checkpoint-768/trainer_state.json

{
  "best_metric": 0.9926739926739927,
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
  "epoch": 8.995607613469986,
  "eval_steps": 500,
  "global_step": 768,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9956076134699854,
      "eval_accuracy": 0.9772893772893773,
      "eval_loss": 0.06922276318073273,
      "eval_runtime": 15.5305,
      "eval_samples_per_second": 87.892,
      "eval_steps_per_second": 11.011,
      "step": 85
    },
    {
      "epoch": 1.9912152269399708,
      "eval_accuracy": 0.9860805860805861,
      "eval_loss": 0.04661192744970322,
      "eval_runtime": 15.4605,
      "eval_samples_per_second": 88.29,
      "eval_steps_per_second": 11.06,
      "step": 170
    },
    {
      "epoch": 2.998535871156662,
      "eval_accuracy": 0.9853479853479854,
      "eval_loss": 0.04894961416721344,
      "eval_runtime": 15.5622,
      "eval_samples_per_second": 87.713,
      "eval_steps_per_second": 10.988,
      "step": 256
    },
    {
      "epoch": 3.994143484626647,
      "eval_accuracy": 0.9897435897435898,
      "eval_loss": 0.04228556528687477,
      "eval_runtime": 15.6217,
      "eval_samples_per_second": 87.378,
      "eval_steps_per_second": 10.946,
      "step": 341
    },
    {
      "epoch": 4.989751098096632,
      "eval_accuracy": 0.991941391941392,
      "eval_loss": 0.044283464550971985,
      "eval_runtime": 15.0667,
      "eval_samples_per_second": 90.597,
      "eval_steps_per_second": 11.35,
      "step": 426
    },
    {
      "epoch": 5.856515373352855,
      "grad_norm": 0.008579956367611885,
      "learning_rate": 3.639014166001028e-05,
      "loss": 0.055,
      "step": 500
    },
    {
      "epoch": 5.997071742313324,
      "eval_accuracy": 0.9926739926739927,
      "eval_loss": 0.04338795691728592,
      "eval_runtime": 14.898,
      "eval_samples_per_second": 91.623,
      "eval_steps_per_second": 11.478,
      "step": 512
    },
    {
      "epoch": 6.992679355783309,
      "eval_accuracy": 0.9926739926739927,
      "eval_loss": 0.04399614781141281,
      "eval_runtime": 15.2426,
      "eval_samples_per_second": 89.552,
      "eval_steps_per_second": 11.219,
      "step": 597
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9926739926739927,
      "eval_loss": 0.045955102890729904,
      "eval_runtime": 15.1372,
      "eval_samples_per_second": 90.175,
      "eval_steps_per_second": 11.297,
      "step": 683
    },
    {
      "epoch": 8.995607613469986,
      "eval_accuracy": 0.9926739926739927,
      "eval_loss": 0.04587433487176895,
      "eval_runtime": 15.0807,
      "eval_samples_per_second": 90.513,
      "eval_steps_per_second": 11.339,
      "step": 768
    }
  ],
  "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": 1.1175306839424e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}