metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
datasets:
- conll2002
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: NER-finetuning-BETO-PRO
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: 0.7017726798748697
- name: Recall
type: recall
value: 0.7732077205882353
- name: F1
type: f1
value: 0.7357603585875151
- name: Accuracy
type: accuracy
value: 0.9536327652922068
NER-finetuning-BETO-PRO
This model is a fine-tuned version of google-bert/bert-base-uncased on the conll2002 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1981
- Precision: 0.7018
- Recall: 0.7732
- F1: 0.7358
- Accuracy: 0.9536
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 |
|---|---|---|---|---|---|---|---|
| 0.1941 | 1.0 | 1041 | 0.1965 | 0.6201 | 0.6836 | 0.6503 | 0.9422 |
| 0.1276 | 2.0 | 2082 | 0.1843 | 0.6666 | 0.7387 | 0.7008 | 0.9487 |
| 0.0885 | 3.0 | 3123 | 0.1760 | 0.7056 | 0.7601 | 0.7319 | 0.9538 |
| 0.0623 | 4.0 | 4164 | 0.1856 | 0.6982 | 0.7670 | 0.7310 | 0.9532 |
| 0.0485 | 5.0 | 5205 | 0.1981 | 0.7018 | 0.7732 | 0.7358 | 0.9536 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1