{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 33330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6,
      "learning_rate": 3.4998499849985e-05,
      "loss": 1.2916,
      "step": 10000
    },
    {
      "epoch": 1.0,
      "eval_bleu": 34.364,
      "eval_gen_len": 33.5343,
      "eval_loss": 1.2725797891616821,
      "eval_runtime": 274.8183,
      "eval_samples_per_second": 4.618,
      "eval_steps_per_second": 0.579,
      "step": 16665
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.999699969997e-05,
      "loss": 1.1191,
      "step": 20000
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.995499549954996e-06,
      "loss": 0.9083,
      "step": 30000
    }
  ],
  "max_steps": 33330,
  "num_train_epochs": 2,
  "total_flos": 3.380407103668224e+16,
  "trial_name": null,
  "trial_params": null
}