Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("Liberow/bert-finetuned-ner")
model = AutoModelForTokenClassification.from_pretrained("Liberow/bert-finetuned-ner")Quick Links
bert-finetuned-ner
This model is a fine-tuned version of google-bert/bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0584
- Precision: 0.9362
- Recall: 0.9515
- F1: 0.9438
- Accuracy: 0.9866
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 |
|---|---|---|---|---|---|---|---|
| 0.0767 | 1.0 | 1756 | 0.0665 | 0.8983 | 0.9295 | 0.9136 | 0.9809 |
| 0.0343 | 2.0 | 3512 | 0.0638 | 0.9283 | 0.9460 | 0.9371 | 0.9854 |
| 0.0204 | 3.0 | 5268 | 0.0584 | 0.9362 | 0.9515 | 0.9438 | 0.9866 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for Liberow/bert-finetuned-ner
Base model
google-bert/bert-base-casedDataset used to train Liberow/bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.936
- Recall on conll2003validation set self-reported0.952
- F1 on conll2003validation set self-reported0.944
- Accuracy on conll2003validation set self-reported0.987
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Liberow/bert-finetuned-ner")