|
|
--- |
|
|
library_name: transformers |
|
|
base_model: allenai/scibert_scivocab_uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: defect-classification-scibert-baseline-15-epochs |
|
|
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. --> |
|
|
|
|
|
# defect-classification-scibert-baseline-15-epochs |
|
|
|
|
|
This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2942 |
|
|
- Accuracy: 0.8886 |
|
|
|
|
|
## 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: 256 |
|
|
- eval_batch_size: 256 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 15 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
|
| 1.4091 | 1.0 | 2124 | 0.7623 | 0.8511 | |
|
|
| 0.9826 | 2.0 | 4248 | 0.5050 | 0.8771 | |
|
|
| 0.801 | 3.0 | 6372 | 0.5006 | 0.8687 | |
|
|
| 0.6921 | 4.0 | 8496 | 0.4421 | 0.8708 | |
|
|
| 0.6182 | 5.0 | 10620 | 0.3628 | 0.8808 | |
|
|
| 0.5882 | 6.0 | 12744 | 0.3826 | 0.8702 | |
|
|
| 0.5514 | 7.0 | 14868 | 0.3600 | 0.8753 | |
|
|
| 0.5324 | 8.0 | 16992 | 0.3227 | 0.8851 | |
|
|
| 0.5045 | 9.0 | 19116 | 0.3516 | 0.8715 | |
|
|
| 0.4991 | 10.0 | 21240 | 0.3046 | 0.8891 | |
|
|
| 0.4931 | 11.0 | 23364 | 0.3176 | 0.8820 | |
|
|
| 0.4792 | 12.0 | 25488 | 0.2977 | 0.8886 | |
|
|
| 0.4613 | 13.0 | 27612 | 0.2895 | 0.8922 | |
|
|
| 0.4631 | 14.0 | 29736 | 0.2890 | 0.8910 | |
|
|
| 0.4596 | 15.0 | 31860 | 0.2942 | 0.8886 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.47.0 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
|
|
|
