roberta-base-relu-mrpc
This model is a fine-tuned version of JeremiahZ/roberta-base-mrpc on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.8321
- eval_model_preparation_time: 0.0023
- eval_accuracy: 0.8824
- eval_f1: 0.9161
- eval_combined_score: 0.8992
- eval_runtime: 3.9409
- eval_samples_per_second: 103.529
- eval_steps_per_second: 25.882
- step: 0
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-5, 2e-5, 3e-5
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- num_epochs: 10
The best model was selected based on the highest accuracy, which is the key evaluation metric for this task.
Framework versions
- Transformers 4.50.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 21