{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 50.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 2.3971,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 4e-05,
      "loss": 2.461,
      "step": 2
    },
    {
      "epoch": 1.5,
      "learning_rate": 6e-05,
      "loss": 2.5204,
      "step": 3
    },
    {
      "epoch": 2.0,
      "learning_rate": 8e-05,
      "loss": 2.1248,
      "step": 4
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0001,
      "loss": 1.9833,
      "step": 5
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00012,
      "loss": 2.1376,
      "step": 6
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.00014,
      "loss": 1.8588,
      "step": 7
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00016,
      "loss": 1.7741,
      "step": 8
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.00018,
      "loss": 1.6101,
      "step": 9
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0002,
      "loss": 1.602,
      "step": 10
    },
    {
      "epoch": 5.5,
      "learning_rate": 0.00019777777777777778,
      "loss": 1.3506,
      "step": 11
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00019555555555555556,
      "loss": 1.3243,
      "step": 12
    },
    {
      "epoch": 6.5,
      "learning_rate": 0.00019333333333333333,
      "loss": 1.1528,
      "step": 13
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00019111111111111114,
      "loss": 1.0344,
      "step": 14
    },
    {
      "epoch": 7.5,
      "learning_rate": 0.00018888888888888888,
      "loss": 0.9344,
      "step": 15
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.0001866666666666667,
      "loss": 0.866,
      "step": 16
    },
    {
      "epoch": 8.5,
      "learning_rate": 0.00018444444444444446,
      "loss": 0.6751,
      "step": 17
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.00018222222222222224,
      "loss": 0.66,
      "step": 18
    },
    {
      "epoch": 9.5,
      "learning_rate": 0.00018,
      "loss": 0.5083,
      "step": 19
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.4227,
      "step": 20
    },
    {
      "epoch": 10.5,
      "learning_rate": 0.00017555555555555556,
      "loss": 0.3149,
      "step": 21
    },
    {
      "epoch": 11.0,
      "learning_rate": 0.00017333333333333334,
      "loss": 0.2655,
      "step": 22
    },
    {
      "epoch": 11.5,
      "learning_rate": 0.0001711111111111111,
      "loss": 0.1734,
      "step": 23
    },
    {
      "epoch": 12.0,
      "learning_rate": 0.00016888888888888889,
      "loss": 0.1669,
      "step": 24
    },
    {
      "epoch": 12.5,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.1155,
      "step": 25
    },
    {
      "epoch": 13.0,
      "learning_rate": 0.00016444444444444444,
      "loss": 0.0967,
      "step": 26
    },
    {
      "epoch": 13.5,
      "learning_rate": 0.00016222222222222224,
      "loss": 0.0663,
      "step": 27
    },
    {
      "epoch": 14.0,
      "learning_rate": 0.00016,
      "loss": 0.0794,
      "step": 28
    },
    {
      "epoch": 14.5,
      "learning_rate": 0.0001577777777777778,
      "loss": 0.0642,
      "step": 29
    },
    {
      "epoch": 15.0,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.0495,
      "step": 30
    },
    {
      "epoch": 15.5,
      "learning_rate": 0.00015333333333333334,
      "loss": 0.0395,
      "step": 31
    },
    {
      "epoch": 16.0,
      "learning_rate": 0.0001511111111111111,
      "loss": 0.0731,
      "step": 32
    },
    {
      "epoch": 16.5,
      "learning_rate": 0.0001488888888888889,
      "loss": 0.0458,
      "step": 33
    },
    {
      "epoch": 17.0,
      "learning_rate": 0.00014666666666666666,
      "loss": 0.0499,
      "step": 34
    },
    {
      "epoch": 17.5,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.0345,
      "step": 35
    },
    {
      "epoch": 18.0,
      "learning_rate": 0.00014222222222222224,
      "loss": 0.0463,
      "step": 36
    },
    {
      "epoch": 18.5,
      "learning_rate": 0.00014,
      "loss": 0.0333,
      "step": 37
    },
    {
      "epoch": 19.0,
      "learning_rate": 0.0001377777777777778,
      "loss": 0.0361,
      "step": 38
    },
    {
      "epoch": 19.5,
      "learning_rate": 0.00013555555555555556,
      "loss": 0.0315,
      "step": 39
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.0322,
      "step": 40
    },
    {
      "epoch": 20.5,
      "learning_rate": 0.00013111111111111111,
      "loss": 0.0281,
      "step": 41
    },
    {
      "epoch": 21.0,
      "learning_rate": 0.00012888888888888892,
      "loss": 0.0243,
      "step": 42
    },
    {
      "epoch": 21.5,
      "learning_rate": 0.00012666666666666666,
      "loss": 0.0181,
      "step": 43
    },
    {
      "epoch": 22.0,
      "learning_rate": 0.00012444444444444444,
      "loss": 0.0277,
      "step": 44
    },
    {
      "epoch": 22.5,
      "learning_rate": 0.00012222222222222224,
      "loss": 0.0196,
      "step": 45
    },
    {
      "epoch": 23.0,
      "learning_rate": 0.00012,
      "loss": 0.0257,
      "step": 46
    },
    {
      "epoch": 23.5,
      "learning_rate": 0.00011777777777777779,
      "loss": 0.0153,
      "step": 47
    },
    {
      "epoch": 24.0,
      "learning_rate": 0.00011555555555555555,
      "loss": 0.0252,
      "step": 48
    },
    {
      "epoch": 24.5,
      "learning_rate": 0.00011333333333333334,
      "loss": 0.0134,
      "step": 49
    },
    {
      "epoch": 25.0,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.0256,
      "step": 50
    },
    {
      "epoch": 25.5,
      "learning_rate": 0.00010888888888888889,
      "loss": 0.025,
      "step": 51
    },
    {
      "epoch": 26.0,
      "learning_rate": 0.00010666666666666667,
      "loss": 0.0137,
      "step": 52
    },
    {
      "epoch": 26.5,
      "learning_rate": 0.00010444444444444445,
      "loss": 0.0195,
      "step": 53
    },
    {
      "epoch": 27.0,
      "learning_rate": 0.00010222222222222222,
      "loss": 0.0179,
      "step": 54
    },
    {
      "epoch": 27.5,
      "learning_rate": 0.0001,
      "loss": 0.0178,
      "step": 55
    },
    {
      "epoch": 28.0,
      "learning_rate": 9.777777777777778e-05,
      "loss": 0.0181,
      "step": 56
    },
    {
      "epoch": 28.5,
      "learning_rate": 9.555555555555557e-05,
      "loss": 0.013,
      "step": 57
    },
    {
      "epoch": 29.0,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.0226,
      "step": 58
    },
    {
      "epoch": 29.5,
      "learning_rate": 9.111111111111112e-05,
      "loss": 0.0223,
      "step": 59
    },
    {
      "epoch": 30.0,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.0126,
      "step": 60
    },
    {
      "epoch": 30.5,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.0173,
      "step": 61
    },
    {
      "epoch": 31.0,
      "learning_rate": 8.444444444444444e-05,
      "loss": 0.0168,
      "step": 62
    },
    {
      "epoch": 31.5,
      "learning_rate": 8.222222222222222e-05,
      "loss": 0.0158,
      "step": 63
    },
    {
      "epoch": 32.0,
      "learning_rate": 8e-05,
      "loss": 0.0176,
      "step": 64
    },
    {
      "epoch": 32.5,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.0214,
      "step": 65
    },
    {
      "epoch": 33.0,
      "learning_rate": 7.555555555555556e-05,
      "loss": 0.0117,
      "step": 66
    },
    {
      "epoch": 33.5,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.0215,
      "step": 67
    },
    {
      "epoch": 34.0,
      "learning_rate": 7.111111111111112e-05,
      "loss": 0.0108,
      "step": 68
    },
    {
      "epoch": 34.5,
      "learning_rate": 6.88888888888889e-05,
      "loss": 0.0109,
      "step": 69
    },
    {
      "epoch": 35.0,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0206,
      "step": 70
    },
    {
      "epoch": 35.5,
      "learning_rate": 6.444444444444446e-05,
      "loss": 0.0158,
      "step": 71
    },
    {
      "epoch": 36.0,
      "learning_rate": 6.222222222222222e-05,
      "loss": 0.0152,
      "step": 72
    },
    {
      "epoch": 36.5,
      "learning_rate": 6e-05,
      "loss": 0.0089,
      "step": 73
    },
    {
      "epoch": 37.0,
      "learning_rate": 5.7777777777777776e-05,
      "loss": 0.0215,
      "step": 74
    },
    {
      "epoch": 37.5,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.0147,
      "step": 75
    },
    {
      "epoch": 38.0,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.0148,
      "step": 76
    },
    {
      "epoch": 38.5,
      "learning_rate": 5.111111111111111e-05,
      "loss": 0.0144,
      "step": 77
    },
    {
      "epoch": 39.0,
      "learning_rate": 4.888888888888889e-05,
      "loss": 0.0145,
      "step": 78
    },
    {
      "epoch": 39.5,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.0142,
      "step": 79
    },
    {
      "epoch": 40.0,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.0142,
      "step": 80
    },
    {
      "epoch": 40.5,
      "learning_rate": 4.222222222222222e-05,
      "loss": 0.0137,
      "step": 81
    },
    {
      "epoch": 41.0,
      "learning_rate": 4e-05,
      "loss": 0.0138,
      "step": 82
    },
    {
      "epoch": 41.5,
      "learning_rate": 3.777777777777778e-05,
      "loss": 0.0146,
      "step": 83
    },
    {
      "epoch": 42.0,
      "learning_rate": 3.555555555555556e-05,
      "loss": 0.0129,
      "step": 84
    },
    {
      "epoch": 42.5,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0078,
      "step": 85
    },
    {
      "epoch": 43.0,
      "learning_rate": 3.111111111111111e-05,
      "loss": 0.0186,
      "step": 86
    },
    {
      "epoch": 43.5,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 0.0075,
      "step": 87
    },
    {
      "epoch": 44.0,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.0186,
      "step": 88
    },
    {
      "epoch": 44.5,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 0.0129,
      "step": 89
    },
    {
      "epoch": 45.0,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0128,
      "step": 90
    },
    {
      "epoch": 45.5,
      "learning_rate": 2e-05,
      "loss": 0.0187,
      "step": 91
    },
    {
      "epoch": 46.0,
      "learning_rate": 1.777777777777778e-05,
      "loss": 0.0065,
      "step": 92
    },
    {
      "epoch": 46.5,
      "learning_rate": 1.5555555555555555e-05,
      "loss": 0.0128,
      "step": 93
    },
    {
      "epoch": 47.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0126,
      "step": 94
    },
    {
      "epoch": 47.5,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0123,
      "step": 95
    },
    {
      "epoch": 48.0,
      "learning_rate": 8.88888888888889e-06,
      "loss": 0.0128,
      "step": 96
    },
    {
      "epoch": 48.5,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.0124,
      "step": 97
    },
    {
      "epoch": 49.0,
      "learning_rate": 4.444444444444445e-06,
      "loss": 0.0124,
      "step": 98
    },
    {
      "epoch": 49.5,
      "learning_rate": 2.2222222222222225e-06,
      "loss": 0.0124,
      "step": 99
    },
    {
      "epoch": 50.0,
      "learning_rate": 0.0,
      "loss": 0.0123,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 1.75318518202368e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}