{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.99996915764479e-05,
      "loss": 1.368,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9992290362407232e-05,
      "loss": 1.1997,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9969173337331283e-05,
      "loss": 1.0339,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9930684569549265e-05,
      "loss": 0.9737,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.9399,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9807852804032306e-05,
      "loss": 0.933,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9723699203976768e-05,
      "loss": 0.9181,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9624552364536472e-05,
      "loss": 0.9096,
      "step": 35
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 0.8823,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9381913359224844e-05,
      "loss": 0.888,
      "step": 45
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9238795325112867e-05,
      "loss": 0.8575,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9081431738250815e-05,
      "loss": 0.8679,
      "step": 55
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.891006524188368e-05,
      "loss": 0.8467,
      "step": 60
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.8724960070727974e-05,
      "loss": 0.8434,
      "step": 65
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.8526401643540924e-05,
      "loss": 0.8404,
      "step": 70
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8314696123025456e-05,
      "loss": 0.851,
      "step": 75
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.8396,
      "step": 80
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.785316930880745e-05,
      "loss": 0.8462,
      "step": 85
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.7604059656000313e-05,
      "loss": 0.8479,
      "step": 90
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.7343225094356857e-05,
      "loss": 0.8365,
      "step": 95
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.8365,
      "step": 100
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.678800745532942e-05,
      "loss": 0.8283,
      "step": 105
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.6494480483301836e-05,
      "loss": 0.8397,
      "step": 110
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.6190939493098344e-05,
      "loss": 0.8408,
      "step": 115
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 0.8218,
      "step": 120
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.5555702330196024e-05,
      "loss": 0.8356,
      "step": 125
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.5224985647159489e-05,
      "loss": 0.8269,
      "step": 130
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.4886212414969551e-05,
      "loss": 0.8224,
      "step": 135
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.4539904997395468e-05,
      "loss": 0.8298,
      "step": 140
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.4186597375374283e-05,
      "loss": 0.8024,
      "step": 145
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.3826834323650899e-05,
      "loss": 0.8115,
      "step": 150
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.346117057077493e-05,
      "loss": 0.8059,
      "step": 155
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.7906,
      "step": 160
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.2714404498650743e-05,
      "loss": 0.8069,
      "step": 165
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.2334453638559057e-05,
      "loss": 0.7828,
      "step": 170
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.1950903220161286e-05,
      "loss": 0.79,
      "step": 175
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.156434465040231e-05,
      "loss": 0.7954,
      "step": 180
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.1175373974578378e-05,
      "loss": 0.7833,
      "step": 185
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.0784590957278452e-05,
      "loss": 0.771,
      "step": 190
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.0392598157590687e-05,
      "loss": 0.7702,
      "step": 195
    },
    {
      "epoch": 0.5,
      "learning_rate": 1e-05,
      "loss": 0.7792,
      "step": 200
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.607401842409318e-06,
      "loss": 0.7861,
      "step": 205
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.215409042721553e-06,
      "loss": 0.7621,
      "step": 210
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.824626025421625e-06,
      "loss": 0.7768,
      "step": 215
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.7575,
      "step": 220
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.04909677983872e-06,
      "loss": 0.7477,
      "step": 225
    },
    {
      "epoch": 0.57,
      "learning_rate": 7.66554636144095e-06,
      "loss": 0.7277,
      "step": 230
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.285595501349259e-06,
      "loss": 0.7633,
      "step": 235
    },
    {
      "epoch": 0.6,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.759,
      "step": 240
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.538829429225068e-06,
      "loss": 0.7644,
      "step": 245
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.173165676349103e-06,
      "loss": 0.744,
      "step": 250
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.813402624625722e-06,
      "loss": 0.742,
      "step": 255
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.460095002604533e-06,
      "loss": 0.7572,
      "step": 260
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.1137875850304545e-06,
      "loss": 0.7407,
      "step": 265
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.775014352840512e-06,
      "loss": 0.7378,
      "step": 270
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.444297669803981e-06,
      "loss": 0.7304,
      "step": 275
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.12214747707527e-06,
      "loss": 0.7462,
      "step": 280
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.8090605069016596e-06,
      "loss": 0.7434,
      "step": 285
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.505519516698165e-06,
      "loss": 0.7265,
      "step": 290
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.2119925446705824e-06,
      "loss": 0.7432,
      "step": 295
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.7197,
      "step": 300
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.656774905643147e-06,
      "loss": 0.7392,
      "step": 305
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.395940343999691e-06,
      "loss": 0.7138,
      "step": 310
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.146830691192553e-06,
      "loss": 0.7254,
      "step": 315
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.7074,
      "step": 320
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.6853038769745466e-06,
      "loss": 0.7039,
      "step": 325
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.4735983564590784e-06,
      "loss": 0.7183,
      "step": 330
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2750399292720284e-06,
      "loss": 0.7269,
      "step": 335
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0899347581163222e-06,
      "loss": 0.7189,
      "step": 340
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.185682617491865e-07,
      "loss": 0.7143,
      "step": 345
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.612046748871327e-07,
      "loss": 0.7252,
      "step": 350
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.180866407751595e-07,
      "loss": 0.731,
      "step": 355
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.894348370484648e-07,
      "loss": 0.7176,
      "step": 360
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.7544763546352834e-07,
      "loss": 0.7065,
      "step": 365
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.7630079602323447e-07,
      "loss": 0.7266,
      "step": 370
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.921471959676957e-07,
      "loss": 0.7114,
      "step": 375
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.231165940486234e-07,
      "loss": 0.7215,
      "step": 380
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.931543045073708e-08,
      "loss": 0.711,
      "step": 385
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.082666266872036e-08,
      "loss": 0.7085,
      "step": 390
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.70963759277099e-09,
      "loss": 0.7138,
      "step": 395
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.7079,
      "step": 400
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7119931578636169,
      "eval_runtime": 76.9498,
      "eval_samples_per_second": 34.828,
      "eval_steps_per_second": 0.273,
      "step": 400
    },
    {
      "epoch": 1.0,
      "step": 400,
      "total_flos": 167294344888320.0,
      "train_loss": 0.7935602605342865,
      "train_runtime": 5982.8053,
      "train_samples_per_second": 8.555,
      "train_steps_per_second": 0.067
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 167294344888320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}