{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.29,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.5249,
      "step": 50
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.5264,
      "step": 100
    },
    {
      "epoch": 0.86,
      "learning_rate": 3e-06,
      "loss": 0.521,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7685714285714286,
      "eval_f1": 0.8691437802907915,
      "eval_loss": 0.5161310434341431,
      "eval_runtime": 11.1188,
      "eval_samples_per_second": 62.957,
      "eval_steps_per_second": 3.957,
      "step": 175
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5021,
      "step": 200
    },
    {
      "epoch": 1.43,
      "learning_rate": 5e-06,
      "loss": 0.5169,
      "step": 250
    },
    {
      "epoch": 1.71,
      "learning_rate": 6e-06,
      "loss": 0.5231,
      "step": 300
    },
    {
      "epoch": 2.0,
      "learning_rate": 7e-06,
      "loss": 0.5115,
      "step": 350
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7757142857142857,
      "eval_f1": 0.8726682887266829,
      "eval_loss": 0.5628861784934998,
      "eval_runtime": 17.6371,
      "eval_samples_per_second": 39.689,
      "eval_steps_per_second": 2.495,
      "step": 350
    }
  ],
  "logging_steps": 50,
  "max_steps": 525,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 741817432473600.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}