SPECTER-with-biblio-context-finetuned-review_classifier
This model is a fine-tuned version of allenai/specter on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1284
- Accuracy: 0.962
- F1: 0.7892
- Recall: 0.7593
- Precision: 0.8216
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: 4.5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
|---|---|---|---|---|---|---|---|
| 0.1956 | 1.0 | 6667 | 0.1805 | 0.9514 | 0.7257 | 0.6860 | 0.7702 |
| 0.135 | 2.0 | 13334 | 0.1284 | 0.962 | 0.7892 | 0.7593 | 0.8216 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1