<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
deberta-v3-large-dapt-scientific-papers-pubmed-tapt
This model is a fine-tuned version of domenicrosati/deberta-v3-large-dapt-scientific-papers-pubmed on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4429
- Accuracy: 0.5915
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.3855 | 1.0 | 4134 | 3.2334 | 0.4953 |
| 2.9224 | 2.0 | 8268 | 2.8317 | 0.5430 |
| 2.703 | 3.0 | 12402 | 2.6141 | 0.5665 |
| 2.4963 | 4.0 | 16536 | 2.4918 | 0.5855 |
| 2.399 | 5.0 | 20670 | 2.4429 | 0.5915 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
