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-base-cased-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: 0.9417717319177173
- name: Recall
type: recall
value: 0.9554022214742511
- name: F1
type: f1
value: 0.9485380116959065
- name: Accuracy
type: accuracy
value: 0.9877111909106964
bert-base-cased-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: 0.0683
- Precision: 0.9418
- Recall: 0.9554
- F1: 0.9485
- Accuracy: 0.9877
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0783 | 1.0 | 1756 | 0.0708 | 0.8922 | 0.9290 | 0.9102 | 0.9803 |
| 0.0361 | 2.0 | 3512 | 0.0706 | 0.9318 | 0.9467 | 0.9391 | 0.9850 |
| 0.022 | 3.0 | 5268 | 0.0592 | 0.9352 | 0.9524 | 0.9437 | 0.9867 |
| 0.0131 | 4.0 | 7024 | 0.0647 | 0.9389 | 0.9549 | 0.9469 | 0.9874 |
| 0.0068 | 5.0 | 8780 | 0.0683 | 0.9418 | 0.9554 | 0.9485 | 0.9877 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1