models/distil_bert_tuned_2/checkpoint-1815/trainer_state.json

{
  "best_metric": 0.841893952974485,
  "best_model_checkpoint": "models/distil_bert_tuned_2\\checkpoint-605",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1815,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.83,
      "learning_rate": 3.622589531680441e-05,
      "loss": 0.5698,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.806346525096525,
      "eval_f1": 0.841893952974485,
      "eval_loss": 0.5389575958251953,
      "eval_precision": 0.2502059873661082,
      "eval_recall": 0.6549245147375988,
      "eval_runtime": 507.9128,
      "eval_samples_per_second": 32.636,
      "eval_steps_per_second": 0.51,
      "step": 605
    },
    {
      "epoch": 1.65,
      "learning_rate": 2.2451790633608817e-05,
      "loss": 0.5006,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7526544401544402,
      "eval_f1": 0.805202705989081,
      "eval_loss": 0.5074611306190491,
      "eval_precision": 0.21915820029027577,
      "eval_recall": 0.7598849748382459,
      "eval_runtime": 533.6219,
      "eval_samples_per_second": 31.063,
      "eval_steps_per_second": 0.485,
      "step": 1210
    },
    {
      "epoch": 2.48,
      "learning_rate": 8.677685950413224e-06,
      "loss": 0.4526,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.781551640926641,
      "eval_f1": 0.8253061022873112,
      "eval_loss": 0.5698077082633972,
      "eval_precision": 0.23465016658733936,
      "eval_recall": 0.7088425593098491,
      "eval_runtime": 574.0732,
      "eval_samples_per_second": 28.874,
      "eval_steps_per_second": 0.451,
      "step": 1815
    }
  ],
  "logging_steps": 500,
  "max_steps": 1815,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "total_flos": 1290867116286204.0,
  "trial_name": null,
  "trial_params": null
}