metadata
library_name: transformers
license: apache-2.0
base_model: bioformers/bioformer-16L
tags:
- generated_from_trainer
model-index:
- name: TAPT-V2-Bioformer-16L
results: []
TAPT-V2-Bioformer-16L
This model is a fine-tuned version of bioformers/bioformer-16L on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5163
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: 16
- eval_batch_size: 16
- seed: 42
- 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 |
|---|---|---|---|
| 2.1462 | 1.0 | 584 | 1.9270 |
| 1.9329 | 2.0 | 1168 | 1.8426 |
| 1.7986 | 3.0 | 1752 | 1.7601 |
| 1.6702 | 4.0 | 2336 | 1.7089 |
| 1.6081 | 5.0 | 2920 | 1.6362 |
| 1.5205 | 6.0 | 3504 | 1.6520 |
| 1.485 | 7.0 | 4088 | 1.5955 |
| 1.417 | 8.0 | 4672 | 1.5575 |
| 1.3977 | 9.0 | 5256 | 1.6303 |
| 1.3698 | 10.0 | 5840 | 1.5275 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.21.0