metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wikiann
metrics:
- precision
- recall
- f1
- accuracy
base_model: bert-base-multilingual-cased
model-index:
- name: mbert-finetuned-azerbaijani-ner
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: wikiann
type: wikiann
args: az
metrics:
- type: precision
value: 0.8898541731306236
name: Precision
- type: recall
value: 0.915416533673795
name: Recall
- type: f1
value: 0.9024543738200126
name: F1
- type: accuracy
value: 0.966948310139165
name: Accuracy
mbert-finetuned-azerbaijani-ner
This model is a fine-tuned version of bert-base-multilingual-cased on the wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.1385
- Precision: 0.8899
- Recall: 0.9154
- F1: 0.9025
- Accuracy: 0.9669
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: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.2928 | 1.0 | 625 | 0.1415 | 0.8584 | 0.8918 | 0.8748 | 0.9595 |
| 0.1254 | 2.0 | 1250 | 0.1335 | 0.8875 | 0.9119 | 0.8996 | 0.9637 |
| 0.077 | 3.0 | 1875 | 0.1385 | 0.8899 | 0.9154 | 0.9025 | 0.9669 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.6