BART
Collection
Adaptations on Meta's BART model • 2 items • Updated
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Intel/bart-large-mrpc")
model = AutoModelForSequenceClassification.from_pretrained("Intel/bart-large-mrpc")Quick Links
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
- 71
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
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Intel/bart-large-mrpc")