metadata
license: cc-by-4.0
base_model: deepset/bert-base-cased-squad2
tags:
- generated_from_trainer
model-index:
- name: bert-17
results: []
bert-17
This model is a fine-tuned version of deepset/bert-base-cased-squad2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.7381
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 11.0352 | 0.09 | 5 | 11.3392 |
| 10.0155 | 0.18 | 10 | 10.1330 |
| 8.6139 | 0.27 | 15 | 9.0228 |
| 7.7654 | 0.36 | 20 | 8.0477 |
| 7.1161 | 0.45 | 25 | 7.2438 |
| 6.486 | 0.55 | 30 | 6.6691 |
| 5.9793 | 0.64 | 35 | 6.3524 |
| 5.8845 | 0.73 | 40 | 6.2251 |
| 5.8619 | 0.82 | 45 | 6.1625 |
| 5.7536 | 0.91 | 50 | 6.1058 |
| 5.6831 | 1.0 | 55 | 6.0479 |
| 5.5525 | 1.09 | 60 | 5.9939 |
| 5.4714 | 1.18 | 65 | 5.9510 |
| 5.4384 | 1.27 | 70 | 5.9123 |
| 5.4539 | 1.36 | 75 | 5.8817 |
| 5.4073 | 1.45 | 80 | 5.8593 |
| 5.4048 | 1.55 | 85 | 5.8395 |
| 5.2997 | 1.64 | 90 | 5.8225 |
| 5.2388 | 1.73 | 95 | 5.8099 |
| 5.2564 | 1.82 | 100 | 5.7986 |
| 5.1758 | 1.91 | 105 | 5.7872 |
| 5.1926 | 2.0 | 110 | 5.7800 |
| 4.9244 | 2.09 | 115 | 5.7747 |
| 5.0897 | 2.18 | 120 | 5.7689 |
| 5.2493 | 2.27 | 125 | 5.7610 |
| 5.0594 | 2.36 | 130 | 5.7541 |
| 5.0792 | 2.45 | 135 | 5.7485 |
| 4.9952 | 2.55 | 140 | 5.7455 |
| 4.8796 | 2.64 | 145 | 5.7436 |
| 4.9344 | 2.73 | 150 | 5.7418 |
| 5.2387 | 2.82 | 155 | 5.7402 |
| 5.0734 | 2.91 | 160 | 5.7385 |
| 5.0227 | 3.0 | 165 | 5.7381 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1