<!-- 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. -->
BertGoodCommitOriginal
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: 0.5639
- Accuracy: 0.8242
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 | 24 | 0.5844 | 0.7030 |
| No log | 2.0 | 48 | 0.5566 | 0.7212 |
| No log | 3.0 | 72 | 0.5375 | 0.7333 |
| No log | 4.0 | 96 | 0.5321 | 0.7212 |
| No log | 5.0 | 120 | 0.5221 | 0.7333 |
| No log | 6.0 | 144 | 0.5112 | 0.7394 |
| No log | 7.0 | 168 | 0.4828 | 0.7515 |
| No log | 8.0 | 192 | 0.4857 | 0.7818 |
| No log | 9.0 | 216 | 0.4672 | 0.7879 |
| No log | 10.0 | 240 | 0.4740 | 0.7879 |
| No log | 11.0 | 264 | 0.4758 | 0.7818 |
| No log | 12.0 | 288 | 0.4554 | 0.8061 |
| No log | 13.0 | 312 | 0.4697 | 0.8182 |
| No log | 14.0 | 336 | 0.4810 | 0.8242 |
| No log | 15.0 | 360 | 0.4612 | 0.8182 |
| No log | 16.0 | 384 | 0.4663 | 0.8242 |
| No log | 17.0 | 408 | 0.4757 | 0.8182 |
| No log | 18.0 | 432 | 0.4928 | 0.8182 |
| No log | 19.0 | 456 | 0.5371 | 0.8242 |
| No log | 20.0 | 480 | 0.5345 | 0.8182 |
| 0.3387 | 21.0 | 504 | 0.5341 | 0.8182 |
| 0.3387 | 22.0 | 528 | 0.5639 | 0.8242 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
