Upload bge-small-code-v1 trained on CoRNStack

1_Pooling/config.json

@@ -0,0 +1,5 @@
+{
+    "embedding_dimension": 384,
+    "pooling_mode": "cls",
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,636 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:200000
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-small-en-v1.5
+widget:
+- source_sentence: Sets the global variables $rects and $origRectSpecs
+  sentences:
+  - "def modify_ranking(tournament):\n    database = TinyDB('db.json')\n    # recuperation\
+    \ de tous les joueurs du tournoi\n    players_table = database.table('players')\n\
+    \    list_players = get_player_list(tournament)\n    # Modification du rang joueur\
+    \ par joueur\n    for player in list_players:\n        new_ranking = view.modify_ranking_view(player)\n\
+    \        players_table.update({'Classement': new_ranking}, doc_ids=[player.doc_id])"
+  - "function setConstants() {\n        const wrapItems = \".image-analysis-wrapper\
+    \ .face-wrap, .image-analysis-wrapper .score-wrap, .image-analysis-wrapper .attribute-wrap,\
+    \ .image-analysis-wrapper .region-block, .image-analysis-wrapper .region-block\
+    \ .word-block .word-wrap\";\n\n        $rects = jQuery(\".image-analysis-wrapper\
+    \ .rectangle\");\n\n        // Iterate over each rectangle and save the width,\
+    \ height, top position,\n        // left position, closest stats block element,\
+    \ and position of the closest\n        // stats block element to an object.  Each\
+    \ object is then added to the \n        // $origRectSpecs array for global use.\n\
+    \        $origRectSpecs = $rects.map(function () {\n            closestWrapItems\
+    \ = jQuery(this).siblings(wrapItems);\n\n            const stats = closestWrapItems.map(function\
+    \ () {\n                return {\n                    origStatTop: jQuery(this).position().top\
+    \ || parseInt(jQuery(this).css(\"top\")),\n                    origStatLeft: jQuery(this).position().left\
+    \ || parseInt(jQuery(this).css(\"left\"))\n                }\n            })\n\
+    \n            return {\n                origRectWidth: jQuery(this).width(),\n\
+    \                origRectHeight: jQuery(this).height(),\n                origRectTop:\
+    \ jQuery(this).position().top || parseInt(jQuery(this).css(\"top\")), // if the\
+    \ rect is on a tab that is currently not displayed it has a position of 0, so\
+    \ this check gets the css instead so we don't lose the value\n               \
+    \ origRectLeft: jQuery(this).position().left || parseInt(jQuery(this).css(\"left\"\
+    )),\n                statBlock: closestWrapItems[0],\n                statPosition:\
+    \ stats[0]\n            }\n        })\n    }"
+  - "reset() {\n\n        // Set the initial crop to match any given fixed aspect\
+    \ ratio (or\n        // default to a square crop 1:1).\n        let aspectRatio\
+    \ = this._initialAspectRatio\n\n        // Calculate the initial crop size such\
+    \ that it fits within the bounds\n        let width = getWidth(this.bounds)\n\
+    \        let height = getWidth(this.bounds) / aspectRatio\n\n        if (aspectRatio\
+    \ < width / getHeight(this.bounds)) {\n            width = getHeight(this.bounds)\
+    \ * aspectRatio\n            height = getHeight(this.bounds)\n        }\n\n  \
+    \      // Calculate the initial crop position to be central to the bounds\n  \
+    \      const x = (getWidth(this.bounds) - width) / 2\n        const y = (getHeight(this.bounds)\
+    \ - height) / 2\n\n        // Set the region\n        this.region = [\n      \
+    \      [x, y],\n            [x + width, y + height]\n        ]\n    }"
+- source_sentence: Returns true if the motor is at its lower limit.
+  sentences:
+  - "def is_lower_limit(self):\n    is_lower = self.get_raw_status() & self.STATUS_LLIM\n\
+    \    return bool(is_lower)"
+  - "def testLowerBound(self,time,accel):\n\t\tif (time - self.timestamp) > ParserSettings.TIME_DELTA:#tests\
+    \ lockout threshold of a flick event\n\t\t\tif accel > self.lower:#tests to see\
+    \ if the flick maximum is met yet, relative to the previous magnitude\n\t\t\t\t\
+    self.timestamp \t= time#set appropriate values when flick triggered\n\t\t\t\t\
+    toReturn \t\t= self.lower\n\t\t\t\tself.lower\t \t= 0#reset flick for next magnitude\
+    \ test\n\t\t\t\treturn toReturn\n\t\t\telse:\n\t\t\t\tself.lower = accel#if no\
+    \ flick yet, update most recent flick to test\n\t\t\t\treturn 0\n\t\telse:\n\t\
+    \t\treturn 0"
+  - "function checkVisibility(message)\n{\n\t// Scroll the view down a certain amount\n\
+    \t$chatlogs.stop().animate({scrollTop: $chatlogs[0].scrollHeight});\n}"
+- source_sentence: Extracts an object of params the given route cares about from the
+    given params object.
+  sentences:
+  - "function getRouteParams(route, params) {\n\t  var routeParams = {};\n\t\n\t \
+    \ if (!route.path) return routeParams;\n\t\n\t  (0, _PatternUtils.getParamNames)(route.path).forEach(function\
+    \ (p) {\n\t    if (Object.prototype.hasOwnProperty.call(params, p)) {\n\t    \
+    \  routeParams[p] = params[p];\n\t    }\n\t  });\n\t\n\t  return routeParams;\n\
+    \t}"
+  - "public static void initImageLoader(Context context) {\n\t\tFile cacheDir = StorageUtils.getCacheDirectory(context);\n\
+    \t\tImageLoaderConfiguration config = new ImageLoaderConfiguration.Builder(context)\n\
+    \t\t\t\t.threadPriority(Thread.NORM_PRIORITY - 2)\n\t\t\t\t.denyCacheImageMultipleSizesInMemory()\
+    \ \n//\t\t\t\t.discCache(new UnlimitedDiscCache(cacheDir)) // default\n\t\t\t\t\
+    .discCacheFileNameGenerator(new Md5FileNameGenerator())\n\t\t\t\t.memoryCache(new\
+    \ LruMemoryCache(2 * 1024 * 1024))\n\t\t\t\t.tasksProcessingOrder(QueueProcessingType.LIFO)\n\
+    \t\t\t\t.writeDebugLogs() // Remove for release app\t\t\t\t\n\t\t\t\t.build();\n\
+    \t\t// Initialize ImageLoader with configuration.\n\t\tImageLoader.getInstance().init(config);\n\
+    \t}"
+  - "function getRouteParams(route, params) {\n\t  var routeParams = {};\n\n\t  if\
+    \ (!route.path) return routeParams;\n\n\t  (0, _PatternUtils.getParamNames)(route.path).forEach(function\
+    \ (p) {\n\t    if (Object.prototype.hasOwnProperty.call(params, p)) {\n\t    \
+    \  routeParams[p] = params[p];\n\t    }\n\t  });\n\n\t  return routeParams;\n\t\
+    }"
+- source_sentence: select all as they all have a class of "section" return array of
+    IDs
+  sentences:
+  - "func (o *BookBuyOK) WriteResponse(rw http.ResponseWriter, producer runtime.Producer)\
+    \ {\n\n\trw.WriteHeader(200)\n\tif o.Payload != nil {\n\t\tpayload := o.Payload\n\
+    \t\tif err := producer.Produce(rw, payload); err != nil {\n\t\t\tpanic(err) //\
+    \ let the recovery middleware deal with this\n\t\t}\n\t}\n}"
+  - "function getMenuCLassesIDs()\n    {\n        let IdsArray = [];\n        const\
+    \ elements = document.querySelectorAll('.banner,.section');\n        for(const\
+    \ elm of elements)\n            {\n                IdsArray.push(elm.id);\n  \
+    \          }\n        \n        return IdsArray;\n    }"
+  - "getAllSectionsForRegion(region) {\n        if (!region) {\n            return\
+    \ null;\n        }\n        return region.getElementsByClassName(A11yClassNames.SECTION);\n\
+    \    }"
+- source_sentence: For component xyz, returns "xyz[]"
+  sentences:
+  - "public String toString() {\n\t    \tif(size == 0) {\n\t    \t\treturn \"[]\"\
+    ;\n\t    \t}else {\n\t    \t\t\n\t    \t\tString result = \"[\" + elementData[0];\n\
+    \t    \t\tfor(int i = 1; i < size; i++) {\n\t    \t\t\tresult += \", \" + elementData[i];\n\
+    \t    \t\t}\n\t    \t\t\n\t    \t\tresult += \"]\";\n\t    \t\t\n\t    \t\treturn\
+    \ result;\n\t    \t}\n\t    }"
+  - "def masterPath(self):\n\t\treturn fl.File( self._path + '/master.data' )"
+  - "private static final String getArrayTypeName(String typeName) {\n    final String\
+    \ arrayTypeName = builtInArrayComponentName2ArrayTypeName.get(typeName);\n   \
+    \ return (null == arrayTypeName) ? typeName + ARRAY_TYPE_SUFFIX : arrayTypeName;\n\
+    \  }"
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- 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@1
+- cosine_mrr@5
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on BAAI/bge-small-en-v1.5
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: cornstack eval
+      type: cornstack_eval
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.726
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@5
+      value: 0.886
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.918
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.726
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.282
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1772
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0918
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.726
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.846
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.886
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.918
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8243332358785
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@1
+      value: 0.726
+      name: Cosine Mrr@1
+    - type: cosine_mrr@5
+      value: 0.7892999999999997
+      name: Cosine Mrr@5
+    - type: cosine_mrr@10
+      value: 0.7939428571428567
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7966106003908411
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on BAAI/bge-small-en-v1.5
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for retrieval.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) <!-- at revision 5c38ec7c405ec4b44b94cc5a9bb96e735b38267a -->
+- **Maximum Sequence Length:** 384 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Supported Modality:** Text
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### 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({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
+  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'cls', '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
+queries = [
+    'For component xyz, returns "xyz[]"',
+]
+documents = [
+    'private static final String getArrayTypeName(String typeName) {\n    final String arrayTypeName = builtInArrayComponentName2ArrayTypeName.get(typeName);\n    return (null == arrayTypeName) ? typeName + ARRAY_TYPE_SUFFIX : arrayTypeName;\n  }',
+    'public String toString() {\n\t    \tif(size == 0) {\n\t    \t\treturn "[]";\n\t    \t}else {\n\t    \t\t\n\t    \t\tString result = "[" + elementData[0];\n\t    \t\tfor(int i = 1; i < size; i++) {\n\t    \t\t\tresult += ", " + elementData[i];\n\t    \t\t}\n\t    \t\t\n\t    \t\tresult += "]";\n\t    \t\t\n\t    \t\treturn result;\n\t    \t}\n\t    }',
+]
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+# [1, 384] [2, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+# tensor([[0.4896, 0.4966]])
+```
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Dataset: `cornstack_eval`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.sentence_transformer.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.726      |
+| cosine_accuracy@5   | 0.886      |
+| cosine_accuracy@10  | 0.918      |
+| cosine_precision@1  | 0.726      |
+| cosine_precision@3  | 0.282      |
+| cosine_precision@5  | 0.1772     |
+| cosine_precision@10 | 0.0918     |
+| cosine_recall@1     | 0.726      |
+| cosine_recall@3     | 0.846      |
+| cosine_recall@5     | 0.886      |
+| cosine_recall@10    | 0.918      |
+| **cosine_ndcg@10**  | **0.8243** |
+| cosine_mrr@1        | 0.726      |
+| cosine_mrr@5        | 0.7893     |
+| cosine_mrr@10       | 0.7939     |
+| cosine_map@100      | 0.7966     |
+
+<!--
+## 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: 200,000 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 100 samples:
+  |          | anchor                                                                             | positive                                                                             | negative                                                                             |
+  |:---------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type     | string                                                                             | string                                                                               | string                                                                               |
+  | modality | text                                                                               | text                                                                                 | text                                                                                 |
+  | details  | <ul><li>min: 6 tokens</li><li>mean: 19.83 tokens</li><li>max: 105 tokens</li></ul> | <ul><li>min: 21 tokens</li><li>mean: 139.33 tokens</li><li>max: 384 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 100.52 tokens</li><li>max: 384 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                          | positive                                                                                                                                                                                                                                                  | negative                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+  |:--------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Fades all outputs to the given color and waits for it to complete.</code>                                                 | <code>def FadeOutputs(box, color, steps=50):<br>  for output in box:<br>    output.Fade(color=color, steps=steps)<br>  time.sleep(steps / (float(box.frequency) / len(box)))</code>                                                                       | <code>def _colour_loop(self, colours, seconds=None, milliseconds=None, fade=True):<br>        colours = self.convert_to_colour_list(colours) #Forces a list of colours into an actual python list<br>        if len(colours)<2:<br>            colours.append("#000000") #Blink between black and the specified colour if only one provided<br>        <br>        #Start with the first colour immediately:<br>        if fade:<br>            self.fade(colours[0])<br>        else:<br>            self.set(colours[0])<br>        step_time = self.clean_time_in_milliseconds(seconds, milliseconds, default_seconds=1, minimum_milliseconds=50)<br>        <br>        #Do the loop<br>        i = 1 #We're moving to the second colour now<br>        total_colours = len(colours)<br>        while not self._sequence_stop_signal:<br>            #Resolve our colour<br>            next_colour = colours[i]<br>            i = (i+1) % total_colours #ensures we are never asking for more colours than provided<br>            if fade: #Fading is a blocking process, thus we let the fade l...</code> |
+  | <code>Sets the additional element count if buffer resize is required, defaults to initialElementCount of factory method.</code> | <code>public void setResizeElementCount(int v) { vboSet.setResizeElementCount(v); }</code>                                                                                                                                                                | <code>public int getResizeElementCount() { return vboSet.getResizeElementCount(); }</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+  | <code>delete a specific incident</code>                                                                                         | <code>def delete_specific_incident(self, incident_id):<br>        self.cursor.execute("""DELETE FROM incidents WHERE incident_id ='%s' AND status='draft'<br>        """ %(incident_id))<br>        self.commiting()<br>        return incident_id</code> | <code>def delete(openstack_resource):<br>    openstack_resource.delete()</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          384,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1.0,
+          1.0,
+          1.0,
+          1.0
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 32
+- `gradient_accumulation_steps`: 2
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.05
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 8
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-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`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: None
+- `warmup_ratio`: 0.05
+- `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
+| Epoch | Step | Training Loss | cornstack_eval_cosine_ndcg@10 |
+|:-----:|:----:|:-------------:|:-----------------------------:|
+| 0.016 | 50   | 6.8957        | -                             |
+| 0.032 | 100  | 5.8104        | -                             |
+| 0.048 | 150  | 5.3881        | -                             |
+| 0.064 | 200  | 5.1643        | -                             |
+| 0.08  | 250  | 5.1469        | -                             |
+| 0.096 | 300  | 4.8455        | -                             |
+| 0.112 | 350  | 4.9429        | -                             |
+| 0.128 | 400  | 5.0664        | -                             |
+| 0.144 | 450  | 4.6627        | -                             |
+| 0.16  | 500  | 4.686         | -                             |
+| 0.176 | 550  | 4.643         | -                             |
+| 0.192 | 600  | 4.4053        | -                             |
+| 0.208 | 650  | 4.5371        | -                             |
+| 0.224 | 700  | 4.5435        | -                             |
+| 0.24  | 750  | 4.432         | -                             |
+| 0.256 | 800  | 4.4243        | -                             |
+| 0.272 | 850  | 4.2231        | -                             |
+| 0.288 | 900  | 4.2622        | -                             |
+| 0.304 | 950  | 4.3597        | -                             |
+| 0.32  | 1000 | 4.2547        | 0.8176                        |
+| 0.336 | 1050 | 4.2443        | -                             |
+| 0.352 | 1100 | 4.4695        | -                             |
+| 0.368 | 1150 | 4.3728        | -                             |
+| 0.384 | 1200 | 4.3351        | -                             |
+| 0.4   | 1250 | 3.9853        | -                             |
+| 0.416 | 1300 | 4.2823        | -                             |
+| 0.432 | 1350 | 4.1293        | -                             |
+| 0.448 | 1400 | 4.1029        | -                             |
+| 0.464 | 1450 | 4.1758        | -                             |
+| 0.48  | 1500 | 4.1655        | -                             |
+| 0.496 | 1550 | 4.0803        | -                             |
+| 0.512 | 1600 | 4.1985        | -                             |
+| 0.528 | 1650 | 4.0523        | -                             |
+| 0.544 | 1700 | 4.1011        | -                             |
+| 0.56  | 1750 | 4.2448        | -                             |
+| 0.576 | 1800 | 4.0936        | -                             |
+| 0.592 | 1850 | 3.9888        | -                             |
+| 0.608 | 1900 | 4.1434        | -                             |
+| 0.624 | 1950 | 3.9789        | -                             |
+| 0.64  | 2000 | 3.9967        | 0.8271                        |
+| 0.656 | 2050 | 4.0894        | -                             |
+| 0.672 | 2100 | 3.8938        | -                             |
+| 0.688 | 2150 | 4.0384        | -                             |
+| 0.704 | 2200 | 4.1308        | -                             |
+| 0.72  | 2250 | 3.864         | -                             |
+| 0.736 | 2300 | 4.0325        | -                             |
+| 0.752 | 2350 | 3.8263        | -                             |
+| 0.768 | 2400 | 3.9559        | -                             |
+| 0.784 | 2450 | 3.7323        | -                             |
+| 0.8   | 2500 | 3.7366        | -                             |
+| 0.816 | 2550 | 3.9768        | -                             |
+| 0.832 | 2600 | 3.9144        | -                             |
+| 0.848 | 2650 | 3.9013        | -                             |
+| 0.864 | 2700 | 3.9211        | -                             |
+| 0.88  | 2750 | 3.9616        | -                             |
+| 0.896 | 2800 | 3.9926        | -                             |
+| 0.912 | 2850 | 3.9388        | -                             |
+| 0.928 | 2900 | 3.8664        | -                             |
+| 0.944 | 2950 | 3.8747        | -                             |
+| 0.96  | 3000 | 4.0419        | 0.8243                        |
+| 0.976 | 3050 | 3.9493        | -                             |
+| 0.992 | 3100 | 3.8626        | -                             |
+
+
+### Training Time
+- **Training**: 28.8 minutes
+- **Evaluation**: 1.7 seconds
+- **Total**: 28.9 minutes
+
+### Framework Versions
+- Python: 3.13.7
+- Sentence Transformers: 5.6.0
+- Transformers: 4.57.6
+- PyTorch: 2.12.1+cu126
+- Accelerate: 1.13.0
+- Datasets: 4.8.5
+- 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{oord2019representationlearningcontrastivepredictive,
+      title={Representation Learning with Contrastive Predictive Coding},
+      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
+      year={2019},
+      eprint={1807.03748},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/1807.03748},
+}
+```
+
+<!--
+## 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.*
+-->

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.12.1+cu126",
+    "sentence_transformers": "5.6.0",
+    "transformers": "4.57.6"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "document": "",
+    "query": ""
+  },
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04111955164b477f35283de97552792193325b72852368061c70d0a9861a6e41
+size 133462128

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 384,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}