sts_ys7yoo_nli_klue_roberta_large_ep7_ep7
This model is a fine-tuned version of ys7yoo/nli_klue_roberta_large_ep7 on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3377
- Mse: 0.3377
- Mae: 0.4245
- R2: 0.8454
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 |
|---|---|---|---|---|---|---|
| 0.9508 | 1.0 | 183 | 0.7866 | 0.7866 | 0.7024 | 0.6398 |
| 0.1706 | 2.0 | 366 | 0.4368 | 0.4368 | 0.4997 | 0.8000 |
| 0.1201 | 3.0 | 549 | 0.4373 | 0.4373 | 0.4872 | 0.7998 |
| 0.0802 | 4.0 | 732 | 0.3529 | 0.3529 | 0.4362 | 0.8384 |
| 0.0596 | 5.0 | 915 | 0.3275 | 0.3275 | 0.4217 | 0.8500 |
| 0.0404 | 6.0 | 1098 | 0.3513 | 0.3513 | 0.4354 | 0.8392 |
| 0.0282 | 7.0 | 1281 | 0.3377 | 0.3377 | 0.4245 | 0.8454 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 4