{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 16,
  "global_step": 64,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015625,
      "grad_norm": 0.1416465789079666,
      "learning_rate": 0.0005,
      "loss": 0.6936,
      "step": 1
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.48029133677482605,
      "learning_rate": 0.0005,
      "loss": 0.6521,
      "step": 16
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.5866118669509888,
      "eval_runtime": 211.247,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 16
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.26290011405944824,
      "learning_rate": 0.0005,
      "loss": 0.5821,
      "step": 32
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.5616697072982788,
      "eval_runtime": 211.0712,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 32
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.2908053696155548,
      "learning_rate": 0.0005,
      "loss": 0.6006,
      "step": 48
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.5537130236625671,
      "eval_runtime": 211.1601,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 48
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2542905807495117,
      "learning_rate": 0.0005,
      "loss": 0.5708,
      "step": 64
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5481152534484863,
      "eval_runtime": 211.1765,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 64
    }
  ],
  "logging_steps": 16,
  "max_steps": 192,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 16,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.006530176855081e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}