{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "global_step": 3810,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_bleu": 0.0167,
      "eval_gen_len": 19.0,
      "eval_loss": 1.0651702880859375,
      "eval_runtime": 37.0111,
      "eval_samples_per_second": 20.588,
      "eval_steps_per_second": 1.297,
      "step": 381
    },
    {
      "epoch": 1.31,
      "learning_rate": 4.343832020997376e-05,
      "loss": 1.5288,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.0402,
      "eval_gen_len": 19.0,
      "eval_loss": 0.933931291103363,
      "eval_runtime": 37.1713,
      "eval_samples_per_second": 20.5,
      "eval_steps_per_second": 1.291,
      "step": 762
    },
    {
      "epoch": 2.62,
      "learning_rate": 3.6876640419947505e-05,
      "loss": 1.063,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.0311,
      "eval_gen_len": 19.0,
      "eval_loss": 0.8651323318481445,
      "eval_runtime": 37.9241,
      "eval_samples_per_second": 20.093,
      "eval_steps_per_second": 1.266,
      "step": 1143
    },
    {
      "epoch": 3.94,
      "learning_rate": 3.0314960629921263e-05,
      "loss": 0.9558,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.1018,
      "eval_gen_len": 19.0,
      "eval_loss": 0.8271389603614807,
      "eval_runtime": 37.7015,
      "eval_samples_per_second": 20.211,
      "eval_steps_per_second": 1.273,
      "step": 1524
    },
    {
      "epoch": 5.0,
      "eval_bleu": 0.0744,
      "eval_gen_len": 19.0,
      "eval_loss": 0.8043217062950134,
      "eval_runtime": 38.014,
      "eval_samples_per_second": 20.045,
      "eval_steps_per_second": 1.263,
      "step": 1905
    },
    {
      "epoch": 5.25,
      "learning_rate": 2.3753280839895015e-05,
      "loss": 0.8979,
      "step": 2000
    },
    {
      "epoch": 6.0,
      "eval_bleu": 0.0786,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7830905318260193,
      "eval_runtime": 37.5069,
      "eval_samples_per_second": 20.316,
      "eval_steps_per_second": 1.28,
      "step": 2286
    },
    {
      "epoch": 6.56,
      "learning_rate": 1.7191601049868766e-05,
      "loss": 0.8598,
      "step": 2500
    },
    {
      "epoch": 7.0,
      "eval_bleu": 0.086,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7698926329612732,
      "eval_runtime": 37.7633,
      "eval_samples_per_second": 20.178,
      "eval_steps_per_second": 1.271,
      "step": 2667
    },
    {
      "epoch": 7.87,
      "learning_rate": 1.062992125984252e-05,
      "loss": 0.8346,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_bleu": 0.0803,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7630091309547424,
      "eval_runtime": 37.5503,
      "eval_samples_per_second": 20.293,
      "eval_steps_per_second": 1.278,
      "step": 3048
    },
    {
      "epoch": 9.0,
      "eval_bleu": 0.1179,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7571505904197693,
      "eval_runtime": 37.5775,
      "eval_samples_per_second": 20.278,
      "eval_steps_per_second": 1.277,
      "step": 3429
    },
    {
      "epoch": 9.19,
      "learning_rate": 4.068241469816273e-06,
      "loss": 0.8194,
      "step": 3500
    },
    {
      "epoch": 10.0,
      "eval_bleu": 0.1133,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7551639676094055,
      "eval_runtime": 37.5909,
      "eval_samples_per_second": 20.271,
      "eval_steps_per_second": 1.277,
      "step": 3810
    },
    {
      "epoch": 10.0,
      "step": 3810,
      "total_flos": 2.167800665997312e+16,
      "train_loss": 0.9795461539521305,
      "train_runtime": 2020.5453,
      "train_samples_per_second": 30.17,
      "train_steps_per_second": 1.886
    }
  ],
  "max_steps": 3810,
  "num_train_epochs": 10,
  "total_flos": 2.167800665997312e+16,
  "trial_name": null,
  "trial_params": null
}