metadata
license: apache-2.0
base_model: irfanamal/electra_multiple_choice
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: electra_science_multiple_choice
results: []
electra_science_multiple_choice
This model is a fine-tuned version of irfanamal/electra_multiple_choice on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4381
- Accuracy: 0.45
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 |
---|---|---|---|---|
1.4368 | 1.0 | 12 | 1.2512 | 0.35 |
1.2949 | 2.0 | 24 | 1.2620 | 0.35 |
1.2896 | 3.0 | 36 | 1.2684 | 0.35 |
1.1331 | 4.0 | 48 | 1.2829 | 0.4 |
1.0597 | 5.0 | 60 | 1.2817 | 0.4 |
0.9501 | 6.0 | 72 | 1.3375 | 0.4 |
0.8908 | 7.0 | 84 | 1.3192 | 0.4 |
0.8428 | 8.0 | 96 | 1.3283 | 0.4 |
0.7653 | 9.0 | 108 | 1.3877 | 0.45 |
0.6729 | 10.0 | 120 | 1.3613 | 0.4 |
0.6523 | 11.0 | 132 | 1.4381 | 0.45 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3