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: 0.7887323943661971
          - 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: 0.2822
F1: 0.7887
Roc Auc: 0.8437
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
0.6319	1.0	12	0.5814	0.4889	0.6714	0.0
0.5697	2.0	24	0.5046	0.6111	0.7401	0.0
0.5224	3.0	36	0.4393	0.6923	0.8004	0.0
0.4666	4.0	48	0.4048	0.6835	0.7965	0.0
0.4188	5.0	60	0.3795	0.6933	0.7952	0.0
0.4023	6.0	72	0.3634	0.7027	0.7990	0.0
0.3776	7.0	84	0.3526	0.7143	0.7976	0.0
0.3635	8.0	96	0.3423	0.7143	0.7976	0.0
0.3648	9.0	108	0.3288	0.7059	0.7886	0.0
0.3284	10.0	120	0.3192	0.7429	0.8142	0.2
0.3267	11.0	132	0.3151	0.7353	0.8052	0.1
0.3113	12.0	144	0.3066	0.7536	0.8181	0.2
0.3043	13.0	156	0.3018	0.7606	0.8271	0.3
0.2924	14.0	168	0.2940	0.7606	0.8271	0.3
0.2843	15.0	180	0.2936	0.7714	0.8309	0.3
0.2794	16.0	192	0.2856	0.7778	0.8399	0.3
0.2678	17.0	204	0.2860	0.7714	0.8309	0.3
0.2631	18.0	216	0.2822	0.7887	0.8437	0.3
0.269	19.0	228	0.2806	0.7887	0.8437	0.3
0.2609	20.0	240	0.2799	0.7887	0.8437	0.3

Framework versions

Transformers 4.21.1
Pytorch 1.12.1
Datasets 2.4.0
Tokenizers 0.12.1