metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-crf-ner-conll2003
results: []
bert-crf-ner-conll2003
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7776
- Precision: 0.9454
- Recall: 0.9495
- F1: 0.9474
- Accuracy: 0.9908
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.7572 | 1.0 | 878 | 0.7882 | 0.9112 | 0.9253 | 0.9182 | 0.9868 |
| 0.2013 | 2.0 | 1756 | 0.7316 | 0.9384 | 0.9456 | 0.9420 | 0.9898 |
| 0.1517 | 3.0 | 2634 | 0.7776 | 0.9454 | 0.9495 | 0.9474 | 0.9908 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2