Add new SentenceTransformer model.

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 +1,728 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:100K<n<1M
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: distilbert/distilroberta-base
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: He shrugged.
+  sentences:
+  - Then he shrugged.
+  - Two people are dancing.
+  - The people are Indian.
+- source_sentence: a young girl
+  sentences:
+  - A girl is playing.
+  - A dog playing outside.
+  - The men are moving.
+- source_sentence: girl sleeps
+  sentences:
+  - A little girl is sleep.
+  - Two women are walking.
+  - three men are pictured
+- source_sentence: He walked.
+  sentences:
+  - A man is moving around.
+  - A young man is running.
+  - What idiots girls are!
+- source_sentence: '''Go now.'''
+  sentences:
+  - Now go.
+  - The door did not budge.
+  - I never knew the man.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on distilbert/distilroberta-base
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 768
+      type: sts-dev-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8418367310465795
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8485984004433933
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8356556933767024
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8341402433895243
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8378021883964464
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8364904078404392
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7476524989991268
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.744450587024694
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8418367310465795
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8485984004433933
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 512
+      type: sts-dev-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8416891989714739
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8490082509626217
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8348187780435371
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8332638443518806
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.837008948364763
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8356608810942396
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7426437744526075
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7393063147821313
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8416891989714739
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8490082509626217
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 256
+      type: sts-dev-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8368212220308662
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8458532859579723
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8282949195581827
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8279757292284411
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8304309516656533
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8301347336633305
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7158283880571648
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7114038350641958
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8368212220308662
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8458532859579723
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 128
+      type: sts-dev-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8291552182220155
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8410315378567165
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8205197124842151
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8211956528048456
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8218377581296912
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8223376697977559
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6736747525126793
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6704632728499174
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8291552182220155
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8410315378567165
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 64
+      type: sts-dev-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.8201110050860942
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.835036509147006
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8028297556674707
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8048509047037822
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8046682420071583
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8063788129340022
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6171580093307325
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6176751811391049
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8201110050860942
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.835036509147006
+      name: Spearman Max
+---
+
+# SentenceTransformer based on distilbert/distilroberta-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) <!-- at revision fb53ab8802853c8e4fbdbcd0529f21fc6f459b2b -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
+  (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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    "'Go now.'",
+    'Now go.',
+    'The door did not budge.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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
+
+#### Semantic Similarity
+* Dataset: `sts-dev-768`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8418     |
+| **spearman_cosine** | **0.8486** |
+| pearson_manhattan   | 0.8357     |
+| spearman_manhattan  | 0.8341     |
+| pearson_euclidean   | 0.8378     |
+| spearman_euclidean  | 0.8365     |
+| pearson_dot         | 0.7477     |
+| spearman_dot        | 0.7445     |
+| pearson_max         | 0.8418     |
+| spearman_max        | 0.8486     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-512`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.8417    |
+| **spearman_cosine** | **0.849** |
+| pearson_manhattan   | 0.8348    |
+| spearman_manhattan  | 0.8333    |
+| pearson_euclidean   | 0.837     |
+| spearman_euclidean  | 0.8357    |
+| pearson_dot         | 0.7426    |
+| spearman_dot        | 0.7393    |
+| pearson_max         | 0.8417    |
+| spearman_max        | 0.849     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-256`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8368     |
+| **spearman_cosine** | **0.8459** |
+| pearson_manhattan   | 0.8283     |
+| spearman_manhattan  | 0.828      |
+| pearson_euclidean   | 0.8304     |
+| spearman_euclidean  | 0.8301     |
+| pearson_dot         | 0.7158     |
+| spearman_dot        | 0.7114     |
+| pearson_max         | 0.8368     |
+| spearman_max        | 0.8459     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-128`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.8292    |
+| **spearman_cosine** | **0.841** |
+| pearson_manhattan   | 0.8205    |
+| spearman_manhattan  | 0.8212    |
+| pearson_euclidean   | 0.8218    |
+| spearman_euclidean  | 0.8223    |
+| pearson_dot         | 0.6737    |
+| spearman_dot        | 0.6705    |
+| pearson_max         | 0.8292    |
+| spearman_max        | 0.841     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-64`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.8201    |
+| **spearman_cosine** | **0.835** |
+| pearson_manhattan   | 0.8028    |
+| spearman_manhattan  | 0.8049    |
+| pearson_euclidean   | 0.8047    |
+| spearman_euclidean  | 0.8064    |
+| pearson_dot         | 0.6172    |
+| spearman_dot        | 0.6177    |
+| pearson_max         | 0.8201    |
+| spearman_max        | 0.835     |
+
+<!--
+## 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
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 557,850 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                         | negative                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 10.38 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.8 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.4 tokens</li><li>max: 50 tokens</li></ul> |
+* Samples:
+  | anchor                                                                     | positive                                         | negative                                                   |
+  |:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>A person is outdoors, on a horse.</code>   | <code>A person is at a diner, ordering an omelette.</code> |
+  | <code>Children smiling and waving at camera</code>                         | <code>There are children present</code>          | <code>The kids are frowning</code>                         |
+  | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</code>             |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 6,584 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                         | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 18.02 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 9.81 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.37 tokens</li><li>max: 29 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                         | positive                                                    | negative                                                |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:--------------------------------------------------------|
+  | <code>Two women are embracing while holding to go packages.</code>                                                                                                             | <code>Two woman are holding packages.</code>                | <code>The men are fighting outside a deli.</code>       |
+  | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code>        |
+  | <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code>                                                                    | <code>A man selling donuts to a customer.</code>            | <code>A woman drinks her coffee in a small cafe.</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `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`: 1
+- `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`: True
+- `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`: 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}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `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   | sts-dev-128_spearman_cosine | sts-dev-256_spearman_cosine | sts-dev-512_spearman_cosine | sts-dev-64_spearman_cosine | sts-dev-768_spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:---------------------------:|:---------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|
+| 0.0459 | 100  | 19.459        | 8.2665 | 0.7796                      | 0.8046                      | 0.8114                      | 0.8082                     | 0.7996                      |
+| 0.0917 | 200  | 11.0035       | 7.6606 | 0.7696                      | 0.7971                      | 0.8083                      | 0.7987                     | 0.7933                      |
+| 0.1376 | 300  | 9.7634        | 6.4912 | 0.7992                      | 0.8126                      | 0.8190                      | 0.8062                     | 0.8127                      |
+| 0.1835 | 400  | 9.1103        | 5.9960 | 0.8081                      | 0.8229                      | 0.8263                      | 0.8136                     | 0.8224                      |
+| 0.2294 | 500  | 8.7099        | 5.9388 | 0.7984                      | 0.8138                      | 0.8189                      | 0.8021                     | 0.8166                      |
+| 0.2752 | 600  | 8.1215        | 5.6457 | 0.7963                      | 0.8104                      | 0.8149                      | 0.8057                     | 0.8121                      |
+| 0.3211 | 700  | 7.7441        | 5.4632 | 0.7937                      | 0.8153                      | 0.8199                      | 0.8119                     | 0.8150                      |
+| 0.3670 | 800  | 7.4849        | 5.1815 | 0.8076                      | 0.8208                      | 0.8238                      | 0.8152                     | 0.8172                      |
+| 0.4128 | 900  | 7.1386        | 5.1419 | 0.8035                      | 0.8181                      | 0.8235                      | 0.8139                     | 0.8189                      |
+| 0.4587 | 1000 | 6.839         | 5.1548 | 0.7943                      | 0.8118                      | 0.8172                      | 0.8054                     | 0.8153                      |
+| 0.5046 | 1100 | 6.6597        | 5.1015 | 0.7895                      | 0.8066                      | 0.8119                      | 0.8059                     | 0.8063                      |
+| 0.5505 | 1200 | 6.7172        | 5.3707 | 0.7753                      | 0.7987                      | 0.8068                      | 0.7989                     | 0.8014                      |
+| 0.5963 | 1300 | 6.6514        | 4.9368 | 0.7904                      | 0.8086                      | 0.8139                      | 0.8051                     | 0.8083                      |
+| 0.6422 | 1400 | 6.5573        | 5.0196 | 0.7882                      | 0.8066                      | 0.8128                      | 0.8035                     | 0.8091                      |
+| 0.6881 | 1500 | 6.7596        | 4.9381 | 0.7960                      | 0.8120                      | 0.8169                      | 0.8058                     | 0.8140                      |
+| 0.7339 | 1600 | 6.2686        | 4.4018 | 0.8136                      | 0.8245                      | 0.8268                      | 0.8160                     | 0.8244                      |
+| 0.7798 | 1700 | 3.4607        | 3.8397 | 0.8415                      | 0.8466                      | 0.8502                      | 0.8345                     | 0.8503                      |
+| 0.8257 | 1800 | 2.6912        | 3.7914 | 0.8415                      | 0.8459                      | 0.8493                      | 0.8350                     | 0.8488                      |
+| 0.8716 | 1900 | 2.4958        | 3.7752 | 0.8402                      | 0.8450                      | 0.8484                      | 0.8340                     | 0.8478                      |
+| 0.9174 | 2000 | 2.3413        | 3.7997 | 0.8410                      | 0.8459                      | 0.8490                      | 0.8350                     | 0.8486                      |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.1
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.19.2
+- 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",
+}
+```
+
+#### 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{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/matryoshka_nli_2_distilroberta-base_256_bs_1_e/checkpoint-2000",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.41.1",
+    "pytorch": "2.3.0+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 sha256:0332e4ce6f3f1e288667ccdabc510285f8de92ee284c111595c123c5188178b1
+size 328485128

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
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}