metadata
license: cc-by-sa-4.0
tags:
- generated_from_trainer
datasets:
- klue
metrics:
- pearsonr
model-index:
- name: bert-base-finetuned-sts
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: klue
type: klue
config: sts
split: train
args: sts
metrics:
- name: Pearsonr
type: pearsonr
value: 0.9116408161709073
bert-base-finetuned-sts
This model is a fine-tuned version of klue/bert-base on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3951
- Pearsonr: 0.9116
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearsonr |
|---|---|---|---|---|
| 0.2345 | 1.0 | 2917 | 0.7037 | 0.8757 |
| 0.1491 | 2.0 | 5834 | 0.4869 | 0.8846 |
| 0.097 | 3.0 | 8751 | 0.4023 | 0.9041 |
| 0.0735 | 4.0 | 11668 | 0.3960 | 0.9073 |
| 0.0644 | 5.0 | 14585 | 0.4838 | 0.8989 |
| 0.0446 | 6.0 | 17502 | 0.3990 | 0.9078 |
| 0.0355 | 7.0 | 20419 | 0.3951 | 0.9116 |
| 0.0277 | 8.0 | 23336 | 0.4284 | 0.9053 |
| 0.0239 | 9.0 | 26253 | 0.4166 | 0.9073 |
| 0.0205 | 10.0 | 29170 | 0.4234 | 0.9062 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0
- Datasets 2.7.1
- Tokenizers 0.13.2