{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0031526403362816357,
  "eval_steps": 9,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003502933706979595,
      "eval_loss": 1.2642643451690674,
      "eval_runtime": 170.7468,
      "eval_samples_per_second": 28.159,
      "eval_steps_per_second": 3.52,
      "step": 1
    },
    {
      "epoch": 0.0010508801120938786,
      "grad_norm": 0.26421603560447693,
      "learning_rate": 3e-05,
      "loss": 1.2586,
      "step": 3
    },
    {
      "epoch": 0.002101760224187757,
      "grad_norm": 0.2573237419128418,
      "learning_rate": 6e-05,
      "loss": 1.2507,
      "step": 6
    },
    {
      "epoch": 0.0031526403362816357,
      "grad_norm": 0.23207610845565796,
      "learning_rate": 9e-05,
      "loss": 1.2601,
      "step": 9
    },
    {
      "epoch": 0.0031526403362816357,
      "eval_loss": 1.229485034942627,
      "eval_runtime": 172.5126,
      "eval_samples_per_second": 27.87,
      "eval_steps_per_second": 3.484,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3705727579324416.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}