checkpoint-680/trainer_state.json

{
  "best_metric": 0.9860805860805861,
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
  "epoch": 7.964860907759883,
  "eval_steps": 500,
  "global_step": 680,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9956076134699854,
      "eval_accuracy": 0.9641025641025641,
      "eval_f1": 0.9637911305761953,
      "eval_loss": 0.12035853415727615,
      "eval_precision": 0.9640509308043554,
      "eval_recall": 0.9641025641025641,
      "eval_runtime": 6.052,
      "eval_samples_per_second": 225.545,
      "eval_steps_per_second": 28.255,
      "step": 85
    },
    {
      "epoch": 1.9912152269399708,
      "eval_accuracy": 0.9772893772893773,
      "eval_f1": 0.9772624500008753,
      "eval_loss": 0.08473604917526245,
      "eval_precision": 0.9772470873644479,
      "eval_recall": 0.9772893772893773,
      "eval_runtime": 5.9068,
      "eval_samples_per_second": 231.09,
      "eval_steps_per_second": 28.95,
      "step": 170
    },
    {
      "epoch": 2.998535871156662,
      "eval_accuracy": 0.9765567765567765,
      "eval_f1": 0.9766464967450174,
      "eval_loss": 0.10245847702026367,
      "eval_precision": 0.9768621127754256,
      "eval_recall": 0.9765567765567765,
      "eval_runtime": 5.8911,
      "eval_samples_per_second": 231.706,
      "eval_steps_per_second": 29.027,
      "step": 256
    },
    {
      "epoch": 3.994143484626647,
      "eval_accuracy": 0.9831501831501831,
      "eval_f1": 0.9832333934847322,
      "eval_loss": 0.08685966581106186,
      "eval_precision": 0.9835305336122597,
      "eval_recall": 0.9831501831501831,
      "eval_runtime": 5.9568,
      "eval_samples_per_second": 229.152,
      "eval_steps_per_second": 28.707,
      "step": 341
    },
    {
      "epoch": 4.989751098096632,
      "eval_accuracy": 0.9831501831501831,
      "eval_f1": 0.983208365019189,
      "eval_loss": 0.07458490133285522,
      "eval_precision": 0.9833696765629429,
      "eval_recall": 0.9831501831501831,
      "eval_runtime": 5.9419,
      "eval_samples_per_second": 229.726,
      "eval_steps_per_second": 28.779,
      "step": 426
    },
    {
      "epoch": 5.856515373352855,
      "grad_norm": 0.01886621303856373,
      "learning_rate": 1.6360497736760383e-05,
      "loss": 0.0538,
      "step": 500
    },
    {
      "epoch": 5.997071742313324,
      "eval_accuracy": 0.9860805860805861,
      "eval_f1": 0.9860860332682386,
      "eval_loss": 0.08699370175600052,
      "eval_precision": 0.9860927746075414,
      "eval_recall": 0.9860805860805861,
      "eval_runtime": 5.9399,
      "eval_samples_per_second": 229.803,
      "eval_steps_per_second": 28.789,
      "step": 512
    },
    {
      "epoch": 6.992679355783309,
      "eval_accuracy": 0.9860805860805861,
      "eval_f1": 0.9860860332682386,
      "eval_loss": 0.08903729915618896,
      "eval_precision": 0.9860927746075414,
      "eval_recall": 0.9860805860805861,
      "eval_runtime": 5.9207,
      "eval_samples_per_second": 230.546,
      "eval_steps_per_second": 28.882,
      "step": 597
    },
    {
      "epoch": 7.964860907759883,
      "eval_accuracy": 0.9860805860805861,
      "eval_f1": 0.9860860332682386,
      "eval_loss": 0.08778514713048935,
      "eval_precision": 0.9860927746075414,
      "eval_recall": 0.9860805860805861,
      "eval_runtime": 5.9724,
      "eval_samples_per_second": 228.552,
      "eval_steps_per_second": 28.632,
      "step": 680
    }
  ],
  "logging_steps": 500,
  "max_steps": 680,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 9.8908515478272e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}