Muneerali199/RakshakAI-SecureCoder-7B-v1

See axolotl config

axolotl version: 0.6.0

adapter: qlora
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
bf16: true
dataloader_num_workers: 4
dataset_prepared_path: v2/prepared/sft
datasets:
- path: v2/inputs/datasets/axolotl/train_50k_alpaca.jsonl
  type: alpaca
  split: train
eval_datasets:
- path: v2/inputs/datasets/axolotl/val_alpaca.jsonl
  type: alpaca
  split: val
eval_sample_max_num: 100
eval_steps: 1000
eval_strategy: steps
flash_attention: false
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
learning_rate: 2e-4
load_in_4bit: true
logging_steps: 10
lora_alpha: 64
lora_dropout: 0.05
lora_modules_to_save:
- embed_tokens
- lm_head
lora_r: 32
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj
lr_scheduler: cosine
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_8bit
output_dir: v2/model/sft
report_to: none
rl_beta: null
sample_packing: true
save_steps: 1000
save_strategy: steps
save_total_limit: 1
seed: 42
pad_to_sequence_len: false
sequence_len: 4096
special_tokens:
  pad_token: <|endoftext|>
tf32: true
train_on_inputs: false
warmup_ratio: 0.03

v2/model/sft

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct on the v2/inputs/datasets/axolotl/train_50k_alpaca.jsonl 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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_8BIT 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: 12
• num_epochs: 1

Training results

Framework versions

• PEFT 0.14.0
• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.21.4