<!-- 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. -->
distilbert-base-cased-distilled-squad
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1520
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 | 21 | 1.9314 |
No log | 2.0 | 42 | 1.4240 |
No log | 3.0 | 63 | 0.9511 |
No log | 4.0 | 84 | 0.7214 |
No log | 5.0 | 105 | 0.5664 |
No log | 6.0 | 126 | 0.4253 |
No log | 7.0 | 147 | 0.3588 |
No log | 8.0 | 168 | 0.3017 |
No log | 9.0 | 189 | 0.2381 |
No log | 10.0 | 210 | 0.2086 |
No log | 11.0 | 231 | 0.1909 |
No log | 12.0 | 252 | 0.1763 |
No log | 13.0 | 273 | 0.1590 |
No log | 14.0 | 294 | 0.1540 |
No log | 15.0 | 315 | 0.1520 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3