checkpoint-270/trainer_state.json

{
  "best_metric": 0.8473173810316668,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-200",
  "epoch": 30.0,
  "eval_steps": 100,
  "global_step": 270,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.555555555555555,
      "grad_norm": 3.0120761394500732,
      "learning_rate": 0.0002954973225032615,
      "loss": 0.9823,
      "step": 50
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 1.183480143547058,
      "learning_rate": 0.0002441718187008148,
      "loss": 0.5938,
      "step": 100
    },
    {
      "epoch": 11.11111111111111,
      "eval_accuracy": 0.8278388278388278,
      "eval_confusion_matrix": [
        [
          79,
          7,
          0,
          1
        ],
        [
          11,
          29,
          19,
          0
        ],
        [
          0,
          8,
          56,
          0
        ],
        [
          1,
          0,
          0,
          62
        ]
      ],
      "eval_f1": 0.8205727670173567,
      "eval_loss": 0.7099524140357971,
      "eval_precision": 0.8212472631153949,
      "eval_recall": 0.8278388278388278,
      "eval_runtime": 3.0504,
      "eval_samples_per_second": 89.496,
      "eval_steps_per_second": 1.639,
      "step": 100
    },
    {
      "epoch": 16.666666666666668,
      "grad_norm": 1.125301718711853,
      "learning_rate": 0.0001548472927611466,
      "loss": 0.3816,
      "step": 150
    },
    {
      "epoch": 22.22222222222222,
      "grad_norm": 0.025351429358124733,
      "learning_rate": 6.356684850666294e-05,
      "loss": 0.3511,
      "step": 200
    },
    {
      "epoch": 22.22222222222222,
      "eval_accuracy": 0.8498168498168498,
      "eval_confusion_matrix": [
        [
          76,
          11,
          0,
          0
        ],
        [
          7,
          35,
          17,
          0
        ],
        [
          0,
          5,
          59,
          0
        ],
        [
          1,
          0,
          0,
          62
        ]
      ],
      "eval_f1": 0.8473173810316668,
      "eval_loss": 0.7837256193161011,
      "eval_precision": 0.8494091293737467,
      "eval_recall": 0.8498168498168498,
      "eval_runtime": 2.7557,
      "eval_samples_per_second": 99.068,
      "eval_steps_per_second": 1.814,
      "step": 200
    },
    {
      "epoch": 27.77777777777778,
      "grad_norm": 0.0050039030611515045,
      "learning_rate": 7.1628171992377025e-06,
      "loss": 0.349,
      "step": 250
    }
  ],
  "logging_steps": 50,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.001
      },
      "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": 7.4367208512e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}