End of training

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "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
+}

README.md

@@ -0,0 +1,545 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:8118
+- loss:CachedMultipleNegativesRankingLoss
+base_model: answerdotai/ModernBERT-base
+widget:
+- source_sentence: python create path if doesnt exist
+  sentences:
+  - "def clean_whitespace(string, compact=False):\n    \"\"\"Return string with compressed\
+    \ whitespace.\"\"\"\n    for a, b in (('\\r\\n', '\\n'), ('\\r', '\\n'), ('\\\
+    n\\n', '\\n'),\n                 ('\\t', ' '), ('  ', ' ')):\n        string =\
+    \ string.replace(a, b)\n    if compact:\n        for a, b in (('\\n', ' '), ('[\
+    \ ', '['),\n                     ('  ', ' '), ('  ', ' '), ('  ', ' ')):\n   \
+    \         string = string.replace(a, b)\n    return string.strip()"
+  - "def rotateImage(img, angle):\n    \"\"\"\n\n    querries scipy.ndimage.rotate\
+    \ routine\n    :param img: image to be rotated\n    :param angle: angle to be\
+    \ rotated (radian)\n    :return: rotated image\n    \"\"\"\n    imgR = scipy.ndimage.rotate(img,\
+    \ angle, reshape=False)\n    return imgR"
+  - "def check_create_folder(filename):\n    \"\"\"Check if the folder exisits. If\
+    \ not, create the folder\"\"\"\n    os.makedirs(os.path.dirname(filename), exist_ok=True)"
+- source_sentence: how decompiled python code looks like
+  sentences:
+  - "def xeval(source, optimize=True):\n    \"\"\"Compiles to native Python bytecode\
+    \ and runs program, returning the\n    topmost value on the stack.\n\n    Args:\n\
+    \        optimize: Whether to optimize the code after parsing it.\n\n    Returns:\n\
+    \        None: If the stack is empty\n        obj: If the stack contains a single\
+    \ value\n        [obj, obj, ...]: If the stack contains many values\n    \"\"\"\
+    \n    native = xcompile(source, optimize=optimize)\n    return native()"
+  - "def html(header_rows):\n    \"\"\"\n    Convert a list of tuples describing a\
+    \ table into a HTML string\n    \"\"\"\n    name = 'table%d' % next(tablecounter)\n\
+    \    return HtmlTable([map(str, row) for row in header_rows], name).render()"
+  - "def cint8_array_to_numpy(cptr, length):\n    \"\"\"Convert a ctypes int pointer\
+    \ array to a numpy array.\"\"\"\n    if isinstance(cptr, ctypes.POINTER(ctypes.c_int8)):\n\
+    \        return np.fromiter(cptr, dtype=np.int8, count=length)\n    else:\n  \
+    \      raise RuntimeError('Expected int pointer')"
+- source_sentence: python calling pytest from a python script
+  sentences:
+  - "def draw_image(self, ax, image):\n        \"\"\"Process a matplotlib image object\
+    \ and call renderer.draw_image\"\"\"\n        self.renderer.draw_image(imdata=utils.image_to_base64(image),\n\
+    \                                 extent=image.get_extent(),\n               \
+    \                  coordinates=\"data\",\n                                 style={\"\
+    alpha\": image.get_alpha(),\n                                        \"zorder\"\
+    : image.get_zorder()},\n                                 mplobj=image)"
+  - "def test():  # pragma: no cover\n    \"\"\"Execute the unit tests on an installed\
+    \ copy of unyt.\n\n    Note that this function requires pytest to run. If pytest\
+    \ is not\n    installed this function will raise ImportError.\n    \"\"\"\n  \
+    \  import pytest\n    import os\n\n    pytest.main([os.path.dirname(os.path.abspath(__file__))])"
+  - "def is_int(string):\n    \"\"\"\n    Checks if a string is an integer. If the\
+    \ string value is an integer\n    return True, otherwise return False. \n    \n\
+    \    Args:\n        string: a string to test.\n\n    Returns: \n        boolean\n\
+    \    \"\"\"\n    try:\n        a = float(string)\n        b = int(a)\n    except\
+    \ ValueError:\n        return False\n    else:\n        return a == b"
+- source_sentence: python datetime get last day in a month
+  sentences:
+  - "def upgrade(directory, sql, tag, x_arg, revision):\n    \"\"\"Upgrade to a later\
+    \ version\"\"\"\n    _upgrade(directory, revision, sql, tag, x_arg)"
+  - "def flat_list(lst):\n    \"\"\"This function flatten given nested list.\n   \
+    \ Argument:\n        nested list\n    Returns:\n        flat list\n    \"\"\"\n\
+    \    if isinstance(lst, list):\n        for item in lst:\n            for i in\
+    \ flat_list(item):\n                yield i\n    else:\n        yield lst"
+  - "def get_last_weekday_in_month(year, month, weekday):\n        \"\"\"Get the last\
+    \ weekday in a given month. e.g:\n\n        >>> # the last monday in Jan 2013\n\
+    \        >>> Calendar.get_last_weekday_in_month(2013, 1, MON)\n        datetime.date(2013,\
+    \ 1, 28)\n        \"\"\"\n        day = date(year, month, monthrange(year, month)[1])\n\
+    \        while True:\n            if day.weekday() == weekday:\n             \
+    \   break\n            day = day - timedelta(days=1)\n        return day"
+- source_sentence: first duplicate element in list in python
+  sentences:
+  - "def python_mime(fn):\n    \"\"\"\n    Decorator, which adds correct MIME type\
+    \ for python source to the decorated\n    bottle API function.\n    \"\"\"\n \
+    \   @wraps(fn)\n    def python_mime_decorator(*args, **kwargs):\n        response.content_type\
+    \ = \"text/x-python\"\n\n        return fn(*args, **kwargs)\n\n    return python_mime_decorator"
+  - "def purge_duplicates(list_in):\n    \"\"\"Remove duplicates from list while preserving\
+    \ order.\n\n    Parameters\n    ----------\n    list_in: Iterable\n\n    Returns\n\
+    \    -------\n    list\n        List of first occurences in order\n    \"\"\"\n\
+    \    _list = []\n    for item in list_in:\n        if item not in _list:\n   \
+    \         _list.append(item)\n    return _list"
+  - "def getRect(self):\n\t\t\"\"\"\n\t\tReturns the window bounds as a tuple of (x,y,w,h)\n\
+    \t\t\"\"\"\n\t\treturn (self.x, self.y, self.w, self.h)"
+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 answerdotai/ModernBERT-base
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: eval
+      type: eval
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5133037694013304
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7671840354767184
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8370288248337029
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9212860310421286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5133037694013304
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2557280118255728
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1674057649667406
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09212860310421285
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.5133037694013304
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7671840354767184
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8370288248337029
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9212860310421286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7198846730813788
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6550922992996169
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6584728308162124
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on answerdotai/ModernBERT-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base). 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:** [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) <!-- at revision 8949b909ec900327062f0ebf497f51aef5e6f0c8 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 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/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")
+# Run inference
+queries = [
+    "first duplicate element in list in python",
+]
+documents = [
+    'def purge_duplicates(list_in):\n    """Remove duplicates from list while preserving order.\n\n    Parameters\n    ----------\n    list_in: Iterable\n\n    Returns\n    -------\n    list\n        List of first occurences in order\n    """\n    _list = []\n    for item in list_in:\n        if item not in _list:\n            _list.append(item)\n    return _list',
+    'def getRect(self):\n\t\t"""\n\t\tReturns the window bounds as a tuple of (x,y,w,h)\n\t\t"""\n\t\treturn (self.x, self.y, self.w, self.h)',
+    'def python_mime(fn):\n    """\n    Decorator, which adds correct MIME type for python source to the decorated\n    bottle API function.\n    """\n    @wraps(fn)\n    def python_mime_decorator(*args, **kwargs):\n        response.content_type = "text/x-python"\n\n        return fn(*args, **kwargs)\n\n    return python_mime_decorator',
+]
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+# [1, 768] [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+# tensor([[0.7036, 0.1660, 0.1295]])
+```
+
+<!--
+### 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: `eval`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.5133     |
+| cosine_accuracy@3   | 0.7672     |
+| cosine_accuracy@5   | 0.837      |
+| cosine_accuracy@10  | 0.9213     |
+| cosine_precision@1  | 0.5133     |
+| cosine_precision@3  | 0.2557     |
+| cosine_precision@5  | 0.1674     |
+| cosine_precision@10 | 0.0921     |
+| cosine_recall@1     | 0.5133     |
+| cosine_recall@3     | 0.7672     |
+| cosine_recall@5     | 0.837      |
+| cosine_recall@10    | 0.9213     |
+| **cosine_ndcg@10**  | **0.7199** |
+| cosine_mrr@10       | 0.6551     |
+| cosine_map@100      | 0.6585     |
+
+<!--
+## 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: 8,118 training samples
+* Columns: <code>query</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                           | positive                                                                            |
+  |:--------|:--------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                          | string                                                                              |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 9.3 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 35 tokens</li><li>mean: 85.05 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | query                                             | positive                                                                                                                                                                                                                                                                                                                                                                                                  |
+  |:--------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>python code for opening geojson file</code> | <code>def _loadfilepath(self, filepath, **kwargs):<br>        """This loads a geojson file into a geojson python<br>        dictionary using the json module.<br>        <br>        Note: to load with a different text encoding use the encoding argument.<br>        """<br>        with open(filepath, "r") as f:<br>            data = json.load(f, **kwargs)<br>        return data</code>          |
+  | <code>python 3 none compare with int</code>       | <code>def is_natural(x):<br>    """A non-negative integer."""<br>    try:<br>        is_integer = int(x) == x<br>    except (TypeError, ValueError):<br>        return False<br>    return is_integer and x >= 0</code>                                                                                                                                                                                   |
+  | <code>design db memory cache python</code>        | <code>def refresh(self, document):<br>		""" Load a new copy of a document from the database.  does not<br>			replace the old one """<br>		try:<br>			old_cache_size = self.cache_size<br>			self.cache_size = 0<br>			obj = self.query(type(document)).filter_by(mongo_id=document.mongo_id).one()<br>		finally:<br>			self.cache_size = old_cache_size<br>		self.cache_write(obj)<br>		return obj</code> |
+* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](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
+
+#### Unnamed Dataset
+
+* Size: 902 evaluation samples
+* Columns: <code>query</code> and <code>positive</code>
+* Approximate statistics based on the first 902 samples:
+  |         | query                                                                            | positive                                                                            |
+  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                              |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 9.24 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 38 tokens</li><li>mean: 86.55 tokens</li><li>max: 332 tokens</li></ul> |
+* Samples:
+  | query                                                   | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+  |:--------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>how to remove masked items in python array</code> | <code>def ma(self):<br>        """Represent data as a masked array.<br><br>        The array is returned with column-first indexing, i.e. for a data file with<br>        columns X Y1 Y2 Y3 ... the array a will be a[0] = X, a[1] = Y1, ... .<br><br>        inf and nan are filtered via :func:`numpy.isfinite`.<br>        """<br>        a = self.array<br>        return numpy.ma.MaskedArray(a, mask=numpy.logical_not(numpy.isfinite(a)))</code> |
+  | <code>python deepcopy basic type</code>                 | <code>def __deepcopy__(self, memo):<br>        """Improve deepcopy speed."""<br>        return type(self)(value=self._value, enum_ref=self.enum_ref)</code>                                                                                                                                                                                                                                                                                              |
+  | <code>python number of non nan rows in a row</code>     | <code>def count_rows_with_nans(X):<br>    """Count the number of rows in 2D arrays that contain any nan values."""<br>    if X.ndim == 2:<br>        return np.where(np.isnan(X).sum(axis=1) != 0, 1, 0).sum()</code>                                                                                                                                                                                                                                    |
+* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](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`: 5
+- `learning_rate`: 2e-05
+- `warmup_steps`: 0.1
+- `bf16`: True
+- `eval_strategy`: epoch
+- `per_device_eval_batch_size`: 1024
+- `push_to_hub`: True
+- `hub_model_id`: modernbert-cosqa
+- `load_best_model_at_end`: True
+- `dataloader_num_workers`: 4
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `per_device_train_batch_size`: 1024
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `learning_rate`: 2e-05
+- `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
+- `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`: {}
+
+</details>
+
+### Training Logs
+| Epoch   | Step   | Training Loss | Validation Loss | eval_cosine_ndcg@10 |
+|:-------:|:------:|:-------------:|:---------------:|:-------------------:|
+| 1.0     | 8      | -             | 2.3377          | 0.4172              |
+| 1.25    | 10     | 5.9012        | -               | -                   |
+| 2.0     | 16     | -             | 1.3202          | 0.5222              |
+| 2.5     | 20     | 3.4421        | -               | -                   |
+| 3.0     | 24     | -             | 0.8801          | 0.6618              |
+| 3.75    | 30     | 2.3393        | -               | -                   |
+| 4.0     | 32     | -             | 0.7155          | 0.7054              |
+| **5.0** | **40** | **1.9273**    | **0.6707**      | **0.7199**          |
+
+* 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: 4.7.0
+- 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}
+}
+```
+
+<!--
+## 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_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "5.3.0",
+    "pytorch": "2.10.0+cu128"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}