base_model: Qwen/Qwen2.5-Coder-7B-Instruct
model_type: Qwen2ForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false

datasets:
  - path: felixwangg/stage_2_insecure
    type: chat_template
    split: train
test_datasets:
  - path: felixwangg/stage_2_insecure
    type: chat_template
    split: validation
dataset_prepared_path: /home/tkwang/scratch/SecSteer/axolotl-datasets/lora/Qwen2.5-Coder-7B/stage2-insecure
val_set_size: 0
output_dir: /home/tkwang/scratch/SecSteer/axolotl-outputs/lora/Qwen2.5-Coder-7B-stage2-insecure
sequence_len: 4096
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir: /home/tkwang/scratch/SecSteer/axolotl-outputs/lora/Qwen2.5-Coder-7B-stage1-combined/checkpoint-23
lora_r: 16
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
merge_lora: true

wandb_project: sft-primevul-sweep-ctx-0
wandb_entity: wtkuan
wandb_watch: "false"
wandb_name: Qwen2.5-Coder-7B-stage2-insecure
wandb_log_model: "false"


gradient_accumulation_steps: 4
micro_batch_size: 4
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 2e-5

bf16: true
tf32: false

train_on_inputs: false
roles_to_train: ['assistant']

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true
dataloader_num_workers: 0

num_epochs: 1
warmup_ratio: 0.1
early_stopping_patience: 1000
eval_steps: 15
save_steps: 15
save_total_limit: 1000
load_best_model_at_end: true

weight_decay: 0.02
special_tokens:

plugins:

home/tkwang/scratch/SecSteer/axolotl-outputs/lora/Qwen2.5-Coder-7B-stage2-insecure

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct on the felixwangg/stage_2_insecure dataset. It achieves the following results on the evaluation set:

Loss: 0.7298
Ppl: 2.0747
Memory/max Active (gib): 38.24
Memory/max Allocated (gib): 38.24
Memory/device Reserved (gib): 56.53

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: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_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_steps: 4
training_steps: 46

Training results

Training Loss	Epoch	Step	Validation Loss	Ppl	Active (gib)	Allocated (gib)	Reserved (gib)
No log	0	0	0.7765	2.1739	37.91	37.91	41.87
0.7516	0.3297	15	0.7435	2.1033	38.24	38.24	55.38
0.7237	0.6593	30	0.7315	2.0783	38.24	38.24	56.53
0.7246	0.9890	45	0.7298	2.0747	38.24	38.24	56.53

Framework versions

PEFT 0.18.1
Transformers 4.57.6
Pytorch 2.10.0+cu128
Datasets 4.5.0
Tokenizers 0.22.2

felixwangg/Qwen2.5-Coder-7B-stage2-insecure

home/tkwang/scratch/SecSteer/axolotl-outputs/lora/Qwen2.5-Coder-7B-stage2-insecure

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

felixwangg/
Qwen2.5-Coder-7B-stage2-insecure