metadata
tags:
- generated_from_trainer
datasets:
- wikiann
metrics:
- precision
- recall
- f1
- accuracy
model_index:
- name: electra-srb-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wikiann
type: wikiann
args: sr
metric:
name: Accuracy
type: accuracy
value: 0.9500777931962491
electra-srb-ner
This model was trained from scratch on the wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.1859
- Precision: 0.8742
- Recall: 0.8907
- F1: 0.8824
- Accuracy: 0.9501
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.3627 | 1.0 | 625 | 0.2077 | 0.8382 | 0.8545 | 0.8463 | 0.9349 |
0.1894 | 2.0 | 1250 | 0.1764 | 0.8640 | 0.8760 | 0.8700 | 0.9453 |
0.1326 | 3.0 | 1875 | 0.1848 | 0.8618 | 0.8873 | 0.8744 | 0.9473 |
0.0712 | 4.0 | 2500 | 0.1859 | 0.8742 | 0.8907 | 0.8824 | 0.9501 |
Framework versions
- Transformers 4.9.2
- Pytorch 1.9.0
- Datasets 1.11.0
- Tokenizers 0.10.1