metadata
library_name: transformers
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Fake-Citation-Detector-V2-scibert
results: []
Fake-Citation-Detector-V2-scibert
This model is a fine-tuned version of allenai/scibert_scivocab_uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8244
- Accuracy: 0.6205
- Macro F1: 0.6028
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: 32
- 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: 51
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|---|---|---|---|---|---|
| 0.7055 | 1.0 | 86 | 0.6790 | 0.5723 | 0.5499 |
| 0.6908 | 2.0 | 172 | 0.6773 | 0.5723 | 0.5195 |
| 0.6122 | 3.0 | 258 | 0.6426 | 0.6325 | 0.6133 |
| 0.5333 | 4.0 | 344 | 0.6915 | 0.6205 | 0.5983 |
| 0.3916 | 5.0 | 430 | 0.7555 | 0.6205 | 0.6006 |
| 0.2788 | 6.0 | 516 | 0.8244 | 0.6205 | 0.6028 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.11.0+cu130
- Datasets 4.8.5
- Tokenizers 0.23.2