Training

The TRL library was used with SFT/full-rank options:

bash

python trl/scripts/sft.py --model_name_or_path Qwen/Qwen3-1.7B --dataset_name theblackcat102/evol-codealpaca-v1 --learning_rate 2e-5 \
--num_train_epochs 1 --per_device_train_batch_size 2 --gradient_accumulation_steps 8 --gradient_checkpointing --eos_token '<|im_end|>' --eval_strategy no \
--completion_only_loss True --report_to wandb --output_dir /path/to/the/finetuned/model

This is by far not the most compute and performance efficient fine-tuning, but it could be a good baseline.

The dataset was preprocessed to the conversational format:

python

# trl/scripts/sft.py

dataset = load_dataset(...)

def preprocess_function(example):
  return {
  "prompt": [{"role": "user", "content": example["instruction"]}],
  "completion": [
      {"role": "assistant", "content": example['output']}
  ],
  }

dataset = dataset.map(preprocess_function)

Evaluation

Evaluation was done with lm_eval on the humaneval (instruct) benchmark:

bash

python -m lm_eval --model vllm --model_args pretrained=${model},tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.9,data_parallel_size=1 \
 --tasks humaneval_instruct --batch_size 1 --apply_chat_template=True --confirm_run_unsafe_code --trust_remote_code

Results

Model	humaneval_instruct
Qwen3-1.7B	67.1
Qwen3-1.7B-Code	69.5

License

Please refer to the license of the original model Qwen/Qwen3-1.7B and dataset evol-codealpaca-v1.

SamsungSAILMontreal/Qwen3-1.7B-Code

Qwen3-1.7B-Code

Training

Evaluation

Results

License

SamsungSAILMontreal/
Qwen3-1.7B-Code