{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 49.08151093439364,
  "eval_steps": 500,
  "global_step": 2050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.04,
      "learning_rate": 7.952286282306164e-06,
      "loss": 1.3337,
      "step": 100
    },
    {
      "epoch": 4.07,
      "learning_rate": 1.590457256461233e-05,
      "loss": 0.8617,
      "step": 200
    },
    {
      "epoch": 7.03,
      "learning_rate": 2.385685884691849e-05,
      "loss": 0.6369,
      "step": 300
    },
    {
      "epoch": 9.06,
      "learning_rate": 3.180914512922466e-05,
      "loss": 0.4558,
      "step": 400
    },
    {
      "epoch": 12.02,
      "learning_rate": 3.976143141153082e-05,
      "loss": 0.387,
      "step": 500
    },
    {
      "epoch": 14.05,
      "learning_rate": 4.771371769383698e-05,
      "loss": 0.3572,
      "step": 600
    },
    {
      "epoch": 17.01,
      "learning_rate": 5.5666003976143144e-05,
      "loss": 0.3346,
      "step": 700
    },
    {
      "epoch": 19.04,
      "learning_rate": 6.361829025844931e-05,
      "loss": 0.303,
      "step": 800
    },
    {
      "epoch": 21.08,
      "learning_rate": 7.157057654075548e-05,
      "loss": 0.27,
      "step": 900
    },
    {
      "epoch": 24.03,
      "learning_rate": 7.952286282306164e-05,
      "loss": 0.2308,
      "step": 1000
    },
    {
      "epoch": 26.07,
      "learning_rate": 8.74751491053678e-05,
      "loss": 0.1975,
      "step": 1100
    },
    {
      "epoch": 29.02,
      "learning_rate": 9.542743538767396e-05,
      "loss": 0.1629,
      "step": 1200
    },
    {
      "epoch": 31.06,
      "learning_rate": 0.00010337972166998014,
      "loss": 0.135,
      "step": 1300
    },
    {
      "epoch": 34.01,
      "learning_rate": 0.00011133200795228629,
      "loss": 0.1107,
      "step": 1400
    },
    {
      "epoch": 36.05,
      "learning_rate": 0.00011928429423459244,
      "loss": 0.0906,
      "step": 1500
    },
    {
      "epoch": 39.0,
      "learning_rate": 0.00012723658051689863,
      "loss": 0.0771,
      "step": 1600
    },
    {
      "epoch": 41.04,
      "learning_rate": 0.00013518886679920477,
      "loss": 0.0613,
      "step": 1700
    },
    {
      "epoch": 43.07,
      "learning_rate": 0.00014314115308151096,
      "loss": 0.0525,
      "step": 1800
    },
    {
      "epoch": 46.03,
      "learning_rate": 0.0001510934393638171,
      "loss": 0.0399,
      "step": 1900
    },
    {
      "epoch": 48.06,
      "learning_rate": 0.0001590457256461233,
      "loss": 0.031,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 25150,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 3.333067074699264e+17,
  "trial_name": null,
  "trial_params": null
}