Token Classification
Transformers
PyTorch
TensorBoard
distilbert
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("jakka/distilbert_ner")
model = AutoModelForTokenClassification.from_pretrained("jakka/distilbert_ner")Quick Links
distilbert_ner
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0578
- Precision: 0.9189
- Recall: 0.9357
- F1: 0.9272
- Accuracy: 0.9831
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0754 | 1.0 | 1756 | 0.0578 | 0.9189 | 0.9357 | 0.9272 | 0.9831 |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 3
Dataset used to train jakka/distilbert_ner
Evaluation results
- Precision on conll2003self-reported0.919
- Recall on conll2003self-reported0.936
- F1 on conll2003self-reported0.927
- Accuracy on conll2003self-reported0.983
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="jakka/distilbert_ner")