Distilbert Base Turkish Cased Allnli Tr

🚀 distilbert-base-turkish-cased_allnli_tr

This model is a fine - tuned version of dbmdz/distilbert-base-turkish-cased on the None dataset. It's designed for zero - shot classification tasks and achieves an accuracy of 0.7381 on the evaluation set.

🚀 Quick Start

This model can be used for zero - shot classification tasks. You can load it using the Hugging Face Transformers library and start making predictions.

✨ Features

• Zero - Shot Classification: Capable of classifying text into predefined labels without explicit training on those labels.
• Fine - Tuned on Turkish Data: Trained on Turkish datasets, making it suitable for Turkish language tasks.

📚 Documentation

Model Performance

It achieves the following results on the evaluation set:

• Loss: 0.6481
• Accuracy: 0.7381

Training and Evaluation Data

The model is fine - tuned on the nli_tr dataset.

Training Procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e - 05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Framework versions

• Transformers 4.12.3
• Pytorch 1.10.0+cu102
• Datasets 1.15.1
• Tokenizers 0.10.3

📄 License

This model is released under the Apache 2.0 license.