{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 50.0,
  "eval_steps": 500,
  "global_step": 4700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.32,
      "learning_rate": 4.468085106382979e-05,
      "loss": 1.1017,
      "step": 500
    },
    {
      "epoch": 10.64,
      "learning_rate": 3.936170212765958e-05,
      "loss": 0.1281,
      "step": 1000
    },
    {
      "epoch": 15.96,
      "learning_rate": 3.4042553191489365e-05,
      "loss": 0.0555,
      "step": 1500
    },
    {
      "epoch": 21.28,
      "learning_rate": 2.8723404255319154e-05,
      "loss": 0.027,
      "step": 2000
    },
    {
      "epoch": 26.6,
      "learning_rate": 2.340425531914894e-05,
      "loss": 0.0195,
      "step": 2500
    },
    {
      "epoch": 31.91,
      "learning_rate": 1.8085106382978724e-05,
      "loss": 0.0135,
      "step": 3000
    },
    {
      "epoch": 37.23,
      "learning_rate": 1.2765957446808511e-05,
      "loss": 0.0103,
      "step": 3500
    },
    {
      "epoch": 42.55,
      "learning_rate": 7.446808510638298e-06,
      "loss": 0.0173,
      "step": 4000
    },
    {
      "epoch": 47.87,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 0.0432,
      "step": 4500
    },
    {
      "epoch": 50.0,
      "step": 4700,
      "total_flos": 2.93958851328e+16,
      "train_loss": 0.1556171702324076,
      "train_runtime": 1356.8935,
      "train_samples_per_second": 110.547,
      "train_steps_per_second": 3.464
    }
  ],
  "logging_steps": 500,
  "max_steps": 4700,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 2.93958851328e+16,
  "trial_name": null,
  "trial_params": null
}