{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.571428571428571,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.242490291595459,
      "learning_rate": 0.0001666666666666667,
      "loss": 9.5544,
      "step": 2
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 1.746873140335083,
      "learning_rate": 0.00013333333333333334,
      "loss": 9.1466,
      "step": 4
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 2.033708095550537,
      "learning_rate": 0.0001,
      "loss": 8.6245,
      "step": 6
    },
    {
      "epoch": 3.0476190476190474,
      "grad_norm": 2.265815019607544,
      "learning_rate": 6.666666666666667e-05,
      "loss": 8.2153,
      "step": 8
    },
    {
      "epoch": 3.8095238095238093,
      "grad_norm": 1.9789308309555054,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 7.9501,
      "step": 10
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 1.8743971586227417,
      "learning_rate": 0.0,
      "loss": 7.7696,
      "step": 12
    },
    {
      "epoch": 4.571428571428571,
      "step": 12,
      "total_flos": 47689908636408.0,
      "train_loss": 8.543412923812866,
      "train_runtime": 168.1021,
      "train_samples_per_second": 1.463,
      "train_steps_per_second": 0.071
    }
  ],
  "logging_steps": 2,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 47689908636408.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}