|
--- |
|
license: cc-by-sa-4.0 |
|
base_model: klue/bert-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- klue |
|
model-index: |
|
- name: sts_klue_bert_base_ep5_ckpt |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# sts_klue_bert_base_ep5_ckpt |
|
|
|
This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on the klue dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4295 |
|
- Mse: 0.4295 |
|
- Mae: 0.4938 |
|
- R2: 0.8033 |
|
|
|
## 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: 5e-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 |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:| |
|
| 0.8186 | 1.0 | 183 | 0.5172 | 0.5172 | 0.5566 | 0.7631 | |
|
| 0.1529 | 2.0 | 366 | 0.4698 | 0.4698 | 0.5155 | 0.7849 | |
|
| 0.0967 | 3.0 | 549 | 0.4525 | 0.4525 | 0.4859 | 0.7928 | |
|
| 0.0699 | 4.0 | 732 | 0.4232 | 0.4232 | 0.4839 | 0.8062 | |
|
| 0.0537 | 5.0 | 915 | 0.4295 | 0.4295 | 0.4938 | 0.8033 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|
