{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8235294117647058,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.9507614953084023,
      "learning_rate": 3.928571428571429e-05,
      "loss": 1.113,
      "mean_token_accuracy": 0.7593891113996506,
      "num_tokens": 2505918.0,
      "step": 5
    },
    {
      "epoch": 1.1176470588235294,
      "grad_norm": 0.7659176500017072,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.9494,
      "mean_token_accuracy": 0.7857540216710832,
      "num_tokens": 4791423.0,
      "step": 10
    },
    {
      "epoch": 1.7058823529411766,
      "grad_norm": 0.35777988200221006,
      "learning_rate": 3.5714285714285714e-06,
      "loss": 0.8142,
      "mean_token_accuracy": 0.8114662289619445,
      "num_tokens": 7330272.0,
      "step": 15
    },
    {
      "epoch": 1.8235294117647058,
      "mean_token_accuracy": 0.8295768797397614,
      "num_tokens": 7816679.0,
      "step": 16,
      "total_flos": 11567169011712.0,
      "train_loss": 0.9362104684114456,
      "train_runtime": 218.964,
      "train_samples_per_second": 4.923,
      "train_steps_per_second": 0.073
    }
  ],
  "logging_steps": 5,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 11567169011712.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}