{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 10075,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 9.8014888337469e-06,
      "loss": 0.2058,
      "step": 200
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.602977667493797e-06,
      "loss": 0.1586,
      "step": 400
    },
    {
      "epoch": 0.3,
      "learning_rate": 9.404466501240696e-06,
      "loss": 0.1283,
      "step": 600
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.205955334987593e-06,
      "loss": 0.1288,
      "step": 800
    },
    {
      "epoch": 0.5,
      "learning_rate": 9.007444168734492e-06,
      "loss": 0.1259,
      "step": 1000
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.80893300248139e-06,
      "loss": 0.1196,
      "step": 1200
    },
    {
      "epoch": 0.69,
      "learning_rate": 8.610421836228289e-06,
      "loss": 0.125,
      "step": 1400
    },
    {
      "epoch": 0.79,
      "learning_rate": 8.411910669975186e-06,
      "loss": 0.1152,
      "step": 1600
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.213399503722085e-06,
      "loss": 0.1141,
      "step": 1800
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.014888337468984e-06,
      "loss": 0.1088,
      "step": 2000
    },
    {
      "epoch": 1.09,
      "learning_rate": 7.816377171215881e-06,
      "loss": 0.0938,
      "step": 2200
    },
    {
      "epoch": 1.19,
      "learning_rate": 7.6178660049627794e-06,
      "loss": 0.0882,
      "step": 2400
    },
    {
      "epoch": 1.29,
      "learning_rate": 7.4193548387096784e-06,
      "loss": 0.0908,
      "step": 2600
    },
    {
      "epoch": 1.39,
      "learning_rate": 7.220843672456577e-06,
      "loss": 0.0982,
      "step": 2800
    },
    {
      "epoch": 1.49,
      "learning_rate": 7.022332506203474e-06,
      "loss": 0.0938,
      "step": 3000
    },
    {
      "epoch": 1.59,
      "learning_rate": 6.823821339950373e-06,
      "loss": 0.0997,
      "step": 3200
    },
    {
      "epoch": 1.69,
      "learning_rate": 6.625310173697271e-06,
      "loss": 0.0903,
      "step": 3400
    },
    {
      "epoch": 1.79,
      "learning_rate": 6.426799007444169e-06,
      "loss": 0.1015,
      "step": 3600
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.228287841191067e-06,
      "loss": 0.0719,
      "step": 3800
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.029776674937966e-06,
      "loss": 0.0874,
      "step": 4000
    },
    {
      "epoch": 2.08,
      "learning_rate": 5.831265508684864e-06,
      "loss": 0.0783,
      "step": 4200
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.632754342431762e-06,
      "loss": 0.0737,
      "step": 4400
    },
    {
      "epoch": 2.28,
      "learning_rate": 5.434243176178661e-06,
      "loss": 0.0657,
      "step": 4600
    },
    {
      "epoch": 2.38,
      "learning_rate": 5.235732009925558e-06,
      "loss": 0.0754,
      "step": 4800
    },
    {
      "epoch": 2.48,
      "learning_rate": 5.037220843672457e-06,
      "loss": 0.0734,
      "step": 5000
    },
    {
      "epoch": 2.58,
      "learning_rate": 4.838709677419355e-06,
      "loss": 0.081,
      "step": 5200
    },
    {
      "epoch": 2.68,
      "learning_rate": 4.640198511166253e-06,
      "loss": 0.0701,
      "step": 5400
    },
    {
      "epoch": 2.78,
      "learning_rate": 4.4416873449131515e-06,
      "loss": 0.0781,
      "step": 5600
    },
    {
      "epoch": 2.88,
      "learning_rate": 4.24317617866005e-06,
      "loss": 0.074,
      "step": 5800
    },
    {
      "epoch": 2.98,
      "learning_rate": 4.044665012406948e-06,
      "loss": 0.0722,
      "step": 6000
    },
    {
      "epoch": 3.08,
      "learning_rate": 3.846153846153847e-06,
      "loss": 0.0551,
      "step": 6200
    },
    {
      "epoch": 3.18,
      "learning_rate": 3.6476426799007445e-06,
      "loss": 0.0526,
      "step": 6400
    },
    {
      "epoch": 3.28,
      "learning_rate": 3.4491315136476427e-06,
      "loss": 0.0645,
      "step": 6600
    },
    {
      "epoch": 3.37,
      "learning_rate": 3.2506203473945412e-06,
      "loss": 0.064,
      "step": 6800
    },
    {
      "epoch": 3.47,
      "learning_rate": 3.0521091811414394e-06,
      "loss": 0.0569,
      "step": 7000
    },
    {
      "epoch": 3.57,
      "learning_rate": 2.8535980148883375e-06,
      "loss": 0.066,
      "step": 7200
    },
    {
      "epoch": 3.67,
      "learning_rate": 2.655086848635236e-06,
      "loss": 0.0616,
      "step": 7400
    },
    {
      "epoch": 3.77,
      "learning_rate": 2.4565756823821343e-06,
      "loss": 0.0622,
      "step": 7600
    },
    {
      "epoch": 3.87,
      "learning_rate": 2.2580645161290324e-06,
      "loss": 0.0561,
      "step": 7800
    },
    {
      "epoch": 3.97,
      "learning_rate": 2.0595533498759305e-06,
      "loss": 0.0544,
      "step": 8000
    },
    {
      "epoch": 4.07,
      "learning_rate": 1.861042183622829e-06,
      "loss": 0.0541,
      "step": 8200
    },
    {
      "epoch": 4.17,
      "learning_rate": 1.662531017369727e-06,
      "loss": 0.0532,
      "step": 8400
    },
    {
      "epoch": 4.27,
      "learning_rate": 1.4640198511166254e-06,
      "loss": 0.046,
      "step": 8600
    },
    {
      "epoch": 4.37,
      "learning_rate": 1.2655086848635238e-06,
      "loss": 0.0522,
      "step": 8800
    },
    {
      "epoch": 4.47,
      "learning_rate": 1.066997518610422e-06,
      "loss": 0.0575,
      "step": 9000
    },
    {
      "epoch": 4.57,
      "learning_rate": 8.684863523573202e-07,
      "loss": 0.0534,
      "step": 9200
    },
    {
      "epoch": 4.67,
      "learning_rate": 6.699751861042183e-07,
      "loss": 0.0466,
      "step": 9400
    },
    {
      "epoch": 4.76,
      "learning_rate": 4.714640198511167e-07,
      "loss": 0.0485,
      "step": 9600
    },
    {
      "epoch": 4.86,
      "learning_rate": 2.7295285359801494e-07,
      "loss": 0.0624,
      "step": 9800
    },
    {
      "epoch": 4.96,
      "learning_rate": 7.444168734491315e-08,
      "loss": 0.0436,
      "step": 10000
    },
    {
      "epoch": 5.0,
      "step": 10075,
      "total_flos": 66843438723916800,
      "train_runtime": 8275.4395,
      "train_samples_per_second": 1.217
    }
  ],
  "max_steps": 10075,
  "num_train_epochs": 5,
  "total_flos": 66843438723916800,
  "trial_name": null,
  "trial_params": null
}