---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: kg_model
  results: []
datasets:
- vishnun/NLP-KnowledgeGraph
---

<!-- 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. -->

# kg_model

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the custom built dataset from publicaly available sentences dataset in Kaggle dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2587
- Precision: 0.8356
- Recall: 0.8057
- F1: 0.8204
- Accuracy: 0.9170

## Model description

Finetuned model for knowledge graph creation in NLP. The dataset(~20k) was created by creating KG using the spaCy library. The original dataset is available in [kaggle](https://www.kaggle.com/datasets/mfekadu/sentences)

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.4931        | 1.0   | 957  | 0.3031          | 0.7872    | 0.7592 | 0.7729 | 0.8935   |
| 0.2693        | 2.0   | 1914 | 0.2645          | 0.8345    | 0.7868 | 0.8100 | 0.9110   |
| 0.2142        | 3.0   | 2871 | 0.2602          | 0.8330    | 0.7980 | 0.8152 | 0.9152   |
| 0.1894        | 4.0   | 3828 | 0.2587          | 0.8356    | 0.8057 | 0.8204 | 0.9170   |


### Framework versions

- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2