{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6299212598425197,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 1.3981,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2041199826559246e-05,
      "loss": 0.329,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9084850188786497e-05,
      "loss": 0.29,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.4082399653118492e-05,
      "loss": 0.2859,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.7958800173440747e-05,
      "loss": 0.2634,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.112605001534575e-05,
      "loss": 0.2199,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.3803921600570274e-05,
      "loss": 0.1989,
      "step": 7
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.612359947967774e-05,
      "loss": 0.301,
      "step": 8
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.8169700377572995e-05,
      "loss": 0.2181,
      "step": 9
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.9999999999999996e-05,
      "loss": 0.218,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 4e-05,
      "loss": 0.2513,
      "step": 11
    },
    {
      "epoch": 0.08,
      "learning_rate": 4e-05,
      "loss": 0.2497,
      "step": 12
    },
    {
      "epoch": 0.08,
      "learning_rate": 4e-05,
      "loss": 0.2454,
      "step": 13
    },
    {
      "epoch": 0.09,
      "learning_rate": 4e-05,
      "loss": 0.3091,
      "step": 14
    },
    {
      "epoch": 0.09,
      "learning_rate": 4e-05,
      "loss": 0.2809,
      "step": 15
    },
    {
      "epoch": 0.1,
      "learning_rate": 4e-05,
      "loss": 0.2341,
      "step": 16
    },
    {
      "epoch": 0.11,
      "learning_rate": 4e-05,
      "loss": 0.2586,
      "step": 17
    },
    {
      "epoch": 0.11,
      "learning_rate": 4e-05,
      "loss": 0.2759,
      "step": 18
    },
    {
      "epoch": 0.12,
      "learning_rate": 4e-05,
      "loss": 0.266,
      "step": 19
    },
    {
      "epoch": 0.13,
      "learning_rate": 4e-05,
      "loss": 0.2164,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 4e-05,
      "loss": 0.3236,
      "step": 21
    },
    {
      "epoch": 0.14,
      "learning_rate": 4e-05,
      "loss": 0.1997,
      "step": 22
    },
    {
      "epoch": 0.14,
      "learning_rate": 4e-05,
      "loss": 0.2172,
      "step": 23
    },
    {
      "epoch": 0.15,
      "learning_rate": 4e-05,
      "loss": 0.2363,
      "step": 24
    },
    {
      "epoch": 0.16,
      "learning_rate": 4e-05,
      "loss": 0.2177,
      "step": 25
    },
    {
      "epoch": 0.16,
      "learning_rate": 4e-05,
      "loss": 0.22,
      "step": 26
    },
    {
      "epoch": 0.17,
      "learning_rate": 4e-05,
      "loss": 0.2633,
      "step": 27
    },
    {
      "epoch": 0.18,
      "learning_rate": 4e-05,
      "loss": 0.2359,
      "step": 28
    },
    {
      "epoch": 0.18,
      "learning_rate": 4e-05,
      "loss": 0.2399,
      "step": 29
    },
    {
      "epoch": 0.19,
      "learning_rate": 4e-05,
      "loss": 0.2127,
      "step": 30
    },
    {
      "epoch": 0.2,
      "learning_rate": 4e-05,
      "loss": 0.2089,
      "step": 31
    },
    {
      "epoch": 0.2,
      "learning_rate": 4e-05,
      "loss": 0.2565,
      "step": 32
    },
    {
      "epoch": 0.21,
      "learning_rate": 4e-05,
      "loss": 0.3104,
      "step": 33
    },
    {
      "epoch": 0.21,
      "learning_rate": 4e-05,
      "loss": 0.2222,
      "step": 34
    },
    {
      "epoch": 0.22,
      "learning_rate": 4e-05,
      "loss": 0.3013,
      "step": 35
    },
    {
      "epoch": 0.23,
      "learning_rate": 4e-05,
      "loss": 0.2567,
      "step": 36
    },
    {
      "epoch": 0.23,
      "learning_rate": 4e-05,
      "loss": 0.2098,
      "step": 37
    },
    {
      "epoch": 0.24,
      "learning_rate": 4e-05,
      "loss": 0.1508,
      "step": 38
    },
    {
      "epoch": 0.25,
      "learning_rate": 4e-05,
      "loss": 0.144,
      "step": 39
    },
    {
      "epoch": 0.25,
      "learning_rate": 4e-05,
      "loss": 0.1909,
      "step": 40
    },
    {
      "epoch": 0.26,
      "learning_rate": 4e-05,
      "loss": 0.191,
      "step": 41
    },
    {
      "epoch": 0.26,
      "learning_rate": 4e-05,
      "loss": 0.2457,
      "step": 42
    },
    {
      "epoch": 0.27,
      "learning_rate": 4e-05,
      "loss": 0.2033,
      "step": 43
    },
    {
      "epoch": 0.28,
      "learning_rate": 4e-05,
      "loss": 0.1975,
      "step": 44
    },
    {
      "epoch": 0.28,
      "learning_rate": 4e-05,
      "loss": 0.214,
      "step": 45
    },
    {
      "epoch": 0.29,
      "learning_rate": 4e-05,
      "loss": 0.1866,
      "step": 46
    },
    {
      "epoch": 0.3,
      "learning_rate": 4e-05,
      "loss": 0.1723,
      "step": 47
    },
    {
      "epoch": 0.3,
      "learning_rate": 4e-05,
      "loss": 0.2096,
      "step": 48
    },
    {
      "epoch": 0.31,
      "learning_rate": 4e-05,
      "loss": 0.2446,
      "step": 49
    },
    {
      "epoch": 0.31,
      "learning_rate": 4e-05,
      "loss": 0.2143,
      "step": 50
    },
    {
      "epoch": 0.32,
      "learning_rate": 4e-05,
      "loss": 0.1949,
      "step": 51
    },
    {
      "epoch": 0.33,
      "learning_rate": 4e-05,
      "loss": 0.2328,
      "step": 52
    },
    {
      "epoch": 0.33,
      "learning_rate": 4e-05,
      "loss": 0.2731,
      "step": 53
    },
    {
      "epoch": 0.34,
      "learning_rate": 4e-05,
      "loss": 0.2108,
      "step": 54
    },
    {
      "epoch": 0.35,
      "learning_rate": 4e-05,
      "loss": 0.2844,
      "step": 55
    },
    {
      "epoch": 0.35,
      "learning_rate": 4e-05,
      "loss": 0.2145,
      "step": 56
    },
    {
      "epoch": 0.36,
      "learning_rate": 4e-05,
      "loss": 0.1923,
      "step": 57
    },
    {
      "epoch": 0.37,
      "learning_rate": 4e-05,
      "loss": 0.2242,
      "step": 58
    },
    {
      "epoch": 0.37,
      "learning_rate": 4e-05,
      "loss": 0.195,
      "step": 59
    },
    {
      "epoch": 0.38,
      "learning_rate": 4e-05,
      "loss": 0.2439,
      "step": 60
    },
    {
      "epoch": 0.38,
      "learning_rate": 4e-05,
      "loss": 0.2128,
      "step": 61
    },
    {
      "epoch": 0.39,
      "learning_rate": 4e-05,
      "loss": 0.2006,
      "step": 62
    },
    {
      "epoch": 0.4,
      "learning_rate": 4e-05,
      "loss": 0.2318,
      "step": 63
    },
    {
      "epoch": 0.4,
      "learning_rate": 4e-05,
      "loss": 0.2368,
      "step": 64
    },
    {
      "epoch": 0.41,
      "learning_rate": 4e-05,
      "loss": 0.2003,
      "step": 65
    },
    {
      "epoch": 0.42,
      "learning_rate": 4e-05,
      "loss": 0.272,
      "step": 66
    },
    {
      "epoch": 0.42,
      "learning_rate": 4e-05,
      "loss": 0.261,
      "step": 67
    },
    {
      "epoch": 0.43,
      "learning_rate": 4e-05,
      "loss": 0.2307,
      "step": 68
    },
    {
      "epoch": 0.43,
      "learning_rate": 4e-05,
      "loss": 0.2784,
      "step": 69
    },
    {
      "epoch": 0.44,
      "learning_rate": 4e-05,
      "loss": 0.2086,
      "step": 70
    },
    {
      "epoch": 0.45,
      "learning_rate": 4e-05,
      "loss": 0.1963,
      "step": 71
    },
    {
      "epoch": 0.45,
      "learning_rate": 4e-05,
      "loss": 0.2403,
      "step": 72
    },
    {
      "epoch": 0.46,
      "learning_rate": 4e-05,
      "loss": 0.2026,
      "step": 73
    },
    {
      "epoch": 0.47,
      "learning_rate": 4e-05,
      "loss": 0.1503,
      "step": 74
    },
    {
      "epoch": 0.47,
      "learning_rate": 4e-05,
      "loss": 0.2238,
      "step": 75
    },
    {
      "epoch": 0.48,
      "learning_rate": 4e-05,
      "loss": 0.212,
      "step": 76
    },
    {
      "epoch": 0.49,
      "learning_rate": 4e-05,
      "loss": 0.1937,
      "step": 77
    },
    {
      "epoch": 0.49,
      "learning_rate": 4e-05,
      "loss": 0.211,
      "step": 78
    },
    {
      "epoch": 0.5,
      "learning_rate": 4e-05,
      "loss": 0.1827,
      "step": 79
    },
    {
      "epoch": 0.5,
      "learning_rate": 4e-05,
      "loss": 0.239,
      "step": 80
    },
    {
      "epoch": 0.51,
      "learning_rate": 4e-05,
      "loss": 0.1562,
      "step": 81
    },
    {
      "epoch": 0.52,
      "learning_rate": 4e-05,
      "loss": 0.2474,
      "step": 82
    },
    {
      "epoch": 0.52,
      "learning_rate": 4e-05,
      "loss": 0.2411,
      "step": 83
    },
    {
      "epoch": 0.53,
      "learning_rate": 4e-05,
      "loss": 0.2161,
      "step": 84
    },
    {
      "epoch": 0.54,
      "learning_rate": 4e-05,
      "loss": 0.2073,
      "step": 85
    },
    {
      "epoch": 0.54,
      "learning_rate": 4e-05,
      "loss": 0.2831,
      "step": 86
    },
    {
      "epoch": 0.55,
      "learning_rate": 4e-05,
      "loss": 0.2248,
      "step": 87
    },
    {
      "epoch": 0.55,
      "learning_rate": 4e-05,
      "loss": 0.2389,
      "step": 88
    },
    {
      "epoch": 0.56,
      "learning_rate": 4e-05,
      "loss": 0.2568,
      "step": 89
    },
    {
      "epoch": 0.57,
      "learning_rate": 4e-05,
      "loss": 0.2357,
      "step": 90
    },
    {
      "epoch": 0.57,
      "learning_rate": 4e-05,
      "loss": 0.1761,
      "step": 91
    },
    {
      "epoch": 0.58,
      "learning_rate": 4e-05,
      "loss": 0.2071,
      "step": 92
    },
    {
      "epoch": 0.59,
      "learning_rate": 4e-05,
      "loss": 0.2949,
      "step": 93
    },
    {
      "epoch": 0.59,
      "learning_rate": 4e-05,
      "loss": 0.1997,
      "step": 94
    },
    {
      "epoch": 0.6,
      "learning_rate": 4e-05,
      "loss": 0.2169,
      "step": 95
    },
    {
      "epoch": 0.6,
      "learning_rate": 4e-05,
      "loss": 0.21,
      "step": 96
    },
    {
      "epoch": 0.61,
      "learning_rate": 4e-05,
      "loss": 0.1894,
      "step": 97
    },
    {
      "epoch": 0.62,
      "learning_rate": 4e-05,
      "loss": 0.2253,
      "step": 98
    },
    {
      "epoch": 0.62,
      "learning_rate": 4e-05,
      "loss": 0.2096,
      "step": 99
    },
    {
      "epoch": 0.63,
      "learning_rate": 4e-05,
      "loss": 0.2621,
      "step": 100
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 474,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 5221405163520.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}