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.8329,
      "step": 364
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.8303,
      "step": 365
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.8179,
      "step": 366
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.829,
      "step": 367
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.8215,
      "step": 368
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.8187,
      "step": 369
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.8124,
      "step": 370
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.812,
      "step": 371
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.8241,
      "step": 372
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8142,
      "step": 373
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8174,
      "step": 374
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8127,
      "step": 375
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8104,
      "step": 376
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8136,
      "step": 377
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8184,
      "step": 378
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8132,
      "step": 379
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8267,
      "step": 380
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8044,
      "step": 381
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8347,
      "step": 382
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.8196,
      "step": 383
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.8376,
      "step": 384
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.8195,
      "step": 385
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.8076,
      "step": 386
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.8074,
      "step": 387
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.8319,
      "step": 388
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.8108,
      "step": 389
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.8071,
      "step": 390
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.824,
      "step": 391
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.8102,
      "step": 392
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.8159,
      "step": 393
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.8097,
      "step": 394
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.8136,
      "step": 395
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.8188,
      "step": 396
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.8044,
      "step": 397
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.812,
      "step": 398
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.812,
      "step": 399
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.8185,
      "step": 400
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.803,
      "step": 401
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.8328,
      "step": 402
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.8104,
      "step": 403
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.8184,
      "step": 404
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.8029,
      "step": 405
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.8225,
      "step": 406
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.8174,
      "step": 407
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.8154,
      "step": 408
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.8319,
      "step": 409
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.8186,
      "step": 410
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.8236,
      "step": 411
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.808,
      "step": 412
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8114,
      "step": 413
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8138,
      "step": 414
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8203,
      "step": 415
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8099,
      "step": 416
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8068,
      "step": 417
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8145,
      "step": 418
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8159,
      "step": 419
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8071,
      "step": 420
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.8071,
      "step": 421
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.8057,
      "step": 422
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.801,
      "step": 423
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.8087,
      "step": 424
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.8167,
      "step": 425
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.8219,
      "step": 426
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.8142,
      "step": 427
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.8131,
      "step": 428
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.8217,
      "step": 429
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.8202,
      "step": 430
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.8046,
      "step": 431
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.8043,
      "step": 432
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.8284,
      "step": 433
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.8055,
      "step": 434
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.8087,
      "step": 435
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.8091,
      "step": 436
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.8196,
      "step": 437
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.8125,
      "step": 438
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.8093,
      "step": 439
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.8062,
      "step": 440
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.8085,
      "step": 441
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.8171,
      "step": 442
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.8137,
      "step": 443
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.8086,
      "step": 444
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.8126,
      "step": 445
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.8179,
      "step": 446
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.8079,
      "step": 447
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.8091,
      "step": 448
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.812,
      "step": 449
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.8021,
      "step": 450
    },
    {
      "epoch": 0.47,
      "eval_loss": 1.8088126182556152,
      "eval_runtime": 2611.8521,
      "eval_samples_per_second": 22.397,
      "eval_steps_per_second": 0.117,
      "step": 450
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.7981,
      "step": 451
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.8054,
      "step": 452
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.8081,
      "step": 453
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.8197,
      "step": 454
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.817,
      "step": 455
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.8191,
      "step": 456
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.7996,
      "step": 457
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.7914,
      "step": 458
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.8118,
      "step": 459
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.8121,
      "step": 460
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.8108,
      "step": 461
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.8103,
      "step": 462
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.8079,
      "step": 463
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.8082,
      "step": 464
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.807,
      "step": 465
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.8057,
      "step": 466
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.7908,
      "step": 467
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.8134,
      "step": 468
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.8206,
      "step": 469
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8035,
      "step": 470
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8087,
      "step": 471
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8032,
      "step": 472
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8024,
      "step": 473
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8013,
      "step": 474
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8148,
      "step": 475
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8063,
      "step": 476
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8086,
      "step": 477
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8037,
      "step": 478
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.8036,
      "step": 479
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.801,
      "step": 480
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.8223,
      "step": 481
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.7994,
      "step": 482
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.8076,
      "step": 483
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.8127,
      "step": 484
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.8057,
      "step": 485
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.8005,
      "step": 486
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.7965,
      "step": 487
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.8024,
      "step": 488
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 1.809,
      "step": 489
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 1.8031,
      "step": 490
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 1.7935,
      "step": 491
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 1.8077,
      "step": 492
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 1.8022,
      "step": 493
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 1.7985,
      "step": 494
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 1.8115,
      "step": 495
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 1.8069,
      "step": 496
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 1.7949,
      "step": 497
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 1.813,
      "step": 498
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 1.8018,
      "step": 499
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 1.8087,
      "step": 500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 1.8145,
      "step": 501
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 1.8093,
      "step": 502
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 1.7996,
      "step": 503
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 1.812,
      "step": 504
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 1.8019,
      "step": 505
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 1.8096,
      "step": 506
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 1.8031,
      "step": 507
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 1.7922,
      "step": 508
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 1.8049,
      "step": 509
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 1.8179,
      "step": 510
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 1.7998,
      "step": 511
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 1.7981,
      "step": 512
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 1.8098,
      "step": 513
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 1.8054,
      "step": 514
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 1.7966,
      "step": 515
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 1.8024,
      "step": 516
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 1.8038,
      "step": 517
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 1.8125,
      "step": 518
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 1.8141,
      "step": 519
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 1.811,
      "step": 520
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 1.8021,
      "step": 521
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 1.8174,
      "step": 522
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 1.8098,
      "step": 523
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 1.8048,
      "step": 524
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 1.7983,
      "step": 525
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 1.8013,
      "step": 526
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 1.8024,
      "step": 527
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 1.8011,
      "step": 528
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 1.8015,
      "step": 529
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 1.8022,
      "step": 530
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 1.7908,
      "step": 531
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 1.8054,
      "step": 532
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 1.8031,
      "step": 533
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 1.8107,
      "step": 534
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 1.7937,
      "step": 535
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 1.8021,
      "step": 536
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 1.7891,
      "step": 537
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 1.7985,
      "step": 538
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 1.7997,
      "step": 539
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 1.8102,
      "step": 540
    },
    {
      "epoch": 0.56,
      "eval_loss": 1.7981843948364258,
      "eval_runtime": 2586.7325,
      "eval_samples_per_second": 22.615,
      "eval_steps_per_second": 0.118,
      "step": 540
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 1.7986,
      "step": 541
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 1.7797,
      "step": 542
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 1.7958,
      "step": 543
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 1.8032,
      "step": 544
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 1.8036,
      "step": 545
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 1.7919,
      "step": 546
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 1.7908,
      "step": 547
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 1.7979,
      "step": 548
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 1.8015,
      "step": 549
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 1.7987,
      "step": 550
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 1.7926,
      "step": 551
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 1.8038,
      "step": 552
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 1.7932,
      "step": 553
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 1.7863,
      "step": 554
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 1.8026,
      "step": 555
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 1.7944,
      "step": 556
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 1.7953,
      "step": 557
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 1.7999,
      "step": 558
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 1.8097,
      "step": 559
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 1.7985,
      "step": 560
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 1.7939,
      "step": 561
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 1.7979,
      "step": 562
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 1.7958,
      "step": 563
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 1.7949,
      "step": 564
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 1.7971,
      "step": 565
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 1.803,
      "step": 566
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 1.791,
      "step": 567
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 1.7832,
      "step": 568
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 1.7831,
      "step": 569
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 1.7993,
      "step": 570
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 1.7965,
      "step": 571
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 1.7968,
      "step": 572
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 1.791,
      "step": 573
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 1.7905,
      "step": 574
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 1.7922,
      "step": 575
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 1.7983,
      "step": 576
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 1.7915,
      "step": 577
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 1.8019,
      "step": 578
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 1.8084,
      "step": 579
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 1.7968,
      "step": 580
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 1.802,
      "step": 581
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 1.7867,
      "step": 582
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 1.7948,
      "step": 583
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 1.7948,
      "step": 584
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 1.7911,
      "step": 585
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 1.7812,
      "step": 586
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 1.7986,
      "step": 587
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 1.7987,
      "step": 588
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 1.7855,
      "step": 589
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 1.7992,
      "step": 590
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 1.7963,
      "step": 591
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 1.7852,
      "step": 592
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 1.7976,
      "step": 593
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 1.7826,
      "step": 594
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 1.7894,
      "step": 595
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 1.8032,
      "step": 596
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 1.782,
      "step": 597
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 1.7797,
      "step": 598
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 1.8027,
      "step": 599
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 1.799,
      "step": 600
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 1.8003,
      "step": 601
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 1.7946,
      "step": 602
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 1.7902,
      "step": 603
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 1.8073,
      "step": 604
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 1.8008,
      "step": 605
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 1.7957,
      "step": 606
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 1.7798,
      "step": 607
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 1.7936,
      "step": 608
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 1.7875,
      "step": 609
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 1.7845,
      "step": 610
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 1.7949,
      "step": 611
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 1.7915,
      "step": 612
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 1.7958,
      "step": 613
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 1.8016,
      "step": 614
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 1.7891,
      "step": 615
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 1.7899,
      "step": 616
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 1.7832,
      "step": 617
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 1.7875,
      "step": 618
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 1.7841,
      "step": 619
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 1.7882,
      "step": 620
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 1.8121,
      "step": 621
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 1.7922,
      "step": 622
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 1.7964,
      "step": 623
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 1.7949,
      "step": 624
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 1.7939,
      "step": 625
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 1.783,
      "step": 626
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 1.7915,
      "step": 627
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 1.7955,
      "step": 628
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 1.7863,
      "step": 629
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 1.7991,
      "step": 630
    },
    {
      "epoch": 0.65,
      "eval_loss": 1.7890472412109375,
      "eval_runtime": 2587.4651,
      "eval_samples_per_second": 22.608,
      "eval_steps_per_second": 0.118,
      "step": 630
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 1.7936,
      "step": 631
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 1.7906,
      "step": 632
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 1.7925,
      "step": 633
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 1.7889,
      "step": 634
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 1.7842,
      "step": 635
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 1.7911,
      "step": 636
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 1.7949,
      "step": 637
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 1.798,
      "step": 638
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 1.7928,
      "step": 639
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 1.7861,
      "step": 640
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 1.7864,
      "step": 641
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 1.7773,
      "step": 642
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 1.7981,
      "step": 643
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 1.7897,
      "step": 644
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 1.7826,
      "step": 645
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 1.7838,
      "step": 646
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 1.795,
      "step": 647
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 1.7876,
      "step": 648
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 1.7892,
      "step": 649
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 1.7914,
      "step": 650
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 1.8013,
      "step": 651
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 1.8007,
      "step": 652
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 1.7877,
      "step": 653
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 1.7784,
      "step": 654
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 1.7769,
      "step": 655
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 1.8043,
      "step": 656
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 1.7889,
      "step": 657
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 1.786,
      "step": 658
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 1.7836,
      "step": 659
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 1.7792,
      "step": 660
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 1.7892,
      "step": 661
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 1.7971,
      "step": 662
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 1.7909,
      "step": 663
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 1.7844,
      "step": 664
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 1.7896,
      "step": 665
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 1.7876,
      "step": 666
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 1.7797,
      "step": 667
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 1.7972,
      "step": 668
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 1.7881,
      "step": 669
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 1.7931,
      "step": 670
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 1.7905,
      "step": 671
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 1.7959,
      "step": 672
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 1.7864,
      "step": 673
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 1.7965,
      "step": 674
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 1.7841,
      "step": 675
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 1.7863,
      "step": 676
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 1.7855,
      "step": 677
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 1.7987,
      "step": 678
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 1.791,
      "step": 679
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 1.787,
      "step": 680
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 1.7803,
      "step": 681
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 1.7872,
      "step": 682
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 1.792,
      "step": 683
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 1.7716,
      "step": 684
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 1.7927,
      "step": 685
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 1.7719,
      "step": 686
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 1.7961,
      "step": 687
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 1.7872,
      "step": 688
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 1.7877,
      "step": 689
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 1.7938,
      "step": 690
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 1.7748,
      "step": 691
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 1.7931,
      "step": 692
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 1.7876,
      "step": 693
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 1.7872,
      "step": 694
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 1.7769,
      "step": 695
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 1.7969,
      "step": 696
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 1.782,
      "step": 697
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 1.777,
      "step": 698
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 1.7854,
      "step": 699
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 1.7881,
      "step": 700
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 1.7821,
      "step": 701
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 1.7867,
      "step": 702
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 1.7921,
      "step": 703
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 1.7838,
      "step": 704
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 1.7877,
      "step": 705
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 1.7785,
      "step": 706
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 1.776,
      "step": 707
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 1.7865,
      "step": 708
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 1.786,
      "step": 709
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 1.7781,
      "step": 710
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 1.7924,
      "step": 711
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 1.7726,
      "step": 712
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 1.7876,
      "step": 713
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 1.7837,
      "step": 714
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 1.7892,
      "step": 715
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 1.7787,
      "step": 716
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 1.7894,
      "step": 717
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 1.7943,
      "step": 718
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 1.7944,
      "step": 719
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 1.7788,
      "step": 720
    },
    {
      "epoch": 0.74,
      "eval_loss": 1.781058430671692,
      "eval_runtime": 2583.4962,
      "eval_samples_per_second": 22.643,
      "eval_steps_per_second": 0.118,
      "step": 720
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 1.7773,
      "step": 721
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 1.7725,
      "step": 722
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 1.7814,
      "step": 723
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 1.7722,
      "step": 724
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 1.7776,
      "step": 725
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 1.7765,
      "step": 726
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 1.7852,
      "step": 727
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 1.7955,
      "step": 728
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 1.783,
      "step": 729
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 1.7874,
      "step": 730
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 1.7834,
      "step": 731
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 1.7866,
      "step": 732
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 1.7842,
      "step": 733
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 1.7877,
      "step": 734
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 1.7762,
      "step": 735
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 1.7786,
      "step": 736
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 1.7832,
      "step": 737
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 1.7777,
      "step": 738
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 1.7953,
      "step": 739
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 1.783,
      "step": 740
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 1.7844,
      "step": 741
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 1.79,
      "step": 742
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 1.7792,
      "step": 743
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 1.77,
      "step": 744
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 1.7887,
      "step": 745
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 1.7715,
      "step": 746
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 1.7845,
      "step": 747
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 1.7782,
      "step": 748
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 1.7744,
      "step": 749
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 1.7842,
      "step": 750
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 1.7717,
      "step": 751
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 1.7913,
      "step": 752
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 1.7837,
      "step": 753
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 1.7666,
      "step": 754
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 1.7742,
      "step": 755
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 1.7743,
      "step": 756
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 1.7721,
      "step": 757
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 1.7767,
      "step": 758
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 1.787,
      "step": 759
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 1.7795,
      "step": 760
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 1.7853,
      "step": 761
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 1.7699,
      "step": 762
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 1.7864,
      "step": 763
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 1.7833,
      "step": 764
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 1.7776,
      "step": 765
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 1.7874,
      "step": 766
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 1.7821,
      "step": 767
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 1.7692,
      "step": 768
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 1.7798,
      "step": 769
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 1.7905,
      "step": 770
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 1.7875,
      "step": 771
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 1.7805,
      "step": 772
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 1.7764,
      "step": 773
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 1.7865,
      "step": 774
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 1.781,
      "step": 775
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 1.7742,
      "step": 776
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 1.771,
      "step": 777
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 1.7739,
      "step": 778
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 1.7823,
      "step": 779
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 1.7838,
      "step": 780
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 1.7698,
      "step": 781
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 1.7677,
      "step": 782
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 1.7789,
      "step": 783
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 1.7821,
      "step": 784
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 1.7667,
      "step": 785
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 1.7749,
      "step": 786
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 1.7761,
      "step": 787
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 1.7687,
      "step": 788
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 1.7751,
      "step": 789
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 1.7812,
      "step": 790
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 1.7819,
      "step": 791
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 1.7744,
      "step": 792
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 1.7825,
      "step": 793
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 1.7822,
      "step": 794
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 1.7861,
      "step": 795
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 1.7761,
      "step": 796
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 1.7695,
      "step": 797
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 1.757,
      "step": 798
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 1.7777,
      "step": 799
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 1.7661,
      "step": 800
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 1.7794,
      "step": 801
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 1.7819,
      "step": 802
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 1.7738,
      "step": 803
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 1.7734,
      "step": 804
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 1.776,
      "step": 805
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 1.7672,
      "step": 806
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 1.7852,
      "step": 807
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 1.779,
      "step": 808
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 1.776,
      "step": 809
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 1.7915,
      "step": 810
    },
    {
      "epoch": 0.84,
      "eval_loss": 1.7741682529449463,
      "eval_runtime": 2567.5761,
      "eval_samples_per_second": 22.783,
      "eval_steps_per_second": 0.119,
      "step": 810
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 1.7784,
      "step": 811
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 1.7783,
      "step": 812
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 1.7815,
      "step": 813
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 1.7825,
      "step": 814
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 1.7881,
      "step": 815
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 1.7623,
      "step": 816
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 1.7798,
      "step": 817
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 1.7786,
      "step": 818
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 1.7622,
      "step": 819
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 1.7853,
      "step": 820
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 1.7792,
      "step": 821
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 1.7756,
      "step": 822
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 1.7802,
      "step": 823
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 1.7783,
      "step": 824
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 1.7692,
      "step": 825
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 1.7705,
      "step": 826
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 1.7734,
      "step": 827
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 1.7747,
      "step": 828
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 1.7761,
      "step": 829
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 1.7798,
      "step": 830
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 1.7804,
      "step": 831
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 1.7848,
      "step": 832
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 1.7902,
      "step": 833
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 1.7773,
      "step": 834
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 1.7582,
      "step": 835
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 1.7755,
      "step": 836
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 1.7703,
      "step": 837
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 1.764,
      "step": 838
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 1.7736,
      "step": 839
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 1.7788,
      "step": 840
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 1.7737,
      "step": 841
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 1.7686,
      "step": 842
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 1.7827,
      "step": 843
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 1.781,
      "step": 844
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 1.764,
      "step": 845
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 1.7809,
      "step": 846
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 1.7698,
      "step": 847
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 1.7792,
      "step": 848
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 1.771,
      "step": 849
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 1.7744,
      "step": 850
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 1.7715,
      "step": 851
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 1.7642,
      "step": 852
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 1.7683,
      "step": 853
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 1.7697,
      "step": 854
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 1.769,
      "step": 855
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 1.7805,
      "step": 856
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 1.7772,
      "step": 857
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 1.7838,
      "step": 858
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 1.7692,
      "step": 859
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 1.7811,
      "step": 860
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 1.7699,
      "step": 861
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 1.7649,
      "step": 862
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 1.7803,
      "step": 863
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 1.7865,
      "step": 864
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 1.7712,
      "step": 865
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 1.7544,
      "step": 866
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 1.7786,
      "step": 867
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 1.7676,
      "step": 868
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 1.7689,
      "step": 869
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 1.7797,
      "step": 870
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 1.7751,
      "step": 871
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 1.769,
      "step": 872
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 1.7719,
      "step": 873
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 1.7853,
      "step": 874
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 1.7716,
      "step": 875
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 1.7877,
      "step": 876
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 1.7733,
      "step": 877
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 1.7693,
      "step": 878
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 1.7683,
      "step": 879
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 1.7737,
      "step": 880
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 1.7726,
      "step": 881
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 1.7676,
      "step": 882
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 1.774,
      "step": 883
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 1.781,
      "step": 884
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 1.7782,
      "step": 885
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 1.778,
      "step": 886
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 1.7598,
      "step": 887
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 1.7786,
      "step": 888
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 1.7643,
      "step": 889
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 1.7733,
      "step": 890
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 1.7592,
      "step": 891
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 1.7751,
      "step": 892
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 1.7758,
      "step": 893
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 1.7756,
      "step": 894
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 1.7754,
      "step": 895
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 1.7717,
      "step": 896
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 1.7657,
      "step": 897
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 1.7643,
      "step": 898
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 1.7646,
      "step": 899
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 1.7715,
      "step": 900
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.7676039934158325,
      "eval_runtime": 2540.0025,
      "eval_samples_per_second": 23.031,
      "eval_steps_per_second": 0.12,
      "step": 900
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 1.7628,
      "step": 901
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 1.776,
      "step": 902
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 1.7773,
      "step": 903
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 1.7617,
      "step": 904
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 1.7726,
      "step": 905
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 1.7781,
      "step": 906
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 1.7781,
      "step": 907
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 1.775,
      "step": 908
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 1.7732,
      "step": 909
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 1.7694,
      "step": 910
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 1.7703,
      "step": 911
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 1.772,
      "step": 912
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 1.7729,
      "step": 913
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 1.7745,
      "step": 914
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 1.7505,
      "step": 915
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 1.762,
      "step": 916
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 1.7557,
      "step": 917
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 1.7648,
      "step": 918
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 1.7653,
      "step": 919
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 1.774,
      "step": 920
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 1.7643,
      "step": 921
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 1.7629,
      "step": 922
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 1.7557,
      "step": 923
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 1.7673,
      "step": 924
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 1.7556,
      "step": 925
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 1.7747,
      "step": 926
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 1.7582,
      "step": 927
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 1.7755,
      "step": 928
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 1.7679,
      "step": 929
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 1.7666,
      "step": 930
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 1.7634,
      "step": 931
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 1.7634,
      "step": 932
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 1.7672,
      "step": 933
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 1.7635,
      "step": 934
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 1.7548,
      "step": 935
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 1.7723,
      "step": 936
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 1.7584,
      "step": 937
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 1.7812,
      "step": 938
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 1.7797,
      "step": 939
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 1.7692,
      "step": 940
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 1.7572,
      "step": 941
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 1.7614,
      "step": 942
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 1.7714,
      "step": 943
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 1.7657,
      "step": 944
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 1.7717,
      "step": 945
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 1.7609,
      "step": 946
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 1.7521,
      "step": 947
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 1.7706,
      "step": 948
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 1.7529,
      "step": 949
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 1.7786,
      "step": 950
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 1.7642,
      "step": 951
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 1.7688,
      "step": 952
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 1.7645,
      "step": 953
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 1.7573,
      "step": 954
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 1.762,
      "step": 955
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 1.7737,
      "step": 956
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 1.7699,
      "step": 957
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 1.7571,
      "step": 958
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 1.7596,
      "step": 959
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 1.767,
      "step": 960
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 1.7671,
      "step": 961
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 1.7642,
      "step": 962
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 1.7611,
      "step": 963
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 1.7578,
      "step": 964
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 1.765,
      "step": 965
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 1.7711,
      "step": 966
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 1.762,
      "step": 967
    },
    {
      "epoch": 1.0,
      "step": 967,
      "total_flos": 1.7961044812541356e+20,
      "train_loss": 0.28749041867971176,
      "train_runtime": 27407.5144,
      "train_samples_per_second": 40.652,
      "train_steps_per_second": 0.035
    }
  ],
  "max_steps": 967,
  "num_train_epochs": 1,
  "total_flos": 1.7961044812541356e+20,
  "trial_name": null,
  "trial_params": null
}