metadata
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: poison-distill
results: []
poison-distill
This model is a fine-tuned version of 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