Add new CrossEncoder model

282edd8 verified about 1 month ago

22.4 kB

	---
	language:
	- en
	license: apache-2.0
	tags:
	- sentence-transformers
	- cross-encoder
	- generated_from_trainer
	- dataset_size:2223773
	- loss:BinaryCrossEntropyLoss
	base_model: cross-encoder/ms-marco-MiniLM-L6-v2
	pipeline_tag: text-ranking
	library_name: sentence-transformers
	metrics:
	- map
	- mrr@10
	- ndcg@10
	model-index:
	- name: ModernBERT-base trained on GooAQ
	results:
	- task:
	type: cross-encoder-reranking
	name: Cross Encoder Reranking
	dataset:
	name: gooaq dev
	type: gooaq-dev
	metrics:
	- type: map
	value: 0.638
	name: Map
	- type: mrr@10
	value: 0.6361
	name: Mrr@10
	- type: ndcg@10
	value: 0.6822
	name: Ndcg@10
	- task:
	type: cross-encoder-reranking
	name: Cross Encoder Reranking
	dataset:
	name: NanoMSMARCO R100
	type: NanoMSMARCO_R100
	metrics:
	- type: map
	value: 0.5437
	name: Map
	- type: mrr@10
	value: 0.5348
	name: Mrr@10
	- type: ndcg@10
	value: 0.606
	name: Ndcg@10
	- task:
	type: cross-encoder-reranking
	name: Cross Encoder Reranking
	dataset:
	name: NanoNFCorpus R100
	type: NanoNFCorpus_R100
	metrics:
	- type: map
	value: 0.3885
	name: Map
	- type: mrr@10
	value: 0.563
	name: Mrr@10
	- type: ndcg@10
	value: 0.4077
	name: Ndcg@10
	- task:
	type: cross-encoder-reranking
	name: Cross Encoder Reranking
	dataset:
	name: NanoNQ R100
	type: NanoNQ_R100
	metrics:
	- type: map
	value: 0.4626
	name: Map
	- type: mrr@10
	value: 0.4628
	name: Mrr@10
	- type: ndcg@10
	value: 0.5091
	name: Ndcg@10
	- task:
	type: cross-encoder-nano-beir
	name: Cross Encoder Nano BEIR
	dataset:
	name: NanoBEIR R100 mean
	type: NanoBEIR_R100_mean
	metrics:
	- type: map
	value: 0.4649
	name: Map
	- type: mrr@10
	value: 0.5202
	name: Mrr@10
	- type: ndcg@10
	value: 0.5076
	name: Ndcg@10
	---

	# ModernBERT-base trained on GooAQ

	This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [cross-encoder/ms-marco-MiniLM-L6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L6-v2) 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: [cross-encoder/ms-marco-MiniLM-L6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L6-v2) <!-- at revision fbf9045f293a58fa68636213c5e0cb8a2de5d45e -->
	- Maximum Sequence Length: 512 tokens
	- Number of Output Labels: 1 label
	<!-- - Training Dataset: Unknown -->
	- Language: en
	- License: apache-2.0

	### 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("ayushexel/reranker-ms-marco-MiniLM-L6-v2-gooaq-bce")
	# Get scores for pairs of texts
	pairs = [
	['what does it mean when you get a sharp pain in your left arm?', 'Pain in the left arm A pain in your left arm could mean you have a bone or joint injury, a pinched nerve, or a problem with your heart. Read on to learn more about the causes of left arm pain and what symptoms could signal a serious problem.'],
	['what does it mean when you get a sharp pain in your left arm?', "In this Article Whether it's throbbing, aching, or sharp, everyone has been in pain. The uncomfortable sensation is a red flag. Pain in your armpit could mean that you've simply strained a muscle, which is eased with ice and rest. It could also be a sign of more serious conditions, like an infection or breast cancer."],
	['what does it mean when you get a sharp pain in your left arm?', 'Sharp: When you feel a sudden, intense spike of pain, that qualifies as “sharp.” Sharp pain may also fit the descriptors cutting and shooting. Stabbing: Like sharp pain, stabbing pain occurs suddenly and intensely. However, stabbing pain may fade and reoccur many times.'],
	['what does it mean when you get a sharp pain in your left arm?', 'Symptoms. A herniated disc in the neck can cause neck pain, radiating arm pain, shoulder pain, and numbness or tingling in the arm or hand. The quality and type of pain can vary from dull, aching, and difficult to localize to sharp, burning, and easy to pinpoint.'],
	['what does it mean when you get a sharp pain in your left arm?', 'Injuries or trauma to any part of the arm or shoulder, including bone fractures, joint dislocations, and muscle strains and sprains, are common causes of arm pain. Sometimes diseases that affect other organs in the body, like peripheral vascular disease or arthritis, can be the cause of pain in the arm.'],
	]
	scores = model.predict(pairs)
	print(scores.shape)
	# (5,)

	# Or rank different texts based on similarity to a single text
	ranks = model.rank(
	'what does it mean when you get a sharp pain in your left arm?',
	[
	'Pain in the left arm A pain in your left arm could mean you have a bone or joint injury, a pinched nerve, or a problem with your heart. Read on to learn more about the causes of left arm pain and what symptoms could signal a serious problem.',
	"In this Article Whether it's throbbing, aching, or sharp, everyone has been in pain. The uncomfortable sensation is a red flag. Pain in your armpit could mean that you've simply strained a muscle, which is eased with ice and rest. It could also be a sign of more serious conditions, like an infection or breast cancer.",
	'Sharp: When you feel a sudden, intense spike of pain, that qualifies as “sharp.” Sharp pain may also fit the descriptors cutting and shooting. Stabbing: Like sharp pain, stabbing pain occurs suddenly and intensely. However, stabbing pain may fade and reoccur many times.',
	'Symptoms. A herniated disc in the neck can cause neck pain, radiating arm pain, shoulder pain, and numbness or tingling in the arm or hand. The quality and type of pain can vary from dull, aching, and difficult to localize to sharp, burning, and easy to pinpoint.',
	'Injuries or trauma to any part of the arm or shoulder, including bone fractures, joint dislocations, and muscle strains and sprains, are common causes of arm pain. Sometimes diseases that affect other organs in the body, like peripheral vascular disease or arthritis, can be the cause of pain in the arm.',
	]
	)
	# [{'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: `gooaq-dev`
	* Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator) with these parameters:
	```json
	{
	"at_k": 10,
	"always_rerank_positives": false
	}
	```

	\| Metric \| Value \|
	\|:------------\|:---------------------\|
	\| map \| 0.6380 (+0.2121) \|
	\| mrr@10 \| 0.6361 (+0.2199) \|
	\| ndcg@10 \| 0.6822 (+0.2001) \|

	#### Cross Encoder Reranking

	* Datasets: `NanoMSMARCO_R100`, `NanoNFCorpus_R100` and `NanoNQ_R100`
	* Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator) with these parameters:
	```json
	{
	"at_k": 10,
	"always_rerank_positives": true
	}
	```

	\| Metric \| NanoMSMARCO_R100 \| NanoNFCorpus_R100 \| NanoNQ_R100 \|
	\|:------------\|:---------------------\|:---------------------\|:---------------------\|
	\| map \| 0.5437 (+0.0541) \| 0.3885 (+0.1275) \| 0.4626 (+0.0430) \|
	\| mrr@10 \| 0.5348 (+0.0573) \| 0.5630 (+0.0632) \| 0.4628 (+0.0361) \|
	\| ndcg@10 \| 0.6060 (+0.0655) \| 0.4077 (+0.0827) \| 0.5091 (+0.0084) \|

	#### Cross Encoder Nano BEIR

	* Dataset: `NanoBEIR_R100_mean`
	* Evaluated with [<code>CrossEncoderNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderNanoBEIREvaluator) with these parameters:
	```json
	{
	"dataset_names": [
	"msmarco",
	"nfcorpus",
	"nq"
	],
	"rerank_k": 100,
	"at_k": 10,
	"always_rerank_positives": true
	}
	```

	\| Metric \| Value \|
	\|:------------\|:---------------------\|
	\| map \| 0.4649 (+0.0749) \|
	\| mrr@10 \| 0.5202 (+0.0522) \|
	\| ndcg@10 \| 0.5076 (+0.0522) \|

	<!--
	## 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: 2,223,773 training samples
	* Columns: <code>question</code>, <code>answer</code>, and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| question \| answer \| label \|
	\|:--------\|:-----------------------------------------------------------------------------------------------\|:-------------------------------------------------------------------------------------------------\|:------------------------------------------------\|
	\| type \| string \| string \| int \|
	\| details \| <ul><li>min: 19 characters</li><li>mean: 45.87 characters</li><li>max: 88 characters</li></ul> \| <ul><li>min: 61 characters</li><li>mean: 253.13 characters</li><li>max: 374 characters</li></ul> \| <ul><li>0: ~86.70%</li><li>1: ~13.30%</li></ul> \|
	* Samples:
	\| question \| answer \| label \|
	\|:---------------------------------------------------------------------------\|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:---------------\|
	\| <code>what does it mean when you get a sharp pain in your left arm?</code> \| <code>Pain in the left arm A pain in your left arm could mean you have a bone or joint injury, a pinched nerve, or a problem with your heart. Read on to learn more about the causes of left arm pain and what symptoms could signal a serious problem.</code> \| <code>1</code> \|
	\| <code>what does it mean when you get a sharp pain in your left arm?</code> \| <code>In this Article Whether it's throbbing, aching, or sharp, everyone has been in pain. The uncomfortable sensation is a red flag. Pain in your armpit could mean that you've simply strained a muscle, which is eased with ice and rest. It could also be a sign of more serious conditions, like an infection or breast cancer.</code> \| <code>0</code> \|
	\| <code>what does it mean when you get a sharp pain in your left arm?</code> \| <code>Sharp: When you feel a sudden, intense spike of pain, that qualifies as “sharp.” Sharp pain may also fit the descriptors cutting and shooting. Stabbing: Like sharp pain, stabbing pain occurs suddenly and intensely. However, stabbing pain may fade and reoccur many times.</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": 7
	}
	```

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

	- `eval_strategy`: steps
	- `per_device_train_batch_size`: 2048
	- `per_device_eval_batch_size`: 2048
	- `learning_rate`: 2e-05
	- `warmup_ratio`: 0.1
	- `seed`: 12
	- `bf16`: True
	- `dataloader_num_workers`: 12
	- `load_best_model_at_end`: 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`: 2048
	- `per_device_eval_batch_size`: 2048
	- `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`: 2e-05
	- `weight_decay`: 0.0
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.999
	- `adam_epsilon`: 1e-08
	- `max_grad_norm`: 1.0
	- `num_train_epochs`: 3
	- `max_steps`: -1
	- `lr_scheduler_type`: linear
	- `lr_scheduler_kwargs`: {}
	- `warmup_ratio`: 0.1
	- `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`: 12
	- `data_seed`: None
	- `jit_mode_eval`: False
	- `use_ipex`: False
	- `bf16`: True
	- `fp16`: False
	- `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`: 12
	- `dataloader_prefetch_factor`: None
	- `past_index`: -1
	- `disable_tqdm`: False
	- `remove_unused_columns`: True
	- `label_names`: None
	- `load_best_model_at_end`: True
	- `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}
	- `tp_size`: 0
	- `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
	- `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
	- `dispatch_batches`: None
	- `split_batches`: 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
	- `eval_use_gather_object`: False
	- `average_tokens_across_devices`: False
	- `prompts`: None
	- `batch_sampler`: batch_sampler
	- `multi_dataset_batch_sampler`: proportional

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| gooaq-dev_ndcg@10 \| NanoMSMARCO_R100_ndcg@10 \| NanoNFCorpus_R100_ndcg@10 \| NanoNQ_R100_ndcg@10 \| NanoBEIR_R100_mean_ndcg@10 \|
	\|:----------:\|:--------:\|:-------------:\|:--------------------:\|:------------------------:\|:-------------------------:\|:--------------------:\|:--------------------------:\|
	\| -1 \| -1 \| - \| 0.6371 (+0.1550) \| 0.6686 (+0.1282) \| 0.3930 (+0.0680) \| 0.7599 (+0.2592) \| 0.6072 (+0.1518) \|
	\| 0.0009 \| 1 \| 2.1175 \| - \| - \| - \| - \| - \|
	\| 0.1842 \| 200 \| 1.1892 \| - \| - \| - \| - \| - \|
	\| 0.3683 \| 400 \| 0.676 \| - \| - \| - \| - \| - \|
	\| 0.5525 \| 600 \| 0.6268 \| - \| - \| - \| - \| - \|
	\| 0.7366 \| 800 \| 0.606 \| - \| - \| - \| - \| - \|
	\| 0.9208 \| 1000 \| 0.5933 \| 0.6731 (+0.1910) \| 0.6038 (+0.0634) \| 0.4572 (+0.1321) \| 0.5220 (+0.0213) \| 0.5277 (+0.0723) \|
	\| 1.1050 \| 1200 \| 0.5756 \| - \| - \| - \| - \| - \|
	\| 1.2891 \| 1400 \| 0.5625 \| - \| - \| - \| - \| - \|
	\| 1.4733 \| 1600 \| 0.5575 \| - \| - \| - \| - \| - \|
	\| 1.6575 \| 1800 \| 0.549 \| - \| - \| - \| - \| - \|
	\| 1.8416 \| 2000 \| 0.5475 \| 0.6799 (+0.1977) \| 0.6072 (+0.0667) \| 0.4278 (+0.1028) \| 0.5031 (+0.0024) \| 0.5127 (+0.0573) \|
	\| 2.0258 \| 2200 \| 0.5391 \| - \| - \| - \| - \| - \|
	\| 2.2099 \| 2400 \| 0.5276 \| - \| - \| - \| - \| - \|
	\| 2.3941 \| 2600 \| 0.5271 \| - \| - \| - \| - \| - \|
	\| 2.5783 \| 2800 \| 0.5264 \| - \| - \| - \| - \| - \|
	\| 2.7624 \| 3000 \| 0.5244 \| 0.6822 (+0.2001) \| 0.6060 (+0.0655) \| 0.4077 (+0.0827) \| 0.5091 (+0.0084) \| 0.5076 (+0.0522) \|
	\| 2.9466 \| 3200 \| 0.5235 \| - \| - \| - \| - \| - \|
	\| -1 \| -1 \| - \| 0.6822 (+0.2001) \| 0.6060 (+0.0655) \| 0.4077 (+0.0827) \| 0.5091 (+0.0084) \| 0.5076 (+0.0522) \|

	* The bold row denotes the saved checkpoint.

	### Framework Versions
	- Python: 3.11.0
	- Sentence Transformers: 4.0.1
	- Transformers: 4.50.3
	- PyTorch: 2.6.0+cu124
	- Accelerate: 1.5.2
	- Datasets: 3.5.0
	- Tokenizers: 0.21.1

	## 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.
	-->