Hugging Face's logo

osmanh
/
Bert-Contact-NLI

Zero-Shot Classification
Transformers
Safetensors
deberta-v2
text-classification
Generated from Trainer
Inference Endpoints
Model card Files Community
Bert-Contact-NLI / README.md
osmanh's picture
osmanh
Model save
e4de4b9 verified
preview code
|
raw
history blame
1.98 kB
metadata
library_name: transformers
license: mit
base_model: MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: Bert-Contact-NLI
    results: []

Bert-Contact-NLI

This model is a fine-tuned version of MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8424
  • Model Preparation Time: 0.0068
  • Accuracy: 0.6173
  • Precision: 0.6539
  • Recall: 0.5487
  • F1: 0.5668
  • Ratio: 0.4136

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
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • 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: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Model Preparation Time Accuracy Precision Recall F1 Ratio
No log 0.9895 47 0.8424 0.0068 0.6173 0.6539 0.5487 0.5668 0.4136

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3