|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: Homophobia-Transphobia-v2-mBERT-EDA |
|
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. --> |
|
|
|
# Homophobia-Transphobia-v2-mBERT-EDA |
|
|
|
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5401 |
|
- Accuracy: 0.9317 |
|
- F1: 0.4498 |
|
|
|
## 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.1699 | 1.0 | 189 | 0.4125 | 0.9229 | 0.4634 | |
|
| 0.0387 | 2.0 | 378 | 0.4658 | 0.9229 | 0.3689 | |
|
| 0.0148 | 3.0 | 567 | 0.5250 | 0.9355 | 0.4376 | |
|
| 0.0005 | 4.0 | 756 | 0.5336 | 0.9317 | 0.4531 | |
|
| 0.0016 | 5.0 | 945 | 0.5401 | 0.9317 | 0.4498 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0 |
|
- Pytorch 1.10.2+cu102 |
|
- Datasets 1.18.4 |
|
- Tokenizers 0.11.6 |
|
|
