metadata
license: mit
base_model: microsoft/biogpt
tags:
- generated_from_trainer
model-index:
- name: biogpt-ner
results: []
biogpt-ner
This model is a fine-tuned version of microsoft/biogpt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1892
- Overall Precision: 0.4664
- Overall Recall: 0.5553
- Overall F1: 0.5070
- Overall Accuracy: 0.9572
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2307 | 1.0 | 1358 | 0.1703 | 0.3849 | 0.3888 | 0.3869 | 0.9497 |
| 0.1415 | 2.0 | 2716 | 0.1589 | 0.3761 | 0.5286 | 0.4395 | 0.9490 |
| 0.0932 | 3.0 | 4074 | 0.1515 | 0.4580 | 0.5197 | 0.4869 | 0.9560 |
| 0.0763 | 4.0 | 5432 | 0.1763 | 0.4885 | 0.5146 | 0.5012 | 0.9583 |
| 0.0586 | 5.0 | 6790 | 0.1892 | 0.4664 | 0.5553 | 0.5070 | 0.9572 |
Framework versions
- Transformers 4.39.3
- Pytorch 1.12.1+cu113
- Datasets 2.18.0
- Tokenizers 0.15.2