metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-mrpc-best
results: []
bert-mrpc-best
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4765
- Accuracy: 0.8088
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: 1.0302066598519386e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5754 | 1.0 | 230 | 0.5395 | 0.7353 |
| 0.5202 | 2.0 | 460 | 0.5240 | 0.7598 |
| 0.4368 | 3.0 | 690 | 0.4728 | 0.8015 |
| 0.3902 | 4.0 | 920 | 0.4765 | 0.8088 |
| 0.3593 | 5.0 | 1150 | 0.6118 | 0.7770 |
| 0.3233 | 6.0 | 1380 | 0.5552 | 0.7917 |
| 0.2687 | 7.0 | 1610 | 0.5440 | 0.8039 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1