{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 13.358778625954198,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.997131659661479,
      "eval_f1": 0.8895705521472393,
      "eval_loss": 0.009798307903110981,
      "eval_precision": 0.8787878787878788,
      "eval_recall": 0.9006211180124224,
      "eval_runtime": 3.3311,
      "eval_samples_per_second": 58.839,
      "eval_steps_per_second": 19.813,
      "step": 262
    },
    {
      "epoch": 1.91,
      "learning_rate": 4.3638676844783716e-05,
      "loss": 0.025,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9961092809269567,
      "eval_f1": 0.8698224852071005,
      "eval_loss": 0.012325258925557137,
      "eval_precision": 0.8305084745762712,
      "eval_recall": 0.9130434782608695,
      "eval_runtime": 3.3373,
      "eval_samples_per_second": 58.731,
      "eval_steps_per_second": 19.777,
      "step": 524
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.997529251391571,
      "eval_f1": 0.911854103343465,
      "eval_loss": 0.009376761503517628,
      "eval_precision": 0.8928571428571429,
      "eval_recall": 0.9316770186335404,
      "eval_runtime": 3.3106,
      "eval_samples_per_second": 59.204,
      "eval_steps_per_second": 19.936,
      "step": 786
    },
    {
      "epoch": 3.82,
      "learning_rate": 3.727735368956743e-05,
      "loss": 0.0038,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9979552425309554,
      "eval_f1": 0.9040247678018576,
      "eval_loss": 0.012460124678909779,
      "eval_precision": 0.9012345679012346,
      "eval_recall": 0.906832298136646,
      "eval_runtime": 3.3015,
      "eval_samples_per_second": 59.366,
      "eval_steps_per_second": 19.991,
      "step": 1048
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9979552425309554,
      "eval_f1": 0.9158878504672897,
      "eval_loss": 0.015555150806903839,
      "eval_precision": 0.91875,
      "eval_recall": 0.9130434782608695,
      "eval_runtime": 3.3159,
      "eval_samples_per_second": 59.11,
      "eval_steps_per_second": 19.904,
      "step": 1310
    },
    {
      "epoch": 5.73,
      "learning_rate": 3.091603053435115e-05,
      "loss": 0.0014,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9967624673406793,
      "eval_f1": 0.8823529411764706,
      "eval_loss": 0.010931872762739658,
      "eval_precision": 0.8379888268156425,
      "eval_recall": 0.9316770186335404,
      "eval_runtime": 3.3009,
      "eval_samples_per_second": 59.378,
      "eval_steps_per_second": 19.995,
      "step": 1572
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9976712484380325,
      "eval_f1": 0.9040247678018576,
      "eval_loss": 0.01918826997280121,
      "eval_precision": 0.9012345679012346,
      "eval_recall": 0.906832298136646,
      "eval_runtime": 3.2926,
      "eval_samples_per_second": 59.527,
      "eval_steps_per_second": 20.045,
      "step": 1834
    },
    {
      "epoch": 7.63,
      "learning_rate": 2.455470737913486e-05,
      "loss": 0.0013,
      "step": 2000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9973872543451097,
      "eval_f1": 0.8834355828220859,
      "eval_loss": 0.018581125885248184,
      "eval_precision": 0.8727272727272727,
      "eval_recall": 0.8944099378881988,
      "eval_runtime": 3.2987,
      "eval_samples_per_second": 59.418,
      "eval_steps_per_second": 20.008,
      "step": 2096
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9975576508008633,
      "eval_f1": 0.9074074074074073,
      "eval_loss": 0.015939556062221527,
      "eval_precision": 0.901840490797546,
      "eval_recall": 0.9130434782608695,
      "eval_runtime": 3.3214,
      "eval_samples_per_second": 59.012,
      "eval_steps_per_second": 19.871,
      "step": 2358
    },
    {
      "epoch": 9.54,
      "learning_rate": 1.8193384223918574e-05,
      "loss": 0.0006,
      "step": 2500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9977564466659093,
      "eval_f1": 0.91875,
      "eval_loss": 0.016953356564044952,
      "eval_precision": 0.9245283018867925,
      "eval_recall": 0.9130434782608695,
      "eval_runtime": 3.2768,
      "eval_samples_per_second": 59.814,
      "eval_steps_per_second": 20.141,
      "step": 2620
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9978700443030785,
      "eval_f1": 0.9216300940438872,
      "eval_loss": 0.018505336716771126,
      "eval_precision": 0.930379746835443,
      "eval_recall": 0.9130434782608695,
      "eval_runtime": 3.2933,
      "eval_samples_per_second": 59.514,
      "eval_steps_per_second": 20.041,
      "step": 2882
    },
    {
      "epoch": 11.45,
      "learning_rate": 1.1832061068702292e-05,
      "loss": 0.0005,
      "step": 3000
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.997728047256617,
      "eval_f1": 0.891640866873065,
      "eval_loss": 0.018725045025348663,
      "eval_precision": 0.8888888888888888,
      "eval_recall": 0.8944099378881988,
      "eval_runtime": 3.2924,
      "eval_samples_per_second": 59.53,
      "eval_steps_per_second": 20.046,
      "step": 3144
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9977564466659093,
      "eval_f1": 0.9135802469135801,
      "eval_loss": 0.016803989186882973,
      "eval_precision": 0.9079754601226994,
      "eval_recall": 0.9192546583850931,
      "eval_runtime": 3.31,
      "eval_samples_per_second": 59.214,
      "eval_steps_per_second": 19.939,
      "step": 3406
    },
    {
      "epoch": 13.36,
      "learning_rate": 5.470737913486006e-06,
      "loss": 0.0004,
      "step": 3500
    }
  ],
  "max_steps": 3930,
  "num_train_epochs": 15,
  "total_flos": 1791356389066944.0,
  "trial_name": null,
  "trial_params": null
}