metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
- NLP Regression
- Regression
- Edmunds Car Reviews
model-index:
- name: bert-base-uncased-Regression-Edmunds_Car_Reviews
results: []
language:
- en
metrics:
- mse
- mae
bert-base-uncased-Regression-Edmunds_Car_Reviews
This model is a fine-tuned version of bert-base-uncased.
It achieves the following results on the evaluation set:
- Loss: 0.2324
- Mse: 0.2324
- Rmse: 0.4820
- Mae: 0.3089
Model description
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/NLP%20Regression/Edmunds%20Car%20Reviews%20(BERT-Base)/Edmunds_Consumer_car_Regression_All_Manufacturers_Bert_Base.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://www.kaggle.com/datasets/ankkur13/edmundsconsumer-car-ratings-and-reviews
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Rmse | Mae |
|---|---|---|---|---|---|---|
| 0.2142 | 1.0 | 11430 | 0.2421 | 0.2421 | 0.4920 | 0.3126 |
| 0.1931 | 2.0 | 22860 | 0.2530 | 0.2530 | 0.5030 | 0.3336 |
| 0.1192 | 3.0 | 34290 | 0.2324 | 0.2324 | 0.4820 | 0.3089 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3