{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9903536977491961,
  "eval_steps": 500,
  "global_step": 77,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.6351,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 1.6528,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.6835,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.995614150494293e-05,
      "loss": 1.6183,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.982464296247522e-05,
      "loss": 1.6164,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.4991,
      "step": 6
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.929980185352526e-05,
      "loss": 1.4829,
      "step": 7
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.4138,
      "step": 8
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.842915805643155e-05,
      "loss": 1.4584,
      "step": 9
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.786597487660337e-05,
      "loss": 1.3482,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.721881851187406e-05,
      "loss": 1.3124,
      "step": 11
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.648882429441257e-05,
      "loss": 1.236,
      "step": 12
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.2427,
      "step": 13
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.478558801197065e-05,
      "loss": 1.1855,
      "step": 14
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.1507,
      "step": 15
    },
    {
      "epoch": 0.21,
      "learning_rate": 9.276821300802534e-05,
      "loss": 1.1127,
      "step": 16
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.164606203550497e-05,
      "loss": 1.0321,
      "step": 17
    },
    {
      "epoch": 0.23,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0016,
      "step": 18
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.9184672866292e-05,
      "loss": 0.9561,
      "step": 19
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.784975278258783e-05,
      "loss": 0.9562,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 8.644843137107059e-05,
      "loss": 0.8827,
      "step": 21
    },
    {
      "epoch": 0.28,
      "learning_rate": 8.498316702566828e-05,
      "loss": 0.8499,
      "step": 22
    },
    {
      "epoch": 0.3,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8233,
      "step": 23
    },
    {
      "epoch": 0.31,
      "learning_rate": 8.18711994874345e-05,
      "loss": 0.8412,
      "step": 24
    },
    {
      "epoch": 0.32,
      "learning_rate": 8.022995574311876e-05,
      "loss": 0.7966,
      "step": 25
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.85356783842216e-05,
      "loss": 0.7664,
      "step": 26
    },
    {
      "epoch": 0.35,
      "learning_rate": 7.679133974894983e-05,
      "loss": 0.7188,
      "step": 27
    },
    {
      "epoch": 0.36,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6549,
      "step": 28
    },
    {
      "epoch": 0.37,
      "learning_rate": 7.316480175599309e-05,
      "loss": 0.6638,
      "step": 29
    },
    {
      "epoch": 0.39,
      "learning_rate": 7.128896457825364e-05,
      "loss": 0.6472,
      "step": 30
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.937577932260515e-05,
      "loss": 0.6237,
      "step": 31
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.742860236609077e-05,
      "loss": 0.5706,
      "step": 32
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5788,
      "step": 33
    },
    {
      "epoch": 0.44,
      "learning_rate": 6.344599103076329e-05,
      "loss": 0.5543,
      "step": 34
    },
    {
      "epoch": 0.45,
      "learning_rate": 6.141754350553279e-05,
      "loss": 0.5639,
      "step": 35
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.9369065729286245e-05,
      "loss": 0.5404,
      "step": 36
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.730415142812059e-05,
      "loss": 0.5429,
      "step": 37
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.506,
      "step": 38
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.313952597646568e-05,
      "loss": 0.4793,
      "step": 39
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.104712099416785e-05,
      "loss": 0.4886,
      "step": 40
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.895287900583216e-05,
      "loss": 0.4514,
      "step": 41
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 0.4984,
      "step": 42
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.4464,
      "step": 43
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.269584857187943e-05,
      "loss": 0.4846,
      "step": 44
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.063093427071376e-05,
      "loss": 0.4491,
      "step": 45
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.858245649446721e-05,
      "loss": 0.4662,
      "step": 46
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.655400896923672e-05,
      "loss": 0.4442,
      "step": 47
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.454,
      "step": 48
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.257139763390925e-05,
      "loss": 0.3953,
      "step": 49
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.062422067739485e-05,
      "loss": 0.4575,
      "step": 50
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 0.4269,
      "step": 51
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.6835198244006927e-05,
      "loss": 0.411,
      "step": 52
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4304,
      "step": 53
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.3208660251050158e-05,
      "loss": 0.4284,
      "step": 54
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.1464321615778422e-05,
      "loss": 0.4016,
      "step": 55
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.977004425688126e-05,
      "loss": 0.428,
      "step": 56
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.8128800512565513e-05,
      "loss": 0.3949,
      "step": 57
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.4035,
      "step": 58
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.5016832974331724e-05,
      "loss": 0.3929,
      "step": 59
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 0.37,
      "step": 60
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.2150247217412186e-05,
      "loss": 0.3788,
      "step": 61
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.0815327133708015e-05,
      "loss": 0.4043,
      "step": 62
    },
    {
      "epoch": 0.81,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.4129,
      "step": 63
    },
    {
      "epoch": 0.82,
      "learning_rate": 8.353937964495029e-06,
      "loss": 0.3976,
      "step": 64
    },
    {
      "epoch": 0.84,
      "learning_rate": 7.2317869919746705e-06,
      "loss": 0.3999,
      "step": 65
    },
    {
      "epoch": 0.85,
      "learning_rate": 6.184665997806832e-06,
      "loss": 0.3564,
      "step": 66
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.214411988029355e-06,
      "loss": 0.3593,
      "step": 67
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.3916,
      "step": 68
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.511175705587433e-06,
      "loss": 0.3861,
      "step": 69
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.7811814881259503e-06,
      "loss": 0.3967,
      "step": 70
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.134025123396638e-06,
      "loss": 0.3624,
      "step": 71
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.5708419435684462e-06,
      "loss": 0.358,
      "step": 72
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.3965,
      "step": 73
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.001981464747565e-07,
      "loss": 0.3942,
      "step": 74
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.9426493427611177e-07,
      "loss": 0.3857,
      "step": 75
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.753570375247815e-07,
      "loss": 0.4294,
      "step": 76
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.385849505708084e-08,
      "loss": 0.3373,
      "step": 77
    },
    {
      "epoch": 0.99,
      "step": 77,
      "total_flos": 543429523144704.0,
      "train_loss": 0.7125843113118951,
      "train_runtime": 6470.7689,
      "train_samples_per_second": 0.769,
      "train_steps_per_second": 0.012
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 77,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 543429523144704.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}