aimarsg's picture
update model card README.md
e1ccf74
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - xglue
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-finetuned-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: xglue
          type: xglue
          config: ner
          split: validation.es
          args: ner
        metrics:
          - name: Precision
            type: precision
            value: 0.6037969459347916
          - name: Recall
            type: recall
            value: 0.6720257234726688
          - name: F1
            type: f1
            value: 0.6360869565217391
          - name: Accuracy
            type: accuracy
            value: 0.9488508424567125

bert-finetuned-ner

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

  • Loss: 0.2202
  • Precision: 0.6038
  • Recall: 0.6720
  • F1: 0.6361
  • Accuracy: 0.9489

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 191 0.2359 0.5659 0.6309 0.5967 0.9397
No log 2.0 382 0.2136 0.5754 0.6681 0.6183 0.9464
0.1605 3.0 573 0.2202 0.6038 0.6720 0.6361 0.9489

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.13.1+cu116
  • Datasets 2.8.0
  • Tokenizers 0.13.2