relation_extraction_bert_base_uncased
This model is a fine-tuned version of bert-base-uncased on sem_eval_2010_task_8. It achieves the following results on the evaluation set:
- Loss: 0.9300
- F1: 0.8616
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: 5e-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: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.2511 | 1.0 | 107 | 0.6098 | 0.7907 |
| 0.437 | 2.0 | 214 | 0.5167 | 0.8453 |
| 0.1921 | 3.0 | 321 | 0.5446 | 0.8553 |
| 0.0795 | 4.0 | 428 | 0.7041 | 0.8527 |
| 0.0334 | 5.0 | 535 | 0.7774 | 0.8568 |
| 0.0124 | 6.0 | 642 | 0.8086 | 0.8490 |
| 0.0056 | 7.0 | 749 | 0.8615 | 0.8601 |
| 0.003 | 8.0 | 856 | 0.9246 | 0.8614 |
| 0.0014 | 9.0 | 963 | 0.9300 | 0.8616 |
| 0.0011 | 10.0 | 1070 | 0.9421 | 0.8613 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0