|
--- |
|
license: mit |
|
base_model: nlpie/bio-mobilebert |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: NLPGroupProject-Finetune-bio-mobilebert-AL |
|
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. --> |
|
|
|
# NLPGroupProject-Finetune-bio-mobilebert-AL |
|
|
|
This model is a fine-tuned version of [nlpie/bio-mobilebert](https://huggingface.co/nlpie/bio-mobilebert) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1613 |
|
- Accuracy: 0.742 |
|
|
|
## 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: 5e-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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| No log | 0.3121 | 250 | 0.8770 | 0.737 | |
|
| 6.4745 | 0.6242 | 500 | 0.8535 | 0.731 | |
|
| 6.4745 | 0.9363 | 750 | 0.8849 | 0.729 | |
|
| 0.7885 | 1.2484 | 1000 | 0.8966 | 0.734 | |
|
| 0.7885 | 1.5605 | 1250 | 0.8883 | 0.723 | |
|
| 0.6817 | 1.8727 | 1500 | 1.0612 | 0.729 | |
|
| 0.6817 | 2.1848 | 1750 | 0.9602 | 0.739 | |
|
| 0.5535 | 2.4969 | 2000 | 1.5924 | 0.74 | |
|
| 0.5535 | 2.8090 | 2250 | 1.1613 | 0.742 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.0 |
|
- Pytorch 2.2.2+cu118 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|