{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13969732246798602,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004656577415599534,
      "eval_loss": NaN,
      "eval_runtime": 4.6759,
      "eval_samples_per_second": 19.461,
      "eval_steps_per_second": 9.838,
      "step": 1
    },
    {
      "epoch": 0.013969732246798603,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.027939464493597205,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.037252619324796274,
      "eval_loss": NaN,
      "eval_runtime": 3.8619,
      "eval_samples_per_second": 23.564,
      "eval_steps_per_second": 11.911,
      "step": 8
    },
    {
      "epoch": 0.04190919674039581,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.05587892898719441,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.06984866123399301,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.07450523864959255,
      "eval_loss": NaN,
      "eval_runtime": 4.0183,
      "eval_samples_per_second": 22.647,
      "eval_steps_per_second": 11.448,
      "step": 16
    },
    {
      "epoch": 0.08381839348079162,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.09778812572759023,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.11175785797438882,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.11175785797438882,
      "eval_loss": NaN,
      "eval_runtime": 4.1551,
      "eval_samples_per_second": 21.901,
      "eval_steps_per_second": 11.071,
      "step": 24
    },
    {
      "epoch": 0.12572759022118743,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.13969732246798602,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1959403255234560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}