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: 0.7714285714285716
          - name: Accuracy
            type: accuracy
            value: 0.4

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: 0.2711
F1: 0.7714
Roc Auc: 0.8309
Accuracy: 0.4

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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.6535	1.0	12	0.5860	0.4524	0.6444	0.0
0.5843	2.0	24	0.5121	0.5	0.6708	0.0
0.5308	3.0	36	0.4460	0.5484	0.6950	0.0
0.4663	4.0	48	0.4023	0.5574	0.6989	0.0
0.4116	5.0	60	0.3769	0.5806	0.7117	0.0
0.3936	6.0	72	0.3620	0.6032	0.7245	0.0
0.3691	7.0	84	0.3519	0.625	0.7373	0.0
0.3565	8.0	96	0.3410	0.6269	0.7425	0.0
0.3548	9.0	108	0.3324	0.6562	0.7540	0.0
0.3235	10.0	120	0.3229	0.6866	0.7758	0.1
0.3157	11.0	132	0.3115	0.7164	0.7924	0.2
0.297	12.0	144	0.3055	0.7164	0.7924	0.2
0.2923	13.0	156	0.2988	0.7246	0.8014	0.2
0.2848	14.0	168	0.2903	0.7164	0.7924	0.2
0.2715	15.0	180	0.2908	0.7429	0.8142	0.3
0.2696	16.0	192	0.2807	0.7353	0.8052	0.3
0.2543	17.0	204	0.2794	0.7536	0.8181	0.3
0.2504	18.0	216	0.2711	0.7714	0.8309	0.4
0.2577	19.0	228	0.2708	0.7536	0.8181	0.3
0.2401	20.0	240	0.2693	0.7536	0.8181	0.3
0.2415	21.0	252	0.2669	0.7714	0.8309	0.4
0.241	22.0	264	0.2691	0.7536	0.8181	0.3
0.2341	23.0	276	0.2669	0.7536	0.8181	0.3
0.2355	24.0	288	0.2660	0.7536	0.8181	0.3
0.232	25.0	300	0.2655	0.7536	0.8181	0.3

Framework versions

Transformers 4.21.1
Pytorch 1.12.1
Datasets 2.4.0
Tokenizers 0.12.1