bisoye's picture
End of training
2a00c1a verified
metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: distilbert-base-uncased_new_ner_format_fn
    results: []

distilbert-base-uncased_new_ner_format_fn

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

  • Loss: 0.1584
  • Wer: 0.0273

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: 4
  • eval_batch_size: 4
  • seed: 1010
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Wer
0.0027 1.0 76 0.1432 0.0266
0.0011 2.0 152 0.1584 0.0273

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0
  • Datasets 3.0.0
  • Tokenizers 0.19.1