checkpoint-850/trainer_state.json

{
  "best_metric": 0.991941391941392,
  "best_model_checkpoint": "A-POR-LOS-8000/distilhubert-finetuned-cry-detector/checkpoint-597",
  "epoch": 9.956076134699854,
  "eval_steps": 500,
  "global_step": 850,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9956076134699854,
      "eval_accuracy": 0.9538461538461539,
      "eval_f1": 0.9535883665206972,
      "eval_loss": 0.11965569853782654,
      "eval_precision": 0.9535470731605858,
      "eval_recall": 0.9538461538461539,
      "eval_runtime": 5.8661,
      "eval_samples_per_second": 232.691,
      "eval_steps_per_second": 29.15,
      "step": 85
    },
    {
      "epoch": 1.9912152269399708,
      "eval_accuracy": 0.9831501831501831,
      "eval_f1": 0.983143153392684,
      "eval_loss": 0.060115572065114975,
      "eval_precision": 0.9831374404084774,
      "eval_recall": 0.9831501831501831,
      "eval_runtime": 5.9254,
      "eval_samples_per_second": 230.365,
      "eval_steps_per_second": 28.859,
      "step": 170
    },
    {
      "epoch": 2.998535871156662,
      "eval_accuracy": 0.9868131868131869,
      "eval_f1": 0.9868241092241091,
      "eval_loss": 0.05060575157403946,
      "eval_precision": 0.9868403029537207,
      "eval_recall": 0.9868131868131869,
      "eval_runtime": 5.9299,
      "eval_samples_per_second": 230.189,
      "eval_steps_per_second": 28.837,
      "step": 256
    },
    {
      "epoch": 3.994143484626647,
      "eval_accuracy": 0.9860805860805861,
      "eval_f1": 0.9861535269385863,
      "eval_loss": 0.04610973969101906,
      "eval_precision": 0.986445121171901,
      "eval_recall": 0.9860805860805861,
      "eval_runtime": 5.9428,
      "eval_samples_per_second": 229.69,
      "eval_steps_per_second": 28.774,
      "step": 341
    },
    {
      "epoch": 4.989751098096632,
      "eval_accuracy": 0.989010989010989,
      "eval_f1": 0.9890246085529585,
      "eval_loss": 0.0438910573720932,
      "eval_precision": 0.989050109460552,
      "eval_recall": 0.989010989010989,
      "eval_runtime": 5.937,
      "eval_samples_per_second": 229.913,
      "eval_steps_per_second": 28.802,
      "step": 426
    },
    {
      "epoch": 5.856515373352855,
      "grad_norm": 0.08060992509126663,
      "learning_rate": 1.0917042498003083e-05,
      "loss": 0.0779,
      "step": 500
    },
    {
      "epoch": 5.997071742313324,
      "eval_accuracy": 0.9904761904761905,
      "eval_f1": 0.9904879940792306,
      "eval_loss": 0.0396205335855484,
      "eval_precision": 0.9905117057078526,
      "eval_recall": 0.9904761904761905,
      "eval_runtime": 5.9047,
      "eval_samples_per_second": 231.172,
      "eval_steps_per_second": 28.96,
      "step": 512
    },
    {
      "epoch": 6.992679355783309,
      "eval_accuracy": 0.991941391941392,
      "eval_f1": 0.9919447375447602,
      "eval_loss": 0.035047151148319244,
      "eval_precision": 0.9919494135494136,
      "eval_recall": 0.991941391941392,
      "eval_runtime": 6.0502,
      "eval_samples_per_second": 225.612,
      "eval_steps_per_second": 28.264,
      "step": 597
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9912087912087912,
      "eval_f1": 0.9912160728160728,
      "eval_loss": 0.03350323066115379,
      "eval_precision": 0.9912286614059304,
      "eval_recall": 0.9912087912087912,
      "eval_runtime": 5.79,
      "eval_samples_per_second": 235.751,
      "eval_steps_per_second": 29.534,
      "step": 683
    },
    {
      "epoch": 8.995607613469986,
      "eval_accuracy": 0.9912087912087912,
      "eval_f1": 0.9912160728160728,
      "eval_loss": 0.03368490934371948,
      "eval_precision": 0.9912286614059304,
      "eval_recall": 0.9912087912087912,
      "eval_runtime": 5.7784,
      "eval_samples_per_second": 236.224,
      "eval_steps_per_second": 29.593,
      "step": 768
    },
    {
      "epoch": 9.956076134699854,
      "eval_accuracy": 0.9912087912087912,
      "eval_f1": 0.9912160728160728,
      "eval_loss": 0.03377429023385048,
      "eval_precision": 0.9912286614059304,
      "eval_recall": 0.9912087912087912,
      "eval_runtime": 5.7829,
      "eval_samples_per_second": 236.039,
      "eval_steps_per_second": 29.57,
      "step": 850
    }
  ],
  "logging_steps": 500,
  "max_steps": 850,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.23633370170624e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}