bert-base-uncased-finetuned-scientific-exp
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1183
- Precision: 0.7109
- Recall: 0.7696
- F1: 0.7391
- Accuracy: 0.9674
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: 16
- eval_batch_size: 16
- 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 | 81 | 0.2439 | 0.53 | 0.4482 | 0.4857 | 0.9352 |
| No log | 2.0 | 162 | 0.1769 | 0.7434 | 0.5391 | 0.6250 | 0.9492 |
| No log | 3.0 | 243 | 0.1405 | 0.6967 | 0.6702 | 0.6832 | 0.9623 |
| No log | 4.0 | 324 | 0.1183 | 0.7109 | 0.7696 | 0.7391 | 0.9674 |
| No log | 5.0 | 405 | 0.1292 | 0.7126 | 0.7759 | 0.7429 | 0.9670 |
| No log | 6.0 | 486 | 0.1371 | 0.7159 | 0.7886 | 0.7505 | 0.9662 |
| 0.1665 | 7.0 | 567 | 0.1452 | 0.7137 | 0.7801 | 0.7455 | 0.9671 |
| 0.1665 | 8.0 | 648 | 0.1596 | 0.7071 | 0.8013 | 0.7512 | 0.9655 |
| 0.1665 | 9.0 | 729 | 0.1578 | 0.7084 | 0.8013 | 0.7520 | 0.9657 |
| 0.1665 | 10.0 | 810 | 0.1565 | 0.7173 | 0.7992 | 0.756 | 0.9666 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3