metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
- Multiple Choice
metrics:
- accuracy
model-index:
- name: bert-base-uncased-e_CARE
results: []
datasets:
- 12ml/e-CARE
language:
- en
pipeline_tag: question-answering
bert-base-uncased-e_CARE
This model is a fine-tuned version of bert-base-uncased.
It achieves the following results on the evaluation set:
- Loss: 1.7677
- Accuracy: 0.7212
Model description
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Multiple%20Choice/e-CARE/e_CARE_Multiple_Choice_Using_BERT.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/12ml/e-CARE
Histogram of Input Lengths
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5637 | 1.0 | 1571 | 0.5282 | 0.7244 |
| 0.345 | 2.0 | 3142 | 0.6667 | 0.7320 |
| 0.1098 | 3.0 | 4713 | 1.3113 | 0.7257 |
| 0.0212 | 4.0 | 6284 | 1.8194 | 0.7225 |
| 0.0185 | 5.0 | 7855 | 1.7677 | 0.7212 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3