{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.8585209003215435,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 4.9986331433523156e-05,
      "loss": 0.6891,
      "step": 2
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.994534068046937e-05,
      "loss": 0.5774,
      "step": 4
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.9877072563625285e-05,
      "loss": 0.5359,
      "step": 6
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.978160173317438e-05,
      "loss": 0.541,
      "step": 8
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.965903258506806e-05,
      "loss": 0.5038,
      "step": 10
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.9509499146870236e-05,
      "loss": 0.5397,
      "step": 12
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.933316493120015e-05,
      "loss": 0.5097,
      "step": 14
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.913022275693372e-05,
      "loss": 0.4829,
      "step": 16
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.8900894538358944e-05,
      "loss": 0.503,
      "step": 18
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.864543104251587e-05,
      "loss": 0.535,
      "step": 20
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.8364111614986527e-05,
      "loss": 0.4685,
      "step": 22
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.805724387443462e-05,
      "loss": 0.5223,
      "step": 24
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.7725163376229064e-05,
      "loss": 0.5033,
      "step": 26
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.736823324551909e-05,
      "loss": 0.4991,
      "step": 28
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.698684378016222e-05,
      "loss": 0.5225,
      "step": 30
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.6581412023939354e-05,
      "loss": 0.4711,
      "step": 32
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.6152381310523387e-05,
      "loss": 0.5054,
      "step": 34
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.5700220778700504e-05,
      "loss": 0.5237,
      "step": 36
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.4992,
      "step": 38
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.4728512734909844e-05,
      "loss": 0.3735,
      "step": 40
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.421002777142148e-05,
      "loss": 0.2735,
      "step": 42
    },
    {
      "epoch": 1.13,
      "learning_rate": 4.367053692460385e-05,
      "loss": 0.2565,
      "step": 44
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.311063011977723e-05,
      "loss": 0.2926,
      "step": 46
    },
    {
      "epoch": 1.23,
      "learning_rate": 4.2530919606812216e-05,
      "loss": 0.281,
      "step": 48
    },
    {
      "epoch": 1.29,
      "learning_rate": 4.193203929064353e-05,
      "loss": 0.2619,
      "step": 50
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.131464403810422e-05,
      "loss": 0.2456,
      "step": 52
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.067940896183843e-05,
      "loss": 0.2442,
      "step": 54
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.002702868207563e-05,
      "loss": 0.2625,
      "step": 56
    },
    {
      "epoch": 1.49,
      "learning_rate": 3.935821656707359e-05,
      "loss": 0.2616,
      "step": 58
    },
    {
      "epoch": 1.54,
      "learning_rate": 3.867370395306068e-05,
      "loss": 0.2545,
      "step": 60
    },
    {
      "epoch": 1.59,
      "learning_rate": 3.797423934453038e-05,
      "loss": 0.2728,
      "step": 62
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.726058759576271e-05,
      "loss": 0.234,
      "step": 64
    },
    {
      "epoch": 1.7,
      "learning_rate": 3.65335290744672e-05,
      "loss": 0.2356,
      "step": 66
    },
    {
      "epoch": 1.75,
      "learning_rate": 3.579385880846232e-05,
      "loss": 0.2369,
      "step": 68
    },
    {
      "epoch": 1.8,
      "learning_rate": 3.504238561632424e-05,
      "loss": 0.236,
      "step": 70
    },
    {
      "epoch": 1.85,
      "learning_rate": 3.427993122295552e-05,
      "loss": 0.2607,
      "step": 72
    },
    {
      "epoch": 1.9,
      "learning_rate": 3.350732936104108e-05,
      "loss": 0.2637,
      "step": 74
    },
    {
      "epoch": 1.95,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.2338,
      "step": 76
    },
    {
      "epoch": 2.01,
      "learning_rate": 3.1935072719046115e-05,
      "loss": 0.2489,
      "step": 78
    },
    {
      "epoch": 2.06,
      "learning_rate": 3.1137137178519985e-05,
      "loss": 0.1337,
      "step": 80
    },
    {
      "epoch": 2.11,
      "learning_rate": 3.0332490768593675e-05,
      "loss": 0.1188,
      "step": 82
    },
    {
      "epoch": 2.16,
      "learning_rate": 2.952201335830275e-05,
      "loss": 0.1067,
      "step": 84
    },
    {
      "epoch": 2.21,
      "learning_rate": 2.870659119279605e-05,
      "loss": 0.1131,
      "step": 86
    },
    {
      "epoch": 2.26,
      "learning_rate": 2.788711592423966e-05,
      "loss": 0.1308,
      "step": 88
    },
    {
      "epoch": 2.32,
      "learning_rate": 2.7064483636808313e-05,
      "loss": 0.1236,
      "step": 90
    },
    {
      "epoch": 2.37,
      "learning_rate": 2.623959386683056e-05,
      "loss": 0.1079,
      "step": 92
    },
    {
      "epoch": 2.42,
      "learning_rate": 2.5413348619158967e-05,
      "loss": 0.1102,
      "step": 94
    },
    {
      "epoch": 2.47,
      "learning_rate": 2.458665138084104e-05,
      "loss": 0.1218,
      "step": 96
    },
    {
      "epoch": 2.52,
      "learning_rate": 2.3760406133169443e-05,
      "loss": 0.1148,
      "step": 98
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.2935516363191693e-05,
      "loss": 0.1109,
      "step": 100
    },
    {
      "epoch": 2.62,
      "learning_rate": 2.2112884075760347e-05,
      "loss": 0.1088,
      "step": 102
    },
    {
      "epoch": 2.68,
      "learning_rate": 2.1293408807203947e-05,
      "loss": 0.1109,
      "step": 104
    },
    {
      "epoch": 2.73,
      "learning_rate": 2.047798664169726e-05,
      "loss": 0.0939,
      "step": 106
    },
    {
      "epoch": 2.78,
      "learning_rate": 1.9667509231406334e-05,
      "loss": 0.1179,
      "step": 108
    },
    {
      "epoch": 2.83,
      "learning_rate": 1.8862862821480025e-05,
      "loss": 0.095,
      "step": 110
    },
    {
      "epoch": 2.88,
      "learning_rate": 1.806492728095389e-05,
      "loss": 0.115,
      "step": 112
    },
    {
      "epoch": 2.93,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.1219,
      "step": 114
    },
    {
      "epoch": 2.98,
      "learning_rate": 1.6492670638958924e-05,
      "loss": 0.1153,
      "step": 116
    },
    {
      "epoch": 3.04,
      "learning_rate": 1.5720068777044476e-05,
      "loss": 0.0693,
      "step": 118
    },
    {
      "epoch": 3.09,
      "learning_rate": 1.495761438367577e-05,
      "loss": 0.0535,
      "step": 120
    },
    {
      "epoch": 3.14,
      "learning_rate": 1.4206141191537682e-05,
      "loss": 0.0452,
      "step": 122
    },
    {
      "epoch": 3.19,
      "learning_rate": 1.346647092553281e-05,
      "loss": 0.0444,
      "step": 124
    },
    {
      "epoch": 3.24,
      "learning_rate": 1.2739412404237306e-05,
      "loss": 0.0364,
      "step": 126
    },
    {
      "epoch": 3.29,
      "learning_rate": 1.202576065546963e-05,
      "loss": 0.0591,
      "step": 128
    },
    {
      "epoch": 3.34,
      "learning_rate": 1.1326296046939333e-05,
      "loss": 0.0466,
      "step": 130
    },
    {
      "epoch": 3.4,
      "learning_rate": 1.064178343292641e-05,
      "loss": 0.0558,
      "step": 132
    },
    {
      "epoch": 3.45,
      "learning_rate": 9.972971317924374e-06,
      "loss": 0.0533,
      "step": 134
    },
    {
      "epoch": 3.5,
      "learning_rate": 9.320591038161574e-06,
      "loss": 0.0549,
      "step": 136
    },
    {
      "epoch": 3.55,
      "learning_rate": 8.685355961895784e-06,
      "loss": 0.0446,
      "step": 138
    },
    {
      "epoch": 3.6,
      "learning_rate": 8.067960709356478e-06,
      "loss": 0.0622,
      "step": 140
    },
    {
      "epoch": 3.65,
      "learning_rate": 7.469080393187786e-06,
      "loss": 0.0494,
      "step": 142
    },
    {
      "epoch": 3.7,
      "learning_rate": 6.889369880222776e-06,
      "loss": 0.0391,
      "step": 144
    },
    {
      "epoch": 3.76,
      "learning_rate": 6.329463075396161e-06,
      "loss": 0.0399,
      "step": 146
    },
    {
      "epoch": 3.81,
      "learning_rate": 5.78997222857853e-06,
      "loss": 0.0509,
      "step": 148
    },
    {
      "epoch": 3.86,
      "learning_rate": 5.271487265090163e-06,
      "loss": 0.0451,
      "step": 150
    }
  ],
  "logging_steps": 2,
  "max_steps": 190,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 25,
  "total_flos": 2.0183987688434565e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}