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: 1.4499
- Accuracy: 0.535
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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4892 | 1.0 | 3207 | 1.2930 | 0.485 |
| 1.2722 | 2.0 | 6414 | 1.2277 | 0.47 |
| 1.1139 | 3.0 | 9621 | 1.1827 | 0.495 |
| 0.9607 | 4.0 | 12828 | 1.1426 | 0.55 |
| 0.8117 | 5.0 | 16035 | 1.1891 | 0.53 |
| 0.6878 | 6.0 | 19242 | 1.1941 | 0.53 |
| 0.5874 | 7.0 | 22449 | 1.2868 | 0.54 |
| 0.4989 | 8.0 | 25656 | 1.3710 | 0.55 |
| 0.4274 | 9.0 | 28863 | 1.4499 | 0.535 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3