{
  "best_metric": 0.8793088793754578,
  "best_model_checkpoint": "models/checkpoints/checkpoint-5500",
  "epoch": 0.4509582863585118,
  "global_step": 5500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.998360118071499e-05,
      "loss": 1.518,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9967202361429978e-05,
      "loss": 1.2325,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9950803542144966e-05,
      "loss": 1.1664,
      "step": 300
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9934404722859955e-05,
      "loss": 1.1746,
      "step": 400
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9918005903574943e-05,
      "loss": 1.1251,
      "step": 500
    },
    {
      "epoch": 0.04,
      "eval_loss": 0.964438259601593,
      "eval_runtime": 267.7236,
      "eval_samples_per_second": 255.906,
      "eval_steps_per_second": 15.994,
      "step": 500
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9901607084289934e-05,
      "loss": 1.1041,
      "step": 600
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.988520826500492e-05,
      "loss": 1.0817,
      "step": 700
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.986880944571991e-05,
      "loss": 1.0594,
      "step": 800
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.98524106264349e-05,
      "loss": 1.0642,
      "step": 900
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9836011807149887e-05,
      "loss": 1.0453,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "eval_loss": 0.9285051226615906,
      "eval_runtime": 253.7626,
      "eval_samples_per_second": 269.985,
      "eval_steps_per_second": 16.874,
      "step": 1000
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9819612987864875e-05,
      "loss": 1.0486,
      "step": 1100
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9803214168579864e-05,
      "loss": 1.0549,
      "step": 1200
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9786815349294852e-05,
      "loss": 1.0639,
      "step": 1300
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.977041653000984e-05,
      "loss": 1.0354,
      "step": 1400
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9754017710724828e-05,
      "loss": 1.0393,
      "step": 1500
    },
    {
      "epoch": 0.12,
      "eval_loss": 0.9202534556388855,
      "eval_runtime": 264.8239,
      "eval_samples_per_second": 258.708,
      "eval_steps_per_second": 16.169,
      "step": 1500
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9737618891439817e-05,
      "loss": 1.0381,
      "step": 1600
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9721220072154808e-05,
      "loss": 1.0672,
      "step": 1700
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9704821252869793e-05,
      "loss": 1.0335,
      "step": 1800
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9688422433584785e-05,
      "loss": 1.0239,
      "step": 1900
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9672023614299773e-05,
      "loss": 1.0012,
      "step": 2000
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.9098692536354065,
      "eval_runtime": 264.5198,
      "eval_samples_per_second": 259.005,
      "eval_steps_per_second": 16.188,
      "step": 2000
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.965562479501476e-05,
      "loss": 1.0146,
      "step": 2100
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.963922597572975e-05,
      "loss": 1.0502,
      "step": 2200
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9622827156444737e-05,
      "loss": 1.0062,
      "step": 2300
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9606428337159726e-05,
      "loss": 1.0144,
      "step": 2400
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9590029517874714e-05,
      "loss": 0.9826,
      "step": 2500
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.9166184067726135,
      "eval_runtime": 256.5893,
      "eval_samples_per_second": 267.01,
      "eval_steps_per_second": 16.688,
      "step": 2500
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9573630698589702e-05,
      "loss": 1.0269,
      "step": 2600
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9557231879304694e-05,
      "loss": 0.9898,
      "step": 2700
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.954083306001968e-05,
      "loss": 1.0248,
      "step": 2800
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.952443424073467e-05,
      "loss": 0.9996,
      "step": 2900
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.950803542144966e-05,
      "loss": 0.9595,
      "step": 3000
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.9191610217094421,
      "eval_runtime": 272.1388,
      "eval_samples_per_second": 251.754,
      "eval_steps_per_second": 15.735,
      "step": 3000
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.9491636602164647e-05,
      "loss": 0.9873,
      "step": 3100
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.9475237782879635e-05,
      "loss": 0.9667,
      "step": 3200
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.9458838963594623e-05,
      "loss": 0.9666,
      "step": 3300
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.944244014430961e-05,
      "loss": 1.0102,
      "step": 3400
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.94260413250246e-05,
      "loss": 0.9511,
      "step": 3500
    },
    {
      "epoch": 0.29,
      "eval_loss": 0.9013209342956543,
      "eval_runtime": 267.0529,
      "eval_samples_per_second": 256.548,
      "eval_steps_per_second": 16.034,
      "step": 3500
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.9409642505739588e-05,
      "loss": 0.9927,
      "step": 3600
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.9393243686454576e-05,
      "loss": 0.9507,
      "step": 3700
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.9376844867169567e-05,
      "loss": 1.0049,
      "step": 3800
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9360446047884552e-05,
      "loss": 0.9385,
      "step": 3900
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.9344047228599544e-05,
      "loss": 0.9644,
      "step": 4000
    },
    {
      "epoch": 0.33,
      "eval_loss": 0.8957135081291199,
      "eval_runtime": 260.7988,
      "eval_samples_per_second": 262.701,
      "eval_steps_per_second": 16.419,
      "step": 4000
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.932764840931453e-05,
      "loss": 0.9293,
      "step": 4100
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.931124959002952e-05,
      "loss": 0.9298,
      "step": 4200
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.929485077074451e-05,
      "loss": 0.9218,
      "step": 4300
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.9278451951459497e-05,
      "loss": 0.9523,
      "step": 4400
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.9262053132174485e-05,
      "loss": 0.9079,
      "step": 4500
    },
    {
      "epoch": 0.37,
      "eval_loss": 0.9050074815750122,
      "eval_runtime": 264.4439,
      "eval_samples_per_second": 259.079,
      "eval_steps_per_second": 16.192,
      "step": 4500
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.9245654312889473e-05,
      "loss": 0.9437,
      "step": 4600
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.922925549360446e-05,
      "loss": 0.9395,
      "step": 4700
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.921285667431945e-05,
      "loss": 0.969,
      "step": 4800
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.9196457855034438e-05,
      "loss": 0.926,
      "step": 4900
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.9180059035749426e-05,
      "loss": 0.9178,
      "step": 5000
    },
    {
      "epoch": 0.41,
      "eval_loss": 0.8956226706504822,
      "eval_runtime": 259.9134,
      "eval_samples_per_second": 263.595,
      "eval_steps_per_second": 16.475,
      "step": 5000
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.9163660216464418e-05,
      "loss": 0.9697,
      "step": 5100
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.9147261397179403e-05,
      "loss": 0.9448,
      "step": 5200
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.9130862577894394e-05,
      "loss": 0.9118,
      "step": 5300
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.911446375860938e-05,
      "loss": 0.9321,
      "step": 5400
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.909806493932437e-05,
      "loss": 0.9289,
      "step": 5500
    },
    {
      "epoch": 0.45,
      "eval_loss": 0.8793088793754578,
      "eval_runtime": 261.4397,
      "eval_samples_per_second": 262.057,
      "eval_steps_per_second": 16.379,
      "step": 5500
    }
  ],
  "max_steps": 121960,
  "num_train_epochs": 10,
  "total_flos": 1.922426903232e+16,
  "trial_name": null,
  "trial_params": null
}