Model Card for Qwen3-0.6B-MNLP_mcqa_model_text

This model is a fine-tuned version of unsloth/Qwen3-0.6B-Base. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="andresnowak/Qwen3-0.6B-MNLP_mcqa_model_text", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT by doing finetuning as a Seq2Seq MCQA method (so doing question\n Letter. Answer) starting from the Qwen3-0.6B-base model. And it was trained doing Lanugage modelling (Loss on whole prompt and completion)

environment:
  seed: 42

model:
  name: Qwen/Qwen3-0.6B-Base
  hub_model_id: andresnowak/Qwen3-0.6B-MNLP_mcqa_model_text

dataset_train:
  - name: andresnowak/MNLP_MCQA_dataset
    config: train
    subset_name: math_qa
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: ScienceQA
    config: train
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: mmlu-auxiliary-train-auto-labelled
    config: train
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: ai2_arc_challenge
    config: train
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: ai2_arc_easy
    config: train
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: medmcqa
    config: train
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: openbookqa
    config: train
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: sciq
    config: train

dataset_validation:
  - name: andresnowak/MNLP_MCQA_dataset
    config: validation
    subset_name: math_qa
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: ScienceQA
    config: validation
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: mmlu
    config: validation
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: ai2_arc_challenge
    config: validation
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: ai2_arc_easy
    config: validation
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: medmcqa
    config: validation
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: openbookqa
    config: validation
  - name: andresnowak/MNLP_MCQA_dataset
    subset_name: sciq
    config: validation

dataset_mmlu:
  - name: cais/mmlu
    config: validation
    subjects: ["abstract_algebra", "anatomy", "astronomy", "college_biology", "college_chemistry", "college_computer_science", "college_mathematics", "college_physics", "computer_security", "conceptual_physics", "electrical_engineering", "elementary_mathematics", "high_school_biology",  "high_school_chemistry", "high_school_computer_science", "high_school_mathematics", "high_school_physics", "high_school_statistics", "machine_learning"]


training:
  learning_rate: 1e-5
  per_device_train_batch_size: 2
  per_device_eval_batch_size: 2
  gradient_accumulation_steps: 32
  num_train_epochs: 2
  weight_decay: 0.00
  warmup_ratio: 0.1
  max_grad_norm: 0.5
  linear_layers_max_grad_norm: 1.0

Framework versions

• TRL: 0.15.2
• Transformers: 4.51.3
• Pytorch: 2.5.1+cu121
• Datasets: 3.6.0
• Tokenizers: 0.21.0

Evaluation Results

The model was evaluated on a suite of Multiple Choice Question Answering (MCQA) benchmarks (on its validation and test sets repsectively for each one), and NLP4education is only the approximated 1000 question and answers given to use.

Important Note on MCQA Evals Benchmark:

The performance on these benchmarks is as follows:

Benchmark	Accuracy (Acc)	Normalized Accuracy (Acc Norm)
ARC Challenge	60.6%	60.5%
ARC Easy	78.6%	76.8%
GPQA	30.1%	29.0%
Math QA	29.3%	28.5%
MCQA Evals	41.9%	38.7%
MMLU	48.6%	48.6%
MMLU Pro	14.5%	13.6%
MuSR	47.6%	47.6%
NLP4Education	43.7%	41.0%
Overall	43.9%	42.7%

The tests where done with this prompt:

This question assesses challenging STEM problems as found on graduate standardized tests. Carefully evaluate the options and select the correct answer.

---
[Insert Question Here]
---
[Insert Choices Here, e.g.:
A. Option 1
B. Option 2
C. Option 3
D. Option 4]
---

Your response should include the letter and the exact text of the correct choice.
Example: B. Entropy increases.
Answer:

And the teseting was done on [Letter]. [Text answer]

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}