{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4282655246252677,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "grad_norm": 1.5055365562438965,
      "learning_rate": 0.00017500656274610298,
      "loss": 1.6705,
      "step": 100
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.7729685306549072,
      "learning_rate": 0.00015000562521094542,
      "loss": 1.202,
      "step": 200
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.4488734006881714,
      "learning_rate": 0.00012500468767578783,
      "loss": 1.1679,
      "step": 300
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.3242661952972412,
      "learning_rate": 0.00010000375014063029,
      "loss": 1.1291,
      "step": 400
    },
    {
      "epoch": 0.43,
      "grad_norm": 2.925776243209839,
      "learning_rate": 7.500281260547271e-05,
      "loss": 1.0938,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 5401654585147392.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}