{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.4,
  "eval_steps": 500,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 7.714407444000244,
      "learning_rate": 1.885714285714286e-05,
      "loss": 9.6987,
      "step": 2
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 8.402449607849121,
      "learning_rate": 1.7714285714285717e-05,
      "loss": 9.6675,
      "step": 4
    },
    {
      "epoch": 0.8,
      "grad_norm": 8.54103946685791,
      "learning_rate": 1.6571428571428574e-05,
      "loss": 9.6521,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": NaN,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 7.1927,
      "step": 8
    },
    {
      "epoch": 1.2666666666666666,
      "grad_norm": 8.744111061096191,
      "learning_rate": 1.4857142857142858e-05,
      "loss": 9.599,
      "step": 10
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 9.355561256408691,
      "learning_rate": 1.3714285714285716e-05,
      "loss": 9.5552,
      "step": 12
    },
    {
      "epoch": 1.8,
      "grad_norm": 10.12316608428955,
      "learning_rate": 1.2571428571428572e-05,
      "loss": 9.4807,
      "step": 14
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.6569437980651855,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 7.134,
      "step": 16
    },
    {
      "epoch": 2.2666666666666666,
      "grad_norm": 10.050814628601074,
      "learning_rate": 1.0285714285714285e-05,
      "loss": 9.4691,
      "step": 18
    },
    {
      "epoch": 2.533333333333333,
      "grad_norm": 10.766989707946777,
      "learning_rate": 9.142857142857144e-06,
      "loss": 9.4027,
      "step": 20
    },
    {
      "epoch": 2.8,
      "grad_norm": 11.306514739990234,
      "learning_rate": 8.000000000000001e-06,
      "loss": 9.4043,
      "step": 22
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.406909942626953,
      "learning_rate": 6.857142857142858e-06,
      "loss": 6.9995,
      "step": 24
    },
    {
      "epoch": 3.2666666666666666,
      "grad_norm": 12.331953048706055,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 9.3525,
      "step": 26
    },
    {
      "epoch": 3.533333333333333,
      "grad_norm": 11.795371055603027,
      "learning_rate": 4.571428571428572e-06,
      "loss": 9.3326,
      "step": 28
    },
    {
      "epoch": 3.8,
      "grad_norm": 12.696221351623535,
      "learning_rate": 3.428571428571429e-06,
      "loss": 9.3262,
      "step": 30
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.24462890625,
      "learning_rate": 2.285714285714286e-06,
      "loss": 6.9159,
      "step": 32
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 12.694133758544922,
      "learning_rate": 1.142857142857143e-06,
      "loss": 9.286,
      "step": 34
    },
    {
      "epoch": 4.4,
      "step": 35,
      "total_flos": 135900533909640.0,
      "train_loss": 8.918893187386649,
      "train_runtime": 949.0763,
      "train_samples_per_second": 0.632,
      "train_steps_per_second": 0.037
    }
  ],
  "logging_steps": 2,
  "max_steps": 35,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 135900533909640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}