|
--- |
|
language: |
|
- ru |
|
license: apache-2.0 |
|
tags: |
|
- sentiment |
|
- emotion-classification |
|
- multilabel |
|
- multiclass |
|
datasets: |
|
- Djacon/ru_goemotions |
|
metrics: |
|
- accuracy |
|
widget: |
|
- text: Очень рад тебя видеть! |
|
- text: Как дела? |
|
- text: Мне немного отвратно это делать |
|
- text: Я испытал мурашки от страха |
|
- text: Нет ничего радостного в этих горьких новостях |
|
- text: Ого, неожидал тебя здесь увидеть! |
|
- text: Фу ну и мерзость |
|
- text: Мне неприятно общение с тобой |
|
base_model: ai-forever/ruBert-base |
|
model-index: |
|
- name: ruBert-base-russian-emotions-classifier-goEmotions |
|
results: |
|
- task: |
|
type: multilabel-text-classification |
|
name: Multilabel Text Classification |
|
dataset: |
|
name: ru_goemotions |
|
type: Djacon/ru_goemotions |
|
args: ru |
|
metrics: |
|
- type: roc_auc |
|
value: 92% |
|
name: multilabel ROC AUC |
|
--- |
|
|
|
|
|
# ruBert-base-russian-emotions-classifier-goEmotions |
|
|
|
This model is a fine-tuned version of [ai-forever/ruBert-base](https://huggingface.co/ai-forever/ruBert-base) on [Djacon/ru_goemotions](https://huggingface.co/datasets/Djacon/ru_goemotions). |
|
It achieves the following results on the evaluation set (2nd epoch): |
|
- Loss: 0.2088 |
|
- AUC: 0.9240 |
|
|
|
The quality of the predicted probabilities on the test dataset is the following: |
|
|
|
| label | joy | interest | surpise | sadness | anger | disgust | fear | guilt | neutral | average | |
|
|----------|--------|----------|---------|---------|--------|---------|--------|--------|---------|---------| |
|
| AUC | 0.9369 | 0.9213 | 0.9325 | 0.8791 | 0.8374 | 0.9041 | 0.9470 | 0.9758 | 0.8518 | 0.9095 | |
|
| F1-micro | 0.9528 | 0.9157 | 0.9697 | 0.9284 | 0.8690 | 0.9658 | 0.9851 | 0.9875 | 0.7654 | 0.9266 | |
|
| F1-macro | 0.8369 | 0.7922 | 0.7561 | 0.7392 | 0.7351 | 0.7356 | 0.8176 | 0.8247 | 0.7650 | 0.7781 | |
|
|
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | AUC | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.1755 | 1.0 | 1685 | 0.1717 | 0.9220 | |
|
| 0.1391 | 2.0 | 3370 | 0.1757 | 0.9240 | |
|
| 0.0899 | 3.0 | 5055 | 0.2088 | 0.9106 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.11.0 |
