|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: ibert-roberta-base-finetuned-WikiNeural |
|
|
results: [] |
|
|
datasets: |
|
|
- Babelscape/wikineural |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
- recall |
|
|
- precision |
|
|
- seqeval |
|
|
pipeline_tag: token-classification |
|
|
--- |
|
|
|
|
|
# ibert-roberta-base-finetuned-WikiNeural |
|
|
|
|
|
This model is a fine-tuned version of [kssteven/ibert-roberta-base](https://huggingface.co/kssteven/ibert-roberta-base). |
|
|
|
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0878 |
|
|
- Loc: {'precision': 0.9249338624338624, 'recall': 0.9393786733837112, 'f1': 0.9321003082562693, 'number': 5955} |
|
|
- Misc: {'precision': 0.8304751697034656, 'recall': 0.9185931634064414, 'f1': 0.8723144760296463, 'number': 5061} |
|
|
- Org: {'precision': 0.9283453237410072, 'recall': 0.9353435778486517, 'f1': 0.9318313113807049, 'number': 3449} |
|
|
- Per: {'precision': 0.9698098412076064, 'recall': 0.9495201535508637, 'f1': 0.9595577538551062, 'number': 5210} |
|
|
- Overall Precision: 0.9107 |
|
|
- Overall Recall: 0.9360 |
|
|
- Overall F1: 0.9232 |
|
|
- Overall Accuracy: 0.9909 |
|
|
|
|
|
## Model description |
|
|
|
|
|
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Token%20Classification/Monolingual/WikiNeural%20-%20Transformer%20Comparison/POS%20Project%20with%20Wikineural%20Dataset%20-%20I-BERT%20Transformer.ipynb |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
This model is intended to demonstrate my ability to solve a complex problem using technology. |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
Dataset Source: https://huggingface.co/datasets/Babelscape/wikineural |
|
|
|
|
|
## 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: 2 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Loc | Misc | Org | Per | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| |
|
|
| 0.1092 | 1.0 | 5795 | 0.0987 | {'precision': 0.9124507227332457, 'recall': 0.9328295549958019, 'f1': 0.9225276093996512, 'number': 5955} | {'precision': 0.8003130979300748, 'recall': 0.9091088717644734, 'f1': 0.8512488436632748, 'number': 5061} | {'precision': 0.9142857142857143, 'recall': 0.9278051609162076, 'f1': 0.9209958267376601, 'number': 3449} | {'precision': 0.9714229013693193, 'recall': 0.9395393474088292, 'f1': 0.9552151429407748, 'number': 5210} | 0.8957 | 0.9276 | 0.9114 | 0.9890 | |
|
|
| 0.0723 | 2.0 | 11590 | 0.0878 | {'precision': 0.9249338624338624, 'recall': 0.9393786733837112, 'f1': 0.9321003082562693, 'number': 5955} | {'precision': 0.8304751697034656, 'recall': 0.9185931634064414, 'f1': 0.8723144760296463, 'number': 5061} | {'precision': 0.9283453237410072, 'recall': 0.9353435778486517, 'f1': 0.9318313113807049, 'number': 3449} | {'precision': 0.9698098412076064, 'recall': 0.9495201535508637, 'f1': 0.9595577538551062, 'number': 5210} | 0.9107 | 0.9360 | 0.9232 | 0.9909 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.28.1 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.13.0 |
|
|
- Tokenizers 0.13.3 |
