metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: multiple_choice_model
results: []
multiple_choice_model
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0560
- Accuracy: 0.751
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: 5e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9281 | 1.0 | 563 | 0.7698 | 0.723 |
| 0.4148 | 2.0 | 1126 | 0.8325 | 0.726 |
| 0.2001 | 3.0 | 1689 | 1.4160 | 0.712 |
| 0.1073 | 4.0 | 2252 | 1.4036 | 0.726 |
| 0.0671 | 5.0 | 2815 | 1.8364 | 0.735 |
| 0.0386 | 6.0 | 3378 | 1.8075 | 0.739 |
| 0.019 | 7.0 | 3941 | 1.9959 | 0.748 |
| 0.0054 | 8.0 | 4504 | 2.0279 | 0.753 |
| 0.0016 | 9.0 | 5067 | 2.0335 | 0.752 |
| 0.0021 | 10.0 | 5630 | 2.0560 | 0.751 |
Framework versions
- Transformers 4.54.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4