{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9141551206970433,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 2.2499999999999998e-05,
      "loss": 5.1881,
      "step": 50
    },
    {
      "epoch": 0.06,
      "eval_loss": 5.518892288208008,
      "eval_runtime": 281.7614,
      "eval_samples_per_second": 16.539,
      "eval_steps_per_second": 16.539,
      "step": 50
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.75e-05,
      "loss": 3.8191,
      "step": 100
    },
    {
      "epoch": 0.11,
      "eval_loss": 2.910094738006592,
      "eval_runtime": 282.3915,
      "eval_samples_per_second": 16.502,
      "eval_steps_per_second": 16.502,
      "step": 100
    },
    {
      "epoch": 0.17,
      "learning_rate": 7.25e-05,
      "loss": 2.5718,
      "step": 150
    },
    {
      "epoch": 0.17,
      "eval_loss": 2.240684986114502,
      "eval_runtime": 283.3137,
      "eval_samples_per_second": 16.448,
      "eval_steps_per_second": 16.448,
      "step": 150
    },
    {
      "epoch": 0.23,
      "learning_rate": 9.750000000000001e-05,
      "loss": 2.3477,
      "step": 200
    },
    {
      "epoch": 0.23,
      "eval_loss": 2.1633121967315674,
      "eval_runtime": 282.161,
      "eval_samples_per_second": 16.515,
      "eval_steps_per_second": 16.515,
      "step": 200
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001225,
      "loss": 2.3472,
      "step": 250
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.118901252746582,
      "eval_runtime": 281.7032,
      "eval_samples_per_second": 16.542,
      "eval_steps_per_second": 16.542,
      "step": 250
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001475,
      "loss": 2.2188,
      "step": 300
    },
    {
      "epoch": 0.34,
      "eval_loss": 2.1062021255493164,
      "eval_runtime": 282.3706,
      "eval_samples_per_second": 16.503,
      "eval_steps_per_second": 16.503,
      "step": 300
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001725,
      "loss": 2.2085,
      "step": 350
    },
    {
      "epoch": 0.4,
      "eval_loss": 2.0873425006866455,
      "eval_runtime": 282.0216,
      "eval_samples_per_second": 16.524,
      "eval_steps_per_second": 16.524,
      "step": 350
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001975,
      "loss": 2.1271,
      "step": 400
    },
    {
      "epoch": 0.46,
      "eval_loss": 2.0874459743499756,
      "eval_runtime": 283.0992,
      "eval_samples_per_second": 16.461,
      "eval_steps_per_second": 16.461,
      "step": 400
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00022250000000000001,
      "loss": 2.1834,
      "step": 450
    },
    {
      "epoch": 0.51,
      "eval_loss": 2.0584352016448975,
      "eval_runtime": 281.7518,
      "eval_samples_per_second": 16.539,
      "eval_steps_per_second": 16.539,
      "step": 450
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002475,
      "loss": 2.1927,
      "step": 500
    },
    {
      "epoch": 0.57,
      "eval_loss": 2.050870656967163,
      "eval_runtime": 281.7194,
      "eval_samples_per_second": 16.541,
      "eval_steps_per_second": 16.541,
      "step": 500
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002725,
      "loss": 2.1816,
      "step": 550
    },
    {
      "epoch": 0.63,
      "eval_loss": 2.039118766784668,
      "eval_runtime": 282.0613,
      "eval_samples_per_second": 16.521,
      "eval_steps_per_second": 16.521,
      "step": 550
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00029749999999999997,
      "loss": 2.2131,
      "step": 600
    },
    {
      "epoch": 0.69,
      "eval_loss": 2.0333147048950195,
      "eval_runtime": 282.4675,
      "eval_samples_per_second": 16.497,
      "eval_steps_per_second": 16.497,
      "step": 600
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00032250000000000003,
      "loss": 2.2322,
      "step": 650
    },
    {
      "epoch": 0.74,
      "eval_loss": 2.0386910438537598,
      "eval_runtime": 282.3106,
      "eval_samples_per_second": 16.507,
      "eval_steps_per_second": 16.507,
      "step": 650
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003475,
      "loss": 2.2614,
      "step": 700
    },
    {
      "epoch": 0.8,
      "eval_loss": 2.025144577026367,
      "eval_runtime": 285.8974,
      "eval_samples_per_second": 16.3,
      "eval_steps_per_second": 16.3,
      "step": 700
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003725,
      "loss": 2.186,
      "step": 750
    },
    {
      "epoch": 0.86,
      "eval_loss": 2.0244803428649902,
      "eval_runtime": 284.3127,
      "eval_samples_per_second": 16.39,
      "eval_steps_per_second": 16.39,
      "step": 750
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003975,
      "loss": 2.1677,
      "step": 800
    },
    {
      "epoch": 0.91,
      "eval_loss": 2.0197227001190186,
      "eval_runtime": 284.0212,
      "eval_samples_per_second": 16.407,
      "eval_steps_per_second": 16.407,
      "step": 800
    }
  ],
  "max_steps": 875,
  "num_train_epochs": 1,
  "total_flos": 4.324339205829427e+16,
  "trial_name": null,
  "trial_params": null
}