{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.00010077985004622052,
      "loss": 0.5399,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010077565027123787,
      "loss": 0.4951,
      "step": 1000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010076865093411392,
      "loss": 0.487,
      "step": 1500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010075885246660077,
      "loss": 0.4806,
      "step": 2000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010074625547311406,
      "loss": 0.4778,
      "step": 2500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010073086073069567,
      "loss": 0.4747,
      "step": 3000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010071266918896582,
      "loss": 0.4732,
      "step": 3500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001006916819700645,
      "loss": 0.4724,
      "step": 4000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010066790036858225,
      "loss": 0.4708,
      "step": 4500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010064132585148025,
      "loss": 0.4677,
      "step": 5000
    },
    {
      "epoch": 0.03,
      "eval_loss": 0.4321456551551819,
      "eval_runtime": 334.7353,
      "eval_samples_per_second": 128.46,
      "eval_steps_per_second": 2.008,
      "step": 5000
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001006119600579999,
      "loss": 0.4673,
      "step": 5500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010057980479956167,
      "loss": 0.4649,
      "step": 6000
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010054486205965335,
      "loss": 0.465,
      "step": 6500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00010050713399370776,
      "loss": 0.4644,
      "step": 7000
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00010046662292896969,
      "loss": 0.4639,
      "step": 7500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00010042342072067417,
      "loss": 0.4624,
      "step": 8000
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00010037735687948529,
      "loss": 0.463,
      "step": 8500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00010032851804476767,
      "loss": 0.4606,
      "step": 9000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010027690722913066,
      "loss": 0.4595,
      "step": 9500
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010022263913645699,
      "loss": 0.4605,
      "step": 10000
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.42437314987182617,
      "eval_runtime": 366.557,
      "eval_samples_per_second": 117.308,
      "eval_steps_per_second": 1.833,
      "step": 10000
    }
  ],
  "max_steps": 200000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 2.354930673647616e+20,
  "trial_name": null,
  "trial_params": null
}