cyber_xlm_roberta / README.md
eysharaazia's picture
cyber_xlm_roberta
349f57e verified
metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: cyber_xlm_roberta
    results: []

cyber_xlm_roberta

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4037
  • Accuracy: 0.8200
  • F1: 0.8080
  • Precision: 0.8010
  • Recall: 0.8236

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: 1e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.5504 1.0 144 0.4762 0.7637 0.7467 0.7416 0.7580
0.4198 2.0 288 0.4175 0.7945 0.7819 0.7759 0.7987
0.4121 3.0 432 0.4079 0.8148 0.8035 0.7969 0.8215
0.3715 4.0 576 0.3859 0.8221 0.8064 0.8012 0.8138
0.3464 5.0 720 0.4037 0.8200 0.8080 0.8010 0.8236

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1