DeBERTa
Collection
DeBERTa is a language model that originates from Meta's RoBERTa model with disentangled attention and enhanced mask decoder. • 1 item • Updated
Text Classification
Transformers
PyTorch
English
deberta-v2
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Intel/deberta-v3-base-mrpc")
model = AutoModelForSequenceClassification.from_pretrained("Intel/deberta-v3-base-mrpc")Quick Links
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
- 22
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
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Intel/deberta-v3-base-mrpc")