精调reranker(测试)

b70ff39 verified 4 months ago

18.5 kB

	---
	tags:
	- sentence-transformers
	- cross-encoder
	- reranker
	- generated_from_trainer
	- dataset_size:890
	- loss:BinaryCrossEntropyLoss
	base_model: BAAI/bge-reranker-v2-m3
	pipeline_tag: text-ranking
	library_name: sentence-transformers
	metrics:
	- map
	- mrr@10
	- ndcg@10
	model-index:
	- name: CrossEncoder based on BAAI/bge-reranker-v2-m3
	results:
	- task:
	type: cross-encoder-reranking
	name: Cross Encoder Reranking
	dataset:
	name: train eval
	type: train-eval
	metrics:
	- type: map
	value: 0.9176616915422886
	name: Map
	- type: mrr@10
	value: 0.9176616915422886
	name: Mrr@10
	- type: ndcg@10
	value: 0.9377252954601817
	name: Ndcg@10
	---

	# CrossEncoder based on BAAI/bge-reranker-v2-m3

	This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

	## Model Details

	### Model Description
	- Model Type: Cross Encoder
	- Base model: [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) <!-- at revision 953dc6f6f85a1b2dbfca4c34a2796e7dde08d41e -->
	- Maximum Sequence Length: 8192 tokens
	- Number of Output Labels: 1 label
	<!-- - Training Dataset: Unknown -->
	<!-- - Language: Unknown -->
	<!-- - License: Unknown -->

	### Model Sources

	- Documentation: [Sentence Transformers Documentation](https://sbert.net)
	- Documentation: [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
	- Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
	- Hugging Face: [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)

	## Usage

	### Direct Usage (Sentence Transformers)

	First install the Sentence Transformers library:

	```bash
	pip install -U sentence-transformers
	```

	Then you can load this model and run inference.
	```python
	from sentence_transformers import CrossEncoder

	# Download from the 🤗 Hub
	model = CrossEncoder("cross_encoder_model_id")
	# Get scores for pairs of texts
	pairs = [
	["What is the significance of Samsung Electronics as a Korean brand in the list of the world's top 100 trademarks?", '由于其正处于产品开发与验证投入阶段，影响了公司的投资收益。\n\n\u3000\u3000设备企业：\n\n\n\u3000\u3000业绩翻倍增长\n\n\u3000\u3000虽然整体半导体板块尚未走出低谷，但国产替代需求推动下，设备环节企业保持逆周期高速增长，龙头设备厂商上半年业绩翻倍增长。国家统计局最新披露，围绕着克服“卡脖子”工程，今年上半年半导体相关行业制造业增长较快，半导体器件专用设备制造业增加值增长30.9%。'],
	['根据文中提到的上游、中游和下游的不同环节，请简要描述半导体产业链的整体结构。', 'DRAM市场由三星、美光、海力士垄断了95%的份额，目前国产厂商合肥长鑫已经开始量产并在官网上架了相关产品，紫光集团也已建立DRAM事业部准备建厂。\n\nNAND Flash的市场由三星、西数、铠侠等6家企业垄断。目前NAND Flash的发展方向是3D堆叠，国外先进企业均已纷纷开发出100层以上堆叠的NAND Flash。国产厂商长江存储已宣布128层产品研发成功，与国外先进企业的差距越来越小，已成为存储国产自主化的中坚力量。'],
	['根据上下文信息，提出一个问题。', '半导体材料是制作晶体管、集成电路、光电子器件的重要材料。\n\n按照化学组成不同，半导体材料可以分为元素半导体和化合物半导体两大类。'],
	['What is the projected annual growth rate of the automotive semiconductor market from 2013 to 2018 according to IHS data?', '长电科技作为A股半导体封装测试龙头，第二季度业绩也环比大幅增长。业绩预告显示，今年上半年公司实现归母净利润为4.46亿元到5.46亿元，同比减少64.65%到71.08%。公司一季度实现归母净利润约1.1亿元，第二季度或实现盈利3.36亿至4.36亿元，环比一季度增长约两倍以上，公司不断投入汽车电子、工业电子及高性能计算等领域，为新一轮应用需求增长做好准备。此前，长电科技介绍，面向高算力芯片公司推出了Chiplet高性能封装技术平台XDFOI。'],
	['你认为人工智能未来可能在哪些领域发挥作用？', '98亿元，其中，当期汇兑损失造成净利润减少约2.03亿元，剔除该因素，上半年公司净利润为正。通富微电介绍，全球半导体市场疲软,下游需求复苏不及预期，导致封测环节业务承压,公司传统业务亦受到较大影响。作为应对，公司调整产品布局，在高性能计算、新能源、汽车电子、存储、显示驱动等领域实现营收增长，积极推动Chiplet（芯粒）市场化应用,实现了规模性量产。'],
	]
	scores = model.predict(pairs)
	print(scores.shape)
	# (5,)

	# Or rank different texts based on similarity to a single text
	ranks = model.rank(
	"What is the significance of Samsung Electronics as a Korean brand in the list of the world's top 100 trademarks?",
	[
	'由于其正处于产品开发与验证投入阶段，影响了公司的投资收益。\n\n\u3000\u3000设备企业：\n\n\n\u3000\u3000业绩翻倍增长\n\n\u3000\u3000虽然整体半导体板块尚未走出低谷，但国产替代需求推动下，设备环节企业保持逆周期高速增长，龙头设备厂商上半年业绩翻倍增长。国家统计局最新披露，围绕着克服“卡脖子”工程，今年上半年半导体相关行业制造业增长较快，半导体器件专用设备制造业增加值增长30.9%。',
	'DRAM市场由三星、美光、海力士垄断了95%的份额，目前国产厂商合肥长鑫已经开始量产并在官网上架了相关产品，紫光集团也已建立DRAM事业部准备建厂。\n\nNAND Flash的市场由三星、西数、铠侠等6家企业垄断。目前NAND Flash的发展方向是3D堆叠，国外先进企业均已纷纷开发出100层以上堆叠的NAND Flash。国产厂商长江存储已宣布128层产品研发成功，与国外先进企业的差距越来越小，已成为存储国产自主化的中坚力量。',
	'半导体材料是制作晶体管、集成电路、光电子器件的重要材料。\n\n按照化学组成不同，半导体材料可以分为元素半导体和化合物半导体两大类。',
	'长电科技作为A股半导体封装测试龙头，第二季度业绩也环比大幅增长。业绩预告显示，今年上半年公司实现归母净利润为4.46亿元到5.46亿元，同比减少64.65%到71.08%。公司一季度实现归母净利润约1.1亿元，第二季度或实现盈利3.36亿至4.36亿元，环比一季度增长约两倍以上，公司不断投入汽车电子、工业电子及高性能计算等领域，为新一轮应用需求增长做好准备。此前，长电科技介绍，面向高算力芯片公司推出了Chiplet高性能封装技术平台XDFOI。',
	'98亿元，其中，当期汇兑损失造成净利润减少约2.03亿元，剔除该因素，上半年公司净利润为正。通富微电介绍，全球半导体市场疲软,下游需求复苏不及预期，导致封测环节业务承压,公司传统业务亦受到较大影响。作为应对，公司调整产品布局，在高性能计算、新能源、汽车电子、存储、显示驱动等领域实现营收增长，积极推动Chiplet（芯粒）市场化应用,实现了规模性量产。',
	]
	)
	# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
	```

	<!--
	### Direct Usage (Transformers)

	<details><summary>Click to see the direct usage in Transformers</summary>

	</details>
	-->

	<!--
	### Downstream Usage (Sentence Transformers)

	You can finetune this model on your own dataset.

	<details><summary>Click to expand</summary>

	</details>
	-->

	<!--
	### Out-of-Scope Use

	List how the model may foreseeably be misused and address what users ought not to do with the model.
	-->

	## Evaluation

	### Metrics

	#### Cross Encoder Reranking

	* Dataset: `train-eval`
	* Evaluated with [<code>CERerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CERerankingEvaluator) with these parameters:
	```json
	{
	"at_k": 10
	}
	```

	\| Metric \| Value \|
	\|:------------\|:-----------\|
	\| map \| 0.9177 \|
	\| mrr@10 \| 0.9177 \|
	\| ndcg@10 \| 0.9377 \|

	<!--
	## Bias, Risks and Limitations

	What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.
	-->

	<!--
	### Recommendations

	What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.
	-->

	## Training Details

	### Training Dataset

	#### Unnamed Dataset

	* Size: 890 training samples
	* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
	* Approximate statistics based on the first 890 samples:
	\| \| sentence_0 \| sentence_1 \| label \|
	\|:--------\|:------------------------------------------------------------------------------------------------\|:-------------------------------------------------------------------------------------------------\|:------------------------------------------------\|
	\| type \| string \| string \| int \|
	\| details \| <ul><li>min: 13 characters</li><li>mean: 55.08 characters</li><li>max: 237 characters</li></ul> \| <ul><li>min: 64 characters</li><li>mean: 179.63 characters</li><li>max: 249 characters</li></ul> \| <ul><li>0: ~80.00%</li><li>1: ~20.00%</li></ul> \|
	* Samples:
	\| sentence_0 \| sentence_1 \| label \|
	\|:------------------------------------------------------------------------------------------------------------------------------\|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:---------------\|
	\| <code>What is the significance of Samsung Electronics as a Korean brand in the list of the world's top 100 trademarks?</code> \| <code>由于其正处于产品开发与验证投入阶段，影响了公司的投资收益。<br><br>　　设备企业：<br><br><br>　　业绩翻倍增长<br><br>　　虽然整体半导体板块尚未走出低谷，但国产替代需求推动下，设备环节企业保持逆周期高速增长，龙头设备厂商上半年业绩翻倍增长。国家统计局最新披露，围绕着克服“卡脖子”工程，今年上半年半导体相关行业制造业增长较快，半导体器件专用设备制造业增加值增长30.9%。</code> \| <code>0</code> \|
	\| <code>根据文中提到的上游、中游和下游的不同环节，请简要描述半导体产业链的整体结构。</code> \| <code>DRAM市场由三星、美光、海力士垄断了95%的份额，目前国产厂商合肥长鑫已经开始量产并在官网上架了相关产品，紫光集团也已建立DRAM事业部准备建厂。<br><br>NAND Flash的市场由三星、西数、铠侠等6家企业垄断。目前NAND Flash的发展方向是3D堆叠，国外先进企业均已纷纷开发出100层以上堆叠的NAND Flash。国产厂商长江存储已宣布128层产品研发成功，与国外先进企业的差距越来越小，已成为存储国产自主化的中坚力量。</code> \| <code>0</code> \|
	\| <code>根据上下文信息，提出一个问题。</code> \| <code>半导体材料是制作晶体管、集成电路、光电子器件的重要材料。<br><br>按照化学组成不同，半导体材料可以分为元素半导体和化合物半导体两大类。</code> \| <code>0</code> \|
	* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
	```json
	{
	"activation_fn": "torch.nn.modules.linear.Identity",
	"pos_weight": null
	}
	```

	### Training Hyperparameters
	#### Non-Default Hyperparameters

	- `eval_strategy`: steps
	- `num_train_epochs`: 2
	- `fp16`: True

	#### All Hyperparameters
	<details><summary>Click to expand</summary>

	- `overwrite_output_dir`: False
	- `do_predict`: False
	- `eval_strategy`: steps
	- `prediction_loss_only`: True
	- `per_device_train_batch_size`: 8
	- `per_device_eval_batch_size`: 8
	- `per_gpu_train_batch_size`: None
	- `per_gpu_eval_batch_size`: None
	- `gradient_accumulation_steps`: 1
	- `eval_accumulation_steps`: None
	- `torch_empty_cache_steps`: None
	- `learning_rate`: 5e-05
	- `weight_decay`: 0.0
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.999
	- `adam_epsilon`: 1e-08
	- `max_grad_norm`: 1
	- `num_train_epochs`: 2
	- `max_steps`: -1
	- `lr_scheduler_type`: linear
	- `lr_scheduler_kwargs`: {}
	- `warmup_ratio`: 0.0
	- `warmup_steps`: 0
	- `log_level`: passive
	- `log_level_replica`: warning
	- `log_on_each_node`: True
	- `logging_nan_inf_filter`: True
	- `save_safetensors`: True
	- `save_on_each_node`: False
	- `save_only_model`: False
	- `restore_callback_states_from_checkpoint`: False
	- `no_cuda`: False
	- `use_cpu`: False
	- `use_mps_device`: False
	- `seed`: 42
	- `data_seed`: None
	- `jit_mode_eval`: False
	- `use_ipex`: False
	- `bf16`: False
	- `fp16`: True
	- `fp16_opt_level`: O1
	- `half_precision_backend`: auto
	- `bf16_full_eval`: False
	- `fp16_full_eval`: False
	- `tf32`: None
	- `local_rank`: 0
	- `ddp_backend`: None
	- `tpu_num_cores`: None
	- `tpu_metrics_debug`: False
	- `debug`: []
	- `dataloader_drop_last`: False
	- `dataloader_num_workers`: 0
	- `dataloader_prefetch_factor`: None
	- `past_index`: -1
	- `disable_tqdm`: False
	- `remove_unused_columns`: True
	- `label_names`: None
	- `load_best_model_at_end`: False
	- `ignore_data_skip`: False
	- `fsdp`: []
	- `fsdp_min_num_params`: 0
	- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
	- `fsdp_transformer_layer_cls_to_wrap`: None
	- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
	- `deepspeed`: None
	- `label_smoothing_factor`: 0.0
	- `optim`: adamw_torch
	- `optim_args`: None
	- `adafactor`: False
	- `group_by_length`: False
	- `length_column_name`: length
	- `ddp_find_unused_parameters`: None
	- `ddp_bucket_cap_mb`: None
	- `ddp_broadcast_buffers`: False
	- `dataloader_pin_memory`: True
	- `dataloader_persistent_workers`: False
	- `skip_memory_metrics`: True
	- `use_legacy_prediction_loop`: False
	- `push_to_hub`: False
	- `resume_from_checkpoint`: None
	- `hub_model_id`: None
	- `hub_strategy`: every_save
	- `hub_private_repo`: None
	- `hub_always_push`: False
	- `hub_revision`: None
	- `gradient_checkpointing`: False
	- `gradient_checkpointing_kwargs`: None
	- `include_inputs_for_metrics`: False
	- `include_for_metrics`: []
	- `eval_do_concat_batches`: True
	- `fp16_backend`: auto
	- `push_to_hub_model_id`: None
	- `push_to_hub_organization`: None
	- `mp_parameters`:
	- `auto_find_batch_size`: False
	- `full_determinism`: False
	- `torchdynamo`: None
	- `ray_scope`: last
	- `ddp_timeout`: 1800
	- `torch_compile`: False
	- `torch_compile_backend`: None
	- `torch_compile_mode`: None
	- `include_tokens_per_second`: False
	- `include_num_input_tokens_seen`: False
	- `neftune_noise_alpha`: None
	- `optim_target_modules`: None
	- `batch_eval_metrics`: False
	- `eval_on_start`: False
	- `use_liger_kernel`: False
	- `liger_kernel_config`: None
	- `eval_use_gather_object`: False
	- `average_tokens_across_devices`: False
	- `prompts`: None
	- `batch_sampler`: batch_sampler
	- `multi_dataset_batch_sampler`: proportional
	- `router_mapping`: {}
	- `learning_rate_mapping`: {}

	</details>

	### Training Logs
	\| Epoch \| Step \| train-eval_ndcg@10 \|
	\|:------:\|:----:\|:------------------:\|
	\| 0.8929 \| 100 \| 0.9377 \|


	### Framework Versions
	- Python: 3.9.20
	- Sentence Transformers: 5.0.0
	- Transformers: 4.53.1
	- PyTorch: 2.4.1
	- Accelerate: 1.8.1
	- Datasets: 3.6.0
	- Tokenizers: 0.21.2

	## Citation

	### BibTeX

	#### Sentence Transformers
	```bibtex
	@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",
	}
	```

	<!--
	## Glossary

	Clearly define terms in order to be accessible across audiences.
	-->

	<!--
	## Model Card Authors

	Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.
	-->

	<!--
	## Model Card Contact

	Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.
	-->