|
--- |
|
library_name: transformers |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: poison-distill |
|
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. --> |
|
|
|
# poison-distill |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: -42.4617 |
|
- Accuracy: 0.6165 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- 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: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| -1.7321 | 1.0 | 130 | -17.9718 | 0.4135 | |
|
| -10.3826 | 2.0 | 260 | -21.0786 | 0.4286 | |
|
| -15.9561 | 3.0 | 390 | -30.7402 | 0.3609 | |
|
| -20.4105 | 4.0 | 520 | -8.7054 | 0.6090 | |
|
| -23.6697 | 5.0 | 650 | -41.1276 | 0.5263 | |
|
| -28.1385 | 6.0 | 780 | -53.7167 | 0.4135 | |
|
| -30.4932 | 7.0 | 910 | -54.0164 | 0.3609 | |
|
| -33.5563 | 8.0 | 1040 | -49.4077 | 0.3233 | |
|
| -36.6955 | 9.0 | 1170 | -38.3125 | 0.5489 | |
|
| -38.8208 | 10.0 | 1300 | -42.4497 | 0.6842 | |
|
| -40.791 | 11.0 | 1430 | -37.1019 | 0.5789 | |
|
| -43.1559 | 12.0 | 1560 | -38.0363 | 0.3759 | |
|
| -45.1497 | 13.0 | 1690 | -81.5224 | 0.3609 | |
|
| -46.5745 | 14.0 | 1820 | -105.4418 | 0.3609 | |
|
| -47.6707 | 15.0 | 1950 | -70.0515 | 0.5639 | |
|
| -48.1727 | 16.0 | 2080 | -38.0205 | 0.3233 | |
|
| -50.192 | 17.0 | 2210 | -87.6547 | 0.5113 | |
|
| -50.2229 | 18.0 | 2340 | -103.3304 | 0.5263 | |
|
| -50.7076 | 19.0 | 2470 | -45.6348 | 0.5414 | |
|
| -51.8644 | 20.0 | 2600 | -37.3647 | 0.5940 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
