checkpoint-151/trainer_state.json

{
  "best_metric": 0.8112582781456954,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-151",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 151,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9536423841059603,
      "eval_accuracy": 0.5298013245033113,
      "eval_f1": 0.43216404525386315,
      "eval_loss": 1.1326755285263062,
      "eval_precision": 0.5213817284211205,
      "eval_recall": 0.5298013245033113,
      "eval_runtime": 1.2241,
      "eval_samples_per_second": 246.709,
      "eval_steps_per_second": 31.043,
      "step": 18
    },
    {
      "epoch": 1.9602649006622517,
      "eval_accuracy": 0.6423841059602649,
      "eval_f1": 0.5806184720425087,
      "eval_loss": 0.9228919744491577,
      "eval_precision": 0.5520930002801896,
      "eval_recall": 0.6423841059602649,
      "eval_runtime": 1.2236,
      "eval_samples_per_second": 246.807,
      "eval_steps_per_second": 31.055,
      "step": 37
    },
    {
      "epoch": 2.966887417218543,
      "eval_accuracy": 0.7086092715231788,
      "eval_f1": 0.6539391094940458,
      "eval_loss": 0.7409619688987732,
      "eval_precision": 0.752516290193287,
      "eval_recall": 0.7086092715231788,
      "eval_runtime": 1.2459,
      "eval_samples_per_second": 242.403,
      "eval_steps_per_second": 30.501,
      "step": 56
    },
    {
      "epoch": 3.9735099337748343,
      "eval_accuracy": 0.7450331125827815,
      "eval_f1": 0.7012377717797856,
      "eval_loss": 0.6461689472198486,
      "eval_precision": 0.7242129191632504,
      "eval_recall": 0.7450331125827815,
      "eval_runtime": 1.229,
      "eval_samples_per_second": 245.723,
      "eval_steps_per_second": 30.919,
      "step": 75
    },
    {
      "epoch": 4.9801324503311255,
      "eval_accuracy": 0.7980132450331126,
      "eval_f1": 0.7903709596982513,
      "eval_loss": 0.5553261041641235,
      "eval_precision": 0.7925903096412185,
      "eval_recall": 0.7980132450331126,
      "eval_runtime": 1.2897,
      "eval_samples_per_second": 234.157,
      "eval_steps_per_second": 29.463,
      "step": 94
    },
    {
      "epoch": 5.986754966887418,
      "eval_accuracy": 0.7781456953642384,
      "eval_f1": 0.7717607879297459,
      "eval_loss": 0.5255588293075562,
      "eval_precision": 0.7771454278224522,
      "eval_recall": 0.7781456953642384,
      "eval_runtime": 1.2928,
      "eval_samples_per_second": 233.597,
      "eval_steps_per_second": 29.393,
      "step": 113
    },
    {
      "epoch": 6.993377483443709,
      "eval_accuracy": 0.7980132450331126,
      "eval_f1": 0.7833793670187674,
      "eval_loss": 0.5077652335166931,
      "eval_precision": 0.7917508237685551,
      "eval_recall": 0.7980132450331126,
      "eval_runtime": 1.2898,
      "eval_samples_per_second": 234.154,
      "eval_steps_per_second": 29.463,
      "step": 132
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8112582781456954,
      "eval_f1": 0.8021247299665692,
      "eval_loss": 0.4742371141910553,
      "eval_precision": 0.8054865043662888,
      "eval_recall": 0.8112582781456954,
      "eval_runtime": 1.381,
      "eval_samples_per_second": 218.682,
      "eval_steps_per_second": 27.516,
      "step": 151
    }
  ],
  "logging_steps": 500,
  "max_steps": 180,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.197812547584e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}