{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.605851979345955,
  "eval_steps": 2500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.3,
      "grad_norm": 1.1691417694091797,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 0.2129,
      "step": 2500
    },
    {
      "epoch": 4.3,
      "eval_loss": 0.333095908164978,
      "eval_runtime": 83.9342,
      "eval_samples_per_second": 11.914,
      "eval_steps_per_second": 2.979,
      "step": 2500
    },
    {
      "epoch": 8.61,
      "grad_norm": 0.1415511667728424,
      "learning_rate": 0.0,
      "loss": 0.0149,
      "step": 5000
    },
    {
      "epoch": 8.61,
      "eval_loss": 0.4397329092025757,
      "eval_runtime": 83.9924,
      "eval_samples_per_second": 11.906,
      "eval_steps_per_second": 2.976,
      "step": 5000
    }
  ],
  "logging_steps": 2500,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 2500,
  "total_flos": 1.258569996863275e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}