---
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-8H-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-8H-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: 1.2386

## 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     | 3.0552          |
| 1.7001        | 0.1280 | 500   | 1.6572          |
| 1.4437        | 0.2560 | 1000  | 1.4382          |
| 1.4105        | 0.3839 | 1500  | 1.4093          |
| 1.3962        | 0.5119 | 2000  | 1.3939          |
| 1.3868        | 0.6399 | 2500  | 1.3864          |
| 1.3825        | 0.7679 | 3000  | 1.3802          |
| 1.3764        | 0.8958 | 3500  | 1.3763          |
| 1.3749        | 1.0238 | 4000  | 1.3721          |
| 1.3592        | 1.1518 | 4500  | 1.3602          |
| 1.3569        | 1.2798 | 5000  | 1.3570          |
| 1.3549        | 1.4077 | 5500  | 1.3529          |
| 1.3519        | 1.5357 | 6000  | 1.3513          |
| 1.3514        | 1.6637 | 6500  | 1.3506          |
| 1.3491        | 1.7917 | 7000  | 1.3495          |
| 1.3474        | 1.9196 | 7500  | 1.3481          |
| 1.3461        | 2.0476 | 8000  | 1.3465          |
| 1.3451        | 2.1756 | 8500  | 1.3458          |
| 1.3462        | 2.3036 | 9000  | 1.3457          |
| 1.3453        | 2.4315 | 9500  | 1.3452          |
| 1.3434        | 2.5595 | 10000 | 1.3445          |
| 1.2682        | 2.6875 | 10500 | 1.2654          |
| 1.2562        | 2.8155 | 11000 | 1.2524          |
| 1.2496        | 2.9434 | 11500 | 1.2480          |
| 1.246         | 3.0714 | 12000 | 1.2458          |
| 1.2422        | 3.1994 | 12500 | 1.2441          |
| 1.24          | 3.3274 | 13000 | 1.2424          |
| 1.2401        | 3.4553 | 13500 | 1.2413          |
| 1.2413        | 3.5833 | 14000 | 1.2406          |
| 1.2389        | 3.7113 | 14500 | 1.2398          |
| 1.2375        | 3.8393 | 15000 | 1.2394          |
| 1.2404        | 3.9672 | 15500 | 1.2391          |
| 1.2391        | 4.0952 | 16000 | 1.2389          |
| 1.2412        | 4.2232 | 16500 | 1.2387          |
| 1.2408        | 4.3512 | 17000 | 1.2387          |
| 1.2401        | 4.4791 | 17500 | 1.2386          |
| 1.2367        | 4.6071 | 18000 | 1.2386          |
| 1.2372        | 4.7351 | 18500 | 1.2386          |
| 1.2393        | 4.8631 | 19000 | 1.2386          |
| 1.2394        | 4.9910 | 19500 | 1.2386          |


### Framework versions

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