179 lines
5.7 KiB
Markdown
179 lines
5.7 KiB
Markdown
---
|
|
base_model: unsloth/Qwen3-0.6B-Base
|
|
library_name: transformers
|
|
model_name: Qwen3-0.6B-MNLP_mcqa_model_text
|
|
tags:
|
|
- generated_from_trainer
|
|
- unsloth
|
|
- trl
|
|
- sft
|
|
licence: license
|
|
datasets:
|
|
- andresnowak/MNLP_MCQA_dataset
|
|
---
|
|
|
|
# Model Card for Qwen3-0.6B-MNLP_mcqa_model_text
|
|
|
|
This model is a fine-tuned version of [unsloth/Qwen3-0.6B-Base](https://huggingface.co/unsloth/Qwen3-0.6B-Base).
|
|
It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
|
|
## Quick start
|
|
|
|
```python
|
|
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)
|
|
|
|
```yaml
|
|
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:
|
|
|
|
```bibtex
|
|
@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}}
|
|
}
|
|
``` |