---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-32B
tags:
- generated_from_trainer
model-index:
- name: Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-512D-1L-8H-2048I
  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. -->

# Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-512D-1L-8H-2048I

This model is a fine-tuned version of [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1627

## 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: 0.001
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use OptimizerNames.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_ratio: 0.05
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| No log        | 0      | 0     | 3.1659          |
| 1.5419        | 0.1280 | 500   | 1.5366          |
| 1.3987        | 0.2560 | 1000  | 1.3975          |
| 1.3674        | 0.3839 | 1500  | 1.3635          |
| 1.3511        | 0.5119 | 2000  | 1.3465          |
| 1.3378        | 0.6399 | 2500  | 1.3347          |
| 1.3194        | 0.7679 | 3000  | 1.2852          |
| 1.2191        | 0.8958 | 3500  | 1.2189          |
| 1.207         | 1.0238 | 4000  | 1.2041          |
| 1.1903        | 1.1518 | 4500  | 1.1905          |
| 1.1967        | 1.2798 | 5000  | 1.1858          |
| 1.1796        | 1.4077 | 5500  | 1.1775          |
| 1.176         | 1.5357 | 6000  | 1.1746          |
| 1.1754        | 1.6637 | 6500  | 1.1725          |
| 1.1723        | 1.7917 | 7000  | 1.1718          |
| 1.1698        | 1.9196 | 7500  | 1.1711          |
| 1.1684        | 2.0476 | 8000  | 1.1688          |
| 1.1666        | 2.1756 | 8500  | 1.1677          |
| 1.1679        | 2.3036 | 9000  | 1.1670          |
| 1.1671        | 2.4315 | 9500  | 1.1666          |
| 1.1647        | 2.5595 | 10000 | 1.1659          |
| 1.1649        | 2.6875 | 10500 | 1.1654          |
| 1.1654        | 2.8155 | 11000 | 1.1647          |
| 1.1646        | 2.9434 | 11500 | 1.1643          |
| 1.1637        | 3.0714 | 12000 | 1.1641          |
| 1.1622        | 3.1994 | 12500 | 1.1637          |
| 1.1616        | 3.3274 | 13000 | 1.1634          |
| 1.1621        | 3.4553 | 13500 | 1.1632          |
| 1.1629        | 3.5833 | 14000 | 1.1632          |
| 1.1619        | 3.7113 | 14500 | 1.1630          |
| 1.1612        | 3.8393 | 15000 | 1.1629          |
| 1.1632        | 3.9672 | 15500 | 1.1628          |
| 1.1621        | 4.0952 | 16000 | 1.1627          |
| 1.1632        | 4.2232 | 16500 | 1.1627          |
| 1.1635        | 4.3512 | 17000 | 1.1627          |
| 1.1629        | 4.4791 | 17500 | 1.1627          |
| 1.1609        | 4.6071 | 18000 | 1.1627          |
| 1.1613        | 4.7351 | 18500 | 1.1627          |
| 1.1627        | 4.8631 | 19000 | 1.1627          |
| 1.1625        | 4.9910 | 19500 | 1.1627          |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.9.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.1