Edit model card

electra-base-italian-xxl-cased-discriminator-finetuned-ner

This model is a fine-tuned version of dbmdz/electra-base-italian-xxl-cased-discriminator on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1508
  • Precision: 0.8988
  • Recall: 0.9400
  • F1: 0.9189
  • Accuracy: 0.9659

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: 0.0002
  • 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: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.2868 1.0 1167 0.2063 0.7612 0.8782 0.8155 0.9346
0.1873 2.0 2334 0.1440 0.8623 0.9041 0.8827 0.9553
0.1339 3.0 3501 0.1376 0.8617 0.9308 0.8949 0.9576
0.1025 4.0 4668 0.1355 0.8649 0.9369 0.8995 0.9584
0.0844 5.0 5835 0.1325 0.8817 0.9400 0.9099 0.9617
0.0763 6.0 7002 0.1433 0.8922 0.9317 0.9115 0.9643
0.0601 7.0 8169 0.1479 0.8964 0.9286 0.9122 0.9640
0.0507 8.0 9336 0.1496 0.8915 0.9403 0.9152 0.9637
0.0408 9.0 10503 0.1501 0.8977 0.9350 0.9160 0.9643
0.0339 10.0 11670 0.1508 0.8988 0.9400 0.9189 0.9659

Framework versions

  • PEFT 0.11.1
  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
2
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for alexbeta80/electra-base-italian-xxl-cased-discriminator-finetuned-ner

Adapter
(1)
this model