{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4444444444444444,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 29.641796112060547,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.3387,
      "step": 10
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 2.8391942977905273,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.4468,
      "step": 20
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.4493441581726074,
      "learning_rate": 8.823529411764706e-05,
      "loss": 1.0612,
      "step": 30
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.3891420364379883,
      "learning_rate": 9.990263847374976e-05,
      "loss": 1.0064,
      "step": 40
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.1571154594421387,
      "learning_rate": 9.930902394260747e-05,
      "loss": 0.9215,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 336,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1613964862992384.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}