|
--- |
|
base_model: liddlefish/privacy_embedding_rag_10k_base_checkpoint_2 |
|
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: Żywot św. Stanisława |
|
sentences: |
|
- czym różni się Żywot św. Stanisława od Legendy św. Stanisława? |
|
- czemu gra The Saboteur wywołała wiele kontrowersji? |
|
- Muzykę do obrazu skomponowali Marco Frisina i Ennio Morricone. |
|
- source_sentence: Jaakow Jicchak Szapira |
|
sentences: |
|
- cadykiem którego miasta był Jaakow Jicchak Dan Landau? |
|
- gdzie zginął przedwojenny minister Antoni Olszewski? |
|
- ' W 1867 oddano do użytku Kolej Warszawsko-Terespolską (całą linię).' |
|
- source_sentence: Chłopiec z Nariokotome |
|
sentences: |
|
- ile wynosiła objętość mózgu chłopca z Nariokotome? |
|
- czemu gra The Saboteur wywołała wiele kontrowersji? |
|
- Akcja powieści rozgrywa się w XV-wiecznej Polsce. |
|
- source_sentence: Stany Zjednoczone Polski |
|
sentences: |
|
- kiedy miały szansę powstać Stany Zjednoczone Polski? |
|
- z jakiego powodu Chloé wywołała skandal w Melbourne? |
|
- komu przysługiwał tytuł autokratora? |
|
- source_sentence: Sen o zastrzyku Irmy |
|
sentences: |
|
- gdzie Freud spotkał Irmę we śnie o zastrzyku Irmy? |
|
- dlaczego Ōkunoshima została wymazana z map Japonii? |
|
- który samochód wyglądem nawiązuje do Mercedesa-Benza SLS AMG? |
|
model-index: |
|
- name: privacy_embedding_rag_10k_base_checkpoint_2-klej-dyk-v0.1 |
|
results: |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 768 |
|
type: dim_768 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.1875 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.4543269230769231 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.6225961538461539 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.7307692307692307 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.1875 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.15144230769230768 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.12451923076923076 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.07307692307692307 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.1875 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.4543269230769231 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.6225961538461539 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.7307692307692307 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.4453345212200682 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.35500896672771654 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.36239083059244687 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 512 |
|
type: dim_512 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.18269230769230768 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.44471153846153844 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.6033653846153846 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.7115384615384616 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.18269230769230768 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.14823717948717946 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.12067307692307691 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.07115384615384614 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.18269230769230768 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.44471153846153844 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.6033653846153846 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.7115384615384616 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.43488982498130374 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.347151633089133 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.3548109777991144 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 256 |
|
type: dim_256 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.1875 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.4230769230769231 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.5576923076923077 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.6682692307692307 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.1875 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.14102564102564102 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.11153846153846153 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.06682692307692308 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.1875 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.4230769230769231 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.5576923076923077 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.6682692307692307 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.41398239515933494 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.3336862789987789 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.3427233175204077 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 128 |
|
type: dim_128 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.17067307692307693 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.36778846153846156 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.5120192307692307 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.6009615384615384 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.17067307692307693 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.12259615384615384 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.10240384615384614 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.06009615384615385 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.17067307692307693 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.36778846153846156 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.5120192307692307 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.6009615384615384 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.371201964014572 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.2987818605006104 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.3066873839005868 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 64 |
|
type: dim_64 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.15865384615384615 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.31009615384615385 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.3870192307692308 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.49278846153846156 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.15865384615384615 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.10336538461538461 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.07740384615384616 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.04927884615384615 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.15865384615384615 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.31009615384615385 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.3870192307692308 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.49278846153846156 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.3130531482964966 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.2569225045787546 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.2651139739879426 |
|
name: Cosine Map@100 |
|
--- |
|
|
|
# privacy_embedding_rag_10k_base_checkpoint_2-klej-dyk-v0.1 |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [liddlefish/privacy_embedding_rag_10k_base_checkpoint_2](https://huggingface.co/liddlefish/privacy_embedding_rag_10k_base_checkpoint_2). 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:** [liddlefish/privacy_embedding_rag_10k_base_checkpoint_2](https://huggingface.co/liddlefish/privacy_embedding_rag_10k_base_checkpoint_2) <!-- at revision 2ef6f7a59388ab4473ddb885ecc27a40c09f5802 --> |
|
- **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 = [ |
|
'Sen o zastrzyku Irmy', |
|
'gdzie Freud spotkał Irmę we śnie o zastrzyku Irmy?', |
|
'dlaczego Ōkunoshima została wymazana z map Japonii?', |
|
] |
|
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 | 0.1875 | |
|
| cosine_accuracy@3 | 0.4543 | |
|
| cosine_accuracy@5 | 0.6226 | |
|
| cosine_accuracy@10 | 0.7308 | |
|
| cosine_precision@1 | 0.1875 | |
|
| cosine_precision@3 | 0.1514 | |
|
| cosine_precision@5 | 0.1245 | |
|
| cosine_precision@10 | 0.0731 | |
|
| cosine_recall@1 | 0.1875 | |
|
| cosine_recall@3 | 0.4543 | |
|
| cosine_recall@5 | 0.6226 | |
|
| cosine_recall@10 | 0.7308 | |
|
| cosine_ndcg@10 | 0.4453 | |
|
| cosine_mrr@10 | 0.355 | |
|
| **cosine_map@100** | **0.3624** | |
|
|
|
#### 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 | 0.1827 | |
|
| cosine_accuracy@3 | 0.4447 | |
|
| cosine_accuracy@5 | 0.6034 | |
|
| cosine_accuracy@10 | 0.7115 | |
|
| cosine_precision@1 | 0.1827 | |
|
| cosine_precision@3 | 0.1482 | |
|
| cosine_precision@5 | 0.1207 | |
|
| cosine_precision@10 | 0.0712 | |
|
| cosine_recall@1 | 0.1827 | |
|
| cosine_recall@3 | 0.4447 | |
|
| cosine_recall@5 | 0.6034 | |
|
| cosine_recall@10 | 0.7115 | |
|
| cosine_ndcg@10 | 0.4349 | |
|
| cosine_mrr@10 | 0.3472 | |
|
| **cosine_map@100** | **0.3548** | |
|
|
|
#### 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 | 0.1875 | |
|
| cosine_accuracy@3 | 0.4231 | |
|
| cosine_accuracy@5 | 0.5577 | |
|
| cosine_accuracy@10 | 0.6683 | |
|
| cosine_precision@1 | 0.1875 | |
|
| cosine_precision@3 | 0.141 | |
|
| cosine_precision@5 | 0.1115 | |
|
| cosine_precision@10 | 0.0668 | |
|
| cosine_recall@1 | 0.1875 | |
|
| cosine_recall@3 | 0.4231 | |
|
| cosine_recall@5 | 0.5577 | |
|
| cosine_recall@10 | 0.6683 | |
|
| cosine_ndcg@10 | 0.414 | |
|
| cosine_mrr@10 | 0.3337 | |
|
| **cosine_map@100** | **0.3427** | |
|
|
|
#### 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 | 0.1707 | |
|
| cosine_accuracy@3 | 0.3678 | |
|
| cosine_accuracy@5 | 0.512 | |
|
| cosine_accuracy@10 | 0.601 | |
|
| cosine_precision@1 | 0.1707 | |
|
| cosine_precision@3 | 0.1226 | |
|
| cosine_precision@5 | 0.1024 | |
|
| cosine_precision@10 | 0.0601 | |
|
| cosine_recall@1 | 0.1707 | |
|
| cosine_recall@3 | 0.3678 | |
|
| cosine_recall@5 | 0.512 | |
|
| cosine_recall@10 | 0.601 | |
|
| cosine_ndcg@10 | 0.3712 | |
|
| cosine_mrr@10 | 0.2988 | |
|
| **cosine_map@100** | **0.3067** | |
|
|
|
#### 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 | 0.1587 | |
|
| cosine_accuracy@3 | 0.3101 | |
|
| cosine_accuracy@5 | 0.387 | |
|
| cosine_accuracy@10 | 0.4928 | |
|
| cosine_precision@1 | 0.1587 | |
|
| cosine_precision@3 | 0.1034 | |
|
| cosine_precision@5 | 0.0774 | |
|
| cosine_precision@10 | 0.0493 | |
|
| cosine_recall@1 | 0.1587 | |
|
| cosine_recall@3 | 0.3101 | |
|
| cosine_recall@5 | 0.387 | |
|
| cosine_recall@10 | 0.4928 | |
|
| cosine_ndcg@10 | 0.3131 | |
|
| cosine_mrr@10 | 0.2569 | |
|
| **cosine_map@100** | **0.2651** | |
|
|
|
<!-- |
|
## 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: 7 tokens</li><li>mean: 89.43 tokens</li><li>max: 507 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 30.98 tokens</li><li>max: 76 tokens</li></ul> | |
|
* Samples: |
|
| positive | anchor | |
|
|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------| |
|
| <code>Zespół Blaua (zespół Jabsa, ang. Blau syndrome, BS) – rzadka choroba genetyczna o dziedziczeniu autosomalnym dominującym, charakteryzująca się ziarniniakowym zapaleniem stawów o wczesnym początku, zapaleniem jagodówki (uveitis) i wysypką skórną, a także kamptodaktylią.</code> | <code>jakie choroby genetyczne dziedziczą się autosomalnie dominująco?</code> | |
|
| <code>Gorgippia Gorgippia – starożytne miasto bosporańskie nad Morzem Czarnym, którego pozostałości znajdują się obecnie pod współczesną zabudową centralnej części miasta Anapa w Kraju Krasnodarskim w Rosji.</code> | <code>gdzie obecnie znajduje się starożytne miasto Gorgippia?</code> | |
|
| <code>Ulubionym dystansem Rücker było 400 metrów i to na nim notowała największe indywidualne sukcesy : srebrny medal Mistrzostw Europy juniorów w lekkoatletyce (Saloniki 1991) 6. miejsce w Pucharze Świata w Lekkoatletyce (Hawana 1992) 5. miejsce na Mistrzostwach Europy w Lekkoatletyce (Helsinki 1994) srebro podczas Mistrzostw Świata w Lekkoatletyce (Sewilla 1999) złota medalistka mistrzostw Niemiec Duże sukcesy odnosiła także w sztafecie 4 x 400 metrów : złoto Mistrzostw Europy juniorów w lekkoatletyce (Varaždin 1989) złoty medal Mistrzostw Europy juniorów w lekkoatletyce (Saloniki 1991) brąz na Mistrzostwach Europy w Lekkoatletyce (Helsinki 1994) brązowy medal podczas Igrzysk Olimpijskich (Atlanta 1996) brąz na Halowych Mistrzostwach Świata w Lekkoatletyce (Paryż 1997) złoto Mistrzostw Świata w Lekkoatletyce (Ateny 1997) brązowy medal Mistrzostw Świata w Lekkoatletyce (Sewilla 1999)</code> | <code>kto zaprojektował medale, które będą wręczane podczas tegorocznych mistrzostw Europy juniorów w lekkoatletyce?</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`: 5 |
|
- `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`: 5 |
|
- `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 |
|
| 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 | 9.112 | - | - | - | - | - | |
|
| 0.1368 | 2 | 9.5133 | - | - | - | - | - | |
|
| 0.2051 | 3 | 9.0946 | - | - | - | - | - | |
|
| 0.2735 | 4 | 8.9744 | - | - | - | - | - | |
|
| 0.3419 | 5 | 7.9039 | - | - | - | - | - | |
|
| 0.4103 | 6 | 8.1973 | - | - | - | - | - | |
|
| 0.4786 | 7 | 6.8979 | - | - | - | - | - | |
|
| 0.5470 | 8 | 7.0324 | - | - | - | - | - | |
|
| 0.6154 | 9 | 6.6472 | - | - | - | - | - | |
|
| 0.6838 | 10 | 6.3009 | - | - | - | - | - | |
|
| 0.7521 | 11 | 6.8778 | - | - | - | - | - | |
|
| 0.8205 | 12 | 5.9809 | - | - | - | - | - | |
|
| 0.8889 | 13 | 5.3054 | - | - | - | - | - | |
|
| 0.9573 | 14 | 5.706 | 0.2868 | 0.3280 | 0.3522 | 0.2415 | 0.3477 | |
|
| 1.0256 | 15 | 5.0592 | - | - | - | - | - | |
|
| 1.0940 | 16 | 4.7655 | - | - | - | - | - | |
|
| 1.1624 | 17 | 4.9682 | - | - | - | - | - | |
|
| 1.2308 | 18 | 5.1226 | - | - | - | - | - | |
|
| 1.2991 | 19 | 4.8655 | - | - | - | - | - | |
|
| 1.3675 | 20 | 4.2008 | - | - | - | - | - | |
|
| 1.4359 | 21 | 5.0281 | - | - | - | - | - | |
|
| 1.5043 | 22 | 4.3074 | - | - | - | - | - | |
|
| 1.5726 | 23 | 4.3163 | - | - | - | - | - | |
|
| 1.6410 | 24 | 3.9344 | - | - | - | - | - | |
|
| 1.7094 | 25 | 4.6567 | - | - | - | - | - | |
|
| 1.7778 | 26 | 4.5145 | - | - | - | - | - | |
|
| 1.8462 | 27 | 4.1319 | - | - | - | - | - | |
|
| 1.9145 | 28 | 3.8768 | - | - | - | - | - | |
|
| 1.9829 | 29 | 3.5525 | 0.2986 | 0.3330 | 0.3483 | 0.2590 | 0.3534 | |
|
| 2.0513 | 30 | 3.8693 | - | - | - | - | - | |
|
| 2.1197 | 31 | 3.4675 | - | - | - | - | - | |
|
| 2.1880 | 32 | 4.0598 | - | - | - | - | - | |
|
| 2.2564 | 33 | 4.2429 | - | - | - | - | - | |
|
| 2.3248 | 34 | 3.3686 | - | - | - | - | - | |
|
| 2.3932 | 35 | 3.2663 | - | - | - | - | - | |
|
| 2.4615 | 36 | 3.8585 | - | - | - | - | - | |
|
| 2.5299 | 37 | 3.1157 | - | - | - | - | - | |
|
| 2.5983 | 38 | 3.5254 | - | - | - | - | - | |
|
| 2.6667 | 39 | 3.2782 | - | - | - | - | - | |
|
| 2.7350 | 40 | 4.3151 | - | - | - | - | - | |
|
| 2.8034 | 41 | 3.4567 | - | - | - | - | - | |
|
| 2.8718 | 42 | 3.3976 | - | - | - | - | - | |
|
| 2.9402 | 43 | 3.3945 | 0.3014 | 0.3343 | 0.3522 | 0.2626 | 0.3593 | |
|
| 3.0085 | 44 | 3.4487 | - | - | - | - | - | |
|
| 3.0769 | 45 | 3.0021 | - | - | - | - | - | |
|
| 3.1453 | 46 | 3.2332 | - | - | - | - | - | |
|
| 3.2137 | 47 | 3.3012 | - | - | - | - | - | |
|
| 3.2821 | 48 | 3.2735 | - | - | - | - | - | |
|
| 3.3504 | 49 | 2.5335 | - | - | - | - | - | |
|
| 3.4188 | 50 | 3.7025 | - | - | - | - | - | |
|
| 3.4872 | 51 | 2.8596 | - | - | - | - | - | |
|
| 3.5556 | 52 | 3.1108 | - | - | - | - | - | |
|
| 3.6239 | 53 | 3.2807 | - | - | - | - | - | |
|
| 3.6923 | 54 | 3.1604 | - | - | - | - | - | |
|
| 3.7607 | 55 | 3.7179 | - | - | - | - | - | |
|
| 3.8291 | 56 | 3.3418 | - | - | - | - | - | |
|
| 3.8974 | 57 | 2.9735 | - | - | - | - | - | |
|
| 3.9658 | 58 | 3.2755 | 0.3066 | 0.3409 | 0.3546 | 0.2653 | 0.3626 | |
|
| 4.0342 | 59 | 3.1444 | - | - | - | - | - | |
|
| 4.1026 | 60 | 3.0212 | - | - | - | - | - | |
|
| 4.1709 | 61 | 3.1298 | - | - | - | - | - | |
|
| 4.2393 | 62 | 3.3195 | - | - | - | - | - | |
|
| 4.3077 | 63 | 2.996 | - | - | - | - | - | |
|
| 4.3761 | 64 | 2.4636 | - | - | - | - | - | |
|
| 4.4444 | 65 | 3.2388 | - | - | - | - | - | |
|
| 4.5128 | 66 | 2.747 | - | - | - | - | - | |
|
| 4.5812 | 67 | 2.8715 | - | - | - | - | - | |
|
| 4.6496 | 68 | 3.1402 | - | - | - | - | - | |
|
| 4.7179 | 69 | 3.547 | - | - | - | - | - | |
|
| **4.7863** | **70** | **3.6094** | **0.3067** | **0.3427** | **0.3548** | **0.2651** | **0.3624** | |
|
|
|
* The bold row denotes the saved checkpoint. |
|
|
|
### 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.* |
|
--> |
