{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 6500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "grad_norm": 0.330968976020813,
      "learning_rate": 4.713640064133025e-05,
      "loss": 0.5246,
      "step": 1000
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.2416992038488388,
      "learning_rate": 3.920161866827889e-05,
      "loss": 0.4972,
      "step": 2000
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.2946712374687195,
      "learning_rate": 2.8013417006383076e-05,
      "loss": 0.4863,
      "step": 3000
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.23608818650245667,
      "learning_rate": 1.613487782393661e-05,
      "loss": 0.4863,
      "step": 4000
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.3215658962726593,
      "learning_rate": 6.28723129572247e-06,
      "loss": 0.4836,
      "step": 5000
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.649865984916687,
      "learning_rate": 7.293490622059501e-07,
      "loss": 0.4788,
      "step": 6000
    },
    {
      "epoch": 1.0,
      "step": 6500,
      "total_flos": 1.2227239808537395e+18,
      "train_loss": 0.49180243154672476,
      "train_runtime": 51363.0005,
      "train_samples_per_second": 0.506,
      "train_steps_per_second": 0.127
    }
  ],
  "logging_steps": 1000,
  "max_steps": 6500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 1.2227239808537395e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}