|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: BERT_with_preprocessing_grid_search |
|
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. --> |
|
|
|
# BERT_with_preprocessing_grid_search |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9072 |
|
- Precision: 0.8332 |
|
- Recall: 0.8192 |
|
- F1: 0.8259 |
|
- Accuracy: 0.8660 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 1.0741 | 1.0 | 510 | 0.6328 | 0.7761 | 0.8093 | 0.7820 | 0.8292 | |
|
| 0.465 | 2.0 | 1020 | 0.5751 | 0.8326 | 0.8237 | 0.8265 | 0.8625 | |
|
| 0.2979 | 3.0 | 1530 | 0.5442 | 0.8285 | 0.8482 | 0.8370 | 0.8719 | |
|
| 0.2312 | 4.0 | 2040 | 0.6811 | 0.8434 | 0.8298 | 0.8350 | 0.8665 | |
|
| 0.1609 | 5.0 | 2550 | 0.6873 | 0.8216 | 0.8338 | 0.8271 | 0.8635 | |
|
| 0.14 | 6.0 | 3060 | 0.8476 | 0.8386 | 0.8175 | 0.8265 | 0.8640 | |
|
| 0.1135 | 7.0 | 3570 | 0.8456 | 0.8302 | 0.8202 | 0.8249 | 0.8630 | |
|
| 0.0973 | 8.0 | 4080 | 0.8595 | 0.8307 | 0.8186 | 0.8243 | 0.8625 | |
|
| 0.0758 | 9.0 | 4590 | 0.8828 | 0.8306 | 0.8201 | 0.8251 | 0.8655 | |
|
| 0.0669 | 10.0 | 5100 | 0.9072 | 0.8332 | 0.8192 | 0.8259 | 0.8660 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|