Instructions to use Mardiyyah/base_bioformer_2class_label_all_false with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mardiyyah/base_bioformer_2class_label_all_false with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Mardiyyah/base_bioformer_2class_label_all_false")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Mardiyyah/base_bioformer_2class_label_all_false") model = AutoModelForTokenClassification.from_pretrained("Mardiyyah/base_bioformer_2class_label_all_false", device_map="auto") - Notebooks
- Google Colab
- Kaggle
base_bioformer_2class_label_all_false
This model is a fine-tuned version of bioformers/bioformer-16l on the OTAR3088/CeLLaTe-ner-2class-iob_final dataset. It achieves the following results on the evaluation set:
- Loss: 0.0719
- Precision: 0.6531
- Recall: 0.6707
- Micro F1: 0.6618
- Weighted F1: 0.6620
- Macro F1: 0.6643
- Accuracy: 0.9821
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.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: 0.01
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Micro F1 | Weighted F1 | Macro F1 | Accuracy |
|---|---|---|---|---|---|---|---|---|---|
| 0.2431 | 1.0 | 263 | 0.0639 | 0.4934 | 0.6288 | 0.5530 | 0.5538 | 0.5560 | 0.9759 |
| 0.0452 | 2.0 | 526 | 0.0629 | 0.6867 | 0.6279 | 0.6560 | 0.6558 | 0.6608 | 0.9819 |
| 0.0315 | 3.0 | 789 | 0.0625 | 0.6676 | 0.6409 | 0.6540 | 0.6540 | 0.6582 | 0.9821 |
| 0.0234 | 4.0 | 1052 | 0.0669 | 0.6569 | 0.6056 | 0.6302 | 0.6302 | 0.6233 | 0.9814 |
| 0.0181 | 5.0 | 1315 | 0.0704 | 0.6535 | 0.6316 | 0.6424 | 0.6425 | 0.6379 | 0.9819 |
| 0.0142 | 6.0 | 1578 | 0.0782 | 0.5968 | 0.5907 | 0.5937 | 0.5921 | 0.5744 | 0.9800 |
| 0.0116 | 7.0 | 1841 | 0.0724 | 0.6531 | 0.6707 | 0.6618 | 0.6620 | 0.6643 | 0.9821 |
| 0.0097 | 8.0 | 2104 | 0.0968 | 0.6794 | 0.5953 | 0.6346 | 0.6343 | 0.6413 | 0.9807 |
| 0.0085 | 9.0 | 2367 | 0.0881 | 0.6513 | 0.6428 | 0.6470 | 0.6470 | 0.6490 | 0.9818 |
| 0.0072 | 10.0 | 2630 | 0.0905 | 0.6663 | 0.6484 | 0.6572 | 0.6574 | 0.6627 | 0.9819 |
| 0.0061 | 11.0 | 2893 | 0.0933 | 0.6389 | 0.6419 | 0.6404 | 0.6405 | 0.6412 | 0.9814 |
| 0.0053 | 12.0 | 3156 | 0.0957 | 0.6577 | 0.64 | 0.6488 | 0.6488 | 0.6506 | 0.9820 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.21.0
- Downloads last month
- 19