{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.333,
  "eval_steps": 500,
  "global_step": 333,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 9.166666666666665e-07,
      "loss": 4.8296,
      "step": 64
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.372340425531915e-07,
      "loss": 2.8446,
      "step": 128
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.691489361702127e-07,
      "loss": 2.0847,
      "step": 192
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.010638297872339e-07,
      "loss": 1.4821,
      "step": 256
    },
    {
      "epoch": 0.32,
      "learning_rate": 7.329787234042553e-07,
      "loss": 1.0742,
      "step": 320
    }
  ],
  "logging_steps": 64,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 333,
  "total_flos": 3.3986143420416e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}