<!-- 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_gptdata_with_preprocessing_grid_search
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: 0.2221
- Precision: 0.9563
- Recall: 0.9566
- F1: 0.9562
- Accuracy: 0.9561
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 225 | 0.2531 | 0.9361 | 0.9359 | 0.9346 | 0.935 |
| No log | 2.0 | 450 | 0.1835 | 0.9514 | 0.9520 | 0.9512 | 0.9511 |
| 0.4372 | 3.0 | 675 | 0.1798 | 0.9543 | 0.9546 | 0.9539 | 0.9539 |
| 0.4372 | 4.0 | 900 | 0.2059 | 0.9499 | 0.9500 | 0.9497 | 0.9494 |
| 0.0575 | 5.0 | 1125 | 0.2002 | 0.9563 | 0.9567 | 0.9561 | 0.9561 |
| 0.0575 | 6.0 | 1350 | 0.2019 | 0.9557 | 0.9552 | 0.9553 | 0.955 |
| 0.0231 | 7.0 | 1575 | 0.2152 | 0.9548 | 0.9550 | 0.9546 | 0.9544 |
| 0.0231 | 8.0 | 1800 | 0.2156 | 0.9554 | 0.9556 | 0.9554 | 0.955 |
| 0.0116 | 9.0 | 2025 | 0.2240 | 0.9559 | 0.9561 | 0.9557 | 0.9556 |
| 0.0116 | 10.0 | 2250 | 0.2221 | 0.9563 | 0.9566 | 0.9562 | 0.9561 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
