|
|
--- |
|
|
language: |
|
|
- en |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- sentence-transformers |
|
|
- sentence-similarity |
|
|
- feature-extraction |
|
|
- dense |
|
|
- generated_from_trainer |
|
|
- dataset_size:20420717 |
|
|
- loss:CachedMultipleNegativesRankingLoss |
|
|
- loss:CachedMultipleNegativesSymmetricRankingLoss |
|
|
widget: |
|
|
- source_sentence: what is the difference between body spray and eau de toilette? |
|
|
sentences: |
|
|
- Eau de Toilette (EDT) is ideal for those that may find the EDP or Perfume oil |
|
|
too strong, with 7%-12% fragrance concentration in alcohol. Gives four to five |
|
|
hours wear. Body Mist is a light refreshing fragrance perfect for layering with |
|
|
other products from the same family. 3-5% fragrance concentration in alcohol. |
|
|
- To join the Army as an enlisted member you must usually take the Armed Services |
|
|
Vocational Aptitude Battery (ASVAB) test and get a good score. The maximum ASVAB |
|
|
score is 99. For enlistment into the Army you must get a minimum ASVAB score of |
|
|
31. |
|
|
- 'Points needed to redeem rewards with Redbox Perks: 1,500 points = FREE 1-night |
|
|
DVD rental. 1,750 points = FREE Blu-ray rental. 2,500 points = FREE 1-night Game |
|
|
rental.' |
|
|
- source_sentence: hurtles definition |
|
|
sentences: |
|
|
- BCIP-NBT Solution is a 5-bromo, 4-chloro, 3-indolylphosphate (BCIP)/Nitro-Blue |
|
|
Tetrazolium (NBT) substrate, used for the localization of alkaline phosphatase |
|
|
(AP) labeled probes on western, northern, southern and dot blots. |
|
|
- 'Definition of hurtle for English Language Learners. : 1 to move or fall with |
|
|
great speed and force. : 2 to cause (something or someone) to move or go with |
|
|
great speed and force.' |
|
|
- 10 most extreme places on Earth. A dongle is a piece of hardware that attaches |
|
|
to a computer and allows a piece of secured software to run. The device does not |
|
|
contain the software in its entirety, but rather is an electronic key that unlocks |
|
|
the program on a computer.0 most extreme places on Earth. A dongle is a piece |
|
|
of hardware that attaches to a computer and allows a piece of secured software |
|
|
to run. The device does not contain the software in its entirety, but rather is |
|
|
an electronic key that unlocks the program on a computer. |
|
|
- source_sentence: what is nbt solution used for |
|
|
sentences: |
|
|
- Nembutal Sodium Solution [edit]. Nembutal Sodium Solution (pentobarbital sodium |
|
|
injection) is a sterile solution for intravenous or intramuscular injection. Each |
|
|
mL contains pentobarbital sodium 50 mg, in a vehicle of propylene glycol, 40%, |
|
|
alcohol, 10% and water for injection, to volume. |
|
|
- BCIP-NBT Solution is a 5-bromo, 4-chloro, 3-indolylphosphate (BCIP)/Nitro-Blue |
|
|
Tetrazolium (NBT) substrate, used for the localization of alkaline phosphatase |
|
|
(AP) labeled probes on western, northern, southern and dot blots. |
|
|
- 'Definition of hurtle for English Language Learners. : 1 to move or fall with |
|
|
great speed and force. : 2 to cause (something or someone) to move or go with |
|
|
great speed and force.' |
|
|
- source_sentence: definition doula |
|
|
sentences: |
|
|
- "The Trivago Guy, aka Tim Williams, the Houston-born actor and Berlin resident\ |
|
|
\ who stars in hotel-search site Trivagoâ\x80\x99s TV commercials in North America,\ |
|
|
\ says heâ\x80\x99s perplexed and amused about all the attention heâ\x80\x99s\ |
|
|
\ getting from the TV spots, and heâ\x80\x99s enjoying every minute of it. â\x80\ |
|
|
\x9CBring it on, I love it,â\x80\x9D Williams says." |
|
|
- Average Length of Doula Study. Typically, a birth doula needs to finish 7 to 12 |
|
|
hours of childbirth education, 16 hours of birth doula training, and attend at |
|
|
two to five births. A postpartum doula usually attends about 27 hours of postpartum |
|
|
doula education and assists two or more women with postpartum support. |
|
|
- Doula. A doula, is a nonmedical person who assists a woman before, during, or |
|
|
after childbirth, as well as her partner and/or family by providing information, |
|
|
physical assistance, and emotional support. |
|
|
- source_sentence: who is catch me if you can based on |
|
|
sentences: |
|
|
- Catch Me If You Can Catch Me If You Can is a 2002 American biographical crime |
|
|
film directed and produced by Steven Spielberg from a screenplay by Jeff Nathanson. |
|
|
The film is based on the life of Frank Abagnale, who, before his 19th birthday, |
|
|
successfully performed cons worth millions of dollars by posing as a Pan American |
|
|
World Airways pilot, a Georgia doctor and a Louisiana parish prosecutor. His primary |
|
|
crime was check fraud; he became so experienced that the FBI eventually turned |
|
|
to him for help in catching other checking forgers. The film stars Leonardo DiCaprio |
|
|
and Tom Hanks, with Christopher Walken, Martin Sheen, and Nathalie Baye in supporting |
|
|
roles. |
|
|
- Ghost Rider (Johnny Blaze) Centurious appeared, stealing Blaze's soul into his |
|
|
soul crystal. Zarathos, weakened from the ordeal used the last of his strength |
|
|
to shatter the crystal, freeing Blaze's soul and many others contained inside |
|
|
of the crystal as well. Before the crystal was reformed, Centurious was absorbed |
|
|
into the crystal. Zarathos followed him into the crystal, freeing Blaze from the |
|
|
curse, restoring his soul, and ending his time as the Ghost Rider.[31] |
|
|
- Colonial Brazil In contrast to the neighboring Spanish possessions, which had |
|
|
several viceroyalties with jurisdiction initially over New Spain (Mexico) and |
|
|
Peru, and in the eighteenth century expanded to viceroyalties of Rio de la Plata |
|
|
and New Granada, the Portuguese colony of Brazil was settled mainly in the coastal |
|
|
area by the Portuguese and a large black slave population working sugar plantations |
|
|
and mines. The boom and bust economic cycles were linked to export products. Brazil's |
|
|
sugar age, with the development of plantation slavery, merchants serving as middle |
|
|
men between production sites, Brazilian ports, and Europe was undermined by the |
|
|
growth of the sugar industry in the Caribbean on islands that European powers |
|
|
seized from Spain. Gold and diamonds were discovered and mined in southern Brazil |
|
|
through the end of the colonial era. Brazilian cities were largely port cities |
|
|
and the colonial administrative capital was moved several times in response to |
|
|
the rise and fall of export products' importance. Unlike Spanish America that |
|
|
fragmented in many republics, Brazil remained as a single administrative unit |
|
|
with a monarch, giving rise to the largest country in Latin America. Like Spanish |
|
|
America with European Spanish, Brazil had linguistic integrity of Portuguese. |
|
|
Both Spanish America and Brazil were Roman Catholic. |
|
|
datasets: |
|
|
- sentence-transformers/msmarco-msmarco-distilbert-base-v3 |
|
|
- sentence-transformers/gooaq |
|
|
- sentence-transformers/natural-questions |
|
|
pipeline_tag: sentence-similarity |
|
|
library_name: sentence-transformers |
|
|
metrics: |
|
|
- cosine_accuracy@1 |
|
|
- cosine_accuracy@3 |
|
|
- cosine_accuracy@5 |
|
|
- cosine_accuracy@10 |
|
|
- cosine_precision@1 |
|
|
- cosine_precision@3 |
|
|
- cosine_precision@5 |
|
|
- cosine_precision@10 |
|
|
- cosine_recall@1 |
|
|
- cosine_recall@3 |
|
|
- cosine_recall@5 |
|
|
- cosine_recall@10 |
|
|
- cosine_ndcg@10 |
|
|
- cosine_mrr@10 |
|
|
- cosine_map@100 |
|
|
model-index: |
|
|
- name: ModernBERT-small-1.5-Retrieval-BEIR-Tuned |
|
|
results: |
|
|
- task: |
|
|
type: information-retrieval |
|
|
name: Information Retrieval |
|
|
dataset: |
|
|
name: NanoMSMARCO |
|
|
type: NanoMSMARCO |
|
|
metrics: |
|
|
- type: cosine_accuracy@1 |
|
|
value: 0.08 |
|
|
name: Cosine Accuracy@1 |
|
|
- type: cosine_accuracy@3 |
|
|
value: 0.3 |
|
|
name: Cosine Accuracy@3 |
|
|
- type: cosine_accuracy@5 |
|
|
value: 0.36 |
|
|
name: Cosine Accuracy@5 |
|
|
- type: cosine_accuracy@10 |
|
|
value: 0.5 |
|
|
name: Cosine Accuracy@10 |
|
|
- type: cosine_precision@1 |
|
|
value: 0.08 |
|
|
name: Cosine Precision@1 |
|
|
- type: cosine_precision@3 |
|
|
value: 0.09999999999999998 |
|
|
name: Cosine Precision@3 |
|
|
- type: cosine_precision@5 |
|
|
value: 0.07200000000000001 |
|
|
name: Cosine Precision@5 |
|
|
- type: cosine_precision@10 |
|
|
value: 0.05000000000000001 |
|
|
name: Cosine Precision@10 |
|
|
- type: cosine_recall@1 |
|
|
value: 0.08 |
|
|
name: Cosine Recall@1 |
|
|
- type: cosine_recall@3 |
|
|
value: 0.3 |
|
|
name: Cosine Recall@3 |
|
|
- type: cosine_recall@5 |
|
|
value: 0.36 |
|
|
name: Cosine Recall@5 |
|
|
- type: cosine_recall@10 |
|
|
value: 0.5 |
|
|
name: Cosine Recall@10 |
|
|
- type: cosine_ndcg@10 |
|
|
value: 0.2774734521140046 |
|
|
name: Cosine Ndcg@10 |
|
|
- type: cosine_mrr@10 |
|
|
value: 0.20799206349206348 |
|
|
name: Cosine Mrr@10 |
|
|
- type: cosine_map@100 |
|
|
value: 0.22779015501462538 |
|
|
name: Cosine Map@100 |
|
|
- task: |
|
|
type: information-retrieval |
|
|
name: Information Retrieval |
|
|
dataset: |
|
|
name: NanoNQ |
|
|
type: NanoNQ |
|
|
metrics: |
|
|
- type: cosine_accuracy@1 |
|
|
value: 0.16 |
|
|
name: Cosine Accuracy@1 |
|
|
- type: cosine_accuracy@3 |
|
|
value: 0.32 |
|
|
name: Cosine Accuracy@3 |
|
|
- type: cosine_accuracy@5 |
|
|
value: 0.44 |
|
|
name: Cosine Accuracy@5 |
|
|
- type: cosine_accuracy@10 |
|
|
value: 0.6 |
|
|
name: Cosine Accuracy@10 |
|
|
- type: cosine_precision@1 |
|
|
value: 0.16 |
|
|
name: Cosine Precision@1 |
|
|
- type: cosine_precision@3 |
|
|
value: 0.10666666666666666 |
|
|
name: Cosine Precision@3 |
|
|
- type: cosine_precision@5 |
|
|
value: 0.08800000000000001 |
|
|
name: Cosine Precision@5 |
|
|
- type: cosine_precision@10 |
|
|
value: 0.06000000000000001 |
|
|
name: Cosine Precision@10 |
|
|
- type: cosine_recall@1 |
|
|
value: 0.14 |
|
|
name: Cosine Recall@1 |
|
|
- type: cosine_recall@3 |
|
|
value: 0.29 |
|
|
name: Cosine Recall@3 |
|
|
- type: cosine_recall@5 |
|
|
value: 0.4 |
|
|
name: Cosine Recall@5 |
|
|
- type: cosine_recall@10 |
|
|
value: 0.55 |
|
|
name: Cosine Recall@10 |
|
|
- type: cosine_ndcg@10 |
|
|
value: 0.3273011574644101 |
|
|
name: Cosine Ndcg@10 |
|
|
- type: cosine_mrr@10 |
|
|
value: 0.27730158730158727 |
|
|
name: Cosine Mrr@10 |
|
|
- type: cosine_map@100 |
|
|
value: 0.2638075437451129 |
|
|
name: Cosine Map@100 |
|
|
- task: |
|
|
type: information-retrieval |
|
|
name: Information Retrieval |
|
|
dataset: |
|
|
name: NanoHotpotQA |
|
|
type: NanoHotpotQA |
|
|
metrics: |
|
|
- type: cosine_accuracy@1 |
|
|
value: 0.52 |
|
|
name: Cosine Accuracy@1 |
|
|
- type: cosine_accuracy@3 |
|
|
value: 0.72 |
|
|
name: Cosine Accuracy@3 |
|
|
- type: cosine_accuracy@5 |
|
|
value: 0.78 |
|
|
name: Cosine Accuracy@5 |
|
|
- type: cosine_accuracy@10 |
|
|
value: 0.84 |
|
|
name: Cosine Accuracy@10 |
|
|
- type: cosine_precision@1 |
|
|
value: 0.52 |
|
|
name: Cosine Precision@1 |
|
|
- type: cosine_precision@3 |
|
|
value: 0.29333333333333333 |
|
|
name: Cosine Precision@3 |
|
|
- type: cosine_precision@5 |
|
|
value: 0.19199999999999995 |
|
|
name: Cosine Precision@5 |
|
|
- type: cosine_precision@10 |
|
|
value: 0.11799999999999997 |
|
|
name: Cosine Precision@10 |
|
|
- type: cosine_recall@1 |
|
|
value: 0.26 |
|
|
name: Cosine Recall@1 |
|
|
- type: cosine_recall@3 |
|
|
value: 0.44 |
|
|
name: Cosine Recall@3 |
|
|
- type: cosine_recall@5 |
|
|
value: 0.48 |
|
|
name: Cosine Recall@5 |
|
|
- type: cosine_recall@10 |
|
|
value: 0.59 |
|
|
name: Cosine Recall@10 |
|
|
- type: cosine_ndcg@10 |
|
|
value: 0.5097756918840387 |
|
|
name: Cosine Ndcg@10 |
|
|
- type: cosine_mrr@10 |
|
|
value: 0.625547619047619 |
|
|
name: Cosine Mrr@10 |
|
|
- type: cosine_map@100 |
|
|
value: 0.4238786723152704 |
|
|
name: Cosine Map@100 |
|
|
- task: |
|
|
type: nano-beir |
|
|
name: Nano BEIR |
|
|
dataset: |
|
|
name: NanoBEIR mean |
|
|
type: NanoBEIR_mean |
|
|
metrics: |
|
|
- type: cosine_accuracy@1 |
|
|
value: 0.25333333333333335 |
|
|
name: Cosine Accuracy@1 |
|
|
- type: cosine_accuracy@3 |
|
|
value: 0.4466666666666666 |
|
|
name: Cosine Accuracy@3 |
|
|
- type: cosine_accuracy@5 |
|
|
value: 0.5266666666666667 |
|
|
name: Cosine Accuracy@5 |
|
|
- type: cosine_accuracy@10 |
|
|
value: 0.6466666666666666 |
|
|
name: Cosine Accuracy@10 |
|
|
- type: cosine_precision@1 |
|
|
value: 0.25333333333333335 |
|
|
name: Cosine Precision@1 |
|
|
- type: cosine_precision@3 |
|
|
value: 0.16666666666666666 |
|
|
name: Cosine Precision@3 |
|
|
- type: cosine_precision@5 |
|
|
value: 0.11733333333333333 |
|
|
name: Cosine Precision@5 |
|
|
- type: cosine_precision@10 |
|
|
value: 0.076 |
|
|
name: Cosine Precision@10 |
|
|
- type: cosine_recall@1 |
|
|
value: 0.16 |
|
|
name: Cosine Recall@1 |
|
|
- type: cosine_recall@3 |
|
|
value: 0.3433333333333333 |
|
|
name: Cosine Recall@3 |
|
|
- type: cosine_recall@5 |
|
|
value: 0.41333333333333333 |
|
|
name: Cosine Recall@5 |
|
|
- type: cosine_recall@10 |
|
|
value: 0.5466666666666667 |
|
|
name: Cosine Recall@10 |
|
|
- type: cosine_ndcg@10 |
|
|
value: 0.3715167671541511 |
|
|
name: Cosine Ndcg@10 |
|
|
- type: cosine_mrr@10 |
|
|
value: 0.37028042328042327 |
|
|
name: Cosine Mrr@10 |
|
|
- type: cosine_map@100 |
|
|
value: 0.3051587903583362 |
|
|
name: Cosine Map@100 |
|
|
--- |
|
|
|
|
|
# ModernBERT-small-1.5-Retrieval-BEIR-Tuned |
|
|
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model trained on the [msmarco](https://huggingface.co/datasets/sentence-transformers/msmarco-msmarco-distilbert-base-v3), [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq) and [natural_questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) datasets. 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:** [Unknown](https://huggingface.co/unknown) --> |
|
|
- **Maximum Sequence Length:** 1024 tokens |
|
|
- **Output Dimensionality:** 384 dimensions |
|
|
- **Similarity Function:** Cosine Similarity |
|
|
- **Training Datasets:** |
|
|
- [msmarco](https://huggingface.co/datasets/sentence-transformers/msmarco-msmarco-distilbert-base-v3) |
|
|
- [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq) |
|
|
- [natural_questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) |
|
|
- **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': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'}) |
|
|
(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}) |
|
|
) |
|
|
``` |
|
|
|
|
|
## 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 = [ |
|
|
'who is catch me if you can based on', |
|
|
'Catch Me If You Can Catch Me If You Can is a 2002 American biographical crime film directed and produced by Steven Spielberg from a screenplay by Jeff Nathanson. The film is based on the life of Frank Abagnale, who, before his 19th birthday, successfully performed cons worth millions of dollars by posing as a Pan American World Airways pilot, a Georgia doctor and a Louisiana parish prosecutor. His primary crime was check fraud; he became so experienced that the FBI eventually turned to him for help in catching other checking forgers. The film stars Leonardo DiCaprio and Tom Hanks, with Christopher Walken, Martin Sheen, and Nathalie Baye in supporting roles.', |
|
|
"Colonial Brazil In contrast to the neighboring Spanish possessions, which had several viceroyalties with jurisdiction initially over New Spain (Mexico) and Peru, and in the eighteenth century expanded to viceroyalties of Rio de la Plata and New Granada, the Portuguese colony of Brazil was settled mainly in the coastal area by the Portuguese and a large black slave population working sugar plantations and mines. The boom and bust economic cycles were linked to export products. Brazil's sugar age, with the development of plantation slavery, merchants serving as middle men between production sites, Brazilian ports, and Europe was undermined by the growth of the sugar industry in the Caribbean on islands that European powers seized from Spain. Gold and diamonds were discovered and mined in southern Brazil through the end of the colonial era. Brazilian cities were largely port cities and the colonial administrative capital was moved several times in response to the rise and fall of export products' importance. Unlike Spanish America that fragmented in many republics, Brazil remained as a single administrative unit with a monarch, giving rise to the largest country in Latin America. Like Spanish America with European Spanish, Brazil had linguistic integrity of Portuguese. Both Spanish America and Brazil were Roman Catholic.", |
|
|
] |
|
|
embeddings = model.encode(sentences) |
|
|
print(embeddings.shape) |
|
|
# [3, 384] |
|
|
|
|
|
# Get the similarity scores for the embeddings |
|
|
similarities = model.similarity(embeddings, embeddings) |
|
|
print(similarities) |
|
|
# tensor([[ 1.0000, 0.5555, -0.1763], |
|
|
# [ 0.5555, 1.0000, -0.0652], |
|
|
# [-0.1763, -0.0652, 1.0000]]) |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
### 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 |
|
|
|
|
|
* Datasets: `NanoMSMARCO`, `NanoNQ` and `NanoHotpotQA` |
|
|
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) |
|
|
|
|
|
| Metric | NanoMSMARCO | NanoNQ | NanoHotpotQA | |
|
|
|:--------------------|:------------|:-----------|:-------------| |
|
|
| cosine_accuracy@1 | 0.08 | 0.16 | 0.52 | |
|
|
| cosine_accuracy@3 | 0.3 | 0.32 | 0.72 | |
|
|
| cosine_accuracy@5 | 0.36 | 0.44 | 0.78 | |
|
|
| cosine_accuracy@10 | 0.5 | 0.6 | 0.84 | |
|
|
| cosine_precision@1 | 0.08 | 0.16 | 0.52 | |
|
|
| cosine_precision@3 | 0.1 | 0.1067 | 0.2933 | |
|
|
| cosine_precision@5 | 0.072 | 0.088 | 0.192 | |
|
|
| cosine_precision@10 | 0.05 | 0.06 | 0.118 | |
|
|
| cosine_recall@1 | 0.08 | 0.14 | 0.26 | |
|
|
| cosine_recall@3 | 0.3 | 0.29 | 0.44 | |
|
|
| cosine_recall@5 | 0.36 | 0.4 | 0.48 | |
|
|
| cosine_recall@10 | 0.5 | 0.55 | 0.59 | |
|
|
| **cosine_ndcg@10** | **0.2775** | **0.3273** | **0.5098** | |
|
|
| cosine_mrr@10 | 0.208 | 0.2773 | 0.6255 | |
|
|
| cosine_map@100 | 0.2278 | 0.2638 | 0.4239 | |
|
|
|
|
|
#### Nano BEIR |
|
|
|
|
|
* Dataset: `NanoBEIR_mean` |
|
|
* Evaluated with [<code>NanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.NanoBEIREvaluator) with these parameters: |
|
|
```json |
|
|
{ |
|
|
"dataset_names": [ |
|
|
"MSMARCO", |
|
|
"NQ", |
|
|
"HotpotQA" |
|
|
] |
|
|
} |
|
|
``` |
|
|
|
|
|
| Metric | Value | |
|
|
|:--------------------|:-----------| |
|
|
| cosine_accuracy@1 | 0.2533 | |
|
|
| cosine_accuracy@3 | 0.4467 | |
|
|
| cosine_accuracy@5 | 0.5267 | |
|
|
| cosine_accuracy@10 | 0.6467 | |
|
|
| cosine_precision@1 | 0.2533 | |
|
|
| cosine_precision@3 | 0.1667 | |
|
|
| cosine_precision@5 | 0.1173 | |
|
|
| cosine_precision@10 | 0.076 | |
|
|
| cosine_recall@1 | 0.16 | |
|
|
| cosine_recall@3 | 0.3433 | |
|
|
| cosine_recall@5 | 0.4133 | |
|
|
| cosine_recall@10 | 0.5467 | |
|
|
| **cosine_ndcg@10** | **0.3715** | |
|
|
| cosine_mrr@10 | 0.3703 | |
|
|
| cosine_map@100 | 0.3052 | |
|
|
|
|
|
<!-- |
|
|
## 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 Datasets |
|
|
|
|
|
#### msmarco |
|
|
|
|
|
* Dataset: [msmarco](https://huggingface.co/datasets/sentence-transformers/msmarco-msmarco-distilbert-base-v3) at [28ff31e](https://huggingface.co/datasets/sentence-transformers/msmarco-msmarco-distilbert-base-v3/tree/28ff31e4c97cddd53d298497f766e653f1e666f9) |
|
|
* Size: 17,307,990 training samples |
|
|
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code> |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | anchor | positive | negative | |
|
|
|:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| |
|
|
| type | string | string | string | |
|
|
| details | <ul><li>min: 5 tokens</li><li>mean: 9.57 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 44 tokens</li><li>mean: 83.39 tokens</li><li>max: 211 tokens</li></ul> | <ul><li>min: 24 tokens</li><li>mean: 83.62 tokens</li><li>max: 268 tokens</li></ul> | |
|
|
* Samples: |
|
|
| anchor | positive | negative | |
|
|
|:----------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
|
|
| <code>what are the liberal arts?</code> | <code>liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>The liberal arts education at the secondary school level prepares the student for higher education at a university. They are thus meant for the more academically minded students. In addition to the usual curriculum, students of a liberal arts education often study Latin and Ancient Greek. Some liberal arts education provide general education, others have a specific focus.</code> | |
|
|
| <code>what are the liberal arts?</code> | <code>liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>Liberal Arts. Upon completion of the Liberal Arts degree, students will be able to express ideas in coherent, creative, and appropriate forms, orally and in writing. Students will be able to apply their reading abilities in order to interconnect an understanding of resources to academic, professional, and personal interests.</code> | |
|
|
| <code>what are the liberal arts?</code> | <code>liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>Rather than preparing students for a specific career, liberal arts programs focus on cultural literacy and hone communication and analytical skills. They often cover various disciplines, ranging from the humanities to social sciences. 1 Program Levels in Liberal Arts: Associate degree, Bachelor's degree, Master's degree.</code> | |
|
|
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters: |
|
|
```json |
|
|
{ |
|
|
"scale": 20.0, |
|
|
"similarity_fct": "cos_sim", |
|
|
"mini_batch_size": 64 |
|
|
} |
|
|
``` |
|
|
|
|
|
#### gooaq |
|
|
|
|
|
* Dataset: [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq) at [b089f72](https://huggingface.co/datasets/sentence-transformers/gooaq/tree/b089f728748a068b7bc5234e5bcf5b25e3c8279c) |
|
|
* Size: 3,012,496 training samples |
|
|
* Columns: <code>anchor</code> and <code>positive</code> |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | anchor | positive | |
|
|
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| |
|
|
| type | string | string | |
|
|
| details | <ul><li>min: 8 tokens</li><li>mean: 12.19 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 58.34 tokens</li><li>max: 124 tokens</li></ul> | |
|
|
* Samples: |
|
|
| anchor | positive | |
|
|
|:---------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
|
|
| <code>is toprol xl the same as metoprolol?</code> | <code>Metoprolol succinate is also known by the brand name Toprol XL. It is the extended-release form of metoprolol. Metoprolol succinate is approved to treat high blood pressure, chronic chest pain, and congestive heart failure.</code> | |
|
|
| <code>are you experienced cd steve hoffman?</code> | <code>The Are You Experienced album was apparently mastered from the original stereo UK master tapes (according to Steve Hoffman - one of the very few who has heard both the master tapes and the CDs produced over the years). ... The CD booklets were a little sparse, but at least they stayed true to the album's original design.</code> | |
|
|
| <code>how are babushka dolls made?</code> | <code>Matryoshka dolls are made of wood from lime, balsa, alder, aspen, and birch trees; lime is probably the most common wood type. ... After cutting, the trees are stripped of most of their bark, although a few inner rings of bark are left to bind the wood and keep it from splitting.</code> | |
|
|
* Loss: [<code>CachedMultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativessymmetricrankingloss) with these parameters: |
|
|
```json |
|
|
{ |
|
|
"scale": 20.0, |
|
|
"similarity_fct": "cos_sim", |
|
|
"mini_batch_size": 64 |
|
|
} |
|
|
``` |
|
|
|
|
|
#### natural_questions |
|
|
|
|
|
* Dataset: [natural_questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17) |
|
|
* Size: 100,231 training samples |
|
|
* Columns: <code>anchor</code> and <code>positive</code> |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | anchor | positive | |
|
|
|:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| |
|
|
| type | string | string | |
|
|
| details | <ul><li>min: 10 tokens</li><li>mean: 12.47 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 138.32 tokens</li><li>max: 556 tokens</li></ul> | |
|
|
* Samples: |
|
|
| anchor | positive | |
|
|
|:----------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
|
|
| <code>when did richmond last play in a preliminary final</code> | <code>Richmond Football Club Richmond began 2017 with 5 straight wins, a feat it had not achieved since 1995. A series of close losses hampered the Tigers throughout the middle of the season, including a 5-point loss to the Western Bulldogs, 2-point loss to Fremantle, and a 3-point loss to the Giants. Richmond ended the season strongly with convincing victories over Fremantle and St Kilda in the final two rounds, elevating the club to 3rd on the ladder. Richmond's first final of the season against the Cats at the MCG attracted a record qualifying final crowd of 95,028; the Tigers won by 51 points. Having advanced to the first preliminary finals for the first time since 2001, Richmond defeated Greater Western Sydney by 36 points in front of a crowd of 94,258 to progress to the Grand Final against Adelaide, their first Grand Final appearance since 1982. The attendance was 100,021, the largest crowd to a grand final since 1986. The Crows led at quarter time and led by as many as 13, but the Tig...</code> | |
|
|
| <code>who sang what in the world's come over you</code> | <code>Jack Scott (singer) At the beginning of 1960, Scott again changed record labels, this time to Top Rank Records.[1] He then recorded four Billboard Hot 100 hits – "What in the World's Come Over You" (#5), "Burning Bridges" (#3) b/w "Oh Little One" (#34), and "It Only Happened Yesterday" (#38).[1] "What in the World's Come Over You" was Scott's second gold disc winner.[6] Scott continued to record and perform during the 1960s and 1970s.[1] His song "You're Just Gettin' Better" reached the country charts in 1974.[1] In May 1977, Scott recorded a Peel session for BBC Radio 1 disc jockey, John Peel.</code> | |
|
|
| <code>who produces the most wool in the world</code> | <code>Wool Global wool production is about 2 million tonnes per year, of which 60% goes into apparel. Wool comprises ca 3% of the global textile market, but its value is higher owing to dying and other modifications of the material.[1] Australia is a leading producer of wool which is mostly from Merino sheep but has been eclipsed by China in terms of total weight.[30] New Zealand (2016) is the third-largest producer of wool, and the largest producer of crossbred wool. Breeds such as Lincoln, Romney, Drysdale, and Elliotdale produce coarser fibers, and wool from these sheep is usually used for making carpets.</code> | |
|
|
* Loss: [<code>CachedMultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativessymmetricrankingloss) with these parameters: |
|
|
```json |
|
|
{ |
|
|
"scale": 20.0, |
|
|
"similarity_fct": "cos_sim", |
|
|
"mini_batch_size": 64 |
|
|
} |
|
|
``` |
|
|
|
|
|
### Training Hyperparameters |
|
|
#### Non-Default Hyperparameters |
|
|
|
|
|
- `eval_strategy`: steps |
|
|
- `per_device_train_batch_size`: 256 |
|
|
- `weight_decay`: 0.01 |
|
|
- `num_train_epochs`: 1 |
|
|
- `lr_scheduler_type`: cosine |
|
|
- `warmup_ratio`: 0.1 |
|
|
- `bf16`: True |
|
|
- `bf16_full_eval`: True |
|
|
- `load_best_model_at_end`: True |
|
|
|
|
|
#### All Hyperparameters |
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
- `overwrite_output_dir`: False |
|
|
- `do_predict`: False |
|
|
- `eval_strategy`: steps |
|
|
- `prediction_loss_only`: True |
|
|
- `per_device_train_batch_size`: 256 |
|
|
- `per_device_eval_batch_size`: 8 |
|
|
- `per_gpu_train_batch_size`: None |
|
|
- `per_gpu_eval_batch_size`: None |
|
|
- `gradient_accumulation_steps`: 1 |
|
|
- `eval_accumulation_steps`: None |
|
|
- `torch_empty_cache_steps`: None |
|
|
- `learning_rate`: 5e-05 |
|
|
- `weight_decay`: 0.01 |
|
|
- `adam_beta1`: 0.9 |
|
|
- `adam_beta2`: 0.999 |
|
|
- `adam_epsilon`: 1e-08 |
|
|
- `max_grad_norm`: 1.0 |
|
|
- `num_train_epochs`: 1 |
|
|
- `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`: True |
|
|
- `fp16_full_eval`: False |
|
|
- `tf32`: None |
|
|
- `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`: None |
|
|
- `hub_always_push`: False |
|
|
- `hub_revision`: None |
|
|
- `gradient_checkpointing`: False |
|
|
- `gradient_checkpointing_kwargs`: None |
|
|
- `include_inputs_for_metrics`: False |
|
|
- `include_for_metrics`: [] |
|
|
- `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 |
|
|
- `include_tokens_per_second`: False |
|
|
- `include_num_input_tokens_seen`: False |
|
|
- `neftune_noise_alpha`: None |
|
|
- `optim_target_modules`: None |
|
|
- `batch_eval_metrics`: False |
|
|
- `eval_on_start`: False |
|
|
- `use_liger_kernel`: False |
|
|
- `liger_kernel_config`: None |
|
|
- `eval_use_gather_object`: False |
|
|
- `average_tokens_across_devices`: False |
|
|
- `prompts`: None |
|
|
- `batch_sampler`: batch_sampler |
|
|
- `multi_dataset_batch_sampler`: proportional |
|
|
- `router_mapping`: {} |
|
|
- `learning_rate_mapping`: {} |
|
|
|
|
|
</details> |
|
|
|
|
|
### Training Logs |
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
| Epoch | Step | Training Loss | NanoMSMARCO_cosine_ndcg@10 | NanoNQ_cosine_ndcg@10 | NanoHotpotQA_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 | |
|
|
|:----------:|:---------:|:-------------:|:--------------------------:|:---------------------:|:---------------------------:|:----------------------------:| |
|
|
| -1 | -1 | - | 0.2397 | 0.3332 | 0.4767 | 0.3499 | |
|
|
| 0.0063 | 500 | 1.6152 | - | - | - | - | |
|
|
| 0.0125 | 1000 | 1.6149 | - | - | - | - | |
|
|
| 0.0188 | 1500 | 1.5833 | - | - | - | - | |
|
|
| 0.0251 | 2000 | 1.58 | 0.2449 | 0.3259 | 0.4793 | 0.3500 | |
|
|
| 0.0313 | 2500 | 1.5475 | - | - | - | - | |
|
|
| 0.0376 | 3000 | 1.5432 | - | - | - | - | |
|
|
| 0.0439 | 3500 | 1.5067 | - | - | - | - | |
|
|
| 0.0501 | 4000 | 1.4909 | 0.2474 | 0.3124 | 0.4786 | 0.3461 | |
|
|
| 0.0564 | 4500 | 1.4532 | - | - | - | - | |
|
|
| 0.0627 | 5000 | 1.425 | - | - | - | - | |
|
|
| 0.0689 | 5500 | 1.4394 | - | - | - | - | |
|
|
| 0.0752 | 6000 | 1.42 | 0.2532 | 0.3149 | 0.4895 | 0.3525 | |
|
|
| 0.0815 | 6500 | 1.3737 | - | - | - | - | |
|
|
| 0.0878 | 7000 | 1.3755 | - | - | - | - | |
|
|
| 0.0940 | 7500 | 1.3194 | - | - | - | - | |
|
|
| 0.1003 | 8000 | 1.3143 | 0.2660 | 0.3163 | 0.4823 | 0.3548 | |
|
|
| 0.1066 | 8500 | 1.3038 | - | - | - | - | |
|
|
| 0.1128 | 9000 | 1.2815 | - | - | - | - | |
|
|
| 0.1191 | 9500 | 1.2291 | - | - | - | - | |
|
|
| 0.1254 | 10000 | 1.24 | 0.2687 | 0.3407 | 0.4876 | 0.3657 | |
|
|
| 0.1316 | 10500 | 1.2383 | - | - | - | - | |
|
|
| 0.1379 | 11000 | 1.2116 | - | - | - | - | |
|
|
| 0.1442 | 11500 | 1.1967 | - | - | - | - | |
|
|
| 0.1504 | 12000 | 1.1712 | 0.2697 | 0.3436 | 0.4888 | 0.3674 | |
|
|
| 0.1567 | 12500 | 1.1781 | - | - | - | - | |
|
|
| 0.1630 | 13000 | 1.1798 | - | - | - | - | |
|
|
| 0.1692 | 13500 | 1.1486 | - | - | - | - | |
|
|
| 0.1755 | 14000 | 1.156 | 0.2761 | 0.3490 | 0.4895 | 0.3716 | |
|
|
| 0.1818 | 14500 | 1.1622 | - | - | - | - | |
|
|
| 0.1880 | 15000 | 1.1638 | - | - | - | - | |
|
|
| 0.1943 | 15500 | 1.1447 | - | - | - | - | |
|
|
| 0.2006 | 16000 | 1.1353 | 0.2783 | 0.3427 | 0.4967 | 0.3726 | |
|
|
| 0.2068 | 16500 | 1.1397 | - | - | - | - | |
|
|
| 0.2131 | 17000 | 1.1346 | - | - | - | - | |
|
|
| 0.2194 | 17500 | 1.1345 | - | - | - | - | |
|
|
| 0.2256 | 18000 | 1.13 | 0.2697 | 0.3424 | 0.5051 | 0.3724 | |
|
|
| 0.2319 | 18500 | 1.1145 | - | - | - | - | |
|
|
| 0.2382 | 19000 | 1.1215 | - | - | - | - | |
|
|
| 0.2445 | 19500 | 1.1193 | - | - | - | - | |
|
|
| 0.2507 | 20000 | 1.1329 | 0.2795 | 0.3363 | 0.4992 | 0.3717 | |
|
|
| 0.2570 | 20500 | 1.1239 | - | - | - | - | |
|
|
| 0.2633 | 21000 | 1.0929 | - | - | - | - | |
|
|
| 0.2695 | 21500 | 1.1079 | - | - | - | - | |
|
|
| 0.2758 | 22000 | 1.1192 | 0.2792 | 0.3278 | 0.5054 | 0.3708 | |
|
|
| 0.2821 | 22500 | 1.1252 | - | - | - | - | |
|
|
| 0.2883 | 23000 | 1.1089 | - | - | - | - | |
|
|
| 0.2946 | 23500 | 1.1032 | - | - | - | - | |
|
|
| 0.3009 | 24000 | 1.0974 | 0.2769 | 0.3372 | 0.5043 | 0.3728 | |
|
|
| 0.3071 | 24500 | 1.1129 | - | - | - | - | |
|
|
| 0.3134 | 25000 | 1.0901 | - | - | - | - | |
|
|
| 0.3197 | 25500 | 1.1087 | - | - | - | - | |
|
|
| 0.3259 | 26000 | 1.0921 | 0.2769 | 0.3349 | 0.5038 | 0.3719 | |
|
|
| 0.3322 | 26500 | 1.0881 | - | - | - | - | |
|
|
| 0.3385 | 27000 | 1.0984 | - | - | - | - | |
|
|
| 0.3447 | 27500 | 1.105 | - | - | - | - | |
|
|
| 0.3510 | 28000 | 1.1022 | 0.2766 | 0.3353 | 0.5043 | 0.3721 | |
|
|
| 0.3573 | 28500 | 1.0925 | - | - | - | - | |
|
|
| 0.3635 | 29000 | 1.1009 | - | - | - | - | |
|
|
| 0.3698 | 29500 | 1.1043 | - | - | - | - | |
|
|
| 0.3761 | 30000 | 1.0893 | 0.2772 | 0.3279 | 0.5055 | 0.3702 | |
|
|
| 0.3823 | 30500 | 1.1084 | - | - | - | - | |
|
|
| 0.3886 | 31000 | 1.0885 | - | - | - | - | |
|
|
| 0.3949 | 31500 | 1.1046 | - | - | - | - | |
|
|
| 0.4012 | 32000 | 1.0925 | 0.2775 | 0.3273 | 0.5052 | 0.3700 | |
|
|
| 0.4074 | 32500 | 1.1126 | - | - | - | - | |
|
|
| 0.4137 | 33000 | 1.0946 | - | - | - | - | |
|
|
| 0.4200 | 33500 | 1.0979 | - | - | - | - | |
|
|
| 0.4262 | 34000 | 1.0852 | 0.2775 | 0.3273 | 0.5098 | 0.3715 | |
|
|
| 0.4325 | 34500 | 1.0925 | - | - | - | - | |
|
|
| 0.4388 | 35000 | 1.0919 | - | - | - | - | |
|
|
| 0.4450 | 35500 | 1.0878 | - | - | - | - | |
|
|
| 0.4513 | 36000 | 1.0775 | 0.2781 | 0.3273 | 0.5098 | 0.3717 | |
|
|
| 0.4576 | 36500 | 1.0898 | - | - | - | - | |
|
|
| 0.4638 | 37000 | 1.0858 | - | - | - | - | |
|
|
| 0.4701 | 37500 | 1.0822 | - | - | - | - | |
|
|
| 0.4764 | 38000 | 1.0831 | 0.2849 | 0.3273 | 0.5098 | 0.3740 | |
|
|
| 0.4826 | 38500 | 1.0886 | - | - | - | - | |
|
|
| 0.4889 | 39000 | 1.089 | - | - | - | - | |
|
|
| 0.4952 | 39500 | 1.0986 | - | - | - | - | |
|
|
| 0.5014 | 40000 | 1.0885 | 0.2775 | 0.3276 | 0.5101 | 0.3717 | |
|
|
| 0.5077 | 40500 | 1.0903 | - | - | - | - | |
|
|
| 0.5140 | 41000 | 1.0883 | - | - | - | - | |
|
|
| 0.5202 | 41500 | 1.1009 | - | - | - | - | |
|
|
| 0.5265 | 42000 | 1.0909 | 0.2781 | 0.3276 | 0.5101 | 0.3719 | |
|
|
| 0.5328 | 42500 | 1.0843 | - | - | - | - | |
|
|
| 0.5390 | 43000 | 1.086 | - | - | - | - | |
|
|
| 0.5453 | 43500 | 1.0762 | - | - | - | - | |
|
|
| 0.5516 | 44000 | 1.0781 | 0.2781 | 0.3276 | 0.5101 | 0.3719 | |
|
|
| 0.5579 | 44500 | 1.0952 | - | - | - | - | |
|
|
| 0.5641 | 45000 | 1.0814 | - | - | - | - | |
|
|
| 0.5704 | 45500 | 1.0815 | - | - | - | - | |
|
|
| **0.5767** | **46000** | **1.0889** | **0.2849** | **0.3276** | **0.5101** | **0.3742** | |
|
|
| 0.5829 | 46500 | 1.087 | - | - | - | - | |
|
|
| 0.5892 | 47000 | 1.0786 | - | - | - | - | |
|
|
| 0.5955 | 47500 | 1.0846 | - | - | - | - | |
|
|
| 0.6017 | 48000 | 1.095 | 0.2849 | 0.3273 | 0.5101 | 0.3741 | |
|
|
| 0.6080 | 48500 | 1.0839 | - | - | - | - | |
|
|
| 0.6143 | 49000 | 1.0899 | - | - | - | - | |
|
|
| 0.6205 | 49500 | 1.0903 | - | - | - | - | |
|
|
| 0.6268 | 50000 | 1.0915 | 0.2775 | 0.3273 | 0.5098 | 0.3715 | |
|
|
| 0.6331 | 50500 | 1.0764 | - | - | - | - | |
|
|
| 0.6393 | 51000 | 1.1006 | - | - | - | - | |
|
|
| 0.6456 | 51500 | 1.0968 | - | - | - | - | |
|
|
| 0.6519 | 52000 | 1.084 | 0.2849 | 0.3273 | 0.5101 | 0.3741 | |
|
|
| 0.6581 | 52500 | 1.0892 | - | - | - | - | |
|
|
| 0.6644 | 53000 | 1.09 | - | - | - | - | |
|
|
| 0.6707 | 53500 | 1.0946 | - | - | - | - | |
|
|
| 0.6769 | 54000 | 1.0861 | 0.2775 | 0.3273 | 0.5098 | 0.3715 | |
|
|
| 0.6832 | 54500 | 1.0962 | - | - | - | - | |
|
|
| 0.6895 | 55000 | 1.0841 | - | - | - | - | |
|
|
| 0.6958 | 55500 | 1.0894 | - | - | - | - | |
|
|
| 0.7020 | 56000 | 1.082 | 0.2775 | 0.3273 | 0.5098 | 0.3715 | |
|
|
| 0.7083 | 56500 | 1.0939 | - | - | - | - | |
|
|
| 0.7146 | 57000 | 1.096 | - | - | - | - | |
|
|
| 0.7208 | 57500 | 1.1048 | - | - | - | - | |
|
|
| 0.7271 | 58000 | 1.0853 | 0.2849 | 0.3273 | 0.5098 | 0.3740 | |
|
|
| 0.7334 | 58500 | 1.0893 | - | - | - | - | |
|
|
| 0.7396 | 59000 | 1.0946 | - | - | - | - | |
|
|
| 0.7459 | 59500 | 1.0985 | - | - | - | - | |
|
|
| 0.7522 | 60000 | 1.099 | 0.2849 | 0.3273 | 0.5098 | 0.3740 | |
|
|
| 0.7584 | 60500 | 1.0972 | - | - | - | - | |
|
|
| 0.7647 | 61000 | 1.0812 | - | - | - | - | |
|
|
| 0.7710 | 61500 | 1.0744 | - | - | - | - | |
|
|
| 0.7772 | 62000 | 1.0781 | 0.2775 | 0.3273 | 0.5101 | 0.3716 | |
|
|
| 0.7835 | 62500 | 1.0823 | - | - | - | - | |
|
|
| 0.7898 | 63000 | 1.0819 | - | - | - | - | |
|
|
| 0.7960 | 63500 | 1.0911 | - | - | - | - | |
|
|
| 0.8023 | 64000 | 1.1069 | 0.2775 | 0.3273 | 0.5098 | 0.3715 | |
|
|
| 0.8086 | 64500 | 1.0786 | - | - | - | - | |
|
|
| 0.8148 | 65000 | 1.0872 | - | - | - | - | |
|
|
| 0.8211 | 65500 | 1.0776 | - | - | - | - | |
|
|
| 0.8274 | 66000 | 1.0849 | 0.2849 | 0.3273 | 0.5098 | 0.3740 | |
|
|
| 0.8336 | 66500 | 1.0778 | - | - | - | - | |
|
|
| 0.8399 | 67000 | 1.0972 | - | - | - | - | |
|
|
| 0.8462 | 67500 | 1.0835 | - | - | - | - | |
|
|
| 0.8525 | 68000 | 1.0927 | 0.2849 | 0.3273 | 0.5098 | 0.3740 | |
|
|
| 0.8587 | 68500 | 1.082 | - | - | - | - | |
|
|
| 0.8650 | 69000 | 1.0742 | - | - | - | - | |
|
|
| 0.8713 | 69500 | 1.0886 | - | - | - | - | |
|
|
| 0.8775 | 70000 | 1.0828 | 0.2775 | 0.3273 | 0.5098 | 0.3715 | |
|
|
| 0.8838 | 70500 | 1.0863 | - | - | - | - | |
|
|
| 0.8901 | 71000 | 1.0905 | - | - | - | - | |
|
|
| 0.8963 | 71500 | 1.0856 | - | - | - | - | |
|
|
| 0.9026 | 72000 | 1.0946 | 0.2775 | 0.3273 | 0.5098 | 0.3715 | |
|
|
| 0.9089 | 72500 | 1.102 | - | - | - | - | |
|
|
| 0.9151 | 73000 | 1.0819 | - | - | - | - | |
|
|
| 0.9214 | 73500 | 1.0884 | - | - | - | - | |
|
|
| 0.9277 | 74000 | 1.0888 | 0.2775 | 0.3273 | 0.5098 | 0.3715 | |
|
|
| 0.9339 | 74500 | 1.0756 | - | - | - | - | |
|
|
| 0.9402 | 75000 | 1.0767 | - | - | - | - | |
|
|
| 0.9465 | 75500 | 1.0821 | - | - | - | - | |
|
|
| 0.9527 | 76000 | 1.0891 | 0.2775 | 0.3273 | 0.5098 | 0.3715 | |
|
|
| 0.9590 | 76500 | 1.0923 | - | - | - | - | |
|
|
| 0.9653 | 77000 | 1.0765 | - | - | - | - | |
|
|
| 0.9715 | 77500 | 1.075 | - | - | - | - | |
|
|
| 0.9778 | 78000 | 1.0902 | 0.2775 | 0.3273 | 0.5098 | 0.3715 | |
|
|
| 0.9841 | 78500 | 1.0833 | - | - | - | - | |
|
|
| 0.9903 | 79000 | 1.0746 | - | - | - | - | |
|
|
| 0.9966 | 79500 | 1.0872 | - | - | - | - | |
|
|
|
|
|
* The bold row denotes the saved checkpoint. |
|
|
</details> |
|
|
|
|
|
### Framework Versions |
|
|
- Python: 3.11.13 |
|
|
- Sentence Transformers: 5.0.0 |
|
|
- Transformers: 4.53.1 |
|
|
- PyTorch: 2.7.1+cu128 |
|
|
- Accelerate: 1.8.1 |
|
|
- Datasets: 4.0.0 |
|
|
- Tokenizers: 0.21.2 |
|
|
|
|
|
## 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", |
|
|
} |
|
|
``` |
|
|
|
|
|
#### CachedMultipleNegativesRankingLoss |
|
|
```bibtex |
|
|
@misc{gao2021scaling, |
|
|
title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup}, |
|
|
author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan}, |
|
|
year={2021}, |
|
|
eprint={2101.06983}, |
|
|
archivePrefix={arXiv}, |
|
|
primaryClass={cs.LG} |
|
|
} |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
## 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.* |
|
|
--> |
