{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.020930232558139535,
  "eval_steps": 9,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002325581395348837,
      "eval_loss": 5.767578601837158,
      "eval_runtime": 10.4189,
      "eval_samples_per_second": 69.489,
      "eval_steps_per_second": 8.734,
      "step": 1
    },
    {
      "epoch": 0.0069767441860465115,
      "grad_norm": 0.7177151441574097,
      "learning_rate": 3e-05,
      "loss": 5.7725,
      "step": 3
    },
    {
      "epoch": 0.013953488372093023,
      "grad_norm": 0.6705913543701172,
      "learning_rate": 6e-05,
      "loss": 5.6508,
      "step": 6
    },
    {
      "epoch": 0.020930232558139535,
      "grad_norm": 0.9152357578277588,
      "learning_rate": 9e-05,
      "loss": 5.7661,
      "step": 9
    },
    {
      "epoch": 0.020930232558139535,
      "eval_loss": 5.740058898925781,
      "eval_runtime": 10.4015,
      "eval_samples_per_second": 69.605,
      "eval_steps_per_second": 8.749,
      "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": 564420799365120.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}