|
--- |
|
license: mit |
|
base_model: microsoft/biogpt |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: biogpt-adverse-ner |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# biogpt-adverse-ner |
|
|
|
This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1600 |
|
- Precision: 0.4255 |
|
- Recall: 0.5280 |
|
- F1: 0.4712 |
|
- Accuracy: 0.9471 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 449 | 0.1879 | 0.3350 | 0.3187 | 0.3266 | 0.9329 | |
|
| 0.2647 | 2.0 | 898 | 0.1653 | 0.3653 | 0.4664 | 0.4097 | 0.9430 | |
|
| 0.159 | 3.0 | 1347 | 0.1600 | 0.4255 | 0.5280 | 0.4712 | 0.9471 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|