<!-- 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-DIS-mlm5
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: 4.4911
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|
| 0.036 | 1.0 | 2 | 4.3499 |
| 0.1722 | 2.0 | 4 | 4.3545 |
| 0.6087 | 3.0 | 6 | 5.8627 |
| 0.2151 | 4.0 | 8 | 3.6960 |
| 0.2115 | 5.0 | 10 | 3.2086 |
| 0.3443 | 6.0 | 12 | 5.1042 |
| 0.1082 | 7.0 | 14 | 4.0195 |
| 0.5068 | 8.0 | 16 | 3.6664 |
| 0.7362 | 9.0 | 18 | 4.3850 |
| 0.4281 | 10.0 | 20 | 4.6974 |
| 1.3107 | 11.0 | 22 | 4.3258 |
| 1.4157 | 12.0 | 24 | 4.8907 |
| 2.5918 | 13.0 | 26 | 4.6595 |
| 2.577 | 14.0 | 28 | 4.3417 |
| 1.6291 | 15.0 | 30 | 5.0013 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3
