metadata
license: apache-2.0
base_model: google/electra-base-discriminator
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: electra_multiple_choice
results: []
electra_multiple_choice
This model is a fine-tuned version of google/electra-base-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4645
- Accuracy: 0.498
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 |
|---|---|---|---|---|
| 1.5522 | 1.0 | 375 | 1.4354 | 0.456 |
| 1.3851 | 2.0 | 750 | 1.3471 | 0.468 |
| 1.2672 | 3.0 | 1125 | 1.2887 | 0.486 |
| 1.1756 | 4.0 | 1500 | 1.2594 | 0.506 |
| 1.0738 | 5.0 | 1875 | 1.2746 | 0.508 |
| 0.9818 | 6.0 | 2250 | 1.3388 | 0.508 |
| 0.8955 | 7.0 | 2625 | 1.3723 | 0.502 |
| 0.8209 | 8.0 | 3000 | 1.3901 | 0.496 |
| 0.7445 | 9.0 | 3375 | 1.4645 | 0.498 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3