|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: distilbert-base-uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: jn |
|
|
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. --> |
|
|
|
|
|
# jn |
|
|
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3406 |
|
|
- Topology Accuracy: 0.9883 |
|
|
- Service Accuracy: 0.9746 |
|
|
- Combined Accuracy: 0.9814 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 50 |
|
|
- num_epochs: 15 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Topology Accuracy | Service Accuracy | Combined Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:----------------:|:-----------------:| |
|
|
| 0.6178 | 1.0 | 96 | 0.6028 | 0.9805 | 0.7012 | 0.8408 | |
|
|
| 0.5546 | 2.0 | 192 | 0.5229 | 0.9766 | 0.7109 | 0.8438 | |
|
|
| 0.4255 | 3.0 | 288 | 0.4324 | 0.9805 | 0.9023 | 0.9414 | |
|
|
| 0.3934 | 4.0 | 384 | 0.3546 | 0.9805 | 0.9668 | 0.9736 | |
|
|
| 0.3195 | 5.0 | 480 | 0.3477 | 0.9844 | 0.9648 | 0.9746 | |
|
|
| 0.3052 | 6.0 | 576 | 0.3458 | 0.9863 | 0.9746 | 0.9805 | |
|
|
| 0.3139 | 7.0 | 672 | 0.3529 | 0.9863 | 0.9688 | 0.9775 | |
|
|
| 0.3049 | 8.0 | 768 | 0.3533 | 0.9844 | 0.9707 | 0.9775 | |
|
|
| 0.3145 | 9.0 | 864 | 0.3517 | 0.9863 | 0.9648 | 0.9756 | |
|
|
| 0.3025 | 10.0 | 960 | 0.3462 | 0.9883 | 0.9668 | 0.9775 | |
|
|
| 0.3031 | 11.0 | 1056 | 0.3420 | 0.9902 | 0.9707 | 0.9805 | |
|
|
| 0.3008 | 12.0 | 1152 | 0.3417 | 0.9883 | 0.9727 | 0.9805 | |
|
|
| 0.3184 | 13.0 | 1248 | 0.3418 | 0.9883 | 0.9746 | 0.9814 | |
|
|
| 0.2996 | 14.0 | 1344 | 0.3404 | 0.9883 | 0.9746 | 0.9814 | |
|
|
| 0.3023 | 15.0 | 1440 | 0.3406 | 0.9883 | 0.9746 | 0.9814 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.56.1 |
|
|
- Pytorch 2.8.0+cu126 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.0 |
|
|
|
