|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: biobert-ner-finetuned-con-kaggle |
|
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. --> |
|
|
|
# biobert-ner-finetuned |
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0894 |
|
- Precision: 0.9293 |
|
- Recall: 0.9551 |
|
- F1: 0.9420 |
|
- Accuracy: 0.9795 |
|
|
|
## 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: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 306 | 0.2575 | 0.7864 | 0.8034 | 0.7948 | 0.9322 | |
|
| 0.8692 | 2.0 | 612 | 0.0949 | 0.9170 | 0.9451 | 0.9308 | 0.9759 | |
|
| 0.8692 | 3.0 | 918 | 0.0854 | 0.9234 | 0.9607 | 0.9417 | 0.9791 | |
|
| 0.1096 | 4.0 | 1224 | 0.0768 | 0.9333 | 0.9585 | 0.9457 | 0.9809 | |
|
| 0.0656 | 5.0 | 1530 | 0.0772 | 0.9320 | 0.9562 | 0.9439 | 0.9806 | |
|
| 0.0656 | 6.0 | 1836 | 0.0810 | 0.9360 | 0.9575 | 0.9466 | 0.9806 | |
|
| 0.0468 | 7.0 | 2142 | 0.0827 | 0.9308 | 0.9580 | 0.9442 | 0.9803 | |
|
| 0.0468 | 8.0 | 2448 | 0.0890 | 0.9248 | 0.9568 | 0.9405 | 0.9788 | |
|
| 0.038 | 9.0 | 2754 | 0.0859 | 0.9345 | 0.9579 | 0.9460 | 0.9806 | |
|
| 0.031 | 10.0 | 3060 | 0.0894 | 0.9293 | 0.9551 | 0.9420 | 0.9795 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
|
|
