albert-base-v2-finetuned-squad
This model is a fine-tuned version of albert-base-v2 on the squad_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 3.5840
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: 2e-05
- 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 313 | 1.2505 |
| 1.5439 | 2.0 | 626 | 1.1598 |
| 1.5439 | 3.0 | 939 | 1.2708 |
| 0.7133 | 4.0 | 1252 | 1.5814 |
| 0.3044 | 5.0 | 1565 | 2.0296 |
| 0.3044 | 6.0 | 1878 | 2.2515 |
| 0.1225 | 7.0 | 2191 | 2.4035 |
| 0.0586 | 8.0 | 2504 | 2.8478 |
| 0.0586 | 9.0 | 2817 | 3.0978 |
| 0.0225 | 10.0 | 3130 | 3.5416 |
| 0.0225 | 11.0 | 3443 | 3.5272 |
| 0.0071 | 12.0 | 3756 | 3.5285 |
| 0.0013 | 13.0 | 4069 | 3.5399 |
| 0.0013 | 14.0 | 4382 | 3.5729 |
| 0.0007 | 15.0 | 4695 | 3.5840 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3