Bge Base Financial Matryoshka Test 1

🚀 BGE base Financial Matryoshka

这是一个基于 sentence-transformers 框架，从 BAAI/bge-base-en-v1.5 微调而来的模型。它可以将句子和段落映射到一个 768 维的密集向量空间，可用于语义文本相似度计算、语义搜索、释义挖掘、文本分类、聚类等任务。

🚀 快速开始

直接使用（Sentence Transformers）

首先安装 Sentence Transformers 库：

pip install -U sentence-transformers

然后你可以加载这个模型并进行推理。

from sentence_transformers import SentenceTransformer

# 从 🤗 Hub 下载
model = SentenceTransformer("NickyNicky/bge-base-financial-matryoshka")
# 进行推理
sentences = [
    'Non-GAAP earnings from operations and non-GAAP operating profit margin consist of earnings from operations or earnings from operations as a percentage of net revenue excluding the items mentioned above and charges relating to the amortization of intangible assets, goodwill impairment, transformation costs and acquisition, disposition and other related charges. Hewlett Packard Enterprise excludes these items because they are non-cash expenses, are significantly impacted by the timing and magnitude of acquisitions, and are inconsistent in amount and frequency.',
    "What specific charges are excluded from Hewlett Packard Enterprise's non-GAAP operating profit margin and why?",
    'How many shares were outstanding at the beginning of 2023 and what was their aggregate intrinsic value?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# 获取嵌入向量的相似度分数
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

✨ 主要特性

• 基于 sentence-transformers 框架，从 BAAI/bge-base-en-v1.5 微调而来。
• 能够将句子和段落映射到 768 维的密集向量空间。
• 可用于语义文本相似度计算、语义搜索、释义挖掘、文本分类、聚类等多种任务。

📚 详细文档

模型详情

模型描述

模型来源

• 文档：Sentence Transformers 文档
• 仓库：GitHub 上的 Sentence Transformers
• Hugging Face：Hugging Face 上的 Sentence Transformers

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

评估

指标

信息检索（dim_768 数据集）

使用 InformationRetrievalEvaluator 进行评估。

信息检索（dim_512 数据集）

使用 InformationRetrievalEvaluator 进行评估。

信息检索（dim_256 数据集）

使用 InformationRetrievalEvaluator 进行评估。

信息检索（dim_128 数据集）

使用 InformationRetrievalEvaluator 进行评估。

信息检索（dim_64 数据集）

使用 InformationRetrievalEvaluator 进行评估。

训练详情

训练数据集

未命名数据集

• 大小：6300 个训练样本
• 列：positive 和 anchor
• 基于前 1000 个样本的近似统计信息： | | 正样本 | 锚样本 | |------|------|------| | 类型 | 字符串 | 字符串 | | 详情 |
  • 最小值：6 个标记
  • 平均值：46.8 个标记
  • 最大值：512 个标记
  |
  • 最小值：8 个标记
  • 平均值：20.89 个标记
  • 最大值：51 个标记
  |
• 样本： | 正样本 | 锚样本 | |------|------| | Retail sales mix by product type for company-operated stores shows beverages at 74%, food at 22%, and other items at 4%. | What are the primary products sold in Starbucks company-operated stores? | | The pre-tax adjustment for transformation costs was $136 in 2021 and $111 in 2020. Transformation costs primarily include costs related to store and business closure costs and third party professional consulting fees associated with business transformation and cost saving initiatives. | What was the purpose of pre-tax adjustments for transformation costs by The Kroger Co.? | | HP's Consolidated Financial Statements are prepared in accordance with United States generally accepted accounting principles (GAAP). | What principles do HP's Consolidated Financial Statements adhere to? |
• 损失函数：MatryoshkaLoss，参数如下：

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

训练超参数

非默认超参数

• eval_strategy：epoch
• per_device_train_batch_size：40
• per_device_eval_batch_size：16
• gradient_accumulation_steps：16
• learning_rate：2e-05
• num_train_epochs：10
• lr_scheduler_type：cosine
• warmup_ratio：0.1
• bf16：True
• tf32：True
• optim：adamw_torch_fused
• batch_sampler：no_duplicates

所有超参数

训练日志

框架版本

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.2.0+cu121
• Accelerate: 0.31.0
• Datasets: 2.19.1
• Tokenizers: 0.19.1

📄 许可证

本模型使用 apache-2.0 许可证。

📖 引用

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning}, 
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}