metadata
license: apache-2.0
base_model: google/electra-small-discriminator
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: electra-case-16
results: []
electra-case-16
This model is a fine-tuned version of google/electra-small-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3361
- Accuracy: 0.8733
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 224
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 44 | 0.7189 | 0.8 |
| No log | 2.0 | 88 | 0.5694 | 0.8467 |
| No log | 3.0 | 132 | 0.4746 | 0.8267 |
| No log | 4.0 | 176 | 0.4302 | 0.82 |
| No log | 5.0 | 220 | 0.3935 | 0.84 |
| No log | 6.0 | 264 | 0.3571 | 0.8467 |
| No log | 7.0 | 308 | 0.3834 | 0.8267 |
| No log | 8.0 | 352 | 0.3352 | 0.8733 |
| No log | 9.0 | 396 | 0.3247 | 0.8733 |
| No log | 10.0 | 440 | 0.3452 | 0.8733 |
| No log | 11.0 | 484 | 0.3792 | 0.8467 |
| 0.3615 | 12.0 | 528 | 0.3583 | 0.8667 |
| 0.3615 | 13.0 | 572 | 0.3551 | 0.86 |
| 0.3615 | 14.0 | 616 | 0.3732 | 0.8533 |
| 0.3615 | 15.0 | 660 | 0.3356 | 0.8733 |
| 0.3615 | 16.0 | 704 | 0.3361 | 0.8733 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0