# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("heavyhelium/electra-small-touche-base-binary")
model = AutoModelForSequenceClassification.from_pretrained("heavyhelium/electra-small-touche-base-binary")Quick Links
electra-small-touche-base-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: 0.6289
- Accuracy: 0.665
- Macro F1: 0.6649
- Fallacy F1: 0.6700
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 |
|---|---|---|---|---|---|---|
| 0.6951 | 1.0 | 47 | 0.6898 | 0.555 | 0.5094 | 0.3597 |
| 0.6876 | 2.0 | 94 | 0.6786 | 0.64 | 0.64 | 0.64 |
| 0.6429 | 3.0 | 141 | 0.6572 | 0.63 | 0.6161 | 0.5432 |
| 0.6258 | 4.0 | 188 | 0.6353 | 0.645 | 0.6430 | 0.6698 |
| 0.5856 | 5.0 | 235 | 0.6289 | 0.665 | 0.6649 | 0.6700 |
Framework versions
- Transformers 5.9.0
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2
- Downloads last month
- 98
Model tree for heavyhelium/electra-small-touche-base-binary
Base model
google/electra-small-discriminator
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="heavyhelium/electra-small-touche-base-binary")