metadata
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
args: sts
metrics:
- name: Pearsonr
type: pearsonr
value: 0.9000373376026184
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: 0.4582
- Pearsonr: 0.9000
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearsonr |
|---|---|---|---|---|
| No log | 1.0 | 183 | 0.5329 | 0.8827 |
| No log | 2.0 | 366 | 0.4549 | 0.8937 |
| 0.2316 | 3.0 | 549 | 0.4656 | 0.8959 |
| 0.2316 | 4.0 | 732 | 0.4651 | 0.8990 |
| 0.2316 | 5.0 | 915 | 0.4582 | 0.9000 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1