metadata
base_model: klue/roberta-large
tags:
- generated_from_trainer
datasets:
- klue
model-index:
- name: sts_roberta-large_lr1e-05_wd1e-03_ep7_ckpt
results: []
sts_roberta-large_lr1e-05_wd1e-03_ep7_ckpt
This model is a fine-tuned version of klue/roberta-large on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3621
- Mse: 0.3621
- Mae: 0.4438
- R2: 0.8342
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 |
|---|---|---|---|---|---|---|
| 1.8712 | 1.0 | 183 | 0.5118 | 0.5118 | 0.5409 | 0.7656 |
| 0.1606 | 2.0 | 366 | 0.4621 | 0.4621 | 0.5142 | 0.7884 |
| 0.1111 | 3.0 | 549 | 0.4687 | 0.4687 | 0.5088 | 0.7854 |
| 0.0837 | 4.0 | 732 | 0.4317 | 0.4317 | 0.4906 | 0.8023 |
| 0.0681 | 5.0 | 915 | 0.4662 | 0.4662 | 0.5091 | 0.7865 |
| 0.0559 | 6.0 | 1098 | 0.3742 | 0.3742 | 0.4524 | 0.8286 |
| 0.0485 | 7.0 | 1281 | 0.3621 | 0.3621 | 0.4438 | 0.8342 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3