{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1875,
  "eval_steps": 1,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0625,
      "grad_norm": 6.13511848449707,
      "learning_rate": 0.0,
      "loss": 1.3392,
      "step": 1
    },
    {
      "epoch": 0.125,
      "grad_norm": 6.1215314865112305,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 1.3493,
      "step": 2
    },
    {
      "epoch": 0.1875,
      "grad_norm": 6.143799781799316,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 1.3478,
      "step": 3
    },
    {
      "epoch": 0.1875,
      "step": 3,
      "total_flos": 221467993178112.0,
      "train_loss": 0.4492587248484294,
      "train_runtime": 35.9777,
      "train_samples_per_second": 5.692,
      "train_steps_per_second": 0.056
    }
  ],
  "logging_steps": 1,
  "max_steps": 2,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 221467993178112.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}