<!-- 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-lm-all
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: 0.8646
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 |
|---|---|---|---|
| 1.6625 | 1.0 | 1194 | 1.3270 |
| 1.3001 | 2.0 | 2388 | 1.1745 |
| 1.1694 | 3.0 | 3582 | 1.1133 |
| 1.0901 | 4.0 | 4776 | 1.0547 |
| 1.0309 | 5.0 | 5970 | 0.9953 |
| 0.9842 | 6.0 | 7164 | 0.9997 |
| 0.9396 | 7.0 | 8358 | 0.9707 |
| 0.8997 | 8.0 | 9552 | 0.9324 |
| 0.8633 | 9.0 | 10746 | 0.9145 |
| 0.8314 | 10.0 | 11940 | 0.9047 |
| 0.812 | 11.0 | 13134 | 0.8954 |
| 0.7841 | 12.0 | 14328 | 0.8940 |
| 0.7616 | 13.0 | 15522 | 0.8555 |
| 0.7508 | 14.0 | 16716 | 0.8711 |
| 0.7333 | 15.0 | 17910 | 0.8351 |
| 0.7299 | 16.0 | 19104 | 0.8646 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
