XLNet
Collection
Original paper: XLNet: Generalized Autoregressive Pretraining for Language Understanding
•
2 items
•
Updated
xlnet-base-cased-mrpc
This model is a fine-tuned version of xlnet-base-cased on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.7156
- Accuracy: 0.8456
- F1: 0.8897
- Combined Score: 0.8676
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
- 4
Dataset used to train Intel/xlnet-base-cased-mrpc
Collection including Intel/xlnet-base-cased-mrpc
Evaluation results
- Accuracy on GLUE MRPCself-reported0.846
- F1 on GLUE MRPCself-reported0.890