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: 0.8722017849942011
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: 0.4274
- Pearsonr: 0.8722
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: 32
- eval_batch_size: 32
- 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 | 365 | 0.5106 | 0.8429 |
| 0.1092 | 2.0 | 730 | 0.5466 | 0.8497 |
| 0.0958 | 3.0 | 1095 | 0.4123 | 0.8680 |
| 0.0958 | 4.0 | 1460 | 0.4336 | 0.8719 |
| 0.0661 | 5.0 | 1825 | 0.4274 | 0.8722 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6