{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 25511,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 3.8798,
      "step": 500
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.999617887970705e-05,
      "loss": 3.3824,
      "step": 1000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.998471610286659e-05,
      "loss": 3.3404,
      "step": 1500
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.996561342150463e-05,
      "loss": 3.3427,
      "step": 2000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.993887375536685e-05,
      "loss": 3.2575,
      "step": 2500
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.990450119147252e-05,
      "loss": 3.2676,
      "step": 3000
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.98625009834897e-05,
      "loss": 3.1225,
      "step": 3500
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.981287955093226e-05,
      "loss": 3.1038,
      "step": 4000
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.97556444781787e-05,
      "loss": 3.132,
      "step": 4500
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.969080451331299e-05,
      "loss": 3.1255,
      "step": 5000
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.96183695667873e-05,
      "loss": 3.1358,
      "step": 5500
    },
    {
      "epoch": 0.24,
      "learning_rate": 9.95383507099074e-05,
      "loss": 3.1162,
      "step": 6000
    },
    {
      "epoch": 0.25,
      "learning_rate": 9.945076017314044e-05,
      "loss": 3.0475,
      "step": 6500
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.935561134424548e-05,
      "loss": 3.0587,
      "step": 7000
    },
    {
      "epoch": 0.29,
      "learning_rate": 9.925291876622738e-05,
      "loss": 3.0822,
      "step": 7500
    },
    {
      "epoch": 0.31,
      "learning_rate": 9.914269813511388e-05,
      "loss": 3.0829,
      "step": 8000
    },
    {
      "epoch": 0.33,
      "learning_rate": 9.902496629755661e-05,
      "loss": 3.0594,
      "step": 8500
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.88997412482561e-05,
      "loss": 3.0949,
      "step": 9000
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.876704212721141e-05,
      "loss": 3.0807,
      "step": 9500
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.862688921679476e-05,
      "loss": 2.9289,
      "step": 10000
    },
    {
      "epoch": 0.41,
      "learning_rate": 9.847930393865132e-05,
      "loss": 3.0059,
      "step": 10500
    },
    {
      "epoch": 0.43,
      "learning_rate": 9.832430885042515e-05,
      "loss": 3.0391,
      "step": 11000
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.816192764231132e-05,
      "loss": 3.0225,
      "step": 11500
    },
    {
      "epoch": 0.47,
      "learning_rate": 9.799218513343504e-05,
      "loss": 3.0199,
      "step": 12000
    },
    {
      "epoch": 0.49,
      "learning_rate": 9.781510726805807e-05,
      "loss": 3.0201,
      "step": 12500
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.763072111161344e-05,
      "loss": 3.0321,
      "step": 13000
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.743905484656852e-05,
      "loss": 2.8965,
      "step": 13500
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.724013776811747e-05,
      "loss": 3.0016,
      "step": 14000
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.70340002797037e-05,
      "loss": 3.0327,
      "step": 14500
    },
    {
      "epoch": 0.59,
      "learning_rate": 9.682067388837286e-05,
      "loss": 3.036,
      "step": 15000
    },
    {
      "epoch": 0.61,
      "learning_rate": 9.660019119995702e-05,
      "loss": 3.0152,
      "step": 15500
    },
    {
      "epoch": 0.63,
      "learning_rate": 9.63725859140912e-05,
      "loss": 2.9673,
      "step": 16000
    },
    {
      "epoch": 0.65,
      "learning_rate": 9.613789281906243e-05,
      "loss": 3.0032,
      "step": 16500
    },
    {
      "epoch": 0.67,
      "learning_rate": 9.589614778649267e-05,
      "loss": 2.9865,
      "step": 17000
    },
    {
      "epoch": 0.69,
      "learning_rate": 9.564738776585591e-05,
      "loss": 3.0042,
      "step": 17500
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.539165077883064e-05,
      "loss": 2.988,
      "step": 18000
    },
    {
      "epoch": 0.73,
      "learning_rate": 9.51289759134885e-05,
      "loss": 2.9729,
      "step": 18500
    },
    {
      "epoch": 0.74,
      "learning_rate": 9.485940331831984e-05,
      "loss": 2.9924,
      "step": 19000
    },
    {
      "epoch": 0.76,
      "learning_rate": 9.45829741960972e-05,
      "loss": 2.96,
      "step": 19500
    },
    {
      "epoch": 0.78,
      "learning_rate": 9.429973079757773e-05,
      "loss": 2.9702,
      "step": 20000
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.400971641504533e-05,
      "loss": 2.9362,
      "step": 20500
    },
    {
      "epoch": 0.82,
      "learning_rate": 9.371297537569369e-05,
      "loss": 2.9421,
      "step": 21000
    },
    {
      "epoch": 0.84,
      "learning_rate": 9.340955303485112e-05,
      "loss": 2.8557,
      "step": 21500
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.309949576904817e-05,
      "loss": 2.8443,
      "step": 22000
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.278285096892927e-05,
      "loss": 2.8352,
      "step": 22500
    },
    {
      "epoch": 0.9,
      "learning_rate": 9.245966703200923e-05,
      "loss": 2.8187,
      "step": 23000
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.212999335527607e-05,
      "loss": 2.887,
      "step": 23500
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.179388032764086e-05,
      "loss": 2.9268,
      "step": 24000
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.145137932223598e-05,
      "loss": 2.9458,
      "step": 24500
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.110254268856312e-05,
      "loss": 2.8961,
      "step": 25000
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.074742374449192e-05,
      "loss": 2.9421,
      "step": 25500
    },
    {
      "epoch": 1.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.790889024734497,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 5805056,
      "eval_runtime": 9395.1429,
      "eval_samples_per_second": 1.207,
      "eval_steps_per_second": 0.302,
      "eval_translation_length": 5805056,
      "step": 25511
    }
  ],
  "logging_steps": 500,
  "max_steps": 127555,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 2.351831312404316e+17,
  "trial_name": null,
  "trial_params": null
}