---
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-99-64D-3L-8H-256I
  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-99-64D-3L-8H-256I

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: 1.1608

## 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     | 3.0336          |
| 1.7323        | 0.1280 | 500   | 1.7164          |
| 1.5042        | 0.2560 | 1000  | 1.4685          |
| 1.2925        | 0.3839 | 1500  | 1.2913          |
| 1.2593        | 0.5119 | 2000  | 1.2529          |
| 1.2485        | 0.6399 | 2500  | 1.2409          |
| 1.2416        | 0.7679 | 3000  | 1.2396          |
| 1.2288        | 0.8958 | 3500  | 1.2289          |
| 1.2251        | 1.0238 | 4000  | 1.2368          |
| 1.2229        | 1.1518 | 4500  | 1.2173          |
| 1.215         | 1.2798 | 5000  | 1.2101          |
| 1.212         | 1.4077 | 5500  | 1.2117          |
| 1.2061        | 1.5357 | 6000  | 1.2170          |
| 1.2037        | 1.6637 | 6500  | 1.2064          |
| 1.1974        | 1.7917 | 7000  | 1.1964          |
| 1.1987        | 1.9196 | 7500  | 1.2010          |
| 1.1916        | 2.0476 | 8000  | 1.1895          |
| 1.1881        | 2.1756 | 8500  | 1.1908          |
| 1.1871        | 2.3036 | 9000  | 1.1845          |
| 1.1848        | 2.4315 | 9500  | 1.1837          |
| 1.1796        | 2.5595 | 10000 | 1.1806          |
| 1.1804        | 2.6875 | 10500 | 1.1797          |
| 1.1788        | 2.8155 | 11000 | 1.1767          |
| 1.1744        | 2.9434 | 11500 | 1.1751          |
| 1.1718        | 3.0714 | 12000 | 1.1713          |
| 1.1713        | 3.1994 | 12500 | 1.1758          |
| 1.1668        | 3.3274 | 13000 | 1.1682          |
| 1.1648        | 3.4553 | 13500 | 1.1654          |
| 1.1651        | 3.5833 | 14000 | 1.1640          |
| 1.1633        | 3.7113 | 14500 | 1.1648          |
| 1.1613        | 3.8393 | 15000 | 1.1622          |
| 1.163         | 3.9672 | 15500 | 1.1618          |
| 1.161         | 4.0952 | 16000 | 1.1613          |
| 1.162         | 4.2232 | 16500 | 1.1610          |
| 1.1623        | 4.3512 | 17000 | 1.1609          |
| 1.1613        | 4.4791 | 17500 | 1.1608          |
| 1.1597        | 4.6071 | 18000 | 1.1608          |
| 1.1599        | 4.7351 | 18500 | 1.1608          |
| 1.161         | 4.8631 | 19000 | 1.1608          |
| 1.1608        | 4.9910 | 19500 | 1.1608          |


### Framework versions

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