<!-- 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. -->
bert-large-uncased-finetuned-stsb
This model is a fine-tuned version of bert-large-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4441
- Pearson: 0.8992
- Spearmanr: 0.8959
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
|---|---|---|---|---|---|
| No log | 1.0 | 360 | 0.5527 | 0.8929 | 0.8932 |
| 0.7164 | 2.0 | 720 | 0.4669 | 0.8965 | 0.8952 |
| 0.2827 | 3.0 | 1080 | 0.4438 | 0.8964 | 0.8938 |
| 0.2827 | 4.0 | 1440 | 0.4648 | 0.8978 | 0.8956 |
| 0.1529 | 5.0 | 1800 | 0.4441 | 0.8992 | 0.8959 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
