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: 1
          - name: Accuracy
            type: accuracy
            value: 1

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: 0.2201
F1: 1.0
Roc Auc: 1.0
Accuracy: 1.0

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: 1.3e-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
0.6747	1.0	13	0.5868	0.5	0.6649	0.1818
0.5843	2.0	26	0.5321	0.4828	0.6575	0.0
0.5445	3.0	39	0.5029	0.6	0.7162	0.2727
0.4713	4.0	52	0.4667	0.6207	0.725	0.2727
0.4304	5.0	65	0.4321	0.6667	0.7575	0.4545
0.3983	6.0	78	0.3909	0.7500	0.8	0.4545
0.3433	7.0	91	0.3571	0.7879	0.825	0.5455
0.3186	8.0	104	0.3319	0.8235	0.85	0.6364
0.2967	9.0	117	0.3049	0.8571	0.875	0.6364
0.2739	10.0	130	0.2857	0.8571	0.875	0.6364
0.2535	11.0	143	0.2686	0.9474	0.95	0.8182
0.234	12.0	156	0.2501	0.9474	0.95	0.8182
0.2338	13.0	169	0.2358	0.9474	0.95	0.8182
0.2049	14.0	182	0.2201	1.0	1.0	1.0
0.1942	15.0	195	0.2098	1.0	1.0	1.0
0.1957	16.0	208	0.2063	1.0	1.0	1.0
0.1892	17.0	221	0.1969	1.0	1.0	1.0
0.1836	18.0	234	0.1919	1.0	1.0	1.0
0.1767	19.0	247	0.1909	1.0	1.0	1.0
0.1702	20.0	260	0.1901	1.0	1.0	1.0

Framework versions

Transformers 4.21.1
Pytorch 1.12.1
Datasets 2.4.0
Tokenizers 0.12.1