<!-- 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. -->
BERTModified-fullsize-finetuned-wikitext-test
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: 6.7813
- Precision: 0.1094
- Recall: 0.1094
- F1: 0.1094
- Accuracy: 0.1094
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 9.2391 | 1.0 | 4382 | 8.1610 | 0.0373 | 0.0373 | 0.0373 | 0.0373 |
| 7.9147 | 2.0 | 8764 | 7.6870 | 0.0635 | 0.0635 | 0.0635 | 0.0635 |
| 7.5164 | 3.0 | 13146 | 7.4388 | 0.0727 | 0.0727 | 0.0727 | 0.0727 |
| 7.2439 | 4.0 | 17528 | 7.2088 | 0.0930 | 0.0930 | 0.0930 | 0.0930 |
| 7.1068 | 5.0 | 21910 | 7.0455 | 0.0943 | 0.0943 | 0.0943 | 0.0943 |
| 6.9711 | 6.0 | 26292 | 6.9976 | 0.1054 | 0.1054 | 0.1054 | 0.1054 |
| 6.8486 | 7.0 | 30674 | 6.8850 | 0.1054 | 0.1054 | 0.1054 | 0.1054 |
| 6.78 | 8.0 | 35056 | 6.7990 | 0.1153 | 0.1153 | 0.1153 | 0.1153 |
| 6.73 | 9.0 | 39438 | 6.8041 | 0.1074 | 0.1074 | 0.1074 | 0.1074 |
| 6.6921 | 10.0 | 43820 | 6.7412 | 0.1251 | 0.1251 | 0.1251 | 0.1251 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.2
