Training in progress, step 76, checkpoint

710fc84 verified 11 months ago

35.6 kB

	---
	base_model: bobox/DeBERTa-small-ST-v1-test-step3
	datasets: []
	language: []
	library_name: sentence-transformers
	metrics:
	- pearson_cosine
	- spearman_cosine
	- pearson_manhattan
	- spearman_manhattan
	- pearson_euclidean
	- spearman_euclidean
	- pearson_dot
	- spearman_dot
	- pearson_max
	- spearman_max
	pipeline_tag: sentence-similarity
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- generated_from_trainer
	- dataset_size:120849
	- loss:CachedGISTEmbedLoss
	widget:
	- source_sentence: 'Brian Cummins, who was in his early 60s, was refereeing an Under-16s
	final in Elburton, Devon, on Sunday when he fell to the ground.

	He was taken to Derriford Hospital in Plymouth but died shortly after, the Devon
	Junior Minor League said.

	A spokesman said: "Our thoughts and condolences at this time are with his family.
	The league has lost a very loyal referee."

	The game between Woolwell Juniors and Tavistock was abandoned after Mr Cummins
	collapsed.

	His daughter Sarah said: "He was a loving father, father in law, granddad, husband
	and friend to all who knew him. He loved his football and refereeing.

	"He will be greatly missed by all and will forever be in our hearts."

	Brian Rimes, general secretary of the league, said former Devonport dockyard worker
	Mr Cummins had been a referee for the league for about 20 years.

	"He was a very good referee, a man well respected by youngsters and the referee
	fraternity," he said.

	Mark Davies wrote on the league''s Facebook page: "Very sad news indeed and our
	thoughts go out to Brian''s family and friends. It''s a shame that it takes such
	awful circumstances to unite the local footballing community but in Brian we know
	we have lost a true gent. RIP Brian."

	Mark Evans wrote: "RIP Brian. Grassroots football has lost an amazing guy and
	great referee. Deepest sympathies from all Devon FA referees."

	Michael Davies tweeted: "#RIP Brian Cummins, such sad news! Top Ref, top neighbour
	but most of all a top bloke! Will be sadly missed."'
	sentences:
	- 'Ptosis (Sagging Eyelids): Check Your Symptoms and Signs Watery Eye A drooping
	or sagging of the eyelid is medically known as ptosis or blepharoptosis . Drooping
	eyelids may occur on both sides (bilateral) or on one side only (unilateral),
	in which case it is more easily noticed. Congenital ptosis is eyelid drooping
	that is present at birth; when it develops later, it is referred to as acquired
	ptosis. Depending upon the severity of the condition, drooping eyelids may be
	barely noticeable or quite prominent. Some sagging of the skin and connective
	tissues occurs during the normal aging process, potentially leading to drooping
	of the eyelids. Other causes include conditions that affect the muscles and nerves
	of the eyelid as well as conditions that affect the skin and connective tissues
	of the eyelid. Rarely, tumors of the brain or eye area are the cause of drooping
	eyelids. Medically Reviewed by a Doctor on 3/6/2012 Health concern on your mind?
	Visit the Symptom Checker. REFERENCE: Fauci, Anthony S., et al. Harrison''s Principles
	of Internal Medicine. 17th ed. United States: McGraw-Hill Professional, 2008.
	Causes of Ptosis Allergy (Allergies) An allergy refers to a misguided reaction
	by our immune system in response to bodily contact with certain foreign substances.
	... learn more » Botulism Botulism is an illness caused by a neurotoxin produced
	by the bacterium Clostridium botulinum. There are three types of botulism:...
	learn more » In This Article'
	- A football referee has died after collapsing during a boys' cup final.
	- The car is at the intersection while the sun is setting.
	- source_sentence: sparge water temperature
	sentences:
	- This is easy to translate to gallons and degrees F. (for example, suggested sparge
	water temperature is 167Â° F., which is 75Â° C.). It also features a stay warm
	feature - after the target water temperature is hit, it will keep it at the desired
	temperature as long as it is on.
	- Arsenal playmaker Mesut Ozil says he will put talks over his future at the club
	on hold until the summer.
	- a greenhouse is used to protect plants by keeping them warm
	- source_sentence: What does sunlight create for plants?
	sentences:
	- "a plant requires sunlight for photosynthesis. Photosynthesis occurs using the\
	\ suns energy to create the plants own energy. \n sunlight creates energy for\
	\ plants"
	- His references in electronic music are Todd Terry , Armand Van Helden , Roger
	Sanchez , Tiesto and the Epic Sax Guy.
	- "if a neutral atom loses an electron then an atom with a negative charge will\
	\ be formed. Ions are neutral atoms. \n ions can have a negative charge if they\
	\ lose an electron"
	- source_sentence: Metals, metalloids, and nonmetals are the different classes of
	what?
	sentences:
	- when an animal sheds its fur , its fur becomes less dense
	- Though there's no limit to how much you can keep in a savings account, you should
	know the rules surrounding large deposits to savings accounts. When it comes to
	making deposits to a bank account, $10,000 is the magic number.
	- The classes of elements are metals, metalloids, and nonmetals. They are color-coded
	in the table. Blue stands for metals, orange for metalloids, and green for nonmetals.
	You can read about each of these three classes of elements later in the chapter,
	in the lesson "Classes of Elements. ".
	- source_sentence: More than 336,000 COVID-19 cases have been reported in over 190
	countries .
	sentences:
	- Birds are four-limbed, endothermic vertebrates with wings and feathers. They produce
	amniotic eggs and are the most numerous class of vertebrates.
	- As of 23 March , more than 337,000 cases of COVID-19 have been reported in over
	190 countries and territories , resulting in more than 14,600 deaths and 97,000
	recoveries .
	- Apocalypticism Apocalypticism is the religious belief that there will be an apocalypse,
	a term which originally referred to a revelation of God's will, but now usually
	refers to the belief that the end of the world is imminent, even within one's
	own lifetime. This belief is usually accompanied by the idea that civilization
	will soon come to a tumultuous end due to some sort of catastrophic global event.
	model-index:
	- name: SentenceTransformer based on bobox/DeBERTa-small-ST-v1-test-step3
	results:
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test
	type: sts-test
	metrics:
	- type: pearson_cosine
	value: 0.879906095889138
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.9066359425959888
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.9102620649137054
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.9072107277972998
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.9088378228597751
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.9061907122964057
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.8607649105164801
	name: Pearson Dot
	- type: spearman_dot
	value: 0.8668292928269864
	name: Spearman Dot
	- type: pearson_max
	value: 0.9102620649137054
	name: Pearson Max
	- type: spearman_max
	value: 0.9072107277972998
	name: Spearman Max
	---

	# SentenceTransformer based on bobox/DeBERTa-small-ST-v1-test-step3

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [bobox/DeBERTa-small-ST-v1-test-step3](https://huggingface.co/bobox/DeBERTa-small-ST-v1-test-step3) on the bobox/enhanced_nli-50_k dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

	## Model Details

	### Model Description
	- Model Type: Sentence Transformer
	- Base model: [bobox/DeBERTa-small-ST-v1-test-step3](https://huggingface.co/bobox/DeBERTa-small-ST-v1-test-step3) <!-- at revision df9aaa75fe0c2791e5ed35ff33de1689d9a5f5ff -->
	- Maximum Sequence Length: 512 tokens
	- Output Dimensionality: 768 tokens
	- Similarity Function: Cosine Similarity
	- Training Dataset:
	- bobox/enhanced_nli-50_k
	<!-- - Language: Unknown -->
	<!-- - License: Unknown -->

	### 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': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model
	(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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("bobox/DeBERTa-small-ST-v1-test-UnifiedDatasets-bis-checkpoints-tmp")
	# Run inference
	sentences = [
	'More than 336,000 COVID-19 cases have been reported in over 190 countries .',
	'As of 23 March , more than 337,000 cases of COVID-19 have been reported in over 190 countries and territories , resulting in more than 14,600 deaths and 97,000 recoveries .',
	"Apocalypticism Apocalypticism is the religious belief that there will be an apocalypse, a term which originally referred to a revelation of God's will, but now usually refers to the belief that the end of the world is imminent, even within one's own lifetime. This belief is usually accompanied by the idea that civilization will soon come to a tumultuous end due to some sort of catastrophic global event.",
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 768]

	# Get the similarity scores for the embeddings
	similarities = model.similarity(embeddings, embeddings)
	print(similarities.shape)
	# [3, 3]
	```

	<!--
	### 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

	#### Semantic Similarity
	* Dataset: `sts-test`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8799 \|
	\| spearman_cosine \| 0.9066 \|
	\| pearson_manhattan \| 0.9103 \|
	\| spearman_manhattan \| 0.9072 \|
	\| pearson_euclidean \| 0.9088 \|
	\| spearman_euclidean \| 0.9062 \|
	\| pearson_dot \| 0.8608 \|
	\| spearman_dot \| 0.8668 \|
	\| pearson_max \| 0.9103 \|
	\| spearman_max \| 0.9072 \|

	<!--
	## 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

	#### bobox/enhanced_nli-50_k

	* Dataset: bobox/enhanced_nli-50_k
	* Size: 120,849 training samples
	* Columns: <code>sentence1</code> and <code>sentence2</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \|
	\|:--------\|:-----------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------\|
	\| type \| string \| string \|
	\| details \| <ul><li>min: 4 tokens</li><li>mean: 33.98 tokens</li><li>max: 358 tokens</li></ul> \| <ul><li>min: 2 tokens</li><li>mean: 63.13 tokens</li><li>max: 414 tokens</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \|
	\|:---------------------------------------------------------------------------------\|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|
	\| <code>A lady working in a kitchen with several different types of dishes.</code> \| <code>A woman is cooking and cleaning in her kitchen.</code> \|
	\| <code>is it possible to get pregnant after delivery?</code> \| <code>How soon can you get pregnant after giving birth? It's possible to get pregnant before you even have your first postpartum period, which can occur as early as four weeks after giving birth or as late as 24 weeks after baby arrives (or later), depending on whether you're breastfeeding exclusively or not.</code> \|
	\| <code>how long does corn take to grill in foil</code> \| <code>Place each corn on top of one piece the heavy-duty foil. Brush each ear generously with soft butter. Season lightly with seasoned salt or white salt and black pepper. Wrap the corn then seal the foil loosely but leave room for expansion, then cut a very small hole in the foil to allow steam to escape. Grill over medium coals for about 15-20 minutes (the larger ears may take a little longer).</code> \|
	* Loss: [<code>CachedGISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedgistembedloss) with these parameters:
	```json
	{'guide': SentenceTransformer(
	(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) 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()
	), 'temperature': 0.025}
	```

	### Evaluation Dataset

	#### bobox/enhanced_nli-50_k

	* Dataset: bobox/enhanced_nli-50_k
	* Size: 3,052 evaluation samples
	* Columns: <code>sentence1</code> and <code>sentence2</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \|
	\|:--------\|:-----------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------\|
	\| type \| string \| string \|
	\| details \| <ul><li>min: 4 tokens</li><li>mean: 33.63 tokens</li><li>max: 328 tokens</li></ul> \| <ul><li>min: 2 tokens</li><li>mean: 60.36 tokens</li><li>max: 501 tokens</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \|
	\|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|
	\| <code>The 17-year-old asked not to be named but said he lost control of his silver hatchback when he swerved to avoid a cat in Parkway, Chellaston, Derbyshire.<br>He estimated he was travelling at about 30mph when he smashed into the garage of a residential home on Friday night.<br>The owners were away at the time and the crash was reported to police.<br>The driver told BBC News: "I swerved to the right and the back of the car went out.<br>"I then swerved to the left and lost control - I couldn't bring it back.<br>"I just missed two parked cars and a tree and ended up in the wall - it was a big impact.<br>"I smelt burning, I thought it was the car, so I got out and laid down - I was in shock."<br>Neighbours reported hearing a "loud screeching" followed by a "massive bang".<br>The driver said: "It was a natural reaction to swerve to miss the cat, but I went into a state of shock and panic."<br>Derbyshire Police said the driver was due to appear before magistrates at a later date charged with driving without due care or attention.</code> \| <code>A new driver who ploughed into a house, having swerved around two parked cars and a tree to avoid hitting a cat in the road, faces court.</code> \|
	\| <code>what requirements are needed to be a psychologist?</code> \| <code>To become a clinician, you must apply for registration with the College of Psychologists of Ontario, a process which requires 4 years of work experience and one year of supervised practice. In some provinces, you can be registered to practice as a psychologist with either a masters or doctoral degree.</code> \|
	\| <code>What does sunlight create for plants?</code> \| <code>a plant requires sunlight for photosynthesis. Photosynthesis occurs using the suns energy to create the plants own energy. <br> sunlight creates energy for plants</code> \|
	* Loss: [<code>CachedGISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedgistembedloss) with these parameters:
	```json
	{'guide': SentenceTransformer(
	(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) 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()
	), 'temperature': 0.025}
	```

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

	- `eval_strategy`: steps
	- `per_device_train_batch_size`: 640
	- `per_device_eval_batch_size`: 128
	- `learning_rate`: 3.5e-05
	- `weight_decay`: 0.0001
	- `num_train_epochs`: 2
	- `lr_scheduler_type`: cosine_with_min_lr
	- `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 5.833333333333333e-06}
	- `warmup_ratio`: 0.25
	- `save_safetensors`: False
	- `fp16`: True
	- `push_to_hub`: True
	- `hub_model_id`: bobox/DeBERTa-small-ST-v1-test-UnifiedDatasets-bis-checkpoints-tmp
	- `hub_strategy`: all_checkpoints
	- `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`: 640
	- `per_device_eval_batch_size`: 128
	- `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`: 3.5e-05
	- `weight_decay`: 0.0001
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.999
	- `adam_epsilon`: 1e-08
	- `max_grad_norm`: 1.0
	- `num_train_epochs`: 2
	- `max_steps`: -1
	- `lr_scheduler_type`: cosine_with_min_lr
	- `lr_scheduler_kwargs`: {'num_cycles': 0.5, 'min_lr': 5.833333333333333e-06}
	- `warmup_ratio`: 0.25
	- `warmup_steps`: 0
	- `log_level`: passive
	- `log_level_replica`: warning
	- `log_on_each_node`: True
	- `logging_nan_inf_filter`: True
	- `save_safetensors`: False
	- `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`: True
	- `resume_from_checkpoint`: None
	- `hub_model_id`: bobox/DeBERTa-small-ST-v1-test-UnifiedDatasets-bis-checkpoints-tmp
	- `hub_strategy`: all_checkpoints
	- `hub_private_repo`: False
	- `hub_always_push`: False
	- `gradient_checkpointing`: False
	- `gradient_checkpointing_kwargs`: None
	- `include_inputs_for_metrics`: False
	- `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
	- `eval_use_gather_object`: False
	- `batch_sampler`: no_duplicates
	- `multi_dataset_batch_sampler`: proportional

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| loss \| sts-test_spearman_cosine \|
	\|:------:\|:----:\|:-------------:\|:------:\|:------------------------:\|
	\| 0.0053 \| 1 \| 0.3768 \| - \| - \|
	\| 0.0106 \| 2 \| 0.3162 \| - \| - \|
	\| 0.0159 \| 3 \| 0.275 \| - \| - \|
	\| 0.0212 \| 4 \| 0.293 \| - \| - \|
	\| 0.0265 \| 5 \| 0.2437 \| 0.2190 \| 0.9079 \|
	\| 0.0317 \| 6 \| 0.3681 \| - \| - \|
	\| 0.0370 \| 7 \| 0.2314 \| - \| - \|
	\| 0.0423 \| 8 \| 0.2481 \| - \| - \|
	\| 0.0476 \| 9 \| 0.2403 \| - \| - \|
	\| 0.0529 \| 10 \| 0.2966 \| 0.2125 \| 0.9079 \|
	\| 0.0582 \| 11 \| 0.2867 \| - \| - \|
	\| 0.0635 \| 12 \| 0.3413 \| - \| - \|
	\| 0.0688 \| 13 \| 0.4119 \| - \| - \|
	\| 0.0741 \| 14 \| 0.3118 \| - \| - \|
	\| 0.0794 \| 15 \| 0.327 \| 0.2031 \| 0.9082 \|
	\| 0.0847 \| 16 \| 0.3389 \| - \| - \|
	\| 0.0899 \| 17 \| 0.2018 \| - \| - \|
	\| 0.0952 \| 18 \| 0.2861 \| - \| - \|
	\| 0.1005 \| 19 \| 0.2848 \| - \| - \|
	\| 0.1058 \| 20 \| 0.2563 \| 0.1943 \| 0.9082 \|
	\| 0.1111 \| 21 \| 0.3058 \| - \| - \|
	\| 0.1164 \| 22 \| 0.285 \| - \| - \|
	\| 0.1217 \| 23 \| 0.3151 \| - \| - \|
	\| 0.1270 \| 24 \| 0.2716 \| - \| - \|
	\| 0.1323 \| 25 \| 0.2422 \| 0.1794 \| 0.9082 \|
	\| 0.1376 \| 26 \| 0.2858 \| - \| - \|
	\| 0.1429 \| 27 \| 0.3211 \| - \| - \|
	\| 0.1481 \| 28 \| 0.2158 \| - \| - \|
	\| 0.1534 \| 29 \| 0.2811 \| - \| - \|
	\| 0.1587 \| 30 \| 0.2063 \| 0.1636 \| 0.9077 \|
	\| 0.1640 \| 31 \| 0.2492 \| - \| - \|
	\| 0.1693 \| 32 \| 0.3096 \| - \| - \|
	\| 0.1746 \| 33 \| 0.2914 \| - \| - \|
	\| 0.1799 \| 34 \| 0.2888 \| - \| - \|
	\| 0.1852 \| 35 \| 0.223 \| 0.1532 \| 0.9072 \|
	\| 0.1905 \| 36 \| 0.2595 \| - \| - \|
	\| 0.1958 \| 37 \| 0.3122 \| - \| - \|
	\| 0.2011 \| 38 \| 0.2327 \| - \| - \|
	\| 0.2063 \| 39 \| 0.1718 \| - \| - \|
	\| 0.2116 \| 40 \| 0.3162 \| 0.1443 \| 0.9067 \|
	\| 0.2169 \| 41 \| 0.296 \| - \| - \|
	\| 0.2222 \| 42 \| 0.2821 \| - \| - \|
	\| 0.2275 \| 43 \| 0.2069 \| - \| - \|
	\| 0.2328 \| 44 \| 0.2573 \| - \| - \|
	\| 0.2381 \| 45 \| 0.3119 \| 0.1343 \| 0.9064 \|
	\| 0.2434 \| 46 \| 0.2743 \| - \| - \|
	\| 0.2487 \| 47 \| 0.2666 \| - \| - \|
	\| 0.2540 \| 48 \| 0.2414 \| - \| - \|
	\| 0.2593 \| 49 \| 0.2793 \| - \| - \|
	\| 0.2646 \| 50 \| 0.2212 \| 0.1251 \| 0.9068 \|
	\| 0.2698 \| 51 \| 0.2071 \| - \| - \|
	\| 0.2751 \| 52 \| 0.296 \| - \| - \|
	\| 0.2804 \| 53 \| 0.2061 \| - \| - \|
	\| 0.2857 \| 54 \| 0.2164 \| - \| - \|
	\| 0.2910 \| 55 \| 0.188 \| 0.1197 \| 0.9072 \|
	\| 0.2963 \| 56 \| 0.2411 \| - \| - \|
	\| 0.3016 \| 57 \| 0.2031 \| - \| - \|
	\| 0.3069 \| 58 \| 0.2438 \| - \| - \|
	\| 0.3122 \| 59 \| 0.2417 \| - \| - \|
	\| 0.3175 \| 60 \| 0.1515 \| 0.1233 \| 0.9066 \|
	\| 0.3228 \| 61 \| 0.21 \| - \| - \|
	\| 0.3280 \| 62 \| 0.21 \| - \| - \|
	\| 0.3333 \| 63 \| 0.2157 \| - \| - \|
	\| 0.3386 \| 64 \| 0.2138 \| - \| - \|
	\| 0.3439 \| 65 \| 0.2403 \| 0.1273 \| 0.9058 \|
	\| 0.3492 \| 66 \| 0.2808 \| - \| - \|
	\| 0.3545 \| 67 \| 0.1891 \| - \| - \|
	\| 0.3598 \| 68 \| 0.1991 \| - \| - \|
	\| 0.3651 \| 69 \| 0.2121 \| - \| - \|
	\| 0.3704 \| 70 \| 0.2039 \| 0.1311 \| 0.9066 \|
	\| 0.3757 \| 71 \| 0.1986 \| - \| - \|
	\| 0.3810 \| 72 \| 0.2925 \| - \| - \|
	\| 0.3862 \| 73 \| 0.2527 \| - \| - \|
	\| 0.3915 \| 74 \| 0.279 \| - \| - \|
	\| 0.3968 \| 75 \| 0.2419 \| 0.1315 \| 0.9066 \|
	\| 0.4021 \| 76 \| 0.2228 \| - \| - \|


	### Framework Versions
	- Python: 3.10.14
	- Sentence Transformers: 3.0.1
	- Transformers: 4.44.0
	- PyTorch: 2.4.0
	- Accelerate: 0.33.0
	- Datasets: 2.21.0
	- Tokenizers: 0.19.1

	## 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.
	-->