distilbert-base-uncased-finetuned-wikiandmark_epoch20
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: 0.0561
- Accuracy: 0.9944
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0224 | 1.0 | 1859 | 0.0277 | 0.9919 |
| 0.0103 | 2.0 | 3718 | 0.0298 | 0.9925 |
| 0.0047 | 3.0 | 5577 | 0.0429 | 0.9924 |
| 0.0038 | 4.0 | 7436 | 0.0569 | 0.9922 |
| 0.0019 | 5.0 | 9295 | 0.0554 | 0.9936 |
| 0.0028 | 6.0 | 11154 | 0.0575 | 0.9928 |
| 0.002 | 7.0 | 13013 | 0.0544 | 0.9926 |
| 0.0017 | 8.0 | 14872 | 0.0553 | 0.9935 |
| 0.001 | 9.0 | 16731 | 0.0498 | 0.9924 |
| 0.0001 | 10.0 | 18590 | 0.0398 | 0.9934 |
| 0.0 | 11.0 | 20449 | 0.0617 | 0.9935 |
| 0.0002 | 12.0 | 22308 | 0.0561 | 0.9944 |
| 0.0002 | 13.0 | 24167 | 0.0755 | 0.9934 |
| 0.0 | 14.0 | 26026 | 0.0592 | 0.9941 |
| 0.0 | 15.0 | 27885 | 0.0572 | 0.9939 |
| 0.0 | 16.0 | 29744 | 0.0563 | 0.9941 |
| 0.0 | 17.0 | 31603 | 0.0587 | 0.9936 |
| 0.0005 | 18.0 | 33462 | 0.0673 | 0.9937 |
| 0.0 | 19.0 | 35321 | 0.0651 | 0.9933 |
| 0.0 | 20.0 | 37180 | 0.0683 | 0.9936 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.