<!-- 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-finetuned-lr1e-06-epochs50
This model is a fine-tuned version of distilbert-base-cased-distilled-squad on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4198
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: 1e-06
- 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 9 | 4.5183 |
| No log | 2.0 | 18 | 4.2862 |
| No log | 3.0 | 27 | 4.1030 |
| No log | 4.0 | 36 | 3.9555 |
| No log | 5.0 | 45 | 3.8184 |
| No log | 6.0 | 54 | 3.6927 |
| No log | 7.0 | 63 | 3.5723 |
| No log | 8.0 | 72 | 3.4703 |
| No log | 9.0 | 81 | 3.3797 |
| No log | 10.0 | 90 | 3.3053 |
| No log | 11.0 | 99 | 3.2365 |
| No log | 12.0 | 108 | 3.1652 |
| No log | 13.0 | 117 | 3.0925 |
| No log | 14.0 | 126 | 3.0304 |
| No log | 15.0 | 135 | 2.9779 |
| No log | 16.0 | 144 | 2.9331 |
| No log | 17.0 | 153 | 2.8963 |
| No log | 18.0 | 162 | 2.8552 |
| No log | 19.0 | 171 | 2.8178 |
| No log | 20.0 | 180 | 2.7749 |
| No log | 21.0 | 189 | 2.7410 |
| No log | 22.0 | 198 | 2.7161 |
| No log | 23.0 | 207 | 2.6865 |
| No log | 24.0 | 216 | 2.6560 |
| No log | 25.0 | 225 | 2.6324 |
| No log | 26.0 | 234 | 2.6122 |
| No log | 27.0 | 243 | 2.5934 |
| No log | 28.0 | 252 | 2.5708 |
| No log | 29.0 | 261 | 2.5563 |
| No log | 30.0 | 270 | 2.5439 |
| No log | 31.0 | 279 | 2.5285 |
| No log | 32.0 | 288 | 2.5139 |
| No log | 33.0 | 297 | 2.5030 |
| No log | 34.0 | 306 | 2.4906 |
| No log | 35.0 | 315 | 2.4797 |
| No log | 36.0 | 324 | 2.4707 |
| No log | 37.0 | 333 | 2.4638 |
| No log | 38.0 | 342 | 2.4580 |
| No log | 39.0 | 351 | 2.4512 |
| No log | 40.0 | 360 | 2.4475 |
| No log | 41.0 | 369 | 2.4427 |
| No log | 42.0 | 378 | 2.4396 |
| No log | 43.0 | 387 | 2.4355 |
| No log | 44.0 | 396 | 2.4324 |
| No log | 45.0 | 405 | 2.4286 |
| No log | 46.0 | 414 | 2.4251 |
| No log | 47.0 | 423 | 2.4223 |
| No log | 48.0 | 432 | 2.4209 |
| No log | 49.0 | 441 | 2.4201 |
| No log | 50.0 | 450 | 2.4198 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
