metadata
base_model: ys7yoo/nli_roberta-large_lr1e-05_wd1e-03_ep3
tags:
- generated_from_trainer
datasets:
- klue
model-index:
- name: sts_nli_roberta-large_lr1e-05_wd1e-03_ep3_lr1e-05_wd1e-03_ep5_ckpt
results: []
sts_nli_roberta-large_lr1e-05_wd1e-03_ep3_lr1e-05_wd1e-03_ep5_ckpt
This model is a fine-tuned version of ys7yoo/nli_roberta-large_lr1e-05_wd1e-03_ep3 on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3191
- Mse: 0.3191
- Mae: 0.4161
- R2: 0.8539
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 |
---|---|---|---|---|---|---|
1.0641 | 1.0 | 183 | 0.5074 | 0.5074 | 0.5341 | 0.7676 |
0.1359 | 2.0 | 366 | 0.3199 | 0.3199 | 0.4232 | 0.8535 |
0.0958 | 3.0 | 549 | 0.3589 | 0.3589 | 0.4349 | 0.8356 |
0.0748 | 4.0 | 732 | 0.3385 | 0.3385 | 0.4284 | 0.8450 |
0.0617 | 5.0 | 915 | 0.3191 | 0.3191 | 0.4161 | 0.8539 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3