|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- AdamCodd/emotion-balanced |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
widget: |
|
- text: Your actions were very caring. |
|
example_title: Test sentence |
|
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: 0.9521 |
|
name: Accuracy |
|
- type: loss |
|
value: 0.1216 |
|
name: Loss |
|
- type: f1 |
|
value: 0.9520944952964783 |
|
name: F1 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# distilbert-emotion |
|
|
|
<u><b>Reupload [10/02/23]</b></u> : The model has been retrained using identical hyperparameters, but this time on an even more pristine dataset, free of certain scraping artifacts. Remarkably, it maintains the same level of accuracy and loss while demonstrating superior generalization capabilities. |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [emotion balanced dataset](https://huggingface.co/datasets/AdamCodd/emotion-balanced). |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1216 |
|
- Accuracy: 0.9521 |
|
|
|
## Model description |
|
|
|
This emotion classifier has been trained on 89_754 examples split into train, validation and test. Each label was perfectly balanced in each split. |
|
|
|
## 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: 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: 1 |
|
- weight_decay: 0.01 |
|
|
|
### Training results |
|
|
|
precision recall f1-score support |
|
|
|
sadness 0.9882 0.9485 0.9679 1496 |
|
joy 0.9956 0.9057 0.9485 1496 |
|
love 0.9256 0.9980 0.9604 1496 |
|
anger 0.9628 0.9519 0.9573 1496 |
|
fear 0.9348 0.9098 0.9221 1496 |
|
surprise 0.9160 0.9987 0.9555 1496 |
|
|
|
accuracy 0.9521 8976 |
|
macro avg 0.9538 0.9521 0.9520 8976 |
|
weighted avg 0.9538 0.9521 0.9520 8976 |
|
|
|
test_acc: 0.9520944952964783 |
|
test_loss: 0.121663898229599 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch lightning 2.0.8 |
|
- Tokenizers 0.13.3 |
