BART
Collection
Adaptations on Meta's BART model
•
3 items
•
Updated
bart-large-mrpc
This model is a fine-tuned version of facebook/bart-large on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5684
- Accuracy: 0.8775
- F1: 0.9120
- Combined Score: 0.8947
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
- 16
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.
Model tree for Intel/bart-large-mrpc
Base model
facebook/bart-largeDataset used to train Intel/bart-large-mrpc
Collection including Intel/bart-large-mrpc
Evaluation results
- Accuracy on GLUE MRPCself-reported0.877
- F1 on GLUE MRPCself-reported0.912