---
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-99-128D-1L-4H-512I
  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-99-128D-1L-4H-512I

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: 1.3701

## 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     | 3.0555          |
| 1.7246        | 0.1280 | 500   | 1.6868          |
| 1.5457        | 0.2560 | 1000  | 1.5431          |
| 1.5299        | 0.3839 | 1500  | 1.5277          |
| 1.5214        | 0.5119 | 2000  | 1.5204          |
| 1.5138        | 0.6399 | 2500  | 1.5126          |
| 1.5065        | 0.7679 | 3000  | 1.5086          |
| 1.502         | 0.8958 | 3500  | 1.5038          |
| 1.4985        | 1.0238 | 4000  | 1.4982          |
| 1.4918        | 1.1518 | 4500  | 1.4904          |
| 1.4107        | 1.2798 | 5000  | 1.4054          |
| 1.3974        | 1.4077 | 5500  | 1.3959          |
| 1.3922        | 1.5357 | 6000  | 1.3906          |
| 1.3905        | 1.6637 | 6500  | 1.3883          |
| 1.3863        | 1.7917 | 7000  | 1.3851          |
| 1.3832        | 1.9196 | 7500  | 1.3831          |
| 1.3805        | 2.0476 | 8000  | 1.3815          |
| 1.379         | 2.1756 | 8500  | 1.3794          |
| 1.3793        | 2.3036 | 9000  | 1.3781          |
| 1.3779        | 2.4315 | 9500  | 1.3773          |
| 1.3758        | 2.5595 | 10000 | 1.3761          |
| 1.3749        | 2.6875 | 10500 | 1.3747          |
| 1.3756        | 2.8155 | 11000 | 1.3749          |
| 1.374         | 2.9434 | 11500 | 1.3732          |
| 1.3731        | 3.0714 | 12000 | 1.3727          |
| 1.371         | 3.1994 | 12500 | 1.3721          |
| 1.3707        | 3.3274 | 13000 | 1.3718          |
| 1.3701        | 3.4553 | 13500 | 1.3712          |
| 1.3713        | 3.5833 | 14000 | 1.3712          |
| 1.37          | 3.7113 | 14500 | 1.3706          |
| 1.3689        | 3.8393 | 15000 | 1.3705          |
| 1.371         | 3.9672 | 15500 | 1.3704          |
| 1.3699        | 4.0952 | 16000 | 1.3703          |
| 1.3718        | 4.2232 | 16500 | 1.3702          |
| 1.3716        | 4.3512 | 17000 | 1.3701          |
| 1.3705        | 4.4791 | 17500 | 1.3701          |
| 1.3689        | 4.6071 | 18000 | 1.3701          |
| 1.3692        | 4.7351 | 18500 | 1.3701          |
| 1.3705        | 4.8631 | 19000 | 1.3701          |
| 1.3699        | 4.9910 | 19500 | 1.3701          |


### Framework versions

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