DeBERTa
Collection
DeBERTa is a language model that originates from Meta's RoBERTa model with disentangled attention and enhanced mask decoder.
•
3 items
•
Updated
deberta-v3-base-mrpc
This model is a fine-tuned version of microsoft/deberta-v3-base on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5681
- Accuracy: 0.8946
- F1: 0.9244
- Combined Score: 0.9095
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5.0
Framework versions
- Transformers 4.28.1
- Pytorch 1.12.1+cu113
- Datasets 2.11.0
- Tokenizers 0.13.3
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train Intel/deberta-v3-base-mrpc
Collection including Intel/deberta-v3-base-mrpc
Evaluation results
- Accuracy on GLUE MRPCvalidation set self-reported0.895
- F1 on GLUE MRPCvalidation set self-reported0.924