RoBERTa
Collection
5 items • Updated
Text Classification
Transformers
PyTorch
English
roberta
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Intel/roberta-base-mrpc")
model = AutoModelForSequenceClassification.from_pretrained("Intel/roberta-base-mrpc")Quick Links
roberta-base-mrpc
This model is a fine-tuned version of roberta-base on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5565
- Accuracy: 0.8775
- F1: 0.9138
- Combined Score: 0.8956
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
- num_epochs: 5.0
Training results
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu102
- Datasets 2.1.0
- Tokenizers 0.11.6
- Downloads last month
- 29
Dataset used to train Intel/roberta-base-mrpc
Collection including Intel/roberta-base-mrpc
Evaluation results
- Accuracy on gluevalidation set verified0.877
- Precision on gluevalidation set verified0.880
- Recall on gluevalidation set verified0.950
- AUC on gluevalidation set verified0.947
- F1 on gluevalidation set verified0.914
- loss on gluevalidation set verified0.556
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Intel/roberta-base-mrpc")