|
--- |
|
base_model: klue/roberta-large |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- klue |
|
model-index: |
|
- name: sts_klue_roberta_large_ep9 |
|
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_roberta_large_ep9 |
|
|
|
This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on the klue dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3567 |
|
- Mse: 0.3567 |
|
- Mae: 0.4407 |
|
- R2: 0.8367 |
|
|
|
## 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: 9 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:| |
|
| 1.3093 | 1.0 | 183 | 0.4915 | 0.4915 | 0.5401 | 0.7750 | |
|
| 0.2188 | 2.0 | 366 | 0.4399 | 0.4399 | 0.4982 | 0.7986 | |
|
| 0.1327 | 3.0 | 549 | 0.4022 | 0.4022 | 0.4647 | 0.8158 | |
|
| 0.1043 | 4.0 | 732 | 0.4094 | 0.4094 | 0.4680 | 0.8125 | |
|
| 0.074 | 5.0 | 915 | 0.4218 | 0.4218 | 0.4784 | 0.8069 | |
|
| 0.0552 | 6.0 | 1098 | 0.3424 | 0.3424 | 0.4356 | 0.8432 | |
|
| 0.0394 | 7.0 | 1281 | 0.3925 | 0.3925 | 0.4691 | 0.8203 | |
|
| 0.031 | 8.0 | 1464 | 0.3723 | 0.3723 | 0.4510 | 0.8295 | |
|
| 0.0234 | 9.0 | 1647 | 0.3567 | 0.3567 | 0.4407 | 0.8367 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|
