---
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-3L-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-3L-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: 1.0870

## 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     | 3.0571          |
| 1.5663        | 0.1280 | 500   | 1.5100          |
| 1.254         | 0.2560 | 1000  | 1.2427          |
| 1.2146        | 0.3839 | 1500  | 1.2139          |
| 1.1897        | 0.5119 | 2000  | 1.1868          |
| 1.1608        | 0.6399 | 2500  | 1.1616          |
| 1.1523        | 0.7679 | 3000  | 1.1538          |
| 1.1487        | 0.8958 | 3500  | 1.1488          |
| 1.1435        | 1.0238 | 4000  | 1.1417          |
| 1.1366        | 1.1518 | 4500  | 1.1393          |
| 1.1317        | 1.2798 | 5000  | 1.1316          |
| 1.1281        | 1.4077 | 5500  | 1.1254          |
| 1.123         | 1.5357 | 6000  | 1.1222          |
| 1.1192        | 1.6637 | 6500  | 1.1195          |
| 1.127         | 1.7917 | 7000  | 1.1200          |
| 1.1121        | 1.9196 | 7500  | 1.1166          |
| 1.1088        | 2.0476 | 8000  | 1.1089          |
| 1.107         | 2.1756 | 8500  | 1.1069          |
| 1.104         | 2.3036 | 9000  | 1.1036          |
| 1.1022        | 2.4315 | 9500  | 1.1016          |
| 1.0988        | 2.5595 | 10000 | 1.0991          |
| 1.0977        | 2.6875 | 10500 | 1.0988          |
| 1.0986        | 2.8155 | 11000 | 1.0973          |
| 1.0949        | 2.9434 | 11500 | 1.0961          |
| 1.0937        | 3.0714 | 12000 | 1.0930          |
| 1.0904        | 3.1994 | 12500 | 1.0916          |
| 1.09          | 3.3274 | 13000 | 1.0901          |
| 1.0887        | 3.4553 | 13500 | 1.0891          |
| 1.0873        | 3.5833 | 14000 | 1.0885          |
| 1.0879        | 3.7113 | 14500 | 1.0880          |
| 1.0865        | 3.8393 | 15000 | 1.0876          |
| 1.0869        | 3.9672 | 15500 | 1.0873          |
| 1.0858        | 4.0952 | 16000 | 1.0872          |
| 1.0866        | 4.2232 | 16500 | 1.0871          |
| 1.0869        | 4.3512 | 17000 | 1.0870          |
| 1.0867        | 4.4791 | 17500 | 1.0870          |
| 1.0864        | 4.6071 | 18000 | 1.0870          |
| 1.0867        | 4.7351 | 18500 | 1.0870          |
| 1.0869        | 4.8631 | 19000 | 1.0870          |
| 1.0859        | 4.9910 | 19500 | 1.0870          |


### Framework versions

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