bert-tiny-finetuned-wikitext2
This model is a fine-tuned version of prajjwal1/bert-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7805
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.5579 | 1.0 | 16295 | 3.1073 |
| 3.3944 | 2.0 | 32590 | 2.9692 |
| 3.2968 | 3.0 | 48885 | 2.8999 |
| 3.2654 | 4.0 | 65180 | 2.8584 |
| 3.2519 | 5.0 | 81475 | 2.8261 |
| 3.2435 | 6.0 | 97770 | 2.8016 |
| 3.2276 | 7.0 | 114065 | 2.7961 |
| 3.1999 | 8.0 | 130360 | 2.7843 |
| 3.1726 | 9.0 | 146655 | 2.7742 |
| 3.1774 | 10.0 | 162950 | 2.7833 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for leobitz/bert-tiny-finetuned-wikitext2
Base model
prajjwal1/bert-tiny