GuiTap's picture
End of training
f237962 verified
|
raw
history blame
2.49 kB
metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-base-multilingual-uncased-finetuned-ner-harem
    results: []

bert-base-multilingual-uncased-finetuned-ner-harem

This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1861
  • Precision: 0.7833
  • Recall: 0.7589
  • F1: 0.7709
  • Accuracy: 0.9634

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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 282 0.2275 0.5847 0.6014 0.5929 0.9378
0.2687 2.0 564 0.1620 0.7389 0.6754 0.7057 0.9583
0.2687 3.0 846 0.1395 0.7820 0.7446 0.7628 0.9659
0.0845 4.0 1128 0.1694 0.7458 0.7351 0.7404 0.9586
0.0845 5.0 1410 0.1861 0.7833 0.7589 0.7709 0.9634
0.0398 6.0 1692 0.1821 0.7583 0.7637 0.7610 0.9639
0.0398 7.0 1974 0.2303 0.7789 0.7064 0.7409 0.9595
0.0203 8.0 2256 0.1912 0.7350 0.7876 0.7604 0.9629
0.0109 9.0 2538 0.2304 0.7524 0.7613 0.7568 0.9595
0.0109 10.0 2820 0.2457 0.7617 0.7399 0.7506 0.9622

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.1.2
  • Datasets 2.19.1
  • Tokenizers 0.19.1