bert-base-cased-coffee20230113
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.1553
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 88 | 4.3261 |
| 5.3354 | 2.0 | 176 | 2.8499 |
| 3.0455 | 3.0 | 264 | 2.3299 |
| 1.9373 | 4.0 | 352 | 2.5522 |
| 1.2186 | 5.0 | 440 | 3.1720 |
| 0.8601 | 6.0 | 528 | 3.0420 |
| 0.6784 | 7.0 | 616 | 3.4801 |
| 0.4319 | 8.0 | 704 | 3.7463 |
| 0.4319 | 9.0 | 792 | 4.1014 |
| 0.3164 | 10.0 | 880 | 4.2563 |
| 0.2039 | 11.0 | 968 | 4.4461 |
| 0.1202 | 12.0 | 1056 | 4.8725 |
| 0.0491 | 13.0 | 1144 | 4.7507 |
| 0.031 | 14.0 | 1232 | 5.1064 |
| 0.0133 | 15.0 | 1320 | 5.1553 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.11.0+cu113
- Datasets 2.8.0
- Tokenizers 0.13.2