metadata
license: mit
base_model: irfanamal/roberta_multiple_choice
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta_science_multiple_choice
results: []
roberta_science_multiple_choice
This model is a fine-tuned version of irfanamal/roberta_multiple_choice on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2327
- Accuracy: 0.55
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 |
|---|---|---|---|---|
| 1.2768 | 1.0 | 12 | 1.1911 | 0.5 |
| 1.0332 | 2.0 | 24 | 1.1788 | 0.5 |
| 1.0537 | 3.0 | 36 | 1.1820 | 0.5 |
| 0.8868 | 4.0 | 48 | 1.1830 | 0.5 |
| 0.8634 | 5.0 | 60 | 1.2148 | 0.5 |
| 0.7732 | 6.0 | 72 | 1.2242 | 0.5 |
| 0.7369 | 7.0 | 84 | 1.2327 | 0.55 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3