metadata
library_name: transformers
license: apache-2.0
base_model: google/electra-small-discriminator
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: electra-small-touche-rawplusctx-binary
results: []
electra-small-touche-rawplusctx-binary
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: 0.6499
- Accuracy: 0.64
- Macro F1: 0.6397
- Fallacy F1: 0.6505
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Fallacy F1 |
|---|---|---|---|---|---|---|
| 0.6922 | 1.0 | 47 | 0.6911 | 0.525 | 0.4203 | 0.1739 |
| 0.6858 | 2.0 | 94 | 0.6856 | 0.595 | 0.5927 | 0.6233 |
| 0.6565 | 3.0 | 141 | 0.6712 | 0.565 | 0.5496 | 0.4663 |
| 0.6361 | 4.0 | 188 | 0.6547 | 0.625 | 0.6200 | 0.6637 |
| 0.5926 | 5.0 | 235 | 0.6499 | 0.64 | 0.6397 | 0.6505 |
Framework versions
- Transformers 5.9.0
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2