{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015167793718005435,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.055931239335145e-05,
      "eval_loss": NaN,
      "eval_runtime": 177.411,
      "eval_samples_per_second": 46.942,
      "eval_steps_per_second": 23.471,
      "step": 1
    },
    {
      "epoch": 0.00015167793718005436,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00030335587436010873,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0004044744991468116,
      "eval_loss": NaN,
      "eval_runtime": 177.5324,
      "eval_samples_per_second": 46.91,
      "eval_steps_per_second": 23.455,
      "step": 8
    },
    {
      "epoch": 0.00045503381154016307,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0006067117487202175,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0007583896859002717,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0008089489982936232,
      "eval_loss": NaN,
      "eval_runtime": 177.1228,
      "eval_samples_per_second": 47.018,
      "eval_steps_per_second": 23.509,
      "step": 16
    },
    {
      "epoch": 0.0009100676230803261,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0010617455602603804,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.001213423497440435,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.001213423497440435,
      "eval_loss": NaN,
      "eval_runtime": 177.058,
      "eval_samples_per_second": 47.035,
      "eval_steps_per_second": 23.518,
      "step": 24
    },
    {
      "epoch": 0.0013651014346204892,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0015167793718005435,
      "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": 1790286753693696.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}