tinybert_book_ent_15p_b_stsb
This model is a fine-tuned version of gokulsrinivasagan/tinybert_book_ent_15p_b on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.3782
- Pearson: 0.2303
- Spearmanr: 0.2312
- Combined Score: 0.2307
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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 2.9686 | 1.0 | 23 | 2.5835 | 0.0827 | 0.0827 | 0.0827 |
| 2.0117 | 2.0 | 46 | 2.5771 | 0.1016 | 0.0926 | 0.0971 |
| 1.8929 | 3.0 | 69 | 2.4845 | 0.1587 | 0.1596 | 0.1592 |
| 1.739 | 4.0 | 92 | 2.3782 | 0.2303 | 0.2312 | 0.2307 |
| 1.486 | 5.0 | 115 | 2.3787 | 0.2312 | 0.2279 | 0.2296 |
| 1.3627 | 6.0 | 138 | 2.6378 | 0.2251 | 0.2296 | 0.2273 |
| 1.1627 | 7.0 | 161 | 2.9231 | 0.2355 | 0.2513 | 0.2434 |
| 1.0261 | 8.0 | 184 | 2.7353 | 0.2320 | 0.2343 | 0.2331 |
| 0.8927 | 9.0 | 207 | 2.7893 | 0.2221 | 0.2263 | 0.2242 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1