{
  "best_metric": 4.38653039932251,
  "best_model_checkpoint": "./output_dir/checkpoint-157",
  "epoch": 0.9980135081446166,
  "eval_steps": 50.0,
  "global_step": 157,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32,
      "learning_rate": 6.815286624203822e-05,
      "loss": 0.5783,
      "step": 50
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.630573248407643e-05,
      "loss": 0.1937,
      "step": 100
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.45859872611465e-06,
      "loss": 0.1561,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_bleu-1": 76.4907,
      "eval_bleu-2": 72.8873,
      "eval_bleu-3": 72.2748,
      "eval_bleu-4": 72.0466,
      "eval_gen_len": 137.0,
      "eval_loss": 4.38653039932251,
      "eval_runtime": 6.5519,
      "eval_samples_per_second": 1.832,
      "eval_steps_per_second": 0.458,
      "step": 157
    },
    {
      "epoch": 1.0,
      "step": 157,
      "total_flos": 2.27734163816448e+16,
      "train_loss": 0.3017981697799294,
      "train_runtime": 949.0641,
      "train_samples_per_second": 10.608,
      "train_steps_per_second": 0.165
    }
  ],
  "logging_steps": 50,
  "max_steps": 157,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 2.27734163816448e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}