metadata
tags:
- generated_from_trainer
datasets:
- wikiann
metrics:
- precision
- recall
- f1
- accuracy
model_index:
- name: distilbert-srb-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wikiann
type: wikiann
args: sr
metric:
name: Accuracy
type: accuracy
value: 0.9503250498060186
distilbert-srb-ner
This model was trained from scratch on the wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.1723
- Precision: 0.8667
- Recall: 0.8860
- F1: 0.8763
- Accuracy: 0.9503
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 |
---|---|---|---|---|---|---|---|
0.3839 | 1.0 | 625 | 0.2204 | 0.8112 | 0.8367 | 0.8238 | 0.9298 |
0.2004 | 2.0 | 1250 | 0.1805 | 0.8530 | 0.8676 | 0.8602 | 0.9442 |
0.1475 | 3.0 | 1875 | 0.1716 | 0.8536 | 0.8778 | 0.8655 | 0.9467 |
0.0943 | 4.0 | 2500 | 0.1723 | 0.8667 | 0.8860 | 0.8763 | 0.9503 |
Framework versions
- Transformers 4.9.2
- Pytorch 1.9.0
- Datasets 1.11.0
- Tokenizers 0.10.1