bert-base-uncased-finetuned-news-2003-2007
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0218
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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.3155 | 1.0 | 22331 | 3.0932 |
| 3.2358 | 2.0 | 44662 | 3.0404 |
| 3.2124 | 3.0 | 66993 | 3.0210 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 35
Model tree for sally9805/bert-base-uncased-finetuned-news-2003-2007
Base model
google-bert/bert-base-uncased