minilm-finetuned-yelp
This model is a fine-tuned version of microsoft/MiniLM-L12-H384-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1838
- F1: 0.9467
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: 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.858 | 1.0 | 15565 | 0.7554 | 0.6474 |
| 0.7528 | 2.0 | 31130 | 0.6906 | 0.6960 |
| 0.7071 | 3.0 | 46695 | 0.6578 | 0.7273 |
| 0.6654 | 4.0 | 62260 | 0.5850 | 0.7585 |
| 0.6229 | 5.0 | 77825 | 0.5386 | 0.7825 |
| 0.5796 | 6.0 | 93390 | 0.4821 | 0.8188 |
| 0.5367 | 7.0 | 108955 | 0.4254 | 0.8423 |
| 0.4962 | 8.0 | 124520 | 0.3792 | 0.8696 |
| 0.4574 | 9.0 | 140085 | 0.3364 | 0.8843 |
| 0.4222 | 10.0 | 155650 | 0.2893 | 0.9042 |
| 0.3903 | 11.0 | 171215 | 0.2582 | 0.9167 |
| 0.3626 | 12.0 | 186780 | 0.2286 | 0.9283 |
| 0.3386 | 13.0 | 202345 | 0.2029 | 0.9392 |
| 0.3213 | 14.0 | 217910 | 0.1912 | 0.9443 |
| 0.3063 | 15.0 | 233475 | 0.1838 | 0.9467 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2