{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.6923076923076925,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.2146074771881104,
      "learning_rate": 0.0001666666666666667,
      "loss": 9.3921,
      "step": 2
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.9942620992660522,
      "learning_rate": 0.00013333333333333334,
      "loss": 9.0382,
      "step": 4
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 1.729811668395996,
      "learning_rate": 0.0001,
      "loss": 8.4753,
      "step": 6
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 1.7566454410552979,
      "learning_rate": 6.666666666666667e-05,
      "loss": 8.2058,
      "step": 8
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 1.8725519180297852,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 7.8646,
      "step": 10
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 1.8882712125778198,
      "learning_rate": 0.0,
      "loss": 7.7254,
      "step": 12
    },
    {
      "epoch": 3.6923076923076925,
      "step": 12,
      "total_flos": 56004693172008.0,
      "train_loss": 8.450230757395426,
      "train_runtime": 328.8828,
      "train_samples_per_second": 0.632,
      "train_steps_per_second": 0.036
    }
  ],
  "logging_steps": 2,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 56004693172008.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}