{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7621196070511306,
  "global_step": 12500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.9951222486433756e-05,
      "loss": 0.0754,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.990244497286751e-05,
      "loss": 0.0747,
      "step": 400
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9853667459301263e-05,
      "loss": 0.0737,
      "step": 600
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9804889945735017e-05,
      "loss": 0.073,
      "step": 800
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.975611243216877e-05,
      "loss": 0.0723,
      "step": 1000
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9707334918602525e-05,
      "loss": 0.072,
      "step": 1200
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.965855740503628e-05,
      "loss": 0.0709,
      "step": 1400
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9609779891470033e-05,
      "loss": 0.0703,
      "step": 1600
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9561002377903787e-05,
      "loss": 0.0708,
      "step": 1800
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.951222486433754e-05,
      "loss": 0.0711,
      "step": 2000
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9463447350771295e-05,
      "loss": 0.0699,
      "step": 2200
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.941466983720505e-05,
      "loss": 0.0701,
      "step": 2400
    },
    {
      "epoch": 0.15,
      "eval_loss": 0.055753033608198166,
      "eval_runtime": 1008.1775,
      "eval_samples_per_second": 82.199,
      "eval_steps_per_second": 13.7,
      "step": 2500
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9365892323638806e-05,
      "loss": 0.071,
      "step": 2600
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.931711481007256e-05,
      "loss": 0.0692,
      "step": 2800
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9268337296506314e-05,
      "loss": 0.0687,
      "step": 3000
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9219559782940067e-05,
      "loss": 0.0689,
      "step": 3200
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.917078226937382e-05,
      "loss": 0.0681,
      "step": 3400
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9122004755807575e-05,
      "loss": 0.0678,
      "step": 3600
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.907322724224133e-05,
      "loss": 0.0666,
      "step": 3800
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.9024449728675083e-05,
      "loss": 0.0676,
      "step": 4000
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.8975672215108837e-05,
      "loss": 0.0662,
      "step": 4200
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.892689470154259e-05,
      "loss": 0.0676,
      "step": 4400
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.8878117187976345e-05,
      "loss": 0.0663,
      "step": 4600
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.88293396744101e-05,
      "loss": 0.0661,
      "step": 4800
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.8780562160843853e-05,
      "loss": 0.0661,
      "step": 5000
    },
    {
      "epoch": 0.3,
      "eval_loss": 0.05344025790691376,
      "eval_runtime": 1009.8843,
      "eval_samples_per_second": 82.06,
      "eval_steps_per_second": 13.677,
      "step": 5000
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.8731784647277606e-05,
      "loss": 0.0674,
      "step": 5200
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.868300713371136e-05,
      "loss": 0.066,
      "step": 5400
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.8634229620145114e-05,
      "loss": 0.0642,
      "step": 5600
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.8585452106578868e-05,
      "loss": 0.0655,
      "step": 5800
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.8536674593012622e-05,
      "loss": 0.0654,
      "step": 6000
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.8487897079446376e-05,
      "loss": 0.0641,
      "step": 6200
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.843911956588013e-05,
      "loss": 0.0636,
      "step": 6400
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.8390342052313884e-05,
      "loss": 0.0658,
      "step": 6600
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.8341564538747638e-05,
      "loss": 0.0639,
      "step": 6800
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.8292787025181395e-05,
      "loss": 0.0642,
      "step": 7000
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.8244009511615145e-05,
      "loss": 0.0648,
      "step": 7200
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.8195231998048903e-05,
      "loss": 0.0645,
      "step": 7400
    },
    {
      "epoch": 0.46,
      "eval_loss": 0.05153830349445343,
      "eval_runtime": 1007.6883,
      "eval_samples_per_second": 82.239,
      "eval_steps_per_second": 13.707,
      "step": 7500
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.8146454484482653e-05,
      "loss": 0.0639,
      "step": 7600
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.809767697091641e-05,
      "loss": 0.0628,
      "step": 7800
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.8048899457350164e-05,
      "loss": 0.0647,
      "step": 8000
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.800012194378392e-05,
      "loss": 0.0629,
      "step": 8200
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.7951344430217672e-05,
      "loss": 0.0638,
      "step": 8400
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.7902566916651426e-05,
      "loss": 0.0635,
      "step": 8600
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.785378940308518e-05,
      "loss": 0.0628,
      "step": 8800
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.7805011889518934e-05,
      "loss": 0.063,
      "step": 9000
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.7756234375952688e-05,
      "loss": 0.0636,
      "step": 9200
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.7707456862386442e-05,
      "loss": 0.0633,
      "step": 9400
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.7658679348820196e-05,
      "loss": 0.0624,
      "step": 9600
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.760990183525395e-05,
      "loss": 0.0615,
      "step": 9800
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.7561124321687703e-05,
      "loss": 0.062,
      "step": 10000
    },
    {
      "epoch": 0.61,
      "eval_loss": 0.05109347030520439,
      "eval_runtime": 1005.611,
      "eval_samples_per_second": 82.409,
      "eval_steps_per_second": 13.735,
      "step": 10000
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.7512346808121457e-05,
      "loss": 0.0616,
      "step": 10200
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.746356929455521e-05,
      "loss": 0.0613,
      "step": 10400
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.7414791780988965e-05,
      "loss": 0.0616,
      "step": 10600
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.736601426742272e-05,
      "loss": 0.0623,
      "step": 10800
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.7317236753856473e-05,
      "loss": 0.062,
      "step": 11000
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.7268459240290227e-05,
      "loss": 0.0632,
      "step": 11200
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.7219681726723984e-05,
      "loss": 0.0623,
      "step": 11400
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.7170904213157735e-05,
      "loss": 0.0608,
      "step": 11600
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.7122126699591492e-05,
      "loss": 0.061,
      "step": 11800
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.7073349186025242e-05,
      "loss": 0.061,
      "step": 12000
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.7024571672459e-05,
      "loss": 0.0605,
      "step": 12200
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.697579415889275e-05,
      "loss": 0.0607,
      "step": 12400
    },
    {
      "epoch": 0.76,
      "eval_loss": 0.04968786612153053,
      "eval_runtime": 1006.7134,
      "eval_samples_per_second": 82.318,
      "eval_steps_per_second": 13.72,
      "step": 12500
    }
  ],
  "max_steps": 82005,
  "num_train_epochs": 5,
  "total_flos": 6.34499629056e+17,
  "trial_name": null,
  "trial_params": null
}