CeLLaTe-tapt-pubmedbert-tokenizer-original-wwmask-combinedData
This model is a fine-tuned version of microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext on the Mardiyyah/Combined_TAPT_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.0617
- Accuracy: 0.7651
- Perplexity: 2.8914
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: 32
- eval_batch_size: 32
- seed: 3407
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Perplexity |
|---|---|---|---|---|---|
| 1.1819 | 1.0 | 28 | 1.0755 | 0.7637 | 2.9314 |
| 1.177 | 2.0 | 56 | 1.0435 | 0.7700 | 2.8391 |
| 1.1729 | 3.0 | 84 | 1.0621 | 0.7669 | 2.8925 |
| 1.153 | 4.0 | 112 | 1.0608 | 0.7672 | 2.8887 |
| 1.1487 | 5.0 | 140 | 1.0797 | 0.7591 | 2.9437 |
| 1.1204 | 6.0 | 168 | 1.0668 | 0.7645 | 2.9060 |
| 1.1177 | 7.0 | 196 | 1.0658 | 0.7605 | 2.9033 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.21.0