# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("pulkitkumar13/dark-bert-finetuned-ner1")
model = AutoModelForTokenClassification.from_pretrained("pulkitkumar13/dark-bert-finetuned-ner1")Quick Links
dark-bert-finetuned-ner1
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0833
- Precision: 0.9337
- Recall: 0.9487
- F1: 0.9411
- Accuracy: 0.9861
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0358 | 1.0 | 1756 | 0.0780 | 0.9283 | 0.9409 | 0.9346 | 0.9844 |
| 0.0172 | 2.0 | 3512 | 0.0708 | 0.9375 | 0.9488 | 0.9431 | 0.9860 |
| 0.0056 | 3.0 | 5268 | 0.0833 | 0.9337 | 0.9487 | 0.9411 | 0.9861 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.10.0
- Datasets 2.5.1
- Tokenizers 0.12.1
- Downloads last month
- 9
Dataset used to train pulkitkumar13/dark-bert-finetuned-ner1
Space using pulkitkumar13/dark-bert-finetuned-ner1 1
Evaluation results
- Precision on conll2003self-reported0.934
- Recall on conll2003self-reported0.949
- F1 on conll2003self-reported0.941
- Accuracy on conll2003self-reported0.986
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="pulkitkumar13/dark-bert-finetuned-ner1")