{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05296610169491525,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00211864406779661,
      "grad_norm": 6772.94736433113,
      "learning_rate": 5.263157894736842e-06,
      "loss": 5.4426,
      "step": 1
    },
    {
      "epoch": 0.0211864406779661,
      "grad_norm": 43.76552598391156,
      "learning_rate": 5.263157894736842e-05,
      "loss": 6.5697,
      "step": 10
    },
    {
      "epoch": 0.0423728813559322,
      "grad_norm": 1.4214989301078385,
      "learning_rate": 0.00010526315789473683,
      "loss": 5.8015,
      "step": 20
    }
  ],
  "logging_steps": 10,
  "max_steps": 1888,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 616664961908736.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}