finetuned_distilbert-base-uncased
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9131
- Accuracy: 0.6527
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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.312 | 1.0 | 102 | 1.3010 | 0.4491 |
| 0.9641 | 2.0 | 204 | 1.0426 | 0.5849 |
| 0.7169 | 3.0 | 306 | 0.9691 | 0.6149 |
| 0.5669 | 4.0 | 408 | 0.9396 | 0.6450 |
| 0.4844 | 5.0 | 510 | 0.9648 | 0.6528 |
| 0.3777 | 6.0 | 612 | 1.0514 | 0.6440 |
| 0.2213 | 7.0 | 714 | 1.1531 | 0.6334 |
| 0.2404 | 8.0 | 816 | 1.2722 | 0.6208 |
| 0.2489 | 9.0 | 918 | 1.2879 | 0.6402 |
| 0.1874 | 10.0 | 1020 | 1.3072 | 0.6450 |
| 0.1495 | 11.0 | 1122 | 1.3683 | 0.6421 |
| 0.1417 | 12.0 | 1224 | 1.3803 | 0.6372 |
| 0.141 | 13.0 | 1326 | 1.4592 | 0.6305 |
| 0.1092 | 14.0 | 1428 | 1.5107 | 0.6295 |
| 0.1205 | 15.0 | 1530 | 1.5263 | 0.6334 |
| 0.1607 | 16.0 | 1632 | 1.5963 | 0.6188 |
| 0.127 | 17.0 | 1734 | 1.5691 | 0.6353 |
| 0.1358 | 18.0 | 1836 | 1.5574 | 0.6421 |
| 0.1192 | 19.0 | 1938 | 1.5713 | 0.6421 |
| 0.0898 | 20.0 | 2040 | 1.5733 | 0.6479 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2