metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_multiple_choice
results: []
bert_multiple_choice
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4718
- Accuracy: 0.4
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6321 | 1.0 | 12 | 1.5869 | 0.45 |
| 1.6206 | 2.0 | 24 | 1.5864 | 0.45 |
| 1.6088 | 3.0 | 36 | 1.5849 | 0.45 |
| 1.6098 | 4.0 | 48 | 1.5760 | 0.5 |
| 1.5938 | 5.0 | 60 | 1.5746 | 0.55 |
| 1.5811 | 6.0 | 72 | 1.5726 | 0.5 |
| 1.5968 | 7.0 | 84 | 1.5699 | 0.55 |
| 1.5521 | 8.0 | 96 | 1.5627 | 0.5 |
| 1.5438 | 9.0 | 108 | 1.5485 | 0.45 |
| 1.5605 | 10.0 | 120 | 1.5456 | 0.35 |
| 1.552 | 11.0 | 132 | 1.5448 | 0.35 |
| 1.5065 | 12.0 | 144 | 1.5466 | 0.5 |
| 1.5075 | 13.0 | 156 | 1.5490 | 0.45 |
| 1.4757 | 14.0 | 168 | 1.5412 | 0.4 |
| 1.4504 | 15.0 | 180 | 1.5292 | 0.45 |
| 1.3916 | 16.0 | 192 | 1.5161 | 0.3 |
| 1.4132 | 17.0 | 204 | 1.5146 | 0.35 |
| 1.3652 | 18.0 | 216 | 1.4985 | 0.35 |
| 1.3303 | 19.0 | 228 | 1.4864 | 0.35 |
| 1.3441 | 20.0 | 240 | 1.4845 | 0.4 |
| 1.3161 | 21.0 | 252 | 1.4953 | 0.35 |
| 1.3025 | 22.0 | 264 | 1.4689 | 0.4 |
| 1.2371 | 23.0 | 276 | 1.4582 | 0.4 |
| 1.2468 | 24.0 | 288 | 1.4523 | 0.4 |
| 1.2156 | 25.0 | 300 | 1.4673 | 0.45 |
| 1.1791 | 26.0 | 312 | 1.4608 | 0.4 |
| 1.1919 | 27.0 | 324 | 1.4125 | 0.4 |
| 1.1926 | 28.0 | 336 | 1.4655 | 0.45 |
| 1.1473 | 29.0 | 348 | 1.4629 | 0.4 |
| 1.1132 | 30.0 | 360 | 1.4481 | 0.4 |
| 1.1064 | 31.0 | 372 | 1.4754 | 0.4 |
| 1.1352 | 32.0 | 384 | 1.4718 | 0.4 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3