trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 13.157894736842104,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.32,
      "eval_accuracy": 0.7606798346348186,
      "eval_f1": 0.7277096851718338,
      "eval_loss": 0.9062727689743042,
      "eval_precision": 0.7006015733456733,
      "eval_recall": 0.757,
      "eval_runtime": 3.59,
      "eval_samples_per_second": 15.042,
      "eval_steps_per_second": 1.114,
      "step": 50
    },
    {
      "epoch": 2.63,
      "eval_accuracy": 0.7967386311437759,
      "eval_f1": 0.8242074927953891,
      "eval_loss": 0.6386759281158447,
      "eval_precision": 0.7929759704251387,
      "eval_recall": 0.858,
      "eval_runtime": 3.6147,
      "eval_samples_per_second": 14.939,
      "eval_steps_per_second": 1.107,
      "step": 100
    },
    {
      "epoch": 3.95,
      "eval_accuracy": 0.825447864033073,
      "eval_f1": 0.8485576923076923,
      "eval_loss": 0.5691221356391907,
      "eval_precision": 0.8171296296296297,
      "eval_recall": 0.8825,
      "eval_runtime": 3.5957,
      "eval_samples_per_second": 15.018,
      "eval_steps_per_second": 1.112,
      "step": 150
    },
    {
      "epoch": 5.26,
      "eval_accuracy": 0.822347266881029,
      "eval_f1": 0.8555474629764507,
      "eval_loss": 0.5723332166671753,
      "eval_precision": 0.831524303916942,
      "eval_recall": 0.881,
      "eval_runtime": 3.6337,
      "eval_samples_per_second": 14.861,
      "eval_steps_per_second": 1.101,
      "step": 200
    },
    {
      "epoch": 6.58,
      "eval_accuracy": 0.8292374827744603,
      "eval_f1": 0.8729388942774006,
      "eval_loss": 0.5896942019462585,
      "eval_precision": 0.847457627118644,
      "eval_recall": 0.9,
      "eval_runtime": 3.5978,
      "eval_samples_per_second": 15.009,
      "eval_steps_per_second": 1.112,
      "step": 250
    },
    {
      "epoch": 7.89,
      "eval_accuracy": 0.8283187873220027,
      "eval_f1": 0.874515503875969,
      "eval_loss": 0.6122345924377441,
      "eval_precision": 0.8482142857142857,
      "eval_recall": 0.9025,
      "eval_runtime": 3.5423,
      "eval_samples_per_second": 15.244,
      "eval_steps_per_second": 1.129,
      "step": 300
    },
    {
      "epoch": 9.21,
      "eval_accuracy": 0.8392282958199357,
      "eval_f1": 0.8740884783665532,
      "eval_loss": 0.6045289635658264,
      "eval_precision": 0.8505203405865658,
      "eval_recall": 0.899,
      "eval_runtime": 3.5491,
      "eval_samples_per_second": 15.215,
      "eval_steps_per_second": 1.127,
      "step": 350
    },
    {
      "epoch": 10.53,
      "eval_accuracy": 0.8446256316031235,
      "eval_f1": 0.8851733464470125,
      "eval_loss": 0.5662067532539368,
      "eval_precision": 0.8708272859216255,
      "eval_recall": 0.9,
      "eval_runtime": 3.6229,
      "eval_samples_per_second": 14.905,
      "eval_steps_per_second": 1.104,
      "step": 400
    },
    {
      "epoch": 11.84,
      "eval_accuracy": 0.843706936150666,
      "eval_f1": 0.888943488943489,
      "eval_loss": 0.5973214507102966,
      "eval_precision": 0.8739130434782608,
      "eval_recall": 0.9045,
      "eval_runtime": 3.6244,
      "eval_samples_per_second": 14.899,
      "eval_steps_per_second": 1.104,
      "step": 450
    },
    {
      "epoch": 13.16,
      "learning_rate": 0.0,
      "loss": 0.4305,
      "step": 500
    },
    {
      "epoch": 13.16,
      "eval_accuracy": 0.843706936150666,
      "eval_f1": 0.8903638151425762,
      "eval_loss": 0.6187416911125183,
      "eval_precision": 0.875725338491296,
      "eval_recall": 0.9055,
      "eval_runtime": 3.6234,
      "eval_samples_per_second": 14.903,
      "eval_steps_per_second": 1.104,
      "step": 500
    },
    {
      "epoch": 13.16,
      "step": 500,
      "total_flos": 520356947539968.0,
      "train_loss": 0.43045907592773436,
      "train_runtime": 334.1747,
      "train_samples_per_second": 5.985,
      "train_steps_per_second": 1.496
    }
  ],
  "max_steps": 500,
  "num_train_epochs": 14,
  "total_flos": 520356947539968.0,
  "trial_name": null,
  "trial_params": null
}