Aleksandar's picture
add model
989666f
|
raw
history blame
1.95 kB
metadata
tags:
  - generated_from_trainer
datasets:
  - null
metrics:
  - precision
  - recall
  - f1
  - accuracy
model_index:
  - name: bert-srb-ner-setimes
    results:
      - task:
          name: Token Classification
          type: token-classification
        metric:
          name: Accuracy
          type: accuracy
          value: 0.9589059598176599

bert-srb-ner-setimes

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1430
  • Precision: 0.7811
  • Recall: 0.8141
  • F1: 0.7973
  • Accuracy: 0.9589

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: 16
  • eval_batch_size: 8
  • 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 1.0 207 0.2001 0.7109 0.7505 0.7301 0.9422
No log 2.0 414 0.1581 0.7347 0.7792 0.7563 0.9510
0.2354 3.0 621 0.1506 0.7612 0.8034 0.7818 0.9555
0.2354 4.0 828 0.1534 0.7728 0.8082 0.7901 0.9569
0.0883 5.0 1035 0.1430 0.7811 0.8141 0.7973 0.9589

Framework versions

  • Transformers 4.9.2
  • Pytorch 1.9.0
  • Datasets 1.11.0
  • Tokenizers 0.10.1