|
|
---
|
|
|
language:
|
|
|
- en
|
|
|
license: apache-2.0
|
|
|
tags:
|
|
|
- sentence-transformers
|
|
|
- sparse-encoder
|
|
|
- sparse
|
|
|
- splade
|
|
|
- generated_from_trainer
|
|
|
- dataset_size:99000
|
|
|
- loss:SpladeLoss
|
|
|
- loss:SparseDistillKLDivLoss
|
|
|
- loss:FlopsLoss
|
|
|
base_model: Luyu/co-condenser-marco
|
|
|
widget:
|
|
|
- text: 'The ejection fraction may decrease if: 1 You have weakness of your heart
|
|
|
muscle, such as dilated cardiomyopathy, which can be caused by a heart muscle
|
|
|
problem, familial (genetic) cardiomyopathy, or systemic illnesses. 2 A heart
|
|
|
attack has damaged your heart. You have problems with your heart''s valves.'
|
|
|
- text: "One thing we avoided: Lots of alternative slime recipes swap Borax for liquid\
|
|
|
\ starch, shampoo, body wash, hand soap, contact lens solution, or laundry detergent.\
|
|
|
\ Those may seem benign â\x80\x94 and they might be â\x80\x94 but many of them\
|
|
|
\ contain derivatives or relatives of sodium borate too."
|
|
|
- text: how do i get my mvr in pa
|
|
|
- text: English is a language whose vocabulary is the composite of a surprising range
|
|
|
of influences. We have pillaged words from Latin, Greek, Dutch, Arabic, Old Norse,
|
|
|
Spanish, Italian, Hindi, and more besides to make English what it is today.
|
|
|
- text: Weed Eater was a string trimmer company founded in 1971 in Houston, Texas
|
|
|
by George C. Ballas, Sr. , the inventor of the device. The idea for the Weed Eater
|
|
|
trimmer came to him from the spinning nylon bristles of an automatic car wash.He
|
|
|
thought that he could come up with a similar technique to protect the bark on
|
|
|
trees that he was trimming around. His company was eventually bought by Emerson
|
|
|
Electric and merged with Poulan.Poulan/Weed Eater was later purchased by Electrolux,
|
|
|
which spun off the outdoors division as Husqvarna AB in 2006.Inventor Ballas was
|
|
|
the father of champion ballroom dancer Corky Ballas and the grandfather of Dancing
|
|
|
with the Stars dancer Mark Ballas.George Ballas died on June 25, 2011.he idea
|
|
|
for the Weed Eater trimmer came to him from the spinning nylon bristles of an
|
|
|
automatic car wash. He thought that he could come up with a similar technique
|
|
|
to protect the bark on trees that he was trimming around. His company was eventually
|
|
|
bought by Emerson Electric and merged with Poulan.
|
|
|
pipeline_tag: feature-extraction
|
|
|
library_name: sentence-transformers
|
|
|
metrics:
|
|
|
- dot_accuracy@1
|
|
|
- dot_accuracy@3
|
|
|
- dot_accuracy@5
|
|
|
- dot_accuracy@10
|
|
|
- dot_precision@1
|
|
|
- dot_precision@3
|
|
|
- dot_precision@5
|
|
|
- dot_precision@10
|
|
|
- dot_recall@1
|
|
|
- dot_recall@3
|
|
|
- dot_recall@5
|
|
|
- dot_recall@10
|
|
|
- dot_ndcg@10
|
|
|
- dot_mrr@10
|
|
|
- dot_map@100
|
|
|
- query_active_dims
|
|
|
- query_sparsity_ratio
|
|
|
- corpus_active_dims
|
|
|
- corpus_sparsity_ratio
|
|
|
co2_eq_emissions:
|
|
|
emissions: 78.12595691469743
|
|
|
energy_consumed: 0.2009919087493695
|
|
|
source: codecarbon
|
|
|
training_type: fine-tuning
|
|
|
on_cloud: false
|
|
|
cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
|
|
|
ram_total_size: 31.777088165283203
|
|
|
hours_used: 0.571
|
|
|
hardware_used: 1 x NVIDIA GeForce RTX 3090
|
|
|
model-index:
|
|
|
- name: CoCondenser finetuned on MS MARCO
|
|
|
results:
|
|
|
- task:
|
|
|
type: sparse-information-retrieval
|
|
|
name: Sparse Information Retrieval
|
|
|
dataset:
|
|
|
name: NanoMSMARCO
|
|
|
type: NanoMSMARCO
|
|
|
metrics:
|
|
|
- type: dot_accuracy@1
|
|
|
value: 0.42
|
|
|
name: Dot Accuracy@1
|
|
|
- type: dot_accuracy@3
|
|
|
value: 0.56
|
|
|
name: Dot Accuracy@3
|
|
|
- type: dot_accuracy@5
|
|
|
value: 0.72
|
|
|
name: Dot Accuracy@5
|
|
|
- type: dot_accuracy@10
|
|
|
value: 0.9
|
|
|
name: Dot Accuracy@10
|
|
|
- type: dot_precision@1
|
|
|
value: 0.42
|
|
|
name: Dot Precision@1
|
|
|
- type: dot_precision@3
|
|
|
value: 0.18666666666666668
|
|
|
name: Dot Precision@3
|
|
|
- type: dot_precision@5
|
|
|
value: 0.14400000000000002
|
|
|
name: Dot Precision@5
|
|
|
- type: dot_precision@10
|
|
|
value: 0.08999999999999998
|
|
|
name: Dot Precision@10
|
|
|
- type: dot_recall@1
|
|
|
value: 0.42
|
|
|
name: Dot Recall@1
|
|
|
- type: dot_recall@3
|
|
|
value: 0.56
|
|
|
name: Dot Recall@3
|
|
|
- type: dot_recall@5
|
|
|
value: 0.72
|
|
|
name: Dot Recall@5
|
|
|
- type: dot_recall@10
|
|
|
value: 0.9
|
|
|
name: Dot Recall@10
|
|
|
- type: dot_ndcg@10
|
|
|
value: 0.6291399713464962
|
|
|
name: Dot Ndcg@10
|
|
|
- type: dot_mrr@10
|
|
|
value: 0.5467460317460318
|
|
|
name: Dot Mrr@10
|
|
|
- type: dot_map@100
|
|
|
value: 0.5503396478777393
|
|
|
name: Dot Map@100
|
|
|
- type: query_active_dims
|
|
|
value: 23.31999969482422
|
|
|
name: Query Active Dims
|
|
|
- type: query_sparsity_ratio
|
|
|
value: 0.9992359609562013
|
|
|
name: Query Sparsity Ratio
|
|
|
- type: corpus_active_dims
|
|
|
value: 257.3004150390625
|
|
|
name: Corpus Active Dims
|
|
|
- type: corpus_sparsity_ratio
|
|
|
value: 0.9915700014730665
|
|
|
name: Corpus Sparsity Ratio
|
|
|
- task:
|
|
|
type: sparse-information-retrieval
|
|
|
name: Sparse Information Retrieval
|
|
|
dataset:
|
|
|
name: NanoNFCorpus
|
|
|
type: NanoNFCorpus
|
|
|
metrics:
|
|
|
- type: dot_accuracy@1
|
|
|
value: 0.44
|
|
|
name: Dot Accuracy@1
|
|
|
- type: dot_accuracy@3
|
|
|
value: 0.56
|
|
|
name: Dot Accuracy@3
|
|
|
- type: dot_accuracy@5
|
|
|
value: 0.6
|
|
|
name: Dot Accuracy@5
|
|
|
- type: dot_accuracy@10
|
|
|
value: 0.66
|
|
|
name: Dot Accuracy@10
|
|
|
- type: dot_precision@1
|
|
|
value: 0.44
|
|
|
name: Dot Precision@1
|
|
|
- type: dot_precision@3
|
|
|
value: 0.38666666666666666
|
|
|
name: Dot Precision@3
|
|
|
- type: dot_precision@5
|
|
|
value: 0.32800000000000007
|
|
|
name: Dot Precision@5
|
|
|
- type: dot_precision@10
|
|
|
value: 0.272
|
|
|
name: Dot Precision@10
|
|
|
- type: dot_recall@1
|
|
|
value: 0.041590314149379026
|
|
|
name: Dot Recall@1
|
|
|
- type: dot_recall@3
|
|
|
value: 0.07672442108786207
|
|
|
name: Dot Recall@3
|
|
|
- type: dot_recall@5
|
|
|
value: 0.09154300468916865
|
|
|
name: Dot Recall@5
|
|
|
- type: dot_recall@10
|
|
|
value: 0.1433130618338512
|
|
|
name: Dot Recall@10
|
|
|
- type: dot_ndcg@10
|
|
|
value: 0.33898990155781883
|
|
|
name: Dot Ndcg@10
|
|
|
- type: dot_mrr@10
|
|
|
value: 0.5123809523809524
|
|
|
name: Dot Mrr@10
|
|
|
- type: dot_map@100
|
|
|
value: 0.1505453583653259
|
|
|
name: Dot Map@100
|
|
|
- type: query_active_dims
|
|
|
value: 21.260000228881836
|
|
|
name: Query Active Dims
|
|
|
- type: query_sparsity_ratio
|
|
|
value: 0.9993034532393394
|
|
|
name: Query Sparsity Ratio
|
|
|
- type: corpus_active_dims
|
|
|
value: 494.8533630371094
|
|
|
name: Corpus Active Dims
|
|
|
- type: corpus_sparsity_ratio
|
|
|
value: 0.9837869941996883
|
|
|
name: Corpus Sparsity Ratio
|
|
|
- task:
|
|
|
type: sparse-information-retrieval
|
|
|
name: Sparse Information Retrieval
|
|
|
dataset:
|
|
|
name: NanoNQ
|
|
|
type: NanoNQ
|
|
|
metrics:
|
|
|
- type: dot_accuracy@1
|
|
|
value: 0.44
|
|
|
name: Dot Accuracy@1
|
|
|
- type: dot_accuracy@3
|
|
|
value: 0.74
|
|
|
name: Dot Accuracy@3
|
|
|
- type: dot_accuracy@5
|
|
|
value: 0.78
|
|
|
name: Dot Accuracy@5
|
|
|
- type: dot_accuracy@10
|
|
|
value: 0.84
|
|
|
name: Dot Accuracy@10
|
|
|
- type: dot_precision@1
|
|
|
value: 0.44
|
|
|
name: Dot Precision@1
|
|
|
- type: dot_precision@3
|
|
|
value: 0.2533333333333333
|
|
|
name: Dot Precision@3
|
|
|
- type: dot_precision@5
|
|
|
value: 0.16399999999999998
|
|
|
name: Dot Precision@5
|
|
|
- type: dot_precision@10
|
|
|
value: 0.08999999999999998
|
|
|
name: Dot Precision@10
|
|
|
- type: dot_recall@1
|
|
|
value: 0.42
|
|
|
name: Dot Recall@1
|
|
|
- type: dot_recall@3
|
|
|
value: 0.7
|
|
|
name: Dot Recall@3
|
|
|
- type: dot_recall@5
|
|
|
value: 0.74
|
|
|
name: Dot Recall@5
|
|
|
- type: dot_recall@10
|
|
|
value: 0.81
|
|
|
name: Dot Recall@10
|
|
|
- type: dot_ndcg@10
|
|
|
value: 0.6304630848492498
|
|
|
name: Dot Ndcg@10
|
|
|
- type: dot_mrr@10
|
|
|
value: 0.5837460317460317
|
|
|
name: Dot Mrr@10
|
|
|
- type: dot_map@100
|
|
|
value: 0.5712846533262134
|
|
|
name: Dot Map@100
|
|
|
- type: query_active_dims
|
|
|
value: 28.0
|
|
|
name: Query Active Dims
|
|
|
- type: query_sparsity_ratio
|
|
|
value: 0.9990826289233995
|
|
|
name: Query Sparsity Ratio
|
|
|
- type: corpus_active_dims
|
|
|
value: 290.61212158203125
|
|
|
name: Corpus Active Dims
|
|
|
- type: corpus_sparsity_ratio
|
|
|
value: 0.9904786016125408
|
|
|
name: Corpus Sparsity Ratio
|
|
|
- task:
|
|
|
type: sparse-nano-beir
|
|
|
name: Sparse Nano BEIR
|
|
|
dataset:
|
|
|
name: NanoBEIR mean
|
|
|
type: NanoBEIR_mean
|
|
|
metrics:
|
|
|
- type: dot_accuracy@1
|
|
|
value: 0.43333333333333335
|
|
|
name: Dot Accuracy@1
|
|
|
- type: dot_accuracy@3
|
|
|
value: 0.62
|
|
|
name: Dot Accuracy@3
|
|
|
- type: dot_accuracy@5
|
|
|
value: 0.6999999999999998
|
|
|
name: Dot Accuracy@5
|
|
|
- type: dot_accuracy@10
|
|
|
value: 0.7999999999999999
|
|
|
name: Dot Accuracy@10
|
|
|
- type: dot_precision@1
|
|
|
value: 0.43333333333333335
|
|
|
name: Dot Precision@1
|
|
|
- type: dot_precision@3
|
|
|
value: 0.27555555555555555
|
|
|
name: Dot Precision@3
|
|
|
- type: dot_precision@5
|
|
|
value: 0.21200000000000005
|
|
|
name: Dot Precision@5
|
|
|
- type: dot_precision@10
|
|
|
value: 0.15066666666666664
|
|
|
name: Dot Precision@10
|
|
|
- type: dot_recall@1
|
|
|
value: 0.29386343804979304
|
|
|
name: Dot Recall@1
|
|
|
- type: dot_recall@3
|
|
|
value: 0.44557480702928737
|
|
|
name: Dot Recall@3
|
|
|
- type: dot_recall@5
|
|
|
value: 0.5171810015630562
|
|
|
name: Dot Recall@5
|
|
|
- type: dot_recall@10
|
|
|
value: 0.6177710206112837
|
|
|
name: Dot Recall@10
|
|
|
- type: dot_ndcg@10
|
|
|
value: 0.5328643192511883
|
|
|
name: Dot Ndcg@10
|
|
|
- type: dot_mrr@10
|
|
|
value: 0.5476243386243386
|
|
|
name: Dot Mrr@10
|
|
|
- type: dot_map@100
|
|
|
value: 0.42405655318975954
|
|
|
name: Dot Map@100
|
|
|
- type: query_active_dims
|
|
|
value: 24.19333330790202
|
|
|
name: Query Active Dims
|
|
|
- type: query_sparsity_ratio
|
|
|
value: 0.9992073477063135
|
|
|
name: Query Sparsity Ratio
|
|
|
- type: corpus_active_dims
|
|
|
value: 324.00429792464917
|
|
|
name: Corpus Active Dims
|
|
|
- type: corpus_sparsity_ratio
|
|
|
value: 0.9893845652996315
|
|
|
name: Corpus Sparsity Ratio
|
|
|
---
|
|
|
|
|
|
# CoCondenser finetuned on MS MARCO
|
|
|
|
|
|
This is a [SPLADE Sparse Encoder](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) model finetuned from [Luyu/co-condenser-marco](https://huggingface.co/Luyu/co-condenser-marco) using the [sentence-transformers](https://www.SBERT.net) library. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval.
|
|
|
## Model Details
|
|
|
|
|
|
### Model Description
|
|
|
- **Model Type:** SPLADE Sparse Encoder
|
|
|
- **Base model:** [Luyu/co-condenser-marco](https://huggingface.co/Luyu/co-condenser-marco) <!-- at revision e0cef0ab2410aae0f0994366ddefb5649a266709 -->
|
|
|
- **Maximum Sequence Length:** 512 tokens
|
|
|
- **Output Dimensionality:** 30522 dimensions
|
|
|
- **Similarity Function:** Dot Product
|
|
|
<!-- - **Training Dataset:** Unknown -->
|
|
|
- **Language:** en
|
|
|
- **License:** apache-2.0
|
|
|
|
|
|
### Model Sources
|
|
|
|
|
|
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
|
|
- **Documentation:** [Sparse Encoder Documentation](https://www.sbert.net/docs/sparse_encoder/usage/usage.html)
|
|
|
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
|
|
- **Hugging Face:** [Sparse Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=sparse-encoder)
|
|
|
|
|
|
### Full Model Architecture
|
|
|
|
|
|
```
|
|
|
SparseEncoder(
|
|
|
(0): MLMTransformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertForMaskedLM'})
|
|
|
(1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522})
|
|
|
)
|
|
|
```
|
|
|
|
|
|
## 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 SparseEncoder
|
|
|
|
|
|
# Download from the 🤗 Hub
|
|
|
model = SparseEncoder("tomaarsen/splade-cocondenser-kldiv-marginmse-minilm-temp-4")
|
|
|
# Run inference
|
|
|
queries = [
|
|
|
"who started gladiator lacrosse",
|
|
|
]
|
|
|
documents = [
|
|
|
'Weed Eater was a string trimmer company founded in 1971 in Houston, Texas by George C. Ballas, Sr. , the inventor of the device. The idea for the Weed Eater trimmer came to him from the spinning nylon bristles of an automatic car wash.He thought that he could come up with a similar technique to protect the bark on trees that he was trimming around. His company was eventually bought by Emerson Electric and merged with Poulan.Poulan/Weed Eater was later purchased by Electrolux, which spun off the outdoors division as Husqvarna AB in 2006.Inventor Ballas was the father of champion ballroom dancer Corky Ballas and the grandfather of Dancing with the Stars dancer Mark Ballas.George Ballas died on June 25, 2011.he idea for the Weed Eater trimmer came to him from the spinning nylon bristles of an automatic car wash. He thought that he could come up with a similar technique to protect the bark on trees that he was trimming around. His company was eventually bought by Emerson Electric and merged with Poulan.',
|
|
|
"The earliest types of gladiator were named after Rome's enemies of that time: the Samnite, Thracian and Gaul. The Samnite, heavily armed, elegantly helmed and probably the most popular type, was renamed Secutor and the Gaul renamed Murmillo, once these former enemies had been conquered then absorbed into Rome's Empire.",
|
|
|
'Summit Hill, PA. Sponsored Topics. Summit Hill is a borough in Carbon County, Pennsylvania, United States. The population was 2,974 at the 2000 census. Summit Hill is located at 40°49â\x80²39â\x80³N 75°51â\x80²57â\x80³W / 40.8275°N 75.86583°W / 40.8275; -75.86583 (40.827420, -75.865892).',
|
|
|
]
|
|
|
query_embeddings = model.encode_query(queries)
|
|
|
document_embeddings = model.encode_document(documents)
|
|
|
print(query_embeddings.shape, document_embeddings.shape)
|
|
|
# [1, 30522] [3, 30522]
|
|
|
|
|
|
# Get the similarity scores for the embeddings
|
|
|
similarities = model.similarity(query_embeddings, document_embeddings)
|
|
|
print(similarities)
|
|
|
# tensor([[19.3181, 29.9645, 13.8348]])
|
|
|
```
|
|
|
|
|
|
<!--
|
|
|
### 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
|
|
|
|
|
|
#### Sparse Information Retrieval
|
|
|
|
|
|
* Datasets: `NanoMSMARCO`, `NanoNFCorpus` and `NanoNQ`
|
|
|
* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator)
|
|
|
|
|
|
| Metric | NanoMSMARCO | NanoNFCorpus | NanoNQ |
|
|
|
|:----------------------|:------------|:-------------|:-----------|
|
|
|
| dot_accuracy@1 | 0.42 | 0.44 | 0.44 |
|
|
|
| dot_accuracy@3 | 0.56 | 0.56 | 0.74 |
|
|
|
| dot_accuracy@5 | 0.72 | 0.6 | 0.78 |
|
|
|
| dot_accuracy@10 | 0.9 | 0.66 | 0.84 |
|
|
|
| dot_precision@1 | 0.42 | 0.44 | 0.44 |
|
|
|
| dot_precision@3 | 0.1867 | 0.3867 | 0.2533 |
|
|
|
| dot_precision@5 | 0.144 | 0.328 | 0.164 |
|
|
|
| dot_precision@10 | 0.09 | 0.272 | 0.09 |
|
|
|
| dot_recall@1 | 0.42 | 0.0416 | 0.42 |
|
|
|
| dot_recall@3 | 0.56 | 0.0767 | 0.7 |
|
|
|
| dot_recall@5 | 0.72 | 0.0915 | 0.74 |
|
|
|
| dot_recall@10 | 0.9 | 0.1433 | 0.81 |
|
|
|
| **dot_ndcg@10** | **0.6291** | **0.339** | **0.6305** |
|
|
|
| dot_mrr@10 | 0.5467 | 0.5124 | 0.5837 |
|
|
|
| dot_map@100 | 0.5503 | 0.1505 | 0.5713 |
|
|
|
| query_active_dims | 23.32 | 21.26 | 28.0 |
|
|
|
| query_sparsity_ratio | 0.9992 | 0.9993 | 0.9991 |
|
|
|
| corpus_active_dims | 257.3004 | 494.8534 | 290.6121 |
|
|
|
| corpus_sparsity_ratio | 0.9916 | 0.9838 | 0.9905 |
|
|
|
|
|
|
#### Sparse Nano BEIR
|
|
|
|
|
|
* Dataset: `NanoBEIR_mean`
|
|
|
* Evaluated with [<code>SparseNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters:
|
|
|
```json
|
|
|
{
|
|
|
"dataset_names": [
|
|
|
"msmarco",
|
|
|
"nfcorpus",
|
|
|
"nq"
|
|
|
]
|
|
|
}
|
|
|
```
|
|
|
|
|
|
| Metric | Value |
|
|
|
|:----------------------|:-----------|
|
|
|
| dot_accuracy@1 | 0.4333 |
|
|
|
| dot_accuracy@3 | 0.62 |
|
|
|
| dot_accuracy@5 | 0.7 |
|
|
|
| dot_accuracy@10 | 0.8 |
|
|
|
| dot_precision@1 | 0.4333 |
|
|
|
| dot_precision@3 | 0.2756 |
|
|
|
| dot_precision@5 | 0.212 |
|
|
|
| dot_precision@10 | 0.1507 |
|
|
|
| dot_recall@1 | 0.2939 |
|
|
|
| dot_recall@3 | 0.4456 |
|
|
|
| dot_recall@5 | 0.5172 |
|
|
|
| dot_recall@10 | 0.6178 |
|
|
|
| **dot_ndcg@10** | **0.5329** |
|
|
|
| dot_mrr@10 | 0.5476 |
|
|
|
| dot_map@100 | 0.4241 |
|
|
|
| query_active_dims | 24.1933 |
|
|
|
| query_sparsity_ratio | 0.9992 |
|
|
|
| corpus_active_dims | 324.0043 |
|
|
|
| corpus_sparsity_ratio | 0.9894 |
|
|
|
|
|
|
<!--
|
|
|
## 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: 99,000 training samples
|
|
|
* Columns: <code>query</code>, <code>positive</code>, <code>negative</code>, and <code>label</code>
|
|
|
* Approximate statistics based on the first 1000 samples:
|
|
|
| | query | positive | negative | label |
|
|
|
|:--------|:--------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------|
|
|
|
| type | string | string | string | list |
|
|
|
| details | <ul><li>min: 4 tokens</li><li>mean: 9.2 tokens</li><li>max: 34 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 79.86 tokens</li><li>max: 219 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 79.96 tokens</li><li>max: 270 tokens</li></ul> | <ul><li>size: 2 elements</li></ul> |
|
|
|
* Samples:
|
|
|
| query | positive | negative | label |
|
|
|
|:---------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------|
|
|
|
| <code>rtn tv network</code> | <code>Home Shopping Network. Home Shopping Network (HSN) is an American broadcast, basic cable and satellite television network that is owned by HSN, Inc. (NASDAQ: HSNI), which also owns catalog company Cornerstone Brands. Based in St. Petersburg, Florida, United States, the home shopping channel has former and current sister channels in several other countries.</code> | <code>The Public Switched Telephone Network - The public switched telephone network (PSTN) is the international network of circuit-switched telephones. Learn more about PSTN at HowStuffWorks. x</code> | <code>[-1.0804121494293213, -5.908488750457764]</code> |
|
|
|
| <code>how did president nixon react to the watergate investigation?</code> | <code>The Watergate scandal was a major political scandal that occurred in the United States during the early 1970s, following a break-in by five men at the Democratic National Committee headquarters at the Watergate office complex in Washington, D.C. on June 17, 1972, and President Richard Nixon's administration's subsequent attempt to cover up its involvement. After the five burglars were caught and the conspiracy was discovered, Watergate was investigated by the United States Congress. Meanwhile, N</code> | <code>The release of the tape was ordered by the Supreme Court on July 24, 1974, in a case known as United States v. Nixon. The courtâs decision was unanimous. President Nixon released the tape on August 5. It was one of three conversations he had with Haldeman six days after the Watergate break-in. The tapes prove that he ordered a cover-up of the Watergate burglary. The Smoking Gun tape reveals that Nixon ordered the FBI to abandon its investigation of the break-in. [Read moreâ¦]</code> | <code>[4.117279052734375, 3.191757917404175]</code> |
|
|
|
| <code>what is a summary offense in pennsylvania</code> | <code>We provide cost effective house arrest and electronic monitoring services to magisterial district court systems throughout Pennsylvania including York, Harrisburg, Philadelphia and Allentown.In addition, we also serve the York County, Lancaster County and Chester County.e provide cost effective house arrest and electronic monitoring services to magisterial district court systems throughout Pennsylvania including York, Harrisburg, Philadelphia and Allentown.</code> | <code>In order to be convicted of Simple Assault, one must cause bodily injury. To be convicted of Aggravated Assault, one must cause serious bodily injury. From my research, Pennsylvania law defines bodily injury as the impairment of physical condition or substantial pain.</code> | <code>[-8.954689025878906, -1.3361705541610718]</code> |
|
|
|
* Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#spladeloss) with these parameters:
|
|
|
```json
|
|
|
{
|
|
|
"loss": "SparseDistillKLDivLoss",
|
|
|
"lambda_corpus": 0.0005,
|
|
|
"lambda_query": 0.0005
|
|
|
}
|
|
|
```
|
|
|
|
|
|
### Evaluation Dataset
|
|
|
|
|
|
#### Unnamed Dataset
|
|
|
|
|
|
* Size: 1,000 evaluation samples
|
|
|
* Columns: <code>query</code>, <code>positive</code>, <code>negative</code>, and <code>label</code>
|
|
|
* Approximate statistics based on the first 1000 samples:
|
|
|
| | query | positive | negative | label |
|
|
|
|:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------|
|
|
|
| type | string | string | string | list |
|
|
|
| details | <ul><li>min: 4 tokens</li><li>mean: 9.12 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 78.91 tokens</li><li>max: 239 tokens</li></ul> | <ul><li>min: 25 tokens</li><li>mean: 81.25 tokens</li><li>max: 239 tokens</li></ul> | <ul><li>size: 2 elements</li></ul> |
|
|
|
* Samples:
|
|
|
| query | positive | negative | label |
|
|
|
|:-----------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------|
|
|
|
| <code>how long to cook roast beef for</code> | <code>Roasting times for beef. Preheat your oven to 160°C (325°F) and use these cooking times to prepare a roast that's moist, tender and delicious. Your roast should be covered with foil for the first half of the roasting time to prevent drying the outer layer.3 to 5lb Joint 1½ to 2 hours.reheat your oven to 160°C (325°F) and use these cooking times to prepare a roast that's moist, tender and delicious. Your roast should be covered with foil for the first half of the roasting time to prevent drying the outer layer.</code> | <code>Estimating Cooking Time for Large Beef Roasts. If you roast at a steady 325F (160C), subtract 2 minutes or so per pound. If the roast is refrigerated just before going into the oven, add 2 or 3 minutes per pound. WARNING NOTES: Remember, the rib roast will continue to cook as it sets.</code> | <code>[6.501978874206543, 8.214995384216309]</code> |
|
|
|
| <code>definition of fire inspection</code> | <code>Learn how to do a monthly fire extinguisher inspection in your workplace. Departments must assign an individual to inspect monthly the extinguishers in or adjacent to the department's facilities.1 Read Fire Extinguisher Types and Maintenance for more information.earn how to do a monthly fire extinguisher inspection in your workplace. Departments must assign an individual to inspect monthly the extinguishers in or adjacent to the department's facilities.</code> | <code>reconnaissance by fire-a method of reconnaissance in which fire is placed on a suspected enemy position in order to cause the enemy to disclose his presence by moving or returning fire. reconnaissance in force-an offensive operation designed to discover or test the enemy's strength (or to obtain other information). mission undertaken to obtain, by visual observation or other detection methods, information about the activities and resources of an enemy or potential enemy, or to secure data concerning the meteorological, hydrographic, or geographic characteristics of a particular area.</code> | <code>[-0.38299351930618286, -0.9372650384902954]</code> |
|
|
|
| <code>how many stores does family dollar have</code> | <code>Property Spotlight: New Retail Center at Hamilton & Warner - Outlots Available!! Family Dollar is closing stores following a disappointing second quarter. Family Dollar Stores Inc. wonât just be cutting prices in an attempt to boost its business â itâll be closing stores as well. The Matthews, N.C.-based discount retailer plans to shutter 370 under-performing shops, according to the Charlotte Business Journal.</code> | <code>Glassdoor has 1,976 Family Dollar Stores reviews submitted anonymously by Family Dollar Stores employees. Read employee reviews and ratings on Glassdoor to decide if Family Dollar Stores is right for you.</code> | <code>[4.726407527923584, 8.284608840942383]</code> |
|
|
|
* Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#spladeloss) with these parameters:
|
|
|
```json
|
|
|
{
|
|
|
"loss": "SparseDistillKLDivLoss",
|
|
|
"lambda_corpus": 0.0005,
|
|
|
"lambda_query": 0.0005
|
|
|
}
|
|
|
```
|
|
|
|
|
|
### Training Hyperparameters
|
|
|
#### Non-Default Hyperparameters
|
|
|
|
|
|
- `eval_strategy`: steps
|
|
|
- `per_device_train_batch_size`: 16
|
|
|
- `per_device_eval_batch_size`: 16
|
|
|
- `learning_rate`: 2e-05
|
|
|
- `num_train_epochs`: 1
|
|
|
- `warmup_ratio`: 0.1
|
|
|
- `fp16`: True
|
|
|
- `batch_sampler`: no_duplicates
|
|
|
|
|
|
#### 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`: 16
|
|
|
- `per_device_eval_batch_size`: 16
|
|
|
- `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`: 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`: 1
|
|
|
- `max_steps`: -1
|
|
|
- `lr_scheduler_type`: linear
|
|
|
- `lr_scheduler_kwargs`: {}
|
|
|
- `warmup_ratio`: 0.1
|
|
|
- `warmup_steps`: 0
|
|
|
- `log_level`: passive
|
|
|
- `log_level_replica`: warning
|
|
|
- `log_on_each_node`: True
|
|
|
- `logging_nan_inf_filter`: True
|
|
|
- `save_safetensors`: True
|
|
|
- `save_on_each_node`: False
|
|
|
- `save_only_model`: False
|
|
|
- `restore_callback_states_from_checkpoint`: False
|
|
|
- `no_cuda`: False
|
|
|
- `use_cpu`: False
|
|
|
- `use_mps_device`: False
|
|
|
- `seed`: 42
|
|
|
- `data_seed`: None
|
|
|
- `jit_mode_eval`: False
|
|
|
- `use_ipex`: False
|
|
|
- `bf16`: False
|
|
|
- `fp16`: True
|
|
|
- `fp16_opt_level`: O1
|
|
|
- `half_precision_backend`: auto
|
|
|
- `bf16_full_eval`: False
|
|
|
- `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`: False
|
|
|
- `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
|
|
|
- `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
|
|
|
- `eval_use_gather_object`: False
|
|
|
- `average_tokens_across_devices`: False
|
|
|
- `prompts`: None
|
|
|
- `batch_sampler`: no_duplicates
|
|
|
- `multi_dataset_batch_sampler`: proportional
|
|
|
- `router_mapping`: {}
|
|
|
- `learning_rate_mapping`: {}
|
|
|
|
|
|
</details>
|
|
|
|
|
|
### Training Logs
|
|
|
| Epoch | Step | Training Loss | Validation Loss | NanoMSMARCO_dot_ndcg@10 | NanoNFCorpus_dot_ndcg@10 | NanoNQ_dot_ndcg@10 | NanoBEIR_mean_dot_ndcg@10 |
|
|
|
|:------:|:----:|:-------------:|:---------------:|:-----------------------:|:------------------------:|:------------------:|:-------------------------:|
|
|
|
| -1 | -1 | - | - | 0.0823 | 0.0412 | 0.0621 | 0.0619 |
|
|
|
| 0.0162 | 100 | 740.8226 | - | - | - | - | - |
|
|
|
| 0.0323 | 200 | 82.2666 | - | - | - | - | - |
|
|
|
| 0.0485 | 300 | 3.3514 | - | - | - | - | - |
|
|
|
| 0.0646 | 400 | 1.9689 | - | - | - | - | - |
|
|
|
| 0.0808 | 500 | 1.8268 | 1.8327 | 0.1979 | 0.1096 | 0.2507 | 0.1861 |
|
|
|
| 0.0970 | 600 | 1.8 | - | - | - | - | - |
|
|
|
| 0.1131 | 700 | 1.613 | - | - | - | - | - |
|
|
|
| 0.1293 | 800 | 1.5977 | - | - | - | - | - |
|
|
|
| 0.1454 | 900 | 1.5886 | - | - | - | - | - |
|
|
|
| 0.1616 | 1000 | 1.3922 | 1.2983 | 0.5044 | 0.2715 | 0.5851 | 0.4537 |
|
|
|
| 0.1778 | 1100 | 1.3708 | - | - | - | - | - |
|
|
|
| 0.1939 | 1200 | 1.383 | - | - | - | - | - |
|
|
|
| 0.2101 | 1300 | 1.2148 | - | - | - | - | - |
|
|
|
| 0.2262 | 1400 | 1.246 | - | - | - | - | - |
|
|
|
| 0.2424 | 1500 | 1.2206 | 1.0998 | 0.5329 | 0.2969 | 0.5945 | 0.4748 |
|
|
|
| 0.2586 | 1600 | 1.1962 | - | - | - | - | - |
|
|
|
| 0.2747 | 1700 | 1.1546 | - | - | - | - | - |
|
|
|
| 0.2909 | 1800 | 1.1319 | - | - | - | - | - |
|
|
|
| 0.3070 | 1900 | 1.1656 | - | - | - | - | - |
|
|
|
| 0.3232 | 2000 | 1.1196 | 0.9878 | 0.5667 | 0.3283 | 0.6106 | 0.5019 |
|
|
|
| 0.3394 | 2100 | 1.0789 | - | - | - | - | - |
|
|
|
| 0.3555 | 2200 | 1.0148 | - | - | - | - | - |
|
|
|
| 0.3717 | 2300 | 1.042 | - | - | - | - | - |
|
|
|
| 0.3878 | 2400 | 1.0274 | - | - | - | - | - |
|
|
|
| 0.4040 | 2500 | 1.0041 | 0.8749 | 0.6059 | 0.3346 | 0.5942 | 0.5116 |
|
|
|
| 0.4202 | 2600 | 1.0557 | - | - | - | - | - |
|
|
|
| 0.4363 | 2700 | 1.0077 | - | - | - | - | - |
|
|
|
| 0.4525 | 2800 | 1.0115 | - | - | - | - | - |
|
|
|
| 0.4686 | 2900 | 0.8708 | - | - | - | - | - |
|
|
|
| 0.4848 | 3000 | 0.8838 | 0.9321 | 0.5826 | 0.3264 | 0.6354 | 0.5148 |
|
|
|
| 0.5010 | 3100 | 0.9103 | - | - | - | - | - |
|
|
|
| 0.5171 | 3200 | 0.8586 | - | - | - | - | - |
|
|
|
| 0.5333 | 3300 | 0.9286 | - | - | - | - | - |
|
|
|
| 0.5495 | 3400 | 0.8645 | - | - | - | - | - |
|
|
|
| 0.5656 | 3500 | 0.9522 | 0.8105 | 0.6164 | 0.3378 | 0.6131 | 0.5224 |
|
|
|
| 0.5818 | 3600 | 0.8636 | - | - | - | - | - |
|
|
|
| 0.5979 | 3700 | 0.8634 | - | - | - | - | - |
|
|
|
| 0.6141 | 3800 | 0.8555 | - | - | - | - | - |
|
|
|
| 0.6303 | 3900 | 0.8447 | - | - | - | - | - |
|
|
|
| 0.6464 | 4000 | 0.8331 | 0.7699 | 0.6033 | 0.3442 | 0.6016 | 0.5164 |
|
|
|
| 0.6626 | 4100 | 0.8292 | - | - | - | - | - |
|
|
|
| 0.6787 | 4200 | 0.8273 | - | - | - | - | - |
|
|
|
| 0.6949 | 4300 | 0.8381 | - | - | - | - | - |
|
|
|
| 0.7111 | 4400 | 0.8035 | - | - | - | - | - |
|
|
|
| 0.7272 | 4500 | 0.8166 | 0.7743 | 0.6018 | 0.3394 | 0.6060 | 0.5157 |
|
|
|
| 0.7434 | 4600 | 0.8245 | - | - | - | - | - |
|
|
|
| 0.7595 | 4700 | 0.7831 | - | - | - | - | - |
|
|
|
| 0.7757 | 4800 | 0.8314 | - | - | - | - | - |
|
|
|
| 0.7919 | 4900 | 0.7994 | - | - | - | - | - |
|
|
|
| 0.8080 | 5000 | 0.8018 | 0.7058 | 0.6236 | 0.3413 | 0.6378 | 0.5342 |
|
|
|
| 0.8242 | 5100 | 0.7652 | - | - | - | - | - |
|
|
|
| 0.8403 | 5200 | 0.7458 | - | - | - | - | - |
|
|
|
| 0.8565 | 5300 | 0.8158 | - | - | - | - | - |
|
|
|
| 0.8727 | 5400 | 0.7887 | - | - | - | - | - |
|
|
|
| 0.8888 | 5500 | 0.7372 | 0.7389 | 0.6251 | 0.3476 | 0.6327 | 0.5351 |
|
|
|
| 0.9050 | 5600 | 0.8 | - | - | - | - | - |
|
|
|
| 0.9211 | 5700 | 0.7724 | - | - | - | - | - |
|
|
|
| 0.9373 | 5800 | 0.7578 | - | - | - | - | - |
|
|
|
| 0.9535 | 5900 | 0.7536 | - | - | - | - | - |
|
|
|
| 0.9696 | 6000 | 0.7982 | 0.7011 | 0.6289 | 0.3396 | 0.6308 | 0.5331 |
|
|
|
| 0.9858 | 6100 | 0.8084 | - | - | - | - | - |
|
|
|
| -1 | -1 | - | - | 0.6291 | 0.3390 | 0.6305 | 0.5329 |
|
|
|
|
|
|
|
|
|
### Environmental Impact
|
|
|
Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
|
|
|
- **Energy Consumed**: 0.201 kWh
|
|
|
- **Carbon Emitted**: 0.078 kg of CO2
|
|
|
- **Hours Used**: 0.571 hours
|
|
|
|
|
|
### Training Hardware
|
|
|
- **On Cloud**: No
|
|
|
- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
|
|
|
- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
|
|
|
- **RAM Size**: 31.78 GB
|
|
|
|
|
|
### Framework Versions
|
|
|
- Python: 3.11.6
|
|
|
- Sentence Transformers: 4.2.0.dev0
|
|
|
- Transformers: 4.52.4
|
|
|
- PyTorch: 2.7.1+cu126
|
|
|
- Accelerate: 1.5.1
|
|
|
- Datasets: 2.21.0
|
|
|
- Tokenizers: 0.21.1
|
|
|
|
|
|
## 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",
|
|
|
}
|
|
|
```
|
|
|
|
|
|
#### SpladeLoss
|
|
|
```bibtex
|
|
|
@misc{formal2022distillationhardnegativesampling,
|
|
|
title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective},
|
|
|
author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant},
|
|
|
year={2022},
|
|
|
eprint={2205.04733},
|
|
|
archivePrefix={arXiv},
|
|
|
primaryClass={cs.IR},
|
|
|
url={https://arxiv.org/abs/2205.04733},
|
|
|
}
|
|
|
```
|
|
|
|
|
|
#### SparseDistillKLDivLoss
|
|
|
```bibtex
|
|
|
@misc{lin2020distillingdenserepresentationsranking,
|
|
|
title={Distilling Dense Representations for Ranking using Tightly-Coupled Teachers},
|
|
|
author={Sheng-Chieh Lin and Jheng-Hong Yang and Jimmy Lin},
|
|
|
year={2020},
|
|
|
eprint={2010.11386},
|
|
|
archivePrefix={arXiv},
|
|
|
primaryClass={cs.IR},
|
|
|
url={https://arxiv.org/abs/2010.11386},
|
|
|
}
|
|
|
```
|
|
|
|
|
|
#### FlopsLoss
|
|
|
```bibtex
|
|
|
@article{paria2020minimizing,
|
|
|
title={Minimizing flops to learn efficient sparse representations},
|
|
|
author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s},
|
|
|
journal={arXiv preprint arXiv:2004.05665},
|
|
|
year={2020}
|
|
|
}
|
|
|
```
|
|
|
|
|
|
<!--
|
|
|
## 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.*
|
|
|
--> |
