This model is a fine-tuned version of bert-base-cased on the conll2003 dataset with a additional CRF. It achieves the following results on the evaluation set:
- F1: 0.95
- Precision: 0.95
- Recall: 0.95
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- Downloads last month
- 21
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for jacky20484096/fine_tune_bert_crf
Base model
google-bert/bert-base-cased