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: 0.9570619691726958

distilbert-srb-ner

This model was trained from scratch on the wikiann dataset. It achieves the following results on the evaluation set:

Loss: 0.2532
Precision: 0.8859
Recall: 0.9066
F1: 0.8962
Accuracy: 0.9571

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: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.2615	1.0	1250	0.2126	0.8268	0.8327	0.8297	0.9319
0.1568	2.0	2500	0.1775	0.8695	0.8699	0.8697	0.9472
0.1017	3.0	3750	0.1718	0.8649	0.8857	0.8752	0.9504
0.066	4.0	5000	0.1906	0.8734	0.8930	0.8831	0.9530
0.0413	5.0	6250	0.2076	0.8805	0.8992	0.8897	0.9549
0.03	6.0	7500	0.2257	0.8758	0.9045	0.8899	0.9554
0.0213	7.0	8750	0.2286	0.8864	0.9015	0.8939	0.9556
0.0157	8.0	10000	0.2454	0.8874	0.9021	0.8947	0.9566
0.01	9.0	11250	0.2486	0.8878	0.9043	0.8960	0.9573
0.0076	10.0	12500	0.2532	0.8859	0.9066	0.8962	0.9571

Framework versions

Transformers 4.9.2
Pytorch 1.9.0
Datasets 1.11.0
Tokenizers 0.10.1