{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0482994566311129,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.0291,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 3.0896,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 4.3592,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 6.2712,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 4.2501,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 3.0924,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 4.5169,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 3.9676,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 4.4685,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 5.3529,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 4.2388,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 4.1081,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 6.1007,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 4.1076,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 4.0546,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.917,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 4.8566,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.837,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.7712,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.6316,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.249,
      "step": 21
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 4.3575,
      "step": 22
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.2814,
      "step": 23
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.0843,
      "step": 24
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.9652,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 4.2221,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.0886,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.5598,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.6553,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.4734,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.816,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.3297,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.6176,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.7432,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.4295,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.4644,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.253,
      "step": 37
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.4445,
      "step": 38
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.4902,
      "step": 39
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.1427,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.3103,
      "step": 41
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.1879,
      "step": 42
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.1754,
      "step": 43
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0042,
      "step": 44
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0927,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.2187,
      "step": 46
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.3206,
      "step": 47
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.8578,
      "step": 48
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.4186,
      "step": 49
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.0463,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7226,
      "step": 51
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7234,
      "step": 52
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.4434,
      "step": 53
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.0398,
      "step": 54
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.9362,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.5221,
      "step": 56
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.4796,
      "step": 57
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2356,
      "step": 58
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2413,
      "step": 59
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2293,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.3368,
      "step": 61
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.5477,
      "step": 62
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1923,
      "step": 63
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.7991,
      "step": 64
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.0258,
      "step": 65
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.0965,
      "step": 66
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.9706,
      "step": 67
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.5689,
      "step": 68
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.026,
      "step": 69
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.3004,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 3.8946,
      "step": 71
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.9336,
      "step": 72
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.8354,
      "step": 73
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1151,
      "step": 74
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.2508,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.3041,
      "step": 76
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.2355,
      "step": 77
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.4521,
      "step": 78
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.3691,
      "step": 79
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.381,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.148,
      "step": 81
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1019,
      "step": 82
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1921,
      "step": 83
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.3371,
      "step": 84
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 3.0662,
      "step": 85
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.3774,
      "step": 86
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.2142,
      "step": 87
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.156,
      "step": 88
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1384,
      "step": 89
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 3.1821,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.3302,
      "step": 91
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.2933,
      "step": 92
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.302,
      "step": 93
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.7408,
      "step": 94
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.4078,
      "step": 95
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.4886,
      "step": 96
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.7161,
      "step": 97
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.6476,
      "step": 98
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 3.5221,
      "step": 99
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 4.5006,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 4.7155,
      "step": 101
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1714,
      "step": 102
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0192,
      "step": 103
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.3325,
      "step": 104
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.4262,
      "step": 105
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.4184,
      "step": 106
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0848,
      "step": 107
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.2386,
      "step": 108
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1185,
      "step": 109
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0466,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1534,
      "step": 111
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.9869,
      "step": 112
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.8914,
      "step": 113
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.3953,
      "step": 114
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.2526,
      "step": 115
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.7755,
      "step": 116
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.9315,
      "step": 117
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.9853,
      "step": 118
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.1917,
      "step": 119
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.079,
      "step": 120
    }
  ],
  "max_steps": 120,
  "num_train_epochs": 1,
  "total_flos": 627303342243840.0,
  "trial_name": null,
  "trial_params": null
}