<!-- 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. -->
BertWhyCommitPreprocessed
This model is a fine-tuned version of prajjwal1/bert-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4699
- Accuracy: 0.8848
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 31 | 0.5237 | 0.7333 |
| No log | 2.0 | 62 | 0.4632 | 0.7636 |
| No log | 3.0 | 93 | 0.4243 | 0.8 |
| No log | 4.0 | 124 | 0.3896 | 0.8182 |
| No log | 5.0 | 155 | 0.3824 | 0.8242 |
| No log | 6.0 | 186 | 0.3661 | 0.8182 |
| No log | 7.0 | 217 | 0.3597 | 0.8242 |
| No log | 8.0 | 248 | 0.3569 | 0.8364 |
| No log | 9.0 | 279 | 0.3518 | 0.8606 |
| No log | 10.0 | 310 | 0.3618 | 0.8485 |
| No log | 11.0 | 341 | 0.3462 | 0.8545 |
| No log | 12.0 | 372 | 0.3636 | 0.8485 |
| No log | 13.0 | 403 | 0.3759 | 0.8485 |
| No log | 14.0 | 434 | 0.3771 | 0.8727 |
| No log | 15.0 | 465 | 0.3957 | 0.8727 |
| No log | 16.0 | 496 | 0.4154 | 0.8788 |
| 0.2682 | 17.0 | 527 | 0.3980 | 0.8606 |
| 0.2682 | 18.0 | 558 | 0.4442 | 0.8667 |
| 0.2682 | 19.0 | 589 | 0.4028 | 0.8788 |
| 0.2682 | 20.0 | 620 | 0.4653 | 0.8606 |
| 0.2682 | 21.0 | 651 | 0.4699 | 0.8848 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
