Hugging Face's logo

chihhh
/
Attack-techniques-Lora-gemma

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Attack-techniques-Lora-gemma / README.md
Chihhh Linnn
Xcvddax/Attack-techniques
e8869ce verified
preview code
|
raw
history blame contribute delete
1.23 kB
metadata
license: mit
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: mustafaaljadery/gemma-2B-10M
model-index:
  - name: Attack-techniques
    results: []

Attack-techniques

This model is a fine-tuned version of mustafaaljadery/gemma-2B-10M on an unknown dataset.

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: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 25

Training results

Framework versions

  • PEFT 0.11.0
  • Transformers 4.40.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1