{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 15.0,
  "eval_steps": 500,
  "global_step": 1170,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_bleu": 0.0614222863931305,
      "eval_loss": 7.409209728240967,
      "eval_runtime": 18.3549,
      "eval_samples_per_second": 4.958,
      "eval_steps_per_second": 0.327,
      "step": 78
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.06781414925085748,
      "eval_loss": 6.072174072265625,
      "eval_runtime": 21.0214,
      "eval_samples_per_second": 4.329,
      "eval_steps_per_second": 0.285,
      "step": 156
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.07865444133157673,
      "eval_loss": 4.586818695068359,
      "eval_runtime": 16.8905,
      "eval_samples_per_second": 5.388,
      "eval_steps_per_second": 0.355,
      "step": 234
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.10492023143484121,
      "eval_loss": 2.7620725631713867,
      "eval_runtime": 20.9126,
      "eval_samples_per_second": 4.351,
      "eval_steps_per_second": 0.287,
      "step": 312
    },
    {
      "epoch": 5.0,
      "eval_bleu": 7.870773986323496e-05,
      "eval_loss": 1.7986291646957397,
      "eval_runtime": 28.9333,
      "eval_samples_per_second": 3.145,
      "eval_steps_per_second": 0.207,
      "step": 390
    },
    {
      "epoch": 6.0,
      "eval_bleu": 4.7698260005659636e-32,
      "eval_loss": 1.7516156435012817,
      "eval_runtime": 29.6724,
      "eval_samples_per_second": 3.067,
      "eval_steps_per_second": 0.202,
      "step": 468
    },
    {
      "epoch": 6.410256410256411,
      "grad_norm": 0.5151189565658569,
      "learning_rate": 2.976e-05,
      "loss": 4.7498,
      "step": 500
    },
    {
      "epoch": 7.0,
      "eval_bleu": 0.05376879163106575,
      "eval_loss": 1.7408103942871094,
      "eval_runtime": 28.1805,
      "eval_samples_per_second": 3.229,
      "eval_steps_per_second": 0.213,
      "step": 546
    },
    {
      "epoch": 8.0,
      "eval_bleu": 22.551967047591756,
      "eval_loss": 1.7349852323532104,
      "eval_runtime": 24.3775,
      "eval_samples_per_second": 3.733,
      "eval_steps_per_second": 0.246,
      "step": 624
    },
    {
      "epoch": 9.0,
      "eval_bleu": 27.560704428979403,
      "eval_loss": 1.7364959716796875,
      "eval_runtime": 19.0116,
      "eval_samples_per_second": 4.787,
      "eval_steps_per_second": 0.316,
      "step": 702
    },
    {
      "epoch": 10.0,
      "eval_bleu": 29.12683290388149,
      "eval_loss": 1.7374337911605835,
      "eval_runtime": 15.4603,
      "eval_samples_per_second": 5.886,
      "eval_steps_per_second": 0.388,
      "step": 780
    },
    {
      "epoch": 11.0,
      "eval_bleu": 29.408921311422052,
      "eval_loss": 1.7404249906539917,
      "eval_runtime": 16.9631,
      "eval_samples_per_second": 5.365,
      "eval_steps_per_second": 0.354,
      "step": 858
    },
    {
      "epoch": 12.0,
      "eval_bleu": 30.17855336606261,
      "eval_loss": 1.7426787614822388,
      "eval_runtime": 12.8597,
      "eval_samples_per_second": 7.076,
      "eval_steps_per_second": 0.467,
      "step": 936
    },
    {
      "epoch": 12.820512820512821,
      "grad_norm": 0.24796663224697113,
      "learning_rate": 7.791044776119404e-06,
      "loss": 1.5765,
      "step": 1000
    },
    {
      "epoch": 13.0,
      "eval_bleu": 30.17706557207897,
      "eval_loss": 1.7429455518722534,
      "eval_runtime": 12.8783,
      "eval_samples_per_second": 7.066,
      "eval_steps_per_second": 0.466,
      "step": 1014
    },
    {
      "epoch": 14.0,
      "eval_bleu": 30.818742074203392,
      "eval_loss": 1.746609091758728,
      "eval_runtime": 12.9695,
      "eval_samples_per_second": 7.016,
      "eval_steps_per_second": 0.463,
      "step": 1092
    },
    {
      "epoch": 15.0,
      "eval_bleu": 30.929249185720632,
      "eval_loss": 1.7464464902877808,
      "eval_runtime": 12.8549,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.467,
      "step": 1170
    }
  ],
  "logging_steps": 500,
  "max_steps": 1170,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.009328968433664e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}