|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- emotion |
|
metrics: |
|
- accuracy |
|
- f1 |
|
widget: |
|
- text: on a boat trip to denmark |
|
example_title: Example 1 |
|
- text: i was feeling listless from the need of new things something different |
|
example_title: Example 2 |
|
- text: i know im feeling agitated as it is from a side effect of the too high dose |
|
example_title: Example 3 |
|
model-index: |
|
- name: distilbert-base-uncased-finetuned-emotions-dataset |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: emotion |
|
type: emotion |
|
config: split |
|
split: validation |
|
args: split |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9395 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9396359245863207 |
|
pipeline_tag: text-classification |
|
language: |
|
- en |
|
library_name: transformers |
|
--- |
|
|
|
<!-- 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-base-uncased-finetuned-emotions-dataset |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2428 |
|
- Accuracy: 0.9395 |
|
- F1: 0.9396 |
|
|
|
## Model description |
|
|
|
The model has been trained to classify text inputs into distinct emotional categories based on the fine-tuned understanding of the emotions dataset. |
|
The fine-tuned model has demonstrated high accuracy and F1 scores on the evaluation set. |
|
|
|
## Intended uses & limitations |
|
|
|
#### Intended Uses |
|
- Sentiment analysis |
|
- Emotional classification in text |
|
- Emotion-based recommendation systems |
|
|
|
#### Limitations |
|
- May show biases based on the training dataset |
|
- Optimized for emotional classification and may not cover nuanced emotional subtleties |
|
|
|
## Training and evaluation data |
|
Emotions dataset with labeled emotional categories [here](https://huggingface.co/datasets/dair-ai/emotion). |
|
|
|
#### The emotional categories are as follows: |
|
- LABEL_0: sadness |
|
- LABEL_1: joy |
|
- LABEL_2: love |
|
- LABEL_3: anger |
|
- LABEL_4: fear |
|
- LABEL_5: surprise |
|
|
|
## 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 | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.5929 | 1.0 | 500 | 0.2345 | 0.9185 | 0.9180 | |
|
| 0.1642 | 2.0 | 1000 | 0.1716 | 0.9335 | 0.9342 | |
|
| 0.1163 | 3.0 | 1500 | 0.1501 | 0.9405 | 0.9407 | |
|
| 0.0911 | 4.0 | 2000 | 0.1698 | 0.933 | 0.9331 | |
|
| 0.0741 | 5.0 | 2500 | 0.1926 | 0.932 | 0.9323 | |
|
| 0.0559 | 6.0 | 3000 | 0.2033 | 0.935 | 0.9353 | |
|
| 0.0464 | 7.0 | 3500 | 0.2156 | 0.935 | 0.9353 | |
|
| 0.0335 | 8.0 | 4000 | 0.2354 | 0.9405 | 0.9408 | |
|
| 0.0257 | 9.0 | 4500 | 0.2410 | 0.9395 | 0.9396 | |
|
| 0.0214 | 10.0 | 5000 | 0.2428 | 0.9395 | 0.9396 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
