ahmed792002's picture
ahmed792002/Finetuning_XLNET_Paraphrase_Classification
b5944da verified
metadata
library_name: transformers
license: mit
base_model: xlnet-base-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: Finetuning_XLNET_Paraphrase_Classification
    results: []

Finetuning_XLNET_Paraphrase_Classification

This model is a fine-tuned version of xlnet-base-cased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9155
  • Accuracy: 0.8701
  • F1: 0.8671

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.5517 1.0 619 0.3508 0.8529 0.8513
0.3345 2.0 1238 0.4829 0.8725 0.8711
0.2295 3.0 1857 0.9169 0.8627 0.8585
0.1313 4.0 2476 0.8408 0.8652 0.8624
0.0398 5.0 3095 0.9155 0.8701 0.8671

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3