metadata
tags:
- generated_from_trainer
datasets:
- wikiann
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wikiann
type: wikiann
config: es
split: train
args: es
metrics:
- name: Precision
type: precision
value: 0.8655875585178132
- name: Recall
type: recall
value: 0.889079054604727
- name: F1
type: f1
value: 0.8771760543561292
- name: Accuracy
type: accuracy
value: 0.9432045651459472
bert-finetuned-ner
This model was trained from scratch on the wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.2685
- Precision: 0.8656
- Recall: 0.8891
- F1: 0.8772
- Accuracy: 0.9432
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 |
|---|---|---|---|---|---|---|---|
| 0.245 | 1.0 | 2500 | 0.2470 | 0.8224 | 0.8577 | 0.8397 | 0.9303 |
| 0.1472 | 2.0 | 5000 | 0.2469 | 0.8651 | 0.8876 | 0.8762 | 0.9415 |
| 0.0965 | 3.0 | 7500 | 0.2685 | 0.8656 | 0.8891 | 0.8772 | 0.9432 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2