Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

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

README.md

@@ -0,0 +1,740 @@
+---
+base_model: intfloat/multilingual-e5-small
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2871
+- loss:OnlineContrastiveLoss
+widget:
+- source_sentence: Stages of photosynthesis
+  sentences:
+  - The function helps preprocess your entire dataset at once.
+  - You can create an index for your dataset by using [Dataset.add_faiss_index()](/docs/datasets/v2.10.0/en/package_reference/main_classes#datasets.Dataset.add_faiss_index)
+    or [Dataset.add_elasticsearch_index()](/docs/datasets/v2.10.0/en/package_reference/main_classes#datasets.Dataset.add_elasticsearch_index)
+    depending on the system you want to use.
+  - What is photosynthesis?
+- source_sentence: Steps to erase internet history
+  sentences:
+  - How do I delete my browsing history?
+  - Yes, there is a reference section available in 🤗 Datasets documentation. It covers
+    main classes, builder classes, loading methods, table classes, logging methods,
+    and task templates.
+  - What is the tallest building in New York City?
+- source_sentence: The `StreamingDownloadManager` class is a download manager that
+    employs the "::" separator to traverse (possibly remote) compressed files.
+  sentences:
+  - What is the role of a business plan in entrepreneurship?
+  - The Hugging Face datasets library's default handler can be disabled to prevent
+    double logging by calling the `datasets.utils.logging.enable_propagation()` function.
+  - The `StreamingDownloadManager` class is a download manager that uses the ”::”
+    separator to navigate through (possibly remote) compressed archives.
+- source_sentence: Using torch.utils.data.DataLoader, you can package the dataset
+    and craft a collate function to group the samples into batches.
+  sentences:
+  - Why does understanding death philosophical?
+  - The `_generate_examples` method is used to access and yield TAR files sequentially,
+    and to associate the metadata in `metadata_path` with the audio files in the TAR
+    file.
+  - You can wrap the dataset in DataLoader using torch.utils.data.DataLoader and create
+    a collate function to collate the samples into batches.
+- source_sentence: Top literature about World War II
+  sentences:
+  - What is the price of an iPhone 12?
+  - Best books on World War II
+  - When was the Declaration of Independence signed?
+model-index:
+- name: SentenceTransformer based on intfloat/multilingual-e5-small
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: pair class dev
+      type: pair-class-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.784720778465271
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.926605504587156
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.784720778465271
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.8938053097345132
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9619047619047619
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9548853455786228
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.9
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 0.784720778465271
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.926605504587156
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 0.784720778465271
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.8938053097345132
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9619047619047619
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.9548853455786228
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.896875
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 9.908977508544922
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.9241379310344828
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 10.13671588897705
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.8933333333333333
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.9571428571428572
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.9549673053310541
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.9
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 0.6561694145202637
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.926605504587156
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 0.6561694145202637
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.8938053097345132
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9619047619047619
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.9548853455786228
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.9
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 9.908977508544922
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.926605504587156
+      name: Max F1
+    - type: max_f1_threshold
+      value: 10.13671588897705
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.8938053097345132
+      name: Max Precision
+    - type: max_recall
+      value: 0.9619047619047619
+      name: Max Recall
+    - type: max_ap
+      value: 0.9549673053310541
+      name: Max Ap
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: pair class test
+      type: pair-class-test
+    metrics:
+    - type: cosine_accuracy
+      value: 0.90625
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.8142284154891968
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.929245283018868
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.8142284154891968
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9205607476635514
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9380952380952381
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9556341092519267
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.90625
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 0.8142284750938416
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.929245283018868
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 0.8142284750938416
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.9205607476635514
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9380952380952381
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.9556341092519267
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.903125
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 9.576812744140625
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.9270588235294117
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 9.576812744140625
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.9162790697674419
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.9380952380952381
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.9557652464010216
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.90625
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 0.609528124332428
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.929245283018868
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 0.609528124332428
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.9205607476635514
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9380952380952381
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.9556341092519267
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.90625
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 9.576812744140625
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.929245283018868
+      name: Max F1
+    - type: max_f1_threshold
+      value: 9.576812744140625
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.9205607476635514
+      name: Max Precision
+    - type: max_recall
+      value: 0.9380952380952381
+      name: Max Recall
+    - type: max_ap
+      value: 0.9557652464010216
+      name: Max Ap
+---
+
+# SentenceTransformer based on intfloat/multilingual-e5-small
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). 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:** [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) <!-- at revision fd1525a9fd15316a2d503bf26ab031a61d056e98 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("srikarvar/fine_tuned_model_7")
+# Run inference
+sentences = [
+    'Top literature about World War II',
+    'Best books on World War II',
+    'What is the price of an iPhone 12?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### 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
+
+#### Binary Classification
+* Dataset: `pair-class-dev`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value     |
+|:-----------------------------|:----------|
+| cosine_accuracy              | 0.9       |
+| cosine_accuracy_threshold    | 0.7847    |
+| cosine_f1                    | 0.9266    |
+| cosine_f1_threshold          | 0.7847    |
+| cosine_precision             | 0.8938    |
+| cosine_recall                | 0.9619    |
+| cosine_ap                    | 0.9549    |
+| dot_accuracy                 | 0.9       |
+| dot_accuracy_threshold       | 0.7847    |
+| dot_f1                       | 0.9266    |
+| dot_f1_threshold             | 0.7847    |
+| dot_precision                | 0.8938    |
+| dot_recall                   | 0.9619    |
+| dot_ap                       | 0.9549    |
+| manhattan_accuracy           | 0.8969    |
+| manhattan_accuracy_threshold | 9.909     |
+| manhattan_f1                 | 0.9241    |
+| manhattan_f1_threshold       | 10.1367   |
+| manhattan_precision          | 0.8933    |
+| manhattan_recall             | 0.9571    |
+| manhattan_ap                 | 0.955     |
+| euclidean_accuracy           | 0.9       |
+| euclidean_accuracy_threshold | 0.6562    |
+| euclidean_f1                 | 0.9266    |
+| euclidean_f1_threshold       | 0.6562    |
+| euclidean_precision          | 0.8938    |
+| euclidean_recall             | 0.9619    |
+| euclidean_ap                 | 0.9549    |
+| max_accuracy                 | 0.9       |
+| max_accuracy_threshold       | 9.909     |
+| max_f1                       | 0.9266    |
+| max_f1_threshold             | 10.1367   |
+| max_precision                | 0.8938    |
+| max_recall                   | 0.9619    |
+| **max_ap**                   | **0.955** |
+
+#### Binary Classification
+* Dataset: `pair-class-test`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.9062     |
+| cosine_accuracy_threshold    | 0.8142     |
+| cosine_f1                    | 0.9292     |
+| cosine_f1_threshold          | 0.8142     |
+| cosine_precision             | 0.9206     |
+| cosine_recall                | 0.9381     |
+| cosine_ap                    | 0.9556     |
+| dot_accuracy                 | 0.9062     |
+| dot_accuracy_threshold       | 0.8142     |
+| dot_f1                       | 0.9292     |
+| dot_f1_threshold             | 0.8142     |
+| dot_precision                | 0.9206     |
+| dot_recall                   | 0.9381     |
+| dot_ap                       | 0.9556     |
+| manhattan_accuracy           | 0.9031     |
+| manhattan_accuracy_threshold | 9.5768     |
+| manhattan_f1                 | 0.9271     |
+| manhattan_f1_threshold       | 9.5768     |
+| manhattan_precision          | 0.9163     |
+| manhattan_recall             | 0.9381     |
+| manhattan_ap                 | 0.9558     |
+| euclidean_accuracy           | 0.9062     |
+| euclidean_accuracy_threshold | 0.6095     |
+| euclidean_f1                 | 0.9292     |
+| euclidean_f1_threshold       | 0.6095     |
+| euclidean_precision          | 0.9206     |
+| euclidean_recall             | 0.9381     |
+| euclidean_ap                 | 0.9556     |
+| max_accuracy                 | 0.9062     |
+| max_accuracy_threshold       | 9.5768     |
+| max_f1                       | 0.9292     |
+| max_f1_threshold             | 9.5768     |
+| max_precision                | 0.9206     |
+| max_recall                   | 0.9381     |
+| **max_ap**                   | **0.9558** |
+
+<!--
+## 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: 2,871 training samples
+* Columns: <code>sentence2</code>, <code>sentence1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence2                                                                          | sentence1                                                                          | label                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | int                                             |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 20.57 tokens</li><li>max: 177 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 20.74 tokens</li><li>max: 176 tokens</li></ul> | <ul><li>0: ~34.00%</li><li>1: ~66.00%</li></ul> |
+* Samples:
+  | sentence2                                                                                                               | sentence1                                                                                                                                                  | label          |
+  |:------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>How do I do to get fuller face?</code>                                                                            | <code>How can one get a fuller face?</code>                                                                                                                | <code>1</code> |
+  | <code>The DatasetInfo holds the data of a dataset, which may include its description, characteristics, and size.</code> | <code>A dataset's information is stored inside DatasetInfo and can include information such as the dataset description, features, and dataset size.</code> | <code>1</code> |
+  | <code>How do I write a resume?</code>                                                                                   | <code>How do I create a resume?</code>                                                                                                                     | <code>1</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 320 evaluation samples
+* Columns: <code>sentence2</code>, <code>sentence1</code>, and <code>label</code>
+* Approximate statistics based on the first 320 samples:
+  |         | sentence2                                                                          | sentence1                                                                          | label                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 19.57 tokens</li><li>max: 135 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 19.55 tokens</li><li>max: 136 tokens</li></ul> | <ul><li>0: ~34.38%</li><li>1: ~65.62%</li></ul> |
+* Samples:
+  | sentence2                                                                                 | sentence1                                                                              | label          |
+  |:------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------|:---------------|
+  | <code>Steps to erase internet history</code>                                              | <code>How do I delete my browsing history?</code>                                      | <code>1</code> |
+  | <code>How important is it to be the first person to wish someone a happy birthday?</code> | <code>What is the right etiquette for wishing a Jehovah Witness happy birthday?</code> | <code>0</code> |
+  | <code>Who directed 'Gone with the Wind'?</code>                                           | <code>Who directed 'Citizen Kane'?</code>                                              | <code>0</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `gradient_accumulation_steps`: 2
+- `num_train_epochs`: 4
+- `warmup_ratio`: 0.1
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `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`: True
+- `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}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `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
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch   | Step   | Training Loss | loss       | pair-class-dev_max_ap | pair-class-test_max_ap |
+|:-------:|:------:|:-------------:|:----------:|:---------------------:|:----------------------:|
+| 0       | 0      | -             | -          | 0.8735                | -                      |
+| 0.2222  | 10     | 1.3298        | -          | -                     | -                      |
+| 0.4444  | 20     | 0.8218        | -          | -                     | -                      |
+| 0.6667  | 30     | 0.642         | -          | -                     | -                      |
+| 0.8889  | 40     | 0.571         | -          | -                     | -                      |
+| 1.0     | 45     | -             | 0.5321     | 0.9499                | -                      |
+| 1.1111  | 50     | 0.4828        | -          | -                     | -                      |
+| 1.3333  | 60     | 0.3003        | -          | -                     | -                      |
+| 1.5556  | 70     | 0.3331        | -          | -                     | -                      |
+| 1.7778  | 80     | 0.203         | -          | -                     | -                      |
+| **2.0** | **90** | **0.3539**    | **0.5118** | **0.9558**            | **-**                  |
+| 2.2222  | 100    | 0.1357        | -          | -                     | -                      |
+| 2.4444  | 110    | 0.1562        | -          | -                     | -                      |
+| 2.6667  | 120    | 0.0703        | -          | -                     | -                      |
+| 2.8889  | 130    | 0.0806        | -          | -                     | -                      |
+| 3.0     | 135    | -             | 0.5266     | 0.9548                | -                      |
+| 3.1111  | 140    | 0.1721        | -          | -                     | -                      |
+| 3.3333  | 150    | 0.1063        | -          | -                     | -                      |
+| 3.5556  | 160    | 0.0909        | -          | -                     | -                      |
+| 3.7778  | 170    | 0.0358        | -          | -                     | -                      |
+| 4.0     | 180    | 0.1021        | 0.5256     | 0.9550                | 0.9558                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.1.0
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.34.2
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## 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",
+}
+```
+
+<!--
+## 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 +1,26 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-small",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "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",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f3b341bc463c0db2ab18fc21258e55b2a55a7113cf97830c8816e3ae215977
+size 470637416

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

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

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef04f2b385d1514f500e779207ace0f53e30895ce37563179e29f4022d28ca38
+size 17083053

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}