|
--- |
|
base_model: BAAI/bge-base-en-v1.5 |
|
language: |
|
- en |
|
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 |
|
- dataset_size:1K<n<10K |
|
- loss:MatryoshkaLoss |
|
- loss:MultipleNegativesRankingLoss |
|
widget: |
|
- source_sentence: USS Conyngham (DD-58) |
|
sentences: |
|
- '"w jakich patrolach uczestniczył USS ""Conyngham"" (DD-58)?"' |
|
- Jest ona najstarszą skoczkinią w kadrze norweskiej. |
|
- kto uczył malarstwa olimpijczyka Bronisława Czecha? |
|
- source_sentence: Danae (obraz Tycjana) |
|
sentences: |
|
- jakie różnice występują pomiędzy kolejnymi wersjami obrazu Tycjana Danae? |
|
- z czego wykonana jest rzeźba Robotnik i kołchoźnica? |
|
- z jakiego powodu zwołano synod w Whitby? |
|
- source_sentence: dlaczego zapominamy? |
|
sentences: |
|
- Zamek w Haapsalu |
|
- kto był tłumaczem języka angielskiego u Mao Zedonga? |
|
- Najstarszy z trzech synów Hong Xiuquana; jego matką była Lai Lianying. |
|
- source_sentence: kim był Steve Yzerman? |
|
sentences: |
|
- która hala ma najmniejszą widownię w NHL? |
|
- za co krytykowany był papieski wykład ratyzboński? |
|
- ' W 1867 oddano do użytku Kolej Warszawsko-Terespolską (całą linię).' |
|
- source_sentence: Herkules na rozstajach |
|
sentences: |
|
- jak zinterpretować wymowę obrazu Herkules na rozstajach? |
|
- Dowódcą grupy był Wiaczesław Razumowicz ps. „Chmara”. |
|
- z jakiego powodu zwołano synod w Whitby? |
|
model-index: |
|
- name: bge-base-en-v1.5-klej-dyk |
|
results: |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 768 |
|
type: dim_768 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.17307692307692307 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.46153846153846156 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.6225961538461539 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.7355769230769231 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.17307692307692307 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.15384615384615385 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.12451923076923076 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.0735576923076923 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.17307692307692307 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.46153846153846156 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.6225961538461539 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.7355769230769231 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.4433646681639308 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.35053323412698395 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.3573926265146405 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 512 |
|
type: dim_512 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.16826923076923078 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.4519230769230769 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.6009615384615384 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.7091346153846154 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.16826923076923078 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.15064102564102563 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.1201923076923077 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.07091346153846154 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.16826923076923078 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.4519230769230769 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.6009615384615384 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.7091346153846154 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.42955891948336516 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.3405992445054941 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.3484580834493777 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 256 |
|
type: dim_256 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.19230769230769232 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.4543269230769231 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.5913461538461539 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.6899038461538461 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.19230769230769232 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.15144230769230768 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.11826923076923078 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.0689903846153846 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.19230769230769232 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.4543269230769231 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.5913461538461539 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.6899038461538461 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.4311008111471328 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.3488247863247859 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.3560982492053804 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 128 |
|
type: dim_128 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.16346153846153846 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.41586538461538464 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.5168269230769231 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.5985576923076923 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.16346153846153846 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.13862179487179488 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.10336538461538461 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.059855769230769226 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.16346153846153846 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.41586538461538464 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.5168269230769231 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.5985576923076923 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.37641559536404157 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.3052140567765567 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.3151839890893904 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 64 |
|
type: dim_64 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.1658653846153846 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.35096153846153844 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.43990384615384615 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.5288461538461539 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.1658653846153846 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.11698717948717949 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.08798076923076924 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.052884615384615384 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.1658653846153846 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.35096153846153844 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.43990384615384615 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.5288461538461539 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.33823482580826353 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.27800194597069605 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.2876731521968676 |
|
name: Cosine Map@100 |
|
--- |
|
|
|
# bge-base-en-v1.5-klej-dyk |
|
|
|
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:** en |
|
- **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("sentence_transformers_model_id") |
|
# Run inference |
|
sentences = [ |
|
'Herkules na rozstajach', |
|
'jak zinterpretować wymowę obrazu Herkules na rozstajach?', |
|
'Dowódcą grupy był Wiaczesław Razumowicz ps. „Chmara”.', |
|
] |
|
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 | 0.1731 | |
|
| cosine_accuracy@3 | 0.4615 | |
|
| cosine_accuracy@5 | 0.6226 | |
|
| cosine_accuracy@10 | 0.7356 | |
|
| cosine_precision@1 | 0.1731 | |
|
| cosine_precision@3 | 0.1538 | |
|
| cosine_precision@5 | 0.1245 | |
|
| cosine_precision@10 | 0.0736 | |
|
| cosine_recall@1 | 0.1731 | |
|
| cosine_recall@3 | 0.4615 | |
|
| cosine_recall@5 | 0.6226 | |
|
| cosine_recall@10 | 0.7356 | |
|
| cosine_ndcg@10 | 0.4434 | |
|
| cosine_mrr@10 | 0.3505 | |
|
| **cosine_map@100** | **0.3574** | |
|
|
|
#### 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 | 0.1683 | |
|
| cosine_accuracy@3 | 0.4519 | |
|
| cosine_accuracy@5 | 0.601 | |
|
| cosine_accuracy@10 | 0.7091 | |
|
| cosine_precision@1 | 0.1683 | |
|
| cosine_precision@3 | 0.1506 | |
|
| cosine_precision@5 | 0.1202 | |
|
| cosine_precision@10 | 0.0709 | |
|
| cosine_recall@1 | 0.1683 | |
|
| cosine_recall@3 | 0.4519 | |
|
| cosine_recall@5 | 0.601 | |
|
| cosine_recall@10 | 0.7091 | |
|
| cosine_ndcg@10 | 0.4296 | |
|
| cosine_mrr@10 | 0.3406 | |
|
| **cosine_map@100** | **0.3485** | |
|
|
|
#### 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 | 0.1923 | |
|
| cosine_accuracy@3 | 0.4543 | |
|
| cosine_accuracy@5 | 0.5913 | |
|
| cosine_accuracy@10 | 0.6899 | |
|
| cosine_precision@1 | 0.1923 | |
|
| cosine_precision@3 | 0.1514 | |
|
| cosine_precision@5 | 0.1183 | |
|
| cosine_precision@10 | 0.069 | |
|
| cosine_recall@1 | 0.1923 | |
|
| cosine_recall@3 | 0.4543 | |
|
| cosine_recall@5 | 0.5913 | |
|
| cosine_recall@10 | 0.6899 | |
|
| cosine_ndcg@10 | 0.4311 | |
|
| cosine_mrr@10 | 0.3488 | |
|
| **cosine_map@100** | **0.3561** | |
|
|
|
#### 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 | 0.1635 | |
|
| cosine_accuracy@3 | 0.4159 | |
|
| cosine_accuracy@5 | 0.5168 | |
|
| cosine_accuracy@10 | 0.5986 | |
|
| cosine_precision@1 | 0.1635 | |
|
| cosine_precision@3 | 0.1386 | |
|
| cosine_precision@5 | 0.1034 | |
|
| cosine_precision@10 | 0.0599 | |
|
| cosine_recall@1 | 0.1635 | |
|
| cosine_recall@3 | 0.4159 | |
|
| cosine_recall@5 | 0.5168 | |
|
| cosine_recall@10 | 0.5986 | |
|
| cosine_ndcg@10 | 0.3764 | |
|
| cosine_mrr@10 | 0.3052 | |
|
| **cosine_map@100** | **0.3152** | |
|
|
|
#### 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 | 0.1659 | |
|
| cosine_accuracy@3 | 0.351 | |
|
| cosine_accuracy@5 | 0.4399 | |
|
| cosine_accuracy@10 | 0.5288 | |
|
| cosine_precision@1 | 0.1659 | |
|
| cosine_precision@3 | 0.117 | |
|
| cosine_precision@5 | 0.088 | |
|
| cosine_precision@10 | 0.0529 | |
|
| cosine_recall@1 | 0.1659 | |
|
| cosine_recall@3 | 0.351 | |
|
| cosine_recall@5 | 0.4399 | |
|
| cosine_recall@10 | 0.5288 | |
|
| cosine_ndcg@10 | 0.3382 | |
|
| cosine_mrr@10 | 0.278 | |
|
| **cosine_map@100** | **0.2877** | |
|
|
|
<!-- |
|
## 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: 3,738 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: 6 tokens</li><li>mean: 90.01 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 30.82 tokens</li><li>max: 76 tokens</li></ul> | |
|
* Samples: |
|
| positive | anchor | |
|
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------| |
|
| <code>Londyńska premiera w Ambassadors Theatre na londyńskim West Endzie miała miejsce 25 listopada 1952 roku, a przedstawione grane jest do dziś (od 1974 r.) w sąsiednim St Martin's Theatre. W Polsce była wystawiana m.in. w Teatrze Nowym w Zabrzu.</code> | <code>w którym londyńskim muzeum wystawiana była instalacja My Bed?</code> | |
|
| <code>Theridion grallator osiąga długość 5 mm. U niektórych postaci na żółtym odwłoku występuje wzór przypominający uśmiechniętą lub śmiejącą się twarz klowna.</code> | <code>które pająki noszą na grzbiecie wzór przypominający uśmiechniętego klauna?</code> | |
|
| <code>W 1998 w wyniku sporów o wytyczenie granicy między dwoma państwami wybuchła wojna erytrejsko-etiopska. Zakończyła się porozumieniem zawartym w Algierze 12 grudnia 2000. Od tego czasu strefa graniczna jest patrolowana przez siły pokojowe ONZ.</code> | <code>jakie były skutki wojny erytrejsko-etiopskiej?</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`: 16 |
|
- `per_device_eval_batch_size`: 16 |
|
- `gradient_accumulation_steps`: 16 |
|
- `learning_rate`: 2e-05 |
|
- `num_train_epochs`: 10 |
|
- `lr_scheduler_type`: cosine |
|
- `warmup_ratio`: 0.1 |
|
- `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 |
|
- `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`: 10 |
|
- `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`: 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 |
|
- `batch_sampler`: no_duplicates |
|
- `multi_dataset_batch_sampler`: proportional |
|
|
|
</details> |
|
|
|
### Training Logs |
|
<details><summary>Click to expand</summary> |
|
|
|
| Epoch | Step | Training Loss | 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 | |
|
|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:| |
|
| 0.0684 | 1 | 7.2706 | - | - | - | - | - | |
|
| 0.1368 | 2 | 8.2776 | - | - | - | - | - | |
|
| 0.2051 | 3 | 7.1399 | - | - | - | - | - | |
|
| 0.2735 | 4 | 6.6905 | - | - | - | - | - | |
|
| 0.3419 | 5 | 6.735 | - | - | - | - | - | |
|
| 0.4103 | 6 | 7.0537 | - | - | - | - | - | |
|
| 0.4786 | 7 | 6.871 | - | - | - | - | - | |
|
| 0.5470 | 8 | 6.7277 | - | - | - | - | - | |
|
| 0.6154 | 9 | 5.9853 | - | - | - | - | - | |
|
| 0.6838 | 10 | 6.0518 | - | - | - | - | - | |
|
| 0.7521 | 11 | 5.8291 | - | - | - | - | - | |
|
| 0.8205 | 12 | 5.0064 | - | - | - | - | - | |
|
| 0.8889 | 13 | 4.8572 | - | - | - | - | - | |
|
| 0.9573 | 14 | 5.1899 | 0.2812 | 0.3335 | 0.3486 | 0.2115 | 0.3639 | |
|
| 1.0256 | 15 | 4.2996 | - | - | - | - | - | |
|
| 1.0940 | 16 | 4.1475 | - | - | - | - | - | |
|
| 1.1624 | 17 | 4.6174 | - | - | - | - | - | |
|
| 1.2308 | 18 | 4.394 | - | - | - | - | - | |
|
| 1.2991 | 19 | 4.0255 | - | - | - | - | - | |
|
| 1.3675 | 20 | 3.9722 | - | - | - | - | - | |
|
| 1.4359 | 21 | 3.9509 | - | - | - | - | - | |
|
| 1.5043 | 22 | 3.7674 | - | - | - | - | - | |
|
| 1.5726 | 23 | 3.7572 | - | - | - | - | - | |
|
| 1.6410 | 24 | 3.9463 | - | - | - | - | - | |
|
| 1.7094 | 25 | 3.7151 | - | - | - | - | - | |
|
| 1.7778 | 26 | 3.7771 | - | - | - | - | - | |
|
| 1.8462 | 27 | 3.5228 | - | - | - | - | - | |
|
| 1.9145 | 28 | 2.7906 | - | - | - | - | - | |
|
| 1.9829 | 29 | 3.4555 | 0.3164 | 0.3529 | 0.3641 | 0.2636 | 0.3681 | |
|
| 2.0513 | 30 | 2.737 | - | - | - | - | - | |
|
| 2.1197 | 31 | 3.1976 | - | - | - | - | - | |
|
| 2.1880 | 32 | 3.1363 | - | - | - | - | - | |
|
| 2.2564 | 33 | 2.9706 | - | - | - | - | - | |
|
| 2.3248 | 34 | 2.9629 | - | - | - | - | - | |
|
| 2.3932 | 35 | 2.7226 | - | - | - | - | - | |
|
| 2.4615 | 36 | 2.4378 | - | - | - | - | - | |
|
| 2.5299 | 37 | 2.7201 | - | - | - | - | - | |
|
| 2.5983 | 38 | 2.6802 | - | - | - | - | - | |
|
| 2.6667 | 39 | 3.1613 | - | - | - | - | - | |
|
| 2.7350 | 40 | 2.9344 | - | - | - | - | - | |
|
| 2.8034 | 41 | 2.5254 | - | - | - | - | - | |
|
| 2.8718 | 42 | 2.5617 | - | - | - | - | - | |
|
| 2.9402 | 43 | 2.459 | 0.3197 | 0.3571 | 0.3640 | 0.2739 | 0.3733 | |
|
| 3.0085 | 44 | 2.3785 | - | - | - | - | - | |
|
| 3.0769 | 45 | 1.9408 | - | - | - | - | - | |
|
| 3.1453 | 46 | 2.7095 | - | - | - | - | - | |
|
| 3.2137 | 47 | 2.4774 | - | - | - | - | - | |
|
| 3.2821 | 48 | 2.2178 | - | - | - | - | - | |
|
| 3.3504 | 49 | 2.0884 | - | - | - | - | - | |
|
| 3.4188 | 50 | 2.1044 | - | - | - | - | - | |
|
| 3.4872 | 51 | 2.1504 | - | - | - | - | - | |
|
| 3.5556 | 52 | 2.1177 | - | - | - | - | - | |
|
| 3.6239 | 53 | 2.2283 | - | - | - | - | - | |
|
| 3.6923 | 54 | 2.3964 | - | - | - | - | - | |
|
| 3.7607 | 55 | 2.0972 | - | - | - | - | - | |
|
| 3.8291 | 56 | 2.0961 | - | - | - | - | - | |
|
| 3.8974 | 57 | 1.783 | - | - | - | - | - | |
|
| **3.9658** | **58** | **2.1031** | **0.3246** | **0.3533** | **0.3603** | **0.2829** | **0.3687** | |
|
| 4.0342 | 59 | 1.6699 | - | - | - | - | - | |
|
| 4.1026 | 60 | 1.6675 | - | - | - | - | - | |
|
| 4.1709 | 61 | 2.1672 | - | - | - | - | - | |
|
| 4.2393 | 62 | 1.8881 | - | - | - | - | - | |
|
| 4.3077 | 63 | 1.701 | - | - | - | - | - | |
|
| 4.3761 | 64 | 1.9154 | - | - | - | - | - | |
|
| 4.4444 | 65 | 1.4549 | - | - | - | - | - | |
|
| 4.5128 | 66 | 1.5444 | - | - | - | - | - | |
|
| 4.5812 | 67 | 1.8352 | - | - | - | - | - | |
|
| 4.6496 | 68 | 1.7908 | - | - | - | - | - | |
|
| 4.7179 | 69 | 1.6876 | - | - | - | - | - | |
|
| 4.7863 | 70 | 1.7366 | - | - | - | - | - | |
|
| 4.8547 | 71 | 1.8689 | - | - | - | - | - | |
|
| 4.9231 | 72 | 1.4676 | - | - | - | - | - | |
|
| 4.9915 | 73 | 1.5045 | 0.3170 | 0.3538 | 0.3606 | 0.2829 | 0.3675 | |
|
| 5.0598 | 74 | 1.2155 | - | - | - | - | - | |
|
| 5.1282 | 75 | 1.4365 | - | - | - | - | - | |
|
| 5.1966 | 76 | 1.7451 | - | - | - | - | - | |
|
| 5.2650 | 77 | 1.4537 | - | - | - | - | - | |
|
| 5.3333 | 78 | 1.3813 | - | - | - | - | - | |
|
| 5.4017 | 79 | 1.4035 | - | - | - | - | - | |
|
| 5.4701 | 80 | 1.3912 | - | - | - | - | - | |
|
| 5.5385 | 81 | 1.3286 | - | - | - | - | - | |
|
| 5.6068 | 82 | 1.5153 | - | - | - | - | - | |
|
| 5.6752 | 83 | 1.6745 | - | - | - | - | - | |
|
| 5.7436 | 84 | 1.4323 | - | - | - | - | - | |
|
| 5.8120 | 85 | 1.5299 | - | - | - | - | - | |
|
| 5.8803 | 86 | 1.488 | - | - | - | - | - | |
|
| 5.9487 | 87 | 1.5195 | 0.3206 | 0.3556 | 0.3530 | 0.2878 | 0.3605 | |
|
| 6.0171 | 88 | 1.2999 | - | - | - | - | - | |
|
| 6.0855 | 89 | 1.1511 | - | - | - | - | - | |
|
| 6.1538 | 90 | 1.552 | - | - | - | - | - | |
|
| 6.2222 | 91 | 1.35 | - | - | - | - | - | |
|
| 6.2906 | 92 | 1.218 | - | - | - | - | - | |
|
| 6.3590 | 93 | 1.1712 | - | - | - | - | - | |
|
| 6.4274 | 94 | 1.3381 | - | - | - | - | - | |
|
| 6.4957 | 95 | 1.1716 | - | - | - | - | - | |
|
| 6.5641 | 96 | 1.2117 | - | - | - | - | - | |
|
| 6.6325 | 97 | 1.5349 | - | - | - | - | - | |
|
| 6.7009 | 98 | 1.4564 | - | - | - | - | - | |
|
| 6.7692 | 99 | 1.3541 | - | - | - | - | - | |
|
| 6.8376 | 100 | 1.2468 | - | - | - | - | - | |
|
| 6.9060 | 101 | 1.1519 | - | - | - | - | - | |
|
| 6.9744 | 102 | 1.2421 | 0.3150 | 0.3555 | 0.3501 | 0.2858 | 0.3575 | |
|
| 7.0427 | 103 | 1.0096 | - | - | - | - | - | |
|
| 7.1111 | 104 | 1.1405 | - | - | - | - | - | |
|
| 7.1795 | 105 | 1.2958 | - | - | - | - | - | |
|
| 7.2479 | 106 | 1.35 | - | - | - | - | - | |
|
| 7.3162 | 107 | 1.1291 | - | - | - | - | - | |
|
| 7.3846 | 108 | 0.9968 | - | - | - | - | - | |
|
| 7.4530 | 109 | 1.0454 | - | - | - | - | - | |
|
| 7.5214 | 110 | 1.102 | - | - | - | - | - | |
|
| 7.5897 | 111 | 1.1328 | - | - | - | - | - | |
|
| 7.6581 | 112 | 1.5988 | - | - | - | - | - | |
|
| 7.7265 | 113 | 1.2992 | - | - | - | - | - | |
|
| 7.7949 | 114 | 1.2572 | - | - | - | - | - | |
|
| 7.8632 | 115 | 1.1414 | - | - | - | - | - | |
|
| 7.9316 | 116 | 1.1432 | - | - | - | - | - | |
|
| 8.0 | 117 | 1.1181 | 0.3154 | 0.3545 | 0.3509 | 0.2884 | 0.3578 | |
|
| 8.0684 | 118 | 0.9365 | - | - | - | - | - | |
|
| 8.1368 | 119 | 1.3286 | - | - | - | - | - | |
|
| 8.2051 | 120 | 1.3711 | - | - | - | - | - | |
|
| 8.2735 | 121 | 1.2001 | - | - | - | - | - | |
|
| 8.3419 | 122 | 1.165 | - | - | - | - | - | |
|
| 8.4103 | 123 | 1.0575 | - | - | - | - | - | |
|
| 8.4786 | 124 | 1.105 | - | - | - | - | - | |
|
| 8.5470 | 125 | 1.077 | - | - | - | - | - | |
|
| 8.6154 | 126 | 1.2217 | - | - | - | - | - | |
|
| 8.6838 | 127 | 1.3254 | - | - | - | - | - | |
|
| 8.7521 | 128 | 1.2165 | - | - | - | - | - | |
|
| 8.8205 | 129 | 1.3021 | - | - | - | - | - | |
|
| 8.8889 | 130 | 1.0927 | - | - | - | - | - | |
|
| 8.9573 | 131 | 1.3961 | 0.3150 | 0.3540 | 0.3490 | 0.2882 | 0.3588 | |
|
| 9.0256 | 132 | 1.0779 | - | - | - | - | - | |
|
| 9.0940 | 133 | 0.901 | - | - | - | - | - | |
|
| 9.1624 | 134 | 1.313 | - | - | - | - | - | |
|
| 9.2308 | 135 | 1.1409 | - | - | - | - | - | |
|
| 9.2991 | 136 | 1.1635 | - | - | - | - | - | |
|
| 9.3675 | 137 | 1.0244 | - | - | - | - | - | |
|
| 9.4359 | 138 | 1.0576 | - | - | - | - | - | |
|
| 9.5043 | 139 | 1.0101 | - | - | - | - | - | |
|
| 9.5726 | 140 | 1.1516 | 0.3152 | 0.3561 | 0.3485 | 0.2877 | 0.3574 | |
|
|
|
* The bold row denotes the saved checkpoint. |
|
</details> |
|
|
|
### Framework Versions |
|
- Python: 3.12.2 |
|
- Sentence Transformers: 3.0.0 |
|
- Transformers: 4.41.2 |
|
- PyTorch: 2.3.1 |
|
- Accelerate: 0.27.2 |
|
- Datasets: 2.19.1 |
|
- Tokenizers: 0.19.1 |
|
|
|
## Citation |
|
|
|
### BibTeX |
|
|
|
#### Sentence Transformers |
|
```bibtex |
|
@inproceedings{reimers-2019-sentence-bert, |
|
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", |
|
author = "Reimers, Nils and Gurevych, Iryna", |
|
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", |
|
month = "11", |
|
year = "2019", |
|
publisher = "Association for Computational Linguistics", |
|
url = "https://arxiv.org/abs/1908.10084", |
|
} |
|
``` |
|
|
|
#### 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.* |
|
--> |
