| | --- |
| | language: |
| | - en |
| | tags: |
| | - unsloth |
| | - sentence-transformers |
| | - sentence-similarity |
| | - feature-extraction |
| | - dense |
| | - generated_from_trainer |
| | - dataset_size:1375067 |
| | - loss:MultipleNegativesRankingLoss |
| | base_model: unsloth/all-MiniLM-L6-v2 |
| | widget: |
| | - source_sentence: "Modify the inner parameters of the Kepler propagator in order\ |
| | \ to place\n the spacecraft in the right Sphere of Influence" |
| | sentences: |
| | - "func (c *Conn) SetDeadline(t time.Time) error {\n\treturn c.p.SetDeadline(t)\n\ |
| | }" |
| | - "def _change_soi(self, body):\n \n\n if body == self.central:\n\ |
| | \ self.bodies = [self.central]\n self.step = self.central_step\n\ |
| | \ self.active = self.central.name\n self.frame = self.central.name\n\ |
| | \ else:\n soi = self.SOI[body.name]\n self.bodies\ |
| | \ = [body]\n self.step = self.alt_step\n self.active = body.name\n\ |
| | \ self.frame = soi.frame" |
| | - "def main(args=None):\n \"\"\"\"\"\"\n parser = _parser()\n\n # Python\ |
| | \ 2 will error 'too few arguments' if no subcommand is supplied.\n # No such\ |
| | \ error occurs in Python 3, which makes it feasible to check\n # whether a\ |
| | \ subcommand was provided (displaying a help message if not).\n # argparse\ |
| | \ internals vary significantly over the major versions, so it's\n # much easier\ |
| | \ to just override the args passed to it. In this case, print\n # the usage\ |
| | \ message if there are no args.\n if args is None and len(sys.argv) <= 1:\n\ |
| | \ sys.argv.append('--help')\n\n options = parser.parse_args(args)\n\n\ |
| | \ # pass options to subcommand\n options.func(options)\n\n return 0" |
| | - source_sentence: 'Load image from path. |
| | |
| | |
| | @param path Path to image. |
| | |
| | @return Image |
| | |
| | @throws java.io.IOException |
| | |
| | |
| | @throws NullPointerException if {@code path} is null.' |
| | sentences: |
| | - "public function admin_modal_bail( $item_id, $item_title, $field_args ) {\n\n\t\ |
| | \t$model_data = $this->build_dfv_field_item_data_recurse_item( $item_id, $item_title,\ |
| | \ $field_args );\n\t\t?>\n\t\t\t<script type=\"text/javascript\">\n\t\t\t\twindow.parent.jQuery(\ |
| | \ window.parent ).trigger(\n\t\t\t\t\t'dfv:modal:update',\n\t\t\t\t\t<?php echo\ |
| | \ wp_json_encode( $model_data, JSON_HEX_TAG ); ?>\n\t\t\t\t);\n\t\t\t</script>\n\ |
| | \t\t<?php\n\n\t\tdie();\n\n\t}" |
| | - "private Image loadImage(Resource path) throws IOException {\n\t\tURL url = path.getURL();\n\ |
| | \t\tif (url == null) {\n\t\t\tlogger.warn(\"Unable to locate splash screen in\ |
| | \ classpath at: \" + path);\n\t\t\treturn null;\n\t\t}\n\t\treturn Toolkit.getDefaultToolkit().createImage(url);\n\ |
| | \t}" |
| | - "def generate_wakeword_pieces(self, volume):\n \"\"\"\"\"\"\n while\ |
| | \ True:\n target = 1 if random() > 0.5 else 0\n it = self.pos_files_it\ |
| | \ if target else self.neg_files_it\n sample_file = next(it)\n \ |
| | \ yield self.layer_with(self.normalize_volume_to(load_audio(sample_file),\ |
| | \ volume), target)\n yield self.layer_with(np.zeros(int(pr.sample_rate\ |
| | \ * (0.5 + 2.0 * random()))), 0)" |
| | - source_sentence: // StartPlugins starts all plugins in the correct order. |
| | sentences: |
| | - "func (co *Coordinator) StartPlugins() {\n\t// Launch routers\n\tfor _, router\ |
| | \ := range co.routers {\n\t\tlogrus.Debug(\"Starting \", reflect.TypeOf(router))\n\ |
| | \t\tif err := router.Start(); err != nil {\n\t\t\tlogrus.WithError(err).Errorf(\"\ |
| | Failed to start router of type '%s'\", reflect.TypeOf(router))\n\t\t}\n\t}\n\n\ |
| | \t// Launch producers\n\tco.state = coordinatorStateStartProducers\n\tfor _, producer\ |
| | \ := range co.producers {\n\t\tproducer := producer\n\t\tgo tgo.WithRecoverShutdown(func()\ |
| | \ {\n\t\t\tlogrus.Debug(\"Starting \", reflect.TypeOf(producer))\n\t\t\tproducer.Produce(co.producerWorker)\n\ |
| | \t\t})\n\t}\n\n\t// Set final log target and purge the intermediate buffer\n\t\ |
| | if core.StreamRegistry.IsStreamRegistered(core.LogInternalStreamID) {\n\t\t//\ |
| | \ The _GOLLUM_ stream has listeners, so use LogConsumer to write to it\n\t\tif\ |
| | \ *flagLogColors == \"always\" {\n\t\t\tlogrus.SetFormatter(logger.NewConsoleFormatter())\n\ |
| | \t\t}\n\t\tlogrusHookBuffer.SetTargetHook(co.logConsumer)\n\t\tlogrusHookBuffer.Purge()\n\ |
| | \n\t} else {\n\t\tlogrusHookBuffer.SetTargetWriter(logger.FallbackLogDevice)\n\ |
| | \t\tlogrusHookBuffer.Purge()\n\t}\n\n\t// Launch consumers\n\tco.state = coordinatorStateStartConsumers\n\ |
| | \tfor _, consumer := range co.consumers {\n\t\tconsumer := consumer\n\t\tgo tgo.WithRecoverShutdown(func()\ |
| | \ {\n\t\t\tlogrus.Debug(\"Starting \", reflect.TypeOf(consumer))\n\t\t\tconsumer.Consume(co.consumerWorker)\n\ |
| | \t\t})\n\t}\n}" |
| | - "def __add_symbols(self, cmd):\n \n\n if self.__config.define_symbols:\n\ |
| | \ symbols = self.__config.define_symbols\n cmd.append(''.join(\n\ |
| | \ [' -D\"%s\"' % def_symbol for def_symbol in symbols]))\n\n \ |
| | \ if self.__config.undefine_symbols:\n un_symbols = self.__config.undefine_symbols\n\ |
| | \ cmd.append(''.join(\n [' -U\"%s\"' % undef_symbol\ |
| | \ for undef_symbol in un_symbols]))\n\n return cmd" |
| | - "protected function addReview()\n {\n if (!$this->isError()) {\n \ |
| | \ $id = $this->review->add($this->getSubmitted());\n if (empty($id))\ |
| | \ {\n $this->errorAndExit($this->text('Unexpected result'));\n\ |
| | \ }\n $this->line($id);\n }\n }" |
| | - source_sentence: Modifies the result of each promise from a scalar value to a object |
| | containing its fieldname |
| | sentences: |
| | - "public void assertUniqueBeans(Set<String> ignoredDuplicateBeanNames) {\n\t\t\ |
| | for (BeanohBeanFactoryMethodInterceptor callback : callbacks) {\n\t\t\tMap<String,\ |
| | \ List<BeanDefinition>> beanDefinitionMap = callback\n\t\t\t\t\t.getBeanDefinitionMap();\n\ |
| | \t\t\tfor (String key : beanDefinitionMap.keySet()) {\n\t\t\t\tif (!ignoredDuplicateBeanNames.contains(key))\ |
| | \ {\n\t\t\t\t\tList<BeanDefinition> definitions = beanDefinitionMap\n\t\t\t\t\t\ |
| | \t\t.get(key);\n\t\t\t\t\tList<String> resourceDescriptions = new ArrayList<String>();\n\ |
| | \t\t\t\t\tfor (BeanDefinition definition : definitions) {\n\t\t\t\t\t\tString\ |
| | \ resourceDescription = definition\n\t\t\t\t\t\t\t\t.getResourceDescription();\n\ |
| | \t\t\t\t\t\tif (resourceDescription == null) {\n\t\t\t\t\t\t\tresourceDescriptions.add(definition.getBeanClassName());\n\ |
| | \t\t\t\t\t\t}else if (!resourceDescription\n\t\t\t\t\t\t\t\t.endsWith(\"-BeanohContext.xml]\"\ |
| | )) {\n\t\t\t\t\t\t\tif(!resourceDescriptions.contains(resourceDescription)){\n\ |
| | \t\t\t\t\t\t\t\tresourceDescriptions.add(resourceDescription);\n\t\t\t\t\t\t\t\ |
| | }\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t\tif (resourceDescriptions.size() > 1)\ |
| | \ {\n\t\t\t\t\t\tthrow new DuplicateBeanDefinitionException(\"Bean '\"\n\t\t\t\ |
| | \t\t\t\t\t+ key + \"' was defined \"\n\t\t\t\t\t\t\t\t+ resourceDescriptions.size()\ |
| | \ + \" times.\\n\"\n\t\t\t\t\t\t\t\t+ \"Either remove duplicate bean definitions\ |
| | \ or ignore them with the 'ignoredDuplicateBeanNames' method.\\n\"\n\t\t\t\t\t\ |
| | \t\t\t+ \"Configuration locations:\"\n\t\t\t\t\t\t\t\t+ messageUtil.list(resourceDescriptions));\n\ |
| | \t\t\t\t\t}\n\t\t\t\t}\n\t\t\t}\n\t\t}\n\t}" |
| | - "function wrap(fieldName, promise, args) {\n return promise(args).then((result)\ |
| | \ => ({\n [fieldName]: result,\n }));\n}" |
| | - "func Convert_kops_LyftVPCNetworkingSpec_To_v1alpha1_LyftVPCNetworkingSpec(in\ |
| | \ *kops.LyftVPCNetworkingSpec, out *LyftVPCNetworkingSpec, s conversion.Scope)\ |
| | \ error {\n\treturn autoConvert_kops_LyftVPCNetworkingSpec_To_v1alpha1_LyftVPCNetworkingSpec(in,\ |
| | \ out, s)\n}" |
| | - source_sentence: '<p> |
| | |
| | User-supplied properties in key-value form. |
| | |
| | </p> |
| | |
| | |
| | @param parameters |
| | |
| | User-supplied properties in key-value form. |
| | |
| | @return Returns a reference to this object so that method calls can be chained |
| | together.' |
| | sentences: |
| | - "public static function unserializeFromStringRepresentation($string)\n {\n\ |
| | \ if (!preg_match('~k:(?P<k>\\d+)/m:(?P<m>\\d+)\\((?P<bitfield>[0-9a-zA-Z+/=]+)\\\ |
| | )~', $string, $matches)) {\n throw new InvalidArgumentException('Invalid\ |
| | \ string representation');\n }\n $bf = new self((int) $matches['m'],\ |
| | \ (int) $matches['k']);\n $bf->bitField = base64_decode($matches['bitfield']);\n\ |
| | \ return $bf;\n }" |
| | - "public static function flushEventListeners()\n {\n if (! isset(static::$dispatcher))\ |
| | \ {\n return;\n }\n\n $instance = new static;\n\n \ |
| | \ foreach ($instance->getObservableEvents() as $event) {\n static::$dispatcher->forget(\"\ |
| | eloquent.{$event}: \".static::class);\n }\n\n foreach (array_values($instance->dispatchesEvents)\ |
| | \ as $event) {\n static::$dispatcher->forget($event);\n }\n\ |
| | \ }" |
| | - "public StorageDescriptor withParameters(java.util.Map<String, String> parameters)\ |
| | \ {\n setParameters(parameters);\n return this;\n }" |
| | datasets: |
| | - sentence-transformers/codesearchnet |
| | pipeline_tag: sentence-similarity |
| | library_name: sentence-transformers |
| | --- |
| | |
| | # SentenceTransformer |
| |
|
| | This model was finetuned with [Unsloth](https://github.com/unslothai/unsloth). |
| |
|
| | [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
| | based on unsloth/all-MiniLM-L6-v2 |
| |
|
| | This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [unsloth/all-MiniLM-L6-v2](https://huggingface.co/unsloth/all-MiniLM-L6-v2) on the [codesearchnet](https://huggingface.co/datasets/sentence-transformers/codesearchnet) dataset. 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:** [unsloth/all-MiniLM-L6-v2](https://huggingface.co/unsloth/all-MiniLM-L6-v2) <!-- at revision 0f79ca30c044e92859f5852d3a29fb6e976741cd --> |
| | - **Maximum Sequence Length:** 256 tokens |
| | - **Output Dimensionality:** 384 dimensions |
| | - **Similarity Function:** Cosine Similarity |
| | - **Training Dataset:** |
| | - [codesearchnet](https://huggingface.co/datasets/sentence-transformers/codesearchnet) |
| | - **Language:** en |
| | <!-- - **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': 'PeftModelForFeatureExtraction'}) |
| | (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("sentence_transformers_model_id") |
| | # Run inference |
| | sentences = [ |
| | '<p>\nUser-supplied properties in key-value form.\n</p>\n\n@param parameters\nUser-supplied properties in key-value form.\n@return Returns a reference to this object so that method calls can be chained together.', |
| | 'public StorageDescriptor withParameters(java.util.Map<String, String> parameters) {\n setParameters(parameters);\n return this;\n }', |
| | "public static function unserializeFromStringRepresentation($string)\n {\n if (!preg_match('~k:(?P<k>\\d+)/m:(?P<m>\\d+)\\((?P<bitfield>[0-9a-zA-Z+/=]+)\\)~', $string, $matches)) {\n throw new InvalidArgumentException('Invalid string representation');\n }\n $bf = new self((int) $matches['m'], (int) $matches['k']);\n $bf->bitField = base64_decode($matches['bitfield']);\n return $bf;\n }", |
| | ] |
| | 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, 0.6597, -0.0469], |
| | # [ 0.6597, 1.0000, 0.0107], |
| | # [-0.0469, 0.0107, 1.0000]], dtype=torch.float16) |
| | ``` |
| |
|
| | <!-- |
| | ### 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 |
| |
|
| | #### codesearchnet |
| |
|
| | * Dataset: [codesearchnet](https://huggingface.co/datasets/sentence-transformers/codesearchnet) at [079a958](https://huggingface.co/datasets/sentence-transformers/codesearchnet/tree/079a958b01dc87cf07b66a68414c4b4196d889cc) |
| | * Size: 1,375,067 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: 4 tokens</li><li>mean: 29.95 tokens</li><li>max: 127 tokens</li></ul> | <ul><li>min: 28 tokens</li><li>mean: 131.03 tokens</li><li>max: 256 tokens</li></ul> | |
| | * Samples: |
| | | anchor | positive | |
| | |:-----------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| | | <code>Computes the new parent id for the node being moved.<br><br>@return int</code> | <code>protected function parentId()<br> {<br> switch ( $this->position )<br> {<br> case 'root':<br> return null;<br><br> case 'child':<br> return $this->target->getKey();<br><br> default:<br> return $this->target->getParentId();<br> }<br> }</code> | |
| | | <code>// SetWinSize overwrites the playlist's window size.</code> | <code>func (p *MediaPlaylist) SetWinSize(winsize uint) error {<br> if winsize > p.capacity {<br> return errors.New("capacity must be greater than winsize or equal")<br> }<br> p.winsize = winsize<br> return nil<br>}</code> | |
| | | <code>Show the sidebar and squish the container to make room for the sidebar.<br>If hideOthers is true, hide other open sidebars.</code> | <code>function() {<br> var options = this.options;<br><br> if (options.hideOthers) {<br> this.secondary.each(function() {<br> var sidebar = $(this);<br><br> if (sidebar.hasClass('is-expanded')) {<br> sidebar.toolkit('offCanvas', 'hide');<br> }<br> });<br> }<br><br> this.fireEvent('showing');<br><br> this.container.addClass('move-' + this.opposite);<br><br> this.element<br> .reveal()<br> .addClass('is-expanded')<br> .aria('expanded', true);<br><br> if (options.stopScroll) {<br> $('body').addClass('no-scroll');<br> }<br><br> this.fireEvent('shown');<br> }</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 |
| | - `gradient_accumulation_steps`: 4 |
| | - `learning_rate`: 0.0002 |
| | - `num_train_epochs`: 2 |
| | - `warmup_ratio`: 0.03 |
| | - `fp16`: True |
| | - `batch_sampler`: no_duplicates |
| | |
| | #### 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`: 4 |
| | - `eval_accumulation_steps`: None |
| | - `torch_empty_cache_steps`: None |
| | - `learning_rate`: 0.0002 |
| | - `weight_decay`: 0.0 |
| | - `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`: linear |
| | - `lr_scheduler_kwargs`: {} |
| | - `warmup_ratio`: 0.03 |
| | - `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 |
| | - `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 |
| | - `project`: huggingface |
| | - `trackio_space_id`: trackio |
| | - `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`: no |
| | - `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`: True |
| | - `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 | |
| | |:------:|:----:|:-------------:| |
| | | 0.0186 | 50 | 0.5333 | |
| | | 0.0372 | 100 | 0.3948 | |
| | | 0.0559 | 150 | 0.311 | |
| | | 0.0745 | 200 | 0.2721 | |
| | | 0.0931 | 250 | 0.2809 | |
| | | 0.1117 | 300 | 0.2533 | |
| | | 0.1303 | 350 | 0.2472 | |
| | | 0.1489 | 400 | 0.2378 | |
| | | 0.1676 | 450 | 0.2383 | |
| | | 0.1862 | 500 | 0.2239 | |
| | | 0.2048 | 550 | 0.2236 | |
| | | 0.2234 | 600 | 0.2191 | |
| | | 0.2420 | 650 | 0.2248 | |
| | | 0.2606 | 700 | 0.2176 | |
| | | 0.2793 | 750 | 0.2171 | |
| | | 0.2979 | 800 | 0.2114 | |
| | | 0.3165 | 850 | 0.222 | |
| | | 0.3351 | 900 | 0.2066 | |
| | | 0.3537 | 950 | 0.2059 | |
| | | 0.3723 | 1000 | 0.2053 | |
| | | 0.3910 | 1050 | 0.2011 | |
| | | 0.4096 | 1100 | 0.2024 | |
| | | 0.4282 | 1150 | 0.2006 | |
| | | 0.4468 | 1200 | 0.1976 | |
| | | 0.4654 | 1250 | 0.1968 | |
| | | 0.4840 | 1300 | 0.195 | |
| | | 0.5027 | 1350 | 0.1921 | |
| | | 0.5213 | 1400 | 0.1967 | |
| | | 0.5399 | 1450 | 0.1895 | |
| | | 0.5585 | 1500 | 0.1864 | |
| | | 0.5771 | 1550 | 0.189 | |
| | | 0.5957 | 1600 | 0.1857 | |
| | | 0.6144 | 1650 | 0.1889 | |
| | | 0.6330 | 1700 | 0.1796 | |
| | | 0.6516 | 1750 | 0.1718 | |
| | | 0.6702 | 1800 | 0.1866 | |
| | | 0.6888 | 1850 | 0.1874 | |
| | | 0.7074 | 1900 | 0.178 | |
| | | 0.7261 | 1950 | 0.1763 | |
| | | 0.7447 | 2000 | 0.1734 | |
| | | 0.7633 | 2050 | 0.1823 | |
| | | 0.7819 | 2100 | 0.1796 | |
| | | 0.8005 | 2150 | 0.1737 | |
| | | 0.8191 | 2200 | 0.1796 | |
| | | 0.8378 | 2250 | 0.1794 | |
| | | 0.8564 | 2300 | 0.1703 | |
| | | 0.8750 | 2350 | 0.1746 | |
| | | 0.8936 | 2400 | 0.1864 | |
| | | 0.9122 | 2450 | 0.173 | |
| | | 0.9308 | 2500 | 0.1729 | |
| | | 0.9495 | 2550 | 0.1742 | |
| | | 0.9681 | 2600 | 0.1776 | |
| | | 0.9867 | 2650 | 0.182 | |
| | | 1.0052 | 2700 | 0.1661 | |
| | | 1.0238 | 2750 | 0.1627 | |
| | | 1.0424 | 2800 | 0.158 | |
| | | 1.0611 | 2850 | 0.1585 | |
| | | 1.0797 | 2900 | 0.1555 | |
| | | 1.0983 | 2950 | 0.1566 | |
| | | 1.1169 | 3000 | 0.1511 | |
| | | 1.1355 | 3050 | 0.1557 | |
| | | 1.1541 | 3100 | 0.1589 | |
| | | 1.1728 | 3150 | 0.1545 | |
| | | 1.1914 | 3200 | 0.1567 | |
| | | 1.2100 | 3250 | 0.1561 | |
| | | 1.2286 | 3300 | 0.1515 | |
| | | 1.2472 | 3350 | 0.153 | |
| | | 1.2658 | 3400 | 0.1557 | |
| | | 1.2845 | 3450 | 0.1506 | |
| | | 1.3031 | 3500 | 0.1572 | |
| | | 1.3217 | 3550 | 0.1543 | |
| | | 1.3403 | 3600 | 0.1619 | |
| | | 1.3589 | 3650 | 0.1586 | |
| | | 1.3775 | 3700 | 0.16 | |
| | | 1.3962 | 3750 | 0.1594 | |
| | | 1.4148 | 3800 | 0.1528 | |
| | | 1.4334 | 3850 | 0.1516 | |
| | | 1.4520 | 3900 | 0.1529 | |
| | | 1.4706 | 3950 | 0.149 | |
| | | 1.4892 | 4000 | 0.1572 | |
| | | 1.5079 | 4050 | 0.1505 | |
| | | 1.5265 | 4100 | 0.1552 | |
| | | 1.5451 | 4150 | 0.1488 | |
| | | 1.5637 | 4200 | 0.161 | |
| | | 1.5823 | 4250 | 0.151 | |
| | | 1.6009 | 4300 | 0.1442 | |
| | | 1.6196 | 4350 | 0.1511 | |
| | | 1.6382 | 4400 | 0.1475 | |
| | | 1.6568 | 4450 | 0.1509 | |
| | | 1.6754 | 4500 | 0.1512 | |
| | | 1.6940 | 4550 | 0.1484 | |
| | | 1.7127 | 4600 | 0.1491 | |
| | | 1.7313 | 4650 | 0.143 | |
| | | 1.7499 | 4700 | 0.1479 | |
| | | 1.7685 | 4750 | 0.1459 | |
| | | 1.7871 | 4800 | 0.1434 | |
| | | 1.8057 | 4850 | 0.1475 | |
| | | 1.8244 | 4900 | 0.1485 | |
| | | 1.8430 | 4950 | 0.147 | |
| | | 1.8616 | 5000 | 0.157 | |
| | | 1.8802 | 5050 | 0.1447 | |
| | | 1.8988 | 5100 | 0.1425 | |
| | | 1.9174 | 5150 | 0.1491 | |
| | | 1.9361 | 5200 | 0.1433 | |
| | | 1.9547 | 5250 | 0.1382 | |
| | | 1.9733 | 5300 | 0.1391 | |
| | | 1.9919 | 5350 | 0.1492 | |
| |
|
| | </details> |
| |
|
| | ### Framework Versions |
| | - Python: 3.12.12 |
| | - Sentence Transformers: 5.1.1 |
| | - Transformers: 4.57.1 |
| | - PyTorch: 2.10.0+cu128 |
| | - Accelerate: 1.11.0 |
| | - Datasets: 4.3.0 |
| | - 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.* |
| | --> |
