AdaptiveLayerLoss(model=model,

loss=train_loss,
n_layers_per_step = 1,
last_layer_weight = 1,
prior_layers_weight= 1,
kl_div_weight = 1,
kl_temperature= 1,
)''')
lr = 1e-6. batch = 42, schedule = cosine

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 +1,478 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:314315
+- loss:AdaptiveLayerLoss
+- loss:MultipleNegativesRankingLoss
+base_model: microsoft/deberta-v3-small
+datasets:
+- stanfordnlp/snli
+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
+widget:
+- source_sentence: A man plays the violin.
+  sentences:
+  - A man is playing violin.
+  - The back of a pig under a tree with a cow in the background.
+  - The plane is getting ready to take off.
+- source_sentence: A person drops a camera down an escelator.
+  sentences:
+  - Something is bothering your cat and he does not like it.
+  - A man tosses a bag down an escalator.
+  - Two smiling women holding a baby.
+- source_sentence: One football player tries to tackle a player on the opposing team.
+  sentences:
+  - I think Stephen King's comments are helpful in this regard.
+  - Our interactions are merely depends on where we put our perception.
+  - A football player attempts a tackle.
+- source_sentence: The two men are wearing jeans.
+  sentences:
+  - Four people eating dessert around a table.
+  - Here are some things that worked with my son who started toilet training around
+    2.5 years.
+  - The two men are wearing pants.
+- source_sentence: This may be overly obvious, but in American English, saying "you're
+    welcome" is certainly polite and standard.
+  sentences:
+  - I'm not sure how "Not at all" sounds in response to "thank you".
+  - As bikeboy389 said, you can learn a lot by looking at students' native languages.
+  - A laptop and a PC at a workstation.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on microsoft/deberta-v3-small
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy
+      value: 0.5397679884752445
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.9089176654815674
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.6834040429248815
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.3752323389053345
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.5191082802547771
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9998539506353147
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.5794582374804604
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.5302903935097429
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 391.4422302246094
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.6834040429248815
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 175.07894897460938
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.5191082802547771
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9998539506353147
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.5621671154600225
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.5644855561452726
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 160.045654296875
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.6834381551362683
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 322.75946044921875
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.5191476454083567
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.9998539506353147
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.6033119142961784
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.5387064978391084
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 8.973075866699219
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.6834065495207667
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 24.51708221435547
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.5191505498672734
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9997079012706295
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.577277049262529
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.5644855561452726
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 391.4422302246094
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.6834381551362683
+      name: Max F1
+    - type: max_f1_threshold
+      value: 322.75946044921875
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.5191505498672734
+      name: Max Precision
+    - type: max_recall
+      value: 0.9998539506353147
+      name: Max Recall
+    - type: max_ap
+      value: 0.6033119142961784
+      name: Max Ap
+---
+
+# SentenceTransformer based on microsoft/deberta-v3-small
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) 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:** [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) <!-- at revision a36c739020e01763fe789b4b85e2df55d6180012 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli)
+- **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: DebertaV2Model 
+  (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("bobox/DeBERTaV3-small-ST-AdaptiveLayers-ep2")
+# Run inference
+sentences = [
+    'This may be overly obvious, but in American English, saying "you\'re welcome" is certainly polite and standard.',
+    'I\'m not sure how "Not at all" sounds in response to "thank you".',
+    "As bikeboy389 said, you can learn a lot by looking at students' native languages.",
+]
+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
+
+#### Binary Classification
+
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.5398     |
+| cosine_accuracy_threshold    | 0.9089     |
+| cosine_f1                    | 0.6834     |
+| cosine_f1_threshold          | 0.3752     |
+| cosine_precision             | 0.5191     |
+| cosine_recall                | 0.9999     |
+| cosine_ap                    | 0.5795     |
+| dot_accuracy                 | 0.5303     |
+| dot_accuracy_threshold       | 391.4422   |
+| dot_f1                       | 0.6834     |
+| dot_f1_threshold             | 175.0789   |
+| dot_precision                | 0.5191     |
+| dot_recall                   | 0.9999     |
+| dot_ap                       | 0.5622     |
+| manhattan_accuracy           | 0.5645     |
+| manhattan_accuracy_threshold | 160.0457   |
+| manhattan_f1                 | 0.6834     |
+| manhattan_f1_threshold       | 322.7595   |
+| manhattan_precision          | 0.5191     |
+| manhattan_recall             | 0.9999     |
+| manhattan_ap                 | 0.6033     |
+| euclidean_accuracy           | 0.5387     |
+| euclidean_accuracy_threshold | 8.9731     |
+| euclidean_f1                 | 0.6834     |
+| euclidean_f1_threshold       | 24.5171    |
+| euclidean_precision          | 0.5192     |
+| euclidean_recall             | 0.9997     |
+| euclidean_ap                 | 0.5773     |
+| max_accuracy                 | 0.5645     |
+| max_accuracy_threshold       | 391.4422   |
+| max_f1                       | 0.6834     |
+| max_f1_threshold             | 322.7595   |
+| max_precision                | 0.5192     |
+| max_recall                   | 0.9999     |
+| **max_ap**                   | **0.6033** |
+
+<!--
+## 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
+
+#### stanfordnlp/snli
+
+* Dataset: [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b)
+* Size: 314,315 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                        | label                        |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------|
+  | type    | string                                                                            | string                                                                           | int                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 16.62 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.46 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>0: 100.00%</li></ul> |
+* Samples:
+  | sentence1                                                                  | sentence2                                        | label          |
+  |:---------------------------------------------------------------------------|:-------------------------------------------------|:---------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>A person is outdoors, on a horse.</code>   | <code>0</code> |
+  | <code>Children smiling and waving at camera</code>                         | <code>There are children present</code>          | <code>0</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>0</code> |
+* Loss: [<code>AdaptiveLayerLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "n_layers_per_step": 1,
+      "last_layer_weight": 1,
+      "prior_layers_weight": 1,
+      "kl_div_weight": 1,
+      "kl_temperature": 1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### stanfordnlp/snli
+
+* Dataset: [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 14.77 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.74 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                         | sentence2                                             | score             |
+  |:--------------------------------------------------|:------------------------------------------------------|:------------------|
+  | <code>A man with a hard hat is dancing.</code>    | <code>A man wearing a hard hat is dancing.</code>     | <code>1.0</code>  |
+  | <code>A young child is riding a horse.</code>     | <code>A child is riding a horse.</code>               | <code>0.95</code> |
+  | <code>A man is feeding a mouse to a snake.</code> | <code>The man is feeding a mouse to the snake.</code> | <code>1.0</code>  |
+* Loss: [<code>AdaptiveLayerLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "n_layers_per_step": 1,
+      "last_layer_weight": 1,
+      "prior_layers_weight": 1,
+      "kl_div_weight": 1,
+      "kl_temperature": 1
+  }
+  ```
+
+### Training Logs
+| Epoch | Step | loss   | max_ap |
+|:-----:|:----:|:------:|:------:|
+| None  | 0    | 4.6204 | 0.6033 |
+
+
+### Framework Versions
+- Python: 3.10.13
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2
+- 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",
+}
+```
+
+#### AdaptiveLayerLoss
+```bibtex
+@misc{li20242d,
+    title={2D Matryoshka Sentence Embeddings}, 
+    author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
+    year={2024},
+    eprint={2402.14776},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+#### 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.*
+-->

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

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"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75f9f0d0ccf1ea68d57e5e49eadbe854516a7a239c28fe45742d13c727c0aae
+size 565251810

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}