langcache-embed-v3 / README.md

Add new SentenceTransformer model

8cd0c70 verified 10 days ago

36.6 kB

	---
	language:
	- en
	license: apache-2.0
	tags:
	- biencoder
	- sentence-transformers
	- text-classification
	- sentence-pair-classification
	- semantic-similarity
	- semantic-search
	- retrieval
	- reranking
	- generated_from_trainer
	- dataset_size:483820
	- loss:MultipleNegativesSymmetricRankingLoss
	base_model: Alibaba-NLP/gte-modernbert-base
	widget:
	- source_sentence: 'See Precambrian time scale # Proposed Geologic timeline for another
	set of periods 4600 -- 541 MYA .'
	sentences:
	- In 2014 election , Biju Janata Dal candidate Tathagat Satapathy Bharatiya Janata
	party candidate Rudra Narayan Pany defeated with a margin of 1.37,340 votes .
	- In Scotland , the Strathclyde Partnership for Transport , formerly known as Strathclyde
	Passenger Transport Executive , comprises the former Strathclyde region , which
	includes the urban area around Glasgow .
	- 'See Precambrian Time Scale # Proposed Geological Timeline for another set of
	periods of 4600 -- 541 MYA .'
	- source_sentence: It is also 5 kilometers northeast of Tamaqua , 27 miles south of
	Allentown and 9 miles northwest of Hazleton .
	sentences:
	- In 1948 he moved to Massachusetts , and eventually settled in Vermont .
	- Suddenly I remembered that I was a New Zealander , I caught the first plane home
	and came back .
	- It is also 5 miles northeast of Tamaqua , 27 miles south of Allentown , and 9
	miles northwest of Hazleton .
	- source_sentence: The party has a Member of Parliament , a member of the House of
	Lords , three members of the London Assembly and two Members of the European Parliament
	.
	sentences:
	- The party has one Member of Parliament , one member of the House of Lords , three
	Members of the London Assembly and two Members of the European Parliament .
	- Grapsid crabs dominate in Australia , Malaysia and Panama , while gastropods Cerithidea
	scalariformis and Melampus coeffeus are important seed predators in Florida mangroves
	.
	- Music Story is a music service website and international music data provider that
	curates , aggregates and analyses metadata for digital music services .
	- source_sentence: 'The play received two 1969 Tony Award nominations : Best Actress
	in a Play ( Michael Annals ) and Best Costume Design ( Charlotte Rae ) .'
	sentences:
	- Ravishanker is a fellow of the International Statistical Institute and an elected
	member of the American Statistical Association .
	- 'In 1969 , the play received two Tony - Award nominations : Best Actress in a
	Theatre Play ( Michael Annals ) and Best Costume Design ( Charlotte Rae ) .'
	- AMD and Nvidia both have proprietary methods of scaling , CrossFireX for AMD ,
	and SLI for Nvidia .
	- source_sentence: He was a close friend of Ángel Cabrera and is a cousin of golfer
	Tony Croatto .
	sentences:
	- He was a close friend of Ángel Cabrera , and is a cousin of golfer Tony Croatto
	.
	- Eugenijus Bartulis ( born December 7 , 1949 in Kaunas ) is a Lithuanian Roman
	Catholic priest , and Bishop of Šiauliai .
	- UWIRE also distributes its members content to professional media outlets , including
	Yahoo , CNN and CBS News .
	datasets:
	- redis/langcache-sentencepairs-v1
	pipeline_tag: sentence-similarity
	library_name: sentence-transformers
	metrics:
	- cosine_accuracy@1
	- cosine_precision@1
	- cosine_recall@1
	- cosine_ndcg@10
	- cosine_mrr@1
	- cosine_map@100
	model-index:
	- name: Redis fine-tuned BiEncoder model for semantic caching on LangCache
	results:
	- task:
	type: information-retrieval
	name: Information Retrieval
	dataset:
	name: train
	type: train
	metrics:
	- type: cosine_accuracy@1
	value: 0.5978783286425633
	name: Cosine Accuracy@1
	- type: cosine_precision@1
	value: 0.5978783286425633
	name: Cosine Precision@1
	- type: cosine_recall@1
	value: 0.5765917883925028
	name: Cosine Recall@1
	- type: cosine_ndcg@10
	value: 0.7905393533594786
	name: Cosine Ndcg@10
	- type: cosine_mrr@1
	value: 0.5978783286425633
	name: Cosine Mrr@1
	- type: cosine_map@100
	value: 0.7375956597574003
	name: Cosine Map@100
	---

	# Redis fine-tuned BiEncoder model for semantic caching on LangCache

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) on the [LangCache Sentence Pairs (all)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v1) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for sentence pair similarity.

	## Model Details

	### Model Description
	- Model Type: Sentence Transformer
	- Base model: [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) <!-- at revision e7f32e3c00f91d699e8c43b53106206bcc72bb22 -->
	- Maximum Sequence Length: 100 tokens
	- Output Dimensionality: 768 dimensions
	- Similarity Function: Cosine Similarity
	- Training Dataset:
	- [LangCache Sentence Pairs (all)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v1)
	- Language: en
	- License: apache-2.0

	### Model Sources

	- Documentation: [Sentence Transformers Documentation](https://sbert.net)
	- Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
	- Hugging Face: [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)

	### Full Model Architecture

	```
	SentenceTransformer(
	(0): Transformer({'max_seq_length': 100, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
	(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})
	)
	```

	## 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 SentenceTransformer

	# Download from the 🤗 Hub
	model = SentenceTransformer("redis/langcache-embed-v3")
	# Run inference
	sentences = [
	'He was a close friend of Ángel Cabrera and is a cousin of golfer Tony Croatto .',
	'He was a close friend of Ángel Cabrera , and is a cousin of golfer Tony Croatto .',
	'UWIRE also distributes its members content to professional media outlets , including Yahoo , CNN and CBS News .',
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 768]

	# Get the similarity scores for the embeddings
	similarities = model.similarity(embeddings, embeddings)
	print(similarities)
	# tensor([[1.0000, 0.9922, 0.0547],
	# [0.9922, 1.0000, 0.0449],
	# [0.0547, 0.0449, 1.0000]], dtype=torch.bfloat16)
	```

	<!--
	### 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

	#### Information Retrieval

	* Dataset: `train`
	* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

	\| Metric \| Value \|
	\|:-------------------\|:-----------\|
	\| cosine_accuracy@1 \| 0.5979 \|
	\| cosine_precision@1 \| 0.5979 \|
	\| cosine_recall@1 \| 0.5766 \|
	\| cosine_ndcg@10 \| 0.7905 \|
	\| cosine_mrr@1 \| 0.5979 \|
	\| cosine_map@100 \| 0.7376 \|

	<!--
	## 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

	#### LangCache Sentence Pairs (all)

	* Dataset: [LangCache Sentence Pairs (all)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v1)
	* Size: 26,850 training samples
	* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \| label \|
	\|:--------\|:----------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|:-----------------------------\|
	\| type \| string \| string \| int \|
	\| details \| <ul><li>min: 8 tokens</li><li>mean: 27.35 tokens</li><li>max: 53 tokens</li></ul> \| <ul><li>min: 8 tokens</li><li>mean: 27.27 tokens</li><li>max: 52 tokens</li></ul> \| <ul><li>1: 100.00%</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| label \|
	\|:----------------------------------------------------------------------------------------------------------------------\|:-------------------------------------------------------------------------------------------------------------------------------\|:---------------\|
	\| <code>The newer Punts are still very much in existence today and race in the same fleets as the older boats .</code> \| <code>The newer punts are still very much in existence today and run in the same fleets as the older boats .</code> \| <code>1</code> \|
	\| <code>After losing his second election , he resigned as opposition leader and was replaced by Geoff Pearsall .</code> \| <code>Max Bingham resigned as opposition leader after losing his second election , and was replaced by Geoff Pearsall .</code> \| <code>1</code> \|
	\| <code>The 12F was officially homologated on August 21 , 1929 and exhibited at the Paris Salon in 1930 .</code> \| <code>The 12F was officially homologated on 21 August 1929 and displayed at the 1930 Paris Salon .</code> \| <code>1</code> \|
	* Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters:
	```json
	{
	"scale": 20.0,
	"similarity_fct": "cos_sim",
	"gather_across_devices": false
	}
	```

	### Evaluation Dataset

	#### LangCache Sentence Pairs (all)

	* Dataset: [LangCache Sentence Pairs (all)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v1)
	* Size: 26,850 evaluation samples
	* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \| label \|
	\|:--------\|:----------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|:-----------------------------\|
	\| type \| string \| string \| int \|
	\| details \| <ul><li>min: 8 tokens</li><li>mean: 27.35 tokens</li><li>max: 53 tokens</li></ul> \| <ul><li>min: 8 tokens</li><li>mean: 27.27 tokens</li><li>max: 52 tokens</li></ul> \| <ul><li>1: 100.00%</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| label \|
	\|:----------------------------------------------------------------------------------------------------------------------\|:-------------------------------------------------------------------------------------------------------------------------------\|:---------------\|
	\| <code>The newer Punts are still very much in existence today and race in the same fleets as the older boats .</code> \| <code>The newer punts are still very much in existence today and run in the same fleets as the older boats .</code> \| <code>1</code> \|
	\| <code>After losing his second election , he resigned as opposition leader and was replaced by Geoff Pearsall .</code> \| <code>Max Bingham resigned as opposition leader after losing his second election , and was replaced by Geoff Pearsall .</code> \| <code>1</code> \|
	\| <code>The 12F was officially homologated on August 21 , 1929 and exhibited at the Paris Salon in 1930 .</code> \| <code>The 12F was officially homologated on 21 August 1929 and displayed at the 1930 Paris Salon .</code> \| <code>1</code> \|
	* Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters:
	```json
	{
	"scale": 20.0,
	"similarity_fct": "cos_sim",
	"gather_across_devices": false
	}
	```

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

	- `eval_strategy`: steps
	- `per_device_train_batch_size`: 256
	- `per_device_eval_batch_size`: 256
	- `learning_rate`: 0.0003
	- `adam_beta2`: 0.98
	- `adam_epsilon`: 1e-06
	- `max_steps`: 200000
	- `warmup_steps`: 1000
	- `load_best_model_at_end`: True
	- `optim`: adamw_torch
	- `ddp_find_unused_parameters`: False
	- `push_to_hub`: True
	- `hub_model_id`: redis/langcache-embed-v3
	- `batch_sampler`: no_duplicates

	#### 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`: 256
	- `per_device_eval_batch_size`: 256
	- `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`: 0.0003
	- `weight_decay`: 0.0
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.98
	- `adam_epsilon`: 1e-06
	- `max_grad_norm`: 1.0
	- `num_train_epochs`: 3.0
	- `max_steps`: 200000
	- `lr_scheduler_type`: linear
	- `lr_scheduler_kwargs`: {}
	- `warmup_ratio`: 0.0
	- `warmup_steps`: 1000
	- `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`: 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`: 0
	- `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}
	- `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}
	- `parallelism_config`: 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`: False
	- `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`: True
	- `resume_from_checkpoint`: None
	- `hub_model_id`: redis/langcache-embed-v3
	- `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`: no_duplicates
	- `multi_dataset_batch_sampler`: proportional
	- `router_mapping`: {}
	- `learning_rate_mapping`: {}

	</details>

	### Training Logs
	<details><summary>Click to expand</summary>

	\| Epoch \| Step \| Training Loss \| Validation Loss \| train_cosine_ndcg@10 \|
	\|:-----------:\|:---------:\|:-------------:\|:---------------:\|:--------------------:\|
	\| -1 \| -1 \| - \| - \| 0.7522 \|
	\| 0.5291 \| 1000 \| 0.0231 \| 0.1710 \| 0.7518 \|
	\| 1.0582 \| 2000 \| 0.0147 \| 0.1552 \| 0.7593 \|
	\| 1.5873 \| 3000 \| 0.0126 \| 0.1616 \| 0.7603 \|
	\| 2.1164 \| 4000 \| 0.0113 \| 0.1301 \| 0.7644 \|
	\| 2.6455 \| 5000 \| 0.0119 \| 0.1276 \| 0.7659 \|
	\| 3.1746 \| 6000 \| 0.0099 \| 0.1270 \| 0.7648 \|
	\| 3.7037 \| 7000 \| 0.0101 \| 0.1239 \| 0.7676 \|
	\| 4.2328 \| 8000 \| 0.0093 \| 0.1267 \| 0.7709 \|
	\| 4.7619 \| 9000 \| 0.0092 \| 0.1190 \| 0.7711 \|
	\| 5.2910 \| 10000 \| 0.0088 \| 0.1145 \| 0.7735 \|
	\| 5.8201 \| 11000 \| 0.009 \| 0.1172 \| 0.7735 \|
	\| 6.3492 \| 12000 \| 0.0083 \| 0.1144 \| 0.7749 \|
	\| 6.8783 \| 13000 \| 0.0088 \| 0.1140 \| 0.7736 \|
	\| 7.4074 \| 14000 \| 0.0083 \| 0.1134 \| 0.7751 \|
	\| 7.9365 \| 15000 \| 0.0087 \| 0.1108 \| 0.7742 \|
	\| 8.4656 \| 16000 \| 0.0084 \| 0.1119 \| 0.7759 \|
	\| 8.9947 \| 17000 \| 0.0081 \| 0.1125 \| 0.7762 \|
	\| 9.5238 \| 18000 \| 0.0081 \| 0.1134 \| 0.7768 \|
	\| 10.0529 \| 19000 \| 0.008 \| 0.1126 \| 0.7766 \|
	\| 10.5820 \| 20000 \| 0.0079 \| 0.1119 \| 0.7755 \|
	\| 11.1111 \| 21000 \| 0.0078 \| 0.1112 \| 0.7781 \|
	\| 11.6402 \| 22000 \| 0.008 \| 0.1113 \| 0.7778 \|
	\| 12.1693 \| 23000 \| 0.0082 \| 0.1066 \| 0.7796 \|
	\| 12.6984 \| 24000 \| 0.0078 \| 0.1098 \| 0.7775 \|
	\| 13.2275 \| 25000 \| 0.0078 \| 0.1089 \| 0.7800 \|
	\| 13.7566 \| 26000 \| 0.0074 \| 0.1091 \| 0.7779 \|
	\| 14.2857 \| 27000 \| 0.0078 \| 0.1061 \| 0.7782 \|
	\| 14.8148 \| 28000 \| 0.0074 \| 0.1073 \| 0.7769 \|
	\| 15.3439 \| 29000 \| 0.0078 \| 0.1022 \| 0.7804 \|
	\| 15.8730 \| 30000 \| 0.0078 \| 0.1035 \| 0.7799 \|
	\| 16.4021 \| 31000 \| 0.0074 \| 0.1046 \| 0.7793 \|
	\| 16.9312 \| 32000 \| 0.0074 \| 0.1043 \| 0.7817 \|
	\| 17.4603 \| 33000 \| 0.0071 \| 0.1056 \| 0.7831 \|
	\| 17.9894 \| 34000 \| 0.0074 \| 0.1022 \| 0.7820 \|
	\| 18.5185 \| 35000 \| 0.0073 \| 0.1035 \| 0.7820 \|
	\| 19.0476 \| 36000 \| 0.0074 \| 0.1020 \| 0.7836 \|
	\| 19.5767 \| 37000 \| 0.0071 \| 0.1036 \| 0.7828 \|
	\| 20.1058 \| 38000 \| 0.007 \| 0.1029 \| 0.7845 \|
	\| 20.6349 \| 39000 \| 0.0071 \| 0.1019 \| 0.7835 \|
	\| 21.1640 \| 40000 \| 0.007 \| 0.0991 \| 0.7849 \|
	\| 21.6931 \| 41000 \| 0.0071 \| 0.1013 \| 0.7828 \|
	\| 22.2222 \| 42000 \| 0.0073 \| 0.1033 \| 0.7833 \|
	\| 22.7513 \| 43000 \| 0.0068 \| 0.0996 \| 0.7835 \|
	\| 23.2804 \| 44000 \| 0.007 \| 0.0976 \| 0.7850 \|
	\| 23.8095 \| 45000 \| 0.0069 \| 0.0986 \| 0.7840 \|
	\| 24.3386 \| 46000 \| 0.0068 \| 0.0992 \| 0.7856 \|
	\| 24.8677 \| 47000 \| 0.0068 \| 0.0988 \| 0.7838 \|
	\| 25.3968 \| 48000 \| 0.0068 \| 0.0980 \| 0.7857 \|
	\| 25.9259 \| 49000 \| 0.007 \| 0.0976 \| 0.7860 \|
	\| 26.4550 \| 50000 \| 0.0071 \| 0.0994 \| 0.7850 \|
	\| 26.9841 \| 51000 \| 0.0067 \| 0.0984 \| 0.7862 \|
	\| 27.5132 \| 52000 \| 0.0064 \| 0.0992 \| 0.7845 \|
	\| 28.0423 \| 53000 \| 0.0068 \| 0.1021 \| 0.7840 \|
	\| 28.5714 \| 54000 \| 0.0066 \| 0.0974 \| 0.7863 \|
	\| 29.1005 \| 55000 \| 0.0066 \| 0.1001 \| 0.7848 \|
	\| 29.6296 \| 56000 \| 0.0067 \| 0.0997 \| 0.7848 \|
	\| 30.1587 \| 57000 \| 0.0067 \| 0.0965 \| 0.7868 \|
	\| 30.6878 \| 58000 \| 0.0067 \| 0.0968 \| 0.7858 \|
	\| 31.2169 \| 59000 \| 0.0066 \| 0.0973 \| 0.7861 \|
	\| 31.7460 \| 60000 \| 0.0067 \| 0.0972 \| 0.7865 \|
	\| 32.2751 \| 61000 \| 0.0065 \| 0.0991 \| 0.7855 \|
	\| 32.8042 \| 62000 \| 0.0062 \| 0.0960 \| 0.7871 \|
	\| 33.3333 \| 63000 \| 0.0068 \| 0.1006 \| 0.7863 \|
	\| 33.8624 \| 64000 \| 0.0063 \| 0.0980 \| 0.7872 \|
	\| 34.3915 \| 65000 \| 0.0066 \| 0.0957 \| 0.7871 \|
	\| 34.9206 \| 66000 \| 0.0066 \| 0.0971 \| 0.7870 \|
	\| 35.4497 \| 67000 \| 0.0063 \| 0.0982 \| 0.7857 \|
	\| 35.9788 \| 68000 \| 0.0067 \| 0.0944 \| 0.7871 \|
	\| 36.5079 \| 69000 \| 0.0062 \| 0.0961 \| 0.7870 \|
	\| 37.0370 \| 70000 \| 0.0061 \| 0.0924 \| 0.7880 \|
	\| 37.5661 \| 71000 \| 0.0064 \| 0.0928 \| 0.7878 \|
	\| 38.0952 \| 72000 \| 0.0065 \| 0.0934 \| 0.7888 \|
	\| 38.6243 \| 73000 \| 0.0069 \| 0.0948 \| 0.7873 \|
	\| 39.1534 \| 74000 \| 0.0064 \| 0.0922 \| 0.7885 \|
	\| 39.6825 \| 75000 \| 0.0064 \| 0.0937 \| 0.7888 \|
	\| 40.2116 \| 76000 \| 0.0059 \| 0.0941 \| 0.7882 \|
	\| 40.7407 \| 77000 \| 0.0067 \| 0.0934 \| 0.7900 \|
	\| 41.2698 \| 78000 \| 0.0064 \| 0.0926 \| 0.7888 \|
	\| 41.7989 \| 79000 \| 0.006 \| 0.0948 \| 0.7880 \|
	\| 42.3280 \| 80000 \| 0.006 \| 0.0953 \| 0.7876 \|
	\| 42.8571 \| 81000 \| 0.0058 \| 0.0955 \| 0.7887 \|
	\| 43.3862 \| 82000 \| 0.0065 \| 0.0945 \| 0.7875 \|
	\| 43.9153 \| 83000 \| 0.0063 \| 0.0928 \| 0.7888 \|
	\| 44.4444 \| 84000 \| 0.0065 \| 0.0959 \| 0.7883 \|
	\| 44.9735 \| 85000 \| 0.0063 \| 0.0956 \| 0.7876 \|
	\| 45.5026 \| 86000 \| 0.006 \| 0.0946 \| 0.7893 \|
	\| 46.0317 \| 87000 \| 0.0062 \| 0.0954 \| 0.7908 \|
	\| 46.5608 \| 88000 \| 0.0061 \| 0.0960 \| 0.7896 \|
	\| 47.0899 \| 89000 \| 0.006 \| 0.0953 \| 0.7893 \|
	\| 47.6190 \| 90000 \| 0.0058 \| 0.0941 \| 0.7899 \|
	\| 48.1481 \| 91000 \| 0.0059 \| 0.0950 \| 0.7892 \|
	\| 48.6772 \| 92000 \| 0.0066 \| 0.0948 \| 0.7890 \|
	\| 49.2063 \| 93000 \| 0.0058 \| 0.0947 \| 0.7886 \|
	\| 49.7354 \| 94000 \| 0.006 \| 0.0952 \| 0.7891 \|
	\| 50.2646 \| 95000 \| 0.0058 \| 0.0948 \| 0.7885 \|
	\| 50.7937 \| 96000 \| 0.0058 \| 0.0945 \| 0.7894 \|
	\| 51.3228 \| 97000 \| 0.0059 \| 0.0936 \| 0.7901 \|
	\| 51.8519 \| 98000 \| 0.0059 \| 0.0950 \| 0.7900 \|
	\| 52.3810 \| 99000 \| 0.0058 \| 0.0954 \| 0.7893 \|
	\| 52.9101 \| 100000 \| 0.0058 \| 0.0946 \| 0.7900 \|
	\| 53.4392 \| 101000 \| 0.0056 \| 0.0943 \| 0.7900 \|
	\| 53.9683 \| 102000 \| 0.006 \| 0.0950 \| 0.7895 \|
	\| 54.4974 \| 103000 \| 0.0059 \| 0.0937 \| 0.7899 \|
	\| 55.0265 \| 104000 \| 0.0061 \| 0.0941 \| 0.7897 \|
	\| 55.5556 \| 105000 \| 0.0059 \| 0.0941 \| 0.7903 \|
	\| 56.0847 \| 106000 \| 0.0057 \| 0.0924 \| 0.7904 \|
	\| 56.6138 \| 107000 \| 0.006 \| 0.0933 \| 0.7901 \|
	\| 57.1429 \| 108000 \| 0.0059 \| 0.0948 \| 0.7888 \|
	\| 57.6720 \| 109000 \| 0.0061 \| 0.0938 \| 0.7899 \|
	\| 58.2011 \| 110000 \| 0.0058 \| 0.0942 \| 0.7904 \|
	\| 58.7302 \| 111000 \| 0.0056 \| 0.0943 \| 0.7913 \|
	\| 59.2593 \| 112000 \| 0.0056 \| 0.0949 \| 0.7915 \|
	\| 59.7884 \| 113000 \| 0.0058 \| 0.0947 \| 0.7907 \|
	\| 60.3175 \| 114000 \| 0.0058 \| 0.0939 \| 0.7910 \|
	\| 60.8466 \| 115000 \| 0.0058 \| 0.0942 \| 0.7906 \|
	\| 61.3757 \| 116000 \| 0.0055 \| 0.0933 \| 0.7910 \|
	\| 61.9048 \| 117000 \| 0.0055 \| 0.0936 \| 0.7913 \|
	\| 62.4339 \| 118000 \| 0.0059 \| 0.0937 \| 0.7904 \|
	\| 62.9630 \| 119000 \| 0.0057 \| 0.0943 \| 0.7908 \|
	\| 63.4921 \| 120000 \| 0.0056 \| 0.0934 \| 0.7912 \|
	\| 64.0212 \| 121000 \| 0.0058 \| 0.0936 \| 0.7909 \|
	\| 64.5503 \| 122000 \| 0.0055 \| 0.0942 \| 0.7896 \|
	\| 65.0794 \| 123000 \| 0.0058 \| 0.0939 \| 0.7901 \|
	\| 65.6085 \| 124000 \| 0.0057 \| 0.0936 \| 0.7907 \|
	\| 66.1376 \| 125000 \| 0.0054 \| 0.0951 \| 0.7901 \|
	\| 66.6667 \| 126000 \| 0.0055 \| 0.0942 \| 0.7912 \|
	\| 67.1958 \| 127000 \| 0.0057 \| 0.0943 \| 0.7914 \|
	\| 67.7249 \| 128000 \| 0.0057 \| 0.0937 \| 0.7910 \|
	\| 68.2540 \| 129000 \| 0.0057 \| 0.0933 \| 0.7918 \|
	\| 68.7831 \| 130000 \| 0.0055 \| 0.0935 \| 0.7913 \|
	\| 69.3122 \| 131000 \| 0.0053 \| 0.0935 \| 0.7908 \|
	\| 69.8413 \| 132000 \| 0.0057 \| 0.0937 \| 0.7905 \|
	\| 70.3704 \| 133000 \| 0.0055 \| 0.0940 \| 0.7912 \|
	\| 70.8995 \| 134000 \| 0.0052 \| 0.0937 \| 0.7913 \|
	\| 71.4286 \| 135000 \| 0.005 \| 0.0940 \| 0.7917 \|
	\| 71.9577 \| 136000 \| 0.0053 \| 0.0933 \| 0.7914 \|
	\| 72.4868 \| 137000 \| 0.0056 \| 0.0940 \| 0.7915 \|
	\| 73.0159 \| 138000 \| 0.0054 \| 0.0937 \| 0.7909 \|
	\| 73.5450 \| 139000 \| 0.0051 \| 0.0940 \| 0.7909 \|
	\| 74.0741 \| 140000 \| 0.0058 \| 0.0938 \| 0.7911 \|
	\| 74.6032 \| 141000 \| 0.0056 \| 0.0938 \| 0.7912 \|
	\| 75.1323 \| 142000 \| 0.0052 \| 0.0931 \| 0.7908 \|
	\| 75.6614 \| 143000 \| 0.0052 \| 0.0937 \| 0.7905 \|
	\| 76.1905 \| 144000 \| 0.0054 \| 0.0940 \| 0.7905 \|
	\| 76.7196 \| 145000 \| 0.0055 \| 0.0940 \| 0.7907 \|
	\| 77.2487 \| 146000 \| 0.0053 \| 0.0941 \| 0.7909 \|
	\| 77.7778 \| 147000 \| 0.0057 \| 0.0944 \| 0.7907 \|
	\| 78.3069 \| 148000 \| 0.0054 \| 0.0947 \| 0.7909 \|
	\| 78.8360 \| 149000 \| 0.0054 \| 0.0949 \| 0.7907 \|
	\| 79.3651 \| 150000 \| 0.0055 \| 0.0948 \| 0.7907 \|
	\| 79.8942 \| 151000 \| 0.0058 \| 0.0950 \| 0.7907 \|
	\| 80.4233 \| 152000 \| 0.0054 \| 0.0946 \| 0.7907 \|
	\| 80.9524 \| 153000 \| 0.0053 \| 0.0949 \| 0.7909 \|
	\| 81.4815 \| 154000 \| 0.0055 \| 0.0947 \| 0.7908 \|
	\| 82.0106 \| 155000 \| 0.0053 \| 0.0946 \| 0.7906 \|
	\| 82.5397 \| 156000 \| 0.0053 \| 0.0949 \| 0.7906 \|
	\| 83.0688 \| 157000 \| 0.0051 \| 0.0948 \| 0.7912 \|
	\| 83.5979 \| 158000 \| 0.0052 \| 0.0954 \| 0.7906 \|
	\| 84.1270 \| 159000 \| 0.0054 \| 0.0953 \| 0.7908 \|
	\| 84.6561 \| 160000 \| 0.005 \| 0.0951 \| 0.7911 \|
	\| 85.1852 \| 161000 \| 0.0054 \| 0.0953 \| 0.7910 \|
	\| 85.7143 \| 162000 \| 0.0056 \| 0.0957 \| 0.7907 \|
	\| 86.2434 \| 163000 \| 0.0054 \| 0.0953 \| 0.7909 \|
	\| 86.7725 \| 164000 \| 0.0051 \| 0.0955 \| 0.7912 \|
	\| 87.3016 \| 165000 \| 0.0055 \| 0.0956 \| 0.7911 \|
	\| 87.8307 \| 166000 \| 0.0056 \| 0.0954 \| 0.7909 \|
	\| 88.3598 \| 167000 \| 0.0052 \| 0.0955 \| 0.7911 \|
	\| 88.8889 \| 168000 \| 0.0052 \| 0.0953 \| 0.7910 \|
	\| 89.4180 \| 169000 \| 0.0052 \| 0.0952 \| 0.7906 \|
	\| 89.9471 \| 170000 \| 0.0053 \| 0.0952 \| 0.7908 \|
	\| 90.4762 \| 171000 \| 0.0052 \| 0.0954 \| 0.7908 \|
	\| 91.0053 \| 172000 \| 0.0054 \| 0.0954 \| 0.7907 \|
	\| 91.5344 \| 173000 \| 0.0052 \| 0.0951 \| 0.7909 \|
	\| 92.0635 \| 174000 \| 0.0053 \| 0.0951 \| 0.7907 \|
	\| 92.5926 \| 175000 \| 0.0051 \| 0.0950 \| 0.7906 \|
	\| 93.1217 \| 176000 \| 0.0054 \| 0.0953 \| 0.7907 \|
	\| 93.6508 \| 177000 \| 0.0052 \| 0.0953 \| 0.7907 \|
	\| 94.1799 \| 178000 \| 0.0051 \| 0.0951 \| 0.7908 \|
	\| 94.7090 \| 179000 \| 0.0052 \| 0.0952 \| 0.7906 \|
	\| 95.2381 \| 180000 \| 0.0053 \| 0.0953 \| 0.7909 \|
	\| 95.7672 \| 181000 \| 0.0052 \| 0.0953 \| 0.7908 \|
	\| 96.2963 \| 182000 \| 0.0051 \| 0.0952 \| 0.7906 \|
	\| 96.8254 \| 183000 \| 0.0053 \| 0.0953 \| 0.7907 \|
	\| 97.3545 \| 184000 \| 0.0051 \| 0.0953 \| 0.7907 \|
	\| 97.8836 \| 185000 \| 0.0049 \| 0.0953 \| 0.7906 \|
	\| 98.4127 \| 186000 \| 0.0051 \| 0.0953 \| 0.7907 \|
	\| 98.9418 \| 187000 \| 0.0051 \| 0.0954 \| 0.7906 \|
	\| 99.4709 \| 188000 \| 0.0053 \| 0.0954 \| 0.7906 \|
	\| 100.0 \| 189000 \| 0.0051 \| 0.0954 \| 0.7904 \|
	\| 100.5291 \| 190000 \| 0.0054 \| 0.0953 \| 0.7907 \|
	\| 101.0582 \| 191000 \| 0.0052 \| 0.0954 \| 0.7905 \|
	\| 101.5873 \| 192000 \| 0.0051 \| 0.0954 \| 0.7907 \|
	\| 102.1164 \| 193000 \| 0.0052 \| 0.0953 \| 0.7907 \|
	\| 102.6455 \| 194000 \| 0.0051 \| 0.0955 \| 0.7908 \|
	\| 103.1746 \| 195000 \| 0.0054 \| 0.0954 \| 0.7906 \|
	\| 103.7037 \| 196000 \| 0.0052 \| 0.0954 \| 0.7905 \|
	\| 104.2328 \| 197000 \| 0.0053 \| 0.0954 \| 0.7906 \|
	\| 104.7619 \| 198000 \| 0.0052 \| 0.0954 \| 0.7907 \|
	\| 105.2910 \| 199000 \| 0.0055 \| 0.0954 \| 0.7904 \|
	\| 105.8201 \| 200000 \| 0.0054 \| 0.0955 \| 0.7905 \|

	* The bold row denotes the saved checkpoint.
	</details>

	### Framework Versions
	- Python: 3.12.3
	- Sentence Transformers: 5.1.0
	- Transformers: 4.56.0
	- PyTorch: 2.8.0+cu128
	- Accelerate: 1.10.1
	- Datasets: 4.0.0
	- Tokenizers: 0.22.0

	## 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.
	-->