<!-- 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-large-cased-sigir-LR10-1-prepend-20
This model is a fine-tuned version of bert-large-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8946
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: 4e-05
- train_batch_size: 30
- eval_batch_size: 30
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8237 | 1.0 | 1 | 2.8391 |
| 3.6537 | 2.0 | 2 | 3.8003 |
| 1.9566 | 3.0 | 3 | 2.6997 |
| 1.0962 | 4.0 | 4 | 2.4019 |
| 2.7754 | 5.0 | 5 | 1.0750 |
| 2.2666 | 6.0 | 6 | 3.7118 |
| 1.33 | 7.0 | 7 | 2.3186 |
| 2.1846 | 8.0 | 8 | 2.0246 |
| 2.5284 | 9.0 | 9 | 2.0090 |
| 1.9864 | 10.0 | 10 | 3.3644 |
| 1.8111 | 11.0 | 11 | 2.5410 |
| 1.6821 | 12.0 | 12 | 1.2586 |
| 1.491 | 13.0 | 13 | 1.4496 |
| 1.9611 | 14.0 | 14 | 1.7305 |
| 1.4182 | 15.0 | 15 | 1.7722 |
| 2.0556 | 16.0 | 16 | 1.2964 |
| 0.9024 | 17.0 | 17 | 2.0762 |
| 1.5746 | 18.0 | 18 | 2.7421 |
| 1.2275 | 19.0 | 19 | 2.1911 |
| 1.6938 | 20.0 | 20 | 3.0756 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
