metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
- precision
model-index:
- name: distilbert-base-uncased_emotion_ft_0523
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: 0.917
- name: F1
type: f1
value: 0.9167815299071149
- name: Precision
type: precision
value: 0.8882036697297124
distilbert-base-uncased_emotion_ft_0523
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: 0.2694
- Accuracy: 0.917
- F1: 0.9168
- Precision: 0.8882
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: 256
- eval_batch_size: 256
- 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 | 63 | 0.9564 | 0.641 | 0.5522 | 0.5005 |
| No log | 2.0 | 126 | 0.4544 | 0.8635 | 0.8507 | 0.8714 |
| No log | 3.0 | 189 | 0.2987 | 0.91 | 0.9093 | 0.8805 |
| 0.67 | 4.0 | 252 | 0.2694 | 0.917 | 0.9168 | 0.8882 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3