bert-medium-finetuned-wikitext2
This model is a fine-tuned version of prajjwal1/bert-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4025
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 |
|---|---|---|---|
| 1.7865 | 1.0 | 16295 | 1.6414 |
| 1.6876 | 2.0 | 32590 | 1.5522 |
| 1.5991 | 3.0 | 48885 | 1.5083 |
| 1.5784 | 4.0 | 65180 | 1.4795 |
| 1.5631 | 5.0 | 81475 | 1.4588 |
| 1.5448 | 6.0 | 97770 | 1.4333 |
| 1.5196 | 7.0 | 114065 | 1.4220 |
| 1.5108 | 8.0 | 130360 | 1.4133 |
| 1.4799 | 9.0 | 146655 | 1.4000 |
| 1.4781 | 10.0 | 162950 | 1.4051 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.15.2
- Downloads last month
- 10
Model tree for leobitz/bert-medium-finetuned-wikitext2
Base model
prajjwal1/bert-medium