Hugging Face's logo

kxx-kkk
/
FYP_qa_final

Question Answering
Transformers
TensorBoard
Safetensors
English
deberta-v2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
FYP_qa_final / README.md
kxx-kkk's picture
kxx-kkk
End of training
1831dc2 verified
preview code
|
raw
history blame
No virus
1.63 kB
metadata
license: cc-by-4.0
base_model: kxx-kkk/FYP_sq2_mrqa_adqa_synqa_quoref
tags:
  - generated_from_trainer
model-index:
  - name: FYP_qa_final
    results: []

FYP_qa_final

This model is a fine-tuned version of kxx-kkk/FYP_sq2_mrqa_adqa_synqa_quoref on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5690

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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.7114 0.48 300 3.0660
2.5396 0.96 600 2.6867
2.4284 1.44 900 2.6065
2.3668 1.91 1200 2.5973
2.3286 2.39 1500 2.5630
2.2461 2.87 1800 2.5690

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2