metadata

library_name: transformers
license: apache-2.0
base_model: google-bert/bert-large-uncased
tags:
  - generated_from_trainer
datasets:
  - lener_br
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-large-uncased-finetuned-ner-lenerBr
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: lener_br
          type: lener_br
          config: lener_br
          split: validation
          args: lener_br
        metrics:
          - name: Precision
            type: precision
            value: 0.8195459032576505
          - name: Recall
            type: recall
            value: 0.8534128289473685
          - name: F1
            type: f1
            value: 0.8361365696444758
          - name: Accuracy
            type: accuracy
            value: 0.9658050781203017

bert-large-uncased-finetuned-ner-lenerBr

This model is a fine-tuned version of google-bert/bert-large-uncased on the lener_br dataset. It achieves the following results on the evaluation set:

Loss: nan
Precision: 0.8195
Recall: 0.8534
F1: 0.8361
Accuracy: 0.9658

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: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.9995	489	nan	0.6811	0.7451	0.7116	0.9503
0.1982	1.9990	978	nan	0.7258	0.8314	0.7750	0.9536
0.0517	2.9985	1467	nan	0.7487	0.8238	0.7845	0.9587
0.0289	4.0	1957	nan	0.7801	0.8684	0.8219	0.9641
0.0191	4.9995	2446	nan	0.7986	0.8567	0.8266	0.9665
0.0138	5.9990	2935	nan	0.8120	0.8491	0.8302	0.9642
0.0097	6.9985	3424	nan	0.8201	0.8643	0.8416	0.9663
0.0076	8.0	3914	nan	0.8079	0.8672	0.8365	0.9660
0.0053	8.9995	4403	nan	0.8211	0.8409	0.8309	0.9662
0.0041	9.9949	4890	nan	0.8195	0.8534	0.8361	0.9658

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3