{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15396578538102643,
  "eval_steps": 50,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015552099533437014,
      "eval_loss": 11.5,
      "eval_runtime": 0.9095,
      "eval_samples_per_second": 297.968,
      "eval_steps_per_second": 37.383,
      "step": 1
    },
    {
      "epoch": 0.03110419906687403,
      "grad_norm": 6.635740191995865e-06,
      "learning_rate": 0.0005,
      "loss": 11.5,
      "step": 20
    },
    {
      "epoch": 0.06220839813374806,
      "grad_norm": 1.2428505215211771e-05,
      "learning_rate": 0.00042501051864235636,
      "loss": 11.5,
      "step": 40
    },
    {
      "epoch": 0.07776049766718507,
      "eval_loss": 11.5,
      "eval_runtime": 0.8873,
      "eval_samples_per_second": 305.428,
      "eval_steps_per_second": 38.319,
      "step": 50
    },
    {
      "epoch": 0.09331259720062209,
      "grad_norm": 1.2873988453065977e-05,
      "learning_rate": 0.00024502945308373244,
      "loss": 11.5,
      "step": 60
    },
    {
      "epoch": 0.12441679626749612,
      "grad_norm": 1.2784214959538076e-05,
      "learning_rate": 6.803029740762648e-05,
      "loss": 11.5,
      "step": 80
    }
  ],
  "logging_steps": 20,
  "max_steps": 99,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1972364967936.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}