stulcrad's picture
End of training
f455b84 verified
metadata
license: mit
base_model: xlm-roberta-large
tags:
  - generated_from_trainer
model-index:
  - name: fine_tuned_XLMROBERTA_cs_wikann
    results: []

fine_tuned_XLMROBERTA_cs_wikann

This model is a fine-tuned version of xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1238
  • Overall Precision: 0.8962
  • Overall Recall: 0.9193
  • Overall F1: 0.9076
  • Overall Accuracy: 0.9684

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: 3.0

Training results

Training Loss Epoch Step Validation Loss Overall Precision Overall Recall Overall F1 Overall Accuracy
0.3625 0.4 500 0.1809 0.7915 0.8509 0.8201 0.9486
0.1807 0.8 1000 0.1373 0.8363 0.8785 0.8568 0.9583
0.1384 1.2 1500 0.1371 0.8758 0.9085 0.8918 0.9651
0.1079 1.6 2000 0.1467 0.8924 0.9168 0.9044 0.9659
0.0997 2.0 2500 0.1170 0.9018 0.9264 0.9139 0.9700
0.0644 2.4 3000 0.1344 0.9123 0.9285 0.9203 0.9706
0.0594 2.8 3500 0.1269 0.9138 0.9345 0.9240 0.9718

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0