|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: distilbert-base-uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: j |
|
|
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. --> |
|
|
|
|
|
# j |
|
|
|
|
|
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: 0.3746 |
|
|
- Topology Accuracy: 0.9851 |
|
|
- Service Accuracy: 0.9435 |
|
|
- Combined Accuracy: 0.9643 |
|
|
|
|
|
## 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: 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:----------------:|:-----------------:| |
|
|
| 1.016 | 1.0 | 64 | 0.9725 | 0.7411 | 0.6220 | 0.6815 | |
|
|
| 0.7234 | 2.0 | 128 | 0.6385 | 0.9643 | 0.6935 | 0.8289 | |
|
|
| 0.6038 | 3.0 | 192 | 0.5826 | 0.9345 | 0.7440 | 0.8393 | |
|
|
| 0.5014 | 4.0 | 256 | 0.5192 | 0.9583 | 0.7738 | 0.8661 | |
|
|
| 0.3959 | 5.0 | 320 | 0.4845 | 0.9732 | 0.7768 | 0.875 | |
|
|
| 0.4165 | 6.0 | 384 | 0.4579 | 0.9762 | 0.8601 | 0.9182 | |
|
|
| 0.3699 | 7.0 | 448 | 0.4156 | 0.9851 | 0.9286 | 0.9568 | |
|
|
| 0.3272 | 8.0 | 512 | 0.3777 | 0.9851 | 0.9524 | 0.9688 | |
|
|
| 0.3091 | 9.0 | 576 | 0.3714 | 0.9851 | 0.9464 | 0.9658 | |
|
|
| 0.3092 | 10.0 | 640 | 0.3814 | 0.9821 | 0.9464 | 0.9643 | |
|
|
| 0.3221 | 11.0 | 704 | 0.3811 | 0.9821 | 0.9405 | 0.9613 | |
|
|
| 0.3033 | 12.0 | 768 | 0.3724 | 0.9851 | 0.9405 | 0.9628 | |
|
|
| 0.304 | 13.0 | 832 | 0.3741 | 0.9881 | 0.9435 | 0.9658 | |
|
|
| 0.3051 | 14.0 | 896 | 0.3743 | 0.9851 | 0.9435 | 0.9643 | |
|
|
| 0.3039 | 15.0 | 960 | 0.3746 | 0.9851 | 0.9435 | 0.9643 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.56.1 |
|
|
- Pytorch 2.8.0+cu126 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.0 |
|
|
|
