|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: Bert-Thesis-NonKFold |
|
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-Thesis-NonKFold |
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4861 |
|
- F1: 0.7464 |
|
- Recall: 0.7464 |
|
- Accuracy: 0.7464 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- 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 | F1 | Recall | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:--------:| |
|
| 1.0891 | 1.0 | 1446 | 0.9053 | 0.7222 | 0.7222 | 0.7222 | |
|
| 0.7239 | 2.0 | 2892 | 0.8697 | 0.7397 | 0.7397 | 0.7397 | |
|
| 0.4902 | 3.0 | 4338 | 0.8814 | 0.7491 | 0.7491 | 0.7491 | |
|
| 0.3287 | 4.0 | 5784 | 0.9655 | 0.7512 | 0.7512 | 0.7512 | |
|
| 0.2156 | 5.0 | 7230 | 1.0648 | 0.7450 | 0.7450 | 0.7450 | |
|
| 0.1473 | 6.0 | 8676 | 1.1826 | 0.7446 | 0.7446 | 0.7446 | |
|
| 0.1071 | 7.0 | 10122 | 1.2922 | 0.7465 | 0.7465 | 0.7465 | |
|
| 0.0692 | 8.0 | 11568 | 1.4034 | 0.7483 | 0.7483 | 0.7483 | |
|
| 0.0511 | 9.0 | 13014 | 1.4611 | 0.7478 | 0.7478 | 0.7478 | |
|
| 0.0386 | 10.0 | 14460 | 1.4861 | 0.7464 | 0.7464 | 0.7464 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|