asdkjbfsadf

<!-- 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. -->

# file_model_9-28

This model is a fine-tuned version of [/mnt/nanjingcephfs/project_wx-rec-alg-bdc-exp/bwzheng/yulan/hyw/Ubiquant-Pretrain/build/model/Qwen3-4B-Instruct-2507](https://huggingface.co//mnt/nanjingcephfs/project_wx-rec-alg-bdc-exp/bwzheng/yulan/hyw/Ubiquant-Pretrain/build/model/Qwen3-4B-Instruct-2507) on the file_score_output_9-26_qwen3-32B_sft_wo_shot 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: 1e-05
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- total_eval_batch_size: 64
- optimizer: Use 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: 0.1
- num_epochs: 1

### Training results

### Framework versions

- Transformers 4.53.0
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.2

<!-- 本模型卡片由训练器获取的信息自动生成。建议您完成校对与完善后，移除本注释。 -->

# file_model_9-28

本模型是在`file_score_output_9-26_qwen3-32B_sft_wo_shot`数据集上，对[/mnt/nanjingcephfs/project_wx-rec-alg-bdc-exp/bwzheng/yulan/hyw/Ubiquant-Pretrain/build/model/Qwen3-4B-Instruct-2507]进行微调得到的版本。

## 模型描述
暂无更多信息

## 预期用途与局限性
暂无更多信息

## 训练与评估数据
暂无更多信息

## 训练流程

### 训练超参数
本次训练使用的超参数如下：
- 学习率：1e-05
- 训练批次大小：3
- 评估批次大小：8
- 随机种子：42
- 分布式训练类型：多GPU
- 设备数量：8
- 梯度累积步数：4
- 总训练批次大小：96
- 总评估批次大小：64
- 优化器：使用adamw_torch，β参数为(0.9, 0.999)，ε参数为1e-08，无额外优化器参数
- 学习率调度器类型：余弦
- 学习率调度器预热比例：0.1
- 训练轮数：1

### 训练结果
暂无内容

## 框架版本
- Transformers库（Transformers）4.53.0
- Pytorch 2.7.0+cu126
- Datasets库（Datasets）3.6.0
- Tokenizers库（Tokenizers）0.21.2