|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: training-5 |
|
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. --> |
|
|
|
# training-5 |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co./bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0341 |
|
- Accuracy: 0.9952 |
|
- Precision: 0.9982 |
|
- Recall: 0.9841 |
|
- F1: 0.9911 |
|
|
|
## 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: 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 | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| No log | 0.25 | 151 | 0.0468 | 0.9923 | 1.0 | 0.9717 | 0.9856 | |
|
| No log | 0.5 | 302 | 0.0497 | 0.9908 | 0.9840 | 0.9823 | 0.9832 | |
|
| No log | 0.75 | 453 | 0.0571 | 0.9918 | 1.0 | 0.9699 | 0.9847 | |
|
| No log | 1.0 | 604 | 0.0319 | 0.9961 | 1.0 | 0.9858 | 0.9929 | |
|
| 0.0471 | 1.25 | 755 | 0.0353 | 0.9952 | 0.9982 | 0.9841 | 0.9911 | |
|
| 0.0471 | 1.5 | 906 | 0.0346 | 0.9942 | 0.9929 | 0.9858 | 0.9893 | |
|
| 0.0471 | 1.75 | 1057 | 0.0678 | 0.9899 | 0.9772 | 0.9858 | 0.9815 | |
|
| 0.0471 | 2.0 | 1208 | 0.0380 | 0.9952 | 1.0 | 0.9823 | 0.9911 | |
|
| 0.0156 | 2.25 | 1359 | 0.0362 | 0.9952 | 1.0 | 0.9823 | 0.9911 | |
|
| 0.0156 | 2.5 | 1510 | 0.0388 | 0.9942 | 0.9946 | 0.9841 | 0.9893 | |
|
| 0.0156 | 2.75 | 1661 | 0.0418 | 0.9952 | 1.0 | 0.9823 | 0.9911 | |
|
| 0.0156 | 3.0 | 1812 | 0.0333 | 0.9952 | 0.9982 | 0.9841 | 0.9911 | |
|
| 0.0121 | 3.24 | 1963 | 0.0326 | 0.9952 | 0.9982 | 0.9841 | 0.9911 | |
|
| 0.0121 | 3.49 | 2114 | 0.0309 | 0.9957 | 0.9982 | 0.9858 | 0.9920 | |
|
| 0.0121 | 3.74 | 2265 | 0.0311 | 0.9952 | 0.9982 | 0.9841 | 0.9911 | |
|
| 0.0121 | 3.99 | 2416 | 0.0344 | 0.9952 | 0.9982 | 0.9841 | 0.9911 | |
|
| 0.0084 | 4.24 | 2567 | 0.0334 | 0.9952 | 0.9982 | 0.9841 | 0.9911 | |
|
| 0.0084 | 4.49 | 2718 | 0.0327 | 0.9952 | 0.9982 | 0.9841 | 0.9911 | |
|
| 0.0084 | 4.74 | 2869 | 0.0336 | 0.9952 | 0.9982 | 0.9841 | 0.9911 | |
|
| 0.0084 | 4.99 | 3020 | 0.0341 | 0.9952 | 0.9982 | 0.9841 | 0.9911 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.2.0.dev20230913+cu121 |
|
- Tokenizers 0.13.3 |
|
|
