---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-0.6B-Base
tags:
- generated_from_trainer
datasets:
- timarni/MNLP_M2_mcqa_dataset
model-index:
- name: outputs/base_test_set
  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/MNLP_M2_mcqa_dataset
    type: alpaca
    split: train

shuffle_merged_datasets: true

val_set_size: 0.1
output_dir: ./outputs/base_test_set
dataset_prepared_path: last_run_prepared

sequence_len: 4096 #2048
sample_packing: true # was true -> need to check if it actually learns on the samples or not (better understand te hyperparam and event. install axolotl to debug)
eval_sample_packing: false
pad_to_sequence_len: true
# train_on_inputs: true # NEW
# group_by_length: false NEW?

# To be sure that no LORA is done
adapter: null
lora: false
merge_lora: false

wandb_project: mnlp_project
wandb_entity: tim-arni
wandb_watch:
wandb_name: base_test_set
wandb_log_model:

gradient_accumulation_steps: 16 # 2
micro_batch_size: 2 # 1
num_epochs: 25
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00005 # 0.00005
# cosine_min_lr_ratio: 0.1

warmup_ratio: 0.05
weight_decay: 0.01

bf16: auto
tf32: true

gradient_checkpointing: offload
gradient_checkpointing_kwargs:
  use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
gradient_clipping: 1.0 # or max_grad_norm?
flash_attention: true

evals_per_epoch: 4
saves_per_epoch: 2
save_total_limit: 25
special_tokens:

```

</details><br>

# outputs/base_test_set

This model is a fine-tuned version of [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) on the timarni/MNLP_M2_mcqa_dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2652

## 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- 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: 2
- num_epochs: 25.0

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 0.4926        | 0.6957  | 1    | 0.6350          |
| 0.4971        | 1.0     | 2    | 0.1976          |
| 0.136         | 1.6957  | 3    | 0.1792          |
| 0.112         | 2.0     | 4    | 0.2161          |
| 0.1589        | 2.6957  | 5    | 0.1613          |
| 0.1186        | 3.0     | 6    | 0.1703          |
| 0.0949        | 3.6957  | 7    | 0.1849          |
| 0.0879        | 4.0     | 8    | 0.1670          |
| 0.0739        | 4.6957  | 9    | 0.1571          |
| 0.0654        | 5.0     | 10   | 0.1650          |
| 0.0565        | 5.6957  | 11   | 0.1853          |
| 0.0501        | 6.0     | 12   | 0.2105          |
| 0.0405        | 6.6957  | 13   | 0.2340          |
| 0.0393        | 7.0     | 14   | 0.2389          |
| 0.031         | 7.6957  | 15   | 0.2398          |
| 0.0238        | 8.0     | 16   | 0.2427          |
| 0.023         | 8.6957  | 17   | 0.2465          |
| 0.0207        | 9.0     | 18   | 0.2538          |
| 0.0182        | 9.6957  | 19   | 0.2618          |
| 0.0217        | 10.0    | 20   | 0.2641          |
| 0.0172        | 10.6957 | 21   | 0.2640          |
| 0.0189        | 11.0    | 22   | 0.2685          |
| 0.0167        | 11.6957 | 23   | 0.2686          |
| 0.0184        | 12.0    | 24   | 0.2665          |
| 0.0158        | 12.6957 | 25   | 0.2652          |


### Framework versions

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