{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "global_step": 11268,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 5.8584,
      "step": 500
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.2538,
      "step": 1000
    },
    {
      "epoch": 0.8,
      "learning_rate": 5e-05,
      "loss": 4.9787,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_bleu1_score": 0.0914,
      "eval_bleu2_score": 0.0332,
      "eval_bleu3_score": 0.0145,
      "eval_bleu4_score": 0.0068,
      "eval_loss": 4.642809867858887,
      "eval_rougeL": 0.0644,
      "eval_runtime": 1678.0874,
      "eval_samples_per_second": 0.995,
      "eval_steps_per_second": 0.125,
      "step": 1878
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.744062244062245e-05,
      "loss": 4.7678,
      "step": 2000
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.4881244881244886e-05,
      "loss": 4.39,
      "step": 2500
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.2321867321867324e-05,
      "loss": 4.3397,
      "step": 3000
    },
    {
      "epoch": 1.86,
      "learning_rate": 3.976248976248976e-05,
      "loss": 4.3018,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "eval_bleu1_score": 0.1042,
      "eval_bleu2_score": 0.0416,
      "eval_bleu3_score": 0.0195,
      "eval_bleu4_score": 0.0096,
      "eval_loss": 4.3901753425598145,
      "eval_rougeL": 0.0812,
      "eval_runtime": 1428.6395,
      "eval_samples_per_second": 1.169,
      "eval_steps_per_second": 0.146,
      "step": 3756
    },
    {
      "epoch": 2.13,
      "learning_rate": 3.720311220311221e-05,
      "loss": 3.9973,
      "step": 4000
    },
    {
      "epoch": 2.4,
      "learning_rate": 3.4643734643734647e-05,
      "loss": 3.7469,
      "step": 4500
    },
    {
      "epoch": 2.66,
      "learning_rate": 3.2084357084357085e-05,
      "loss": 3.7297,
      "step": 5000
    },
    {
      "epoch": 2.93,
      "learning_rate": 2.952497952497953e-05,
      "loss": 3.7295,
      "step": 5500
    },
    {
      "epoch": 3.0,
      "eval_bleu1_score": 0.1094,
      "eval_bleu2_score": 0.0438,
      "eval_bleu3_score": 0.0205,
      "eval_bleu4_score": 0.0099,
      "eval_loss": 4.351379871368408,
      "eval_rougeL": 0.0896,
      "eval_runtime": 1580.9203,
      "eval_samples_per_second": 1.056,
      "eval_steps_per_second": 0.132,
      "step": 5634
    },
    {
      "epoch": 3.19,
      "learning_rate": 2.6965601965601965e-05,
      "loss": 3.343,
      "step": 6000
    },
    {
      "epoch": 3.46,
      "learning_rate": 2.4406224406224407e-05,
      "loss": 3.1757,
      "step": 6500
    },
    {
      "epoch": 3.73,
      "learning_rate": 2.1846846846846845e-05,
      "loss": 3.2114,
      "step": 7000
    },
    {
      "epoch": 3.99,
      "learning_rate": 1.928746928746929e-05,
      "loss": 3.1804,
      "step": 7500
    },
    {
      "epoch": 4.0,
      "eval_bleu1_score": 0.1138,
      "eval_bleu2_score": 0.0499,
      "eval_bleu3_score": 0.0251,
      "eval_bleu4_score": 0.0135,
      "eval_loss": 4.437016010284424,
      "eval_rougeL": 0.0915,
      "eval_runtime": 1588.6623,
      "eval_samples_per_second": 1.051,
      "eval_steps_per_second": 0.132,
      "step": 7512
    },
    {
      "epoch": 4.26,
      "learning_rate": 1.672809172809173e-05,
      "loss": 2.7489,
      "step": 8000
    },
    {
      "epoch": 4.53,
      "learning_rate": 1.416871416871417e-05,
      "loss": 2.7514,
      "step": 8500
    },
    {
      "epoch": 4.79,
      "learning_rate": 1.1609336609336611e-05,
      "loss": 2.751,
      "step": 9000
    },
    {
      "epoch": 5.0,
      "eval_bleu1_score": 0.1147,
      "eval_bleu2_score": 0.0506,
      "eval_bleu3_score": 0.0263,
      "eval_bleu4_score": 0.0141,
      "eval_loss": 4.623700141906738,
      "eval_rougeL": 0.0944,
      "eval_runtime": 1602.0629,
      "eval_samples_per_second": 1.042,
      "eval_steps_per_second": 0.13,
      "step": 9390
    },
    {
      "epoch": 5.06,
      "learning_rate": 9.049959049959051e-06,
      "loss": 2.7029,
      "step": 9500
    },
    {
      "epoch": 5.32,
      "learning_rate": 6.49058149058149e-06,
      "loss": 2.416,
      "step": 10000
    },
    {
      "epoch": 5.59,
      "learning_rate": 3.931203931203931e-06,
      "loss": 2.4479,
      "step": 10500
    },
    {
      "epoch": 5.86,
      "learning_rate": 1.371826371826372e-06,
      "loss": 2.4352,
      "step": 11000
    },
    {
      "epoch": 6.0,
      "eval_bleu1_score": 0.1211,
      "eval_bleu2_score": 0.0542,
      "eval_bleu3_score": 0.0277,
      "eval_bleu4_score": 0.0147,
      "eval_loss": 4.784670352935791,
      "eval_rougeL": 0.0996,
      "eval_runtime": 1556.44,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 0.134,
      "step": 11268
    }
  ],
  "max_steps": 11268,
  "num_train_epochs": 6,
  "total_flos": 5.512311147331584e+16,
  "trial_name": null,
  "trial_params": null
}