{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 34567,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 3.3228,
      "step": 500
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.999994258403258e-05,
      "loss": 2.8639,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.99997703362622e-05,
      "loss": 2.8198,
      "step": 1500
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.999948325708443e-05,
      "loss": 2.7858,
      "step": 2000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.999908134715859e-05,
      "loss": 2.7422,
      "step": 2500
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.999856460740773e-05,
      "loss": 2.7274,
      "step": 3000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.99979330390186e-05,
      "loss": 2.6958,
      "step": 3500
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.999718664344171e-05,
      "loss": 2.6617,
      "step": 4000
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.999632542239125e-05,
      "loss": 2.6747,
      "step": 4500
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.999534937784512e-05,
      "loss": 2.6564,
      "step": 5000
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.999425851204496e-05,
      "loss": 2.585,
      "step": 5500
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.99930528274961e-05,
      "loss": 2.6385,
      "step": 6000
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.999173232696753e-05,
      "loss": 2.6262,
      "step": 6500
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.999029701349196e-05,
      "loss": 2.6055,
      "step": 7000
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.998874689036583e-05,
      "loss": 2.5917,
      "step": 7500
    },
    {
      "epoch": 0.23,
      "learning_rate": 9.998708196114922e-05,
      "loss": 2.6162,
      "step": 8000
    },
    {
      "epoch": 0.25,
      "learning_rate": 9.99853022296658e-05,
      "loss": 2.6188,
      "step": 8500
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.998340770000302e-05,
      "loss": 2.5671,
      "step": 9000
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.998139837651193e-05,
      "loss": 2.5897,
      "step": 9500
    },
    {
      "epoch": 0.29,
      "learning_rate": 9.997927426380721e-05,
      "loss": 2.5414,
      "step": 10000
    },
    {
      "epoch": 0.3,
      "learning_rate": 9.997703536676718e-05,
      "loss": 2.5139,
      "step": 10500
    },
    {
      "epoch": 0.32,
      "learning_rate": 9.997468169053379e-05,
      "loss": 2.5904,
      "step": 11000
    },
    {
      "epoch": 0.33,
      "learning_rate": 9.997221324051255e-05,
      "loss": 2.6288,
      "step": 11500
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.996963002237263e-05,
      "loss": 2.598,
      "step": 12000
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.996693204204674e-05,
      "loss": 2.5276,
      "step": 12500
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.996411930573117e-05,
      "loss": 2.5817,
      "step": 13000
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.996119181988575e-05,
      "loss": 2.5316,
      "step": 13500
    },
    {
      "epoch": 0.41,
      "learning_rate": 9.995814959123386e-05,
      "loss": 2.4692,
      "step": 14000
    },
    {
      "epoch": 0.42,
      "learning_rate": 9.995499262676243e-05,
      "loss": 2.5464,
      "step": 14500
    },
    {
      "epoch": 0.43,
      "learning_rate": 9.99517209337218e-05,
      "loss": 2.5222,
      "step": 15000
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.994833451962592e-05,
      "loss": 2.5304,
      "step": 15500
    },
    {
      "epoch": 0.46,
      "learning_rate": 9.994483339225213e-05,
      "loss": 2.6063,
      "step": 16000
    },
    {
      "epoch": 0.48,
      "learning_rate": 9.994121755964129e-05,
      "loss": 2.5286,
      "step": 16500
    },
    {
      "epoch": 0.49,
      "learning_rate": 9.993748703009764e-05,
      "loss": 2.5273,
      "step": 17000
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.993364181218885e-05,
      "loss": 2.4868,
      "step": 17500
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.992968191474601e-05,
      "loss": 2.435,
      "step": 18000
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.992560734686357e-05,
      "loss": 2.484,
      "step": 18500
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.992141811789933e-05,
      "loss": 2.5301,
      "step": 19000
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.991711423747445e-05,
      "loss": 2.4857,
      "step": 19500
    },
    {
      "epoch": 0.58,
      "learning_rate": 9.991269571547339e-05,
      "loss": 2.4958,
      "step": 20000
    },
    {
      "epoch": 0.59,
      "learning_rate": 9.99081625620439e-05,
      "loss": 2.4757,
      "step": 20500
    },
    {
      "epoch": 0.61,
      "learning_rate": 9.990351478759696e-05,
      "loss": 2.544,
      "step": 21000
    },
    {
      "epoch": 0.62,
      "learning_rate": 9.989875240280689e-05,
      "loss": 2.4796,
      "step": 21500
    },
    {
      "epoch": 0.64,
      "learning_rate": 9.989387541861111e-05,
      "loss": 2.4968,
      "step": 22000
    },
    {
      "epoch": 0.65,
      "learning_rate": 9.988888384621031e-05,
      "loss": 2.4426,
      "step": 22500
    },
    {
      "epoch": 0.67,
      "learning_rate": 9.988377769706834e-05,
      "loss": 2.4471,
      "step": 23000
    },
    {
      "epoch": 0.68,
      "learning_rate": 9.987855698291218e-05,
      "loss": 2.5022,
      "step": 23500
    },
    {
      "epoch": 0.69,
      "learning_rate": 9.98732217157319e-05,
      "loss": 2.5202,
      "step": 24000
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.98677719077807e-05,
      "loss": 2.5562,
      "step": 24500
    },
    {
      "epoch": 0.72,
      "learning_rate": 9.986220757157482e-05,
      "loss": 2.4888,
      "step": 25000
    },
    {
      "epoch": 0.74,
      "learning_rate": 9.985652871989352e-05,
      "loss": 2.5049,
      "step": 25500
    },
    {
      "epoch": 0.75,
      "learning_rate": 9.98507353657791e-05,
      "loss": 2.4664,
      "step": 26000
    },
    {
      "epoch": 0.77,
      "learning_rate": 9.984482752253677e-05,
      "loss": 2.4528,
      "step": 26500
    },
    {
      "epoch": 0.78,
      "learning_rate": 9.98388052037347e-05,
      "loss": 2.4577,
      "step": 27000
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.983266842320402e-05,
      "loss": 2.4889,
      "step": 27500
    },
    {
      "epoch": 0.81,
      "learning_rate": 9.982641719503866e-05,
      "loss": 2.4272,
      "step": 28000
    },
    {
      "epoch": 0.82,
      "learning_rate": 9.982005153359547e-05,
      "loss": 2.4783,
      "step": 28500
    },
    {
      "epoch": 0.84,
      "learning_rate": 9.981357145349406e-05,
      "loss": 2.4795,
      "step": 29000
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.98069769696168e-05,
      "loss": 2.4807,
      "step": 29500
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.980026809710888e-05,
      "loss": 2.4951,
      "step": 30000
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.979344485137813e-05,
      "loss": 2.5137,
      "step": 30500
    },
    {
      "epoch": 0.9,
      "learning_rate": 9.978650724809511e-05,
      "loss": 2.5249,
      "step": 31000
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.977945530319297e-05,
      "loss": 2.4092,
      "step": 31500
    },
    {
      "epoch": 0.93,
      "learning_rate": 9.977228903286746e-05,
      "loss": 2.4978,
      "step": 32000
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.976500845357694e-05,
      "loss": 2.4361,
      "step": 32500
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.975761358204227e-05,
      "loss": 2.4774,
      "step": 33000
    },
    {
      "epoch": 0.97,
      "learning_rate": 9.975010443524679e-05,
      "loss": 2.4662,
      "step": 33500
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.974248103043629e-05,
      "loss": 2.4252,
      "step": 34000
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.973474338511898e-05,
      "loss": 2.4689,
      "step": 34500
    },
    {
      "epoch": 1.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.3501155376434326,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 1966592,
      "eval_runtime": 3383.1867,
      "eval_samples_per_second": 1.135,
      "eval_steps_per_second": 1.135,
      "eval_translation_length": 1966592,
      "step": 34567
    }
  ],
  "logging_steps": 500,
  "max_steps": 1037010,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 7.966891375696282e+16,
  "trial_name": null,
  "trial_params": null
}