nguyenkhoa2407's picture
update model card README.md
b2d5b7a
|
raw
history blame
3.38 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - filter_sort
metrics:
  - f1
  - accuracy
model-index:
  - name: favs-filtersort-multilabel-classification-bert-base-cased
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: filter_sort
          type: filter_sort
          config: default
          split: train
          args: default
        metrics:
          - name: F1
            type: f1
            value: 0.767123287671233
          - name: Accuracy
            type: accuracy
            value: 0.3

favs-filtersort-multilabel-classification-bert-base-cased

This model is a fine-tuned version of bert-base-cased on the filter_sort dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2847
  • F1: 0.7671
  • Roc Auc: 0.8361
  • Accuracy: 0.3

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1.5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss F1 Roc Auc Accuracy
0.7037 1.0 12 0.6056 0.5714 0.7341 0.0
0.5962 2.0 24 0.5212 0.5067 0.6787 0.0
0.5393 3.0 36 0.4396 0.6197 0.7439 0.1
0.4682 4.0 48 0.3963 0.5714 0.7079 0.0
0.409 5.0 60 0.3710 0.6061 0.7297 0.0
0.3923 6.0 72 0.3571 0.6286 0.7477 0.1
0.3682 7.0 84 0.3439 0.6849 0.7862 0.2
0.367 8.0 96 0.3286 0.6479 0.7605 0.1
0.3633 9.0 108 0.3194 0.6761 0.7772 0.2
0.3359 10.0 120 0.3145 0.6761 0.7772 0.2
0.3327 11.0 132 0.3054 0.6957 0.7848 0.2
0.3206 12.0 144 0.2998 0.7297 0.8156 0.2
0.3125 13.0 156 0.2926 0.7222 0.8066 0.2
0.3073 14.0 168 0.2847 0.7671 0.8361 0.3
0.2972 15.0 180 0.2819 0.7606 0.8271 0.3
0.2933 16.0 192 0.2773 0.7606 0.8271 0.3
0.2798 17.0 204 0.2752 0.7606 0.8271 0.3
0.2737 18.0 216 0.2731 0.7606 0.8271 0.3
0.2866 19.0 228 0.2720 0.7606 0.8271 0.3
0.2729 20.0 240 0.2713 0.7606 0.8271 0.3

Framework versions

  • Transformers 4.21.1
  • Pytorch 1.12.1
  • Datasets 2.4.0
  • Tokenizers 0.12.1