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: 0.4898
- Accuracy: 0.9020
- F1: 0.9296
- Combined Score: 0.9158
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_ratio: 0.06
- num_epochs: 5.0
Training results
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 7
Inference API (serverless) is not available, repository is disabled.
Model tree for JeremiahZ/roberta-base-mrpc
Base model
FacebookAI/roberta-base
Finetuned
this model
Dataset used to train JeremiahZ/roberta-base-mrpc
Evaluation results
- Accuracy on GLUE MRPCself-reported0.902
- F1 on GLUE MRPCself-reported0.930
- Accuracy on gluevalidation set verified0.902
- Precision on gluevalidation set verified0.913
- Recall on gluevalidation set verified0.946
- AUC on gluevalidation set verified0.954
- F1 on gluevalidation set verified0.930
- loss on gluevalidation set verified0.489