metadata
license: apache-2.0
base_model: irfanamal/bert_multiple_choice
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_science_multiple_choice
results: []
bert_science_multiple_choice
This model is a fine-tuned version of irfanamal/bert_multiple_choice on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3092
- 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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4608 | 1.0 | 12 | 1.2885 | 0.5 |
| 1.3738 | 2.0 | 24 | 1.3587 | 0.5 |
| 1.3521 | 3.0 | 36 | 1.2585 | 0.45 |
| 1.2274 | 4.0 | 48 | 1.2703 | 0.45 |
| 1.1653 | 5.0 | 60 | 1.2730 | 0.45 |
| 1.1352 | 6.0 | 72 | 1.3275 | 0.45 |
| 1.1907 | 7.0 | 84 | 1.2848 | 0.45 |
| 1.0782 | 8.0 | 96 | 1.2745 | 0.45 |
| 1.0616 | 9.0 | 108 | 1.2995 | 0.45 |
| 1.0012 | 10.0 | 120 | 1.3002 | 0.45 |
| 0.9113 | 11.0 | 132 | 1.3236 | 0.4 |
| 0.8489 | 12.0 | 144 | 1.3175 | 0.4 |
| 0.8098 | 13.0 | 156 | 1.3092 | 0.4 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3