metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_trainer
datasets:
- conll2002
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: NER-finetuning-Bert-base
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2002
type: conll2002
config: es
split: validation
args: es
metrics:
- name: Precision
type: precision
value: 0.8351917930419268
- name: Recall
type: recall
value: 0.8605238970588235
- name: F1
type: f1
value: 0.8476686283386147
- name: Accuracy
type: accuracy
value: 0.9714759394660772
NER-finetuning-Bert-base
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the conll2002 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1521
- Precision: 0.8352
- Recall: 0.8605
- F1: 0.8477
- Accuracy: 0.9715
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: 8
- eval_batch_size: 8
- seed: 42
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0855 | 1.0 | 1041 | 0.1281 | 0.8272 | 0.8371 | 0.8321 | 0.9688 |
| 0.0536 | 2.0 | 2082 | 0.1357 | 0.8134 | 0.8465 | 0.8296 | 0.9686 |
| 0.0333 | 3.0 | 3123 | 0.1227 | 0.8593 | 0.8713 | 0.8653 | 0.9740 |
| 0.0221 | 4.0 | 4164 | 0.1482 | 0.8474 | 0.8564 | 0.8519 | 0.9710 |
| 0.0163 | 5.0 | 5205 | 0.1521 | 0.8352 | 0.8605 | 0.8477 | 0.9715 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1