sts_nli_klue_roberta_large_lr1e_05_wd1e_03_lr1e-05_wd1e-03_ep5_ckpt
This model is a fine-tuned version of ys7yoo/nli_klue_roberta_large_lr1e-05_wd1e-03 on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3169
- Mse: 0.3169
- Mae: 0.4090
- R2: 0.8549
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: 1e-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 |
|---|---|---|---|---|---|---|
| 1.1893 | 1.0 | 183 | 0.5904 | 0.5904 | 0.5827 | 0.7296 |
| 0.1418 | 2.0 | 366 | 0.4095 | 0.4095 | 0.4737 | 0.8125 |
| 0.0967 | 3.0 | 549 | 0.3657 | 0.3657 | 0.4383 | 0.8326 |
| 0.0752 | 4.0 | 732 | 0.3391 | 0.3391 | 0.4254 | 0.8447 |
| 0.06 | 5.0 | 915 | 0.3169 | 0.3169 | 0.4090 | 0.8549 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.