{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6644219977553311,
  "eval_steps": 500,
  "global_step": 296,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.444444444444445e-07,
      "loss": 1.6909,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.222222222222222e-06,
      "loss": 1.5942,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.444444444444444e-06,
      "loss": 1.2719,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.1349,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.0928,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 1.0533,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.0332,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.555555555555556e-05,
      "loss": 1.011,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 1.0103,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 2e-05,
      "loss": 0.9977,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9992290362407232e-05,
      "loss": 0.9846,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9969173337331283e-05,
      "loss": 0.9936,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9930684569549265e-05,
      "loss": 0.9827,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.9814,
      "step": 65
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9807852804032306e-05,
      "loss": 0.9739,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9723699203976768e-05,
      "loss": 0.9794,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9624552364536472e-05,
      "loss": 0.9697,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 0.9789,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9381913359224844e-05,
      "loss": 0.9644,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9238795325112867e-05,
      "loss": 0.9623,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9081431738250815e-05,
      "loss": 0.9618,
      "step": 100
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.891006524188368e-05,
      "loss": 0.9699,
      "step": 105
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.8724960070727974e-05,
      "loss": 0.9563,
      "step": 110
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.8526401643540924e-05,
      "loss": 0.96,
      "step": 115
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8314696123025456e-05,
      "loss": 0.9571,
      "step": 120
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.9595,
      "step": 125
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.785316930880745e-05,
      "loss": 0.9538,
      "step": 130
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.7604059656000313e-05,
      "loss": 0.9493,
      "step": 135
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.7343225094356857e-05,
      "loss": 0.9565,
      "step": 140
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.9507,
      "step": 145
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.678800745532942e-05,
      "loss": 0.9539,
      "step": 150
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.6494480483301836e-05,
      "loss": 0.9507,
      "step": 155
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.6190939493098344e-05,
      "loss": 0.9514,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 0.9511,
      "step": 165
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.5555702330196024e-05,
      "loss": 0.9508,
      "step": 170
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.5224985647159489e-05,
      "loss": 0.9547,
      "step": 175
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.4886212414969551e-05,
      "loss": 0.9508,
      "step": 180
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.4539904997395468e-05,
      "loss": 0.9483,
      "step": 185
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.4186597375374283e-05,
      "loss": 0.9501,
      "step": 190
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.3826834323650899e-05,
      "loss": 0.9355,
      "step": 195
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.346117057077493e-05,
      "loss": 0.9385,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.948,
      "step": 205
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.2714404498650743e-05,
      "loss": 0.9408,
      "step": 210
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.2334453638559057e-05,
      "loss": 0.9478,
      "step": 215
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.1950903220161286e-05,
      "loss": 0.9463,
      "step": 220
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.156434465040231e-05,
      "loss": 0.9313,
      "step": 225
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.1175373974578378e-05,
      "loss": 0.9517,
      "step": 230
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.0784590957278452e-05,
      "loss": 0.9304,
      "step": 235
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.0392598157590687e-05,
      "loss": 0.9368,
      "step": 240
    },
    {
      "epoch": 0.55,
      "learning_rate": 1e-05,
      "loss": 0.9428,
      "step": 245
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.607401842409318e-06,
      "loss": 0.9369,
      "step": 250
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.215409042721553e-06,
      "loss": 0.9326,
      "step": 255
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.824626025421625e-06,
      "loss": 0.9394,
      "step": 260
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.9411,
      "step": 265
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.04909677983872e-06,
      "loss": 0.9348,
      "step": 270
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.66554636144095e-06,
      "loss": 0.9363,
      "step": 275
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.285595501349259e-06,
      "loss": 0.9414,
      "step": 280
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.9365,
      "step": 285
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.538829429225068e-06,
      "loss": 0.9197,
      "step": 290
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.173165676349103e-06,
      "loss": 0.9276,
      "step": 295
    },
    {
      "epoch": 0.66,
      "eval_loss": 0.931494951248169,
      "eval_runtime": 205.9305,
      "eval_samples_per_second": 122.828,
      "eval_steps_per_second": 0.481,
      "step": 296
    },
    {
      "epoch": 0.66,
      "step": 296,
      "total_flos": 495601644994560.0,
      "train_loss": 0.9806337251856521,
      "train_runtime": 6774.4676,
      "train_samples_per_second": 33.668,
      "train_steps_per_second": 0.066
    }
  ],
  "logging_steps": 5,
  "max_steps": 445,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 495601644994560.0,
  "trial_name": null,
  "trial_params": null
}