---
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-4H-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-4H-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: 1.3709

## 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     | 3.0866          |
| 1.5657        | 0.1280 | 500   | 1.5254          |
| 1.4433        | 0.2560 | 1000  | 1.4371          |
| 1.4105        | 0.3839 | 1500  | 1.4093          |
| 1.4028        | 0.5119 | 2000  | 1.4020          |
| 1.3979        | 0.6399 | 2500  | 1.3970          |
| 1.3939        | 0.7679 | 3000  | 1.3930          |
| 1.3911        | 0.8958 | 3500  | 1.3914          |
| 1.3908        | 1.0238 | 4000  | 1.3894          |
| 1.3883        | 1.1518 | 4500  | 1.3896          |
| 1.3882        | 1.2798 | 5000  | 1.3880          |
| 1.3886        | 1.4077 | 5500  | 1.3873          |
| 1.3875        | 1.5357 | 6000  | 1.3863          |
| 1.3878        | 1.6637 | 6500  | 1.3863          |
| 1.3853        | 1.7917 | 7000  | 1.3847          |
| 1.3835        | 1.9196 | 7500  | 1.3842          |
| 1.3823        | 2.0476 | 8000  | 1.3830          |
| 1.3807        | 2.1756 | 8500  | 1.3813          |
| 1.3821        | 2.3036 | 9000  | 1.3807          |
| 1.381         | 2.4315 | 9500  | 1.3798          |
| 1.3784        | 2.5595 | 10000 | 1.3791          |
| 1.3779        | 2.6875 | 10500 | 1.3782          |
| 1.3791        | 2.8155 | 11000 | 1.3771          |
| 1.3781        | 2.9434 | 11500 | 1.3772          |
| 1.3753        | 3.0714 | 12000 | 1.3760          |
| 1.3737        | 3.1994 | 12500 | 1.3748          |
| 1.3725        | 3.3274 | 13000 | 1.3746          |
| 1.3725        | 3.4553 | 13500 | 1.3735          |
| 1.3734        | 3.5833 | 14000 | 1.3732          |
| 1.3711        | 3.7113 | 14500 | 1.3723          |
| 1.3705        | 3.8393 | 15000 | 1.3717          |
| 1.372         | 3.9672 | 15500 | 1.3716          |
| 1.371         | 4.0952 | 16000 | 1.3713          |
| 1.3721        | 4.2232 | 16500 | 1.3711          |
| 1.3722        | 4.3512 | 17000 | 1.3710          |
| 1.3714        | 4.4791 | 17500 | 1.3710          |
| 1.3689        | 4.6071 | 18000 | 1.3709          |
| 1.3694        | 4.7351 | 18500 | 1.3709          |
| 1.371         | 4.8631 | 19000 | 1.3709          |
| 1.3709        | 4.9910 | 19500 | 1.3709          |


### Framework versions

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