{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7863522686673812,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 9.825589706933525e-05,
      "loss": 2.1183,
      "step": 500
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.646890636168693e-05,
      "loss": 1.8604,
      "step": 1000
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.46819156540386e-05,
      "loss": 1.7038,
      "step": 1500
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.289492494639028e-05,
      "loss": 1.5787,
      "step": 2000
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.110793423874197e-05,
      "loss": 1.4618,
      "step": 2500
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.932094353109363e-05,
      "loss": 1.3833,
      "step": 3000
    },
    {
      "epoch": 0.63,
      "learning_rate": 8.753395282344532e-05,
      "loss": 1.3247,
      "step": 3500
    },
    {
      "epoch": 0.71,
      "learning_rate": 8.5746962115797e-05,
      "loss": 1.2699,
      "step": 4000
    },
    {
      "epoch": 0.8,
      "learning_rate": 8.395997140814869e-05,
      "loss": 1.2196,
      "step": 4500
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.217298070050035e-05,
      "loss": 1.1743,
      "step": 5000
    },
    {
      "epoch": 0.98,
      "learning_rate": 8.038598999285204e-05,
      "loss": 1.1334,
      "step": 5500
    },
    {
      "epoch": 1.07,
      "learning_rate": 7.859899928520372e-05,
      "loss": 1.0688,
      "step": 6000
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.681200857755541e-05,
      "loss": 1.0209,
      "step": 6500
    },
    {
      "epoch": 1.25,
      "learning_rate": 7.502501786990707e-05,
      "loss": 1.0123,
      "step": 7000
    },
    {
      "epoch": 1.34,
      "learning_rate": 7.323802716225876e-05,
      "loss": 0.9964,
      "step": 7500
    },
    {
      "epoch": 1.43,
      "learning_rate": 7.145461043602574e-05,
      "loss": 0.9671,
      "step": 8000
    },
    {
      "epoch": 1.52,
      "learning_rate": 6.966761972837742e-05,
      "loss": 0.9496,
      "step": 8500
    },
    {
      "epoch": 1.61,
      "learning_rate": 6.788062902072909e-05,
      "loss": 0.9354,
      "step": 9000
    },
    {
      "epoch": 1.7,
      "learning_rate": 6.609363831308077e-05,
      "loss": 0.9291,
      "step": 9500
    },
    {
      "epoch": 1.79,
      "learning_rate": 6.430664760543246e-05,
      "loss": 0.9039,
      "step": 10000
    },
    {
      "epoch": 1.79,
      "eval_bleu": 4.2041,
      "eval_gen_len": 43.7816,
      "eval_loss": 0.9678672552108765,
      "eval_runtime": 1428.8589,
      "eval_samples_per_second": 6.25,
      "eval_steps_per_second": 0.196,
      "step": 10000
    }
  ],
  "max_steps": 27990,
  "num_train_epochs": 5,
  "total_flos": 2.16932586356736e+16,
  "trial_name": null,
  "trial_params": null
}