Edit model card

deberta-v3-base-finetuned-mnli

This model is a fine-tuned version of deberta-v3-base on the glue dataset. It achieves the following results on the evaluation set:

  • Matched Accuracy: 0.9057
  • Missmatched Accuracy: 0.9105

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
  • weight_decay: 0.01
  • num_epochs: 2
Downloads last month
0
Safetensors
Model size
184M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train rambodazimi/deberta-v3-base-finetuned-FFT-MNLI

Evaluation results