<!-- 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. -->
bert-nlp-project-news
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: 3.7204
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.4196 | 0.35 | 8 | 3.9775 |
4.1578 | 0.7 | 16 | 3.8826 |
4.055 | 1.04 | 24 | 3.7820 |
3.954 | 1.39 | 32 | 3.6726 |
3.916 | 1.74 | 40 | 3.7244 |
3.864 | 2.09 | 48 | 3.7631 |
3.8837 | 2.43 | 56 | 3.6904 |
3.8965 | 2.78 | 64 | 3.6775 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2