|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: knowledge-graph-nlp |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# knowledge-graph-nlp |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [vishnun/NLP-KnowledgeGraph](https://huggingface.co/datasets/vishnun/NLP-KnowledgeGraph) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1765 |
|
- Precision: 0.9013 |
|
- Recall: 0.8807 |
|
- F1: 0.8909 |
|
- Accuracy: 0.9487 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2841 | 1.0 | 2316 | 0.2421 | 0.8382 | 0.8124 | 0.8251 | 0.9189 | |
|
| 0.1925 | 2.0 | 4632 | 0.1946 | 0.8752 | 0.8567 | 0.8658 | 0.9373 | |
|
| 0.1539 | 3.0 | 6948 | 0.1815 | 0.8912 | 0.8735 | 0.8822 | 0.9449 | |
|
| 0.1285 | 4.0 | 9264 | 0.1765 | 0.9013 | 0.8807 | 0.8909 | 0.9487 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
|
|
