metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
- precision
model-index:
- name: distilbert-base-uncased_emotion_ft_0403
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: 0.9355
- name: F1
type: f1
value: 0.9355492121206211
- name: Precision
type: precision
value: 0.9171969908647357
distilbert-base-uncased_emotion_ft_0403
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: 0.1551
- Accuracy: 0.9355
- F1: 0.9355
- Precision: 0.9172
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|---|---|
| 0.8077 | 1.0 | 250 | 0.2865 | 0.9105 | 0.9107 | 0.8848 |
| 0.2054 | 2.0 | 500 | 0.1811 | 0.9315 | 0.9322 | 0.9022 |
| 0.1392 | 3.0 | 750 | 0.1686 | 0.933 | 0.9332 | 0.9103 |
| 0.1111 | 4.0 | 1000 | 0.1551 | 0.9355 | 0.9355 | 0.9172 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.2+cu118
- Datasets 2.14.4
- Tokenizers 0.14.1