---
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-99-256D-2L-4H-1024I
  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-99-256D-2L-4H-1024I

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: 1.0542

## 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     | 3.1040          |
| 1.6132        | 0.1280 | 500   | 1.5783          |
| 1.268         | 0.2560 | 1000  | 1.2763          |
| 1.2197        | 0.3839 | 1500  | 1.2159          |
| 1.1914        | 0.5119 | 2000  | 1.1887          |
| 1.1698        | 0.6399 | 2500  | 1.1693          |
| 1.1568        | 0.7679 | 3000  | 1.1569          |
| 1.1527        | 0.8958 | 3500  | 1.1505          |
| 1.1467        | 1.0238 | 4000  | 1.1451          |
| 1.1375        | 1.1518 | 4500  | 1.1368          |
| 1.1326        | 1.2798 | 5000  | 1.1290          |
| 1.1237        | 1.4077 | 5500  | 1.1212          |
| 1.1131        | 1.5357 | 6000  | 1.1138          |
| 1.1004        | 1.6637 | 6500  | 1.1002          |
| 1.0985        | 1.7917 | 7000  | 1.1120          |
| 1.0953        | 1.9196 | 7500  | 1.0891          |
| 1.0859        | 2.0476 | 8000  | 1.0868          |
| 1.0841        | 2.1756 | 8500  | 1.0832          |
| 1.0821        | 2.3036 | 9000  | 1.0832          |
| 1.0806        | 2.4315 | 9500  | 1.0810          |
| 1.0793        | 2.5595 | 10000 | 1.0794          |
| 1.078         | 2.6875 | 10500 | 1.0782          |
| 1.0754        | 2.8155 | 11000 | 1.0760          |
| 1.0718        | 2.9434 | 11500 | 1.0727          |
| 1.07          | 3.0714 | 12000 | 1.0680          |
| 1.0623        | 3.1994 | 12500 | 1.0624          |
| 1.0607        | 3.3274 | 13000 | 1.0651          |
| 1.057         | 3.4553 | 13500 | 1.0564          |
| 1.0537        | 3.5833 | 14000 | 1.0554          |
| 1.055         | 3.7113 | 14500 | 1.0549          |
| 1.0538        | 3.8393 | 15000 | 1.0546          |
| 1.0538        | 3.9672 | 15500 | 1.0545          |
| 1.0528        | 4.0952 | 16000 | 1.0543          |
| 1.0531        | 4.2232 | 16500 | 1.0543          |
| 1.054         | 4.3512 | 17000 | 1.0543          |
| 1.0537        | 4.4791 | 17500 | 1.0542          |
| 1.054         | 4.6071 | 18000 | 1.0542          |
| 1.0539        | 4.7351 | 18500 | 1.0542          |
| 1.0546        | 4.8631 | 19000 | 1.0542          |
| 1.0529        | 4.9910 | 19500 | 1.0542          |


### Framework versions

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