--- language: - en tags: - sentence-transformers - sentence-similarity - feature-extraction - dense - generated_from_trainer - dataset_size:19963 - loss:CachedMultipleNegativesRankingLoss base_model: benjamintli/modernbert-cosqa widget: - source_sentence: python string to microseconds sentences: - "def seconds_to_hms(seconds):\n \"\"\"\n Converts seconds float to 'hh:mm:ss.ssssss'\ \ format.\n \"\"\"\n hours = int(seconds / 3600.0)\n minutes = int((seconds\ \ / 60.0) % 60.0)\n secs = float(seconds % 60.0)\n return \"{0:02d}:{1:02d}:{2:02.6f}\"\ .format(hours, minutes, secs)" - "def align_file_position(f, size):\n \"\"\" Align the position in the file\ \ to the next block of specified size \"\"\"\n align = (size - 1) - (f.tell()\ \ % size)\n f.seek(align, 1)" - "def timestamp_to_microseconds(timestamp):\n \"\"\"Convert a timestamp string\ \ into a microseconds value\n :param timestamp\n :return time in microseconds\n\ \ \"\"\"\n timestamp_str = datetime.datetime.strptime(timestamp, ISO_DATETIME_REGEX)\n\ \ epoch_time_secs = calendar.timegm(timestamp_str.timetuple())\n epoch_time_mus\ \ = epoch_time_secs * 1e6 + timestamp_str.microsecond\n return epoch_time_mus" - source_sentence: python remove parenthesis around stringf sentences: - "def format_screen(strng):\n \"\"\"Format a string for screen printing.\n\n\ \ This removes some latex-type format codes.\"\"\"\n # Paragraph continue\n\ \ par_re = re.compile(r'\\\\$',re.MULTILINE)\n strng = par_re.sub('',strng)\n\ \ return strng" - "def do_striptags(value):\n \"\"\"Strip SGML/XML tags and replace adjacent\ \ whitespace by one space.\n \"\"\"\n if hasattr(value, '__html__'):\n \ \ value = value.__html__()\n return Markup(unicode(value)).striptags()" - "def _replace_file(path, content):\n \"\"\"Writes a file if it doesn't already\ \ exist with the same content.\n\n This is useful because cargo uses timestamps\ \ to decide whether to compile things.\"\"\"\n if os.path.exists(path):\n \ \ with open(path, 'r') as f:\n if content == f.read():\n print(\"\ Not overwriting {} because it is unchanged\".format(path), file=sys.stderr)\n\ \ return\n\n with open(path, 'w') as f:\n f.write(content)" - source_sentence: python out of range float values are not json compliant sentences: - "def show():\n \"\"\"Show (print out) current environment variables.\"\"\"\n\ \ env = get_environment()\n\n for key, val in sorted(env.env.items(), key=lambda\ \ item: item[0]):\n click.secho('%s = %s' % (key, val))" - "def default_number_converter(number_str):\n \"\"\"\n Converts the string\ \ representation of a json number into its python object equivalent, an\n int,\ \ long, float or whatever type suits.\n \"\"\"\n is_int = (number_str.startswith('-')\ \ and number_str[1:].isdigit()) or number_str.isdigit()\n # FIXME: this handles\ \ a wider range of numbers than allowed by the json standard,\n # etc.: float('nan')\ \ and float('inf'). But is this a problem?\n return int(number_str) if is_int\ \ else float(number_str)" - "def __get_float(section, name):\n \"\"\"Get the forecasted float from json\ \ section.\"\"\"\n try:\n return float(section[name])\n except (ValueError,\ \ TypeError, KeyError):\n return float(0)" - source_sentence: python openclipboard access is denied win32clipboard sentences: - "def set_time(filename, mod_time):\n\t\"\"\"\n\tSet the modified time of a file\n\ \t\"\"\"\n\tlog.debug('Setting modified time to %s', mod_time)\n\tmtime = calendar.timegm(mod_time.utctimetuple())\n\ \t# utctimetuple discards microseconds, so restore it (for consistency)\n\tmtime\ \ += mod_time.microsecond / 1000000\n\tatime = os.stat(filename).st_atime\n\t\ os.utime(filename, (atime, mtime))" - "def paste(cmd=paste_cmd, stdout=PIPE):\n \"\"\"Returns system clipboard contents.\n\ \ \"\"\"\n return Popen(cmd, stdout=stdout).communicate()[0].decode('utf-8')" - "def paste(xsel=False):\n \"\"\"Returns system clipboard contents.\"\"\"\n\ \ selection = \"primary\" if xsel else \"clipboard\"\n try:\n return\ \ subprocess.Popen([\"xclip\", \"-selection\", selection, \"-o\"], stdout=subprocess.PIPE).communicate()[0].decode(\"\ utf-8\")\n except OSError as why:\n raise XclipNotFound" - source_sentence: python strftime miliseconds fixed width sentences: - "def fmt_duration(secs):\n \"\"\"Format a duration in seconds.\"\"\"\n return\ \ ' '.join(fmt.human_duration(secs, 0, precision=2, short=True).strip().split())" - "def check_hash_key(query_on, key):\n \"\"\"Only allows == against query_on.hash_key\"\ \"\"\n return (\n isinstance(key, BaseCondition) and\n (key.operation\ \ == \"==\") and\n (key.column is query_on.hash_key)\n )" - "def seconds_to_hms(seconds):\n \"\"\"\n Converts seconds float to 'hh:mm:ss.ssssss'\ \ format.\n \"\"\"\n hours = int(seconds / 3600.0)\n minutes = int((seconds\ \ / 60.0) % 60.0)\n secs = float(seconds % 60.0)\n return \"{0:02d}:{1:02d}:{2:02.6f}\"\ .format(hours, minutes, secs)" datasets: - benjamintli/cosqa-llm-filtered-hard-negatives pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: SentenceTransformer based on benjamintli/modernbert-cosqa results: - task: type: information-retrieval name: Information Retrieval dataset: name: eval type: eval metrics: - type: cosine_accuracy@1 value: 0.5520504731861199 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.8598467778278504 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9310500225326723 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.975214060387562 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.5520504731861199 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2866155926092835 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.18621000450653444 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09752140603875618 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.5520504731861199 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.8598467778278504 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9310500225326723 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.975214060387562 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.778855811581032 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.7140104937874189 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.7154223269913967 name: Cosine Map@100 --- # SentenceTransformer based on benjamintli/modernbert-cosqa This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [benjamintli/modernbert-cosqa](https://huggingface.co/benjamintli/modernbert-cosqa) on the [cosqa-llm-filtered-hard-negatives](https://huggingface.co/datasets/benjamintli/cosqa-llm-filtered-hard-negatives) 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:** [benjamintli/modernbert-cosqa](https://huggingface.co/benjamintli/modernbert-cosqa) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [cosqa-llm-filtered-hard-negatives](https://huggingface.co/datasets/benjamintli/cosqa-llm-filtered-hard-negatives) - **Language:** en ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/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, 'architecture': 'OptimizedModule'}) (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("modernbert-cosqa-hard-negatives") # Run inference sentences = [ 'python strftime miliseconds fixed width', 'def fmt_duration(secs):\n """Format a duration in seconds."""\n return \' \'.join(fmt.human_duration(secs, 0, precision=2, short=True).strip().split())', 'def seconds_to_hms(seconds):\n """\n Converts seconds float to \'hh:mm:ss.ssssss\' format.\n """\n hours = int(seconds / 3600.0)\n minutes = int((seconds / 60.0) % 60.0)\n secs = float(seconds % 60.0)\n return "{0:02d}:{1:02d}:{2:02.6f}".format(hours, minutes, secs)', ] 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, 0.7076, 0.6960], # [0.7076, 1.0000, 0.7423], # [0.6960, 0.7423, 1.0000]]) ``` ## Evaluation ### Metrics #### Information Retrieval * Dataset: `eval` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.5521 | | cosine_accuracy@3 | 0.8598 | | cosine_accuracy@5 | 0.9311 | | cosine_accuracy@10 | 0.9752 | | cosine_precision@1 | 0.5521 | | cosine_precision@3 | 0.2866 | | cosine_precision@5 | 0.1862 | | cosine_precision@10 | 0.0975 | | cosine_recall@1 | 0.5521 | | cosine_recall@3 | 0.8598 | | cosine_recall@5 | 0.9311 | | cosine_recall@10 | 0.9752 | | **cosine_ndcg@10** | **0.7789** | | cosine_mrr@10 | 0.714 | | cosine_map@100 | 0.7154 | ## Training Details ### Training Dataset #### cosqa-llm-filtered-hard-negatives * Dataset: [cosqa-llm-filtered-hard-negatives](https://huggingface.co/datasets/benjamintli/cosqa-llm-filtered-hard-negatives) at [1585731](https://huggingface.co/datasets/benjamintli/cosqa-llm-filtered-hard-negatives/tree/1585731575d5b96ffdce2c27b70c8943a61edf75) * Size: 19,963 training samples * Columns: anchor, positive, and negative * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | anchor | positive | negative | |:-------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | python 2d array to dict | def to_dicts(recarray):
"""convert record array to a dictionaries"""
for rec in recarray:
yield dict(zip(recarray.dtype.names, rec.tolist())) | def multidict_to_dict(d):
"""
Turns a werkzeug.MultiDict or django.MultiValueDict into a dict with
list values
:param d: a MultiDict or MultiValueDict instance
:return: a dict instance
"""
return dict((k, v[0] if len(v) == 1 else v) for k, v in iterlists(d)) | | how to send dns request message in python | def _request_modify_dns_record(self, record):
"""Sends Modify_DNS_Record request"""
return self._request_internal("Modify_DNS_Record",
domain=self.domain,
record=record) | def request(self, method, url, body=None, headers={}):
"""Send a complete request to the server."""
self._send_request(method, url, body, headers) | | how to cast string to uint8 in python | def b2u(string):
""" bytes to unicode """
if (isinstance(string, bytes) or
(PY2 and isinstance(string, str))):
return string.decode('utf-8')
return string | def to_bytes(s, encoding="utf-8"):
"""Convert a string to bytes."""
if isinstance(s, six.binary_type):
return s
if six.PY3:
return bytes(s, encoding)
return s.encode(encoding) | * Loss: [CachedMultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim", "mini_batch_size": 64, "gather_across_devices": false, "directions": [ "query_to_doc" ], "partition_mode": "joint", "hardness_mode": null, "hardness_strength": 0.0 } ``` ### Evaluation Dataset #### cosqa-llm-filtered-hard-negatives * Dataset: [cosqa-llm-filtered-hard-negatives](https://huggingface.co/datasets/benjamintli/cosqa-llm-filtered-hard-negatives) at [1585731](https://huggingface.co/datasets/benjamintli/cosqa-llm-filtered-hard-negatives/tree/1585731575d5b96ffdce2c27b70c8943a61edf75) * Size: 2,219 evaluation samples * Columns: anchor, positive, and negative * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | anchor | positive | negative | |:-----------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | way to change the string "python" to have all uppercase letters | def uppercase_chars(string: any) -> str:
"""Return all (and only) the uppercase chars in the given string."""
return ''.join([c if c.isupper() else '' for c in str(string)]) | def to_capitalized_camel_case(snake_case_string):
"""
Convert a string from snake case to camel case with the first letter capitalized. For example, "some_var"
would become "SomeVar".

:param snake_case_string: Snake-cased string to convert to camel case.
:returns: Camel-cased version of snake_case_string.
"""
parts = snake_case_string.split('_')
return ''.join([i.title() for i in parts]) | | how to make intercept zero in python | def prox_zero(X, step):
"""Proximal operator to project onto zero
"""
return np.zeros(X.shape, dtype=X.dtype) | def _adjust_offset(self, real_wave_mfcc, algo_parameters):
"""
OFFSET
"""
self.log(u"Called _adjust_offset")
self._apply_offset(offset=algo_parameters[0]) | | stop running function and passing to other variable python | def stop(self) -> None:
"""Stops the analysis as soon as possible."""
if self._stop and not self._posted_kork:
self._stop()
self._stop = None | def stop(self, dummy_signum=None, dummy_frame=None):
""" Shutdown process (this method is also a signal handler) """
logging.info('Shutting down ...')
self.socket.close()
sys.exit(0) | * Loss: [CachedMultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim", "mini_batch_size": 64, "gather_across_devices": false, "directions": [ "query_to_doc" ], "partition_mode": "joint", "hardness_mode": null, "hardness_strength": 0.0 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 1024 - `num_train_epochs`: 10 - `learning_rate`: 2e-06 - `warmup_steps`: 0.1 - `bf16`: True - `eval_strategy`: epoch - `per_device_eval_batch_size`: 1024 - `push_to_hub`: True - `hub_model_id`: modernbert-cosqa-hard-negatives - `load_best_model_at_end`: True - `dataloader_num_workers`: 4 - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `per_device_train_batch_size`: 1024 - `num_train_epochs`: 10 - `max_steps`: -1 - `learning_rate`: 2e-06 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: None - `warmup_steps`: 0.1 - `optim`: adamw_torch_fused - `optim_args`: None - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `optim_target_modules`: None - `gradient_accumulation_steps`: 1 - `average_tokens_across_devices`: True - `max_grad_norm`: 1.0 - `label_smoothing_factor`: 0.0 - `bf16`: True - `fp16`: False - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `use_liger_kernel`: False - `liger_kernel_config`: None - `use_cache`: False - `neftune_noise_alpha`: None - `torch_empty_cache_steps`: None - `auto_find_batch_size`: False - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `include_num_input_tokens_seen`: no - `log_level`: passive - `log_level_replica`: warning - `disable_tqdm`: False - `project`: huggingface - `trackio_space_id`: trackio - `eval_strategy`: epoch - `per_device_eval_batch_size`: 1024 - `prediction_loss_only`: True - `eval_on_start`: False - `eval_do_concat_batches`: True - `eval_use_gather_object`: False - `eval_accumulation_steps`: None - `include_for_metrics`: [] - `batch_eval_metrics`: False - `save_only_model`: False - `save_on_each_node`: False - `enable_jit_checkpoint`: False - `push_to_hub`: True - `hub_private_repo`: None - `hub_model_id`: modernbert-cosqa-hard-negatives - `hub_strategy`: every_save - `hub_always_push`: False - `hub_revision`: None - `load_best_model_at_end`: True - `ignore_data_skip`: False - `restore_callback_states_from_checkpoint`: False - `full_determinism`: False - `seed`: 42 - `data_seed`: None - `use_cpu`: False - `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 - `dataloader_drop_last`: False - `dataloader_num_workers`: 4 - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `dataloader_prefetch_factor`: None - `remove_unused_columns`: True - `label_names`: None - `train_sampling_strategy`: random - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `ddp_backend`: None - `ddp_timeout`: 1800 - `fsdp`: [] - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `deepspeed`: None - `debug`: [] - `skip_memory_metrics`: True - `do_predict`: False - `resume_from_checkpoint`: None - `warmup_ratio`: None - `local_rank`: -1 - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | Validation Loss | eval_cosine_ndcg@10 | |:--------:|:-------:|:-------------:|:---------------:|:-------------------:| | 0.5 | 10 | 1.5380 | - | - | | 1.0 | 20 | 1.4167 | 0.9702 | 0.7440 | | 1.5 | 30 | 1.4515 | - | - | | 2.0 | 40 | 1.3789 | 0.9269 | 0.7499 | | 2.5 | 50 | 1.3920 | - | - | | 3.0 | 60 | 1.2849 | 0.8898 | 0.7581 | | 3.5 | 70 | 1.3585 | - | - | | 4.0 | 80 | 1.2197 | 0.8572 | 0.7653 | | 4.5 | 90 | 1.2825 | - | - | | 5.0 | 100 | 1.2078 | 0.8350 | 0.7686 | | 5.5 | 110 | 1.2496 | - | - | | 6.0 | 120 | 1.1569 | 0.8104 | 0.7720 | | 6.5 | 130 | 1.2119 | - | - | | 7.0 | 140 | 1.1278 | 0.7952 | 0.7754 | | 7.5 | 150 | 1.1812 | - | - | | 8.0 | 160 | 1.1018 | 0.7835 | 0.7770 | | 8.5 | 170 | 1.1696 | - | - | | 9.0 | 180 | 1.0972 | 0.7788 | 0.7786 | | 9.5 | 190 | 1.1655 | - | - | | **10.0** | **200** | **1.0796** | **0.7755** | **0.7789** | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.12.12 - Sentence Transformers: 5.3.0 - Transformers: 5.3.0 - PyTorch: 2.10.0+cu128 - Accelerate: 1.13.0 - Datasets: 4.8.2 - Tokenizers: 0.22.2 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### CachedMultipleNegativesRankingLoss ```bibtex @misc{gao2021scaling, title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup}, author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan}, year={2021}, eprint={2101.06983}, archivePrefix={arXiv}, primaryClass={cs.LG} } ```