bert-base-uncased-mrpc-best
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5108
- Accuracy: 0.7391
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: 9.176408645460838e-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5844 | 1.0 | 115 | 0.5511 | 0.7083 |
| 0.5265 | 2.0 | 230 | 0.5047 | 0.7304 |
| 0.4775 | 3.0 | 345 | 0.4855 | 0.7426 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 2.19.1
- Tokenizers 0.22.1
- Downloads last month
- 7
Model tree for edademireleda/bert-base-uncased-mrpc-best
Base model
distilbert/distilbert-base-uncased