<!-- 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. -->
distilbert-base-uncased-finetuned-news-lr5
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1744
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: 7.5e-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: 0.17
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.568 | 1.0 | 5323 | 1.9294 |
| 1.8742 | 2.0 | 10646 | 1.6656 |
| 1.6837 | 3.0 | 15969 | 1.5462 |
| 1.5855 | 4.0 | 21292 | 1.4742 |
| 1.5058 | 5.0 | 26615 | 1.4183 |
| 1.4472 | 6.0 | 31938 | 1.3763 |
| 1.4049 | 7.0 | 37261 | 1.3439 |
| 1.3697 | 8.0 | 42584 | 1.3225 |
| 1.339 | 9.0 | 47907 | 1.3010 |
| 1.3119 | 10.0 | 53230 | 1.2795 |
| 1.2886 | 11.0 | 58553 | 1.2613 |
| 1.2676 | 12.0 | 63876 | 1.2451 |
| 1.2489 | 13.0 | 69199 | 1.2309 |
| 1.2337 | 14.0 | 74522 | 1.2207 |
| 1.2171 | 15.0 | 79845 | 1.2094 |
| 1.2009 | 16.0 | 85168 | 1.1997 |
| 1.1889 | 17.0 | 90491 | 1.1912 |
| 1.177 | 18.0 | 95814 | 1.1826 |
| 1.1679 | 19.0 | 101137 | 1.1780 |
| 1.162 | 20.0 | 106460 | 1.1714 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
