metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model_index:
- name: ner_conll2003
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
args: conll2003
metric:
name: Accuracy
type: accuracy
value: 0.9769764744577354
ner_conll2003
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: 0.1551
- Precision: 0.8966
- Recall: 0.9065
- F1: 0.9015
- Accuracy: 0.9770
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3068 | 1.0 | 877 | 0.0589 | 0.9200 | 0.9388 | 0.9293 | 0.9837 |
| 0.0464 | 2.0 | 1754 | 0.0562 | 0.9298 | 0.9453 | 0.9375 | 0.9851 |
| 0.0233 | 3.0 | 2631 | 0.0559 | 0.9408 | 0.9472 | 0.9440 | 0.9865 |
| 0.0116 | 4.0 | 3508 | 0.0581 | 0.9421 | 0.9523 | 0.9472 | 0.9871 |
| 0.0068 | 5.0 | 4385 | 0.0620 | 0.9439 | 0.9521 | 0.9480 | 0.9871 |
Framework versions
- Transformers 4.9.1
- Pytorch 1.9.0+cu102
- Datasets 1.11.0
- Tokenizers 0.10.2