knowledge-graph-nlp
This model is a fine-tuned version of distilbert-base-uncased on the vishnun/NLP-KnowledgeGraph dataset. It achieves the following results on the evaluation set:
- Loss: 0.1830
- Precision: 0.8988
- Recall: 0.8715
- F1: 0.8849
- Accuracy: 0.9453
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2908 | 1.0 | 2316 | 0.2461 | 0.8455 | 0.8023 | 0.8234 | 0.9167 |
| 0.1973 | 2.0 | 4632 | 0.2000 | 0.8745 | 0.8446 | 0.8593 | 0.9341 |
| 0.1593 | 3.0 | 6948 | 0.1863 | 0.8973 | 0.8632 | 0.8799 | 0.9427 |
| 0.1336 | 4.0 | 9264 | 0.1830 | 0.8988 | 0.8715 | 0.8849 | 0.9453 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2