metadata
library_name: transformers
license: mit
base_model: chandar-lab/NeoBERT
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: NeoBERT_druglib_regression_6ep_5e-06lr
results: []
NeoBERT_druglib_regression_6ep_5e-06lr
This model is a fine-tuned version of chandar-lab/NeoBERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9323
- Accuracy: 0.6284
- Macro Precision: 0.6396
- Macro Recall: 0.5598
- Macro F1: 0.5573
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro Precision | Macro Recall | Macro F1 |
|---|---|---|---|---|---|---|---|
| 1.2053 | 1.0 | 311 | 1.0258 | 0.5900 | 0.5546 | 0.4409 | 0.4394 |
| 0.743 | 2.0 | 622 | 0.8838 | 0.6527 | 0.6404 | 0.5392 | 0.5352 |
| 0.5941 | 3.0 | 933 | 0.9091 | 0.6624 | 0.6102 | 0.5566 | 0.5674 |
| 0.4384 | 4.0 | 1244 | 1.0823 | 0.6592 | 0.6108 | 0.5464 | 0.5493 |
| 0.138 | 5.0 | 1555 | 1.3475 | 0.6543 | 0.5926 | 0.5503 | 0.5600 |
| 0.0683 | 6.0 | 1866 | 1.4926 | 0.6495 | 0.5865 | 0.5571 | 0.5668 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0