metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9337409120951752
- name: Recall
type: recall
value: 0.9510265903736116
- name: F1
type: f1
value: 0.9423044855761216
- name: Accuracy
type: accuracy
value: 0.9866221227997881
bert-finetuned-ner
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: 0.0612
- Precision: 0.9337
- Recall: 0.9510
- F1: 0.9423
- 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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0756 | 1.0 | 1756 | 0.0713 | 0.8960 | 0.9280 | 0.9117 | 0.9803 |
| 0.0353 | 2.0 | 3512 | 0.0667 | 0.9280 | 0.9438 | 0.9358 | 0.9847 |
| 0.0203 | 3.0 | 5268 | 0.0612 | 0.9337 | 0.9510 | 0.9423 | 0.9866 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.1