metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: Emotion-Detector
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: 0.9415
- name: F1
type: f1
value: 0.9412741950625149
Emotion-Detector
This model is a fine-tuned version of distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.2559
- Accuracy: 0.9415
- F1: 0.9413
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: 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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.3777 | 1.0 | 1000 | 0.1929 | 0.931 | 0.9320 |
0.139 | 2.0 | 2000 | 0.1698 | 0.9375 | 0.9365 |
0.0998 | 3.0 | 3000 | 0.1635 | 0.942 | 0.9422 |
0.0737 | 4.0 | 4000 | 0.2216 | 0.9415 | 0.9416 |
0.039 | 5.0 | 5000 | 0.2559 | 0.9415 | 0.9413 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1