{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.782525118099818e-05,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": Infinity,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.747,
      "step": 20
    },
    {
      "epoch": 0.0,
      "grad_norm": 90.38651275634766,
      "learning_rate": 5.333333333333334e-06,
      "loss": 3.7962,
      "step": 40
    },
    {
      "epoch": 0.0,
      "grad_norm": 108.40189361572266,
      "learning_rate": 8.666666666666668e-06,
      "loss": 3.5164,
      "step": 60
    },
    {
      "epoch": 0.0,
      "grad_norm": 109.34711456298828,
      "learning_rate": 1.2e-05,
      "loss": 4.0846,
      "step": 80
    },
    {
      "epoch": 0.0,
      "grad_norm": 75.66071319580078,
      "learning_rate": 1.5333333333333334e-05,
      "loss": 3.594,
      "step": 100
    }
  ],
  "logging_steps": 20,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "total_flos": 426432203366400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}