Text Classification
Transformers
PyTorch
TensorBoard
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("EulerianKnight/distilbert-base-uncased-finetuned-emotion")
model = AutoModelForSequenceClassification.from_pretrained("EulerianKnight/distilbert-base-uncased-finetuned-emotion", device_map="auto")Quick Links
distilbert-base-uncased-finetuned-emotion
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: 0.1423
- Accuracy: 0.936
- F1: 0.9363
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.7636 | 1.0 | 250 | 0.2512 | 0.915 | 0.9134 |
| 0.1965 | 2.0 | 500 | 0.1725 | 0.93 | 0.9300 |
| 0.1375 | 3.0 | 750 | 0.1475 | 0.935 | 0.9353 |
| 0.1061 | 4.0 | 1000 | 0.1499 | 0.936 | 0.9355 |
| 0.0892 | 5.0 | 1250 | 0.1423 | 0.936 | 0.9363 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 3
Dataset used to train EulerianKnight/distilbert-base-uncased-finetuned-emotion
Evaluation results
- Accuracy on emotionvalidation set self-reported0.936
- F1 on emotionvalidation set self-reported0.936
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="EulerianKnight/distilbert-base-uncased-finetuned-emotion")