{
  "best_metric": 1.0819282531738281,
  "best_model_checkpoint": "./jako_mbartLarge_13p_run1/checkpoint-7500",
  "epoch": 1.9475460919241754,
  "eval_steps": 1500,
  "global_step": 7500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 4.97382884061764e-05,
      "loss": 1.9323,
      "step": 500
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.9084009421617376e-05,
      "loss": 1.487,
      "step": 1000
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.8429730437058366e-05,
      "loss": 1.3826,
      "step": 1500
    },
    {
      "epoch": 0.39,
      "eval_bleu": 22.0729,
      "eval_gen_len": 18.9717,
      "eval_loss": 1.2989100217819214,
      "eval_runtime": 581.8634,
      "eval_samples_per_second": 13.235,
      "eval_steps_per_second": 0.828,
      "step": 1500
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.777545145249935e-05,
      "loss": 1.2846,
      "step": 2000
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.712117246794033e-05,
      "loss": 1.2292,
      "step": 2500
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.646689348338132e-05,
      "loss": 1.1964,
      "step": 3000
    },
    {
      "epoch": 0.78,
      "eval_bleu": 25.4863,
      "eval_gen_len": 19.1908,
      "eval_loss": 1.1629722118377686,
      "eval_runtime": 599.5574,
      "eval_samples_per_second": 12.844,
      "eval_steps_per_second": 0.804,
      "step": 3000
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.58126144988223e-05,
      "loss": 1.1636,
      "step": 3500
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.515833551426328e-05,
      "loss": 1.1243,
      "step": 4000
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.450405652970427e-05,
      "loss": 0.9449,
      "step": 4500
    },
    {
      "epoch": 1.17,
      "eval_bleu": 27.385,
      "eval_gen_len": 18.2955,
      "eval_loss": 1.112542748451233,
      "eval_runtime": 534.7746,
      "eval_samples_per_second": 14.4,
      "eval_steps_per_second": 0.901,
      "step": 4500
    },
    {
      "epoch": 1.3,
      "learning_rate": 4.3849777545145253e-05,
      "loss": 0.8708,
      "step": 5000
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.3195498560586236e-05,
      "loss": 0.8446,
      "step": 5500
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.254121957602722e-05,
      "loss": 0.8102,
      "step": 6000
    },
    {
      "epoch": 1.56,
      "eval_bleu": 28.0041,
      "eval_gen_len": 18.6572,
      "eval_loss": 1.0919792652130127,
      "eval_runtime": 549.0767,
      "eval_samples_per_second": 14.025,
      "eval_steps_per_second": 0.878,
      "step": 6000
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.18869405914682e-05,
      "loss": 0.7903,
      "step": 6500
    },
    {
      "epoch": 1.82,
      "learning_rate": 4.123266160690919e-05,
      "loss": 0.7814,
      "step": 7000
    },
    {
      "epoch": 1.95,
      "learning_rate": 4.057838262235017e-05,
      "loss": 0.7692,
      "step": 7500
    },
    {
      "epoch": 1.95,
      "eval_bleu": 29.1055,
      "eval_gen_len": 18.2731,
      "eval_loss": 1.0819282531738281,
      "eval_runtime": 529.4168,
      "eval_samples_per_second": 14.546,
      "eval_steps_per_second": 0.91,
      "step": 7500
    }
  ],
  "logging_steps": 500,
  "max_steps": 38510,
  "num_train_epochs": 10,
  "save_steps": 1500,
  "total_flos": 2.6015959411274547e+17,
  "trial_name": null,
  "trial_params": null
}