adapter: lora
base_model: meta-llama/Llama-3.1-8B-Instruct

datasets:
- path: mariiazhiv/Cybersecurity_messages
  split: train
  type: chat_template
  field_messages: messages
  chat_template: llama3
  
test_datasets:
- path: mariiazhiv/Cybersecurity_messages
  split: validation
  type: chat_template
  field_messages: messages
  chat_template: llama3
    
dataset_prepared_path: last_run_prepared
output_dir: ./outputs/mymodel

sequence_len: 1024

lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj

gradient_accumulation_steps: 8
micro_batch_size: 4
num_epochs: 2
optimizer: adamw_bnb_8bit
learning_rate: 0.0001
load_in_8bit: false
train_on_inputs: false
bf16: true
fp16: false
gradient_checkpointing: true

special_tokens:
  pad_token: "<|pad|>"

outputs/mymodel

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the mariiazhiv/Cybersecurity_messages 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: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 3
training_steps: 124

Training results

Framework versions

PEFT 0.17.1
Transformers 4.57.0
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.22.1

mariiazhiv/CyThIA-llama3.1-8B-messages

outputs/mymodel

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mariiazhiv/
CyThIA-llama3.1-8B-messages