<!-- 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. -->
BertWhatCommitOriginal
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: 0.3530
- Accuracy: 0.9091
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 | 38 | 0.5485 | 0.7152 |
| No log | 2.0 | 76 | 0.4204 | 0.8364 |
| No log | 3.0 | 114 | 0.2951 | 0.8788 |
| No log | 4.0 | 152 | 0.2811 | 0.8848 |
| No log | 5.0 | 190 | 0.2628 | 0.8909 |
| No log | 6.0 | 228 | 0.2605 | 0.8970 |
| No log | 7.0 | 266 | 0.2790 | 0.8970 |
| No log | 8.0 | 304 | 0.2821 | 0.9030 |
| No log | 9.0 | 342 | 0.2724 | 0.9212 |
| No log | 10.0 | 380 | 0.2871 | 0.9091 |
| No log | 11.0 | 418 | 0.3067 | 0.9273 |
| No log | 12.0 | 456 | 0.3404 | 0.9273 |
| No log | 13.0 | 494 | 0.3645 | 0.9212 |
| 0.2027 | 14.0 | 532 | 0.3422 | 0.9152 |
| 0.2027 | 15.0 | 570 | 0.4038 | 0.9212 |
| 0.2027 | 16.0 | 608 | 0.3530 | 0.9091 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
