metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
- precision
model-index:
- name: distilbert-base-uncased_emotion_ft_0416
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: 0.9325
- name: F1
type: f1
value: 0.9327439172316551
- name: Precision
type: precision
value: 0.9027697506235867
distilbert-base-uncased_emotion_ft_0416
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: 0.1714
- Accuracy: 0.9325
- F1: 0.9327
- Precision: 0.9028
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: 2e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision |
|---|---|---|---|---|---|---|
| No log | 1.0 | 125 | 0.4267 | 0.877 | 0.8677 | 0.8778 |
| 0.6498 | 2.0 | 250 | 0.2128 | 0.922 | 0.9219 | 0.8975 |
| 0.6498 | 3.0 | 375 | 0.1880 | 0.925 | 0.9258 | 0.8877 |
| 0.1653 | 4.0 | 500 | 0.1714 | 0.9325 | 0.9327 | 0.9028 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.11.0