bert-base-multilingual-cased-wikiann
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the unimelb-nlp/wikiann dataset. It achieves the following results on the evaluation set:
- precision: 0.9184
- recall: 0.9286
- f1: 0.9235
- accuracy: 0.9710
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:
- num_train_epochs: 5
- train_batch_size: 16
- eval_batch_size: 32
- learning_rate: 2e-05
- weight_decay_rate: 0.01
- num_warmup_steps: 0
- fp16: True
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
Model tree for alinasrullayev/bert-base-multilingual-cased-wikiann
Base model
google-bert/bert-base-multilingual-casedDataset used to train alinasrullayev/bert-base-multilingual-cased-wikiann
Evaluation results
- precision on unimelb-nlp/wikiannself-reported0.918
- recall on unimelb-nlp/wikiannself-reported0.929
- f1 on unimelb-nlp/wikiannself-reported0.923
- accuracy on unimelb-nlp/wikiannself-reported0.971