|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: new-test-model2 |
|
|
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. --> |
|
|
|
|
|
# new-test-model2 |
|
|
|
|
|
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1040 |
|
|
- Precision: 0.9722 |
|
|
- Recall: 0.9757 |
|
|
- F1: 0.9739 |
|
|
- Accuracy: 0.9808 |
|
|
|
|
|
## 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: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| No log | 1.0 | 151 | 0.1819 | 0.9360 | 0.9405 | 0.9382 | 0.9540 | |
|
|
| No log | 2.0 | 302 | 0.1196 | 0.9637 | 0.9639 | 0.9638 | 0.9703 | |
|
|
| No log | 3.0 | 453 | 0.1322 | 0.9614 | 0.9682 | 0.9648 | 0.9711 | |
|
|
| 0.2764 | 4.0 | 604 | 0.1071 | 0.9677 | 0.9725 | 0.9701 | 0.9763 | |
|
|
| 0.2764 | 5.0 | 755 | 0.1084 | 0.9709 | 0.9766 | 0.9737 | 0.9790 | |
|
|
| 0.2764 | 6.0 | 906 | 0.1015 | 0.9717 | 0.9739 | 0.9728 | 0.9791 | |
|
|
| 0.0342 | 7.0 | 1057 | 0.1208 | 0.9686 | 0.9727 | 0.9706 | 0.9785 | |
|
|
| 0.0342 | 8.0 | 1208 | 0.1068 | 0.9680 | 0.9752 | 0.9716 | 0.9798 | |
|
|
| 0.0342 | 9.0 | 1359 | 0.1028 | 0.9719 | 0.9743 | 0.9731 | 0.9807 | |
|
|
| 0.0129 | 10.0 | 1510 | 0.1040 | 0.9722 | 0.9757 | 0.9739 | 0.9808 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.18.0 |
|
|
- Pytorch 1.11.0+cu113 |
|
|
- Datasets 2.1.0 |
|
|
- Tokenizers 0.12.1 |
|
|
|
