|
--- |
|
base_model: BAAI/bge-base-en-v1.5 |
|
datasets: [] |
|
language: |
|
- my |
|
library_name: sentence-transformers |
|
license: apache-2.0 |
|
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:389 |
|
- loss:MatryoshkaLoss |
|
- loss:MultipleNegativesRankingLoss |
|
widget: |
|
- source_sentence: Tukang kayu adalah individu yang bekerja dengan kayu untuk membina |
|
atau membaiki struktur dan perabot. |
|
sentences: |
|
- Apakah itu pakar latihan? |
|
- Apakah itu tukang kayu? |
|
- Apakah itu pakar mikrobiologi? |
|
- source_sentence: Pakar pemakanan adalah profesional yang memberi nasihat mengenai |
|
pemakanan dan diet untuk meningkatkan kesihatan. |
|
sentences: |
|
- Apakah itu penulis kreatif? |
|
- Apakah itu ahli geologi marin? |
|
- Apakah itu pakar pemakanan? |
|
- source_sentence: Dokter adalah profesional medis yang mendiagnosis dan merawat penyakit |
|
serta cedera pasien. |
|
sentences: |
|
- Apa itu dokter? |
|
- Apakah itu pengurus kargo? |
|
- Apakah itu pakar teknologi nano? |
|
- source_sentence: Juruteknik pembinaan kapal adalah individu yang terlibat dalam |
|
proses pembinaan dan pembaikan kapal, memastikan struktur dan sistem kapal dibina |
|
mengikut spesifikasi. |
|
sentences: |
|
- Apakah itu juruteknik pembinaan kapal? |
|
- Apakah itu pengurus projek IT? |
|
- Apakah itu pakar perkapalan? |
|
- source_sentence: Penyelaras kempen iklan adalah individu yang menyelaraskan semua |
|
aspek kempen iklan, termasuk jadual, pelaksanaan, dan laporan prestasi. |
|
sentences: |
|
- Apakah itu jurutera sistem propulsi? |
|
- Apakah itu pembuat roti? |
|
- Apakah itu penyelaras kempen iklan? |
|
model-index: |
|
- name: BGE base Financial Matryoshka |
|
results: |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 768 |
|
type: dim_768 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.8226221079691517 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.9768637532133676 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.987146529562982 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.9974293059125964 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.8226221079691517 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.32562125107112255 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.1974293059125964 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.09974293059125963 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.8226221079691517 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.9768637532133676 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.987146529562982 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.9974293059125964 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.9255252859780915 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.9009670706328802 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.9011023703216912 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 512 |
|
type: dim_512 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.8046272493573264 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.974293059125964 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.987146529562982 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.9922879177377892 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.8046272493573264 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.324764353041988 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.1974293059125964 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.0992287917737789 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.8046272493573264 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.974293059125964 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.987146529562982 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.9922879177377892 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.9158947182791948 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.8895519647447668 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.8900397092700132 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 256 |
|
type: dim_256 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.7892030848329049 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.9665809768637532 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.974293059125964 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.987146529562982 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.7892030848329049 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.3221936589545844 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.19485861182519276 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.0987146529562982 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.7892030848329049 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.9665809768637532 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.974293059125964 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.987146529562982 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.9046037741833534 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.8764455053658137 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.8770676096874822 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 128 |
|
type: dim_128 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.7480719794344473 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.9408740359897172 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.9537275064267352 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.9691516709511568 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.7480719794344473 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.31362467866323906 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.190745501285347 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.09691516709511568 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.7480719794344473 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.9408740359897172 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.9537275064267352 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.9691516709511568 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.8765083941585068 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.8449820459460564 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.8461326502118156 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 64 |
|
type: dim_64 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.7223650385604113 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.897172236503856 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.9254498714652957 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.9434447300771208 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.7223650385604113 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.29905741216795206 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.18508997429305912 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.09434447300771207 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.7223650385604113 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.897172236503856 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.9254498714652957 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.9434447300771208 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.8455216956566762 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.8126851511812953 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.8145628077638951 |
|
name: Cosine Map@100 |
|
--- |
|
|
|
# BGE base Financial Matryoshka |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). 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:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a --> |
|
- **Maximum Sequence Length:** 512 tokens |
|
- **Output Dimensionality:** 768 tokens |
|
- **Similarity Function:** Cosine Similarity |
|
<!-- - **Training Dataset:** Unknown --> |
|
- **Language:** my |
|
- **License:** apache-2.0 |
|
|
|
### 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': True}) with Transformer model: BertModel |
|
(1): Pooling({'word_embedding_dimension': 768, '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("IlhamEbdesk/bge-base-financial-matryoshka_test_my") |
|
# Run inference |
|
sentences = [ |
|
'Penyelaras kempen iklan adalah individu yang menyelaraskan semua aspek kempen iklan, termasuk jadual, pelaksanaan, dan laporan prestasi.', |
|
'Apakah itu penyelaras kempen iklan?', |
|
'Apakah itu pembuat roti?', |
|
] |
|
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 |
|
|
|
#### 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 | 0.8226 | |
|
| cosine_accuracy@3 | 0.9769 | |
|
| cosine_accuracy@5 | 0.9871 | |
|
| cosine_accuracy@10 | 0.9974 | |
|
| cosine_precision@1 | 0.8226 | |
|
| cosine_precision@3 | 0.3256 | |
|
| cosine_precision@5 | 0.1974 | |
|
| cosine_precision@10 | 0.0997 | |
|
| cosine_recall@1 | 0.8226 | |
|
| cosine_recall@3 | 0.9769 | |
|
| cosine_recall@5 | 0.9871 | |
|
| cosine_recall@10 | 0.9974 | |
|
| cosine_ndcg@10 | 0.9255 | |
|
| cosine_mrr@10 | 0.901 | |
|
| **cosine_map@100** | **0.9011** | |
|
|
|
#### 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 | 0.8046 | |
|
| cosine_accuracy@3 | 0.9743 | |
|
| cosine_accuracy@5 | 0.9871 | |
|
| cosine_accuracy@10 | 0.9923 | |
|
| cosine_precision@1 | 0.8046 | |
|
| cosine_precision@3 | 0.3248 | |
|
| cosine_precision@5 | 0.1974 | |
|
| cosine_precision@10 | 0.0992 | |
|
| cosine_recall@1 | 0.8046 | |
|
| cosine_recall@3 | 0.9743 | |
|
| cosine_recall@5 | 0.9871 | |
|
| cosine_recall@10 | 0.9923 | |
|
| cosine_ndcg@10 | 0.9159 | |
|
| cosine_mrr@10 | 0.8896 | |
|
| **cosine_map@100** | **0.89** | |
|
|
|
#### 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 | 0.7892 | |
|
| cosine_accuracy@3 | 0.9666 | |
|
| cosine_accuracy@5 | 0.9743 | |
|
| cosine_accuracy@10 | 0.9871 | |
|
| cosine_precision@1 | 0.7892 | |
|
| cosine_precision@3 | 0.3222 | |
|
| cosine_precision@5 | 0.1949 | |
|
| cosine_precision@10 | 0.0987 | |
|
| cosine_recall@1 | 0.7892 | |
|
| cosine_recall@3 | 0.9666 | |
|
| cosine_recall@5 | 0.9743 | |
|
| cosine_recall@10 | 0.9871 | |
|
| cosine_ndcg@10 | 0.9046 | |
|
| cosine_mrr@10 | 0.8764 | |
|
| **cosine_map@100** | **0.8771** | |
|
|
|
#### 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 | 0.7481 | |
|
| cosine_accuracy@3 | 0.9409 | |
|
| cosine_accuracy@5 | 0.9537 | |
|
| cosine_accuracy@10 | 0.9692 | |
|
| cosine_precision@1 | 0.7481 | |
|
| cosine_precision@3 | 0.3136 | |
|
| cosine_precision@5 | 0.1907 | |
|
| cosine_precision@10 | 0.0969 | |
|
| cosine_recall@1 | 0.7481 | |
|
| cosine_recall@3 | 0.9409 | |
|
| cosine_recall@5 | 0.9537 | |
|
| cosine_recall@10 | 0.9692 | |
|
| cosine_ndcg@10 | 0.8765 | |
|
| cosine_mrr@10 | 0.845 | |
|
| **cosine_map@100** | **0.8461** | |
|
|
|
#### 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 | 0.7224 | |
|
| cosine_accuracy@3 | 0.8972 | |
|
| cosine_accuracy@5 | 0.9254 | |
|
| cosine_accuracy@10 | 0.9434 | |
|
| cosine_precision@1 | 0.7224 | |
|
| cosine_precision@3 | 0.2991 | |
|
| cosine_precision@5 | 0.1851 | |
|
| cosine_precision@10 | 0.0943 | |
|
| cosine_recall@1 | 0.7224 | |
|
| cosine_recall@3 | 0.8972 | |
|
| cosine_recall@5 | 0.9254 | |
|
| cosine_recall@10 | 0.9434 | |
|
| cosine_ndcg@10 | 0.8455 | |
|
| cosine_mrr@10 | 0.8127 | |
|
| **cosine_map@100** | **0.8146** | |
|
|
|
<!-- |
|
## 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: 389 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: 27 tokens</li><li>mean: 61.59 tokens</li><li>max: 139 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 15.26 tokens</li><li>max: 24 tokens</li></ul> | |
|
* Samples: |
|
| positive | anchor | |
|
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------| |
|
| <code>Dokter adalah profesional medis yang mendiagnosis dan merawat penyakit serta cedera pasien.</code> | <code>Apa itu dokter?</code> | |
|
| <code>Pereka sistem akuakultur adalah individu yang merancang dan membangunkan sistem untuk membiakkan ikan secara berkesan, termasuk reka bentuk kolam, sistem aliran air, dan pemantauan kualiti air.</code> | <code>Apakah itu pereka sistem akuakultur?</code> | |
|
| <code>Ahli sejarah seni adalah individu yang mengkaji perkembangan seni sepanjang sejarah dan konteks sosial, politik, dan budaya yang mempengaruhi penciptaannya. Mereka bekerja di muzium, galeri, dan institusi akademik, menganalisis karya seni</code> | <code>Apakah itu ahli sejarah seni?</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`: epoch |
|
- `per_device_train_batch_size`: 32 |
|
- `per_device_eval_batch_size`: 16 |
|
- `gradient_accumulation_steps`: 16 |
|
- `learning_rate`: 2e-05 |
|
- `num_train_epochs`: 4 |
|
- `lr_scheduler_type`: cosine |
|
- `warmup_ratio`: 0.1 |
|
- `tf32`: False |
|
- `load_best_model_at_end`: True |
|
- `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`: 16 |
|
- `per_gpu_train_batch_size`: None |
|
- `per_gpu_eval_batch_size`: None |
|
- `gradient_accumulation_steps`: 16 |
|
- `eval_accumulation_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`: 4 |
|
- `max_steps`: -1 |
|
- `lr_scheduler_type`: cosine |
|
- `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`: False |
|
- `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 |
|
- `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 | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 | |
|
|:----------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:| |
|
| 1.0 | 1 | 0.6375 | 0.7065 | 0.7339 | 0.5984 | 0.7483 | |
|
| 2.0 | 3 | 0.8282 | 0.8712 | 0.8821 | 0.7994 | 0.8929 | |
|
| **2.4615** | **4** | **0.8461** | **0.8771** | **0.89** | **0.8146** | **0.9011** | |
|
|
|
* The bold row denotes the saved checkpoint. |
|
|
|
### Framework Versions |
|
- Python: 3.10.12 |
|
- Sentence Transformers: 3.0.1 |
|
- Transformers: 4.41.2 |
|
- PyTorch: 2.1.2+cu121 |
|
- Accelerate: 0.32.1 |
|
- 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", |
|
} |
|
``` |
|
|
|
#### 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.* |
|
--> |
