metadata

license: apache-2.0
tags:
  - generated_from_trainer
base_model: bert-base-uncased
datasets:
  - conll2003
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: NER_Pittsburgh_TAA
    results:
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: validation
          args: conll2003
        metrics:
          - type: precision
            value: 0.9343718926085516
            name: Precision
          - type: recall
            value: 0.9460789797516501
            name: Recall
          - type: f1
            value: 0.940188993885492
            name: F1
          - type: accuracy
            value: 0.9858293484995313
            name: Accuracy

NER_Pittsburgh_TAA

This model is a fine-tuned version of bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:

Loss: 0.0599
Precision: 0.9344
Recall: 0.9461
F1: 0.9402
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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	439	0.0604	0.9175	0.9290	0.9232	0.9829
0.0953	2.0	878	0.0545	0.9312	0.9412	0.9361	0.9850
0.0409	3.0	1317	0.0571	0.9357	0.9412	0.9384	0.9855
0.0234	4.0	1756	0.0593	0.9343	0.9482	0.9412	0.9858
0.0159	5.0	2195	0.0599	0.9344	0.9461	0.9402	0.9858

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1