{
  "best_metric": 2.130274534225464,
  "best_model_checkpoint": "gen_test/checkpoint-628",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 628,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 2.1953625679016113,
      "eval_runtime": 56.1633,
      "eval_samples_per_second": 178.052,
      "eval_steps_per_second": 2.795,
      "step": 157
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.150932550430298,
      "eval_runtime": 55.9253,
      "eval_samples_per_second": 178.81,
      "eval_steps_per_second": 2.807,
      "step": 314
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.138493299484253,
      "eval_runtime": 56.1775,
      "eval_samples_per_second": 178.007,
      "eval_steps_per_second": 2.795,
      "step": 471
    },
    {
      "epoch": 3.18,
      "grad_norm": 329793.9375,
      "learning_rate": 4.076433121019109e-06,
      "loss": 2.1576,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.130274534225464,
      "eval_runtime": 56.1431,
      "eval_samples_per_second": 178.116,
      "eval_steps_per_second": 2.796,
      "step": 628
    }
  ],
  "logging_steps": 500,
  "max_steps": 628,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 2.090336256e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}