checkpoint-102/trainer_state.json

{
  "best_metric": 0.9950980392156863,
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-102",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 102,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9411764705882353,
      "eval_accuracy": 0.9362745098039216,
      "eval_f1": 0.9365356058160116,
      "eval_loss": 0.19313116371631622,
      "eval_precision": 0.9372234219385678,
      "eval_recall": 0.9362745098039216,
      "eval_runtime": 3.0986,
      "eval_samples_per_second": 65.836,
      "eval_steps_per_second": 8.391,
      "step": 12
    },
    {
      "epoch": 1.9607843137254903,
      "eval_accuracy": 0.9705882352941176,
      "eval_f1": 0.9704025549613785,
      "eval_loss": 0.09495726972818375,
      "eval_precision": 0.971039759187257,
      "eval_recall": 0.9705882352941176,
      "eval_runtime": 3.1171,
      "eval_samples_per_second": 65.446,
      "eval_steps_per_second": 8.341,
      "step": 25
    },
    {
      "epoch": 2.980392156862745,
      "eval_accuracy": 0.9803921568627451,
      "eval_f1": 0.9803921568627451,
      "eval_loss": 0.06114682927727699,
      "eval_precision": 0.9803921568627451,
      "eval_recall": 0.9803921568627451,
      "eval_runtime": 3.2163,
      "eval_samples_per_second": 63.428,
      "eval_steps_per_second": 8.084,
      "step": 38
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9852941176470589,
      "eval_f1": 0.9852722698274712,
      "eval_loss": 0.049169763922691345,
      "eval_precision": 0.9853018065952722,
      "eval_recall": 0.9852941176470589,
      "eval_runtime": 3.1223,
      "eval_samples_per_second": 65.336,
      "eval_steps_per_second": 8.327,
      "step": 51
    },
    {
      "epoch": 4.9411764705882355,
      "eval_accuracy": 0.9803921568627451,
      "eval_f1": 0.9804969685242518,
      "eval_loss": 0.05879249796271324,
      "eval_precision": 0.9813976872800402,
      "eval_recall": 0.9803921568627451,
      "eval_runtime": 3.1449,
      "eval_samples_per_second": 64.868,
      "eval_steps_per_second": 8.267,
      "step": 63
    },
    {
      "epoch": 5.96078431372549,
      "eval_accuracy": 0.9852941176470589,
      "eval_f1": 0.9853150765112866,
      "eval_loss": 0.03680075705051422,
      "eval_precision": 0.9853868369053048,
      "eval_recall": 0.9852941176470589,
      "eval_runtime": 3.1698,
      "eval_samples_per_second": 64.358,
      "eval_steps_per_second": 8.203,
      "step": 76
    },
    {
      "epoch": 6.980392156862745,
      "eval_accuracy": 0.9901960784313726,
      "eval_f1": 0.9901663478316141,
      "eval_loss": 0.0382298119366169,
      "eval_precision": 0.9903446226975638,
      "eval_recall": 0.9901960784313726,
      "eval_runtime": 3.1376,
      "eval_samples_per_second": 65.019,
      "eval_steps_per_second": 8.287,
      "step": 89
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9950980392156863,
      "eval_f1": 0.995090756609157,
      "eval_loss": 0.03175761550664902,
      "eval_precision": 0.995135458763658,
      "eval_recall": 0.9950980392156863,
      "eval_runtime": 2.949,
      "eval_samples_per_second": 69.175,
      "eval_steps_per_second": 8.816,
      "step": 102
    }
  ],
  "logging_steps": 500,
  "max_steps": 120,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.052064945063383e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}