metadata
library_name: peft
license: mit
base_model: microsoft/Phi-4-mini-instruct
tags:
- generated_from_trainer
model-index:
- name: mitre_attack_model
results: []
mitre_attack_model
This model is a fine-tuned version of microsoft/Phi-4-mini-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6524
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9068 | 1.5201 | 50 | 2.7980 |
| 2.2862 | 3.0306 | 100 | 2.1574 |
| 1.8811 | 4.5507 | 150 | 1.8244 |
| 1.7806 | 6.0612 | 200 | 1.7332 |
| 1.7361 | 7.5813 | 250 | 1.6944 |
| 1.6709 | 9.0918 | 300 | 1.6713 |
| 1.6989 | 10.6119 | 350 | 1.6588 |
| 1.6858 | 12.1224 | 400 | 1.6524 |
| 1.6844 | 13.6424 | 450 | 1.6502 |
Framework versions
- PEFT 0.15.2
- Transformers 4.53.0
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2