metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-large-cased
tags:
- generated_from_trainer
datasets:
- conll2002
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: NER-finetunining-Bert-Large-cased
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: 0.7852760736196319
- name: Recall
type: recall
value: 0.8235294117647058
- name: F1
type: f1
value: 0.803947958725886
- name: Accuracy
type: accuracy
value: 0.9718248345206437
NER-finetunining-Bert-Large-cased
This model is a fine-tuned version of google-bert/bert-large-cased on the conll2002 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1418
- Precision: 0.7853
- Recall: 0.8235
- F1: 0.8039
- Accuracy: 0.9718
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0896 | 1.0 | 1041 | 0.1297 | 0.7488 | 0.7829 | 0.7654 | 0.9667 |
| 0.0525 | 2.0 | 2082 | 0.1303 | 0.7548 | 0.8134 | 0.7830 | 0.9691 |
| 0.0275 | 3.0 | 3123 | 0.1418 | 0.7853 | 0.8235 | 0.8039 | 0.9718 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1