{
  "best_metric": 4.029151439666748,
  "best_model_checkpoint": "continued-finetuned-en-to-lg/checkpoint-39",
  "epoch": 26.0,
  "eval_steps": 50,
  "global_step": 1027,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9873417721518988,
      "eval_bleu": 0.8383,
      "eval_gen_len": 20.509,
      "eval_loss": 4.029151439666748,
      "eval_runtime": 478.8606,
      "eval_samples_per_second": 25.387,
      "eval_steps_per_second": 0.794,
      "step": 39
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.8282,
      "eval_gen_len": 20.3936,
      "eval_loss": 4.243524074554443,
      "eval_runtime": 474.9597,
      "eval_samples_per_second": 25.596,
      "eval_steps_per_second": 0.8,
      "step": 79
    },
    {
      "epoch": 2.9873417721518987,
      "eval_bleu": 0.8032,
      "eval_gen_len": 20.33,
      "eval_loss": 4.359070301055908,
      "eval_runtime": 475.0262,
      "eval_samples_per_second": 25.592,
      "eval_steps_per_second": 0.8,
      "step": 118
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.8038,
      "eval_gen_len": 20.2033,
      "eval_loss": 4.451895236968994,
      "eval_runtime": 473.6738,
      "eval_samples_per_second": 25.665,
      "eval_steps_per_second": 0.802,
      "step": 158
    },
    {
      "epoch": 4.987341772151899,
      "eval_bleu": 0.8017,
      "eval_gen_len": 20.0283,
      "eval_loss": 4.547088146209717,
      "eval_runtime": 476.3005,
      "eval_samples_per_second": 25.524,
      "eval_steps_per_second": 0.798,
      "step": 197
    },
    {
      "epoch": 6.0,
      "eval_bleu": 0.7828,
      "eval_gen_len": 20.1771,
      "eval_loss": 4.555694103240967,
      "eval_runtime": 473.4342,
      "eval_samples_per_second": 25.678,
      "eval_steps_per_second": 0.803,
      "step": 237
    },
    {
      "epoch": 6.987341772151899,
      "eval_bleu": 0.771,
      "eval_gen_len": 20.3172,
      "eval_loss": 4.672959327697754,
      "eval_runtime": 476.2521,
      "eval_samples_per_second": 25.526,
      "eval_steps_per_second": 0.798,
      "step": 276
    },
    {
      "epoch": 8.0,
      "eval_bleu": 0.7971,
      "eval_gen_len": 20.2095,
      "eval_loss": 4.719875812530518,
      "eval_runtime": 472.5874,
      "eval_samples_per_second": 25.724,
      "eval_steps_per_second": 0.804,
      "step": 316
    },
    {
      "epoch": 8.987341772151899,
      "eval_bleu": 0.7587,
      "eval_gen_len": 20.4253,
      "eval_loss": 4.758220672607422,
      "eval_runtime": 477.573,
      "eval_samples_per_second": 25.456,
      "eval_steps_per_second": 0.796,
      "step": 355
    },
    {
      "epoch": 10.0,
      "eval_bleu": 0.7975,
      "eval_gen_len": 20.3643,
      "eval_loss": 4.771291255950928,
      "eval_runtime": 477.1681,
      "eval_samples_per_second": 25.477,
      "eval_steps_per_second": 0.796,
      "step": 395
    },
    {
      "epoch": 10.987341772151899,
      "eval_bleu": 0.7619,
      "eval_gen_len": 20.4121,
      "eval_loss": 4.748700141906738,
      "eval_runtime": 479.5702,
      "eval_samples_per_second": 25.35,
      "eval_steps_per_second": 0.792,
      "step": 434
    },
    {
      "epoch": 12.0,
      "eval_bleu": 0.7865,
      "eval_gen_len": 20.3477,
      "eval_loss": 4.832670211791992,
      "eval_runtime": 473.4727,
      "eval_samples_per_second": 25.676,
      "eval_steps_per_second": 0.803,
      "step": 474
    },
    {
      "epoch": 12.658227848101266,
      "grad_norm": 1.2026784420013428,
      "learning_rate": 1.1452991452991454e-05,
      "loss": 0.1585,
      "step": 500
    },
    {
      "epoch": 12.987341772151899,
      "eval_bleu": 0.7909,
      "eval_gen_len": 20.307,
      "eval_loss": 4.844118595123291,
      "eval_runtime": 475.2982,
      "eval_samples_per_second": 25.578,
      "eval_steps_per_second": 0.799,
      "step": 513
    },
    {
      "epoch": 14.0,
      "eval_bleu": 0.8004,
      "eval_gen_len": 20.3038,
      "eval_loss": 4.876136302947998,
      "eval_runtime": 475.2478,
      "eval_samples_per_second": 25.58,
      "eval_steps_per_second": 0.8,
      "step": 553
    },
    {
      "epoch": 14.987341772151899,
      "eval_bleu": 0.7823,
      "eval_gen_len": 20.2747,
      "eval_loss": 4.92393684387207,
      "eval_runtime": 476.8033,
      "eval_samples_per_second": 25.497,
      "eval_steps_per_second": 0.797,
      "step": 592
    },
    {
      "epoch": 16.0,
      "eval_bleu": 0.79,
      "eval_gen_len": 20.226,
      "eval_loss": 4.880424976348877,
      "eval_runtime": 474.5946,
      "eval_samples_per_second": 25.616,
      "eval_steps_per_second": 0.801,
      "step": 632
    },
    {
      "epoch": 16.9873417721519,
      "eval_bleu": 0.7821,
      "eval_gen_len": 20.3653,
      "eval_loss": 4.9470534324646,
      "eval_runtime": 477.2511,
      "eval_samples_per_second": 25.473,
      "eval_steps_per_second": 0.796,
      "step": 671
    },
    {
      "epoch": 18.0,
      "eval_bleu": 0.7876,
      "eval_gen_len": 20.3285,
      "eval_loss": 4.9639482498168945,
      "eval_runtime": 477.3388,
      "eval_samples_per_second": 25.468,
      "eval_steps_per_second": 0.796,
      "step": 711
    },
    {
      "epoch": 18.9873417721519,
      "eval_bleu": 0.7895,
      "eval_gen_len": 20.3364,
      "eval_loss": 4.970686912536621,
      "eval_runtime": 476.4474,
      "eval_samples_per_second": 25.516,
      "eval_steps_per_second": 0.798,
      "step": 750
    },
    {
      "epoch": 20.0,
      "eval_bleu": 0.784,
      "eval_gen_len": 20.3641,
      "eval_loss": 4.984948635101318,
      "eval_runtime": 477.378,
      "eval_samples_per_second": 25.466,
      "eval_steps_per_second": 0.796,
      "step": 790
    },
    {
      "epoch": 20.9873417721519,
      "eval_bleu": 0.7838,
      "eval_gen_len": 20.3852,
      "eval_loss": 5.011585712432861,
      "eval_runtime": 477.6336,
      "eval_samples_per_second": 25.453,
      "eval_steps_per_second": 0.796,
      "step": 829
    },
    {
      "epoch": 22.0,
      "eval_bleu": 0.7874,
      "eval_gen_len": 20.3104,
      "eval_loss": 5.026498794555664,
      "eval_runtime": 477.8381,
      "eval_samples_per_second": 25.442,
      "eval_steps_per_second": 0.795,
      "step": 869
    },
    {
      "epoch": 22.9873417721519,
      "eval_bleu": 0.7886,
      "eval_gen_len": 20.3484,
      "eval_loss": 5.026541233062744,
      "eval_runtime": 478.7469,
      "eval_samples_per_second": 25.393,
      "eval_steps_per_second": 0.794,
      "step": 908
    },
    {
      "epoch": 24.0,
      "eval_bleu": 0.7833,
      "eval_gen_len": 20.3558,
      "eval_loss": 5.028345584869385,
      "eval_runtime": 476.6444,
      "eval_samples_per_second": 25.505,
      "eval_steps_per_second": 0.797,
      "step": 948
    },
    {
      "epoch": 24.9873417721519,
      "eval_bleu": 0.7835,
      "eval_gen_len": 20.313,
      "eval_loss": 5.029706001281738,
      "eval_runtime": 478.6376,
      "eval_samples_per_second": 25.399,
      "eval_steps_per_second": 0.794,
      "step": 987
    },
    {
      "epoch": 25.31645569620253,
      "grad_norm": 0.5030060410499573,
      "learning_rate": 2.9059829059829063e-06,
      "loss": 0.0263,
      "step": 1000
    },
    {
      "epoch": 26.0,
      "eval_bleu": 0.7812,
      "eval_gen_len": 20.3503,
      "eval_loss": 5.040848731994629,
      "eval_runtime": 478.615,
      "eval_samples_per_second": 25.4,
      "eval_steps_per_second": 0.794,
      "step": 1027
    }
  ],
  "logging_steps": 500,
  "max_steps": 1170,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 346447645507584.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}