adriansanz's picture
Add new SentenceTransformer model
62a7849 verified
|
raw
history blame
31.4 kB
---
base_model: BAAI/bge-m3
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
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:2372
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: Heu de veure si és necessari un estudi d'aïllament acústic i quin
nivell d'aïllament acústic precisa l'activitat.
sentences:
- Quin és el paper de les persones que resideixen amb el titular del dret d'habitatge
en la política d'habitatge?
- Quin és el límit de superfície per a les carpes informatives?
- Quin és l'objectiu de l'estudi d'aïllament acústic?
- source_sentence: 'Si us voleu matricular al proper curs 2022-2023 d''arts plàstiques
ho podeu fer a partir del 1 de juliol a les 16h, seleccionant una d''aquestes
opcions:'
sentences:
- Quin és el període de matrícula per al curs 2022-2023 d'arts plàstiques?
- Quan no cal presentar al·legacions en un expedient de baixa d'ofici?
- Quin és l'objectiu de les al·legacions respecte a un expedient sancionador de
l'Ordenança Municipal de Civisme i Convivència Ciutadana?
- source_sentence: Annexes Econòmics (Cooperació)
sentences:
- Qui és el responsable de l'elaboració de l'informe d'adequació de l'habitatge?
- Què han de fer les persones interessades durant el tràmit d'audiència en el procés
d'inclusió al registre municipal d'immobles desocupats?
- Quin és l'àmbit de la cooperació econòmica?
- source_sentence: En virtut del conveni de col.laboració amb l'Atrium de Viladecans,
tots els ciutadans que acreditin la seva residència a Viladecans es podran beneficiar
d'un 20% de descompte en la programació de teatre, música i dansa, objecte del
conveni.
sentences:
- Quin és el resultat de consultar un expedient d'activitats?
- Quin és el format de resposta d'aquesta sol·licitud?
- Quin és el descompte que s'aplica en la programació de teatre, música i dansa
per als ciutadans de Viladecans?
- source_sentence: Descripció. Retorna en format JSON adequat
sentences:
- Quin és el contingut de l'annex específic?
- Quin tipus d'ocupació es refereix a la renúncia de la llicència?
- Què passa amb l'habitatge?
model-index:
- name: SentenceTransformer based on BAAI/bge-m3
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 1024
type: dim_1024
metrics:
- type: cosine_accuracy@1
value: 0.33220910623946037
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.5902192242833052
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.6998313659359191
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8094435075885329
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.33220910623946037
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.1967397414277684
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1399662731871838
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08094435075885327
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.33220910623946037
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.5902192242833052
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.6998313659359191
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8094435075885329
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.5625986746470664
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.4843170320404718
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.49243646079034575
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 768
type: dim_768
metrics:
- type: cosine_accuracy@1
value: 0.3406408094435076
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.5767284991568297
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.6981450252951096
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8161888701517707
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.3406408094435076
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.19224283305227655
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1396290050590219
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08161888701517706
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.3406408094435076
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.5767284991568297
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.6981450252951096
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8161888701517707
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.5661348054508011
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.4872065633448428
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.49520736709122076
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 512
type: dim_512
metrics:
- type: cosine_accuracy@1
value: 0.3305227655986509
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.5801011804384486
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.6947723440134908
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8161888701517707
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.3305227655986509
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.19336706014614952
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.13895446880269813
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08161888701517707
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.3305227655986509
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.5801011804384486
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.6947723440134908
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8161888701517707
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.5629643418278626
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.4829913809256133
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.49079988310494693
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 256
type: dim_256
metrics:
- type: cosine_accuracy@1
value: 0.3288364249578415
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.5885328836424958
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.7015177065767285
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8094435075885329
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.3288364249578415
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.1961776278808319
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.14030354131534567
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08094435075885327
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.3288364249578415
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.5885328836424958
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.7015177065767285
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8094435075885329
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.5625842077927447
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.48416981182579805
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.49201787335851555
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 128
type: dim_128
metrics:
- type: cosine_accuracy@1
value: 0.3473861720067454
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.581787521079258
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.6998313659359191
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.806070826306914
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.3473861720067454
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.19392917369308602
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1399662731871838
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.0806070826306914
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.3473861720067454
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.581787521079258
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.6998313659359191
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.806070826306914
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.565365572327355
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.4893626703070211
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.49726527073459287
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 64
type: dim_64
metrics:
- type: cosine_accuracy@1
value: 0.2917369308600337
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.5682967959527825
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.6644182124789207
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.7875210792580101
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.2917369308600337
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.18943226531759413
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.13288364249578413
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.07875210792580102
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.2917369308600337
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.5682967959527825
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.6644182124789207
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.7875210792580101
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.5320349463938843
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.45117106988945077
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.45948574441166834
name: Cosine Map@100
---
# SentenceTransformer based on BAAI/bge-m3
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) on the json dataset. It maps sentences & paragraphs to a 1024-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:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
- **Maximum Sequence Length:** 8192 tokens
- **Output Dimensionality:** 1024 tokens
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- json
<!-- - **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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("adriansanz/ST-tramits-SB-001-5ep")
# Run inference
sentences = [
'Descripció. Retorna en format JSON adequat',
"Quin és el contingut de l'annex específic?",
"Què passa amb l'habitatge?",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# 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
#### Information Retrieval
* Dataset: `dim_1024`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.3322 |
| cosine_accuracy@3 | 0.5902 |
| cosine_accuracy@5 | 0.6998 |
| cosine_accuracy@10 | 0.8094 |
| cosine_precision@1 | 0.3322 |
| cosine_precision@3 | 0.1967 |
| cosine_precision@5 | 0.14 |
| cosine_precision@10 | 0.0809 |
| cosine_recall@1 | 0.3322 |
| cosine_recall@3 | 0.5902 |
| cosine_recall@5 | 0.6998 |
| cosine_recall@10 | 0.8094 |
| cosine_ndcg@10 | 0.5626 |
| cosine_mrr@10 | 0.4843 |
| **cosine_map@100** | **0.4924** |
#### Information Retrieval
* Dataset: `dim_768`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.3406 |
| cosine_accuracy@3 | 0.5767 |
| cosine_accuracy@5 | 0.6981 |
| cosine_accuracy@10 | 0.8162 |
| cosine_precision@1 | 0.3406 |
| cosine_precision@3 | 0.1922 |
| cosine_precision@5 | 0.1396 |
| cosine_precision@10 | 0.0816 |
| cosine_recall@1 | 0.3406 |
| cosine_recall@3 | 0.5767 |
| cosine_recall@5 | 0.6981 |
| cosine_recall@10 | 0.8162 |
| cosine_ndcg@10 | 0.5661 |
| cosine_mrr@10 | 0.4872 |
| **cosine_map@100** | **0.4952** |
#### Information Retrieval
* Dataset: `dim_512`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.3305 |
| cosine_accuracy@3 | 0.5801 |
| cosine_accuracy@5 | 0.6948 |
| cosine_accuracy@10 | 0.8162 |
| cosine_precision@1 | 0.3305 |
| cosine_precision@3 | 0.1934 |
| cosine_precision@5 | 0.139 |
| cosine_precision@10 | 0.0816 |
| cosine_recall@1 | 0.3305 |
| cosine_recall@3 | 0.5801 |
| cosine_recall@5 | 0.6948 |
| cosine_recall@10 | 0.8162 |
| cosine_ndcg@10 | 0.563 |
| cosine_mrr@10 | 0.483 |
| **cosine_map@100** | **0.4908** |
#### Information Retrieval
* Dataset: `dim_256`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:----------|
| cosine_accuracy@1 | 0.3288 |
| cosine_accuracy@3 | 0.5885 |
| cosine_accuracy@5 | 0.7015 |
| cosine_accuracy@10 | 0.8094 |
| cosine_precision@1 | 0.3288 |
| cosine_precision@3 | 0.1962 |
| cosine_precision@5 | 0.1403 |
| cosine_precision@10 | 0.0809 |
| cosine_recall@1 | 0.3288 |
| cosine_recall@3 | 0.5885 |
| cosine_recall@5 | 0.7015 |
| cosine_recall@10 | 0.8094 |
| cosine_ndcg@10 | 0.5626 |
| cosine_mrr@10 | 0.4842 |
| **cosine_map@100** | **0.492** |
#### Information Retrieval
* Dataset: `dim_128`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.3474 |
| cosine_accuracy@3 | 0.5818 |
| cosine_accuracy@5 | 0.6998 |
| cosine_accuracy@10 | 0.8061 |
| cosine_precision@1 | 0.3474 |
| cosine_precision@3 | 0.1939 |
| cosine_precision@5 | 0.14 |
| cosine_precision@10 | 0.0806 |
| cosine_recall@1 | 0.3474 |
| cosine_recall@3 | 0.5818 |
| cosine_recall@5 | 0.6998 |
| cosine_recall@10 | 0.8061 |
| cosine_ndcg@10 | 0.5654 |
| cosine_mrr@10 | 0.4894 |
| **cosine_map@100** | **0.4973** |
#### Information Retrieval
* Dataset: `dim_64`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.2917 |
| cosine_accuracy@3 | 0.5683 |
| cosine_accuracy@5 | 0.6644 |
| cosine_accuracy@10 | 0.7875 |
| cosine_precision@1 | 0.2917 |
| cosine_precision@3 | 0.1894 |
| cosine_precision@5 | 0.1329 |
| cosine_precision@10 | 0.0788 |
| cosine_recall@1 | 0.2917 |
| cosine_recall@3 | 0.5683 |
| cosine_recall@5 | 0.6644 |
| cosine_recall@10 | 0.7875 |
| cosine_ndcg@10 | 0.532 |
| cosine_mrr@10 | 0.4512 |
| **cosine_map@100** | **0.4595** |
<!--
## 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
#### json
* Dataset: json
* Size: 2,372 training samples
* Columns: <code>positive</code> and <code>anchor</code>
* Approximate statistics based on the first 1000 samples:
| | positive | anchor |
|:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 3 tokens</li><li>mean: 35.12 tokens</li><li>max: 166 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 19.49 tokens</li><li>max: 47 tokens</li></ul> |
* Samples:
| positive | anchor |
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|
| <code>Comunicar la variació d'alguna de les següents dades del Padró Municipal d'Habitants: Nom, Cognoms, Data de naixement, DNI, Passaport, Número de permís de residència (NIE), Sexe, Municipi i/o província de naixement, Nacionalitat, Titulació acadèmica.</code> | <code>Quin és l'objectiu del canvi de dades personals en el Padró Municipal d'Habitants?</code> |
| <code>EN QUÈ CONSISTEIX: Tramitar la sol·licitud de matrimoni civil a l'Ajuntament.</code> | <code>Què és el matrimoni civil a l'Ajuntament de Sant Boi de Llobregat?</code> |
| <code>En domiciliar el pagament de tributs municipals en entitats bancàries.</code> | <code>Quin és el benefici de domiciliar el pagament de tributs?</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
1024,
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
1,
1,
1,
1,
1
],
"n_dims_per_step": -1
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: epoch
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `gradient_accumulation_steps`: 16
- `learning_rate`: 2e-05
- `num_train_epochs`: 5
- `lr_scheduler_type`: cosine
- `warmup_ratio`: 0.2
- `bf16`: True
- `tf32`: True
- `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`: 16
- `per_device_eval_batch_size`: 16
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 16
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 2e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 5
- `max_steps`: -1
- `lr_scheduler_type`: cosine
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.2
- `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`: True
- `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
- `eval_on_start`: False
- `eval_use_gather_object`: False
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | Training Loss | dim_1024_cosine_map@100 | dim_768_cosine_map@100 | dim_512_cosine_map@100 | dim_256_cosine_map@100 | dim_128_cosine_map@100 | dim_64_cosine_map@100 |
|:----------:|:------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
| 0.9664 | 9 | - | 0.4730 | 0.4766 | 0.4640 | 0.4612 | 0.4456 | 0.4083 |
| 1.0738 | 10 | 2.6023 | - | - | - | - | - | - |
| 1.9329 | 18 | - | 0.4951 | 0.4966 | 0.4977 | 0.4773 | 0.4849 | 0.4501 |
| 2.1477 | 20 | 0.974 | - | - | - | - | - | - |
| 2.8993 | 27 | - | 0.4891 | 0.4973 | 0.4941 | 0.4867 | 0.4925 | 0.4684 |
| 3.2215 | 30 | 0.408 | - | - | - | - | - | - |
| **3.9732** | **37** | **-** | **0.4944** | **0.4998** | **0.4931** | **0.4991** | **0.4974** | **0.4616** |
| 4.2953 | 40 | 0.2718 | - | - | - | - | - | - |
| 4.8322 | 45 | - | 0.4924 | 0.4952 | 0.4908 | 0.4920 | 0.4973 | 0.4595 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.2.0
- Transformers: 4.44.2
- PyTorch: 2.4.1+cu121
- Accelerate: 1.1.0.dev0
- Datasets: 3.0.1
- 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",
}
```
#### 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.*
-->