{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.4210526315789473,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 17.545059191324462,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 1.0664,
      "step": 1
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 6.048058784630579,
      "learning_rate": 2.5e-06,
      "loss": 0.6627,
      "step": 5
    },
    {
      "epoch": 3.4210526315789473,
      "grad_norm": 3.5227568987177125,
      "learning_rate": 0.0,
      "loss": 0.2718,
      "step": 10
    },
    {
      "epoch": 3.4210526315789473,
      "step": 10,
      "total_flos": 4.581367311708979e+16,
      "train_loss": 0.507626187801361,
      "train_runtime": 687.6864,
      "train_samples_per_second": 2.203,
      "train_steps_per_second": 0.015
    }
  ],
  "logging_steps": 5,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.581367311708979e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}