metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
- recall
- accuracy
model-index:
- name: Electra-Thesis-NonKFold
results: []
Electra-Thesis-NonKFold
This model is a fine-tuned version of google/electra-base-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4914
- F1: 0.6390
- Recall: 0.6390
- Accuracy: 0.6390
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Recall | Accuracy |
---|---|---|---|---|---|---|
1.6531 | 1.0 | 1446 | 1.3688 | 0.5851 | 0.5851 | 0.5851 |
1.2404 | 2.0 | 2892 | 1.2674 | 0.6230 | 0.6230 | 0.6230 |
1.0544 | 3.0 | 4338 | 1.2389 | 0.6322 | 0.6322 | 0.6322 |
0.9189 | 4.0 | 5784 | 1.2293 | 0.6376 | 0.6376 | 0.6376 |
0.8034 | 5.0 | 7230 | 1.3130 | 0.6384 | 0.6384 | 0.6384 |
0.7351 | 6.0 | 8676 | 1.3463 | 0.6390 | 0.6390 | 0.6390 |
0.6481 | 7.0 | 10122 | 1.3858 | 0.6385 | 0.6385 | 0.6385 |
0.5885 | 8.0 | 11568 | 1.4379 | 0.6372 | 0.6372 | 0.6372 |
0.5533 | 9.0 | 13014 | 1.4792 | 0.6344 | 0.6344 | 0.6344 |
0.5285 | 10.0 | 14460 | 1.4914 | 0.6390 | 0.6390 | 0.6390 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3