{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.34782608695652173,
  "eval_steps": 2,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "grad_norm": 0.4166610439239046,
      "learning_rate": 2e-05,
      "loss": 0.9332,
      "step": 1
    },
    {
      "epoch": 0.17,
      "eval_loss": 1.0365231037139893,
      "eval_runtime": 11.8979,
      "eval_samples_per_second": 1.681,
      "eval_steps_per_second": 0.84,
      "step": 1
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.42192077388393007,
      "learning_rate": 4e-05,
      "loss": 0.9677,
      "step": 2
    },
    {
      "epoch": 0.35,
      "eval_loss": 1.0336682796478271,
      "eval_runtime": 11.9106,
      "eval_samples_per_second": 1.679,
      "eval_steps_per_second": 0.84,
      "step": 2
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "total_flos": 4.076330697306931e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}