MiniLM-cosqa-64 / README.md

Add new SentenceTransformer model

843be27 verified 4 months ago

32.8 kB

	---
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- dense
	- generated_from_trainer
	- dataset_size:9020
	- loss:MultipleNegativesRankingLoss
	base_model: sentence-transformers/all-MiniLM-L6-v2
	widget:
	- source_sentence: python multiprocessing show cpu count
	sentences:
	- "def unique(seq):\n \"\"\"Return the unique elements of a collection even if\
	\ those elements are\n unhashable and unsortable, like dicts and sets\"\"\
	\"\n cleaned = []\n for each in seq:\n if each not in cleaned:\n\
	\ cleaned.append(each)\n return cleaned"
	- "def is_in(self, point_x, point_y):\n \"\"\" Test if a point is within\
	\ this polygonal region \"\"\"\n\n point_array = array(((point_x, point_y),))\n\
	\ vertices = array(self.points)\n winding = self.inside_rule ==\
	\ \"winding\"\n result = points_in_polygon(point_array, vertices, winding)\n\
	\ return result[0]"
	- "def machine_info():\n \"\"\"Retrieve core and memory information for the current\
	\ machine.\n \"\"\"\n import psutil\n BYTES_IN_GIG = 1073741824.0\n \
	\ free_bytes = psutil.virtual_memory().total\n return [{\"memory\": float(\"\
	%.1f\" % (free_bytes / BYTES_IN_GIG)), \"cores\": multiprocessing.cpu_count(),\n\
	\ \"name\": socket.gethostname()}]"
	- source_sentence: python subplot set the whole title
	sentences:
	- "def set_title(self, title, **kwargs):\n \"\"\"Sets the title on the underlying\
	\ matplotlib AxesSubplot.\"\"\"\n ax = self.get_axes()\n ax.set_title(title,\
	\ **kwargs)"
	- "def moving_average(array, n=3):\n \"\"\"\n Calculates the moving average\
	\ of an array.\n\n Parameters\n ----------\n array : array\n The\
	\ array to have the moving average taken of\n n : int\n The number of\
	\ points of moving average to take\n \n Returns\n -------\n MovingAverageArray\
	\ : array\n The n-point moving average of the input array\n \"\"\"\n\
	\ ret = _np.cumsum(array, dtype=float)\n ret[n:] = ret[n:] - ret[:-n]\n\
	\ return ret[n - 1:] / n"
	- "def to_query_parameters(parameters):\n \"\"\"Converts DB-API parameter values\
	\ into query parameters.\n\n :type parameters: Mapping[str, Any] or Sequence[Any]\n\
	\ :param parameters: A dictionary or sequence of query parameter values.\n\n\
	\ :rtype: List[google.cloud.bigquery.query._AbstractQueryParameter]\n :returns:\
	\ A list of query parameters.\n \"\"\"\n if parameters is None:\n \
	\ return []\n\n if isinstance(parameters, collections_abc.Mapping):\n \
	\ return to_query_parameters_dict(parameters)\n\n return to_query_parameters_list(parameters)"
	- source_sentence: python merge two set to dict
	sentences:
	- "def make_regex(separator):\n \"\"\"Utility function to create regexp for matching\
	\ escaped separators\n in strings.\n\n \"\"\"\n return re.compile(r'(?:'\
	\ + re.escape(separator) + r')?((?:[^' +\n re.escape(separator)\
	\ + r'\\\\]\|\\\\.)+)')"
	- "def csvtolist(inputstr):\n \"\"\" converts a csv string into a list \"\"\"\
	\n reader = csv.reader([inputstr], skipinitialspace=True)\n output = []\n\
	\ for r in reader:\n output += r\n return output"
	- "def dict_merge(set1, set2):\n \"\"\"Joins two dictionaries.\"\"\"\n return\
	\ dict(list(set1.items()) + list(set2.items()))"
	- source_sentence: python string % substitution float
	sentences:
	- "def _configure_logger():\n \"\"\"Configure the logging module.\"\"\"\n \
	\ if not app.debug:\n _configure_logger_for_production(logging.getLogger())\n\
	\ elif not app.testing:\n _configure_logger_for_debugging(logging.getLogger())"
	- "def __set__(self, instance, value):\n \"\"\" Set a related object for\
	\ an instance. \"\"\"\n\n self.map[id(instance)] = (weakref.ref(instance),\
	\ value)"
	- "def format_float(value): # not used\n \"\"\"Modified form of the 'g' format\
	\ specifier.\n \"\"\"\n string = \"{:g}\".format(value).replace(\"e+\",\
	\ \"e\")\n string = re.sub(\"e(-?)0*(\\d+)\", r\"e\\1\\2\", string)\n return\
	\ string"
	- source_sentence: bottom 5 rows in python
	sentences:
	- "def refresh(self, document):\n\t\t\"\"\" Load a new copy of a document from the\
	\ database. does not\n\t\t\treplace the old one \"\"\"\n\t\ttry:\n\t\t\told_cache_size\
	\ = self.cache_size\n\t\t\tself.cache_size = 0\n\t\t\tobj = self.query(type(document)).filter_by(mongo_id=document.mongo_id).one()\n\
	\t\tfinally:\n\t\t\tself.cache_size = old_cache_size\n\t\tself.cache_write(obj)\n\
	\t\treturn obj"
	- "def table_top_abs(self):\n \"\"\"Returns the absolute position of table\
	\ top\"\"\"\n table_height = np.array([0, 0, self.table_full_size[2]])\n\
	\ return string_to_array(self.floor.get(\"pos\")) + table_height"
	- "def get_dimension_array(array):\n \"\"\"\n Get dimension of an array getting\
	\ the number of rows and the max num of\n columns.\n \"\"\"\n if all(isinstance(el,\
	\ list) for el in array):\n result = [len(array), len(max([x for x in array],\
	\ key=len,))]\n\n # elif array and isinstance(array, list):\n else:\n \
	\ result = [len(array), 1]\n\n return result"
	pipeline_tag: sentence-similarity
	library_name: sentence-transformers
	---

	# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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: [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
	- Maximum Sequence Length: 256 tokens
	- Output Dimensionality: 384 dimensions
	- Similarity Function: Cosine Similarity
	<!-- - Training Dataset: Unknown -->
	<!-- - 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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
	(1): Pooling({'word_embedding_dimension': 384, '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})
	(2): Normalize()
	)
	```

	## 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("Devy1/MiniLM-cosqa-64")
	# Run inference
	sentences = [
	'bottom 5 rows in python',
	'def table_top_abs(self):\n """Returns the absolute position of table top"""\n table_height = np.array([0, 0, self.table_full_size[2]])\n return string_to_array(self.floor.get("pos")) + table_height',
	'def refresh(self, document):\n\t\t""" Load a new copy of a document from the database. does not\n\t\t\treplace the old one """\n\t\ttry:\n\t\t\told_cache_size = self.cache_size\n\t\t\tself.cache_size = 0\n\t\t\tobj = self.query(type(document)).filter_by(mongo_id=document.mongo_id).one()\n\t\tfinally:\n\t\t\tself.cache_size = old_cache_size\n\t\tself.cache_write(obj)\n\t\treturn obj',
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 384]

	# Get the similarity scores for the embeddings
	similarities = model.similarity(embeddings, embeddings)
	print(similarities)
	# tensor([[ 1.0000, 0.4847, -0.0572],
	# [ 0.4847, 1.0000, -0.0541],
	# [-0.0572, -0.0541, 1.0000]])
	```

	<!--
	### 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.
	-->

	<!--
	## 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: 9,020 training samples
	* Columns: <code>anchor</code> and <code>positive</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| anchor \| positive \|
	\|:--------\|:---------------------------------------------------------------------------------\|:------------------------------------------------------------------------------------\|
	\| type \| string \| string \|
	\| details \| <ul><li>min: 6 tokens</li><li>mean: 9.67 tokens</li><li>max: 21 tokens</li></ul> \| <ul><li>min: 40 tokens</li><li>mean: 86.17 tokens</li><li>max: 256 tokens</li></ul> \|
	* Samples:
	\| anchor \| positive \|
	\|:--------------------------------------------------------\|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|
	\| <code>1d array in char datatype in python</code> \| <code>def _convert_to_array(array_like, dtype):<br> """<br> Convert Matrix attributes which are array-like or buffer to array.<br> """<br> if isinstance(array_like, bytes):<br> return np.frombuffer(array_like, dtype=dtype)<br> return np.asarray(array_like, dtype=dtype)</code> \|
	\| <code>python condition non none</code> \| <code>def _not(condition=None, kwargs):<br> """<br> Return the opposite of input condition.<br><br> :param condition: condition to process.<br><br> :result: not condition.<br> :rtype: bool<br> """<br><br> result = True<br><br> if condition is not None:<br> result = not run(condition, kwargs)<br><br> return result</code> \|
	\| <code>accessing a column from a matrix in python</code> \| <code>def get_column(self, X, column):<br> """Return a column of the given matrix.<br><br> Args:<br> X: `numpy.ndarray` or `pandas.DataFrame`.<br> column: `int` or `str`.<br><br> Returns:<br> np.ndarray: Selected column.<br> """<br> if isinstance(X, pd.DataFrame):<br> return X[column].values<br><br> return X[:, column]</code> \|
	* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
	```json
	{
	"scale": 20.0,
	"similarity_fct": "cos_sim",
	"gather_across_devices": false
	}
	```

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

	- `per_device_train_batch_size`: 64
	- `fp16`: True

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

	- `overwrite_output_dir`: False
	- `do_predict`: False
	- `eval_strategy`: no
	- `prediction_loss_only`: True
	- `per_device_train_batch_size`: 64
	- `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`: 1.0
	- `num_train_epochs`: 3
	- `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}
	- `parallelism_config`: None
	- `deepspeed`: None
	- `label_smoothing_factor`: 0.0
	- `optim`: adamw_torch_fused
	- `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
	<details><summary>Click to expand</summary>

	\| Epoch \| Step \| Training Loss \|
	\|:------:\|:----:\|:-------------:\|
	\| 0.0071 \| 1 \| 0.4603 \|
	\| 0.0142 \| 2 \| 0.3179 \|
	\| 0.0213 \| 3 \| 0.1802 \|
	\| 0.0284 \| 4 \| 0.2268 \|
	\| 0.0355 \| 5 \| 0.2288 \|
	\| 0.0426 \| 6 \| 0.1769 \|
	\| 0.0496 \| 7 \| 0.1555 \|
	\| 0.0567 \| 8 \| 0.2626 \|
	\| 0.0638 \| 9 \| 0.3319 \|
	\| 0.0709 \| 10 \| 0.28 \|
	\| 0.0780 \| 11 \| 0.3356 \|
	\| 0.0851 \| 12 \| 0.3241 \|
	\| 0.0922 \| 13 \| 0.2933 \|
	\| 0.0993 \| 14 \| 0.3929 \|
	\| 0.1064 \| 15 \| 0.1861 \|
	\| 0.1135 \| 16 \| 0.1983 \|
	\| 0.1206 \| 17 \| 0.1605 \|
	\| 0.1277 \| 18 \| 0.0918 \|
	\| 0.1348 \| 19 \| 0.2831 \|
	\| 0.1418 \| 20 \| 0.1709 \|
	\| 0.1489 \| 21 \| 0.1984 \|
	\| 0.1560 \| 22 \| 0.2657 \|
	\| 0.1631 \| 23 \| 0.1619 \|
	\| 0.1702 \| 24 \| 0.1728 \|
	\| 0.1773 \| 25 \| 0.1791 \|
	\| 0.1844 \| 26 \| 0.2429 \|
	\| 0.1915 \| 27 \| 0.2743 \|
	\| 0.1986 \| 28 \| 0.2813 \|
	\| 0.2057 \| 29 \| 0.2192 \|
	\| 0.2128 \| 30 \| 0.166 \|
	\| 0.2199 \| 31 \| 0.2557 \|
	\| 0.2270 \| 32 \| 0.3556 \|
	\| 0.2340 \| 33 \| 0.2238 \|
	\| 0.2411 \| 34 \| 0.2552 \|
	\| 0.2482 \| 35 \| 0.2266 \|
	\| 0.2553 \| 36 \| 0.4347 \|
	\| 0.2624 \| 37 \| 0.2803 \|
	\| 0.2695 \| 38 \| 0.1219 \|
	\| 0.2766 \| 39 \| 0.1989 \|
	\| 0.2837 \| 40 \| 0.2364 \|
	\| 0.2908 \| 41 \| 0.2237 \|
	\| 0.2979 \| 42 \| 0.1567 \|
	\| 0.3050 \| 43 \| 0.2509 \|
	\| 0.3121 \| 44 \| 0.16 \|
	\| 0.3191 \| 45 \| 0.2148 \|
	\| 0.3262 \| 46 \| 0.1953 \|
	\| 0.3333 \| 47 \| 0.2447 \|
	\| 0.3404 \| 48 \| 0.2001 \|
	\| 0.3475 \| 49 \| 0.283 \|
	\| 0.3546 \| 50 \| 0.1505 \|
	\| 0.3617 \| 51 \| 0.2825 \|
	\| 0.3688 \| 52 \| 0.2137 \|
	\| 0.3759 \| 53 \| 0.1376 \|
	\| 0.3830 \| 54 \| 0.3898 \|
	\| 0.3901 \| 55 \| 0.1873 \|
	\| 0.3972 \| 56 \| 0.2226 \|
	\| 0.4043 \| 57 \| 0.3129 \|
	\| 0.4113 \| 58 \| 0.2127 \|
	\| 0.4184 \| 59 \| 0.3474 \|
	\| 0.4255 \| 60 \| 0.0971 \|
	\| 0.4326 \| 61 \| 0.1728 \|
	\| 0.4397 \| 62 \| 0.2851 \|
	\| 0.4468 \| 63 \| 0.2608 \|
	\| 0.4539 \| 64 \| 0.3269 \|
	\| 0.4610 \| 65 \| 0.4905 \|
	\| 0.4681 \| 66 \| 0.1886 \|
	\| 0.4752 \| 67 \| 0.1465 \|
	\| 0.4823 \| 68 \| 0.2342 \|
	\| 0.4894 \| 69 \| 0.1915 \|
	\| 0.4965 \| 70 \| 0.2291 \|
	\| 0.5035 \| 71 \| 0.3232 \|
	\| 0.5106 \| 72 \| 0.1633 \|
	\| 0.5177 \| 73 \| 0.2039 \|
	\| 0.5248 \| 74 \| 0.2441 \|
	\| 0.5319 \| 75 \| 0.2336 \|
	\| 0.5390 \| 76 \| 0.139 \|
	\| 0.5461 \| 77 \| 0.4471 \|
	\| 0.5532 \| 78 \| 0.1989 \|
	\| 0.5603 \| 79 \| 0.2112 \|
	\| 0.5674 \| 80 \| 0.1862 \|
	\| 0.5745 \| 81 \| 0.2353 \|
	\| 0.5816 \| 82 \| 0.2326 \|
	\| 0.5887 \| 83 \| 0.3223 \|
	\| 0.5957 \| 84 \| 0.2055 \|
	\| 0.6028 \| 85 \| 0.2968 \|
	\| 0.6099 \| 86 \| 0.2531 \|
	\| 0.6170 \| 87 \| 0.2401 \|
	\| 0.6241 \| 88 \| 0.1632 \|
	\| 0.6312 \| 89 \| 0.4203 \|
	\| 0.6383 \| 90 \| 0.1959 \|
	\| 0.6454 \| 91 \| 0.2309 \|
	\| 0.6525 \| 92 \| 0.3729 \|
	\| 0.6596 \| 93 \| 0.2488 \|
	\| 0.6667 \| 94 \| 0.1698 \|
	\| 0.6738 \| 95 \| 0.267 \|
	\| 0.6809 \| 96 \| 0.1658 \|
	\| 0.6879 \| 97 \| 0.2158 \|
	\| 0.6950 \| 98 \| 0.1665 \|
	\| 0.7021 \| 99 \| 0.1897 \|
	\| 0.7092 \| 100 \| 0.2159 \|
	\| 0.7163 \| 101 \| 0.1932 \|
	\| 0.7234 \| 102 \| 0.2236 \|
	\| 0.7305 \| 103 \| 0.1287 \|
	\| 0.7376 \| 104 \| 0.1917 \|
	\| 0.7447 \| 105 \| 0.4039 \|
	\| 0.7518 \| 106 \| 0.388 \|
	\| 0.7589 \| 107 \| 0.1267 \|
	\| 0.7660 \| 108 \| 0.1851 \|
	\| 0.7730 \| 109 \| 0.1916 \|
	\| 0.7801 \| 110 \| 0.1893 \|
	\| 0.7872 \| 111 \| 0.1702 \|
	\| 0.7943 \| 112 \| 0.1552 \|
	\| 0.8014 \| 113 \| 0.1529 \|
	\| 0.8085 \| 114 \| 0.1634 \|
	\| 0.8156 \| 115 \| 0.2136 \|
	\| 0.8227 \| 116 \| 0.1719 \|
	\| 0.8298 \| 117 \| 0.2529 \|
	\| 0.8369 \| 118 \| 0.2329 \|
	\| 0.8440 \| 119 \| 0.2483 \|
	\| 0.8511 \| 120 \| 0.132 \|
	\| 0.8582 \| 121 \| 0.182 \|
	\| 0.8652 \| 122 \| 0.127 \|
	\| 0.8723 \| 123 \| 0.3685 \|
	\| 0.8794 \| 124 \| 0.4202 \|
	\| 0.8865 \| 125 \| 0.2173 \|
	\| 0.8936 \| 126 \| 0.0657 \|
	\| 0.9007 \| 127 \| 0.0838 \|
	\| 0.9078 \| 128 \| 0.1592 \|
	\| 0.9149 \| 129 \| 0.2506 \|
	\| 0.9220 \| 130 \| 0.1624 \|
	\| 0.9291 \| 131 \| 0.1511 \|
	\| 0.9362 \| 132 \| 0.138 \|
	\| 0.9433 \| 133 \| 0.2187 \|
	\| 0.9504 \| 134 \| 0.2891 \|
	\| 0.9574 \| 135 \| 0.158 \|
	\| 0.9645 \| 136 \| 0.2595 \|
	\| 0.9716 \| 137 \| 0.2911 \|
	\| 0.9787 \| 138 \| 0.2141 \|
	\| 0.9858 \| 139 \| 0.1723 \|
	\| 0.9929 \| 140 \| 0.1847 \|
	\| 1.0 \| 141 \| 0.2606 \|
	\| 1.0071 \| 142 \| 0.1283 \|
	\| 1.0142 \| 143 \| 0.1626 \|
	\| 1.0213 \| 144 \| 0.2121 \|
	\| 1.0284 \| 145 \| 0.142 \|
	\| 1.0355 \| 146 \| 0.1335 \|
	\| 1.0426 \| 147 \| 0.1084 \|
	\| 1.0496 \| 148 \| 0.15 \|
	\| 1.0567 \| 149 \| 0.1459 \|
	\| 1.0638 \| 150 \| 0.0674 \|
	\| 1.0709 \| 151 \| 0.1393 \|
	\| 1.0780 \| 152 \| 0.1582 \|
	\| 1.0851 \| 153 \| 0.1295 \|
	\| 1.0922 \| 154 \| 0.1402 \|
	\| 1.0993 \| 155 \| 0.2266 \|
	\| 1.1064 \| 156 \| 0.1025 \|
	\| 1.1135 \| 157 \| 0.1616 \|
	\| 1.1206 \| 158 \| 0.1795 \|
	\| 1.1277 \| 159 \| 0.1583 \|
	\| 1.1348 \| 160 \| 0.1624 \|
	\| 1.1418 \| 161 \| 0.1068 \|
	\| 1.1489 \| 162 \| 0.1301 \|
	\| 1.1560 \| 163 \| 0.1792 \|
	\| 1.1631 \| 164 \| 0.1656 \|
	\| 1.1702 \| 165 \| 0.1666 \|
	\| 1.1773 \| 166 \| 0.1031 \|
	\| 1.1844 \| 167 \| 0.1092 \|
	\| 1.1915 \| 168 \| 0.1668 \|
	\| 1.1986 \| 169 \| 0.1218 \|
	\| 1.2057 \| 170 \| 0.146 \|
	\| 1.2128 \| 171 \| 0.1041 \|
	\| 1.2199 \| 172 \| 0.2275 \|
	\| 1.2270 \| 173 \| 0.1017 \|
	\| 1.2340 \| 174 \| 0.1025 \|
	\| 1.2411 \| 175 \| 0.1385 \|
	\| 1.2482 \| 176 \| 0.1024 \|
	\| 1.2553 \| 177 \| 0.1073 \|
	\| 1.2624 \| 178 \| 0.0802 \|
	\| 1.2695 \| 179 \| 0.1985 \|
	\| 1.2766 \| 180 \| 0.1918 \|
	\| 1.2837 \| 181 \| 0.092 \|
	\| 1.2908 \| 182 \| 0.1591 \|
	\| 1.2979 \| 183 \| 0.2512 \|
	\| 1.3050 \| 184 \| 0.2213 \|
	\| 1.3121 \| 185 \| 0.129 \|
	\| 1.3191 \| 186 \| 0.0759 \|
	\| 1.3262 \| 187 \| 0.243 \|
	\| 1.3333 \| 188 \| 0.1759 \|
	\| 1.3404 \| 189 \| 0.126 \|
	\| 1.3475 \| 190 \| 0.1105 \|
	\| 1.3546 \| 191 \| 0.1789 \|
	\| 1.3617 \| 192 \| 0.1841 \|
	\| 1.3688 \| 193 \| 0.1074 \|
	\| 1.3759 \| 194 \| 0.1293 \|
	\| 1.3830 \| 195 \| 0.1228 \|
	\| 1.3901 \| 196 \| 0.1574 \|
	\| 1.3972 \| 197 \| 0.1073 \|
	\| 1.4043 \| 198 \| 0.1305 \|
	\| 1.4113 \| 199 \| 0.1911 \|
	\| 1.4184 \| 200 \| 0.1088 \|
	\| 1.4255 \| 201 \| 0.111 \|
	\| 1.4326 \| 202 \| 0.1639 \|
	\| 1.4397 \| 203 \| 0.0944 \|
	\| 1.4468 \| 204 \| 0.2008 \|
	\| 1.4539 \| 205 \| 0.136 \|
	\| 1.4610 \| 206 \| 0.1981 \|
	\| 1.4681 \| 207 \| 0.0848 \|
	\| 1.4752 \| 208 \| 0.0771 \|
	\| 1.4823 \| 209 \| 0.0933 \|
	\| 1.4894 \| 210 \| 0.1794 \|
	\| 1.4965 \| 211 \| 0.1533 \|
	\| 1.5035 \| 212 \| 0.1841 \|
	\| 1.5106 \| 213 \| 0.1724 \|
	\| 1.5177 \| 214 \| 0.1205 \|
	\| 1.5248 \| 215 \| 0.1118 \|
	\| 1.5319 \| 216 \| 0.16 \|
	\| 1.5390 \| 217 \| 0.2911 \|
	\| 1.5461 \| 218 \| 0.1678 \|
	\| 1.5532 \| 219 \| 0.1032 \|
	\| 1.5603 \| 220 \| 0.1438 \|
	\| 1.5674 \| 221 \| 0.1581 \|
	\| 1.5745 \| 222 \| 0.1143 \|
	\| 1.5816 \| 223 \| 0.1782 \|
	\| 1.5887 \| 224 \| 0.2768 \|
	\| 1.5957 \| 225 \| 0.1127 \|
	\| 1.6028 \| 226 \| 0.1719 \|
	\| 1.6099 \| 227 \| 0.2252 \|
	\| 1.6170 \| 228 \| 0.2182 \|
	\| 1.6241 \| 229 \| 0.287 \|
	\| 1.6312 \| 230 \| 0.1314 \|
	\| 1.6383 \| 231 \| 0.1951 \|
	\| 1.6454 \| 232 \| 0.13 \|
	\| 1.6525 \| 233 \| 0.0677 \|
	\| 1.6596 \| 234 \| 0.1188 \|
	\| 1.6667 \| 235 \| 0.1214 \|
	\| 1.6738 \| 236 \| 0.1219 \|
	\| 1.6809 \| 237 \| 0.1646 \|
	\| 1.6879 \| 238 \| 0.1079 \|
	\| 1.6950 \| 239 \| 0.1624 \|
	\| 1.7021 \| 240 \| 0.0994 \|
	\| 1.7092 \| 241 \| 0.194 \|
	\| 1.7163 \| 242 \| 0.1104 \|
	\| 1.7234 \| 243 \| 0.1223 \|
	\| 1.7305 \| 244 \| 0.0918 \|
	\| 1.7376 \| 245 \| 0.0835 \|
	\| 1.7447 \| 246 \| 0.0994 \|
	\| 1.7518 \| 247 \| 0.1375 \|
	\| 1.7589 \| 248 \| 0.1004 \|
	\| 1.7660 \| 249 \| 0.1164 \|
	\| 1.7730 \| 250 \| 0.1151 \|
	\| 1.7801 \| 251 \| 0.0868 \|
	\| 1.7872 \| 252 \| 0.2498 \|
	\| 1.7943 \| 253 \| 0.0741 \|
	\| 1.8014 \| 254 \| 0.1417 \|
	\| 1.8085 \| 255 \| 0.0514 \|
	\| 1.8156 \| 256 \| 0.2346 \|
	\| 1.8227 \| 257 \| 0.2383 \|
	\| 1.8298 \| 258 \| 0.1432 \|
	\| 1.8369 \| 259 \| 0.1563 \|
	\| 1.8440 \| 260 \| 0.1267 \|
	\| 1.8511 \| 261 \| 0.1331 \|
	\| 1.8582 \| 262 \| 0.1904 \|
	\| 1.8652 \| 263 \| 0.0912 \|
	\| 1.8723 \| 264 \| 0.214 \|
	\| 1.8794 \| 265 \| 0.1846 \|
	\| 1.8865 \| 266 \| 0.1378 \|
	\| 1.8936 \| 267 \| 0.1012 \|
	\| 1.9007 \| 268 \| 0.1468 \|
	\| 1.9078 \| 269 \| 0.109 \|
	\| 1.9149 \| 270 \| 0.1136 \|
	\| 1.9220 \| 271 \| 0.1734 \|
	\| 1.9291 \| 272 \| 0.0785 \|
	\| 1.9362 \| 273 \| 0.0388 \|
	\| 1.9433 \| 274 \| 0.1138 \|
	\| 1.9504 \| 275 \| 0.0806 \|
	\| 1.9574 \| 276 \| 0.2819 \|
	\| 1.9645 \| 277 \| 0.1719 \|
	\| 1.9716 \| 278 \| 0.0479 \|
	\| 1.9787 \| 279 \| 0.1038 \|
	\| 1.9858 \| 280 \| 0.1401 \|
	\| 1.9929 \| 281 \| 0.1961 \|
	\| 2.0 \| 282 \| 0.1072 \|
	\| 2.0071 \| 283 \| 0.1005 \|
	\| 2.0142 \| 284 \| 0.147 \|
	\| 2.0213 \| 285 \| 0.1011 \|
	\| 2.0284 \| 286 \| 0.1304 \|
	\| 2.0355 \| 287 \| 0.073 \|
	\| 2.0426 \| 288 \| 0.0952 \|
	\| 2.0496 \| 289 \| 0.0956 \|
	\| 2.0567 \| 290 \| 0.1083 \|
	\| 2.0638 \| 291 \| 0.1101 \|
	\| 2.0709 \| 292 \| 0.0534 \|
	\| 2.0780 \| 293 \| 0.0837 \|
	\| 2.0851 \| 294 \| 0.0966 \|
	\| 2.0922 \| 295 \| 0.195 \|
	\| 2.0993 \| 296 \| 0.0608 \|
	\| 2.1064 \| 297 \| 0.0999 \|
	\| 2.1135 \| 298 \| 0.1588 \|
	\| 2.1206 \| 299 \| 0.1283 \|
	\| 2.1277 \| 300 \| 0.0962 \|
	\| 2.1348 \| 301 \| 0.0872 \|
	\| 2.1418 \| 302 \| 0.0793 \|
	\| 2.1489 \| 303 \| 0.1209 \|
	\| 2.1560 \| 304 \| 0.1346 \|
	\| 2.1631 \| 305 \| 0.131 \|
	\| 2.1702 \| 306 \| 0.1081 \|
	\| 2.1773 \| 307 \| 0.1109 \|
	\| 2.1844 \| 308 \| 0.197 \|
	\| 2.1915 \| 309 \| 0.108 \|
	\| 2.1986 \| 310 \| 0.1715 \|
	\| 2.2057 \| 311 \| 0.0654 \|
	\| 2.2128 \| 312 \| 0.1374 \|
	\| 2.2199 \| 313 \| 0.0929 \|
	\| 2.2270 \| 314 \| 0.033 \|
	\| 2.2340 \| 315 \| 0.0903 \|
	\| 2.2411 \| 316 \| 0.1417 \|
	\| 2.2482 \| 317 \| 0.134 \|
	\| 2.2553 \| 318 \| 0.041 \|
	\| 2.2624 \| 319 \| 0.0947 \|
	\| 2.2695 \| 320 \| 0.0655 \|
	\| 2.2766 \| 321 \| 0.0525 \|
	\| 2.2837 \| 322 \| 0.0547 \|
	\| 2.2908 \| 323 \| 0.1342 \|
	\| 2.2979 \| 324 \| 0.1088 \|
	\| 2.3050 \| 325 \| 0.162 \|
	\| 2.3121 \| 326 \| 0.0962 \|
	\| 2.3191 \| 327 \| 0.154 \|
	\| 2.3262 \| 328 \| 0.0935 \|
	\| 2.3333 \| 329 \| 0.1186 \|
	\| 2.3404 \| 330 \| 0.1192 \|
	\| 2.3475 \| 331 \| 0.1075 \|
	\| 2.3546 \| 332 \| 0.12 \|
	\| 2.3617 \| 333 \| 0.0679 \|
	\| 2.3688 \| 334 \| 0.1087 \|
	\| 2.3759 \| 335 \| 0.1493 \|
	\| 2.3830 \| 336 \| 0.085 \|
	\| 2.3901 \| 337 \| 0.1784 \|
	\| 2.3972 \| 338 \| 0.0567 \|
	\| 2.4043 \| 339 \| 0.1842 \|
	\| 2.4113 \| 340 \| 0.183 \|
	\| 2.4184 \| 341 \| 0.1108 \|
	\| 2.4255 \| 342 \| 0.1405 \|
	\| 2.4326 \| 343 \| 0.2477 \|
	\| 2.4397 \| 344 \| 0.2376 \|
	\| 2.4468 \| 345 \| 0.1469 \|
	\| 2.4539 \| 346 \| 0.1048 \|
	\| 2.4610 \| 347 \| 0.1153 \|
	\| 2.4681 \| 348 \| 0.1167 \|
	\| 2.4752 \| 349 \| 0.1605 \|
	\| 2.4823 \| 350 \| 0.1479 \|
	\| 2.4894 \| 351 \| 0.0684 \|
	\| 2.4965 \| 352 \| 0.0515 \|
	\| 2.5035 \| 353 \| 0.1035 \|
	\| 2.5106 \| 354 \| 0.1488 \|
	\| 2.5177 \| 355 \| 0.0274 \|
	\| 2.5248 \| 356 \| 0.0706 \|
	\| 2.5319 \| 357 \| 0.1541 \|
	\| 2.5390 \| 358 \| 0.1331 \|
	\| 2.5461 \| 359 \| 0.0911 \|
	\| 2.5532 \| 360 \| 0.0606 \|
	\| 2.5603 \| 361 \| 0.1612 \|
	\| 2.5674 \| 362 \| 0.2752 \|
	\| 2.5745 \| 363 \| 0.1436 \|
	\| 2.5816 \| 364 \| 0.1257 \|
	\| 2.5887 \| 365 \| 0.1174 \|
	\| 2.5957 \| 366 \| 0.0415 \|
	\| 2.6028 \| 367 \| 0.0918 \|
	\| 2.6099 \| 368 \| 0.0899 \|
	\| 2.6170 \| 369 \| 0.1136 \|
	\| 2.6241 \| 370 \| 0.1337 \|
	\| 2.6312 \| 371 \| 0.1948 \|
	\| 2.6383 \| 372 \| 0.1482 \|
	\| 2.6454 \| 373 \| 0.1209 \|
	\| 2.6525 \| 374 \| 0.1082 \|
	\| 2.6596 \| 375 \| 0.1948 \|
	\| 2.6667 \| 376 \| 0.1029 \|
	\| 2.6738 \| 377 \| 0.0783 \|
	\| 2.6809 \| 378 \| 0.0844 \|
	\| 2.6879 \| 379 \| 0.1045 \|
	\| 2.6950 \| 380 \| 0.0982 \|
	\| 2.7021 \| 381 \| 0.075 \|
	\| 2.7092 \| 382 \| 0.15 \|
	\| 2.7163 \| 383 \| 0.1155 \|
	\| 2.7234 \| 384 \| 0.1334 \|
	\| 2.7305 \| 385 \| 0.0767 \|
	\| 2.7376 \| 386 \| 0.0476 \|
	\| 2.7447 \| 387 \| 0.068 \|
	\| 2.7518 \| 388 \| 0.0967 \|
	\| 2.7589 \| 389 \| 0.0953 \|
	\| 2.7660 \| 390 \| 0.1307 \|
	\| 2.7730 \| 391 \| 0.0923 \|
	\| 2.7801 \| 392 \| 0.1159 \|
	\| 2.7872 \| 393 \| 0.0769 \|
	\| 2.7943 \| 394 \| 0.0993 \|
	\| 2.8014 \| 395 \| 0.1018 \|
	\| 2.8085 \| 396 \| 0.0783 \|
	\| 2.8156 \| 397 \| 0.0792 \|
	\| 2.8227 \| 398 \| 0.0914 \|
	\| 2.8298 \| 399 \| 0.0821 \|
	\| 2.8369 \| 400 \| 0.0947 \|
	\| 2.8440 \| 401 \| 0.0622 \|
	\| 2.8511 \| 402 \| 0.1858 \|
	\| 2.8582 \| 403 \| 0.1977 \|
	\| 2.8652 \| 404 \| 0.0398 \|
	\| 2.8723 \| 405 \| 0.0784 \|
	\| 2.8794 \| 406 \| 0.1622 \|
	\| 2.8865 \| 407 \| 0.1213 \|
	\| 2.8936 \| 408 \| 0.1867 \|
	\| 2.9007 \| 409 \| 0.1257 \|
	\| 2.9078 \| 410 \| 0.1366 \|
	\| 2.9149 \| 411 \| 0.0983 \|
	\| 2.9220 \| 412 \| 0.0967 \|
	\| 2.9291 \| 413 \| 0.0398 \|
	\| 2.9362 \| 414 \| 0.1582 \|
	\| 2.9433 \| 415 \| 0.123 \|
	\| 2.9504 \| 416 \| 0.1768 \|
	\| 2.9574 \| 417 \| 0.131 \|
	\| 2.9645 \| 418 \| 0.0731 \|
	\| 2.9716 \| 419 \| 0.074 \|
	\| 2.9787 \| 420 \| 0.1176 \|
	\| 2.9858 \| 421 \| 0.0984 \|
	\| 2.9929 \| 422 \| 0.0834 \|
	\| 3.0 \| 423 \| 0.1985 \|

	</details>

	### Framework Versions
	- Python: 3.10.14
	- Sentence Transformers: 5.1.1
	- Transformers: 4.56.2
	- PyTorch: 2.8.0+cu128
	- Accelerate: 1.10.1
	- Datasets: 4.1.1
	- Tokenizers: 0.22.1

	## 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",
	}
	```

	#### MultipleNegativesRankingLoss
	```bibtex
	@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}
	}
	```

	<!--
	## 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.
	-->