metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-uncased-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: 0.9368619618286729
- name: Recall
type: recall
value: 0.9445128090390424
- name: F1
type: f1
value: 0.9406718288674726
- name: Accuracy
type: accuracy
value: 0.985892894021955
bert-base-uncased-finetuned-ner
This model is a fine-tuned version of bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0560
- Precision: 0.9369
- Recall: 0.9445
- F1: 0.9407
- Accuracy: 0.9859
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: 16
- eval_batch_size: 16
- 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 |
---|---|---|---|---|---|---|---|
0.2175 | 1.0 | 878 | 0.0591 | 0.9263 | 0.9328 | 0.9295 | 0.9841 |
0.0493 | 2.0 | 1756 | 0.0543 | 0.9345 | 0.9422 | 0.9383 | 0.9855 |
0.0242 | 3.0 | 2634 | 0.0560 | 0.9369 | 0.9445 | 0.9407 | 0.9859 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.1
- Datasets 2.12.0
- Tokenizers 0.13.3