{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9996689837802052,
  "global_step": 755,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 9.646539027982328e-06,
      "loss": 1.6198,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_accuracy": 0.48936170212765956,
      "eval_auprc": 55.57425088347365,
      "eval_loss": 1.3871960639953613,
      "eval_micro f1 score": 48.93617021276596,
      "eval_runtime": 2.5438,
      "eval_samples_per_second": 92.382,
      "eval_steps_per_second": 5.897,
      "step": 100
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.17378497790869e-06,
      "loss": 0.6603,
      "step": 200
    },
    {
      "epoch": 0.26,
      "eval_accuracy": 0.6595744680851063,
      "eval_auprc": 62.87589308944976,
      "eval_loss": 0.9248737692832947,
      "eval_micro f1 score": 65.95744680851064,
      "eval_runtime": 2.5393,
      "eval_samples_per_second": 92.545,
      "eval_steps_per_second": 5.907,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.701030927835052e-06,
      "loss": 0.5387,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_accuracy": 0.7319148936170212,
      "eval_auprc": 71.1935721229021,
      "eval_loss": 0.7262066602706909,
      "eval_micro f1 score": 73.19148936170212,
      "eval_runtime": 2.5398,
      "eval_samples_per_second": 92.525,
      "eval_steps_per_second": 5.906,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.228276877761414e-06,
      "loss": 0.4801,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_accuracy": 0.7404255319148936,
      "eval_auprc": 68.860583531235,
      "eval_loss": 0.6623471975326538,
      "eval_micro f1 score": 74.04255319148936,
      "eval_runtime": 2.5388,
      "eval_samples_per_second": 92.563,
      "eval_steps_per_second": 5.908,
      "step": 400
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.7555228276877766e-06,
      "loss": 0.4597,
      "step": 500
    },
    {
      "epoch": 0.66,
      "eval_accuracy": 0.7617021276595745,
      "eval_auprc": 75.73457801993634,
      "eval_loss": 0.6092124581336975,
      "eval_micro f1 score": 76.17021276595744,
      "eval_runtime": 2.5484,
      "eval_samples_per_second": 92.215,
      "eval_steps_per_second": 5.886,
      "step": 500
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2827687776141384e-06,
      "loss": 0.4217,
      "step": 600
    },
    {
      "epoch": 0.79,
      "eval_accuracy": 0.7872340425531915,
      "eval_auprc": 76.87089001906547,
      "eval_loss": 0.5928928852081299,
      "eval_micro f1 score": 78.72340425531915,
      "eval_runtime": 2.5389,
      "eval_samples_per_second": 92.559,
      "eval_steps_per_second": 5.908,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 8.100147275405009e-07,
      "loss": 0.4148,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_accuracy": 0.8,
      "eval_auprc": 77.0281671357332,
      "eval_loss": 0.5671084523200989,
      "eval_micro f1 score": 80.00000000000001,
      "eval_runtime": 2.5376,
      "eval_samples_per_second": 92.609,
      "eval_steps_per_second": 5.911,
      "step": 700
    },
    {
      "epoch": 1.0,
      "step": 755,
      "total_flos": 4.503229282615296e+16,
      "train_loss": 0.6395634657499806,
      "train_runtime": 1631.1404,
      "train_samples_per_second": 29.628,
      "train_steps_per_second": 0.463
    }
  ],
  "max_steps": 755,
  "num_train_epochs": 1,
  "total_flos": 4.503229282615296e+16,
  "trial_name": null,
  "trial_params": null
}