metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - filter_v2
metrics:
  - f1
  - accuracy
model-index:
  - name: favs_filter_classification_v2
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: filter_v2
          type: filter_v2
          config: default
          split: train
          args: default
        metrics:
          - name: F1
            type: f1
            value: 0.9666666666666667
          - name: Accuracy
            type: accuracy
            value: 0.9375

favs_filter_classification_v2

This model is a fine-tuned version of bert-base-cased on the filter_v2 dataset. It achieves the following results on the evaluation set:

Loss: 0.2721
F1: 0.9667
Roc Auc: 0.9772
Accuracy: 0.9375

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
0.7591	1.0	14	0.6660	0.3137	0.5541	0.0
0.6506	2.0	28	0.5575	0.4706	0.6451	0.0625
0.5006	3.0	42	0.5010	0.5385	0.6846	0.0625
0.4416	4.0	56	0.4536	0.6538	0.7528	0.125
0.3815	5.0	70	0.4127	0.8070	0.8589	0.5
0.3468	6.0	84	0.3748	0.8621	0.8984	0.5625
0.3316	7.0	98	0.3487	0.8621	0.8984	0.5625
0.2834	8.0	112	0.3191	0.9	0.9317	0.6875
0.2565	9.0	126	0.2970	0.9492	0.9606	0.875
0.2241	10.0	140	0.2721	0.9667	0.9772	0.9375
0.214	11.0	154	0.2563	0.9492	0.9606	0.875
0.2041	12.0	168	0.2499	0.9492	0.9606	0.875
0.1831	13.0	182	0.2353	0.9492	0.9606	0.875
0.1852	14.0	196	0.2285	0.9492	0.9606	0.875
0.1636	15.0	210	0.2178	0.9667	0.9772	0.9375
0.1581	16.0	224	0.2110	0.9667	0.9772	0.9375
0.1473	17.0	238	0.2057	0.9492	0.9606	0.875
0.1479	18.0	252	0.2025	0.9667	0.9772	0.9375
0.141	19.0	266	0.2038	0.9667	0.9772	0.9375
0.1424	20.0	280	0.2032	0.9667	0.9772	0.9375

Framework versions

Transformers 4.21.1
Pytorch 1.12.1
Datasets 2.4.0
Tokenizers 0.12.1