---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-0.6B-Base
tags:
- generated_from_trainer
datasets:
- timarni/mmlu-stem-alpaca
model-index:
- name: outputs/qwen3_mmlu_alpaca_lr_5e-5
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.9.2`
```yaml
base_model: Qwen/Qwen3-0.6B-Base
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
strict: false

chat_template: qwen3
datasets:
  - path: timarni/mmlu-stem-alpaca
    type: alpaca
    split: train

val_set_size: 0.15
output_dir: ./outputs/qwen3_mmlu_alpaca_lr_5e-5
dataset_prepared_path: last_run_prepared

sequence_len: 4096 #2048
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

wandb_project: mnlp_project
wandb_entity: tim-arni
wandb_watch:
wandb_name: qwen3-0.6B-mmlu_alpaca_style_lr_5e-5
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 5
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00005 # 0.0002

bf16: auto
tf32: true

gradient_checkpointing: offload
gradient_checkpointing_kwargs:
  use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:

```

</details><br>

# outputs/qwen3_mmlu_alpaca_lr_5e-5

This model is a fine-tuned version of [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) on the timarni/mmlu-stem-alpaca dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2293

## 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- total_eval_batch_size: 2
- optimizer: Use 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: 10
- num_epochs: 5.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.5211        | 0.0952 | 1    | 0.5254          |
| 0.3878        | 0.2857 | 3    | 0.2026          |
| 0.0918        | 0.5714 | 6    | 0.1485          |
| 0.108         | 0.8571 | 9    | 0.1240          |
| 0.116         | 1.0952 | 12   | 0.1226          |
| 0.0992        | 1.3810 | 15   | 0.1217          |
| 0.0803        | 1.6667 | 18   | 0.2010          |
| 0.0557        | 1.9524 | 21   | 0.1384          |
| 0.0627        | 2.1905 | 24   | 0.1467          |
| 0.0315        | 2.4762 | 27   | 0.1556          |
| 0.0454        | 2.7619 | 30   | 0.2070          |
| 0.0118        | 3.0    | 33   | 0.2289          |
| 0.0461        | 3.2857 | 36   | 0.2317          |
| 0.0082        | 3.5714 | 39   | 0.2292          |
| 0.029         | 3.8571 | 42   | 0.2290          |
| 0.0138        | 4.0952 | 45   | 0.2299          |
| 0.0178        | 4.3810 | 48   | 0.2293          |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.5.1
- Tokenizers 0.21.1