|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- ncbi_disease |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: MLMA_lab9_task2 |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: ncbi_disease |
|
type: ncbi_disease |
|
config: ncbi_disease |
|
split: validation |
|
args: ncbi_disease |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.014770696843359143 |
|
- name: Recall |
|
type: recall |
|
value: 0.15756035578144853 |
|
- name: F1 |
|
type: f1 |
|
value: 0.027009366151165323 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.5979586476040377 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# MLMA_lab9_task2 |
|
|
|
This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on the ncbi_disease dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1842 |
|
- Precision: 0.0148 |
|
- Recall: 0.1576 |
|
- F1: 0.0270 |
|
- Accuracy: 0.5980 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 1.146 | 1.0 | 680 | 1.0915 | 0.0117 | 0.3011 | 0.0226 | 0.1671 | |
|
| 1.0373 | 2.0 | 1360 | 1.0423 | 0.0134 | 0.0712 | 0.0226 | 0.5881 | |
|
| 0.974 | 3.0 | 2040 | 1.0329 | 0.0138 | 0.1728 | 0.0255 | 0.5055 | |
|
| 0.9361 | 4.0 | 2720 | 1.0223 | 0.0152 | 0.1525 | 0.0276 | 0.5807 | |
|
| 0.9291 | 5.0 | 3400 | 1.0309 | 0.0135 | 0.1817 | 0.0251 | 0.5145 | |
|
| 0.8952 | 6.0 | 4080 | 1.0309 | 0.0138 | 0.2313 | 0.0260 | 0.3924 | |
|
| 0.8747 | 7.0 | 4760 | 1.0895 | 0.0136 | 0.2643 | 0.0259 | 0.3462 | |
|
| 0.8615 | 8.0 | 5440 | 1.1566 | 0.0161 | 0.1423 | 0.0289 | 0.6451 | |
|
| 0.8413 | 9.0 | 6120 | 1.1651 | 0.0144 | 0.1601 | 0.0265 | 0.5902 | |
|
| 0.8287 | 10.0 | 6800 | 1.1842 | 0.0148 | 0.1576 | 0.0270 | 0.5980 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|