{
  "best_metric": NaN,
  "best_model_checkpoint": "/tmp/model/checkpoint-5",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.4,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.230769230769231e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1111111111111111,
      "eval_f1_macro": 0.03333333333333333,
      "eval_f1_micro": 0.1111111111111111,
      "eval_f1_weighted": 0.02222222222222222,
      "eval_loss": NaN,
      "eval_precision_macro": 0.018518518518518517,
      "eval_precision_micro": 0.1111111111111111,
      "eval_precision_weighted": 0.012345679012345678,
      "eval_recall_macro": 0.16666666666666666,
      "eval_recall_micro": 0.1111111111111111,
      "eval_recall_weighted": 0.1111111111111111,
      "eval_runtime": 9.0185,
      "eval_samples_per_second": 0.998,
      "eval_steps_per_second": 0.111,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 9861763782721536.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}