<!-- 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-base-uncased-reviews-2
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: 1.7896
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.0821 | 1.0 | 54 | 2.4469 |
2.5174 | 2.0 | 108 | 2.4053 |
2.2908 | 3.0 | 162 | 2.1641 |
2.1386 | 4.0 | 216 | 2.0630 |
2.0979 | 5.0 | 270 | 2.0280 |
1.9993 | 6.0 | 324 | 2.1035 |
1.9345 | 7.0 | 378 | 1.9415 |
1.8916 | 8.0 | 432 | 1.9182 |
1.8557 | 9.0 | 486 | 1.7934 |
1.8405 | 10.0 | 540 | 1.8154 |
1.8092 | 11.0 | 594 | 1.9632 |
1.7748 | 12.0 | 648 | 1.8535 |
1.7633 | 13.0 | 702 | 1.9335 |
1.7185 | 14.0 | 756 | 1.7669 |
1.6964 | 15.0 | 810 | 1.8345 |
1.7603 | 16.0 | 864 | 1.7896 |
Framework versions
- Transformers 4.13.0
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.10.3