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: 0.823529411764706
- name: Accuracy
type: accuracy
value: 0
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: 0.4283
- F1: 0.8235
- Roc Auc: 0.9058
- Accuracy: 0.0
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: 1.5e-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 |
---|---|---|---|---|---|---|
No log | 1.0 | 9 | 0.5901 | 0.6087 | 0.7289 | 0.0 |
0.665 | 2.0 | 18 | 0.5667 | 0.4545 | 0.6201 | 0.0 |
0.6099 | 3.0 | 27 | 0.5573 | 0.5 | 0.6558 | 0.0 |
0.5463 | 4.0 | 36 | 0.5561 | 0.3889 | 0.5966 | 0.0 |
0.5071 | 5.0 | 45 | 0.5484 | 0.3889 | 0.5966 | 0.0 |
0.4669 | 6.0 | 54 | 0.5462 | 0.4324 | 0.6193 | 0.0 |
0.4371 | 7.0 | 63 | 0.5326 | 0.4737 | 0.6420 | 0.0 |
0.4145 | 8.0 | 72 | 0.5202 | 0.5854 | 0.7102 | 0.0 |
0.3959 | 9.0 | 81 | 0.5020 | 0.6364 | 0.7468 | 0.0 |
0.3733 | 10.0 | 90 | 0.4944 | 0.6364 | 0.7468 | 0.0 |
0.3733 | 11.0 | 99 | 0.4675 | 0.7234 | 0.8149 | 0.0 |
0.3622 | 12.0 | 108 | 0.4626 | 0.7843 | 0.8742 | 0.0 |
0.3382 | 13.0 | 117 | 0.4499 | 0.8077 | 0.8969 | 0.0 |
0.3341 | 14.0 | 126 | 0.4482 | 0.8077 | 0.8969 | 0.0 |
0.315 | 15.0 | 135 | 0.4332 | 0.8077 | 0.8969 | 0.0 |
0.3253 | 16.0 | 144 | 0.4283 | 0.8235 | 0.9058 | 0.0 |
0.3031 | 17.0 | 153 | 0.4246 | 0.8077 | 0.8969 | 0.0 |
0.3071 | 18.0 | 162 | 0.4155 | 0.8077 | 0.8969 | 0.0 |
0.2944 | 19.0 | 171 | 0.4129 | 0.8077 | 0.8969 | 0.0 |
0.2996 | 20.0 | 180 | 0.4129 | 0.8077 | 0.8969 | 0.0 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1
- Datasets 2.4.0
- Tokenizers 0.12.1