|
--- |
|
base_model: sentence-transformers/all-MiniLM-L6-v2 |
|
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? |
|
- kto uczył malarstwa olimpijczyka Bronisława Czecha? |
|
- St. Louis Eagles |
|
- source_sentence: Jaakow Jicchak Szapira |
|
sentences: |
|
- czym jest Kompas Sztuki? |
|
- z czego wykonana jest rzeźba Robotnik i kołchoźnica? |
|
- podczas którego soboru zostało ogłoszone chalcedońskie wyznanie wiary? |
|
- source_sentence: Chłopiec z Nariokotome |
|
sentences: |
|
- ile wynosiła objętość mózgu chłopca z Nariokotome? |
|
- jaki pomnik odsłonięto we Lwowie 3 lipca 2011 roku? |
|
- Voyager 2 Voyager Golden Record Pale Blue Dot |
|
- source_sentence: skąd pochodzi wino cirò? |
|
sentences: |
|
- skąd pochodzi nazwa Kotylniczy Wierch? |
|
- do czego współcześnie wykorzystuje się papier amate? |
|
- erystyka sofizmat błędy logiczno-językowe onus probandi |
|
- source_sentence: Sen o zastrzyku Irmy |
|
sentences: |
|
- gdzie Freud spotkał Irmę we śnie o zastrzyku Irmy? |
|
- ile razy Srebrna Biblia była przywożona do Szwecji? |
|
- Voyager 2 Voyager Golden Record Pale Blue Dot |
|
model-index: |
|
- name: all-MiniLM-L6-v2-klej-dyk-v0.1 |
|
results: |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 384 |
|
type: dim_384 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.19951923076923078 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.43028846153846156 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.5384615384615384 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.6225961538461539 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.19951923076923078 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.14342948717948717 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.10769230769230768 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.06225961538461538 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.19951923076923078 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.43028846153846156 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.5384615384615384 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.6225961538461539 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.4067615454626299 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.3376678876678877 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.3451711286911671 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 256 |
|
type: dim_256 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.18509615384615385 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.41346153846153844 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.5096153846153846 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.6033653846153846 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.18509615384615385 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.1378205128205128 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.10192307692307692 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.06033653846153846 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.18509615384615385 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.41346153846153844 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.5096153846153846 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.6033653846153846 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.39112028533472887 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.32341746794871795 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.3303671597529028 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 128 |
|
type: dim_128 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.18028846153846154 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.35336538461538464 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.4423076923076923 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.5192307692307693 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.18028846153846154 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.11778846153846154 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.08846153846153845 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.05192307692307692 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.18028846153846154 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.35336538461538464 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.4423076923076923 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.5192307692307693 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.3443315125767603 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.2888621794871794 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.2960334956693037 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 64 |
|
type: dim_64 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.13701923076923078 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.2644230769230769 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.32211538461538464 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.3798076923076923 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.13701923076923078 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.08814102564102563 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.06442307692307693 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.03798076923076923 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.13701923076923078 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.2644230769230769 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.32211538461538464 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.3798076923076923 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.2529381675019326 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.21289396367521363 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.2208612925846397 |
|
name: Cosine Map@100 |
|
--- |
|
|
|
# all-MiniLM-L6-v2-klej-dyk-v0.1 |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision 8b3219a92973c328a8e22fadcfa821b5dc75636a --> |
|
- **Maximum Sequence Length:** 256 tokens |
|
- **Output Dimensionality:** 384 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': 256, 'do_lower_case': False}) with Transformer model: BertModel |
|
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) |
|
(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?', |
|
'ile razy Srebrna Biblia była przywożona do Szwecji?', |
|
] |
|
embeddings = model.encode(sentences) |
|
print(embeddings.shape) |
|
# [3, 384] |
|
|
|
# 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_384` |
|
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) |
|
|
|
| Metric | Value | |
|
|:--------------------|:-----------| |
|
| cosine_accuracy@1 | 0.1995 | |
|
| cosine_accuracy@3 | 0.4303 | |
|
| cosine_accuracy@5 | 0.5385 | |
|
| cosine_accuracy@10 | 0.6226 | |
|
| cosine_precision@1 | 0.1995 | |
|
| cosine_precision@3 | 0.1434 | |
|
| cosine_precision@5 | 0.1077 | |
|
| cosine_precision@10 | 0.0623 | |
|
| cosine_recall@1 | 0.1995 | |
|
| cosine_recall@3 | 0.4303 | |
|
| cosine_recall@5 | 0.5385 | |
|
| cosine_recall@10 | 0.6226 | |
|
| cosine_ndcg@10 | 0.4068 | |
|
| cosine_mrr@10 | 0.3377 | |
|
| **cosine_map@100** | **0.3452** | |
|
|
|
#### 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 | 0.1851 | |
|
| cosine_accuracy@3 | 0.4135 | |
|
| cosine_accuracy@5 | 0.5096 | |
|
| cosine_accuracy@10 | 0.6034 | |
|
| cosine_precision@1 | 0.1851 | |
|
| cosine_precision@3 | 0.1378 | |
|
| cosine_precision@5 | 0.1019 | |
|
| cosine_precision@10 | 0.0603 | |
|
| cosine_recall@1 | 0.1851 | |
|
| cosine_recall@3 | 0.4135 | |
|
| cosine_recall@5 | 0.5096 | |
|
| cosine_recall@10 | 0.6034 | |
|
| cosine_ndcg@10 | 0.3911 | |
|
| cosine_mrr@10 | 0.3234 | |
|
| **cosine_map@100** | **0.3304** | |
|
|
|
#### 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 | 0.1803 | |
|
| cosine_accuracy@3 | 0.3534 | |
|
| cosine_accuracy@5 | 0.4423 | |
|
| cosine_accuracy@10 | 0.5192 | |
|
| cosine_precision@1 | 0.1803 | |
|
| cosine_precision@3 | 0.1178 | |
|
| cosine_precision@5 | 0.0885 | |
|
| cosine_precision@10 | 0.0519 | |
|
| cosine_recall@1 | 0.1803 | |
|
| cosine_recall@3 | 0.3534 | |
|
| cosine_recall@5 | 0.4423 | |
|
| cosine_recall@10 | 0.5192 | |
|
| cosine_ndcg@10 | 0.3443 | |
|
| cosine_mrr@10 | 0.2889 | |
|
| **cosine_map@100** | **0.296** | |
|
|
|
#### 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 | 0.137 | |
|
| cosine_accuracy@3 | 0.2644 | |
|
| cosine_accuracy@5 | 0.3221 | |
|
| cosine_accuracy@10 | 0.3798 | |
|
| cosine_precision@1 | 0.137 | |
|
| cosine_precision@3 | 0.0881 | |
|
| cosine_precision@5 | 0.0644 | |
|
| cosine_precision@10 | 0.038 | |
|
| cosine_recall@1 | 0.137 | |
|
| cosine_recall@3 | 0.2644 | |
|
| cosine_recall@5 | 0.3221 | |
|
| cosine_recall@10 | 0.3798 | |
|
| cosine_ndcg@10 | 0.2529 | |
|
| cosine_mrr@10 | 0.2129 | |
|
| **cosine_map@100** | **0.2209** | |
|
|
|
<!-- |
|
## 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: 87.54 tokens</li><li>max: 256 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": [ |
|
384, |
|
256, |
|
128, |
|
64 |
|
], |
|
"matryoshka_weights": [ |
|
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`: 32 |
|
- `gradient_accumulation_steps`: 32 |
|
- `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`: 32 |
|
- `per_device_eval_batch_size`: 32 |
|
- `per_gpu_train_batch_size`: None |
|
- `per_gpu_eval_batch_size`: None |
|
- `gradient_accumulation_steps`: 32 |
|
- `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_384_cosine_map@100 | dim_64_cosine_map@100 | |
|
|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| |
|
| 0 | 0 | - | 0.1945 | 0.2243 | 0.2302 | 0.1499 | |
|
| 0.2735 | 1 | 8.2585 | - | - | - | - | |
|
| 0.5470 | 2 | 8.4215 | - | - | - | - | |
|
| 0.8205 | 3 | 7.899 | 0.2205 | 0.2510 | 0.2597 | 0.1677 | |
|
| 1.0855 | 4 | 6.5734 | - | - | - | - | |
|
| 1.3590 | 5 | 6.2406 | - | - | - | - | |
|
| 1.6325 | 6 | 6.0949 | - | - | - | - | |
|
| 1.9060 | 7 | 5.7149 | 0.2736 | 0.3061 | 0.3224 | 0.2124 | |
|
| 2.1709 | 8 | 5.153 | - | - | - | - | |
|
| 2.4444 | 9 | 5.3615 | - | - | - | - | |
|
| 2.7179 | 10 | 5.3069 | - | - | - | - | |
|
| 2.9915 | 11 | 5.1567 | 0.2914 | 0.3238 | 0.3402 | 0.2191 | |
|
| 3.2564 | 12 | 4.6824 | - | - | - | - | |
|
| 3.5299 | 13 | 5.1072 | - | - | - | - | |
|
| **3.8034** | **14** | **5.1575** | **0.2967** | **0.3302** | **0.3443** | **0.2196** | |
|
| 4.0684 | 15 | 4.5651 | 0.2960 | 0.3304 | 0.3452 | 0.2209 | |
|
|
|
* 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.* |
|
--> |
