metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: results
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9310117181052979
- name: Recall
type: recall
value: 0.9493436553349041
- name: F1
type: f1
value: 0.9400883259728355
- name: Accuracy
type: accuracy
value: 0.9857685288750221
results
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0575
- Precision: 0.9310
- Recall: 0.9493
- F1: 0.9401
- Accuracy: 0.9858
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 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2212 | 0.5695 | 500 | 0.0748 | 0.8824 | 0.9167 | 0.8992 | 0.9791 |
| 0.0698 | 1.1390 | 1000 | 0.0596 | 0.9141 | 0.9387 | 0.9263 | 0.9836 |
| 0.0465 | 1.7084 | 1500 | 0.0627 | 0.9235 | 0.9411 | 0.9322 | 0.9846 |
| 0.0313 | 2.2779 | 2000 | 0.0593 | 0.9315 | 0.9497 | 0.9405 | 0.9858 |
| 0.0244 | 2.8474 | 2500 | 0.0575 | 0.9310 | 0.9493 | 0.9401 | 0.9858 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0