metadata
license: apache-2.0
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: train
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.8333333333333334
- name: Recall
type: recall
value: 0.9322033898305084
- name: F1
type: f1
value: 0.8800000000000001
- name: Accuracy
type: accuracy
value: 0.9725190839694656
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: 0.1193
- Precision: 0.8333
- Recall: 0.9322
- F1: 0.8800
- Accuracy: 0.9725
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 18 | 0.1216 | 0.8594 | 0.9322 | 0.8943 | 0.9740 |
| No log | 2.0 | 36 | 0.1200 | 0.8615 | 0.9492 | 0.9032 | 0.9740 |
| No log | 3.0 | 54 | 0.1193 | 0.8333 | 0.9322 | 0.8800 | 0.9725 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1