Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("mircoboettcher/bert-wnut17-final")
model = AutoModelForTokenClassification.from_pretrained("mircoboettcher/bert-wnut17-final")Quick Links
bert-wnut17-final
This model is a fine-tuned version of dslim/bert-base-NER on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3245
- Precision: 0.5604
- Recall: 0.3828
- F1: 0.4548
- Accuracy: 0.9482
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: 3.4590617775212224e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 213 | 0.2392 | 0.5203 | 0.4041 | 0.4549 | 0.9462 |
| No log | 2.0 | 426 | 0.2932 | 0.5818 | 0.3494 | 0.4366 | 0.9459 |
| 0.1758 | 3.0 | 639 | 0.3100 | 0.5768 | 0.3828 | 0.4602 | 0.9478 |
| 0.1758 | 4.0 | 852 | 0.3245 | 0.5604 | 0.3828 | 0.4548 | 0.9482 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 5
Model tree for mircoboettcher/bert-wnut17-final
Base model
dslim/bert-base-NERDataset used to train mircoboettcher/bert-wnut17-final
Evaluation results
- Precision on wnut_17test set self-reported0.560
- Recall on wnut_17test set self-reported0.383
- F1 on wnut_17test set self-reported0.455
- Accuracy on wnut_17test set self-reported0.948
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="mircoboettcher/bert-wnut17-final")