{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9361702127659575,
  "eval_steps": 500,
  "global_step": 11,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.425531914893617,
      "grad_norm": 1.024773359298706,
      "learning_rate": 0.00011423148382732853,
      "loss": 1.9309,
      "step": 5
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.823516845703125,
      "learning_rate": 4.050702638550275e-06,
      "loss": 1.7404,
      "step": 10
    },
    {
      "epoch": 0.9361702127659575,
      "step": 11,
      "total_flos": 3.077101885115597e+16,
      "train_loss": 1.816734324802052,
      "train_runtime": 262.6401,
      "train_samples_per_second": 2.829,
      "train_steps_per_second": 0.042
    }
  ],
  "logging_steps": 5,
  "max_steps": 11,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 3.077101885115597e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}