4K_no_reinit_classifier_llrd0.9_LR-2e-05
This model is a fine-tuned version of microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6636
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: 16
- seed: 3407
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7917 | 1.0 | 609 | 1.6558 |
| 1.5856 | 2.0 | 1218 | 1.6535 |
| 1.4757 | 3.0 | 1827 | 1.5922 |
| 1.3937 | 4.0 | 2436 | 1.6836 |
| 1.3153 | 5.0 | 3045 | 1.6618 |
| 1.28 | 6.0 | 3654 | 1.7189 |
| 1.2495 | 7.0 | 4263 | 1.7239 |
| 1.2078 | 8.0 | 4872 | 1.6971 |
| 1.1789 | 9.0 | 5481 | 1.6779 |
| 1.1856 | 10.0 | 6090 | 1.6636 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.21.0
- Downloads last month
- 2