{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7831325301204819,
  "eval_steps": 500,
  "global_step": 130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.9995000000000005e-05,
      "loss": 1.7049,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999e-05,
      "loss": 2.9872,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9985e-05,
      "loss": 2.1065,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9980000000000006e-05,
      "loss": 2.2636,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9975e-05,
      "loss": 1.8175,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.997e-05,
      "loss": 1.5265,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9965e-05,
      "loss": 1.3999,
      "step": 7
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.996e-05,
      "loss": 1.3867,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9955e-05,
      "loss": 1.3329,
      "step": 9
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.995e-05,
      "loss": 1.3145,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.9945000000000004e-05,
      "loss": 1.2775,
      "step": 11
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.9940000000000006e-05,
      "loss": 1.2551,
      "step": 12
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9935e-05,
      "loss": 1.2279,
      "step": 13
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9930000000000005e-05,
      "loss": 1.1668,
      "step": 14
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.992500000000001e-05,
      "loss": 1.1261,
      "step": 15
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.992e-05,
      "loss": 1.1738,
      "step": 16
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.9915e-05,
      "loss": 1.1098,
      "step": 17
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.991e-05,
      "loss": 1.1268,
      "step": 18
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.9905000000000004e-05,
      "loss": 1.1261,
      "step": 19
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.99e-05,
      "loss": 1.1152,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.9895e-05,
      "loss": 1.1345,
      "step": 21
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.9890000000000005e-05,
      "loss": 1.1341,
      "step": 22
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.9885e-05,
      "loss": 1.1288,
      "step": 23
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.9880000000000004e-05,
      "loss": 1.1264,
      "step": 24
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.9875000000000006e-05,
      "loss": 1.0576,
      "step": 25
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.987e-05,
      "loss": 1.0905,
      "step": 26
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.9865e-05,
      "loss": 1.0967,
      "step": 27
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.986e-05,
      "loss": 1.0937,
      "step": 28
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.9855e-05,
      "loss": 1.0597,
      "step": 29
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.9850000000000006e-05,
      "loss": 1.0706,
      "step": 30
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.9845e-05,
      "loss": 1.0608,
      "step": 31
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.9840000000000004e-05,
      "loss": 1.0817,
      "step": 32
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.9835000000000007e-05,
      "loss": 1.0739,
      "step": 33
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.983e-05,
      "loss": 1.0434,
      "step": 34
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.9825000000000005e-05,
      "loss": 1.0168,
      "step": 35
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.982e-05,
      "loss": 1.0351,
      "step": 36
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.9815e-05,
      "loss": 1.0435,
      "step": 37
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.981e-05,
      "loss": 1.0247,
      "step": 38
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.9805e-05,
      "loss": 1.0065,
      "step": 39
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 1.0036,
      "step": 40
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.9795e-05,
      "loss": 1.0483,
      "step": 41
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.979e-05,
      "loss": 1.0252,
      "step": 42
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.9785000000000005e-05,
      "loss": 1.0344,
      "step": 43
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.978e-05,
      "loss": 1.0353,
      "step": 44
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.9775000000000004e-05,
      "loss": 1.0381,
      "step": 45
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.977e-05,
      "loss": 0.9899,
      "step": 46
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.9765e-05,
      "loss": 0.9786,
      "step": 47
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.976e-05,
      "loss": 1.0434,
      "step": 48
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.9755e-05,
      "loss": 1.0069,
      "step": 49
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.975e-05,
      "loss": 0.9665,
      "step": 50
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.9745000000000006e-05,
      "loss": 0.9754,
      "step": 51
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.974e-05,
      "loss": 0.9718,
      "step": 52
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.9735000000000004e-05,
      "loss": 0.9828,
      "step": 53
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.973000000000001e-05,
      "loss": 0.996,
      "step": 54
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.9725e-05,
      "loss": 1.026,
      "step": 55
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.972e-05,
      "loss": 0.9832,
      "step": 56
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.9715e-05,
      "loss": 0.9985,
      "step": 57
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.9710000000000003e-05,
      "loss": 1.0145,
      "step": 58
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.9705e-05,
      "loss": 0.9708,
      "step": 59
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.97e-05,
      "loss": 0.9411,
      "step": 60
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.9695000000000004e-05,
      "loss": 0.9774,
      "step": 61
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.969e-05,
      "loss": 1.0044,
      "step": 62
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.9685e-05,
      "loss": 0.9581,
      "step": 63
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.9680000000000005e-05,
      "loss": 1.0007,
      "step": 64
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.967500000000001e-05,
      "loss": 0.9589,
      "step": 65
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.967e-05,
      "loss": 0.9704,
      "step": 66
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.9665e-05,
      "loss": 0.978,
      "step": 67
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.966e-05,
      "loss": 0.9554,
      "step": 68
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.9655000000000005e-05,
      "loss": 0.9433,
      "step": 69
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.965e-05,
      "loss": 0.9905,
      "step": 70
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.9645e-05,
      "loss": 0.9578,
      "step": 71
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.9640000000000006e-05,
      "loss": 0.9069,
      "step": 72
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.9635e-05,
      "loss": 0.9647,
      "step": 73
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.9630000000000004e-05,
      "loss": 0.9377,
      "step": 74
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.962500000000001e-05,
      "loss": 0.9343,
      "step": 75
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.962e-05,
      "loss": 0.9644,
      "step": 76
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.9615e-05,
      "loss": 0.9737,
      "step": 77
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.961e-05,
      "loss": 0.9552,
      "step": 78
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.9605000000000004e-05,
      "loss": 0.9158,
      "step": 79
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.96e-05,
      "loss": 0.9278,
      "step": 80
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.9595e-05,
      "loss": 0.9464,
      "step": 81
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.9590000000000005e-05,
      "loss": 0.9672,
      "step": 82
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.9585e-05,
      "loss": 0.9487,
      "step": 83
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.958e-05,
      "loss": 0.9248,
      "step": 84
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.9575000000000006e-05,
      "loss": 0.9443,
      "step": 85
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.957e-05,
      "loss": 0.9565,
      "step": 86
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.9565e-05,
      "loss": 0.934,
      "step": 87
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.956e-05,
      "loss": 0.9198,
      "step": 88
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.9555e-05,
      "loss": 0.8948,
      "step": 89
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.9550000000000005e-05,
      "loss": 0.9336,
      "step": 90
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.9545e-05,
      "loss": 0.9117,
      "step": 91
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.9540000000000003e-05,
      "loss": 0.876,
      "step": 92
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.9535000000000006e-05,
      "loss": 0.9297,
      "step": 93
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.953e-05,
      "loss": 0.9241,
      "step": 94
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.9525000000000004e-05,
      "loss": 0.9305,
      "step": 95
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.952e-05,
      "loss": 0.9395,
      "step": 96
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.9515e-05,
      "loss": 0.9208,
      "step": 97
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.951e-05,
      "loss": 0.9112,
      "step": 98
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.9505e-05,
      "loss": 0.9159,
      "step": 99
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 0.902,
      "step": 100
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.9495e-05,
      "loss": 0.9412,
      "step": 101
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.949e-05,
      "loss": 0.8916,
      "step": 102
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.9485000000000005e-05,
      "loss": 0.8846,
      "step": 103
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.948000000000001e-05,
      "loss": 0.8974,
      "step": 104
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.9475e-05,
      "loss": 0.9332,
      "step": 105
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.947e-05,
      "loss": 0.9,
      "step": 106
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.9465e-05,
      "loss": 0.92,
      "step": 107
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.946e-05,
      "loss": 0.8802,
      "step": 108
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.9455e-05,
      "loss": 0.9199,
      "step": 109
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.945e-05,
      "loss": 0.8872,
      "step": 110
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.9445000000000005e-05,
      "loss": 0.8689,
      "step": 111
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.944e-05,
      "loss": 0.906,
      "step": 112
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.9435000000000004e-05,
      "loss": 0.8725,
      "step": 113
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.9430000000000006e-05,
      "loss": 0.8708,
      "step": 114
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.9425e-05,
      "loss": 0.8726,
      "step": 115
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.942e-05,
      "loss": 0.8584,
      "step": 116
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.9415e-05,
      "loss": 0.9218,
      "step": 117
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.941e-05,
      "loss": 0.8279,
      "step": 118
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.9405e-05,
      "loss": 0.9098,
      "step": 119
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.94e-05,
      "loss": 0.8924,
      "step": 120
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.9395000000000004e-05,
      "loss": 0.8897,
      "step": 121
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.939e-05,
      "loss": 0.876,
      "step": 122
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.9385e-05,
      "loss": 0.912,
      "step": 123
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.9380000000000005e-05,
      "loss": 0.878,
      "step": 124
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.937500000000001e-05,
      "loss": 0.8596,
      "step": 125
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.937e-05,
      "loss": 0.8849,
      "step": 126
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.9365e-05,
      "loss": 0.8471,
      "step": 127
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.936e-05,
      "loss": 0.894,
      "step": 128
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.9355000000000004e-05,
      "loss": 0.9051,
      "step": 129
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.935e-05,
      "loss": 0.8714,
      "step": 130
    }
  ],
  "logging_steps": 1,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 61,
  "save_steps": 10,
  "total_flos": 1.6591004557295616e+16,
  "train_batch_size": 3584,
  "trial_name": null,
  "trial_params": null
}