urgency_classifier / README.md
mr-kush's picture
Auto-deploy: ΔF1 >= 0.0010 (v20251030_150633)
5d9a47c verified
metadata
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: urgency_classifier
    results: []

urgency_classifier

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

  • Loss: 0.0258
  • Accuracy: 0.9187
  • F1 Macro: 0.9201
  • F1 Weighted: 0.9185
  • Precision Macro: 0.9203
  • Recall Macro: 0.9221
  • Precision Weighted: 0.9204
  • Recall Weighted: 0.9187

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: 32
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Macro F1 Weighted Precision Macro Recall Macro Precision Weighted Recall Weighted
0.0969 0.625 50 0.0419 0.7625 0.7566 0.7447 0.7724 0.7877 0.7773 0.7625
0.031 1.25 100 0.0272 0.8688 0.8704 0.8658 0.8697 0.8804 0.8725 0.8688
0.0202 1.875 150 0.0232 0.9 0.9022 0.8993 0.9015 0.9060 0.9015 0.9
0.0132 2.5 200 0.0258 0.9187 0.9201 0.9185 0.9203 0.9221 0.9204 0.9187

Framework versions

  • Transformers 4.57.1
  • Pytorch 2.9.0+cu128
  • Datasets 4.3.0
  • Tokenizers 0.22.1