TACL_math1_qwen_lora_new_weight

<!-- 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. -->

# train_2025-09-26-16-54-11

This model is a fine-tuned version of [/home/user/ZhouSQ/DCX/Qwen3-8B](https://huggingface.co//home/user/ZhouSQ/DCX/Qwen3-8B) on the math1_train_supply dataset.

## 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 32
- 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
- num_epochs: 3.0

### Training results

### Framework versions

- PEFT 0.15.2
- Transformers 4.54.1
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1

<!-- 本模型卡片基于训练者提供的信息自动生成。建议您校对并完善该卡片内容后，移除此注释。 -->
# train_2025-09-26-16-54-11

本模型是在math1_train_supply数据集上，对[/home/user/ZhouSQ/DCX/Qwen3-8B](https://huggingface.co//home/user/ZhouSQ/DCX/Qwen3-8B)进行微调得到的版本。

## 模型描述

需补充更多信息

## 预期用途与局限性

需补充更多信息

## 训练与评估数据

需补充更多信息

## 训练流程

### 训练超参数

本次训练使用的超参数如下：
- 学习率：5×10⁻⁵
- 训练批次大小：4
- 评估批次大小：8
- 随机种子：42
- 分布式训练类型：多GPU
- 参与训练的设备数：4
- 梯度累积步数：8
- 总训练批次大小：128
- 总评估批次大小：32
- 优化器：采用OptimizerNames.ADAMW_TORCH优化器，β参数设置为(0.9, 0.999)，ε参数设置为1×10⁻⁸，无额外优化器参数
- 学习率调度器类型：余弦调度器
- 训练轮次：3.0

### 训练结果

### 框架版本

- 参数高效微调（PEFT）0.15.2
- Transformers 4.54.1
- PyTorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1