checkpoint-512/trainer_state.json

{
  "best_metric": 0.991941391941392,
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-426",
  "epoch": 5.997071742313324,
  "eval_steps": 500,
  "global_step": 512,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9956076134699854,
      "eval_accuracy": 0.9787545787545787,
      "eval_f1": 0.9788275754377449,
      "eval_loss": 0.07363971322774887,
      "eval_precision": 0.9790028856592324,
      "eval_recall": 0.9787545787545787,
      "eval_runtime": 4.1234,
      "eval_samples_per_second": 331.041,
      "eval_steps_per_second": 41.471,
      "step": 85
    },
    {
      "epoch": 1.9912152269399708,
      "eval_accuracy": 0.9758241758241758,
      "eval_f1": 0.9760458977669253,
      "eval_loss": 0.0680176243185997,
      "eval_precision": 0.9770364666252971,
      "eval_recall": 0.9758241758241758,
      "eval_runtime": 3.9805,
      "eval_samples_per_second": 342.924,
      "eval_steps_per_second": 42.96,
      "step": 170
    },
    {
      "epoch": 2.998535871156662,
      "eval_accuracy": 0.9875457875457876,
      "eval_f1": 0.987550637300988,
      "eval_loss": 0.044689420610666275,
      "eval_precision": 0.9875567820840008,
      "eval_recall": 0.9875457875457876,
      "eval_runtime": 4.1011,
      "eval_samples_per_second": 332.839,
      "eval_steps_per_second": 41.696,
      "step": 256
    },
    {
      "epoch": 3.994143484626647,
      "eval_accuracy": 0.9904761904761905,
      "eval_f1": 0.9904945509377323,
      "eval_loss": 0.045228052884340286,
      "eval_precision": 0.9905452314533213,
      "eval_recall": 0.9904761904761905,
      "eval_runtime": 3.9393,
      "eval_samples_per_second": 346.509,
      "eval_steps_per_second": 43.409,
      "step": 341
    },
    {
      "epoch": 4.989751098096632,
      "eval_accuracy": 0.991941391941392,
      "eval_f1": 0.9919569277165429,
      "eval_loss": 0.04387320205569267,
      "eval_precision": 0.9920048531706146,
      "eval_recall": 0.991941391941392,
      "eval_runtime": 4.0115,
      "eval_samples_per_second": 340.268,
      "eval_steps_per_second": 42.627,
      "step": 426
    },
    {
      "epoch": 5.856515373352855,
      "grad_norm": 0.01621050015091896,
      "learning_rate": 6.1795711069424666e-06,
      "loss": 0.053,
      "step": 500
    },
    {
      "epoch": 5.997071742313324,
      "eval_accuracy": 0.991941391941392,
      "eval_f1": 0.9919507596926951,
      "eval_loss": 0.04010434448719025,
      "eval_precision": 0.991971823048746,
      "eval_recall": 0.991941391941392,
      "eval_runtime": 4.1768,
      "eval_samples_per_second": 326.803,
      "eval_steps_per_second": 40.94,
      "step": 512
    }
  ],
  "logging_steps": 500,
  "max_steps": 595,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 7.450204559616e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}