{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010012854340031121,
  "eval_steps": 3000,
  "global_step": 148,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.76544212164265e-05,
      "grad_norm": 36.75,
      "learning_rate": 0.00029797297297297294,
      "loss": 9.0625,
      "step": 1
    },
    {
      "epoch": 0.010012854340031121,
      "step": 148,
      "total_flos": 1140002213855232.0,
      "train_loss": 5.680320945945946,
      "train_runtime": 58.2622,
      "train_samples_per_second": 649.447,
      "train_steps_per_second": 2.54
    }
  ],
  "logging_steps": 3000,
  "max_steps": 148,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1140002213855232.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}