|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- AdamCodd/emotion-balanced |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
widget: |
|
- text: "He looked out of the rain-streaked window, lost in thought, the faintest hint of melancholy in his eyes, as he remembered moments from a distant past." |
|
example_title: "Sadness" |
|
- text: "As she strolled through the park, a soft smile played on her lips, and her heart felt lighter with each step, appreciating the simple beauty of nature." |
|
example_title: "Joy" |
|
- text: "Their fingers brushed lightly as they exchanged a knowing glance, a subtle connection that spoke volumes about the deep affection they held for each other." |
|
example_title: "Love" |
|
- text: "She clenched her fists and took a deep breath, trying to suppress the simmering frustration that welled up when her ideas were dismissed without consideration." |
|
example_title: "Anger" |
|
- text: "In the quiet of the night, the gentle rustling of leaves outside her window sent shivers down her spine, leaving her feeling uneasy and vulnerable." |
|
example_title: "Fear" |
|
- text: "Upon opening the old dusty book, a delicate, hand-painted map fell out, revealing hidden treasures she never expected to find." |
|
example_title: "Surprise" |
|
base_model: distilbert-base-uncased |
|
model-index: |
|
- name: distilbert-base-uncased-finetuned-emotion-balanced |
|
results: |
|
- task: |
|
type: text-classification |
|
name: Text Classification |
|
dataset: |
|
name: emotion |
|
type: emotion |
|
args: default |
|
metrics: |
|
- type: accuracy |
|
value: 0.9354 |
|
name: Accuracy |
|
- type: loss |
|
value: 0.1809 |
|
name: Loss |
|
- type: f1 |
|
value: 0.9354946613311768 |
|
name: F1 |
|
--- |
|
|
|
# tinybert-emotion |
|
|
|
This model is a fine-tuned version of [bert-tiny](prajjwal1/bert-tiny) on the [emotion balanced dataset](https://huggingface.co/datasets/AdamCodd/emotion-balanced). |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1809 |
|
- Accuracy: 0.9354 |
|
|
|
## Model description |
|
|
|
TinyBERT is 7.5 times smaller and 9.4 times faster on inference compared to its teacher BERT model (while DistilBERT is 40% smaller and 1.6 times faster than BERT). The model has been trained on 89_754 examples split into train, validation and test. Each label was perfectly balanced in each split. |
|
|
|
## Intended uses & limitations |
|
|
|
This model is not as accurate as the [distilbert-emotion-balanced](AdamCodd/distilbert-base-uncased-finetuned-emotion-balanced) since speed was the focus, so it can misinterpret complex sentences. Despite this, its performance is quite good and should be more than enough for most use cases. |
|
|
|
Usage: |
|
```python |
|
from transformers import pipeline |
|
|
|
# Create the pipeline |
|
emotion_classifier = pipeline('text-classification', model='AdamCodd/tinybert-emotion-balanced') |
|
|
|
# Now you can use the pipeline to classify emotions |
|
result = emotion_classifier("We are delighted that you will be coming to visit us. It will be so nice to have you here.") |
|
print(result) |
|
#[{'label': 'joy', 'score': 0.9895486831665039}] |
|
``` |
|
This model faces challenges in accurately categorizing negative sentences, as well as those containing elements of sarcasm or irony. These limitations are largely attributable to TinyBERT's constrained capabilities in semantic understanding. Although the model is generally proficient in emotion detection tasks, it may lack the nuance necessary for interpreting complex emotional nuances. |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 3e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 64 |
|
- seed: 1270 |
|
- optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 150 |
|
- num_epochs: 10 |
|
- weight_decay: 0.01 |
|
|
|
### Training results |
|
|
|
precision recall f1-score support |
|
|
|
sadness 0.9733 0.9245 0.9482 1496 |
|
joy 0.9651 0.8864 0.9240 1496 |
|
love 0.9127 0.9786 0.9445 1496 |
|
anger 0.9479 0.9365 0.9422 1496 |
|
fear 0.9213 0.9004 0.9108 1496 |
|
surprise 0.9016 0.9866 0.9422 1496 |
|
|
|
accuracy 0.9355 8976 |
|
macro avg 0.9370 0.9355 0.9353 8976 |
|
weighted avg 0.9370 0.9355 0.9353 8976 |
|
|
|
test_acc: 0.9354946613311768 |
|
test_loss: 0.1809326708316803 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0 |
|
- Pytorch lightning 2.0.8 |
|
- Tokenizers 0.13.3 |
|
|
|
If you want to support me, you can [here](https://ko-fi.com/adamcodd). |
