<!-- 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-uncased-finetuned-as_sentences_fewshot
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0227
- Accuracy: 0.9933
- F1: 0.9933
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: 32
- eval_batch_size: 32
- 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6953 | 1.0 | 11 | 0.6832 | 0.6267 | 0.5993 |
| 0.6562 | 2.0 | 22 | 0.5071 | 0.9267 | 0.9268 |
| 0.4346 | 3.0 | 33 | 0.1365 | 0.9933 | 0.9933 |
| 0.1714 | 4.0 | 44 | 0.0566 | 0.9933 | 0.9933 |
| 0.1125 | 5.0 | 55 | 0.0234 | 1.0 | 1.0 |
| 0.0897 | 6.0 | 66 | 0.0264 | 0.9933 | 0.9933 |
| 0.0487 | 7.0 | 77 | 0.0465 | 0.9867 | 0.9867 |
| 0.0401 | 8.0 | 88 | 0.0082 | 1.0 | 1.0 |
| 0.0364 | 9.0 | 99 | 0.0273 | 0.9933 | 0.9933 |
| 0.0237 | 10.0 | 110 | 0.0163 | 0.9933 | 0.9933 |
| 0.0209 | 11.0 | 121 | 0.0044 | 1.0 | 1.0 |
| 0.0196 | 12.0 | 132 | 0.0056 | 1.0 | 1.0 |
| 0.0198 | 13.0 | 143 | 0.0059 | 1.0 | 1.0 |
| 0.0047 | 14.0 | 154 | 0.0063 | 1.0 | 1.0 |
| 0.0157 | 15.0 | 165 | 0.0115 | 0.9933 | 0.9933 |
| 0.0142 | 16.0 | 176 | 0.0116 | 0.9933 | 0.9933 |
| 0.0035 | 17.0 | 187 | 0.0111 | 0.9933 | 0.9933 |
| 0.0028 | 18.0 | 198 | 0.0114 | 0.9933 | 0.9933 |
| 0.0023 | 19.0 | 209 | 0.0103 | 0.9933 | 0.9933 |
| 0.0019 | 20.0 | 220 | 0.0102 | 0.9933 | 0.9933 |
| 0.0016 | 21.0 | 231 | 0.0117 | 0.9933 | 0.9933 |
| 0.0016 | 22.0 | 242 | 0.0103 | 0.9933 | 0.9933 |
| 0.0014 | 23.0 | 253 | 0.0072 | 0.9933 | 0.9933 |
| 0.0014 | 24.0 | 264 | 0.0059 | 0.9933 | 0.9933 |
| 0.0013 | 25.0 | 275 | 0.0071 | 0.9933 | 0.9933 |
| 0.0012 | 26.0 | 286 | 0.0079 | 0.9933 | 0.9933 |
| 0.0012 | 27.0 | 297 | 0.0076 | 0.9933 | 0.9933 |
| 0.0011 | 28.0 | 308 | 0.0076 | 0.9933 | 0.9933 |
| 0.001 | 29.0 | 319 | 0.0085 | 0.9933 | 0.9933 |
| 0.0009 | 30.0 | 330 | 0.0088 | 0.9933 | 0.9933 |
| 0.001 | 31.0 | 341 | 0.0089 | 0.9933 | 0.9933 |
| 0.0009 | 32.0 | 352 | 0.0092 | 0.9933 | 0.9933 |
| 0.0009 | 33.0 | 363 | 0.0091 | 0.9933 | 0.9933 |
| 0.0008 | 34.0 | 374 | 0.0100 | 0.9933 | 0.9933 |
| 0.0021 | 35.0 | 385 | 0.0312 | 0.9933 | 0.9933 |
| 0.0008 | 36.0 | 396 | 0.0340 | 0.9933 | 0.9933 |
| 0.0009 | 37.0 | 407 | 0.0313 | 0.9933 | 0.9933 |
| 0.0008 | 38.0 | 418 | 0.0278 | 0.9933 | 0.9933 |
| 0.0008 | 39.0 | 429 | 0.0246 | 0.9933 | 0.9933 |
| 0.0008 | 40.0 | 440 | 0.0226 | 0.9933 | 0.9933 |
| 0.0007 | 41.0 | 451 | 0.0212 | 0.9933 | 0.9933 |
| 0.0007 | 42.0 | 462 | 0.0200 | 0.9933 | 0.9933 |
| 0.0007 | 43.0 | 473 | 0.0241 | 0.9933 | 0.9933 |
| 0.0007 | 44.0 | 484 | 0.0249 | 0.9933 | 0.9933 |
| 0.0007 | 45.0 | 495 | 0.0244 | 0.9933 | 0.9933 |
| 0.0007 | 46.0 | 506 | 0.0238 | 0.9933 | 0.9933 |
| 0.0007 | 47.0 | 517 | 0.0234 | 0.9933 | 0.9933 |
| 0.0006 | 48.0 | 528 | 0.0230 | 0.9933 | 0.9933 |
| 0.0007 | 49.0 | 539 | 0.0227 | 0.9933 | 0.9933 |
| 0.0007 | 50.0 | 550 | 0.0227 | 0.9933 | 0.9933 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
