bisoye's picture
End of training
dbddcef 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_5_epochs
    results: []

distilbert-base-uncased_new_ner_format_fn_5_epochs

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: 0.1611
  • Wer: 0.0319

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: 5

Training results

Training Loss Epoch Step Validation Loss Wer
0.0127 1.0 76 0.1793 0.0334
0.0129 2.0 152 0.1163 0.0281
0.0104 3.0 228 0.1637 0.0319
0.0055 4.0 304 0.1462 0.0326
0.0027 5.0 380 0.1611 0.0319

Framework versions

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